CN119467406A - Energy-saving fan for inflatable model and control method thereof - Google Patents
Energy-saving fan for inflatable model and control method thereof Download PDFInfo
- Publication number
- CN119467406A CN119467406A CN202411854045.5A CN202411854045A CN119467406A CN 119467406 A CN119467406 A CN 119467406A CN 202411854045 A CN202411854045 A CN 202411854045A CN 119467406 A CN119467406 A CN 119467406A
- Authority
- CN
- China
- Prior art keywords
- wind speed
- time sequence
- internal pressure
- vector
- external wind
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F04—POSITIVE - DISPLACEMENT MACHINES FOR LIQUIDS; PUMPS FOR LIQUIDS OR ELASTIC FLUIDS
- F04D—NON-POSITIVE-DISPLACEMENT PUMPS
- F04D27/00—Control, e.g. regulation, of pumps, pumping installations or pumping systems specially adapted for elastic fluids
Landscapes
- Engineering & Computer Science (AREA)
- Mechanical Engineering (AREA)
- General Engineering & Computer Science (AREA)
- Feedback Control In General (AREA)
Abstract
本申请涉及智能风机控制技术领域，其具体地公开了一种应用于充气模型的节能风机及其控制方法，其采用传感技术对充气模型的外部风速和内部压力进行持续监控，并利用基于深度学习的人工智能技术对外部风速和内部压力数据进行时序分析，以捕捉到外部风速和内部压力的时序变化模式，进而，通过对两者进行时序响应分析，以挖掘出外部环境风速对充气模型内部压力的关联影响，从而结合充气模型的外部环境条件和内部压力状态对风机转速进行智能控制，以维持充气模型的稳定性。通过这种方式，可以有效降低能源消耗，同时确保充气模型在各种环境条件下的稳定性和安全性，从而提高充气模型的能效性。
The present application relates to the field of intelligent fan control technology, and specifically discloses an energy-saving fan and a control method thereof applied to an inflatable model, which uses sensing technology to continuously monitor the external wind speed and internal pressure of the inflatable model, and uses artificial intelligence technology based on deep learning to perform time series analysis on the external wind speed and internal pressure data to capture the time series change pattern of the external wind speed and internal pressure, and then, by performing time series response analysis on the two, the correlation effect of the external environmental wind speed on the internal pressure of the inflatable model is excavated, so as to intelligently control the fan speed in combination with the external environmental conditions and internal pressure state of the inflatable model to maintain the stability of the inflatable model. In this way, energy consumption can be effectively reduced, while ensuring the stability and safety of the inflatable model under various environmental conditions, thereby improving the energy efficiency of the inflatable model.
Description
Technical Field
The application relates to the technical field of intelligent fan control, in particular to an energy-saving fan applied to an inflation model and a control method thereof.
Background
The inflatable model, as a structural form widely applied to the fields of entertainment, advertising, exhibition, emergency rescue and the like, has stability and energy efficiency which are the focus of design and use. The shape and the volume of the model are maintained by continuously supplying air through the internal fan, so that good display effect or function realization can be ensured under various environments.
During operation of the inflatable model, external environmental factors, particularly changes in wind speed, have a direct and significant impact on the internal pressure state of the inflatable model. For example, in a strong wind environment, the external air flow directly acts on the surface of the model, which may cause the internal pressure to change sharply, and if the fan control system cannot respond quickly, the model may deform or even be damaged due to the excessive internal and external pressure difference. Conversely, overfeeding is also an unnecessary energy consumption in weak or windless conditions.
However, conventional fan control strategies mostly rely on simple sensor feedback, such as by monitoring the internal pressure of the inflatable model and comparing it to a set pressure threshold, to adjust the fan speed, which, although maintaining the basic form of the model to some extent, lacks adaptability to external environmental changes, which may not only lead to energy waste, but may also affect the structural stability and the service life of the inflatable model due to inability to adjust in time.
Therefore, an optimized energy-saving fan applied to an inflation model and a control method thereof are desired.
Disclosure of Invention
The present application has been made to solve the above-mentioned technical problems. The embodiment of the application provides an energy-saving fan applied to an inflation model and a control method thereof, wherein a sensing technology is adopted to continuously monitor the external wind speed and the internal pressure of the inflation model, an artificial intelligence technology based on deep learning is utilized to perform time sequence analysis on the external wind speed and the internal pressure data so as to capture the time sequence change mode of the external wind speed and the internal pressure, and furthermore, the time sequence response analysis is performed on the external wind speed and the internal pressure to extract the associated influence of the external environment wind speed on the internal pressure of the inflation model, so that the fan rotating speed is intelligently controlled by combining the external environment condition and the internal pressure state of the inflation model so as to maintain the stability of the inflation model. By the method, energy consumption can be effectively reduced, and meanwhile, stability and safety of the inflatable model under various environmental conditions are ensured, so that energy efficiency of the inflatable model is improved.
According to an aspect of the present application, there is provided a control method of an energy saving fan applied to an inflation model, comprising:
Acquiring a time sequence data set of real-time wind speed values through a wind speed sensor arranged outside the inflation model, and acquiring a time data set of internal pressure values through a pressure sensor arranged inside the inflation model;
transmitting the time sequence data set of the real-time wind speed value and the time data set of the internal pressure value to a fan central controller through a wireless transmission module;
the fan central controller extracts time sequence characteristics of the time sequence data set of the real-time wind speed value and the time data set of the internal pressure value to obtain an external wind speed time sequence implicit association characteristic vector and a model internal pressure time sequence implicit association characteristic vector;
the fan central controller performs time sequence response analysis based on inter-feature implicit association on the external wind speed time sequence implicit association characteristic vector and the model internal pressure time sequence implicit association characteristic vector to obtain an external wind speed-internal pressure time sequence response coding vector;
and the fan central controller is used for generating a control signal of the fan rotating speed based on the external wind speed-internal pressure time sequence response coding vector, and the control signal is used for controlling a variable frequency driver of the energy-saving fan.
