CN117768495A - Hydropower station auxiliary machine state edge monitoring method and system - Google Patents
Hydropower station auxiliary machine state edge monitoring method and system Download PDFInfo
- Publication number
- CN117768495A CN117768495A CN202311474692.9A CN202311474692A CN117768495A CN 117768495 A CN117768495 A CN 117768495A CN 202311474692 A CN202311474692 A CN 202311474692A CN 117768495 A CN117768495 A CN 117768495A
- Authority
- CN
- China
- Prior art keywords
- hydropower station
- fitness
- edge node
- data
- identification
- 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
- 238000012544 monitoring process Methods 0.000 title claims abstract description 147
- 238000000034 method Methods 0.000 title claims abstract description 58
- 230000005540 biological transmission Effects 0.000 claims abstract description 64
- 238000012549 training Methods 0.000 claims abstract description 44
- 238000011156 evaluation Methods 0.000 claims abstract description 32
- 238000006243 chemical reaction Methods 0.000 claims abstract description 23
- 238000012545 processing Methods 0.000 claims abstract description 21
- 230000010354 integration Effects 0.000 claims description 29
- 238000004364 calculation method Methods 0.000 claims description 22
- 238000004891 communication Methods 0.000 claims description 18
- 230000002159 abnormal effect Effects 0.000 claims description 15
- 238000012216 screening Methods 0.000 claims description 15
- 238000000354 decomposition reaction Methods 0.000 claims description 10
- 238000001514 detection method Methods 0.000 claims description 9
- 230000003993 interaction Effects 0.000 claims description 4
- 238000004458 analytical method Methods 0.000 abstract description 4
- 238000012423 maintenance Methods 0.000 description 12
- 230000008569 process Effects 0.000 description 6
- 230000008439 repair process Effects 0.000 description 5
- 238000012360 testing method Methods 0.000 description 5
- 238000005457 optimization Methods 0.000 description 4
- 239000000498 cooling water Substances 0.000 description 3
- 238000010801 machine learning Methods 0.000 description 3
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 3
- 238000007689 inspection Methods 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 238000013515 script Methods 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000013136 deep learning model Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000011990 functional testing Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000011056 performance test Methods 0.000 description 1
- 230000002195 synergetic effect Effects 0.000 description 1
Landscapes
- Testing And Monitoring For Control Systems (AREA)
Abstract
The application provides a hydropower station auxiliary machine state edge monitoring method and system, and relates to the technical field of state monitoring, wherein the method comprises the following steps: firstly acquiring a sensor integrated module, then acquiring information of auxiliary machines of a distributed hydropower station, then performing edge fitness evaluation to acquire first fitness, acquiring an identification edge node if the first fitness is not met, acquiring a protocol conversion instruction, establishing a transmission protocol of the auxiliary machines of the distributed hydropower station and the identification edge node, training a hydropower station fault identification model, embedding the hydropower station fault identification model in the identification edge node, and generating fault reminding information. The method mainly solves the problems that potential faults are difficult to monitor, are easily affected by human factors, are low in efficiency, cannot be monitored in real time and find faults in time. The data of real-time monitoring and data acquisition are transmitted to the edge computing equipment for processing and analysis, so that the reliability and stability of equipment operation are improved.
Description
Technical Field
The application relates to the technical field of state monitoring, in particular to a hydropower station auxiliary machine state edge monitoring method and system.
Background
The background of the hydropower station auxiliary machine state edge monitoring method mainly aims at the problems of state monitoring and fault diagnosis of hydropower station auxiliary machine equipment. The hydropower station auxiliary equipment comprises auxiliary equipment of a hydroelectric generating set, such as a water inlet valve, a butterfly valve, a volute, a draft tube, a cooling water system and the like. These devices play a very important role in the operation of the hydropower station, and if a fault occurs, the operation of the entire hydropower station is seriously affected.
In the traditional monitoring of the state of auxiliary equipment of a hydropower station, regular maintenance and inspection are usually adopted, and although some obvious faults can be found by the method, the faults are difficult to find for some potential early faults. In addition, this conventional method requires a great deal of manual intervention, is inefficient, and is susceptible to human factors.
However, in the process of implementing the technical scheme of the invention in the embodiment of the application, the inventor of the application finds that at least the following technical problems exist in the above technology:
the traditional mode is difficult to monitor potential faults, is easily influenced by human factors, has low efficiency, can not monitor in real time, and can discover the problems of faults in time.
Disclosure of Invention
The method mainly solves the problems that potential faults are difficult to monitor, are easily affected by human factors, are low in efficiency, cannot be monitored in real time and find faults in time.
In view of the above problems, the present application provides a method and a system for monitoring a state edge of a hydropower station auxiliary machine, and in a first aspect, the present application provides a method for monitoring a state edge of a hydropower station auxiliary machine, where the method includes: the sensor integration module is integrated by a plurality of sensor groups, and each sensor group is in communication connection with the hydropower station auxiliary machine; acquiring information of auxiliary machines of a distributed hydropower station, and performing edge fitness evaluation based on a data monitoring terminal of the auxiliary machines of the distributed hydropower station to acquire a first fitness; when the first fitness does not meet the preset fitness, acquiring an identification edge node, and acquiring a protocol conversion instruction based on the identification edge node; the protocol conversion instruction is used for converting a transmission protocol between the distributed hydropower station auxiliary machine and the data monitoring terminal, establishing a transmission protocol between the distributed hydropower station auxiliary machine and the identification edge node, and transmitting data obtained by monitoring the sensor integrated module arranged on the distributed hydropower station auxiliary machine to the identification edge node; training a hydropower station fault identification model, and embedding the hydropower station fault identification model into the identification edge node; and generating fault reminding information according to the identification edge node.
