CN119476056B - Turbine rotating speed dynamic adjustment method and system based on machine learning - Google Patents
Turbine rotating speed dynamic adjustment method and system based on machine learning Download PDFInfo
- Publication number
- CN119476056B CN119476056B CN202510056426.7A CN202510056426A CN119476056B CN 119476056 B CN119476056 B CN 119476056B CN 202510056426 A CN202510056426 A CN 202510056426A CN 119476056 B CN119476056 B CN 119476056B
- Authority
- CN
- China
- Prior art keywords
- water flow
- preset
- turbine
- speed
- data
- 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.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/28—Design optimisation, verification or simulation using fluid dynamics, e.g. using Navier-Stokes equations or computational fluid dynamics [CFD]
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2113/00—Details relating to the application field
- G06F2113/08—Fluids
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/14—Force analysis or force optimisation, e.g. static or dynamic forces
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E10/00—Energy generation through renewable energy sources
- Y02E10/20—Hydro energy
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Computer Hardware Design (AREA)
- Geometry (AREA)
- General Engineering & Computer Science (AREA)
- Pure & Applied Mathematics (AREA)
- Mathematical Analysis (AREA)
- Fluid Mechanics (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Mathematical Optimization (AREA)
- Algebra (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Control Of Water Turbines (AREA)
Abstract
本发明涉及涡轮转速调节技术领域，公开了一种基于机器学习的涡轮转速动态调节方法及系统，该方法包括：获取目标水域的环境信息以及水流信息，并将环境信息和水流信息代入至预先建立的水流波动模型中，获取预设时段内目标水域的预设水流波动数据。获取目标水域位于预设时段内的实时水流数据，并根据实时水流数据与预设水流波动数据之间进行比对，并根据比对结果确定涡轮的预设涡轮转速。获取涡轮的实时转动速度，并根据实时转动速度与预设涡轮转速之间的转速差值，并对涡轮进行调节。本发明通过将环境信息和水流数据与预设水流波动模型结合，实时比对涡轮转速和水流条件，实现涡轮转速的动态调整，提高水电系统在不同水流条件下发电电压的稳定性。
The present invention relates to the technical field of turbine speed regulation, and discloses a method and system for dynamic regulation of turbine speed based on machine learning, the method comprising: obtaining environmental information and water flow information of a target water area, substituting the environmental information and water flow information into a pre-established water flow fluctuation model, and obtaining preset water flow fluctuation data of the target water area within a preset time period. Real-time water flow data of the target water area within a preset time period is obtained, and a comparison is made between the real-time water flow data and the preset water flow fluctuation data, and a preset turbine speed of the turbine is determined according to the comparison result. The real-time rotation speed of the turbine is obtained, and the turbine is regulated according to the speed difference between the real-time rotation speed and the preset turbine speed. The present invention combines environmental information and water flow data with a preset water flow fluctuation model, and compares the turbine speed and water flow conditions in real time, thereby realizing dynamic adjustment of the turbine speed and improving the stability of the generated voltage of the hydropower system under different water flow conditions.
Description
Technical Field
The invention relates to the technical field of turbine rotating speed adjustment, in particular to a turbine rotating speed dynamic adjustment method and system based on machine learning.
Background
Hydroelectric power generation is widely used worldwide as a clean energy source, and its operation generally depends on a stable water flow to ensure continuous output of electric energy. However, in some special water environments, such as seasonal rivers, tidal influences on water or pressure fluctuation significant scenes, the stability of the water flow is often significantly disturbed by external factors. These unstable water flow conditions may cause the turbine speed to be difficult to maintain within an optimal range, thereby inducing output voltage fluctuations that affect the stability and quality of the power grid.
Existing hydro-power generation systems are mostly based on continuous and stable water flow designs, the rotational speed control of which depends on fixed parameter adjustment or simple feedback control mechanisms. When large water flow fluctuations or sudden pressure changes are encountered, these systems are difficult to respond in time, which may result in turbine speeds that are too high or too low, further exacerbating the problem of voltage fluctuations. In addition, the traditional method has poor adaptability to nonlinear and complex water flow characteristics, cannot realize accurate control on real-time fluctuation, and restricts the operation efficiency of a hydroelectric power generation system.
Therefore, under the condition of unstable water flow, it is important to develop a method capable of sensing water flow fluctuation in real time and intelligently adjusting the rotation speed of the turbine.
Disclosure of Invention
In view of the above, the invention provides a turbine rotating speed dynamic adjustment method and system based on machine learning, which aims to solve the problems that a hydroelectric power generation system in the prior art is difficult to cope with nonlinear characteristics caused by water flow fluctuation or pressure change, and cannot realize accurate real-time adjustment of the turbine rotating speed, so that the operation efficiency and voltage output stability of the hydroelectric power generation system are affected.