According to another aspect of the present application, there is provided an energy saving fan applied to an inflation model, comprising:
The inflation model state monitoring module is used for acquiring a time sequence data set of real-time wind speed values through a wind speed sensor arranged outside the inflation model, and acquiring a time data set of internal pressure values through a pressure sensor arranged inside the inflation model;
the data transmission module is used for transmitting the time sequence data set of the real-time wind speed value and the time data set of the internal pressure value to the fan central controller through the wireless transmission module;
The data time sequence feature extraction module is used for extracting time sequence features of the time sequence data set of the real-time wind speed value and the time data set of the internal pressure value at the fan central controller to obtain an external wind speed time sequence implicit association feature vector and a model internal pressure time sequence implicit association feature vector;
The time sequence response analysis module is used for carrying out time sequence response analysis based on inter-feature implicit association on the external wind speed time sequence implicit association characteristic vector and the model internal pressure time sequence implicit association characteristic vector at the fan central controller so as to obtain an external wind speed-internal pressure time sequence response coding vector;
The control signal generation module is used for generating a control signal of the rotating speed of the fan based on the external wind speed-internal pressure time sequence response coding vector at the fan central controller, and the control signal is used for controlling a variable frequency driver of the energy-saving fan.
Compared with the prior art, the energy-saving fan applied to the inflation model and the control method thereof provided by the application have the advantages that the sensing technology is adopted to continuously monitor the external wind speed and the internal pressure of the inflation model, the artificial intelligence technology based on deep learning is utilized to perform time sequence analysis on the external wind speed and the internal pressure data so as to capture the time sequence change mode of the external wind speed and the internal pressure, and furthermore, the time sequence response analysis is performed on the external wind speed and the internal pressure to excavate the associated influence of the external environment wind speed on the internal pressure of the inflation model, so that the fan rotating speed is intelligently controlled by combining the external environment condition and the internal pressure state of the inflation model so as to maintain the stability of the inflation model. By the method, energy consumption can be effectively reduced, and meanwhile, stability and safety of the inflatable model under various environmental conditions are ensured, so that energy efficiency of the inflatable model is improved.
Drawings
The above and other objects, features and advantages of the present application will become more apparent by describing embodiments of the present application in more detail with reference to the attached drawings. The accompanying drawings are included to provide a further understanding of embodiments of the application and are incorporated in and constitute a part of this specification, illustrate the application and together with the embodiments of the application, and not constitute a limitation to the application. In the drawings, like reference numerals generally refer to like parts or steps.
Fig. 1 is a schematic view of an application scenario of a control method of an energy-saving fan applied to an inflation model according to an embodiment of the present application;
FIG. 2 is a flow chart of a method of controlling an energy-efficient blower applied to an inflatable model in accordance with an embodiment of the present application;
FIG. 3 is a data flow diagram of a control method of an energy-saving fan applied to an inflatable model according to an embodiment of the present application;
FIG. 4 is a flowchart of step S4 in a control method of an energy-saving fan applied to an inflation model according to an embodiment of the present application;
FIG. 5 is a block diagram of an energy efficient blower applied to an inflatable model in accordance with an embodiment of the present application;
In the figure, 1, an inflation model, 2, a pressure sensor, 3, a wind speed sensor, 4, a fan central controller, 5, a variable frequency driver and 6, an energy-saving fan.
Detailed Description
Hereinafter, exemplary embodiments according to the present application will be described in detail with reference to the accompanying drawings. It should be apparent that the described embodiments are only some embodiments of the present application and not all embodiments of the present application, and it should be understood that the present application is not limited by the example embodiments described herein.
Aiming at the technical problems in the background art, the application provides a control method of an energy-saving fan applied to an inflation model, which adopts a sensing technology to continuously monitor the external wind speed and the internal pressure of the inflation model, utilizes an artificial intelligence technology based on deep learning to perform time sequence analysis on the external wind speed and the internal pressure data so as to capture the time sequence change modes of the external wind speed and the internal pressure, and further, extracts the associated influence of the external environment wind speed on the internal pressure of the inflation model by performing time sequence response analysis on the external environment wind speed and the internal pressure state of the inflation model, so that the fan rotating speed is intelligently controlled by combining the external environment condition and the internal pressure state of the inflation model to maintain the stability of the inflation model. By the method, energy consumption can be effectively reduced, and meanwhile, stability and safety of the inflatable model under various environmental conditions are ensured, so that energy efficiency of the inflatable model is improved.
Fig. 1 is a schematic diagram of an application scenario of a control method of an energy-saving fan applied to an inflation model according to an embodiment of the present application. As shown in fig. 1, in this application scenario, first, an internal real-time pressure value is acquired by the pressure sensor 2 disposed inside the inflation model 1, and an external real-time wind speed value is acquired by the wind speed sensor 3 disposed outside the inflation model 1. Then, the acquired time data set of the real-time pressure value and the acquired time data set of the real-time wind speed value are input into a fan central controller 4 deployed with a fan rotating speed control algorithm for data processing to generate a control signal for adjusting the fan rotating speed, and the control signal is sent to a variable frequency driver 5 of an energy-saving fan 6 for fan rotating speed control.
Fig. 2 is a flowchart of a control method of an energy-saving fan applied to an inflation model according to an embodiment of the present application. Fig. 3 is a data flow diagram of a control method of an energy-saving fan applied to an inflation model according to an embodiment of the present application. The control method of the energy-saving fan applied to the inflation model comprises the steps of S1, collecting a time sequence data set of real-time wind speed values through a wind speed sensor arranged outside the inflation model, collecting a time data set of internal pressure values through a pressure sensor arranged inside the inflation model, S2, transmitting the time sequence data set of the real-time wind speed values and the time data set of the internal pressure values to a fan central controller through a wireless transmission module, S3, carrying out time sequence feature extraction on the time sequence data set of the real-time wind speed values and the time data set of the internal pressure values at the fan central controller to obtain an external wind speed time sequence implicit association feature vector and a model internal pressure time sequence implicit association feature vector, S4, carrying out time sequence response analysis on the external wind speed time sequence implicit association feature vector and the model internal pressure time sequence implicit association feature vector at the fan central controller to obtain an external wind speed-internal pressure time sequence response code vector, and generating a fan speed control signal based on the external wind speed-internal pressure time sequence response code vector at the fan central controller, wherein the fan central controller is used for controlling the frequency conversion of a driving signal of the energy-saving fan.