In a second aspect, the present application provides a hydropower station auxiliary machine state edge monitoring system, the system comprising: the communication connection module is used for acquiring a sensor integration module, the sensor integration module is integrated by a plurality of sensor groups, and each sensor group is in communication connection with the hydropower station auxiliary machine; the first fitness acquisition module is used for acquiring information of the distributed hydropower station auxiliary machines, carrying out edge fitness evaluation based on the data monitoring terminals of the distributed hydropower station auxiliary machines, and acquiring first fitness; the protocol conversion instruction acquisition module is used for acquiring an identification edge node when the first fitness does not meet a preset fitness and acquiring a protocol conversion instruction based on the identification edge node; the transmission protocol establishment module is used for converting the transmission protocol of the distributed hydropower station auxiliary machine and the data monitoring terminal, establishing the transmission protocol of the distributed hydropower station auxiliary machine and the identification edge node, and transmitting the data obtained by monitoring by the sensor integration module arranged on the distributed hydropower station auxiliary machine to the identification edge node; the failure recognition model acquisition module is used for training a hydropower station failure recognition model and embedding the hydropower station failure recognition model into the identification edge node; the fault reminding information generation module is used for generating fault reminding information according to the identification edge node.
One or more technical solutions provided in the present application have at least the following technical effects or advantages:
the application provides a hydropower station auxiliary machine state edge monitoring method and system, and relates to the technical field of state monitoring, wherein the method comprises the following steps: firstly acquiring a sensor integrated module, then acquiring information of auxiliary machines of a distributed hydropower station, then performing edge fitness evaluation to acquire first fitness, acquiring an identification edge node if the first fitness is not met, acquiring a protocol conversion instruction, establishing a transmission protocol of the auxiliary machines of the distributed hydropower station and the identification edge node, training a hydropower station fault identification model, embedding the hydropower station fault identification model in the identification edge node, and generating fault reminding information.
The method mainly solves the problems that potential faults are difficult to monitor, are easily affected by human factors, are low in efficiency, cannot be monitored in real time and find faults in time. The data of real-time monitoring and data acquisition are transmitted to the edge computing equipment for processing and analysis, so that the reliability and stability of equipment operation are improved.
The foregoing description is merely an overview of the technical solutions of the present application, and may be implemented according to the content of the specification in order to make the technical means of the present application more clearly understood, and in order to make the above-mentioned and other objects, features and advantages of the present application more clearly understood, the following detailed description of the present application will be given.
Drawings
For a clearer description of the technical solutions of the present application or of the prior art, the drawings used in the description of the embodiments or of the prior art will be briefly described below, it being obvious that the drawings in the description below are only exemplary and that other drawings can be obtained, without inventive effort, by a person skilled in the art from the drawings provided.
Fig. 1 is a schematic flow chart of a hydropower station auxiliary machine state edge monitoring method according to an embodiment of the application;
fig. 2 is a schematic flow chart of a method for outputting a first fitness in a hydropower station auxiliary machine state edge monitoring method according to an embodiment of the present application;
fig. 3 is a schematic flow chart of a method for obtaining an identified edge node in a hydropower station auxiliary machine state edge monitoring method according to an embodiment of the present application;
fig. 4 is a schematic structural diagram of an edge monitoring system for a state of an auxiliary machine of a hydropower station according to an embodiment of the application.
Reference numerals illustrate: the system comprises a communication connection module 10, a first adaptability acquisition module 20, a protocol conversion instruction acquisition module 30, a transmission protocol establishment module 40, a fault identification model acquisition module 50 and a fault reminding information generation module 60.
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 only some, but not all, of the embodiments of the present application. All other embodiments, which can be made by one of ordinary skill in the art without undue burden from the present disclosure, are within the scope of the present disclosure.
The method mainly solves the problems that potential faults are difficult to monitor, are easily affected by human factors, are low in efficiency, cannot be monitored in real time and find faults in time. The data of real-time monitoring and data acquisition are transmitted to the edge computing equipment for processing and analysis, so that the reliability and stability of equipment operation are improved.
For a better understanding of the foregoing technical solutions, the following detailed description will be given with reference to the accompanying drawings and specific embodiments of the present invention:
example 1
The method for monitoring the state edge of the hydropower station auxiliary machine as shown in fig. 1 comprises the following steps:
the sensor integration module is integrated by a plurality of sensor groups, and each sensor group is in communication connection with the hydropower station auxiliary machine;
specifically, hydropower station auxiliary machinery equipment to be monitored is determined, including but not limited to, water inlet valves, butterfly valves, volutes, draft tubes, cooling water systems, and the like. And selecting proper sensor types and quantity according to the equipment to be monitored, and determining the installation position and connection mode of each sensor. The selected sensors are mounted to the hydropower station auxiliary equipment in a defined manner and each sensor is ensured to accurately monitor the required state parameters. Each sensor is connected with the edge computing device through a communication line, so that efficient transmission and processing of data are realized. And installing corresponding data processing and analysis software on the edge computing equipment, processing and analyzing the sensor data, and sending out fault early warning and alarm information in time. Through the steps, a sensor integrated module formed by integrating a plurality of sensor groups can be obtained, and each sensor group is in communication connection with the hydropower station auxiliary machine, so that the real-time monitoring and data acquisition of the state of the sensor group are realized. The sensor integrated module can greatly improve the reliability and stability of equipment operation and reduce the operation cost and maintenance difficulty.
