CN119439825A - Computer room monitoring method, device, electronic equipment and storage medium - Google Patents
Computer room monitoring method, device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN119439825A CN119439825A CN202411420284.XA CN202411420284A CN119439825A CN 119439825 A CN119439825 A CN 119439825A CN 202411420284 A CN202411420284 A CN 202411420284A CN 119439825 A CN119439825 A CN 119439825A
- Authority
- CN
- China
- Prior art keywords
- data
- equipment
- cluster
- target
- operation 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 55
- 238000012544 monitoring process Methods 0.000 title claims abstract description 51
- 230000002159 abnormal effect Effects 0.000 claims abstract description 66
- 238000013507 mapping Methods 0.000 claims abstract description 10
- 238000012545 processing Methods 0.000 claims description 34
- 230000007613 environmental effect Effects 0.000 claims description 18
- 238000004590 computer program Methods 0.000 claims description 8
- 230000015654 memory Effects 0.000 claims description 7
- 238000012806 monitoring device Methods 0.000 claims description 5
- 238000010276 construction Methods 0.000 claims description 4
- 230000000007 visual effect Effects 0.000 abstract description 7
- 238000012549 training Methods 0.000 description 15
- 238000007726 management method Methods 0.000 description 13
- 238000004458 analytical method Methods 0.000 description 11
- 238000010586 diagram Methods 0.000 description 10
- 230000008569 process Effects 0.000 description 7
- 238000012360 testing method Methods 0.000 description 5
- 230000001932 seasonal effect Effects 0.000 description 4
- 238000013506 data mapping Methods 0.000 description 3
- 238000010801 machine learning Methods 0.000 description 3
- 230000007246 mechanism Effects 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 238000009877 rendering Methods 0.000 description 3
- 230000005856 abnormality Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 238000013468 resource allocation Methods 0.000 description 2
- 239000003086 colorant Substances 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 238000013523 data management Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000000354 decomposition reaction Methods 0.000 description 1
- 238000013136 deep learning model Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000005111 flow chemistry technique Methods 0.000 description 1
- 230000002068 genetic effect Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B19/00—Programme-control systems
- G05B19/02—Programme-control systems electric
- G05B19/04—Programme control other than numerical control, i.e. in sequence controllers or logic controllers
- G05B19/042—Programme control other than numerical control, i.e. in sequence controllers or logic controllers using digital processors
- G05B19/0428—Safety, monitoring
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B2219/00—Program-control systems
- G05B2219/20—Pc systems
- G05B2219/24—Pc safety
- G05B2219/24024—Safety, surveillance
-
- 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
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
The embodiment of the application discloses a machine room monitoring method, a device, electronic equipment and a storage medium, wherein the method comprises the steps of constructing a digital twin body according to equipment information of a target machine room, wherein the digital twin body comprises a three-dimensional model of the target machine room and a three-dimensional object of each equipment; the method comprises the steps of obtaining environment data of a target machine room, obtaining equipment operation data of each equipment, displaying a digital twin body, displaying the environment data, mapping the equipment operation data of each equipment to a three-dimensional object for displaying, inputting a historical data sequence of the equipment in a target historical time period into a time sequence prediction model for each equipment when preset time is reached, determining a predicted equipment operation data sequence of the equipment in a target future time period, and displaying the abnormal predicted data in the three-dimensional object corresponding to the equipment if the abnormal predicted data exists in the predicted equipment operation data sequence. The embodiment of the application realizes the visual monitoring of all the devices in the machine room and the early warning of faults.
Description
Technical Field
The embodiment of the application relates to the technical field of data processing, in particular to a machine room monitoring method and device, electronic equipment and a storage medium.
Background
In the prior art, the machine room monitoring is to acquire information in the machine room based on a physical camera and a manual inspection mode, and monitor the information in a list mode through a background monitoring system of each device, so that a global and visual monitoring means cannot be provided. The machine room monitoring is aimed at generating equipment fault alarms, and corresponding alarms are usually generated only through equipment faults or threshold values, so that fault early warning cannot be performed in advance, and therefore a means capable of predicting faults in real time is lacking.
Disclosure of Invention
The embodiment of the application provides a machine room monitoring method, a device, electronic equipment and a storage medium, which can be used for visually monitoring a machine room and performing fault early warning.
In order to solve the above problem, in a first aspect, an embodiment of the present application provides a machine room monitoring method, including:
According to the equipment information of the target equipment room, constructing a digital twin body of the target equipment room, wherein the digital twin body comprises a three-dimensional model of the target equipment room and a three-dimensional object of each equipment in the target equipment room;
acquiring environment data of the target machine room, and acquiring equipment operation data of each equipment in the target machine room;
Displaying the digital twin, displaying the environmental data in the digital twin, and mapping the equipment operation data of each equipment to a three-dimensional object of the corresponding equipment in the digital twin for displaying;
Inputting a historical data sequence of each device in a target historical time period into a time sequence prediction model when a preset time is reached for each device, and determining a predicted device operation data sequence of the device in a target future time period through the time sequence prediction model;
if abnormal prediction data exist in the operation data sequence of the prediction equipment, displaying the abnormal prediction data in the three-dimensional object corresponding to the equipment.
In a second aspect, an embodiment of the present application provides a machine room monitoring apparatus, including:
The digital twin body construction module is used for constructing a digital twin body of the target machine room according to the equipment information of the target machine room, wherein the digital twin body comprises a three-dimensional model of the target machine room and a three-dimensional object of each equipment in the target machine room;
The data acquisition module is used for acquiring the environmental data of the target machine room and acquiring the equipment operation data of each equipment in the target machine room;
The first display module is used for displaying the digital twin, displaying the environmental data in the digital twin, and mapping the equipment operation data of each equipment to a three-dimensional object of the corresponding equipment in the digital twin for displaying;
The data prediction module is used for inputting a historical data sequence of each device in a target historical time period into a time sequence prediction model when a preset time is reached, and determining a predicted device operation data sequence of the device in a target future time period through the time sequence prediction model;
And the second display module is used for displaying the abnormal prediction data in the three-dimensional object corresponding to the equipment if the abnormal prediction data exists in the operation data sequence of the prediction equipment.