In the above control method of the energy-saving fan applied to the inflation model, in step S1, a time-series data set of real-time wind speed values is collected by a wind speed sensor disposed outside the inflation model, and a time data set of internal pressure values is collected by a pressure sensor disposed inside the inflation model. It should be appreciated that internal pressure is a critical factor in maintaining the shape and structural integrity of the inflatable mold. By monitoring the internal pressure, it is ensured that the inflatable model is at an appropriate pressure level, neither over-inflation resulting in the material being subjected to excessive stress nor under-pressure resulting in the model collapsing or destabilizing. Whereas changes in external wind speed have a direct effect on the inflatable model. For example, in strong wind conditions, the inflatable model may be deformed or damaged by external pressure. Therefore, by monitoring the external wind speed, the working state of the fan can be timely adjusted to ensure that the inflation model can respond to external environment changes properly and maintain the shape and stability of the inflation model. For example, when the external wind speed is lower and the internal pressure is stable, the rotation speed of the fan can be reduced to reduce unnecessary energy consumption, and conversely, when the external wind speed is increased or the internal pressure is reduced, the rotation speed of the fan can be increased to ensure the normal operation of the inflation model. Therefore, the response efficiency of fan control is improved, and the purposes of energy conservation and emission reduction are achieved.
It will be appreciated that in performing monitoring of internal and external conditions of an inflatable model, it is important to select the appropriate sensor and ensure its proper deployment. In particular, when deployment of wind speed sensors is performed, the purpose is to accurately obtain the change of wind in the surrounding environment. This not only involves what type of sensor is selected, but also needs to take into account its specific mounting location to ensure that the data obtained is representative. In an outdoor environment, wind speed is a dynamic factor and varies with time and space. Therefore, in order to obtain data that most truly reflects the actual situation, it is necessary to employ a high-precision and durable wind speed sensor. Among them, an ultrasonic type or propeller type anemometer is an ideal choice because of its good response speed and accuracy. Such sensors are capable of providing stable measurements under a variety of weather conditions and respond rapidly to rapidly changing wind conditions.
Regarding the installation location of the wind speed sensor, it should be placed in a place that can represent the average wind speed in the area where the entire air-filled model is located. At the same time, in order to avoid local obstructions from interfering with the measurement results, the sensor should be kept as far away from the building or other objects that may affect the airflow. In addition, if the inflation model is located in an open area, several sensors may be arranged in multiple directions, further improving the reliability of the data by multi-point sampling. By the aid of the wind speed control method, the current wind speed condition can be known more accurately, and important basis is provided for follow-up intelligent control.
Next, pressure monitoring is performed on the interior of the inflation model. The pressure sensor used here must have sufficient sensitivity in order to detect small pressure fluctuations. Given that the pressure inside the inflation model is typically at a lower level (relative to atmospheric pressure), a micro differential pressure sensor may be used to do this. This type of sensor is designed for accurate measurement in a low pressure range and is well suited for monitoring the pressure conditions inside an inflatable model. In addition, since there may be different pressure distributions inside the inflation model, in selecting the mounting location of the sensor, the sensor should be mounted in a position that reflects the overall pressure level while avoiding direct exposure to environmental factors that may cause sudden pressure changes. For example, the sensor may be mounted near a central region of the inflatable model or a connection point of the support structure, which locations generally provide relatively stable and representative pressure readings.
After the type and installation position of the sensor are ensured, the next step is data acquisition. In order to guarantee the quality of the data, a reasonable sampling frequency must be set. In dynamic environments such as outdoor exhibitions, a higher sampling rate (e.g., several times per second) is necessary because the external conditions change faster and frequent updating of the data helps the control system react faster. In a relatively stable indoor display scene, the sampling frequency is kept low, so that the monitoring requirement can be met, and excessive redundant data cannot be generated. It should be noted that in any case, the data collection of the wind speed sensor and the pressure sensor should be ensured to be performed synchronously, so that the values of the wind speed sensor and the pressure sensor can be obtained at the same time point at the same time, thereby facilitating the subsequent analysis of the association relationship between the wind speed sensor and the pressure sensor.
In addition to setting an appropriate sampling frequency, preliminary processing of the raw data is required. Since data from sensors often contains noise and other forms of error, erroneous determinations may result if not cleaned. The preprocessing of the data can be started at the sensor end, including measures to remove unnecessary noise, calibrate possible deviations, etc. In addition, the abnormal value is filtered, so that erroneous readings generated in extreme cases are prevented from affecting the decision making process of the control system. By preprocessing the data, the accuracy of subsequent analysis can be greatly improved, and meanwhile, the workload of the central controller is also reduced.
In the above control method of the energy-saving fan applied to the inflation model, in step S2, the time-series data set of the real-time wind speed value and the time data set of the internal pressure value are transmitted to the fan central controller through a wireless transmission module. It should be understood that, in order to realize efficient transmission and processing of data, the application further transmits the time sequence data set of the real-time wind speed value and the time data set of the internal pressure value to the central controller of the fan through the wireless transmission module, so that the collected wind speed data and pressure data are subjected to data analysis by using a data processing algorithm deployed by the central controller of the fan, and intelligent control of the rotating speed of the fan is realized. In addition, in the technical scheme of the application, the wireless transmission module is adopted for data transmission, so that the wiring cost and the maintenance difficulty can be effectively reduced, and the trouble and the extra expense caused by laying long-distance cables are avoided especially in the outdoor or large-scale places. Moreover, modern wireless transmission techniques can provide sufficiently low latency to support real-time data transmission to ensure that the fan central controller can quickly receive up-to-date wind speed and pressure information to respond in time.
In particular, in implementations where the wireless transmission module is used to transmit the time series data sets of real-time wind speed values and the time data sets of internal pressure values to the blower central controller, including but not limited to selecting appropriate wireless communication technologies, ensuring security and reliability of data transmission, optimizing network configuration to support large-scale deployment, and coping with various challenges that may be encountered. Accordingly, the following is a comprehensive description of this process:
First, to ensure the effectiveness and efficiency of data transmission, selecting an appropriate wireless communication technology is a critical first step. Considering the characteristics of application scenarios, namely the need to perform Long-distance data transmission in a relatively wide space, and the need to ensure low delay and high stability, several common wireless communication protocols become candidates, i.e., wi-Fi, loRa (Long Range), zigbee, and Bluetooth Low Energy (BLE). Each protocol has unique advantages and disadvantages and is suitable for different types of project requirements. For the present application, a solution is needed that can provide a stable connection over a large area while having lower power consumption characteristics. Therefore, loRa is preferred after comprehensively evaluating factors such as transmission distance, bandwidth requirements, energy consumption level, etc.
The LoRa technology is known for its long distance coverage capability, and maintains good signal quality even under complex terrain conditions. The operating frequency of the LoRa technology is typically in the unlicensed band, which means that it can be used without additional application for spectrum resources. In addition, the LoRa equipment consumes very little energy, and is very suitable for application scenes with higher requirements on the service life of the battery. More importantly, the LoRa network architecture supports a star topology, which enables the LoRa network architecture to be easily expanded to a plurality of nodes, and meets the requirements of a large inflation model site. By installing the loRa gateway at a proper position around the inflation model, a stable wireless network environment can be established, so that all deployed sensors can be accessed into the wireless network environment and upload data to the fan central controller in real time.