Acquiring information of auxiliary machines of a distributed hydropower station, and performing edge fitness evaluation based on a data monitoring terminal of the auxiliary machines of the distributed hydropower station to acquire a first fitness;
specifically, information of the distributed hydropower station auxiliary machines is acquired, and the types and the number of the distributed hydropower station auxiliary machines are determined, including but not limited to a hydroelectric generating set, a water inlet valve, a butterfly valve, a volute, a draft tube, a cooling water system and the like. And carrying out edge fitness evaluation on the data monitoring terminals based on the distributed hydropower station auxiliary machine, determining evaluation indexes and evaluation standards, and testing and evaluating the data monitoring terminals, wherein the performance test, the functional test and the like under different environmental conditions are included. And according to the test and evaluation results, evaluating the edge fitness of the data monitoring terminal, and according to the evaluation results, selecting the data monitoring terminal with the highest edge fitness. And further testing and verifying the data monitoring terminal to confirm that the performance and the function of the data monitoring terminal meet the monitoring requirement of auxiliary machines of the distributed hydropower station. The data monitoring terminal is deployed on a distributed hydropower station auxiliary machine, and real-time monitoring and management are performed. And (3) periodically carrying out inspection and maintenance on the data monitoring terminal so as to ensure the normal operation and the data accuracy of the data monitoring terminal. The information of the distributed hydropower station auxiliary machines can be obtained, and the data monitoring terminals based on the distributed hydropower station auxiliary machines are subjected to edge fitness evaluation to obtain first fitness.
As shown in fig. 2, in the method, edge fitness evaluation is performed based on the data monitoring terminal of the auxiliary machine of the distributed hydropower station, and the method further includes:
acquiring a calculation power detection index and a capacity task quantity index of the data monitoring terminal;
acquiring a required calculation power upper limit index and a training task quantity index for training a hydropower station fault identification model;
establishing an adaptability evaluation network layer according to the calculation power detection index, the capacity task quantity index, the required calculation power upper limit index and the training task quantity index, and outputting calculation power adaptability and task adaptability based on the adaptability evaluation network layer;
outputting the first fitness according to the computational power fitness and the task fitness;
the first fitness is the fitness of identifying the data monitoring terminal as an edge node for training and executing the hydropower station fault identification model.
Specifically, an calculation power detection index and a capacity task amount index of the data monitoring terminal are obtained: calculating force detection indexes: this typically includes CPU usage, GPU usage, memory usage, etc., which may be obtained by specific monitoring software or operating system tools. The capacity task quantity index: this refers to the number of tasks that the data monitoring terminal can handle, which can be obtained by actual testing or by consulting an equipment manual. Acquiring a required calculation power upper limit index and a training task quantity index for training a hydropower station fault identification model: the required calculation power upper limit index: depending on the machine learning or deep learning model used, as well as the complexity and number of parameters of the model. These indices may be determined experimentally or empirically. Training task volume index: this is generally dependent on the size and complexity of the training data, as well as the time and memory required for model training. Establishing a fitness evaluation network layer according to the calculation power detection index, the capacity task quantity index, the required calculation power upper limit index and the training task quantity index: this may involve complex computational and optimization procedures, such as using neural networks or other machine learning methods to predict whether the computational power and task processing capabilities of the data monitoring terminals meet the requirements for training a hydropower station fault recognition model. Based on the fitness evaluation network layer, outputting the computational power fitness and the task fitness: calculating the force adaptability: this indicates whether the computational effort of the data monitoring terminal is sufficient to support training of the hydropower station fault identification model. Task fitness: this represents whether the data monitoring terminal has sufficient capacity to handle the tasks required for hydropower station failure recognition model training. Outputting a first fitness according to the computational power fitness and the task fitness: first fitness: the method is a comprehensive index, and represents the adaptation degree of the data monitoring terminal serving as an edge node training execution hydropower station fault identification model. It may be based on a weighted average of the fitness of the computing force and the fitness of the task or other more complex computing methods. The goal of this process is to find the edge node that is most suitable for training the hydropower station failure recognition model. By the method, the model can be ensured to operate as efficiently as possible under limited resources, so that the reliability and stability of equipment operation are improved, and the operation cost and maintenance difficulty are reduced.
When the first fitness does not meet the preset fitness, acquiring an identification edge node, and acquiring a protocol conversion instruction based on the identification edge node;
specifically, when the first fitness does not satisfy the preset fitness, a cause of the first fitness not satisfying the preset fitness, such as insufficient performance of the data monitoring terminal, sensor failure, or the like, is determined. Depending on the reasons, aspects that need to be optimized, such as replacing high performance data monitoring terminals, adjusting sensor parameters, etc., are determined. And determining the identification edge nodes, namely edge computing equipment or nodes capable of realizing the optimization target, according to the optimization requirement. Based on the identification edge node, a protocol conversion instruction, namely an optimization scheme and measures aiming at the identification edge node, is obtained. And according to the protocol conversion instruction, optimizing and improving the identification edge node so as to improve the edge fitness and the performance of the identification edge node. The method can optimize and improve problems existing in the information monitoring system of the auxiliary machine of the distributed hydropower station by acquiring the identification edge node and acquiring the protocol conversion instruction based on the identification edge node, and improves the edge fitness and performance of the system so as to meet the requirement of preset fitness.