In a third aspect, an embodiment of the present application further provides an electronic device, including a memory, a processor, and a computer program stored in the memory and capable of running on the processor, where the computer program is executed by the processor to implement the machine room monitoring method according to the embodiment of the present application.
In a fourth aspect, an embodiment of the present application provides a computer readable storage medium having stored thereon a computer program, which when executed by a processor, performs the steps of the machine room monitoring method disclosed in the embodiment of the present application.
According to the machine room monitoring method, the device, the electronic equipment and the storage medium, the digital twin body of the target machine room is constructed according to the equipment information of the target machine room, the environment data of the target machine room are obtained, the equipment operation data of all the equipment in the target machine room are obtained, the digital twin body is displayed, the environment data are displayed in the digital twin body, the equipment operation data of all the equipment are mapped to the three-dimensional objects of the corresponding equipment in the digital twin body for displaying, when the preset time is reached, the historical data sequence of the equipment in the target historical time period is input into a time sequence prediction model, the predicted equipment operation data sequence of the equipment in the target future time period is determined through the time sequence prediction model, if abnormal data exist in the predicted equipment operation data sequence, the abnormal data are displayed in the three-dimensional objects corresponding to the equipment, the real-time visual monitoring of all the equipment in the machine room is realized through the display of the environment data in the digital twin body and the equipment operation data are displayed in the three-dimensional objects of all the equipment, the equipment operation data can be predicted through the time sequence prediction model, and faults can be prevented from occurring in the predicted equipment operation data in the three-dimensional objects corresponding to the predicted equipment in the future time period, and the fault can be effectively prevented.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings used in the embodiments or the description of the prior art will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present application, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flowchart of a machine room monitoring method provided in an embodiment of the present application;
FIG. 2 is an exemplary diagram of a digital twin body of a destination machine room in an embodiment of the present application;
FIG. 3 is an exemplary diagram of distinguishing between presentation device operational data and exception prediction data in an embodiment of the present application;
FIG. 4 is a schematic diagram of a Hadoop cluster build mode in an embodiment of the present application;
Fig. 5 is a schematic structural diagram of a machine room monitoring and early warning platform in the embodiment of the application;
FIG. 6 is a flow chart illustrating the operation of the intelligent analysis module in an embodiment of the present application;
fig. 7 is a schematic structural diagram of a machine room monitoring device according to an embodiment of the present application;
Fig. 8 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
The following description of the embodiments of the present application will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are some, but not all embodiments of the application. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
Before the technical scheme provided by the application is specifically introduced, nouns involved in the application are explained as follows:
The digital twin (DIGITAL TWIN) is a digital mapping system which fully utilizes data such as physical models, sensor updating, operation histories and the like, integrates simulation processes of multiple disciplines, multiple physical quantities, multiple scales and multiple probabilities, and completes mapping in a virtual space so as to reflect the full life cycle process of corresponding entity equipment, and can be regarded as one or more important and mutually dependent equipment systems.
Prophet (Facebook Prophet) A time series model based on time and variable values in combination with time series decomposition and machine learning fit. The modeling process considers the influences of factors such as trend lines, seasonality, periodicity, exogenous variables and the like, has good prediction effect, has extremely strong robustness to missing values, transition of trend and a large number of abnormal values, and has great advantages compared with the traditional time sequence model.
TensorFlow an open source machine learning library, which is widely used for realizing various machine learning applications, can construct, train and deploy deep learning models on various platforms. TensorFlow provides a powerful computational framework for numerical computation, particularly large-scale distributed computation on large-scale graphics processing units.
Hadoop (Apache Hadoop) a distributed system infrastructure. The user can develop the distributed program without knowing the details of the distributed bottom layer, and the power of the cluster is fully utilized for high-speed operation and storage.
HDFS (Hadoop Distributed FILE SYSTEM ) is a distributed file system that is characterized by high fault tolerance and designed to be deployed on inexpensive hardware, and provides high throughput to access data of applications that are adapted to applications with very large data sets and can access data in the file system in a streaming fashion.
YARN (Yet Another Resource Negotiator, another resource coordinator), a resource management system in Hadoop, is a universal resource management system that provides unified resource management and task scheduling for upper layer applications. The main advantages are that it is capable of running various types of jobs, including batch, interactive, containerized jobs, and is capable of providing flexible allocation of resources when the jobs are run.
The ZooKeeper is a high-availability distributed data management and coordination framework, can well ensure the consistency of data in a distributed environment, and is an important component of Hadoop and Hbase.
Hbase (Hadoop Database) A high-reliability, high-performance, column-oriented and scalable distributed database, which can build a large-scale structured storage cluster on a cheap PC by utilizing the HBase technology, is different from a general relational database based on HDFS as a file storage system thereof, and is a database suitable for unstructured data storage.
Kafka (Apache Kafka) a distributed publish-subscribe messaging system and a powerful queue that can handle large amounts of data suitable for offline and online message consumption, kafka messages are kept on disk and replicated within the cluster to prevent data loss.
Flink (Apache Flink) an open source stream processing framework that executes arbitrary stream data programs in a data parallel and pipelined fashion, where the system can execute batch and stream processing programs during pipeline operation.
The following describes a specific scheme of a machine room monitoring method provided by the embodiment of the application.
Fig. 1 is a flowchart of a machine room monitoring method according to an embodiment of the present application, as shown in fig. 1, the method includes steps 110 to 150.