However, there is also a need to ensure that the transmitted data has a high degree of security and integrity after selecting the appropriate wireless communication technology. After all, this data is directly related to the proper functioning of the fan control system, and any tampering or loss can have serious consequences. For this reason, various security measures are employed to protect data during wireless transmission. On one hand, the transmitted data packet is encrypted by an encryption algorithm to prevent an unauthorized third party from stealing sensitive information, and on the other hand, the identity validity of each device is confirmed by an identity verification mechanism, and only authenticated devices can be added into the network to participate in communication. Meanwhile, access permission rules can be set, and specific devices are limited to execute certain operations, so that the security of the system is further enhanced.
In addition to basic security, consideration needs to be given to how to optimize the network configuration to support large-scale deployment. When the number of inflation models is large or the occupied area is large, the condition that a plurality of sensors work simultaneously may be involved. In this case, if the network resources cannot be effectively managed, congestion phenomenon is easily caused, and thus the overall performance is affected. To solve this problem, some intelligent scheduling algorithms, such as priority-based data queuing mechanism or method for dynamically adjusting channel occupancy, may be introduced to ensure that important data is processed preferentially, while unimportant data may be transmitted during idle periods. In addition, the idea of edge calculation can be utilized, a small server or gateway equipment can be deployed at a place close to the sensor, partial data analysis tasks can be completed in advance, the pressure of a central server is reduced, and the response speed is improved.
Of course, various emergency situations are also unavoidable in the actual deployment process. For example, due to the influence of natural environmental factors (such as bad weather), the wireless signal may be attenuated or even interrupted. For this situation, an emergency plan needs to be pre-established, such as adding a standby route path or adopting a self-healing network technology, and once the problem occurs in the main link, the system can be automatically switched to the standby link to continue to work. In addition, considering the risk of possible hardware faults in the long-term operation process, a perfect maintenance system should be established, the equipment state is checked regularly, the aging components are replaced in time, and the continuous and stable operation of the whole system is ensured.
In summary, the specific flow of data transmission includes that firstly, data collected from a sensor is initially processed locally to remove noise, calibration errors and the like, and then is packed into a data frame according to a preset format. Each data frame contains not only the actual measured values of wind speed and pressure, but also metadata such as a time stamp, a device identifier and the like, so as to facilitate subsequent analysis. These data frames are then sent out through the selected wireless communication protocol and eventually reach the blower central controller after a series of intermediate links (e.g., gateway forwarding). Here, the central controller decodes, parses, and stores the received data in a database for further analysis. It should be noted that, to accommodate different application scenario requirements, the central controller should also have a flexible data receiving interface, which is compatible with multiple types of input sources, whether from a single sensor or multiple distributed nodes.
In the above control method of the energy-saving fan applied to the inflation model, in step S3, in the fan central controller, a time sequence feature extraction is performed on the time sequence data set of the real-time wind speed value and the time data set of the internal pressure value to obtain an external wind speed time sequence implicit association feature vector and a model internal pressure time sequence implicit association feature vector. In a specific example of the application, the time series data set of real-time wind speed values and the time series data set of internal pressure values are input to a time series encoder based on an LSTM-RNN hybrid model to obtain the external wind speed time series implicit correlation feature vector and the model internal pressure time series implicit correlation feature vector. Here, considering that the external wind speed and the internal pressure of the inflation model are dynamic data which change with time and have high time sequence characteristics, in order to fully capture the time sequence change modes of the wind speed data and the pressure data, the application adopts an LSTM-RNN hybrid model to construct a time sequence encoder to respectively extract time sequence characteristics of the time sequence data set of the real-time wind speed value and the time sequence data set of the internal pressure value so as to obtain an external wind speed time sequence implicit relation characteristic vector and a model internal pressure time sequence implicit relation characteristic vector. Those of ordinary skill in the art will appreciate that both the LSTM (long short term memory network) model and the RNN (recurrent neural network) model are deep learning models that are good at processing time series data. The RNN model can effectively capture short-term dependency relationships in time series data through an internal circulating connection structure, but the RNN model has poor effect when processing long series data due to the fact that the RNN model faces the problem of gradient disappearance or gradient explosion in practical application. The LSTM model can better capture and utilize the long-term dependence information in the sequence data by introducing a gating mechanism, so that the gradient disappearance problem in the traditional RNN model is avoided. Therefore, in the technical scheme of the application, in order to comprehensively utilize the advantages of the LSTM model and the RNN model, the LSTM-RNN hybrid model is constructed so as to capture short-term dynamic changes and retain long-term dependency information in the time sequence feature extraction process of wind speed data and pressure data, thereby providing a more accurate data base for subsequent fan rotation speed control.
In the above control method of the energy-saving fan applied to the inflation model, in step S4, in the fan central controller, a time sequence response analysis based on inter-feature implicit association is performed on the external wind speed time sequence implicit association feature vector and the model internal pressure time sequence implicit association feature vector to obtain an external wind speed-internal pressure time sequence response coding vector. That is, it is contemplated that for the inflatable model, dynamic changes between external wind speed and internal pressure are not isolated events, but rather, there is some correlation. Therefore, the application further carries out time sequence response analysis on the external wind speed time sequence implicit association characteristic vector and the model internal pressure time sequence implicit association characteristic vector, and reveals the action relationship between the external wind speed and the internal pressure, so as to fully understand the time sequence change mode of the internal pressure of the inflation model under the specific external wind speed condition, thereby timely adjusting the rotating speed of the fan to adapt to the pressure change and avoiding the damage or the over inflation of the inflation model caused by the abrupt pressure change.
Fig. 4 is a flowchart of step S4 in a control method of an energy-saving fan applied to an inflation model according to an embodiment of the present application. As shown in FIG. 4, the step S4 includes S41 of inputting the external wind speed time sequence implicit association feature vector and the model internal pressure time sequence implicit association feature vector into a collaborative feature extraction network to obtain an external wind speed-internal pressure time sequence inter-feature implicit collaborative code vector, and S42 of carrying out feature modulation interaction fusion on the external wind speed time sequence implicit association feature vector and the model internal pressure time sequence implicit association feature vector based on the external wind speed-internal pressure time sequence inter-feature implicit collaborative code vector to obtain the external wind speed-internal pressure time sequence response code vector.