The invention provides a turbine rotating speed dynamic adjustment method based on machine learning, which comprises the following steps:
Acquiring environmental information and water flow information of a target water area, substituting the environmental information and the water flow information into a pre-established water flow fluctuation model, and acquiring preset water flow fluctuation data of the target water area within a preset period;
acquiring real-time water flow data of the target water area in the preset period, and comparing the real-time water flow data with the preset water flow fluctuation data, wherein:
if the real-time water flow data are consistent with the preset water flow fluctuation data, determining a preset rotating speed corresponding to the preset water flow fluctuation data as a preset turbine rotating speed;
if the real-time water flow data are inconsistent with the preset water flow fluctuation data, determining an adjustment coefficient according to a data difference value between the real-time water flow data and the preset water flow fluctuation data, adjusting the preset rotating speed according to the adjustment coefficient, and determining that the adjusted preset rotating speed is a preset turbine rotating speed;
acquiring the real-time rotation speed of the turbine, and acquiring a rotation speed difference value between the real-time rotation speed and the preset turbine rotation speed, wherein:
if the real-time water flow data are consistent with the preset water flow fluctuation data, determining a rotation speed adjustment parameter of the turbine in a preset period according to the preset water flow fluctuation data, and controlling the turbine to adjust according to the rotation speed adjustment parameter serving as an output instruction;
And if the real-time water flow data are inconsistent with the preset water flow fluctuation data, determining a rotation speed adjustment parameter of the turbine according to the rotation speed difference value, and controlling the turbine to adjust according to the rotation speed adjustment parameter serving as an output instruction.
Further, when the water flow fluctuation model is pre-established, the method comprises the following steps:
Acquiring environmental information, water flow information and turbine rotating speed of each historical water flow fluctuation in the target water area, and establishing a water flow fluctuation relation according to the environmental information, the water flow information and the turbine rotating speed of each historical water flow fluctuation;
obtaining a linear relation and a distance measure between each water flow fluctuation relational expression, and establishing a water flow fluctuation model according to the linear relation and the distance measure between each water flow fluctuation relational expression;
Substituting the environmental information and the water flow information of the target water area into the water flow fluctuation model to obtain preset water flow fluctuation data of the target water area and preset rotating speed of the turbine within a preset period.
Further, when the water flow fluctuation model is built according to the linear relation and the distance measure between the water flow fluctuation relations, the method comprises the following steps:
establishing a distance matrix according to the distance measurement, and carrying out iterative combination on each water flow fluctuation relation according to the distance matrix;
Acquiring each water flow fluctuation relation after iterative combination, and determining the water flow fluctuation relation as a water flow fluctuation influence type;
Acquiring environmental characteristics and water flow characteristics in the water flow fluctuation influence type, and classifying each water flow fluctuation relation based on the environmental characteristics and the water flow characteristics;
And acquiring a linear relation between the water flow fluctuation relational expressions in the water flow fluctuation influence types, and establishing the water flow fluctuation model according to the linear relation of the water flow fluctuation influence types.
Further, when the water flow fluctuation model is built according to the linear relation of the influence types of the water flow fluctuation, the method comprises the following steps:
acquiring environmental information and water flow information when any historical water flow fluctuates, substituting the environmental information and the water flow information when the historical water flow fluctuates into the water flow fluctuation model, and acquiring the preset water flow fluctuation data;
comparing the water flow fluctuation data according to the historical water flow fluctuation with the preset water flow fluctuation data, wherein the historical water flow fluctuation data are obtained by comparing the historical water flow fluctuation data with the preset water flow fluctuation data;
and if the water flow fluctuation data are inconsistent with the preset water flow fluctuation data, correcting the water flow fluctuation model.
Further, if the real-time water flow data is inconsistent with the preset water flow fluctuation data, determining the adjustment coefficient according to the data difference between the real-time water flow data and the preset water flow fluctuation data includes:
Acquiring the water flow velocity and the water pressure in the real-time water flow data, and presetting the preset water flow velocity and the preset water pressure in the preset water flow fluctuation data;
Acquiring a flow velocity difference value between the water flow velocity and a preset water flow velocity, and a pressure difference value between the water pressure and a preset water pressure;
Determining an acquisition index of the adjustment coefficient according to the relation between the flow velocity difference value and a preset flow velocity difference value range which is preset, and determining the adjustment coefficient according to the acquisition index, wherein the relation between the pressure difference value and the preset pressure difference value range which is preset:
if the flow speed difference value is in the preset flow speed difference value range, and the pressure difference value is in the preset pressure difference value range, determining that the acquisition index of the adjustment coefficient is zero, and the adjustment coefficient is 0;
If the flow speed difference value is in the preset flow speed difference value range, and the pressure difference value is not in the pressure difference value range, determining the acquisition index of the adjustment coefficient as the pressure difference value;
if the flow speed difference value is not in the preset flow speed difference value range, and the pressure difference value is in the preset pressure difference value range, determining the acquisition index of the adjustment coefficient as the flow speed difference value;
and if the flow speed difference value is not in the preset flow speed difference value range and the pressure difference value is not in the preset pressure difference value range, determining that the acquisition index of the adjustment coefficient is the flow speed difference value and the pressure difference value.
Further, when determining the adjustment coefficient according to the acquisition index, the method includes:
substituting the acquisition index into a formula to acquire the adjustment coefficient, wherein the formula is as follows:
;
Wherein S is the adjustment coefficient, 1 is the weight coefficient, M is the acquisition index, M min is the minimum value of the acquisition index, and M max is the maximum value of the acquisition index.
Further, determining a rotation speed adjustment parameter of the turbine in a preset period according to the preset water flow fluctuation data, and controlling the turbine to adjust according to the rotation speed adjustment parameter as an output instruction, wherein the method comprises the following steps:
Acquiring preset water flow speeds of all preset time periods in the preset water flow fluctuation data, and fitting a linear shaft between the preset water flow speeds of all preset time periods according to a least square method;
mapping the rotating speed difference value to the linear shaft, obtaining the speed adjustment quantity of each preset water flow speed, and converting the speed adjustment quantity into the adjustment parameter;
and controlling the turbine to adjust according to the rotation speed adjusting parameter serving as an output instruction.