Step 110, constructing a digital twin body of the target machine room according to the equipment information of the target machine room, wherein the digital twin body comprises a three-dimensional model of the target machine room and a three-dimensional object of each equipment in the target machine room.
The device information may include information such as model number, location, configuration, etc. The equipment within the target room may include at least one of cabinets, various types of sensors, distribution frames, network equipment, data equipment, transmission equipment, power equipment, and the like.
And constructing a three-dimensional model of the target machine room according to the equipment information of the target machine room by using a three-dimensional modeling tool, constructing a three-dimensional object corresponding to each equipment in the target machine room, and constructing a sub-module three-dimensional object corresponding to each equipment on the corresponding three-dimensional object based on the functional entity (such as a button and the like) of each equipment in the equipment information to obtain a digital twin body of the target machine room.
Fig. 2 is an exemplary diagram of a digital twin body of a target machine room in an embodiment of the present application, and as shown in fig. 2, the constructed digital twin body embodies information such as a position of each device in the target machine room.
And 120, acquiring environment data of the target machine room and acquiring equipment operation data of each equipment in the target machine room.
And configuring environment data acquisition equipment in the target machine room, acquiring environment data of the target machine room in real time through the environment information acquisition equipment, transmitting the acquired environment data to equipment for executing a machine room monitoring method, and storing the environment data after the equipment for executing the machine room monitoring method receives the environment data. The environmental data collection device may include a sensor, a camera, and the like. The environmental data may include temperature, humidity, etc. information.
And each device in the target machine room acquires device operation data by using a device data interface, the device operation data is sent to the device executing the machine room monitoring method, and the device executing the machine room monitoring method stores the device operation data after receiving the device operation data. The equipment executing the machine room monitoring method can monitor and predict the equipment in the target machine room in real time based on the stored environmental data and the equipment operation data. The device operation data is data in the device operation process, and may include, for example, optical power, current, and other data.
In the embodiment of the application, the environment data and the device operation data can be acquired in the form of data streams, for example, the environment data sent by each sensor can be received through a Kafka cluster, and the device operation data sent by each device through a device data interface can be received.
And 130, displaying the digital twin, displaying the environmental data in the digital twin, and mapping the device operation data of each device to a three-dimensional object of a corresponding device in the digital twin for display.
The digital twin body can be rendered in the WEB application by utilizing the Vue framework and the three.js engine, the environment data and the equipment operation data are mapped into the digital twin body, and the equipment operation data of the equipment are displayed in the three-dimensional object of the corresponding equipment, so that the real-time monitoring of each equipment in the target machine room is realized.
And 140, inputting a historical data sequence of the equipment in a target historical time period into a time sequence prediction model for each equipment when a preset time is reached, and determining a predicted equipment operation data sequence of the equipment in a target future time period through the time sequence prediction model.
The preset time is a preset trigger time for data prediction, and may be a fixed time of a certain day, for example, a fixed time of each day, or a fixed time of every other day. The target history period is a history period before the current time (i.e., the preset time), i.e., the current time is the end time of the target history period. The target future time period is a time period after the current time (i.e., the preset time), i.e., the current time is the start time of the target future time period. The target historical time period may be, for example, within one year of the history, the target future time period may be, for example, within a future week, etc., and may be specifically set according to the requirement.
The historical data sequence of the device in the target historical time period is a sequence formed by the device operation data collected by the device at each collection time point in the target historical time period aiming at the data of the prediction index (such as optical power, current and the like) according to the time sequence. And inputting the historical data sequence into a time sequence prediction model corresponding to the equipment and the prediction index, extracting data features from the historical data sequence through the time sequence prediction model, wherein the data features can comprise data growth type features, seasonal period features, holiday features and the like, and predicting equipment operation data of the equipment at each time point (corresponding to an acquisition time point) in a target future time period based on the extracted data features to obtain a predicted equipment operation data sequence.
It should be noted that, the historical data sequence input into the time sequence prediction model includes the device operation data in the target historical time period, and may also include the environmental data corresponding to the time of the device operation data, so as to improve the accuracy of data prediction.
In an exemplary embodiment, the time series prediction model is a Prophet model. The Prophet model can comprehensively consider the influence of factors such as data growth type, seasonal period, holidays and the like, has extremely strong robustness on missing values, trend transformation and a large number of abnormal values, and can improve the prediction accuracy.
Before the historical data sequence is input into a time sequence prediction model, differential ADF (extended Dickey-Fuller) test is carried out on the historical data sequence, whether the historical data sequence is a stable time sequence is judged, if the historical data sequence is a non-stable time sequence, differential processing is carried out on the historical data sequence, the processed stable data sequence is input into the time sequence prediction model, and a predicted equipment operation data sequence in a future time period of a target is determined through the time sequence prediction model.
Wherein, the n-step difference formula is as follows:
Δnyx＝Δ(Δn-1yx)＝Δn-1yx+1-Δn-1yx
Wherein Δ nyx represents the n-order difference of the x-th operation data in the history data sequence, Δ n-1yx represents the n-1 order difference of the x-th operation data in the history data sequence, and Δ n-1yx+1 represents the n-1 order difference of the x+1th operation data in the history data sequence.
The ADF test formula is as follows:
ADF(t)=(Y(t)-Y(t-1))-λΔY(t-1)+αt+βY(t-1)+ε(t)
Wherein ADF (t) represents an ADF test value, Y (t) represents a historical data sequence, Y (t-1) represents a hysteresis first order value of the historical data sequence, deltaY (t-1) represents a first order difference of the historical data sequence, epsilon (t) represents an error, and lambda, alpha and beta are constants.
And step 150, if abnormal prediction data exist in the operation data sequence of the prediction equipment, displaying the abnormal prediction data in the three-dimensional object corresponding to the equipment.