In a specific example of the present application, the collaborative feature extraction network includes three parallel feature interaction layers, a multi-level interaction feature cascade layer, a point convolution layer, and a activation layer based on a leakage ReLU function. Based on this, the calculation process of step S41 can be formulated as:
wherein V 1 represents the external wind speed timing implicit correlation feature vector, V 2 represents the model internal pressure timing implicit correlation feature vector, Indicates that the addition is performed by the position point, +.,Conv 1×1 represents a1×1 convolution operation, leaky ReLU represents a Leaky ReLU activation function, and V J represents an external wind speed-internal pressure timing sequence inter-feature implicit collaborative coding vector.
The method comprises the steps of firstly carrying out multi-level interaction, point convolution, nonlinear activation and other operations on the external wind speed time sequence implicit association feature vector and the model internal pressure time sequence implicit association feature vector through a collaborative feature extraction network so as to capture deep level association between the external wind speed time sequence implicit association feature vector and the model internal pressure time sequence implicit association feature vector and excavate time sequence collaborative feature representation between the external wind speed time sequence implicit association feature vector and the model internal pressure time sequence implicit association feature vector.
In one specific example of the present application, the step S42 includes first writing the implicit collaborative code vector between the external wind speed and internal pressure time sequence characteristics into a dynamic memory unit to obtain a dynamic key vector, expressed by a formula:
mu＝M(VJ)
Where M (·) represents a1×1 convolution operation and M u represents a dynamic key vector.
Here, the dynamic memory unit is a special type of memory structure, the working principle of which is similar to that of the memory unit in the recurrent neural network, and the memory content and the internal state of the dynamic memory unit can be dynamically adjusted according to the current input characteristics so as to better adapt to the context requirements of the current scene.
And then, based on the dynamic key vector, respectively carrying out feature attention modulation optimization on the external wind speed time sequence implicit association feature vector and the model internal pressure time sequence implicit association feature vector to obtain an optimized external wind speed time sequence implicit association feature vector and an optimized model internal pressure time sequence implicit association feature vector. More specifically, firstly, extracting the dynamic key vector from the dynamic memory unit, and inputting the external wind speed time sequence implicit association feature vector and the dynamic key vector into a feature attention modulation module based on a first converter structure to obtain the optimized external wind speed time sequence implicit association feature vector, wherein the optimized external wind speed time sequence implicit association feature vector is expressed as follows by a formula:
Wherein, W 1q and W 1v respectively represent a first query embedding matrix and a first value embedding matrix, V 1q and V 1v respectively represent a first query vector and a first value vector, b 1q and b 1v respectively represent different bias terms, softmax (·) represents a normalized exponential function, S represents a feature scale value of the dynamic key vector, and V' 1 represents an optimized external wind speed time sequence implicit correlation feature vector.
Then, extracting the dynamic key vector from the dynamic memory unit, and inputting the model internal pressure time sequence implicit association feature vector and the dynamic key vector into a feature attention modulation module based on a second converter structure to obtain the optimized model internal pressure time sequence implicit association feature vector, wherein the optimized model internal pressure time sequence implicit association feature vector is expressed as follows by a formula:
wherein, W 2q and W 2v represent a second query embedding matrix and a second value embedding matrix, V 2q and V 2v represent a second query vector and a second value vector, b 2q and b 2v represent different bias terms, and V' 2 represents an internal pressure time sequence hidden associated feature vector of the optimized model.
That is, the query vector and the value vector for the external wind speed time sequence hidden associated feature vector and the query vector and the value vector for the model internal pressure time sequence hidden associated feature vector are respectively constructed, a self-attention mechanism in a converter structure is utilized, and the external wind speed time sequence hidden associated feature vector and the model internal pressure time sequence hidden associated feature vector are subjected to feature modulation based on query attention based on the dynamic key vector (namely, the time sequence cooperative feature between the external wind speed and the internal pressure), which is equivalent to taking the dynamic key vector as a common attention space, so that the expression of key information in original features is enhanced, the influence of noise and irrelevant information is reduced, and meanwhile, the optimized external wind speed time sequence hidden associated feature vector and the model internal pressure time sequence hidden associated feature vector are positioned in an aligned semantic space, so that feature interaction and fusion processing between the external wind speed time sequence hidden associated feature vector and the model internal pressure time sequence hidden associated feature vector are convenient.
And finally, fusing the optimized external wind speed time sequence implicit association characteristic vector and the optimized model internal pressure time sequence implicit association characteristic vector to obtain the external wind speed-internal pressure time sequence response coding vector. More specifically, the optimized external wind speed time sequence implicit association characteristic vector and the optimized model internal pressure time sequence implicit association characteristic vector are input into a characteristic linear interaction network to obtain the external wind speed-internal pressure time sequence response coding vector, and the external wind speed-internal pressure time sequence response coding vector is expressed as follows by a formula:
V=γV'1+(1-γ)V'2
Wherein, gamma is a fusion weight parameter, and V represents the external wind speed-internal pressure time sequence response coding vector.
The method comprises the steps of carrying out interactive fusion processing on an optimized external wind speed time sequence implicit association feature vector and an optimized model internal pressure time sequence implicit association feature vector by using a characteristic linear interaction network, namely carrying out weighted fusion between wind speed time sequence change features and pressure time sequence change features in a linear transformation mode to generate an external wind speed-internal pressure time sequence response coding vector, so that comprehensive response analysis of an inflatable model under different external wind speeds and internal pressure conditions is realized, and more accurate and comprehensive decision support is provided for intelligent control of the rotating speed of a subsequent fan.
In the above control method of the energy-saving fan applied to the inflation model, in step S5, the fan central controller generates a control signal of the fan rotation speed based on the external wind speed-internal pressure time sequence response coding vector, where the control signal is used to control the variable frequency driver of the energy-saving fan. In one specific example of the present application, the step S5 includes inputting the external wind speed-internal pressure time sequence response encoding vector into a decoder-based wind speed optimizer to obtain a decoded value of an optimal fan speed, and generating the control signal based on a comparison between the decoded value of the optimal fan speed and a current fan speed value.
Specifically, after the decoder structure in the wind speed optimizer receives the external wind speed-internal pressure time sequence response coding vector, the decoder structure learns and simulates the complex dynamic relationship between the external wind speed and the internal pressure by extracting the layer-by-layer characteristics of the external wind speed-internal pressure time sequence response coding vector, and predicts the optimal rotating speed which the fan should reach under the current external wind speed and the internal pressure condition based on the complex dynamic relationship. In an embodiment of the application, the decoder employs a multi-layer perceptron (MLP) model.