Further, when determining the adjustment parameter, the method includes:
acquiring the real-time response speed of the turbine rotating speed, and determining whether to correct the adjustment parameter according to the relation between the real-time response speed and the preset response speed;
when the real-time response speed is equal to the preset response speed, determining that the adjustment parameters are not corrected;
When the real-time response speed is smaller than the preset response speed, a correction coefficient is determined according to a response speed difference value between the real-time response speed and the preset response speed, and the adjustment parameter is corrected according to the correction coefficient.
Further, determining the correction coefficient according to the response speed difference between the real-time response speed and the preset response speed includes:
Determining the correction coefficient according to the relation between the response speed difference and a preset first preset response speed difference and a preset second preset response speed difference;
When the response speed difference value is smaller than or equal to the first preset response speed difference value, determining that the correction coefficient is Q1;
When the response speed difference is larger than the first preset response speed difference and the response speed difference is smaller than or equal to the second preset response speed difference, determining that the correction coefficient is Q2;
when the response speed difference value is larger than the second preset response speed difference value, determining that the correction coefficient is Q3;
The first preset response speed difference value is smaller than the second preset response speed difference value, and 1< Q2< Q3<1.5.
Compared with the prior art, the method has the beneficial effects that the method can dynamically adjust the rotation speed of the turbine under different water flow fluctuation conditions by acquiring the environmental information and the water flow information of the target water area in real time and utilizing the pre-established water flow fluctuation model, so that the power generation system can keep higher stability and efficiency under any water flow condition. In addition, the uncertainty of water flow fluctuation can be dealt with by means of comparing real-time water flow data with preset water flow fluctuation data in real time. If the real-time water flow data is consistent with the preset fluctuation data, the real-time water flow data can be directly adjusted according to the preset rotation speed, unnecessary calculation and energy waste are avoided, and when the water flow fluctuation difference occurs, the rotation speed of the turbine is automatically adjusted according to the difference value, so that the problem of unstable operation of the turbine caused by overlarge water flow fluctuation is avoided. Therefore, the quick response capability to water flow fluctuation is enhanced, and the flexibility and the robustness of the hydroelectric power generation system are improved through an intelligent adjusting process. On the other hand, according to the accumulated data of long-term operation, the water flow fluctuation model is gradually optimized, so that the adaptability of the water flow fluctuation model to different water areas is stronger. By mining the regularity in the data, the adjustment strategy is gradually adjusted in the process of water flow change, so that blind and low-efficiency operation in the traditional method is avoided. The data-based adjusting method not only helps the hydroelectric power generation system effectively cope with complex water flow characteristics and realizes dynamic real-time adjustment, but also can improve the running accuracy of the turbine and the overall efficiency of the power generation system. By the intelligent dynamic adjustment method, the hydroelectric power generation system can be automatically adjusted when facing different water flow fluctuation, so that the problems of excessive adjustment or slow reaction and the like are avoided, the accurate control of the turbine rotation speed is ensured, and the loss of equipment and the energy waste are reduced.
In another aspect, the present application also provides a turbine rotational speed dynamic adjustment system based on machine learning, including:
The acquisition module is configured to acquire environment information and water flow information of a target water area, and substitutes the environment information and the water flow information into a pre-established water flow fluctuation model to acquire preset water flow fluctuation data of the target water area within a preset period;
The turbine control module is electrically connected with the acquisition module and is configured to acquire real-time water flow data of the target water area in the preset period, compare the real-time water flow data with the preset water flow fluctuation data, determine a preset rotating speed corresponding to the preset water flow fluctuation data as a preset turbine rotating speed if the real-time water flow data are consistent with the preset water flow fluctuation data, determine an adjustment coefficient according to a data difference value between the real-time water flow data and the preset water flow fluctuation data if the real-time water flow data are inconsistent with the preset water flow fluctuation data, adjust the preset rotating speed according to the adjustment coefficient, and determine the adjusted preset rotating speed as the preset turbine rotating speed;
The turbine control module is further configured to obtain a real-time rotation speed of the turbine, and obtain a rotation speed difference value between the real-time rotation speed and the preset turbine rotation speed, wherein if the real-time water flow data is consistent with the preset water flow fluctuation data, the turbine control module determines a rotation speed adjustment parameter of the turbine within a preset period according to the preset water flow fluctuation data, and controls the turbine to adjust according to the rotation speed adjustment parameter as an output instruction, and if the real-time water flow data is inconsistent with the preset water flow fluctuation data, the turbine control module determines the rotation speed adjustment parameter of the turbine and controls the turbine to adjust according to the rotation speed adjustment parameter as an output instruction.
It can be appreciated that the method and the system for dynamically adjusting the turbine rotation speed based on machine learning in the above embodiments of the present invention have the same beneficial effects and are not repeated.
Drawings
Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the invention. Also, like reference numerals are used to designate like parts throughout the figures. In the drawings:
FIG. 1 is a block flow diagram of a method for dynamically adjusting turbine rotational speed based on machine learning according to an embodiment of the present invention;
Fig. 2 is a functional block diagram of a turbine speed dynamic adjustment system based on machine learning according to an embodiment of the present invention.
Detailed Description
Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art. It should be noted that, without conflict, the embodiments of the present invention and features of the embodiments may be combined with each other. The invention will be described in detail below with reference to the drawings in connection with embodiments.