The protocol conversion instruction is used for converting a transmission protocol between the distributed hydropower station auxiliary machine and the data monitoring terminal, establishing a transmission protocol between the distributed hydropower station auxiliary machine and the identification edge node, and transmitting data obtained by monitoring the sensor integrated module arranged on the distributed hydropower station auxiliary machine to the identification edge node;
specifically, the protocol conversion instruction is used for converting the transmission protocol of the distributed hydropower station auxiliary machine and the data monitoring terminal, and establishing the transmission protocol of the distributed hydropower station auxiliary machine and the identification edge node. And determining the transmission protocol types of the distributed hydropower station auxiliary machines and the data monitoring terminals, such as an industrial communication protocol of Modbus, profibus, CAN. And selecting a proper protocol converter or gateway for converting the transmission protocol of the distributed hydropower station auxiliary machine and the data monitoring terminal. According to the requirements of the identified edge node and the support of the protocol converter, a proper communication protocol and connection mode are selected, such as a network communication protocol of TCP/IP, UDP and the like. And converting the transmission protocol of the auxiliary machine of the distributed hydropower station and the data monitoring terminal into a communication protocol and a connection mode supported by the identification edge node through a protocol converter or a gateway. And establishing a transmission protocol of the distributed hydropower station auxiliary machine and the identification edge node, wherein the transmission protocol comprises parameters such as data transmission format, data type, data rate and the like. And transmitting the monitored data to the identification edge node through a sensor integrated module arranged on the auxiliary machine of the distributed hydropower station. The received data is processed, analyzed and stored at the identified edge node and transmitted to other systems or devices for further processing and application as needed. Through the protocol conversion instruction, the conversion of the data transmission protocol between the distributed hydropower station auxiliary machine and the data monitoring terminal can be realized, and stable communication connection with the identification edge node is established. This helps to improve the reliability and stability of data transmission while reducing the cost and maintenance difficulty of data transmission.
Training a hydropower station fault identification model, and embedding the hydropower station fault identification model into the identification edge node;
specifically, a hydropower station fault recognition model is trained, the model is embedded into an identification edge node, and operation data and fault data of auxiliary machines of the hydropower station are collected, wherein the operation data and the fault data comprise state data, fault history data and the like obtained through monitoring by a sensor integration module. The collected data is utilized to train a hydropower station fault recognition model, and algorithms such as machine learning, deep learning and the like can be used for training the model. In the training process, the model needs to be optimized and adjusted, including feature selection, design of a model structure, adjustment of super parameters and the like. After training, embedding the model obtained by training into the identification edge node, and embedding the model code into an operating system or an application program of the identification edge node. And running a hydropower station fault identification model in the identification edge node, carrying out real-time monitoring and fault identification on the received data, and timely finding potential faults and problems. And according to the output result of the model, adopting corresponding measures to perform fault processing and repair, such as sending out an alarm, performing repair operation and the like. By embedding the hydropower station fault identification model into the identification edge node, real-time monitoring and fault early warning of the hydropower station auxiliary machine can be realized, the reliability and stability of equipment operation are improved, and the operation cost and maintenance difficulty are reduced. Meanwhile, the model can be updated and optimized according to actual conditions, so that the identification accuracy and performance of the model can be improved.
And generating fault reminding information according to the identification edge node.
Specifically, according to the identification edge node, generating fault reminding information, running a hydropower station fault identification model in the identification edge node, and carrying out real-time monitoring and fault identification on the received data. If a potential fault or problem is found, the hydropower station fault identification model outputs corresponding fault information or alarm information. The outputted fault information or alarm information is collated and formatted, for example, the information is converted into a text format or JSON format. And sending the formatted fault information or alarm information to a corresponding fault reminding system, for example, notifying by means of an email, a short message, a telephone and the like. The fault reminding system can send corresponding fault reminding information to related personnel, such as equipment maintenance personnel, technicians, management personnel and the like, according to the received fault information or alarm information. The related personnel can carry out corresponding processing and repair according to the received fault reminding information, such as checking the equipment state, carrying out maintenance operation and the like. By generating the fault reminding information, the fault or problem of the auxiliary machine of the hydropower station can be timely notified to related personnel, the efficiency and accuracy of equipment maintenance are improved, and the loss and risk caused by the fault are reduced. Meanwhile, the fault reminding information can be customized and optimized according to actual conditions so as to meet the requirements of different users.
Further, the method of the present application further comprises:
when the first fitness meets the preset fitness, configuring the data monitoring terminal as an edge node;
embedding the hydropower station fault recognition model into the data monitoring terminal, wherein the data monitoring terminal receives the data obtained by monitoring the sensor integration module, inputs the data into the hydropower station fault recognition model for recognition, and generates fault reminding information.
Specifically, when the first fitness meets the preset fitness, the first fitness is confirmed to meet the preset fitness, which indicates that the data monitoring terminal has enough computing power and task processing capacity to train and run the hydropower station fault identification model. The configuration data monitoring terminal acts as an edge node, which may be done by writing a corresponding configuration script or using a special configuration tool. The configuration content comprises a target position of designating the data monitoring terminal as an edge node, network connection parameters, a data transmission protocol and the like. The hydropower station fault identification model is embedded in the data monitoring terminal, and the hydropower station fault identification model can be realized by embedding codes and related configuration information of the model into an operating system or an application program of the data monitoring terminal. After embedding, the data monitoring terminal can receive the data obtained by monitoring the sensor integrated module and input the data into a hydropower station fault recognition model for recognition. And running a hydropower station fault identification model at the data monitoring terminal, and carrying out fault identification and prediction on the model according to the input data to generate corresponding fault reminding information. Such information may include fault type, location, possible cause, suggested repair measures, etc. The data monitoring terminal can send the generated fault reminding information to related fault processing personnel or systems so as to provide timely fault response and processing. By configuring the data monitoring terminal as an edge node and embedding the hydropower station fault identification model therein, real-time monitoring and fault early warning of the hydropower station auxiliary machine can be realized, the reliability and stability of equipment operation are improved, and the operation cost and maintenance difficulty are reduced.
Further, as shown in fig. 3, the method of the present application further includes:
acquiring a data transmission route of the sensor integrated module;
screening according to the data transmission route to obtain a first-stage transmission node, wherein the first-stage transmission node is a node for directly receiving data sent by the sensor integration module;
evaluating each first-stage transmission node by utilizing the fitness evaluation network layer to acquire a plurality of fitness, wherein each fitness corresponds to one first-stage transmission node;
and screening nodes based on the plurality of fitness to obtain the identification edge nodes.
In particular, the data transmission route of the sensor integration module is acquired, which may be determined according to an actual hardware connection or a network communication protocol. The data transmission route may be considered as a data flow path from the sensor integration module to the data monitoring terminal or edge node. And screening according to the data transmission route to obtain the first-stage transmission node. The first-stage transmission node refers to a node directly receiving data after the data is sent out by the sensor integrated module, and is usually directly connected with the sensor integrated module. The evaluation of each first level transmission node by the fitness evaluation network layer can be performed based on the aforementioned indicators such as the computational fitness and the task fitness. Through evaluation, a plurality of fitness degrees can be obtained, and each fitness degree corresponds to one first-stage transmission node. And node screening is performed based on a plurality of fitness, and a node with higher fitness can be selected as an identification edge node. The nodes have higher edge fitness, and can better process and transmit data of the hydropower station auxiliary machine, so that the requirements of a distributed hydropower station auxiliary machine monitoring system are met. The data transmission route of the sensor integrated module is obtained, the first-stage transmission nodes are screened according to the data transmission route, and the adaptability evaluation network layer is utilized for evaluation and screening, so that equipment suitable for being used as an identification edge node can be determined, and the efficiency and the reliability of the monitoring system of the auxiliary machine of the distributed hydropower station are improved.
Further, in the method, node screening is performed based on the plurality of fitness degrees, and the identified edge node is obtained, and the method further includes:
acquiring a first edge node in the plurality of fitness degrees, wherein the fitness of the first edge node is highest;
judging whether the first edge node meets the preset fitness or not, and if the first edge node meets the preset fitness, outputting the first edge node as an identification edge node;
and if the edge node does not meet the preset fitness, configuring a newly added edge node.
Specifically, a first edge node of the plurality of fitness levels is acquired, and the node with the highest fitness level is generally selected as the identified edge node. In this way, the selected nodes can be ensured to have higher edge fitness, and data of the hydropower station auxiliary machine can be better processed and transmitted. Judging whether the first edge node meets the preset fitness, and if so, outputting the first edge node as an identification edge node. The preset fitness here may be set according to actual requirements, and may include requirements in terms of computing power, task processing capacity, data transmission quality, and the like. If the first edge node does not meet the preset fitness, a newly added edge node can be configured. The number and the positions of the newly added edge nodes are determined according to the requirements of the system and the layout of the auxiliary machines of the distributed hydropower station. The newly added edge nodes are configured and initialized, which may include installing the necessary software and drivers, setting network connection parameters, assigning IP addresses, etc. The addition of the newly added edge node to the distributed hydropower station auxiliary machine monitoring system can be achieved by writing corresponding scripts or using special software tools. And testing and verifying the newly added edge node to ensure that the newly added edge node can work normally and meet the requirement of preset fitness. If the newly added edge node still does not meet the requirement of the preset fitness, the configuration and adjustment can be continued until the requirement is met. By configuring the newly added edge nodes, the edge fitness and the performance of the system can be increased, so that the requirement of a distributed hydropower station auxiliary machine monitoring system can be met. Meanwhile, the newly added edge nodes can be optimized and adjusted according to actual conditions so as to improve the edge fitness and the performance of the newly added edge nodes.
Further, in the method of the present application, if the edge node does not meet the preset fitness, the method further includes:
if the first edge node does not meet the preset fitness, identifying a cooperative relationship among the first-stage transmission nodes to obtain a first edge node and a second edge node, wherein the second edge node is in data interaction with the first edge node;
decomposing a training task for training a hydropower station fault identification model to obtain a first decomposing task table and a second decomposing task table;
and receiving data of the sensor integration module by using the first edge node and the second edge node, and carrying out cooperative processing according to the first decomposition task table and the second decomposition task table respectively.
Specifically, when the first edge node does not meet the preset fitness, the cooperative relationship between the first-stage transmission nodes is identified, and the first edge node and the second edge node are obtained. The first edge node and the second edge node are here node pairs for data interaction. Decomposing a training task for training a hydropower station fault identification model to obtain a first decomposing task list and a second decomposing task list. These decomposition task tables may be formulated based on the performance of the nodes and the characteristics of the tasks. And receiving data of the sensor integrated module by using the first edge node and the second edge node, and performing cooperative processing according to the first decomposition task table and the second decomposition task table respectively. This means that the first edge node and the second edge node will process different tasks according to the resolved task table, respectively, and process data through the synergistic relationship. The training tasks are decomposed, the cooperative processing capacity of a plurality of edge nodes is utilized, the requirement of preset fitness can be better met, and the performance and efficiency of the monitoring system of the auxiliary machine of the distributed hydropower station are improved. Meanwhile, the decomposition task table can be adjusted and optimized according to actual conditions so as to meet the requirements of different scenes.
Further, according to the method of the present application, according to the identified edge node, a fault reminding message is generated, and the method further includes:
acquiring temperature monitoring data, vibration monitoring data, current monitoring data and voltage monitoring data according to the sensor integration module;
inputting the temperature monitoring data, the vibration monitoring data, the current monitoring data and the voltage monitoring data into a hydropower station fault identification model embedded in the identification edge node to synchronously identify all hydropower station auxiliary machines, and obtaining N fault risk indexes;
and screening abnormal hydropower station auxiliary machines from the N fault risk indexes, wherein the abnormal hydropower station auxiliary machines are hydropower station auxiliary machines with the largest deviation degree of the fault risk indexes, and generating fault reminding information by the abnormal hydropower station auxiliary machines.
Specifically, temperature monitoring data, vibration monitoring data, current monitoring data and voltage monitoring data are obtained according to the sensor integration module. These data are all important parameters for the operation of the hydropower station auxiliary machinery, and are very important for judging the state of the auxiliary machinery and identifying faults. And inputting the temperature monitoring data, the vibration monitoring data, the current monitoring data and the voltage monitoring data into a hydropower station fault identification model embedded in the identification edge node, and synchronously identifying all hydropower station auxiliary machines. Through calculation and analysis of the model, N fault risk indexes can be obtained. And screening abnormal hydropower station auxiliary machines from the N fault risk indexes. The abnormal hydropower station auxiliary machine refers to the hydropower station auxiliary machine with the largest deviation of the failure risk index. By comparing the risk of failure index with a preset threshold or reference value, it is possible to determine which hydropower station auxiliary machines are abnormal. Generating fault reminding information by using the abnormal hydropower station auxiliary machine. Such information may include fault type, location, possible cause, suggested repair measures, etc. By sending the fault reminding information to related personnel or systems, fault response and processing can be timely carried out, and operation cost and maintenance difficulty are reduced. The real-time monitoring and fault early warning of the auxiliary machine of the hydropower station can be realized by acquiring the data of the sensor integrated module and inputting the data into the hydropower station fault identification model. Meanwhile, the abnormal hydropower station auxiliary machines are screened according to the N fault risk indexes, so that the fault positions and types can be more accurately positioned, and the maintenance efficiency is improved.
Example two
Based on the same inventive concept as the hydropower station auxiliary machine state edge monitoring method of the foregoing embodiment, as shown in fig. 4, the present application provides a hydropower station auxiliary machine state edge monitoring system, which includes:
the communication connection module 10 is used for acquiring a sensor integration module, wherein the sensor integration module is integrated by a plurality of sensor groups, and each sensor group is in communication connection with the hydropower station auxiliary machine;
the first fitness acquiring module 20 is used for acquiring information of the distributed hydropower station auxiliary machine, and performing edge fitness evaluation based on a data monitoring terminal of the distributed hydropower station auxiliary machine to acquire first fitness;
a protocol conversion instruction obtaining module 30, where the protocol conversion instruction obtaining module 30 is configured to obtain an identification edge node when the first fitness does not meet a preset fitness, and obtain a protocol conversion instruction based on the identification edge node;
the transmission protocol establishment module 40 is the protocol conversion instruction, and is used for converting the transmission protocol between the distributed hydropower station auxiliary machine and the data monitoring terminal, establishing the transmission protocol between the distributed hydropower station auxiliary machine and the identification edge node, and transmitting the data obtained by monitoring by the sensor integration module arranged on the distributed hydropower station auxiliary machine to the identification edge node;
the failure recognition model acquisition module 50 is used for training a hydropower station failure recognition model, and embedding the hydropower station failure recognition model into the identification edge node;
the fault reminding information generating module 60 is configured to generate fault reminding information according to the identified edge node by the fault reminding information generating module 60.
Further, the system further comprises:
the first fitness output module is used for acquiring the calculation power detection index and the capacity task quantity index of the data monitoring terminal; acquiring a required calculation power upper limit index and a training task quantity index for training a hydropower station fault identification model; establishing an adaptability evaluation network layer according to the calculation power detection index, the capacity task quantity index, the required calculation power upper limit index and the training task quantity index, and outputting calculation power adaptability and task adaptability based on the adaptability evaluation network layer; outputting the first fitness according to the computational power fitness and the task fitness; the first fitness is the fitness of identifying the data monitoring terminal as an edge node for training and executing the hydropower station fault identification model.
Further, the system further comprises:
the fault reminding information generation module is used for configuring the data monitoring terminal as an edge node when the first fitness meets the preset fitness; embedding the hydropower station fault recognition model into the data monitoring terminal, wherein the data monitoring terminal receives the data obtained by monitoring the sensor integration module, inputs the data into the hydropower station fault recognition model for recognition, and generates fault reminding information.
Further, the system further comprises:
the identification edge node acquisition module is used for acquiring a data transmission route of the sensor integration module; screening according to the data transmission route to obtain a first-stage transmission node, wherein the first-stage transmission node is a node for directly receiving data sent by the sensor integration module; evaluating each first-stage transmission node by utilizing the fitness evaluation network layer to acquire a plurality of fitness, wherein each fitness corresponds to one first-stage transmission node; and screening nodes based on the plurality of fitness to obtain the identification edge nodes.
Further, the system further comprises:
the newly added edge node configuration module is used for acquiring a first edge node in the plurality of fitness degrees, wherein the fitness of the first edge node is highest; judging whether the first edge node meets the preset fitness or not, and if the first edge node meets the preset fitness, outputting the first edge node as an identification edge node; and if the edge node does not meet the preset fitness, configuring a newly added edge node.
Further, the system further comprises:
the cooperative processing module is used for identifying the cooperative relationship among the first-stage transmission nodes if the first edge node does not meet the preset fitness to acquire a first edge node and a second edge node, wherein the second edge node is in data interaction with the first edge node; decomposing a training task for training a hydropower station fault identification model to obtain a first decomposing task table and a second decomposing task table; and receiving data of the sensor integration module by using the first edge node and the second edge node, and carrying out cooperative processing according to the first decomposition task table and the second decomposition task table respectively.
Further, the system further comprises:
generating a fault reminding information module by using an abnormal hydropower station auxiliary machine, wherein the fault reminding information module is used for acquiring temperature monitoring data, vibration monitoring data, current monitoring data and voltage monitoring data according to the sensor integration module; inputting the temperature monitoring data, the vibration monitoring data, the current monitoring data and the voltage monitoring data into a hydropower station fault identification model embedded in the identification edge node to synchronously identify all hydropower station auxiliary machines, and obtaining N fault risk indexes; and screening abnormal hydropower station auxiliary machines from the N fault risk indexes, wherein the abnormal hydropower station auxiliary machines are hydropower station auxiliary machines with the largest deviation degree of the fault risk indexes, and generating fault reminding information by the abnormal hydropower station auxiliary machines.
Through the detailed description of the method for monitoring the state edge of the hydropower station auxiliary machine, a person skilled in the art can clearly know the state edge monitoring system of the hydropower station auxiliary machine in the embodiment, and for the system disclosed in the embodiment, the description is relatively simple because the system corresponds to the device disclosed in the embodiment, and relevant places refer to the description of the method.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (8)
1. The method for monitoring the state edge of the hydropower station auxiliary machine is characterized by comprising the following steps:
the sensor integration module is integrated by a plurality of sensor groups, and each sensor group is in communication connection with the hydropower station auxiliary machine;
acquiring information of auxiliary machines of a distributed hydropower station, and performing edge fitness evaluation based on a data monitoring terminal of the auxiliary machines of the distributed hydropower station to acquire a first fitness;
when the first fitness does not meet the preset fitness, acquiring an identification edge node, and acquiring a protocol conversion instruction based on the identification edge node;
the protocol conversion instruction is used for converting a transmission protocol between the distributed hydropower station auxiliary machine and the data monitoring terminal, establishing a transmission protocol between the distributed hydropower station auxiliary machine and the identification edge node, and transmitting data obtained by monitoring the sensor integrated module arranged on the distributed hydropower station auxiliary machine to the identification edge node;
training a hydropower station fault identification model, and embedding the hydropower station fault identification model into the identification edge node;
and generating fault reminding information according to the identification edge node.
2. The method of claim 1, wherein the edge fitness evaluation is performed based on a data monitoring terminal of the distributed hydropower station auxiliary machine, the method further comprising:
acquiring a calculation power detection index and a capacity task quantity index of the data monitoring terminal;
acquiring a required calculation power upper limit index and a training task quantity index for training a hydropower station fault identification model;
establishing an adaptability evaluation network layer according to the calculation power detection index, the capacity task quantity index, the required calculation power upper limit index and the training task quantity index, and outputting calculation power adaptability and task adaptability based on the adaptability evaluation network layer;
outputting the first fitness according to the computational power fitness and the task fitness;
the first fitness is the fitness of identifying the data monitoring terminal as an edge node for training and executing the hydropower station fault identification model.
3. The method of claim 2, wherein the method further comprises:
when the first fitness meets the preset fitness, configuring the data monitoring terminal as an edge node;
embedding the hydropower station fault recognition model into the data monitoring terminal, wherein the data monitoring terminal receives the data obtained by monitoring the sensor integration module, inputs the data into the hydropower station fault recognition model for recognition, and generates fault reminding information.
4. The method of claim 2, wherein the method further comprises:
acquiring a data transmission route of the sensor integrated module;
screening according to the data transmission route to obtain a first-stage transmission node, wherein the first-stage transmission node is a node for directly receiving data sent by the sensor integration module;
evaluating each first-stage transmission node by utilizing the fitness evaluation network layer to acquire a plurality of fitness, wherein each fitness corresponds to one first-stage transmission node;
and screening nodes based on the plurality of fitness to obtain the identification edge nodes.
5. The method of claim 4, wherein node screening is performed based on the plurality of fitness levels to obtain an identified edge node, the method further comprising:
acquiring a first edge node in the plurality of fitness degrees, wherein the fitness of the first edge node is highest;
judging whether the first edge node meets the preset fitness or not, and if the first edge node meets the preset fitness, outputting the first edge node as an identification edge node;
and if the edge node does not meet the preset fitness, configuring a newly added edge node.
6. The method of claim 5, wherein if the edge node does not meet the predetermined fitness, the method further comprises:
if the first edge node does not meet the preset fitness, identifying a cooperative relationship among the first-stage transmission nodes to obtain a first edge node and a second edge node, wherein the second edge node is in data interaction with the first edge node;
decomposing a training task for training a hydropower station fault identification model to obtain a first decomposing task table and a second decomposing task table;
and receiving data of the sensor integration module by using the first edge node and the second edge node, and carrying out cooperative processing according to the first decomposition task table and the second decomposition task table respectively.
7. The method of claim 1, wherein generating fault alert information based on the identified edge node, the method further comprises:
acquiring temperature monitoring data, vibration monitoring data, current monitoring data and voltage monitoring data according to the sensor integration module;
inputting the temperature monitoring data, the vibration monitoring data, the current monitoring data and the voltage monitoring data into a hydropower station fault identification model embedded in the identification edge node to synchronously identify all hydropower station auxiliary machines, and obtaining N fault risk indexes;
and screening abnormal hydropower station auxiliary machines from the N fault risk indexes, wherein the abnormal hydropower station auxiliary machines are hydropower station auxiliary machines with the largest deviation degree of the fault risk indexes, and generating fault reminding information by the abnormal hydropower station auxiliary machines.
8. Hydropower station auxiliary machine state edge monitoring system, characterized in that the system comprises:
the communication connection module is used for acquiring a sensor integration module, the sensor integration module is integrated by a plurality of sensor groups, and each sensor group is in communication connection with the hydropower station auxiliary machine;
the first fitness acquisition module is used for acquiring information of the distributed hydropower station auxiliary machines, carrying out edge fitness evaluation based on the data monitoring terminals of the distributed hydropower station auxiliary machines, and acquiring first fitness;
the protocol conversion instruction acquisition module is used for acquiring an identification edge node when the first fitness does not meet a preset fitness and acquiring a protocol conversion instruction based on the identification edge node;
the transmission protocol establishment module is used for converting the transmission protocol of the distributed hydropower station auxiliary machine and the data monitoring terminal, establishing the transmission protocol of the distributed hydropower station auxiliary machine and the identification edge node, and transmitting the data obtained by monitoring by the sensor integration module arranged on the distributed hydropower station auxiliary machine to the identification edge node;
the failure recognition model acquisition module is used for training a hydropower station failure recognition model and embedding the hydropower station failure recognition model into the identification edge node;
the fault reminding information generation module is used for generating fault reminding information according to the identification edge node.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311474692.9A CN117768495A (en) | 2023-11-07 | 2023-11-07 | Hydropower station auxiliary machine state edge monitoring method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311474692.9A CN117768495A (en) | 2023-11-07 | 2023-11-07 | Hydropower station auxiliary machine state edge monitoring method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117768495A true CN117768495A (en) | 2024-03-26 |
Family
ID=90315131
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311474692.9A Pending CN117768495A (en) | 2023-11-07 | 2023-11-07 | Hydropower station auxiliary machine state edge monitoring method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117768495A (en) |
-
2023
- 2023-11-07 CN CN202311474692.9A patent/CN117768495A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110221558B (en) | Electro-hydraulic servo valve online fault diagnosis gateway based on edge computing technology | |
| CA2564724C (en) | Automatic remote monitoring and diagnostics system and communication method for communicating between a programmable logic controller and a central unit | |
| CN111597204A (en) | AI technology-based intelligent operation and maintenance knowledge analysis method | |
| JP2020123951A (en) | Method, apparatus, and device, for predicting failure of optical module | |
| CN108268023B (en) | Remote fault diagnosis method and system for rail transit platform door | |
| US11906112B2 (en) | Methods for safety management of compressors in smart gas pipeline network and internet of things systems thereof | |
| CN112734977B (en) | Equipment risk early warning system and algorithm based on Internet of things | |
| CN115453254B (en) | Power quality monitoring method and system based on special transformer acquisition terminal | |
| CN111124852A (en) | Fault prediction method and system based on BMC health management module | |
| KR20220073314A (en) | A System and Method for Monitoring Manufacturing Process | |
| CN117289085A (en) | Multi-line fault analysis and diagnosis method and system | |
| CN117354171B (en) | Platform health condition early warning method and system based on Internet of things platform | |
| CN115827411A (en) | Online monitoring and operation and maintenance evaluation system and method for automation equipment | |
| CN117768495A (en) | Hydropower station auxiliary machine state edge monitoring method and system | |
| CN110537347B (en) | Method and central computer for detecting and determining the probability of failure of a radio network | |
| CN116863664A (en) | Real-time monitoring method and system for gas equipment | |
| CN115788771A (en) | Intelligent operation and maintenance management system of wind power generation system based on Internet of things technology | |
| KR102411915B1 (en) | System and method for froviding real time monitering and ai diagnosing abnormality sign for facilities and equipments | |
| CN110596586B (en) | Motor current waveform analysis method based on Alexnet algorithm | |
| CN117560300B (en) | Intelligent internet of things flow prediction and optimization system | |
| CN110232482B (en) | Equipment management method and device based on neural network | |
| CN118101429A (en) | Power distribution network communication fault diagnosis method and system | |
| CN117914734A (en) | Gateway equipment switching method and system based on data analysis | |
| CN118052653A (en) | System evaluation method for effect of distributed power supply accessing to power distribution network | |
| CN116415149A (en) | Multi-data fusion predictive fault diagnosis method |
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 |