Comparing each piece of prediction equipment operation data in the prediction equipment operation data sequence with a preset normal data range corresponding to the data, if the prediction equipment operation data is within the preset normal data range, determining that the prediction equipment operation data is normal prediction data, and if the prediction equipment operation data is outside the preset normal data range, determining that the prediction equipment operation data is abnormal prediction data. When abnormal prediction data exists in the operation data sequence of the prediction equipment, the abnormal prediction data is displayed in a three-dimensional object corresponding to the equipment in the digital twin body, so that early warning can be performed in advance.
In one embodiment of the application, the displaying the anomaly prediction data in the three-dimensional object corresponding to the device comprises distinguishing and displaying the anomaly prediction data and the device operation data in the three-dimensional object corresponding to the device.
The device operation data and the abnormal prediction data of the corresponding device need to be displayed in the three-dimensional object of the digital twin body, and in order to facilitate distinguishing, the two data can be displayed in a distinguishing mode, for example, the abnormal prediction data can be highlighted or displayed in different font colors, and as shown in fig. 3, the abnormal prediction data is displayed at the early warning position.
According to the machine room monitoring method provided by the embodiment of the application, the digital twin body of the target machine room is constructed according to the equipment information of the target machine room, the environment data of the target machine room is obtained, the equipment operation data of each equipment in the target machine room is obtained, the digital twin body is displayed, the environment data is displayed in the digital twin body, the equipment operation data of each equipment are mapped to the three-dimensional object of the corresponding equipment in the digital twin body for displaying, when each equipment reaches the preset time, the historical data sequence of the equipment in the target historical time period is input into the time sequence prediction model, the predicted equipment operation data sequence of the equipment in the target future time period is determined through the time sequence prediction model, if abnormal data exists in the predicted equipment operation data sequence, the abnormal data is displayed in the three-dimensional object corresponding to the equipment, the real-time visual monitoring of each equipment in the machine room is realized through the display of the environment data in the digital twin body and the equipment operation data in the three-dimensional object corresponding to the equipment, the time sequence prediction model can predict the equipment operation data in the target future time period, and the abnormal data can be displayed in the three-dimensional object corresponding to the equipment in the digital twin body when the predicted equipment operation data exists, and the fault can be effectively prevented.
On the basis of the technical scheme, the machine room monitoring method is executed by a Hadoop cluster;
The Hadoop clusters comprise a Zookeeper cluster, an HDFS cluster, a Yarn cluster, a Kafka cluster, a Flink cluster and an Hbase cluster;
the Zookeeper cluster is used for guaranteeing the consistency of data in the Hadoop cluster;
The HDFS cluster is used as a bottom file storage system;
The Yarn cluster is used for carrying out resource scheduling for the execution of data processing tasks, and the data processing tasks comprise tasks for determining the operation data sequence of the prediction equipment;
the Kafka cluster is used for executing the receiving and transmitting of the data in the Hadoop cluster;
the Flink cluster is used for executing batch processing and stream processing of data in the Hadoop cluster;
the Hbase cluster is used for storing the environment data, the equipment operation data and the time sequence prediction model, and based on the operation of the HDFS cluster, the HDFS cluster is used as a bottom file storage system.
The Zookeeper cluster, the HDFS cluster and the Yarn cluster form a basic cluster of the Hadoop cluster.
The whole Hadoop cluster adopts a mode of one Master and two slaves, deployment is carried out based on three servers, one server is used as a Master server (Master), the other two servers are used as Slave servers (Slave 1 and Slave 2), and the construction mode can be referred to as figure 4. The operating system employed by each server may be a centOS (Community Enterprise Operating System ).
The Zookeeper cluster can be deployed in three servers to ensure the consistency of data in a distributed environment, quorumPeerMain is a startup class of the Zookeeper cluster, is an important component of the Zookeeper cluster and is a main entry point of Zookeeper service and responsible for starting and managing the Zookeeper service, the HDFS cluster can be deployed in three servers and is deployed in a high-availability HA mode, the single-point failure problem of the Namenode is effectively avoided, the availability and the reliability of the HDFS cluster are improved, the HDFS cluster is provided with two types of nodes and operates in a Manager-worker mode, namely a Namenode (Manager) and a plurality of datanodes (workers), a backup Manager (Secondary NameNode) is mainly used for backing up a data snapshot (snapshots) of the Namenode at regular time, the Yarn cluster can be deployed in the three servers and is responsible for providing uniform Resource management and scheduling for the operation of data processing tasks, and the global Resource Manager (Resource Manager) is responsible for the management and allocation of the whole cluster, and the Resource Manager (Resource Manager) is used for storing history information of each Node (Manager) and each history Node is used for storing history information (Manager and Manager) and each history Node (Manager) is used for storing history information Job History Server).
The Kafka cluster is used for receiving and transmitting data and is deployed in three servers. The Kafka cluster may receive environmental data sent by a sensor in the target machine room and device operation data sent by a device in the target machine room, and transmit the environmental data and the device operation data to the Flink cluster, and may also receive data returned by the Flink cluster after processing the data, and transmit the data to an early warning platform for display, where the early warning platform is a platform for displaying the digital twin body.
The Flink cluster unit is used for executing batch processing and stream processing of data, is deployed in three servers, adopts Flink On Yarn mode deployment, can utilize a resource scheduling mechanism of a Yarn cluster to complete resource allocation, avoids the problem of single-point failure of an operation manager (JobManager), and realizes high availability. The job manager controls a main process executed by one application (job). The task manager (TASK MANAGER) is a work process in the Flink. The Flink On Yarn mode includes a Session mode, a split (Per-Job) mode, and an application mode. The session mode needs to start the flank cluster first, apply resources to the Yarn cluster, and submit tasks to the applied resources later, and the flank cluster can reside in the Yarn cluster unless stopped manually. In the separation mode, one Job (Job) corresponds to one Flink cluster, resources can be independently applied to the Yarn cluster according to the condition of each Job submitted until the execution of the Job is completed, whether one Job fails or not does not influence the normal submission and operation of the next Job, and each Job is independent of a Dispatcher (Dispatcher) and a resource manager (ResourceManager) to accept resource application as required, so that the method is suitable for large-scale and long-time operation. The application mode starts the Flink cluster on the Yarn cluster, the main function of the application jar package (main function of the user class) is executed on the job manager (JobManager), and the Flink cluster can be immediately closed as long as the execution of the application program is finished, or the Flink cluster can be manually stopped.