As shown in fig. 1, in some embodiments of the present application, the present embodiment provides a method for dynamically adjusting a turbine rotational speed based on machine learning, including:
And step S100, acquiring environment information and water flow information of the target water area, substituting the environment information and the water flow information into a pre-established water flow fluctuation model, and acquiring preset water flow fluctuation data of the target water area in a preset period.
The method comprises the steps of obtaining environment information, water flow information and turbine rotating speed when historical water flow in a target water area fluctuates, and establishing a water flow fluctuation relation according to the environment information, the water flow information and the turbine rotating speed when the historical water flow fluctuates. And obtaining a linear relation and a distance measure between the water flow fluctuation relational expressions, and establishing a water flow fluctuation model according to the linear relation and the distance measure between the water flow fluctuation relational expressions. Substituting the environmental information and the water flow information of the target water area into a water flow fluctuation model to obtain preset water flow fluctuation data of the target water area and preset rotating speed of the turbine in a preset period.
The method comprises the steps of establishing a distance matrix according to the distance measure, and carrying out iterative merging on each water flow fluctuation relation according to the distance matrix. And acquiring each water flow fluctuation relation after iterative combination, and determining the water flow fluctuation relation as a water flow fluctuation influence type. And acquiring environmental characteristics and water flow characteristics in the water flow fluctuation influence type, and classifying each water flow fluctuation relation based on the environmental characteristics and the water flow characteristics. And obtaining a linear relation among all water flow fluctuation relational expressions in the water flow fluctuation influence types, and establishing a water flow fluctuation model according to the linear relation of all water flow fluctuation influence types.
It can be seen that by establishing a distance matrix and optimizing and integrating the historical water flow fluctuation relation by utilizing an iterative combination mode, the method can effectively refine water flow fluctuation influence factors and classify and determine different water flow fluctuation influence types. Compared with the traditional model based on single characteristics, the method fully considers the diversity of complex water flow fluctuation, and lays a solid foundation for the rotation speed prediction and adjustment of the hydroelectric turbine. And secondly, by taking the environmental characteristics and the water flow characteristics as classification basis, the main influencing factors of the water flow fluctuation can be accurately captured, so that the targeted model optimization is realized. Especially under complex water flow conditions, the classified water flow fluctuation relation can remarkably improve the pertinence and accuracy of the model, and the problem of prediction deviation caused by uneven characteristic distribution in the traditional model is avoided. In addition, by substituting the real-time environmental information and the water flow information of the target water area into the model, the water flow fluctuation data in the preset period and the preset rotating speed of the turbine can be quickly generated. The real-time performance and the dynamic adaptive capacity enable the model to timely provide reliable adjusting parameters in sudden water flow fluctuation or pressure change, so that the influence of turbine rotation speed fluctuation on the power generation efficiency and the system stability is effectively reduced. Finally, through iterative optimization and linear relation analysis, the potential value of the historical data can be fully mined in the construction process of the model. The similarity between different water flow fluctuation relational expressions can be measured more intuitively by the distance matrix constructed by the distance measurement, so that key features are effectively reserved in the iterative merging process. The scientific data processing mode not only improves the robustness of the model, but also provides high-reliability data support for the accurate adjustment of the rotation speed of the subsequent turbine.
It will be appreciated that by utilizing historical data of the target body of water, including environmental information, water flow information and corresponding turbine speeds, water flow fluctuation relationships are generated that characterize the dynamics of the water flow fluctuations and their impact on turbine speed. And secondly, deeply analyzing the water flow fluctuation relational expression to generate a distance matrix, thereby quantifying the similarity and the difference between the relational expressions. And clustering the water flow fluctuation relation with similar characteristics into an influence type through an iterative merging algorithm. In the process, the data dimension reduction and structuring processing is realized, and the main driving factors and characteristic modes of water flow fluctuation can be revealed, so that the model can be better adapted to complex water flow conditions of different water areas. And meanwhile, after clustering is completed, extracting and classifying the environmental characteristics and the water flow characteristics of each type of water flow fluctuation influence type. The aim of this step is to divide the complex water flow fluctuation characteristics into several types with interpretability and predictability, ensuring the operability and accuracy of the model. And finally, an integral water flow fluctuation model is established by extracting the linear relation among various influence types. The model not only can dynamically respond to the changes of different environmental characteristics and water flow conditions, but also has stronger generalization capability, and can be suitable for various water area scenes. And finally, substituting the real-time environment information and the water flow information of the target water area into a water flow fluctuation model, so that water flow fluctuation data and turbine preset rotating speed in a preset period can be rapidly generated. The process is based on the deep learning of the model to the historical data and the dynamic adaptation of the relational expression, and the accuracy and the instantaneity of the output data are ensured. By the mode, the model can provide accurate guidance for the rotation speed control of the turbine, and particularly under the condition that the water flow fluctuation is frequent or the nonlinear characteristic is obvious, the response capability and the operation efficiency of the hydroelectric system to the water flow fluctuation are greatly improved.
Specifically, the water flow fluctuation relational expression is as follows:
q= (z 1, z2, z 3), where q is the water flow fluctuation relation, z1 is the environmental information, z2 is the water flow information, and z3 is the turbine speed.
Specifically, when the distance measure between the water flow fluctuation relations is obtained, the distance measure between the water flow fluctuation relations may be obtained by euclidean distance, manhattan distance, cosine similarity, KL divergence (relative entropy), or the like.