Finally, according to the difference between the optimal rotation speed decoding value provided by the decoder and the current fan speed value, the fan central controller further calculates corresponding adjustment quantity through a control algorithm, generates corresponding control signals and adjusts the rotation speed of the fan through the variable frequency driver so as to achieve the purposes of energy saving and efficiency optimization. By the mode, the fan can be ensured to stably run under various wind speeds and pressure conditions, the service life of the fan can be effectively prolonged, and the extra energy consumption caused by frequent rotation speed adjustment is reduced.
Preferably, inputting the external wind speed-internal pressure timing response encoded vector into a decoder-based wind speed optimizer to obtain a decoded value of an optimal fan speed comprises:
first, the square root of the sum of the absolute values and the sum of squares of all eigenvalues of the external wind speed-internal pressure time series response encoding vectors is calculated to obtain first and second external wind speed-internal pressure time series response encoding spatial structure values, namely:
w1＝∑i|vi|
Wherein v i is a characteristic value of the i-th position in the external wind speed-internal pressure time sequence response coding vector, w 1 is a first external wind speed-internal pressure time sequence response coding spatial structure value, and w 2 is a second external wind speed-internal pressure time sequence response coding spatial structure value;
next, determining the number of eigenvalues L of the external wind speed-internal pressure time sequence response coding vector;
Then, for each eigenvalue of the external wind speed-internal pressure time series response coding vector, calculating a first external wind speed-internal pressure time series response coding length dependent value obtained by subtracting the product of the eigenvalue and the number of eigenvalues from the first external wind speed-internal pressure time series response coding spatial structure value, namely:
xi＝w1-vi×L
Wherein x i is a first external wind speed-internal pressure time sequence response code length dependent value corresponding to v i;
meanwhile, calculating a second external wind speed-internal pressure time sequence response code length dependent value obtained by subtracting the second external wind speed-internal pressure time sequence response code space structure value from the square root of the number of the characteristic values multiplied by the characteristic values, namely:
Wherein y i is a second external wind speed-internal pressure time sequence response code length dependent value corresponding to v i;
Secondly, weighting and summing the index value obtained by calculating the index taking the first external wind speed-internal pressure time sequence response coding length dependence value as a natural constant and the inverse of the second external wind speed-internal pressure time sequence response coding length dependence value to obtain an optimized characteristic value corresponding to each characteristic value, namely:
Wherein alpha and beta represent different weighting parameters, and v' i represents an optimized eigenvalue corresponding to v i;
and finally, inputting the optimized external wind speed-internal pressure time sequence response coding vector composed of the optimized characteristic values into a wind speed optimizer based on a decoder to obtain a decoded value of the optimal fan speed.
Here, considering that in the case of the external wind speed time sequence implicit correlation feature vector and the model internal pressure time sequence implicit correlation feature vector distribution represent the multi-scale time sequence correlation feature of the real-time wind speed value and the internal pressure value of the inflation model, after the inter-feature attention interaction is performed on the external wind speed-internal pressure time sequence response coding vector, the external wind speed-internal pressure time sequence response coding vector also has significant attention interaction distribution space structure difference due to the time sequence correlation feature distribution dynamic memory difference caused by the source data time sequence distribution difference, the convergence consistency of the decoder is affected, and the accuracy of the decoding value of the optimal fan speed obtained by the wind speed optimizer based on the decoder is affected.
Based on the above, spatial structure lack possibly existing in a high-dimensional space for the feature set of the external wind speed-internal pressure time sequence response coding vector causes that the weight matrix of the decoder implicitly deduces spatial structure information based on features so that convergence is inconsistent, a long-distance feature dependency relationship is established by establishing a spatial structure representation of the external wind speed-internal pressure time sequence response coding vector relative to the external wind speed-internal pressure time sequence response coding vector based on the whole feature scale of the external wind speed-internal pressure time sequence response coding vector so as to establish the feature local connectivity of the external wind speed-internal pressure time sequence response coding vector, and spatial ambiguity information of the feature value of a capturing object is predicted through unstructured feature value points of the external wind speed-internal pressure time sequence response coding vector, so that the spatial induction deviation perception capability of the feature set of the external wind speed-internal pressure time sequence response coding vector is improved, the convergence consistency of the decoder is improved, and the accuracy of a decoding value of an optimal fan speed obtained by a wind speed optimizer based on the external wind speed input of the external wind speed-internal pressure time sequence response coding vector is improved.
Further, the application also provides an energy-saving fan applied to the inflation model.
FIG. 5 is a block diagram of an energy efficient blower applied to an inflatable model in accordance with an embodiment of the present application. As shown in fig. 5, the energy-saving fan 100 applied to the inflation model according to the embodiment of the application comprises an inflation model state monitoring module 110, a data transmission module 120, a data timing characteristic extraction module 130, a control signal generation module 150, and a control signal generation module 140, wherein the inflation model state monitoring module 110 is used for acquiring a time sequence data set of real-time wind speed values through a wind speed sensor arranged outside the inflation model, acquiring a time sequence data set of internal pressure values through a pressure sensor arranged inside the inflation model, transmitting the time sequence data set of real-time wind speed values and the time sequence data set of internal pressure values to a fan central controller through a wireless transmission module, the data timing characteristic extraction module 130 is used for extracting time sequence characteristics of the time sequence data set of real-time wind speed values and the time sequence data set of internal pressure values to obtain an external wind speed timing implicit correlation characteristic vector and a model internal pressure timing implicit correlation characteristic vector, and the time sequence response analysis module 140 is used for performing time sequence response analysis based on the time sequence response implicit correlation characteristic vector between characteristics to obtain an external wind speed and internal pressure timing response coding vector at the fan central controller, and the control signal generation module 150 is used for generating a frequency conversion signal to control the fan based on the frequency conversion signal.
Here, it will be understood by those skilled in the art that the specific operations of the respective modules in the above-described energy saving fan applied to the inflation model have been described in detail in the above description of the control method of the energy saving fan applied to the inflation model with reference to fig. 1 to 4, and thus, repetitive descriptions thereof will be omitted.
The basic principles of the present invention have been described above in connection with specific embodiments, but it should be noted that the advantages, benefits, effects, etc. mentioned in the present invention are merely examples and not intended to be limiting, and these advantages, benefits, effects, etc. are not to be construed as necessarily possessed by the various embodiments of the invention. Furthermore, the particular details of the above-described embodiments are for purposes of illustration and understanding only, and are not intended to limit the invention to the particular details described above, but are not necessarily employed.