The Hbase cluster unit is used for storing data, is deployed in three servers, operates based on the HDFS, and utilizes the HDFS as a bottom file storage system, and the data is stored in the HDFS. The master node (HMaster) is the master node of the whole HBase cluster. The slave node (Region Server) is responsible for the read-write operation of the data. The Backup master nodes (Backup Masters) are configured to ensure high availability of the Hbase cluster, and when the active master node is down, one of the Backup master nodes is selected to be active as the master node.
The data acquisition of the traditional machine room monitoring system adopts an on-demand type collection mechanism, and protocol interpretation is carried out by a monitoring host, so that the large data volume of equipment operation can cause large network data flow and large bandwidth pressure due to numerous equipment of the machine room, the system performance and stability are affected, and real-time monitoring in the real sense and operation of certain specific tasks can not be realized. The embodiment of the application can conduct real-time streaming processing and analysis on the data through the Hadoop cluster comprising the Zookeeper cluster, the HDFS cluster, the Yarn cluster, the Kafka cluster, the Flink cluster and the Hbase cluster.
On the basis of the technical scheme, the historical data sequence of the equipment in the target historical time period is input into a time sequence prediction model, and the predicted equipment operation data sequence of the equipment in the target future time period is determined through the time sequence prediction model, wherein the time sequence prediction model is loaded from an Hbase cluster through a Flink cluster; and inputting the historical data sequence into a time sequence prediction model through a Flink cluster, and determining a predicted equipment operation data sequence of the equipment in a target future time period through the time sequence prediction model.
When the preset time is reached, the Flink cluster triggers the execution of a data prediction task, a historical data sequence is obtained by loading a time sequence prediction model with training completed and equipment operation data in a target historical time period from the Hbase cluster, the historical data sequence is input into the time sequence prediction model, the time sequence prediction model extracts data features from the historical data sequence, data prediction is carried out on the data features based on the extracted data features, and a predicted equipment operation data sequence in a target future time period is determined.
When data prediction is performed through the Flink cluster, different data prediction tasks can be respectively generated aiming at different prediction indexes, and each data prediction task is respectively executed.
The Flink cluster can efficiently process the streaming data, so that the accuracy of the predicted data is improved, and the data processing efficiency is improved.
On the basis of the technical scheme, after the equipment operation data of each equipment in the target machine room are obtained, the method further comprises the steps of generating early warning information comprising abnormal data if the abnormal data exist in the equipment operation data of each equipment, and sending the early warning information to target personnel.
When the equipment operation data of each equipment are obtained, judging whether the equipment operation data have abnormal data, if so, generating early warning information comprising the abnormal data, and sending the early warning information to target personnel so as to facilitate the target personnel to maintain the equipment in advance based on the early warning information and the like, thereby avoiding the equipment from being failed. The sending mode of the early warning information can comprise mobile phone short messages, mobile phone push messages, mails and the like.
When judging whether the equipment operation data contains abnormal data or not, the equipment can determine that the equipment operation data is abnormal data if the equipment operation data contains the alarm of the abnormal data or compare the equipment operation data with a normal data range corresponding to the data index (the data index corresponding to the equipment operation data) when the equipment operation data does not contain the alarm of the abnormal data, if the equipment operation data is in the normal data range, the equipment operation data is determined to be the normal data, and if the equipment operation data is out of the normal data range, the equipment operation data is determined to be the abnormal data.
On the basis of the technical scheme, after the equipment operation data of each equipment in the target machine room are obtained, the method further comprises the steps of retraining the time sequence prediction model according to the abnormal data if the equipment operation data of each equipment has abnormal data, and storing the retrained time sequence prediction model.
If the abnormal data exists in the equipment operation data through judging the equipment operation data, retraining of the time sequence prediction model is triggered, and a training data set is generated by using historical data corresponding to the abnormal data (the historical data with the same data index as the abnormal data) and the abnormal data, wherein the abnormal data is included in input data of training samples in the training data set. When the training data set is generated, intercepting data with the time period length corresponding to the target historical time period as input data, intercepting the data with the time period length corresponding to the target future time period length from the historical data as output annotation data, intercepting the input data and the output data from different starting times according to the mode, and obtaining a plurality of training samples to obtain the training data set.
And retraining the time sequence prediction model by using the training data set, namely inputting input data in the training data set into the time sequence prediction model to be trained to obtain predicted output data, adjusting parameters of the time sequence prediction model based on the predicted output data and the output annotation data, and carrying out iteration training according to the mode until the training ending condition is met to obtain the retrained time sequence prediction model. After the retraining is completed, the retraining completed time sequence prediction model is saved, and the latest time sequence prediction model can be used for prediction when the data prediction is performed next time, so that the accuracy of the data prediction can be improved.
When the time sequence prediction model is retrained, the TensorFlow framework can be utilized to run in the Flink cluster, so that after retrained, the newly trained time sequence prediction model can be stored in the Hbase database, and when the next trigger prediction is convenient, the Flink cluster can directly call the time sequence prediction model stored in the Hbase cluster to conduct data prediction.
When training the propset model, differential ADF test is firstly performed on input data of the propset model, whether the data is in a stable time sequence is judged, if not, differential processing is performed on the input data, the processed stable data starts training, and n-order differential and ADF test formulas are described above and are not repeated here.
In the Prophet model, the data growth type, seasonal period, holidays and other influencing factors can be customized according to the data types of different environments and equipment parameters, and as more super parameters need to be regulated, a genetic algorithm can be introduced to optimize the super parameters of the Prophet model, the optimized super parameter values can be determined, the model prediction effect can be improved, and finally the accuracy of the Prophet model after training can be checked by adopting Root Mean Square Error (RMSE), mean Absolute Percentage Error (MAPE) and Mean Absolute Error (MAE), wherein the smaller the RMSE, the MAPE and the MAE are, the higher the model accuracy is represented.
The propset principle formula is expressed as follows:
y(t)=g(t)+s(t)+h(t)+∈t
wherein g (t), s (t), h (t) respectively represent data growth type influence factor items, seasonal period influence factor items, holiday influence factor items, and e t represents adjustment items.
The formulas for RMSE, MAPE and MAE are as follows:
Where RMSE denotes root mean square error, y i denotes the i-th data in the output data sequence, Represents an average value of each data in the output data sequence, n represents the number of data in the output data sequence,The i-th data in the real data sequence (output label data sequence) corresponding to the output data sequence is represented.
On the basis of the technical scheme, before the historical data sequence of the equipment in the target historical time period is input into the time sequence prediction model when reaching the preset time, the method further comprises the step of receiving the preset time, the target historical time period and the target future time period set by a user.
The preset time, the target historical time period and the target future time period of the time sequence prediction model support the user-defined setting, and a user can set through the early warning platform, for example, the user can set historical data, the predicted time period and the predicted time interval in the platform by himself, so that the target historical time period, the target future time period and the preset time for triggering the prediction set by the user are obtained. If the user does not make a setting, the data in the future week can be predicted by default with the data in the history of one year, with predictions made every other day.
The machine room monitoring method provided by the embodiment of the application can be executed based on the machine room monitoring early warning platform. Fig. 5 is a schematic structural diagram of a machine room monitoring and early warning platform in an embodiment of the present application, and as shown in fig. 5, the machine room monitoring and early warning platform may include a digital twin module, a data acquisition module, a big data module, an intelligent analysis module, an anomaly reporting module and an information management module.
The digital twin module is used for constructing and rendering a three-dimensional model of a physical machine room, interacting with the large data module, mapping environment, equipment and other data into the digital twin body one by one to realize unified, global and visual man-machine interaction, the data acquisition module is used for acquiring the environment data, equipment operation data and other data of the machine room in real time and sending the acquired data to the large data module, the large data module is used for constructing a Hadoop large data cluster, constructing a distributed and real-time processing frame, providing an operation environment for data processing analysis and prediction, finally sending the data to the digital twin module, the intelligent analysis module is used for data processing analysis and predicting the data by utilizing TensorFlow, prophet models and operating on the basis of the large data module, the abnormal reporting module is used for notifying an operation and maintenance person of abnormal alarms and recording the abnormal alarms in an alarm log, and the information management module is used for storing the environment, the equipment and user information of the machine room.
The digital twin module is respectively connected with the big data module and the information management module, the data acquisition module is connected with the big data module, the big data module is respectively connected with the digital twin module, the data acquisition module, the intelligent analysis module, the abnormal reporting module and the information management module, the intelligent analysis module is connected with the big data module, the abnormal reporting module is connected with the information management module, and the information management module is connected with the big data module.
The digital twin module may include a data twin unit and a data mapping unit. The data twin body unit builds and renders a digital twin body of a target machine room (an actual physical machine room) by using a Blender modeling tool, interacts with the data mapping unit, performs three-dimensional modeling on the target machine room, builds corresponding three-dimensional objects on a cabinet, various sensors, a distribution frame, network equipment, data equipment, transmission equipment, power equipment and the like in the target machine room, builds corresponding sub-module three-dimensional objects according to functional entities of corresponding equipment, and realizes the control and other operations on the equipment. The data mapping unit is used for receiving the data in the big data module, sending the data to the digital twin body unit, rendering the digital twin body in the WEB application by utilizing the Vue framework and the three.js engine, mapping the data into the digital twin body, and displaying the data in the three-dimensional object of the corresponding equipment.
The data acquisition module may include an environmental information acquisition unit and a device information acquisition unit. The environment information acquisition unit is used for acquiring environment data of the target machine room, acquiring the environment data by means of a sensor, a camera and the like, and sending the environment data to the big data module. The equipment information acquisition unit is used for acquiring equipment operation data of the target machine room, acquiring the equipment operation data by means of an equipment data interface and the like, and sending the equipment operation data to the big data module.
The big data module is mainly a Hadoop cluster and can comprise a basic cluster unit, a Kafka cluster unit, a Flink cluster unit and an Hbase cluster unit. The whole Hadoop cluster adopts a mode of one Master and two slaves, and is deployed based on three CentOS servers, namely Master, slave1 and Slave 2.
The basic cluster unit is used for Zookeeper, HDFS, yarn cluster building. The Zookeeper cluster is deployed in three servers and used for guaranteeing data consistency in a distributed environment, the HDFS cluster is deployed in the three servers and deployed by adopting a high-availability HA mode, so that the single-point failure problem of Namenode is effectively avoided, the availability and reliability of the Namenode are improved, and the Yarn cluster is deployed in the three servers and provides uniform resource management and scheduling for task operation.
The Kafka cluster unit is used for receiving and transmitting data and is deployed in three servers. The Flink cluster unit is used for executing batch processing and stream processing of data, is deployed in three servers, adopts Flink On Yarn mode deployment, can utilize a resource scheduling mechanism of a Yarn cluster to complete resource allocation, avoids JobManager single-point fault problems, and realizes high availability. The Hbase cluster unit is used for storing data, is deployed in three servers, operates based on the HDFS, and utilizes the HDFS as a bottom file storage system, and the data is stored in the HDFS.
The intelligent analysis module may include a data processing unit and a data prediction unit, and operate based on the big data module, and the operation flow of the intelligent analysis module may refer to fig. 6. The data processing unit is used for simply processing data acquired in real time, such as data of a device data interface, a sensor, a camera and the like, distributing the data to the Flink cluster for processing, analyzing whether the data is abnormal, directly returning the analyzed data to the Kafka cluster, mapping the data to a digital twin body, facilitating real-time monitoring of a user, and sending the data to the data prediction unit and the abnormality reporting module if the data is abnormal. The data prediction unit is used for training historical data of environments, equipment and the like and predicting future data, predicting the data in a week in the future by defaulting to data in the history of one year, predicting every other day, supporting self-definition, enabling a user to set the historical data, a predicted time period and a predicted time interval in a platform by himself, triggering a Prophet model to retrain when the data acquired in real time are abnormal, enabling the retrained model to be stored in an Hbase database after the use of TensorFlow frames to run in the Flink cluster, enabling the Flink cluster to directly call the Prophet model for prediction without retrained model when the next triggering and enabling the predicted future data (predicted equipment operation data sequence) to be directly returned to the Kafka cluster to be mapped to a digital twin body, and highlighting the abnormal predicted data.
The exception reporting module may include an exception notification unit and a log recording unit. The abnormality notification unit is used for sending the fault information and the early warning information to the target personnel in the forms of mobile phones, mails and the like. The log record unit is used for storing fault information and early warning information into the Hbase database.
The information management module may include an environment information unit, a device information unit, and a user information unit. The environment information unit is used for storing information such as temperature, humidity and rack of the environment of the target machine room, the equipment information unit is used for storing information such as model, position and configuration of equipment, and the user information unit is used for storing information such as name, mobile phone number and mailbox of the machine room and corresponding target personnel of the equipment.
The embodiment of the application adopts a digital twin technology, and the Blender, vue and three.js are used for carrying out three-dimensional modeling and rendering on the machine room environment and equipment, so as to construct a digital twin body of the target machine room, and provide a global and visual machine room monitoring and interaction means.
According to the embodiment of the application, the Hadoop big data frame and the Flink real-time flow processing frame are adopted, so that the real-time processing analysis of the acquired data is realized, and the real-time prediction of the machine room and the equipment state is carried out by combining with the Prophet time sequence prediction model, so that the occurrence of faults can be effectively reduced and prevented, the monitoring efficiency, accuracy and reliability are improved, and the working efficiency and productivity of operation and maintenance personnel are improved.
Fig. 7 is a schematic structural diagram of a machine room monitoring device according to an embodiment of the present application, as shown in fig. 7, where the device includes:
A digital twin body construction module 710, configured to construct a digital twin body of a target machine room according to equipment information of the target machine room, where the digital twin body includes a three-dimensional model of the target machine room and a three-dimensional object of each equipment in the target machine room;
the data acquisition module 720 is configured to acquire environmental data of the target machine room, and acquire device operation data of each device in the target machine room;
A first display module 730, configured to display the digital twin, display the environmental data in the digital twin, and map device operation data of each device to a three-dimensional object of a corresponding device in the digital twin for display;
The data prediction module 740 is configured to, for each device, input, when a preset time is reached, a historical data sequence of the device in a target historical time period into a time sequence prediction model, and determine, according to the time sequence prediction model, a predicted device operation data sequence of the device in a target future time period;
And the second display module 750 is configured to display the abnormal prediction data in the three-dimensional object corresponding to the device if the abnormal prediction data exists in the operation data sequence of the prediction device.
Optionally, the second display module includes:
And the distinguishing and displaying unit is used for distinguishing and displaying the abnormal prediction data and the equipment operation data in the three-dimensional object corresponding to the equipment.
Optionally, the time series prediction model is a propset model.
Optionally, the machine room monitoring method is executed by a Hadoop cluster;
The Hadoop clusters comprise a Zookeeper cluster, an HDFS cluster, a Yarn cluster, a Kafka cluster, a Flink cluster and an Hbase cluster;
the Zookeeper cluster is used for guaranteeing the consistency of data in the Hadoop cluster;
The HDFS cluster is used as a bottom file storage system;
The Yarn cluster is used for carrying out resource scheduling for the execution of data processing tasks, and the data processing tasks comprise tasks for determining the operation data sequence of the prediction equipment;
the Kafka cluster is used for executing the receiving and transmitting of the data in the Hadoop cluster;
the Flink cluster is used for executing batch processing and stream processing of data in the Hadoop cluster;
the Hbase cluster is used for storing the environment data, the equipment operation data and the time sequence prediction model, and based on the operation of the HDFS cluster, the HDFS cluster is used as a bottom file storage system.
Optionally, the data prediction module includes:
the model loading unit is used for loading the time sequence prediction model from the Hbase cluster through the Flink cluster;
And the data prediction unit is used for inputting the historical data sequence into a time sequence prediction model through the Flink cluster, and determining a predicted equipment operation data sequence of the equipment in a target future time period through the time sequence prediction model.
Optionally, the apparatus further includes:
And the early warning sending module is used for generating early warning information comprising abnormal data if the abnormal data exist in the equipment operation data of each equipment and sending the early warning information to a target person.
Optionally, the apparatus further includes:
And the model retraining module is used for retraining the time sequence prediction model according to the abnormal data if the abnormal data exists in the equipment operation data of each equipment, and storing the retrained time sequence prediction model.
Optionally, the apparatus further includes:
and the prediction setting module is used for receiving the preset time, the target historical time period and the target future time period set by a user.
The machine room monitoring device provided by the embodiment of the application is used for realizing each step of the machine room monitoring method provided by the embodiment of the application, and specific implementation modes of each module of the device refer to corresponding steps and are not repeated here.
According to the machine room monitoring device provided by the embodiment of the application, the digital twin body of the target machine room is constructed according to the equipment information of the target machine room, the environment data of the target machine room is obtained, the equipment operation data of each equipment in the target machine room is obtained, the digital twin body is displayed, the environment data is displayed in the digital twin body, the equipment operation data of each equipment are mapped to the three-dimensional object of the corresponding equipment in the digital twin body for displaying, when each equipment reaches the preset time, the historical data sequence of the equipment in the target historical time period is input into the time sequence prediction model, the predicted equipment operation data sequence of the equipment in the target future time period is determined through the time sequence prediction model, if abnormal data exists in the predicted equipment operation data sequence, the abnormal data is displayed in the three-dimensional object corresponding to the equipment, the real-time visual monitoring of each equipment in the machine room is realized through the display of the environment data in the digital twin body and the equipment operation data in the three-dimensional object corresponding to the equipment, the time sequence prediction model can predict the equipment operation data in the target future time period, and the abnormal data can be displayed in the three-dimensional object corresponding to the equipment in the digital twin body when the predicted equipment operation data exists, and the fault can be effectively prevented.
Fig. 8 is a schematic structural diagram of an electronic device according to an embodiment of the present application, and as shown in fig. 8, the electronic device 800 may include one or more processors 810 and one or more memories 820 connected to the processors 810. Electronic device 800 may also include an input interface 830 and an output interface 840 for communicating with another apparatus or system. Program code executed by processor 810 may be stored in memory 820.
The processor 810 in the electronic device 800 invokes the program code stored in the memory 820 to perform the room monitoring method in the above-described embodiment.
The embodiment of the application also provides a computer readable storage medium, on which a computer program is stored, which when being executed by a processor, implements the steps of the machine room monitoring method according to the embodiment of the application.
The embodiment of the application also provides a computer program product which realizes the steps of the machine room monitoring method according to the embodiment of the application when being executed by a processor.
In this specification, each embodiment is described in a progressive manner, and each embodiment is mainly described by differences from other embodiments, and identical and similar parts between the embodiments are all enough to be referred to each other. For the device embodiments, since they are substantially similar to the method embodiments, the description is relatively simple, and reference is made to the description of the method embodiments for relevant points.
The foregoing describes a method, an apparatus, an electronic device, and a storage medium for monitoring a machine room in detail, and specific examples are applied to describe the principles and implementations of the present application, and the description of the foregoing examples is only for aiding in understanding the method and core concept of the present application, and meanwhile, to those skilled in the art, according to the concept of the present application, there are variations in the specific implementations and application ranges, so that the disclosure should not be construed as limiting the scope of the present application.
From the above description of the embodiments, it will be apparent to those skilled in the art that the embodiments may be implemented by means of software plus necessary general hardware platforms, or may be implemented by hardware. Based on this understanding, the foregoing technical solution may be embodied essentially or in a part contributing to the prior art in the form of a software product, which may be stored in a computer readable storage medium, such as ROM/RAM, a magnetic disk, an optical disk, etc., including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the method described in the respective embodiments or some parts of the embodiments.
Claims (11)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411420284.XA CN119439825A (en) | 2024-10-11 | 2024-10-11 | Computer room monitoring method, device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411420284.XA CN119439825A (en) | 2024-10-11 | 2024-10-11 | Computer room monitoring method, device, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN119439825A true CN119439825A (en) | 2025-02-14 |
Family
ID=94506733
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202411420284.XA Pending CN119439825A (en) | 2024-10-11 | 2024-10-11 | Computer room monitoring method, device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN119439825A (en) |
-
2024
- 2024-10-11 CN CN202411420284.XA patent/CN119439825A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11847130B2 (en) | Extract, transform, load monitoring platform | |
| Peres et al. | IDARTS–Towards intelligent data analysis and real-time supervision for industry 4.0 | |
| US20210194767A1 (en) | Systems and methods for adaptive industrial internet of things (iiot) edge platform | |
| US11409962B2 (en) | System and method for automated insight curation and alerting | |
| US10713307B2 (en) | Dynamic search engine for an industrial environment | |
| US11567783B2 (en) | Data format transformation for downstream processing in a data pipeline | |
| US20190369984A1 (en) | Edge Computing Platform | |
| US9143563B2 (en) | Integrated and scalable architecture for accessing and delivering data | |
| CN112581303A (en) | Artificial intelligence channel for industrial automation | |
| CN112580813A (en) | Contextualization of industrial data at the device level | |
| CN112579653A (en) | Progressive contextualization and analysis of industrial data | |
| US20160132538A1 (en) | Crawler for discovering control system data in an industrial automation environment | |
| Wang et al. | Task offloading in cloud-edge collaboration-based cyber physical machine tool | |
| Peres et al. | A highly flexible, distributed data analysis framework for industry 4.0 manufacturing systems | |
| Han et al. | RT-DAP: A real-time data analytics platform for large-scale industrial process monitoring and control | |
| Yahouni et al. | A smart reporting framework as an application of multi-agent system in machining industry | |
| CN117311982A (en) | Digital twin body display method, system, device and computer equipment | |
| Hung et al. | Development of an advanced manufacturing cloud for machine tool industry based on AVM technology | |
| CN112904807B (en) | Industrial analysis system, method, and non-transitory computer readable medium | |
| US20250004451A1 (en) | Asset risk predictor of operation of an industrial asset | |
| CN119439825A (en) | Computer room monitoring method, device, electronic equipment and storage medium | |
| Corallo et al. | Processing Big Data in streaming for fault prediction: an industrial application | |
| Subramaniam et al. | Automated resource scaling in Kubeflow through time series forecasting | |
| US12380011B2 (en) | Methods and systems for sensor-assisted monitoring of temporal state of device | |
| US20240272625A1 (en) | Automated data transfer between automation systems and the cloud |
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 |