The method comprises the steps of obtaining environmental information and water flow information when any historical water flow fluctuates according to the linear relation of the influence types of the water flow fluctuation, substituting the environmental information and the water flow information when the historical water flow fluctuates into the water flow fluctuation model, and obtaining preset water flow fluctuation data. And comparing the water flow fluctuation data according to the historical water flow fluctuation with preset water flow fluctuation data, wherein if the water flow fluctuation data are inconsistent with the preset water flow fluctuation data, the water flow fluctuation model is corrected.
It will be appreciated that the water flow fluctuation model is built based on historical water flow fluctuation data, and preliminary preset water flow fluctuation data is generated by using these historical data as a basis. However, due to the dynamics and complexity of the water flow environment, relying solely on historical data makes it difficult to fully cover all possible water flow fluctuations. The model adopts a self-adaptive correction mechanism, namely, environmental information and water flow information when historical water flow fluctuates are substituted into preset data generated by the model, and the preset data are compared with actual historical data to detect prediction deviation of the model.
It can be seen that this alignment process is critical for dynamic correction. When the preset data and the actual data generated by the comparison result display model are inconsistent, a correction process is triggered. The modification process improves the model structure by adjusting model parameters, revising the water flow fluctuation relationship, or optimizing the linear relationship. After correction, the prediction capability of the water flow fluctuation model is further improved, so that the actual water flow characteristics of the target water area are reflected more accurately. In this way, the water flow fluctuation model can be continuously and iteratively optimized along with the accumulation of historical data, and the self-learning and self-adaption characteristics are formed. Furthermore, such dynamic correction mechanisms are particularly important for turbine speed regulation in complex water flow environments. In real application scenarios, water flow fluctuations may be affected by a variety of factors, such as the topography of the water area, seasonal variations, and sudden water flow disturbances. These factors result in the water flow fluctuations exhibiting a high degree of non-linearity and randomness. If the water flow fluctuation model cannot be updated and corrected in real time, the prediction capability of the water flow fluctuation model can be rapidly reduced, so that the rotating speed control precision of the turbine is affected. By continuously comparing the historical data with the preset data, the model can quickly find out deviation and adjust the deviation, so that the predicted result is ensured to be kept highly consistent with the actual situation. And the historical data and the real-time data are combined through the dynamic correction mechanism to form a dynamic updated model structure. The water flow fluctuation model not only can capture the conventional water flow change, but also can rapidly adapt to abnormal water flow fluctuation, and provides more accurate guidance for turbine speed adjustment, so that the problem that the running speed of the hydroelectric turbine is abnormal due to poor water flow fluctuation prediction is avoided.
Step 200, acquiring real-time water flow data of a target water area in a preset period, and comparing the real-time water flow data with preset water flow fluctuation data.
The method comprises the step of determining a preset rotating speed corresponding to preset water flow fluctuation data as a preset turbine rotating speed if the real-time water flow data are consistent with the preset water flow fluctuation data. If the real-time water flow data is inconsistent with the preset water flow fluctuation data, determining an adjustment coefficient according to a data difference value between the real-time water flow data and the preset water flow fluctuation data, adjusting the preset rotating speed according to the adjustment coefficient, and determining the adjusted preset rotating speed as the preset turbine rotating speed.
Specifically, if the real-time water flow data is inconsistent with the preset water flow fluctuation data, determining the adjustment coefficient according to the data difference between the real-time water flow data and the preset water flow fluctuation data comprises the steps of acquiring the water flow velocity and the water pressure in the real-time water flow data, and presetting the water flow velocity and the preset water pressure in the preset water flow fluctuation data. And obtaining a flow velocity difference value between the flow velocity of the water body and a preset flow velocity of the water body, and a pressure difference value between the water body pressure and the preset water body pressure. According to the relation between the flow speed difference value and a preset flow speed difference value range which is preset, the pressure difference value and a preset pressure difference value range which is preset, an acquisition index of the adjustment coefficient is determined, and the adjustment coefficient is determined according to the acquisition index, wherein if the flow speed difference value is located in the preset flow speed difference value range, and the pressure difference value is located in the preset pressure difference value range, the acquisition index of the adjustment coefficient is determined to be zero, and the adjustment coefficient is determined to be 0. If the flow speed difference value is in the preset flow speed difference value range and the pressure difference value is not in the pressure difference value range, determining an acquisition index of the adjustment coefficient as the pressure difference value. If the flow speed difference value is not in the preset flow speed difference value range, and the pressure difference value is in the preset pressure difference value range, determining an acquisition index of the adjustment coefficient as the flow speed difference value. If the flow speed difference value is not in the preset flow speed difference value range and the pressure difference value is not in the preset pressure difference value range, determining the acquisition index of the adjustment coefficient as the flow speed difference value and the pressure difference value.
Specifically, when the adjustment coefficient is determined according to the acquisition index, the method comprises the steps of substituting the acquisition index into a formula to acquire the adjustment coefficient, wherein the formula is as follows: . Wherein S is an adjustment coefficient, 1 is a weight coefficient, M is an acquisition index, M min is an acquisition index minimum, and M max is an acquisition index maximum.