Claims (9)
1. The control method of the energy-saving fan applied to the inflation model is characterized by comprising the following steps of:
Acquiring a time sequence data set of real-time wind speed values through a wind speed sensor arranged outside the inflation model, and acquiring a time data set of internal pressure values through a pressure sensor arranged inside the inflation model;
transmitting the time sequence data set of the real-time wind speed value and the time data set of the internal pressure value to a fan central controller through a wireless transmission module;
the fan central controller extracts time sequence characteristics of the time sequence data set of the real-time wind speed value and the time data set of the internal pressure value to obtain an external wind speed time sequence implicit association characteristic vector and a model internal pressure time sequence implicit association characteristic vector;
the fan central controller performs time sequence response analysis based on inter-feature implicit association on the external wind speed time sequence implicit association characteristic vector and the model internal pressure time sequence implicit association characteristic vector to obtain an external wind speed-internal pressure time sequence response coding vector;
and the fan central controller is used for generating a control signal of the fan rotating speed based on the external wind speed-internal pressure time sequence response coding vector, and the control signal is used for controlling a variable frequency driver of the energy-saving fan.
2. The method according to claim 1, wherein the step of extracting the time series characteristic of the time series data set of the real-time wind speed value and the time series data set of the internal pressure value to obtain an external wind speed time series implicit correlation characteristic vector and a model internal pressure time series implicit correlation characteristic vector comprises the steps of:
Inputting the time sequence data set of the real-time wind speed value and the time data set of the internal pressure value into a time sequence encoder based on an LSTM-RNN hybrid model to obtain the external wind speed time sequence implicit correlation characteristic vector and the model internal pressure time sequence implicit correlation characteristic vector.
3. The method according to claim 2, wherein the performing a time-series response analysis based on inter-feature implicit correlations on the external wind speed time-series implicit correlations feature vector and the model internal pressure time-series implicit correlations feature vector to obtain an external wind speed-internal pressure time-series response code vector comprises:
inputting the external wind speed time sequence implicit association feature vector and the model internal pressure time sequence implicit association feature vector into a collaborative feature extraction network to obtain an external wind speed-internal pressure time sequence inter-feature implicit collaborative coding vector;
and based on the implicit collaborative coding vector between the external wind speed and internal pressure time sequence characteristics, carrying out characteristic modulation interactive fusion on the external wind speed time sequence implicit association characteristic vector and the model internal pressure time sequence implicit association characteristic vector to obtain the external wind speed and internal pressure time sequence response coding vector.
4. The method of claim 3, wherein the collaborative feature extraction network comprises three parallel feature interaction layers, a multi-level interaction feature cascade layer, a point convolution layer, and a activation layer based on a leakage ReLU function.
5. The method according to claim 4, wherein performing feature modulation interactive fusion on the external wind speed time sequence implicit correlation feature vector and the model internal pressure time sequence implicit correlation feature vector based on the external wind speed-internal pressure time sequence inter-feature implicit cooperative coding vector to obtain the external wind speed-internal pressure time sequence response coding vector comprises:
Writing the implicit collaborative coding vector between the external wind speed and internal pressure time sequence characteristics into a dynamic memory unit to obtain a dynamic key vector;
Based on the dynamic key vector, respectively carrying out feature attention modulation optimization on the external wind speed time sequence implicit association feature vector and the model internal pressure time sequence implicit association feature vector to obtain an optimized external wind speed time sequence implicit association feature vector and an optimized model internal pressure time sequence implicit association feature vector;
And fusing the optimized external wind speed time sequence implicit association characteristic vector and the optimized model internal pressure time sequence implicit association characteristic vector to obtain the external wind speed-internal pressure time sequence response coding vector.
6. The method according to claim 5, wherein the performing feature attention modulation optimization on the external wind speed timing implicit correlation feature vector and the model internal pressure timing implicit correlation feature vector based on the dynamic key vector to obtain an optimized external wind speed timing implicit correlation feature vector and an optimized model internal pressure timing implicit correlation feature vector, respectively, includes:
extracting the dynamic key vector from the dynamic memory unit, and inputting the external wind speed time sequence implicit association feature vector and the dynamic key vector into a feature attention modulation module based on a first converter structure to obtain the optimized external wind speed time sequence implicit association feature vector;
And extracting the dynamic key vector from the dynamic memory unit, and inputting the model internal pressure time sequence implicit association feature vector and the dynamic key vector into a feature attention modulation module based on a second converter structure to obtain the optimized model internal pressure time sequence implicit association feature vector.
7. The method of claim 6, wherein fusing the optimized external wind speed timing implication correlation feature vector and the optimized model internal pressure timing implication correlation feature vector to obtain the external wind speed-internal pressure timing response code vector, comprising:
inputting the optimized external wind speed time sequence implicit association characteristic vector and the optimized model internal pressure time sequence implicit association characteristic vector into a characteristic linear interaction network to obtain the external wind speed-internal pressure time sequence response coding vector.
8. The method of claim 7, wherein generating a control signal for a fan speed based on the external wind speed-internal pressure time sequence response encoding vector, the control signal being used to control a variable frequency drive of the energy efficient fan, comprises:
Inputting the external wind speed-internal pressure time sequence response coding vector into a wind speed optimizer based on a decoder to obtain a decoding value of the optimal fan speed;
The control signal is generated based on a comparison between the decoded value of the optimal fan speed and a current fan speed value.
9. An energy-saving fan applied to an inflatable model, comprising:
The inflation model state monitoring module is used for acquiring a time sequence data set of real-time wind speed values through a wind speed sensor arranged outside the inflation model, and acquiring a time data set of internal pressure values through a pressure sensor arranged inside the inflation model;
the data transmission module is used for transmitting the time sequence data set of the real-time wind speed value and the time data set of the internal pressure value to the fan central controller through the wireless transmission module;
The data time sequence feature extraction module is used for extracting time sequence features of the time sequence data set of the real-time wind speed value and the time data set of the internal pressure value at the fan central controller to obtain an external wind speed time sequence implicit association feature vector and a model internal pressure time sequence implicit association feature vector;
The time sequence response analysis module is used for carrying out time sequence response analysis based on inter-feature implicit association on the external wind speed time sequence implicit association characteristic vector and the model internal pressure time sequence implicit association characteristic vector at the fan central controller so as to obtain an external wind speed-internal pressure time sequence response coding vector;
The control signal generation module is used for generating a control signal of the rotating speed of the fan based on the external wind speed-internal pressure time sequence response coding vector at the fan central controller, and the control signal is used for controlling a variable frequency driver of the energy-saving fan.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411854045.5A CN119467406A (en) | 2024-12-14 | 2024-12-14 | Energy-saving fan for inflatable model and control method thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411854045.5A CN119467406A (en) | 2024-12-14 | 2024-12-14 | Energy-saving fan for inflatable model and control method thereof |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN119467406A true CN119467406A (en) | 2025-02-18 |
Family
ID=94571678
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202411854045.5A Pending CN119467406A (en) | 2024-12-14 | 2024-12-14 | Energy-saving fan for inflatable model and control method thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN119467406A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN120065888A (en) * | 2025-04-29 | 2025-05-30 | 四川川净洁净技术股份有限公司 | Clean environment control system for clean cold operation room |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040042217A1 (en) * | 2002-08-30 | 2004-03-04 | Airstar | Balloon for lighted sign comprising an inflatable envelope with self-regulated internal pressure |
| CN205940854U (en) * | 2016-08-30 | 2017-02-08 | 李坚祥 | A wind -force monitoring system for getting angry mould |
| CN110538461A (en) * | 2019-09-04 | 2019-12-06 | 台州学院 | Intelligent wind-resistant bouncy castle |
| CN116538127A (en) * | 2023-06-16 | 2023-08-04 | 湖州越球电机有限公司 | Axial flow fan and control system thereof |
| CN220370421U (en) * | 2023-02-07 | 2024-01-23 | 广州市柏拉图新材料有限公司 | Inflatable fort |
| CN118224112A (en) * | 2024-02-28 | 2024-06-21 | 宁波瑞能智慧科技股份有限公司 | Intelligent electric fan control system and method based on Internet of Things technology |
| CN118300102A (en) * | 2024-06-05 | 2024-07-05 | 齐鲁工业大学(山东省科学院) | Method for predicting wind power based on mechanism and data hybrid driving neural network |
| CN118746013A (en) * | 2024-07-10 | 2024-10-08 | 广东亿邦达科技有限公司 | A fan system and a cooling control method thereof |
-
2024
- 2024-12-14 CN CN202411854045.5A patent/CN119467406A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040042217A1 (en) * | 2002-08-30 | 2004-03-04 | Airstar | Balloon for lighted sign comprising an inflatable envelope with self-regulated internal pressure |
| CN1490217A (en) * | 2002-08-30 | 2004-04-21 | 艾尔斯达公司 | Balloon with inner pressure self adjustable inflatable pouch |
| CN205940854U (en) * | 2016-08-30 | 2017-02-08 | 李坚祥 | A wind -force monitoring system for getting angry mould |
| CN110538461A (en) * | 2019-09-04 | 2019-12-06 | 台州学院 | Intelligent wind-resistant bouncy castle |
| CN220370421U (en) * | 2023-02-07 | 2024-01-23 | 广州市柏拉图新材料有限公司 | Inflatable fort |
| CN116538127A (en) * | 2023-06-16 | 2023-08-04 | 湖州越球电机有限公司 | Axial flow fan and control system thereof |
| CN118224112A (en) * | 2024-02-28 | 2024-06-21 | 宁波瑞能智慧科技股份有限公司 | Intelligent electric fan control system and method based on Internet of Things technology |
| CN118300102A (en) * | 2024-06-05 | 2024-07-05 | 齐鲁工业大学(山东省科学院) | Method for predicting wind power based on mechanism and data hybrid driving neural network |
| CN118746013A (en) * | 2024-07-10 | 2024-10-08 | 广东亿邦达科技有限公司 | A fan system and a cooling control method thereof |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN120065888A (en) * | 2025-04-29 | 2025-05-30 | 四川川净洁净技术股份有限公司 | Clean environment control system for clean cold operation room |
| CN120065888B (en) * | 2025-04-29 | 2025-07-29 | 四川川净洁净技术股份有限公司 | Clean environment control system for clean cold operation room |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN117460129B (en) | Energy-saving street lamp control method and system based on Internet of things driving | |
| CN119467406A (en) | Energy-saving fan for inflatable model and control method thereof | |
| CN109902259B (en) | A lightweight reconstruction method for missing spatio-temporal data | |
| CN118797966B (en) | Cloud-edge-collaboration-based power grid digital twin modeling method and platform | |
| Yuan et al. | Occupancy estimation in buildings based on infrared array sensors detection | |
| CN108388291A (en) | A kind of greenhouse cluster environment regulation and control method and system | |
| TW202204939A (en) | Predictive modeling for tintable windows | |
| CN115387836B (en) | System and method for intelligent decision-making and remote linkage based on mine ventilation system | |
| KR102067110B1 (en) | Energy data processing apparatus and method with high accuracy for constructed building | |
| CN117729673A (en) | Intelligent street lamp control method and system based on real-time environment | |
| CN113676534B (en) | Bridge data uploading method based on edge calculation | |
| Wang et al. | Air quality forecasting using the GRU model based on multiple sensors nodes | |
| CN119760472A (en) | Intelligent anomaly detection and analysis method and system for electric power multi-mode space | |
| CN113033772A (en) | Multi-equipment state monitoring method based on federal learning | |
| CN119324937A (en) | Industrial environment information wireless monitoring system based on Internet of things and control method thereof | |
| CN119164050A (en) | Central air conditioning safety monitoring method and system based on BIM | |
| CN118896615B (en) | Intelligent building operation and maintenance system and method based on BIM and indoor positioning technology | |
| CN120127828A (en) | A contact network parts detection system | |
| CN109688598B (en) | Distributed data acquisition system and transmission optimization method for complex pipeline network based on WSAN | |
| CN119989111A (en) | Urban traffic detection system, method, medium and electronic device based on bidirectional memory federated learning | |
| Hoang et al. | Rotating sensor for multi-direction light intensity measurement | |
| CN118555715A (en) | Floodlight cooperation control method based on urban landscapes and intelligent control platform | |
| Mohammadi et al. | Exploiting the spatio-temporal patterns in IoT data to establish a dynamic ensemble of distributed learners | |
| Pan et al. | All‐Round Control of High‐Rise Buildings by Construction Organization Design Based on Distributed Control System | |
| CN119449849B (en) | IPV6+-based twin network synchronization control system for tunnel electromechanical equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |