Intelligent management and control method, system and equipment for high-voltage circuit breaker and storage medium

Abstract

The invention relates to an intelligent management and control method, system and device for a high-voltage circuit breaker and a storage medium, and relates to the field of high-voltage circuit breakers, and the method comprises the steps: obtaining electrical data in real time, the electrical data being data corresponding to electrical parameters in a power network where the high-voltage circuit breaker is located; preprocessing the electrical data, inputting the electrical data into a pre-constructed adaptive learning model, analyzing the electrical data through the adaptive learning model, and outputting an optimal decision scheme; the high-voltage circuit breaker is controlled to execute the optimal decision scheme, and the optimal decision scheme at least comprises opening / closing operation of the high-voltage circuit breaker and / or adjustment of working parameter values of the high-voltage circuit breaker. According to the invention, the high-voltage circuit breaker can be efficiently managed and controlled in a complex and changeable electric power environment.

Description

Technical Field

[0001] The present application relates to the field of high - voltage circuit breakers, and in particular to an intelligent control method, system, device and storage medium for a high - voltage circuit breaker. Background Art

[0002] With the continuous expansion of the scale of the power system and the progress of technology, traditional manual or semi - automatic circuit breakers have been difficult to meet the needs of modern complex power networks. Most of the existing high - voltage circuit breaker control systems rely on preset operating procedures and fixed time intervals for switching operations, lacking the ability to flexibly respond to various emergencies; therefore, in the face of different power loads and environmental changes, these traditional systems often exhibit characteristics such as slow response, high failure rate, and high maintenance cost. Therefore, researching and developing a more intelligent, efficient, and reliable high - voltage circuit breaker control system has become an urgent need in the current power industry.

[0003] Currently, the more common high - voltage circuit breaker control solutions on the market are mainly time - periodic inspection methods. However, although this method can detect problems regularly, it cannot monitor potential safety hazards in real time and cannot achieve timely and efficient control of high - voltage circuit breakers, so it needs to be improved. Summary of the Invention

[0004] In order to achieve efficient control of high - voltage circuit breakers in a complex and changeable power environment, the present application provides an intelligent control method, system, device and storage medium for high - voltage circuit breakers.

[0005] In a first aspect, the present application provides an intelligent control method for a high - voltage circuit breaker, including: Obtaining electrical data in real time, where the electrical data is data corresponding to electrical parameters in the power network where the high - voltage circuit breaker is located; After pre - processing the electrical data, inputting it into a pre - constructed adaptive learning model, and outputting an optimal decision - making scheme by analyzing the electrical data through the adaptive learning model; Controlling the high - voltage circuit breaker to execute the optimal decision - making scheme, where the optimal decision - making scheme at least includes opening / closing operations of the high - voltage circuit breaker and / or adjusting the working parameter values of the high - voltage circuit breaker.

[0006] By adopting the above technical solution, various electrical data (such as current, voltage, temperature, instantaneous power factor, three-phase unbalance degree, harmonic content, etc.) generated in the power network where the high-voltage circuit breaker is located are monitored in real time. Then, after the electrical data is initially processed, it is input into a pre-constructed adaptive learning model, and an adaptive learning algorithm included in the adaptive learning model and pre-trained is used to identify the current power environment (i.e., the working scenario where the high-voltage circuit breaker is located) based on the current electrical data, and a decision-making plan is output. It is considered that when the high-voltage circuit breaker executes this decision-making plan, the high-voltage circuit breaker will reach the best working state in the current power environment, so as to realize the adaptive adjustment of the working state of the high-voltage circuit breaker according to the changeable and complex power environment, and the adjustment method is more intelligent and efficient than the manual intervention adjustment method.

[0007] Optionally, the output of the optimal decision-making plan after the adaptive learning model analyzes the electrical data includes: The adaptive learning model screens out the working scenarios matching the electrical data from a pre-constructed experience knowledge base, and outputs the decision-making plan corresponding to the working scenario as the optimal decision-making plan; wherein, the experience knowledge base at least includes several working scenarios, and each working scenario corresponds to an electrical data set. The method further includes: Regularly analyze the electrical data obtained in a specified period by using a pre-constructed interpolation model to generate virtual data related to the electrical data; Whenever virtual data is generated, input the virtual data into the adaptive learning model so that it outputs the optimal decision-making plan corresponding to the virtual data; Send simulation information composed of the virtual data and its corresponding optimal decision-making plan to the client, and when the feedback content related to the simulation information sent by the client meets the preset value-added conditions, match the working scenario for the virtual data, and store the defined working scenario, its virtual data, and the optimal decision-making plan in the experience knowledge base.

[0008] By adopting the above technical solution, the interpolation model can regularly generate virtual data based on the existing actual electrical data, and analyze and obtain the optimal decision-making scheme corresponding to the virtual data with the help of the adaptive learning model. The virtual data refers to electrical data whose specific numerical values are different from those of the actually obtained electrical data. The simulation information composed of the virtual data and its corresponding optimal decision-making scheme will be sent to the client for the client operator to feedback and decide whether to store it as a data sample in the experience knowledge base. If so (that is, the feedback content meets the preset value-added conditions), a working scenario will be matched for the virtual data (the working scenario here is a newly added working scenario), and the virtual data and its corresponding optimal decision-making scheme will be used to expand the experience knowledge base and optimize the learning and decision-making ability of the adaptive learning model.

[0009] Optionally, the electrical data at least includes grid load data and the working state data corresponding to the high-voltage circuit breaker; The method further includes: Using a pre-constructed grid load change model to predict the low-power consumption stage in real time based on the change of the grid load data; Using a pre-constructed fault risk prediction model to predict the potential fault occurrence time period in real time based on the electrical data of the high-voltage circuit breaker, and determining the maintenance time based on the low-power consumption stage, so that the maintenance time is within the low-power consumption time period and earlier than the fault occurrence time period; Feedback the maintenance time to the client for the client maintenance personnel to know the maintenance time of the high-voltage circuit breaker.

[0010] By adopting the above technical solution, the health status of the high-voltage circuit breaker is monitored and evaluated by analyzing historical data, and possible faults or abnormal conditions are predicted. Further, the maintenance time is determined for the maintenance personnel. And since the probability of the power network generating a fault and requiring the high-voltage circuit breaker to be put into use is relatively low during the low-power consumption stage, therefore, this application proposes to intelligently schedule the pre-inspection and maintenance work of the high-voltage circuit breaker during the predicted low-power consumption time period, so as to place the maintenance time of the high-voltage circuit breaker during the low-power consumption stage to reduce the load on the power network.

[0011] Optionally, after using the pre-constructed fault risk prediction model to predict the potential fault occurrence time period in real time based on the electrical data of the high-voltage circuit breaker, it further includes: Communicate and dock with a preset energy consumption platform to obtain the energy consumption data of the high-voltage circuit breaker monitored in real time by the energy consumption platform; Based on the energy consumption data and a preset risk investigation list, determine the incentives affecting the energy consumption of the high-voltage circuit breaker. When the energy consumption data exceeds the preset range, send the energy consumption data exceeding the preset range and its corresponding incentives to the client; wherein, the incentives at least include the upper limit of the high-voltage circuit breaker's lifespan, frequent switching of the high-voltage circuit breaker's working state, and abnormal working environment.

[0012] By adopting the above technical solution, docking with the energy consumption platform and sharing resources to form a more extensive ecosystem closed-loop; in addition, this solution can use the energy consumption data of the high-voltage circuit breaker monitored by the energy consumption platform as the basis for judging the health of the high-voltage circuit breaker, realizing the efficient and intelligent maintenance of the high-voltage circuit breaker; furthermore, since too high or too low ambient temperature, the presence of corrosive gases or dust in the environment, etc. will also affect the energy consumption of the high-voltage circuit breaker, the above solution also provides a new way of judging whether the working environment is abnormal.

[0013] Optionally, the method further includes: Analyze the operating stability of the power network and the high-voltage circuit breaker based on the electrical data, and adjust the learning step size of the adaptive learning model based on the operating stability, and make the higher the operating stability, the shorter the corresponding learning step size.

[0014] By adopting the above technical solution, dynamically adjusting the learning step size is an effective way for the adaptive learning model to respond to changes in a real-time changing working environment. Specifically, when the electrical data in the real-time working environment fluctuates greatly, increase the learning step size so that the adaptive learning model can adapt to the new data faster, accelerate the convergence of the learning process, help the adaptive learning model capture the characteristics in the working environment in a timely manner, and adjust the model parameters to match the change; on the contrary, when the electrical data in the real-time working environment changes little, the learning step size can be shortened to ensure the stability of the adaptive learning model.

[0015] Optionally, the method further includes: Whenever the high-voltage circuit breaker executes the optimal decision-making scheme, monitor the response duration of the high-voltage circuit breaker. The response duration refers to the time taken for the high-voltage circuit breaker to complete the execution of the optimal decision-making scheme. Based on the response duration, timely adjust the acquisition frequency of the electrical data obtained in real time, and make the longer the response duration, the higher the adjusted acquisition frequency.

[0016] By adopting the above technical solution, as the working duration and service life of the high-voltage circuit breaker change, its corresponding response duration is also likely to change. In order to control the high-voltage circuit breaker to execute the corresponding optimal decision-making scheme more efficiently and timely, this application proposes that when acquiring electrical data, the acquisition frequency is adaptively adjusted based on the length of the response duration, so as to improve the time for the high-voltage circuit breaker to execute the optimal decision-making scheme as much as possible.

[0017] Optionally, the method further includes: Display the position distribution of the high-voltage circuit breaker in the power grid, and the working state of each high-voltage circuit breaker, where the working state at least includes the open / closed state of the high-voltage circuit breaker and the working parameter value of the high-voltage circuit breaker.

[0018] By adopting the above technical solution, displaying the distribution and working state of the high-voltage circuit breaker in the power grid can enable maintenance personnel and power control personnel to more intuitively and vividly understand the operating state of the power grid and the high-voltage circuit breaker.

[0019] In a second aspect, this application provides an intelligent control system for a high-voltage circuit breaker, including: An electrical data monitoring module for real-time acquiring electrical data, where the electrical data is the data corresponding to the electrical parameters in the power grid where the high-voltage circuit breaker is located; An adaptive learning module for preprocessing the electrical data and then inputting it into a pre-constructed adaptive learning model, and outputting an optimal decision-making scheme after analyzing the electrical data through the adaptive learning model; A decision-making regulation module for controlling the high-voltage circuit breaker to execute the optimal decision-making scheme, where the optimal decision-making scheme at least includes the open / close operation of the high-voltage circuit breaker and / or adjusting the working parameter value of the high-voltage circuit breaker.

[0020] In a third aspect, this application provides an intelligent control device for a high-voltage circuit breaker, including a memory and a processor, and a computer program capable of being loaded and executed by the processor and implementing any method described in the first aspect is stored on the memory.

[0021] In a fourth aspect, this application provides a computer-readable storage medium storing a computer program capable of being loaded and executed by the processor and implementing any method described in the first aspect.

[0022] In summary, this application includes at least one of the following beneficial technical effects: 1. In this application, by real-time monitoring various electrical data generated in the power network where the high-voltage circuit breaker is located (such as current, voltage, temperature, instantaneous power factor, three-phase unbalance degree, harmonic content, etc.), and then inputting the initially processed electrical data into a pre-constructed adaptive learning model, so as to identify the current power environment (i.e., the working scenario where the high-voltage circuit breaker is located) based on the current electrical data through the pre-trained adaptive learning algorithm included in the adaptive learning model, and output a decision-making plan. And it is considered that when the high-voltage circuit breaker executes this decision-making plan, the high-voltage circuit breaker will reach the best working state in the current power environment, so as to realize the adaptive adjustment of the working state of the high-voltage circuit breaker according to the variable and complex power environment, and the adjustment method is relatively more intelligent and efficient than the manual intervention adjustment method; 2. Further, by analyzing historical data to predict the monitoring and evaluation of the health status of the high-voltage circuit breaker, and predicting possible faults or abnormal conditions, and further determining the maintenance time for maintenance personnel. And since the probability of the power network generating a fault and the high-voltage circuit breaker being put into use is relatively low during the low electricity consumption period, therefore, this application proposes to intelligently schedule the pre-inspection and maintenance work of the high-voltage circuit breaker during the predicted low electricity consumption period, so as to place the maintenance time of the high-voltage circuit breaker during the low electricity consumption stage to reduce the load on the power network. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0024] Figure 1 It is a schematic flowchart of an intelligent control method for a high-voltage circuit breaker disclosed in an embodiment of this application.

[0025] Figure 2 It is a structural block diagram of an intelligent control system for a high-voltage circuit breaker disclosed in an embodiment of this application.

[0026] Description of the reference numerals: 201, electrical data monitoring module; 202, adaptive learning module; 203, decision-making and control module. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0027] The following will further elaborate on this application in combination with the attached Figure 1-2 to make a more detailed description of this application.

[0028] An embodiment of the present application discloses an intelligent control method for a high-voltage circuit breaker (hereinafter simply referred to as the intelligent control method), which is used to monitor the working environment where the high-voltage circuit breaker is located (i.e., the power network where the high-voltage circuit breaker is located) in real time, analyze and learn the changes in the corresponding working environment, and then adaptively and intelligently and efficiently adjust the working state of the high-voltage circuit breaker according to the changes, so that the high-voltage circuit breaker can adapt to the complex and changeable power grid environment and maintain the best working window sill in the corresponding working environment to maintain the stability of the power grid environment. The execution entity of the intelligent control method is the intelligent control system of the high-voltage circuit breaker (hereinafter simply referred to as the intelligent control system), and the following will be combined with the attached Figure 1 Specifically elaborate on the specific process steps for the intelligent control system to execute the intelligent control method.

[0029] S101, Obtain electrical data in real time, where the electrical data is the data corresponding to the electrical parameters in the power network where the high-voltage circuit breaker is located.

[0030] S102, After preprocessing the electrical data, input it into a pre-constructed adaptive learning model, and output an optimal decision-making plan by analyzing the electrical data through the adaptive learning model; Among them, "output an optimal decision-making plan by analyzing the electrical data through the adaptive learning model" in S102 includes: Through the adaptive learning model, screen out the working scenarios that match the electrical data from the pre-constructed experience knowledge base, and output the decision-making plan corresponding to the working scenario as the optimal decision-making plan; among them, the experience knowledge base includes at least several working scenarios, and each working scenario corresponds to an electrical data set.

[0031] S103, Control the high-voltage circuit breaker to execute the optimal decision-making plan, where the optimal decision-making plan at least includes the opening / closing operation of the high-voltage circuit breaker and / or adjusting the working parameter value of the high-voltage circuit breaker.

[0032] In implementation, the intelligent control system is pre-connected to several sensors in communication. The sensors are pre-deployed in the power network environment where the high-voltage circuit breaker is located to detect the electrical data in the power network environment. The electrical data described here includes both the electrical data generated during the operation of the power network itself (such as current data, voltage data, instantaneous power factor, three-phase unbalance degree, harmonic content, etc.) and the working state data of each high-voltage circuit breaker in the power network (such as current data, voltage data, temperature data, and mechanical state, etc.).

[0033] The intelligent control system is used to obtain the electrical data monitored by the aforementioned sensors according to a preset acquisition frequency. After performing preprocessing such as fine data cleaning and feature extraction on the electrical data, it is input into a pre-constructed adaptive learning model. The adaptive learning model is used to execute an adaptive learning algorithm that has been pre-trained and continuously iteratively optimized. For example, the adaptive learning algorithm in this embodiment is specifically a deep neural network algorithm. In other embodiments, it can also be a fuzzy control algorithm, etc. The adaptive learning model takes the electrical data as input and outputs an optimal decision-making scheme, which is a scheme for switching and regulating the working state of the high-voltage circuit breaker. Specifically, it is the opening / closing operation of the high-voltage circuit breaker and / or the adjustment of the working parameter values of the high-voltage circuit breaker.

[0034] The adaptive learning model is used to perform learning and analysis on the electrical data to divide the power network (hereinafter referred to as the working environment) where the high-voltage circuit breaker is located into different working scenarios, and store the electrical data used to describe the corresponding working scenarios in the form of a set (i.e., the electrical data set mentioned above) in a pre-constructed experience knowledge base. In other words, in the experience knowledge base, there are several electrical data sets stored, and the corresponding working scenario is the basis for distinguishing different electrical data sets (i.e., the label), and each working scenario corresponds to an optimal decision-making scheme, which is used to represent the best working state of the high-voltage circuit breaker in the corresponding working scenario. The optimal decision-making scheme stored in the experience knowledge base is the content obtained by training and converging the adaptive learning algorithm using the preprocessed data to describe the working state and parameter values of the high-voltage circuit breaker; in other embodiments, the intelligent control system can provide managers with the permission to access and edit the experience knowledge base, so that managers can, based on human experience, further edit and modify the specific content of the corresponding optimal decision-making scheme on the basis of the optimal decision-making scheme provided by the adaptive learning algorithm.

[0035] Optionally, the intelligent control method further includes the following steps: Regularly analyze the electrical data obtained in a specified period using a pre-constructed interpolation model to generate virtual data related to the electrical data; Whenever virtual data is generated, input the virtual data into the adaptive learning model so that it outputs the optimal decision-making scheme corresponding to the virtual data; Send simulation information composed of the virtual data and its corresponding optimal decision-making scheme to the client. When the feedback content related to the simulation information sent by the client meets the preset value-added conditions, match the working scenario for the virtual data, and store the defined working scenario, its virtual data, and the optimal decision-making scheme in the experience knowledge base.

[0036] In implementation, the interpolation model is used to analyze the changing trend of the acquired electrical data over time every specified period and predict the trend of the electrical data after the specified period, so as to generate virtual data. For example, first determine the change rate corresponding to the electrical data corresponding to any two adjacent acquisition times within the specified period, and then, based on the last electrical data within the specified period (hereinafter referred to as the reference data), each electrical data obtained by changing the reference data at each of the above change rates is used as virtual data. Then, the intelligent control system is used to input the virtual data into the adaptive learning model, and an optimal decision-making scheme corresponding to the virtual data is output through the adaptive learning model. Here, it should be noted that since the virtual data is newly generated and does not exist in the empirical knowledge base, therefore, the optimal decision-making scheme corresponding to it cannot be found in the empirical knowledge base. At this time, the adaptive learning algorithm included in the adaptive learning model is used to learn the virtual data and automatically generate the corresponding optimal decision-making scheme. That is to say, when using the adaptive learning model to match the corresponding optimal decision-making scheme for the electrical data in this application, it will first determine whether the electrical data is included in a certain electrical data set from the empirical knowledge base. If so, the optimal decision-making scheme corresponding to the electrical data set is used as the output of the adaptive learning model. If not, the learning and analysis technology of the adaptive learning algorithm itself is used to generate and output the optimal decision-making scheme.

[0037] The intelligent control system is also used to send the virtual data and its corresponding optimal decision-making scheme to the client (such as the intelligent terminal of the management personnel) for the management personnel to decide whether to include it in the empirical knowledge base (that is, to determine whether the feedback content sent by the client meets the preset value-added conditions). For example, the feedback content is compared with the specific content corresponding to the preset value-added conditions. If they are consistent, it is considered that the value-added conditions are met. At this time, the virtual data and its corresponding optimal scheme can be stored in the empirical knowledge base, and a new working scenario is defined for it to realize the expansion of the empirical knowledge base.

[0038] Optionally, the electrical data may also include the grid load data of the power network where the high-voltage circuit breaker is located. Correspondingly, the intelligent control method further includes the following steps: Using a pre-constructed grid load change model, predict the low-power consumption stage in real time based on the change of the grid load data; Using a pre-constructed fault risk prediction model, predict the potential fault occurrence time based on the electrical data of the high-voltage circuit breaker in real time, and determine the maintenance time based on the low-power consumption stage, so that the maintenance time is within the low-power consumption period and earlier than the fault occurrence time; Feedback the maintenance time to the client for the client maintenance personnel to know the maintenance time of the high-voltage circuit breaker; Communicate and interface with the preset energy consumption platform to obtain the energy consumption data of the high-voltage circuit breaker obtained by real-time monitoring of the energy consumption platform; Based on the energy consumption data and the preset risk investigation list, determine the incentives affecting the energy consumption of the high-voltage circuit breaker. When the energy consumption data exceeds the preset range, send the energy consumption data exceeding the preset range and its corresponding incentives to the client; among them, the incentives at least include the upper limit of the high-voltage circuit breaker's lifespan, frequent switching of the high-voltage circuit breaker's working state, and abnormal working environment.

[0039] In implementation, the power grid load change model is used to execute the power grid load prediction algorithm to fit and generate the curve of the power grid load data changing with time according to the power grid load data, and then use the time period corresponding to the trough in the change curve as the low-power consumption period. Since the power grid load prediction algorithm for the power grid load change trend and future power grid load data is an existing technology, it will not be elaborated here.

[0040] The fault risk prediction model is used to predict the possible fault abnormalities and the time when the corresponding fault abnormalities occur (i.e., the potential fault occurrence period) based on the working state data of the high-voltage circuit breaker in the historical period. Among them, the fault risk prediction model can specifically include an adaptive learning algorithm and PHM technology. Through the adaptive learning algorithm, learn the working state data corresponding to different faults of the high-voltage circuit breaker in the historical period, and at the same time use PHM to predict potential faults and their occurrence times. Then, set the maintenance time of the high-voltage circuit breaker through the intelligent control system, and limit the maintenance time to any low-power consumption period before the fault occurrence period to improve the maintenance efficiency. The intelligent control system is used to send the determined maintenance time to the client so that the client maintenance personnel can know the specific time recommended by the intelligent control system for maintaining the high-voltage circuit breaker.

[0041] In addition, the intelligent control system has also achieved communication docking with the energy consumption platform in advance. The energy consumption platform here integrates the real-time monitoring function of the high-voltage circuit breaker to track the energy consumption of the high-voltage circuit breaker. By analyzing the real-time energy consumption data, the energy consumption data that exceeds the preset stable energy consumption range (i.e., the energy consumption data that causes abnormal energy consumption of the high-voltage circuit breaker) and its corresponding high-voltage circuit breaker identity information are screened out, and the screened information is sent to the intelligent control system; the intelligent control system is used to determine the inducement affecting the energy consumption of the high-voltage circuit breaker according to the preset risk investigation list. Among them, it can be considered that the preset risk investigation list contains several inducements for affecting the energy consumption of the high-voltage circuit breaker (such as the upper limit of the high-voltage circuit breaker life, frequent switching of the working state of the high-voltage circuit breaker, and abnormal working environment mentioned above), and the induction conditions corresponding to the foregoing inducements. Among them, the induction condition is a preset determination content for judging whether the reason for the abnormal energy consumption of the high-voltage circuit breaker is the current inducement. Exemplarily, the induction condition corresponding to the inducement with the content of "frequent switching of the working state of the high-voltage circuit breaker" can be "the interval duration between the high-voltage circuit breaker executing the two most recent optimal decision-making schemes is less than the preset duration before the current time".

[0042] The induction condition corresponding to the inducement with the content of "abnormal working environment" is that "the temperature of the physical environment where the high-voltage circuit breaker is located exceeds the preset range, or the concentration of corrosive gases or particulate matter in the physical environment where it is located exceeds the standard". Next, the intelligent control system is used to judge one by one the induction conditions corresponding to the inducements in the preset risk investigation list, take the inducement that meets any induction condition as the inducement of the energy consumption data with abnormal energy consumption (i.e., the energy consumption data exceeding the preset range), and then send the inducement and its corresponding energy consumption data to the client for the client maintenance personnel to investigate and eliminate.

[0043] Optionally, the intelligent control method further includes the following steps: Based on the electrical data analysis, the operation stability of the power grid and the high-voltage circuit breaker is analyzed, and the learning step size of the adaptive learning model is adjusted based on the operation stability, and the higher the operation stability is, the shorter the corresponding learning step size is.

[0044] In implementation, the intelligent control system is used to calculate the difference between the electrical data corresponding to adjacent acquisition moments in real time, and determine the running stability based on this difference. For example, according to the preset corresponding relationship table of the difference range, the running stability level, and the learning step range, determine the difference range where the current difference is located, as well as the corresponding running stability level and learning step range. Here, the learning step can be regarded as the learning rate range of the adaptive learning model, which is a set containing several specific learning step values. And because the performance of the high-voltage circuit breaker changes with its working duration and service life, when determining the learning step, this application further proposes that the intelligent control system is used to take each of the learning step values included in this learning step range as the learning step of the adaptive learning model, and determine the performance indicators (such as accuracy rate, loss value, training time) of the adaptive learning model under each learning step, so as to determine the influence of the learning step on the adaptive learning model, and finally determine the learning step whose performance indicator parameters meet the preset best indicator requirements as the learning step of the adaptive learning model.

[0045] Optionally, the intelligent control method further includes the following steps: Whenever the high-voltage circuit breaker executes the optimal decision-making plan, monitor the response duration of the high-voltage circuit breaker. The response duration refers to the time taken for the high-voltage circuit breaker to complete the execution of the optimal decision-making plan. Based on the response duration, timely adjust the acquisition frequency of the electrical data obtained in real time, and make the longer the response duration, the higher the corresponding adjusted acquisition frequency.

[0046] Display the position distribution of the high-voltage circuit breakers in the power network, and the working status of each high-voltage circuit breaker. The working status at least includes the open / closed status of the high-voltage circuit breaker and the working parameter values of the high-voltage circuit breaker.

[0047] In implementation, start timing from when the high-voltage circuit breaker starts to execute the optimal decision-making plan until the execution of the optimal decision-making plan is completed. The timing duration is the response duration. Based on the several response duration ranges included in the preset corresponding relationship and the acquisition frequency corresponding to each response duration range, determine the acquisition frequency corresponding to the current response duration. Finally, the intelligent control system uses the currently determined acquisition frequency to obtain electrical data.

[0048] In addition, the intelligent control system is also used to provide a display function, and when receiving a query instruction sent by the client, display on the preset display interface the connection relationship and geographical location information of all power equipment in the power network where the high-voltage circuit breaker is located, as well as the connection relationship and geographical location information between the high-voltage circuit breaker and other power equipment in this power network, and the working status of each high-voltage circuit breaker.

[0049] The embodiment of the present application also discloses an intelligent control system for a high-voltage circuit breaker. It includes: An electrical data monitoring module 201, configured to obtain electrical data in real time, where the electrical data is data corresponding to electrical parameters in the power network where the high-voltage circuit breaker is located; An adaptive learning module 202, configured to preprocess the electrical data and then input it into a pre-constructed adaptive learning model. After analyzing the electrical data through the adaptive learning model, it outputs an optimal decision-making plan; A decision-making and control module 203, configured to control the high-voltage circuit breaker to execute the optimal decision-making plan, where the decision-making plan at least includes the opening / closing operation of the high-voltage circuit breaker and / or adjusting the working parameter values of the high-voltage circuit breaker.

[0050] Optionally, the adaptive learning module 202 is further configured to screen out a working scenario that matches the electrical data from a pre-constructed experience knowledge base through the adaptive learning model, and output the decision-making plan corresponding to the working scenario as the optimal decision-making plan; where the experience knowledge base at least includes several working scenarios, and each working scenario corresponds to an electrical data set; It further includes an interpolation module, configured to regularly analyze the electrical data obtained in a specified period by using a pre-constructed interpolation model to generate virtual data related to the electrical data; whenever virtual data is generated, input the virtual data into the adaptive learning model so that it outputs the optimal decision-making plan corresponding to the virtual data; it is also configured to send simulation information composed of the virtual data and its corresponding optimal decision-making plan to the client, and when the feedback content related to the simulation information sent by the client meets a preset value-added condition, match a working scenario for the virtual data, and store the defined working scenario, its virtual data, and the optimal decision-making plan in the experience knowledge base.

[0051] Optionally, it further includes a maintenance timing control module, configured to use a pre-constructed power grid load change model to predict the low-power consumption stage in real time based on the change of power grid load data; use a pre-constructed fault risk prediction model to predict the potential fault occurrence time based on the electrical data of the high-voltage circuit breaker in real time, and determine the maintenance time based on the low-power consumption stage, so that the maintenance time is within the low-power consumption period and earlier than the fault occurrence time; feedback the maintenance time to the client for the client maintenance personnel to know the maintenance time of the high-voltage circuit breaker.

[0052] Optionally, the maintenance timing control module is further configured to communicate and dock with a preset energy consumption platform to obtain the energy consumption data of the high-voltage circuit breaker monitored in real time by the energy consumption platform; based on the energy consumption data and a preset risk investigation list, determine the inducements affecting the energy consumption of the high-voltage circuit breaker, and when the energy consumption data exceeds the preset range, send the energy consumption data exceeding the preset range and its corresponding inducements to the client; wherein, the inducements at least include the upper limit of the high-voltage circuit breaker's lifespan, frequent switching of the high-voltage circuit breaker's working state, and abnormal working environment.

[0053] Optionally, it further includes a learning rate adjustment module, which is configured to analyze the power grid and the operation stability of the high-voltage circuit breaker based on electrical data, adjust the learning step of the adaptive learning model based on the operation stability, and make the corresponding learning step shorter when the operation stability is higher.

[0054] Optionally, it further includes an acquisition frequency adjustment module, which is configured to monitor the response duration of the high-voltage circuit breaker whenever the high-voltage circuit breaker executes the optimal decision-making scheme, where the response duration refers to the time taken for the high-voltage circuit breaker to complete the execution of the optimal decision-making scheme; it is also configured to adjust the acquisition frequency of the electrical data obtained in real time in a timely manner based on the response duration, and make the adjusted acquisition frequency higher when the response duration is longer.

[0055] Optionally, the status information display module is configured to display the position distribution of the high-voltage circuit breaker in the power grid and the working status of each high-voltage circuit breaker, and the working status at least includes the open / closed status of the high-voltage circuit breaker and the working parameter values of the high-voltage circuit breaker.

[0056] An embodiment of this application also discloses an intelligent control device for a high-voltage circuit breaker. The intelligent control device for the high-voltage circuit breaker includes a memory and a processor, and a computer program capable of being loaded and executed by the processor, such as the intelligent control method for the high-voltage circuit breaker as described above, is stored on the memory.

[0057] An embodiment of this application also discloses a computer-readable storage medium, which stores a computer program capable of being loaded and executed by the processor, such as the intelligent control method for the high-voltage circuit breaker as described above. The computer-readable storage medium includes, for example: various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memories (ROM), random access memories (RAM), magnetic disks, or optical discs.

[0058] It should be noted that in this article, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations.

[0059] The above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit the protection scope of the application. Obviously, the described embodiments are only some embodiments of the present application, rather than all embodiments. Based on these embodiments, all other embodiments obtained by those of ordinary skill in the art without making creative efforts shall fall within the scope to be protected by the present application.

Claims

1. An intelligent control method for a high voltage circuit breaker, characterized in that: include: Acquiring electrical data in real time, wherein the electrical data is data corresponding to electrical parameters in the power network where the high-voltage circuit breaker is located; After the electrical data is preprocessed, the input value is put into a pre-constructed adaptive learning model, and the adaptive learning model is used to analyze the electrical data and output an optimal decision solution; The high-voltage circuit breaker is controlled to execute the optimal decision-making scheme, wherein the optimal decision-making scheme at least includes an opening / closing operation of the high-voltage circuit breaker and / or adjusting an operating parameter value of the high-voltage circuit breaker.

2. The intelligent control method of high-voltage circuit breaker according to claim 1, characterized in that: The output of the optimal decision-making solution after analyzing the electrical data through the adaptive learning model includes: Screening out work scenarios matching the electrical data from a pre-built experience knowledge base through an adaptive learning model, and outputting the decision plan corresponding to the work scenario as the optimal decision plan; wherein the experience knowledge base includes at least a number of work scenarios, and each of the work scenarios corresponds to an electrical data set; The method further comprises: periodically analyzing electrical data acquired during a specified period using a pre-built interpolation model to generate virtual data related to the electrical data; Whenever virtual data is generated, the virtual data is adaptively applied to the learning model so that the model outputs the optimal decision solution corresponding to the virtual data; Send simulation information consisting of virtual data and its corresponding optimal decision plan to the client, and when the feedback content corresponding to the simulation information sent by the client meets the preset value-added conditions, match the virtual data with a work scene, and store the defined work scene and its virtual data and the optimal decision plan in the experience knowledge base.

3. The intelligent control method of high-voltage circuit breaker according to claim 1, characterized in that: The electrical data at least includes grid load data and working status data corresponding to the high-voltage circuit breaker; The method further comprises: Using a pre-built grid load change model, predicting the power consumption valley stage based on the grid load data change in real time; Using a pre-built fault risk prediction model, a potential fault occurrence period is predicted in real time based on the electrical data of the high-voltage circuit breaker, and a maintenance time is determined based on the power consumption valley stage, so that the maintenance time is within the power consumption valley period and earlier than the fault occurrence period; The maintenance time is fed back to the client so that the client maintenance personnel can know the maintenance time of the high-voltage circuit breaker.

4. The intelligent control method for high-voltage circuit breaker according to claim 3, characterized in that: The method uses a pre-built fault risk prediction model to predict a potential fault occurrence period based on the electrical data of the high-voltage circuit breaker in real time, and then further includes: Communicate and connect with a preset energy consumption platform to obtain energy consumption data of the high-voltage circuit breaker monitored in real time by the energy consumption platform; Based on the energy consumption data and a preset risk investigation list, the factors affecting the energy consumption of the high-voltage circuit breaker are determined. When the energy consumption data exceeds a preset range, the energy consumption data exceeding the preset range and its corresponding factors are sent to the client; wherein the factors include at least the upper limit of the life of the high-voltage circuit breaker, frequent switching of the working state of the high-voltage circuit breaker, and abnormal working environment.

5. The intelligent control method for high-voltage circuit breaker according to claim 3, characterized in that: The method further comprises: The operating stability of the power network and the high-voltage circuit breaker is analyzed based on the electrical data, and the learning step of the adaptive learning model is adjusted based on the operating stability, so that the higher the operating stability, the shorter the corresponding learning step.

6. The intelligent management and control method of high-voltage circuit breaker according to claim 1, characterized in that: The method further comprises: Whenever the high-voltage circuit breaker executes the optimal decision-making solution, the response time of the high-voltage circuit breaker is monitored, where the response time refers to the time taken for the high-voltage circuit breaker to complete the execution of the optimal decision-making solution; Based on the response time, the acquisition frequency of real-time electrical data is adjusted in a timely manner, and the longer the response time, the higher the corresponding adjusted acquisition frequency.

7. The intelligent management and control method of high-voltage circuit breaker according to claim 1, characterized in that: The method further comprises: The location distribution of the high-voltage circuit breakers in the power network and the working status of each high-voltage circuit breaker are displayed, and the working status at least includes the open / closed state of the high-voltage circuit breaker and the working parameter value of the high-voltage circuit breaker.

8. An intelligent management and control system for high-voltage circuit breakers, characterized in that: include, An electrical data monitoring module (201) is used to obtain electrical data in real time, wherein the electrical data is data corresponding to electrical parameters in the power network where the high-voltage circuit breaker is located; An adaptive learning module (202) is used to pre-process the electrical data and input it into a pre-constructed adaptive learning model, and output an optimal decision solution after analyzing the electrical data through the adaptive learning model; A decision control module (203) is used to control the high-voltage circuit breaker to execute the optimal decision plan, wherein the optimal decision plan at least includes an opening / closing operation of the high-voltage circuit breaker and / or adjusting an operating parameter value of the high-voltage circuit breaker.

9. An intelligent control device for a high-voltage circuit breaker, characterized in that: The method comprises a memory and a processor, wherein the memory stores a computer program that can be loaded by the processor and execute any one of the methods according to claims 1 to 7.

10. A computer-readable storage medium, characterized in that: A computer program is stored which can be loaded by a processor and execute any one of the methods as claimed in claims 1 to 7.

Images