It can be seen that the difference between the real-time water flow data (including the water flow rate and the pressure) of the target water area and the preset water flow data (the preset water flow rate and the pressure) predicted by the model are obtained and compared. If the two are consistent, the preset rotating speed predicted by the model is directly used as the preset rotating speed of the turbine, and if the two are inconsistent, the adjustment coefficient is dynamically calculated according to the data difference value so as to correct the preset rotating speed. In the process of determining the adjustment coefficient, key influence factors of adjustment are distinguished through threshold judgment of a preset range. The index of the adjustment coefficient may be a pressure difference, a flow rate difference, or a combination of both, depending on whether the difference is outside a preset range. When the difference value exceeds the range, substituting the difference value into an adjustment formula according to the difference value, and calculating a final adjustment coefficient. The weight coefficient in the formula is used for balancing the influence of each acquisition index on adjustment, and the minimum value and the maximum value ensure that the adjustment amplitude is in a reasonable range.
It can be understood that by comparing the real-time water flow data with the preset water flow fluctuation data, whether the current water flow condition is consistent with the model prediction or not is rapidly judged. The process can verify the accuracy of the preset model in real time, and ensures that parameters are adjusted according to actual conditions in the running process. When the real-time data is consistent with the preset data, the preset rotating speed is directly adopted, so that the calculation flow is simplified, and unnecessary complex adjustment is avoided. When the two are inconsistent, the data difference value is utilized to further analyze and adjust the requirement, so that an accurate basis is provided for the dynamic adjustment of the rotation speed of the subsequent turbine. Secondly, by introducing a flow velocity difference value and a pressure difference value, multidimensional factors influencing water flow fluctuation are comprehensively considered, and a finer adjustment mechanism is constructed. In the calculation process of the adjustment coefficient, the acquisition index is set for different difference ranges respectively, so that the adjustment process is ensured to have definite logic and reasonable step control. For example, when the flow speed difference value and the pressure difference value are both in the set range, the adjustment is judged not to be needed, so that the interference of frequent adjustment on the running stability of the equipment is effectively avoided, and when the flow speed difference value or the pressure difference value exceeds the preset range, the accurate correction can be carried out aiming at specific difference sources, and the running adaptability of the turbine is further improved. Again, the formulation of the adjustment coefficients embodies the scientificity and flexibility of dynamic adjustment. By introducing the weight coefficient and acquiring the boundary range of the index, the formula effectively balances the adjustment amplitude and the control accuracy. In this process, the adjustment coefficient is calculated not only by considering the magnitude of the current difference value, but also by setting the boundary range, the negative influence of extreme adjustment on the turbine operation is avoided. In addition, through reasonable distribution of weight coefficients, differentiation processing can be performed according to the influence degree of actual demands on flow speed and pressure, so that a more personalized rotating speed adjusting scheme is realized. Finally, the turbine rotating speed is regulated in real time, so that the turbine rotating speed is always matched with the current water flow state, and the energy loss in operation is reduced to the greatest extent. Meanwhile, accurate difference analysis and dynamic acquisition of adjustment coefficients effectively reduce equipment wear and prolong the service life of the turbine. In the whole application, the method can meet the high-efficiency operation requirement under the complex water flow environment, and is widely applicable to the operation optimization scene of various hydrodynamic power generation or water flow driving equipment.
And step S300, acquiring the real-time rotation speed of the turbine, and acquiring a rotation speed difference value between the real-time rotation speed and a preset rotation speed of the turbine.
The method comprises the steps of determining a rotation speed adjustment parameter of the turbine in a preset period according to preset water flow fluctuation data if the real-time water flow data are consistent with the preset water flow fluctuation data, and controlling the turbine to adjust according to the rotation speed adjustment parameter serving as an output instruction. If the real-time water flow data is inconsistent with the preset water flow fluctuation data, determining a rotation speed adjustment parameter of the turbine by the rotation speed difference value, and controlling the turbine to adjust according to the rotation speed adjustment parameter serving as an output instruction.
The method comprises the steps of obtaining preset water flow speeds of all preset time periods in preset water flow fluctuation data, and fitting a linear shaft between the preset water flow speeds of all preset time periods according to a least square method. And mapping the rotating speed difference value to a linear shaft, obtaining speed adjustment amounts of each preset water flow speed, and converting the speed adjustment amounts into adjustment parameters. And controlling the turbine to adjust according to the rotation speed adjusting parameter serving as an output instruction.
The method comprises the steps of obtaining the real-time response speed of the turbine rotating speed, determining whether to correct the adjustment parameter according to the relation between the real-time response speed and the preset response speed, and determining not to correct the adjustment parameter when the real-time response speed is equal to the preset response speed. When the real-time response speed is smaller than the preset response speed, a correction coefficient is determined according to the response speed difference between the real-time response speed and the preset response speed, and the adjustment parameter is corrected according to the correction coefficient.
The method comprises the steps of determining a correction coefficient according to the relation between the response speed difference and a preset first preset response speed difference and a preset second preset response speed difference. And when the response speed difference is smaller than or equal to the first preset response speed difference, determining that the correction coefficient is Q1. And when the response speed difference is larger than the first preset response speed difference and the response speed difference is smaller than or equal to the second preset response speed difference, determining that the correction coefficient is Q2. And when the response speed difference is larger than the second preset response speed difference, determining that the correction coefficient is Q3. The first preset response speed difference value is smaller than the second preset response speed difference value, and 1< Q1< Q2< Q3<1.5.
It can be seen that the difference between the real-time rotational speed and the preset rotational speed is determined by comparison between the real-time water flow data and the preset water flow fluctuation data. When the water flow fluctuation is consistent, the preset rotating speed is directly used as a control target of the turbine, so that unnecessary calculation and adjustment steps are avoided, and the response speed is improved. This approach may reduce energy waste and over-regulation. At this time, the preset water flow fluctuation data serves as a stable reference standard, and by rapidly performing turbine adjustment above the standard, optimal operation under minimum fluctuation is achieved. However, if there is an inconsistency between the real-time water flow data and the preset water flow fluctuation data, the dynamic adjustment is triggered by calculating the rotational speed difference. In this process, the rotational speed adjustment of the turbine is no longer dependent on a single preset value, but is modified according to real-time conditions. Specifically, the flow velocity and the pressure of the water body in the real-time water flow data are compared with preset data to obtain a flow velocity difference value and a pressure difference value, and then an adjustment coefficient is deduced according to the difference values, so that the rotating speed of the turbine is adjusted. The real-time feedback of two key parameters, namely the flow rate and the pressure, greatly enhances the self-correction of the rotating speed of the turbine in a complex water flow environment. In addition, in the further refinement process of the rotation speed adjustment, the linear trend of the water flow fluctuation data is fitted by adopting a least square method. By mapping the rotational speed difference to the linear axis, the speed adjustment amount can be effectively converted into an actual rotational speed adjustment parameter. This approach ensures that smooth changes in water flow fluctuations are effectively tracked and negative effects of abrupt water flow changes are avoided. The mapped adjustment parameters are fed back to the turbine through control instructions, so that fine rotating speed adjustment is achieved, and the highest matching degree of the turbine and water flow fluctuation is ensured.
Finally, the adjustment parameters are further corrected by calculating the response speed difference value so as to adapt to the actual running condition. By means of this correction factor, its control logic can be adjusted to cope with errors in the actual operation. In particular, when the response speed difference is less than or equal to the preset response speed difference, the adjustment parameters are considered to be accurate enough, so that no correction is performed. On the contrary, if the response speed difference is large, a stronger correction coefficient is generated, so that the turbine speed can be accurately adjusted, and the performance degradation of the turbine is avoided. The response speed difference correction mechanism is divided into a plurality of levels (Q1, Q2 and Q3), and each level corresponds to different response correction forces, so that proper correction strategies can be adopted according to different deviation ranges. The multistage correction mechanism can enable the turbine to operate at the most proper rotating speed under various water flow fluctuation conditions, and further effectively ensure that the hydroelectric system keeps the stability of power generation voltage under various water flow fluctuation conditions.
In the embodiment, the environmental information and the water flow information of the target water area are obtained in real time, and the turbine rotating speed can be dynamically adjusted under different water flow fluctuation conditions by utilizing the pre-established water flow fluctuation model, so that the power generation system can keep higher stability and efficiency under any water flow condition. In addition, the uncertainty of water flow fluctuation can be dealt with by means of comparing real-time water flow data with preset water flow fluctuation data in real time. If the real-time water flow data is consistent with the preset fluctuation data, the real-time water flow data can be directly adjusted according to the preset rotating speed, so that unnecessary calculation and energy waste are avoided. When the fluctuation difference of the water flow occurs, the rotation speed of the turbine can be automatically adjusted according to the difference, so that the problem of unstable operation of the turbine caused by overlarge fluctuation of the water flow is avoided. Therefore, the quick response capability to water flow fluctuation is enhanced, and the flexibility and the robustness of the hydroelectric power generation system are improved through an intelligent adjusting process. On the other hand, according to the accumulated data of long-term operation, the water flow fluctuation model is gradually optimized, so that the adaptability of the water flow fluctuation model to different water areas is stronger. By mining the regularity in the data, the adjustment strategy is gradually adjusted in the process of water flow change, so that blind and low-efficiency operation in the traditional method is avoided. The data-based adjusting method not only helps the hydroelectric power generation system effectively cope with complex water flow characteristics and realizes dynamic real-time adjustment, but also can improve the running accuracy of the turbine and the overall efficiency of the power generation system. By the intelligent dynamic adjustment method, the hydroelectric power generation system can be automatically adjusted when facing different water flow fluctuation, so that the problems of excessive adjustment or slow reaction and the like are avoided, the accurate control of the turbine rotation speed is ensured, and the loss of equipment and the energy waste are reduced.
In another preferred mode based on the above embodiment, as shown in fig. 2, the present embodiment provides a turbine rotational speed dynamic adjustment system based on machine learning, which includes an acquisition module and a turbine control module.
Specifically, the acquisition module is configured to acquire environmental information and water flow information of the target water area, and substitutes the environmental information and the water flow information into a pre-established water flow fluctuation model to acquire preset water flow fluctuation data of the target water area within a preset period. The turbine control module is electrically connected with the acquisition module, and is configured to acquire real-time water flow data of the target water area within a preset period, and compare the real-time water flow data with preset water flow fluctuation data, wherein if the real-time water flow data is consistent with the preset water flow fluctuation data, the turbine control module determines a preset rotating speed corresponding to the preset water flow fluctuation data as a preset turbine rotating speed. If the real-time water flow data is inconsistent with the preset water flow fluctuation data, the turbine control module determines an adjustment coefficient according to a data difference value between the real-time water flow data and the preset water flow fluctuation data, adjusts the preset rotating speed according to the adjustment coefficient, and determines the adjusted preset rotating speed as the preset turbine rotating speed. The turbine control module is further configured to acquire real-time rotation speed of the turbine and acquire a rotation speed difference value between the real-time rotation speed and a preset turbine rotation speed, wherein if the real-time water flow data is consistent with the preset water flow fluctuation data, the turbine control module determines a rotation speed adjustment parameter of the turbine within a preset period according to the preset water flow fluctuation data, and controls the turbine to adjust according to the rotation speed adjustment parameter as an output instruction. If the real-time water flow data is inconsistent with the preset water flow fluctuation data, the turbine control module determines a rotation speed adjustment parameter of the turbine according to the rotation speed difference value and controls the turbine to adjust according to the rotation speed adjustment parameter serving as an output instruction.
It can be appreciated that the method and the system for dynamically adjusting the turbine rotation speed based on machine learning in the above embodiments of the present invention have the same beneficial effects and are not repeated.
It will be appreciated by those skilled in the art that embodiments of the application may be provided as methods, systems, or computer program products. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each flowchart and/or block of the flowchart illustrations and/or block diagrams, and combinations of flowcharts and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
Finally, it should be noted that the above embodiments are only for illustrating the technical solution of the present invention and not for limiting the same, and although the present invention has been described in detail with reference to the above embodiments, it should be understood by those skilled in the art that modifications and equivalents may be made to the specific embodiments of the present invention without departing from the spirit and scope of the present invention, and any modifications and equivalents are intended to be included in the scope of the claims of the present invention.
Claims (10)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202510056426.7A CN119476056B (en) | 2025-01-14 | 2025-01-14 | Turbine rotating speed dynamic adjustment method and system based on machine learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202510056426.7A CN119476056B (en) | 2025-01-14 | 2025-01-14 | Turbine rotating speed dynamic adjustment method and system based on machine learning |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN119476056A CN119476056A (en) | 2025-02-18 |
| CN119476056B true CN119476056B (en) | 2025-04-29 |
Family
ID=94592422
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202510056426.7A Active CN119476056B (en) | 2025-01-14 | 2025-01-14 | Turbine rotating speed dynamic adjustment method and system based on machine learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN119476056B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103843244A (en) * | 2011-08-12 | 2014-06-04 | 开放水知识产权有限公司 | Method and system for controlling hydroelectric turbines |
| CN103929106A (en) * | 2013-01-11 | 2014-07-16 | 株式会社东芝 | Control device and control method for variable-speed water pumping power generation system |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP6926932B2 (en) * | 2017-10-18 | 2021-08-25 | 株式会社Ihi | Attitude control system for hydroelectric power generators |
| CN110397548B (en) * | 2019-06-25 | 2020-12-01 | 武汉大学 | A multi-model predictive control method for a doubly-fed variable-speed pumped-storage unit |
-
2025
- 2025-01-14 CN CN202510056426.7A patent/CN119476056B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103843244A (en) * | 2011-08-12 | 2014-06-04 | 开放水知识产权有限公司 | Method and system for controlling hydroelectric turbines |
| CN103929106A (en) * | 2013-01-11 | 2014-07-16 | 株式会社东芝 | Control device and control method for variable-speed water pumping power generation system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN119476056A (en) | 2025-02-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113862728B (en) | Pressure control method, system, equipment and medium for PEM pure water electrolysis hydrogen production | |
| US20210071638A1 (en) | Method and apparatus for dynamically determining yaw control precision | |
| CN117762221A (en) | Server temperature control method and device, server and storage medium | |
| CN117117992A (en) | Output power adjusting method, device, computer equipment and storage medium | |
| JP2020198686A (en) | Control apparatus for hydrogen production system and control method for hydrogen production system | |
| CN109327041B (en) | Providing regulated power when a renewable energy generating unit, in particular a wind power plant, is in operation | |
| CN119511983A (en) | Method, system, device and storage medium for optimizing frequency and peak regulation performance of thermal power units | |
| CN119476056B (en) | Turbine rotating speed dynamic adjustment method and system based on machine learning | |
| CN110824927A (en) | Thermal power generating unit primary frequency modulation accurate adjustment method with self-adaptive learning characteristic | |
| CN110928341A (en) | Temperature control method, device, equipment and storage medium | |
| CN119727498A (en) | Control method of self-tuning parameters of permanent magnet synchronous motor | |
| CN118673253A (en) | Radiator thermostatic valve and data processing method thereof | |
| CN119737793B (en) | Condenser optimization control method and system based on equal vacuum line | |
| CN119134535B (en) | An advanced power control method suitable for marine photovoltaic power generation system | |
| CN118934101B (en) | A control system for steam turbine valves | |
| CN118795828B (en) | Intelligent power-saving control cabinet real-time detection and adjustment system | |
| CN113090453B (en) | Control method and device of wind generating set and wind generating set | |
| CN118209773B (en) | Mining alternating current frequency converter voltage detection correction method | |
| CN119267086A (en) | Intelligent control system for adjusting the speed of wind turbine generator | |
| CN117452802B (en) | Low-carbon water supply control method | |
| CN114614490A (en) | Reactive power and voltage control method and device, medium and computing device | |
| CN120578281B (en) | A server fan speed adjustment method and device based on BMC | |
| CN117905637B (en) | Fan dynamic adjustment method and system based on multi-sensor data | |
| CN118889636B (en) | A charging control method and system for a battery charger | |
| CN120292014B (en) | Power generation fan blade tip speed ratio optimizing control method and system |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |