Primary and secondary fusion pole-mounted circuit breaker intelligent fault diagnosis and monitoring system

Abstract

The invention discloses a primary and secondary fusion pole-mounted circuit breaker intelligent fault diagnosis and monitoring system, and relates to the technical field of electric appliance fault diagnosis analysis, and the system comprises an information collection module, a sensing monitoring module, a diagnosis prediction module, an evaluation module and an optimization module. Communication barriers among different devices are broken through, the system can be compatible with various devices, comprehensiveness and compatibility of data acquisition are improved, it is ensured that data of various devices can be effectively acquired and integrated, accuracy and reliability of the data are ensured, data transmission quantity is reduced through compression transmission, network bandwidth pressure is reduced, and key fault information can be transmitted in time. Operation and maintenance personnel can quickly respond and process, the fault influence range and time are reduced, key information can be accurately extracted according to actual requirements through the feature extraction module, and the pertinence and accuracy of fault diagnosis are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of electrical fault diagnosis and analysis, and in particular to an intelligent fault diagnosis and monitoring system for an integrated primary and secondary pole-mounted circuit breaker. Background Art

[0002] A circuit breaker refers to a switching device that can close, carry, and interrupt the current under normal circuit conditions and can close, carry, and interrupt the current under abnormal circuit conditions within a specified time. Circuit breakers are classified into high-voltage circuit breakers and low-voltage circuit breakers according to their application scope. The division between high and low voltages is relatively blurred. Generally, voltages above 3 kV are called high voltages. Circuit breakers can be used to distribute electric energy, start asynchronous motors infrequently, and protect power supply lines and motors, etc. When they encounter serious overload, short circuit, undervoltage and other faults, they can automatically cut off the circuit. Its function is equivalent to the combination of a fuse switch and an over- and under-thermal relay, etc. Moreover, generally no components need to be changed after breaking the fault current, and it has been widely used; When common intelligent fault diagnosis and monitoring systems are in use, it is difficult to achieve direct communication and data interaction. As a result, when integrating multiple devices, it is necessary to develop communication interfaces separately for each device, increasing development costs and time, and compatibility problems are likely to occur, hindering comprehensive data collection and system integration. There is a lack of effective means for filtering out abnormal values, and key fault information cannot be promptly transmitted to maintenance personnel, delaying the timing of fault handling. For this reason, we propose an intelligent fault diagnosis and monitoring system for an integrated primary and secondary pole-mounted circuit breaker. Summary of the Invention

[0003] The purpose of the present invention is to provide an intelligent fault diagnosis and monitoring system for an integrated primary and secondary pole-mounted circuit breaker.

[0004] To achieve the above purpose, the present invention provides the following technical solution: An intelligent fault diagnosis and monitoring system for an integrated primary and secondary pole-mounted circuit breaker, the intelligent fault diagnosis and monitoring system includes: An information acquisition module that acquires fault information of the integrated primary and secondary pole-mounted circuit breaker and corresponding environmental information from the Internet and regards them as case information, a perception and monitoring module that acquires electrical parameters, mechanical parameters, and environmental indexes of the circuit breaker to obtain circuit breaker parameter information, and designs an integrated intelligent monitoring terminal that integrates an edge computing unit and a multi-protocol communication module; Collect the Modbus-TCP, IEC61850, and MQTT protocol stacks, and use the Modbus-TCP, IEC61850, and MQTT protocol stacks to enable the circuit breaker to have the function of multi-protocol conversion. Automatically match the communication protocol according to the device type to unify the data formats of heterogeneous devices. Perform real-time verification through CRC checksum verification during the data collection stage, and collect the sliding window algorithm. Use the sliding window algorithm to filter outlier data. The window size in the sliding window algorithm is set to 10 sampling points. After removing the noise data, perform compressed transmission. Collect the priority queue to manage the data stream, and use the priority queue to manage the data stream and time-sensitive network technology to make the data delay 50 ms, and set the priority of the fault alarm data to the highest level; The feature extraction module collects the information types in the case information, arranges the information types in order, and the user has the permission to edit the order of the information types to obtain the standard sequence list. According to the output of the dynamic protocol adaptation layer, standardize the data, and perform feature sorting on it according to the standard sequence list. Use the edge computing algorithm to extract parameter features and fault features; The diagnosis and prediction module collects the deep learning framework to train the time series diagnosis model to obtain the basic model. The case information and the circuit breaker parameter information form the training set. Randomly select a subset of the training set as the test set, and the remaining subsets as the training set to train the basic model to obtain the training result set; The evaluation module evaluates the effect of the circuit breaker according to different case information and parameter features.

[0005] As a further solution of the present invention: The intelligent fault diagnosis and monitoring system further includes: The optimization module uses the training results to optimize the basic model to obtain the optimized model, constructs a hierarchical computing architecture, where the hierarchical computing architecture includes an edge side and a cloud platform. Use the edge side for real-time data analysis and primary decision-making to analyze different case information and record it on the cloud platform. Iterate and optimize the optimized model through the cloud platform, develop a visual monitoring interface, integrate functions such as device status display, fault alarm, and maintenance suggestion generation, support multi-terminal access, dock with the power grid management system, realize automatic push of fault information, work order dispatch, and resource scheduling, and form an intelligent operation and maintenance closed loop.

[0006] As a further solution of the present invention: When sorting the circuit breaker parameter information in the feature extraction module, a blank processing unit is established. When the information type recorded in the standard sequence list is not available in the circuit breaker parameter information, the corresponding position in the parameter sequence list is left blank. Here, blank processing means leaving blank the position where the information type fills in the value. When collecting the circuit breaker parameter information, sort the circuit breaker parameter information according to the order of the standard sequence list to obtain the parameter sequence list.

[0007] As a further solution of the present invention: when evaluating the effect of the circuit breaker in the evaluation module, the fault characteristics of different case information are converted into retrieval characteristics, parameter characteristics are extracted, the retrieval characteristic values and parameter characteristic values are analyzed, the ratio of the parameter characteristic value to the retrieval characteristic values of all case information and the total number of ratios are calculated to obtain the characteristic ratio and the total characteristic value. The total characteristic value is sorted in ascending order, the position of the circuit breaker is collected, a three-dimensional visualization model is established, and the position of the circuit breaker is input into the three-dimensional visualization model to obtain the circuit breaker model.

[0008] As a further solution of the present invention: when extracting the parameter characteristics corresponding to the retrieval characteristics in the evaluation module, the retrieval characteristics corresponding to the parameter characteristics are synchronously screened to make the information types corresponding to the retrieval characteristic values and the parameter characteristic values the same. At the same time, the fluctuation range of the parameter characteristic values of the same type of circuit breaker in historical fault cases is statistically analyzed, the standard deviation of the parameter characteristic values is calculated, let the parameter characteristic value be Let the number of parameter characteristic values be Let the mean value of the parameter characteristic values be : ; The mean value of the parameter characteristic values is calculated through the above formula.

[0009] As a further solution of the present invention: after the mean value of the parameter characteristic values is calculated, let the standard deviation of the parameter characteristic values be : ; The standard deviation of the parameter characteristic values is calculated through the above formula.

[0010] As a further solution of the present invention: after the standard deviation of the parameter characteristic values is calculated, one-tenth of the standard deviation of the parameter characteristic values is extracted as the characteristic threshold, let the retrieval characteristic value be Let the characteristic ratio of different case information be At the same time, weight coefficients are set for different parameter characteristics. Let the weight coefficients set for different parameter characteristics be ; ; The characteristic ratio of different case information is calculated through the above formula.

[0011] As a further solution of the present invention: after the characteristic ratio in the evaluation module is calculated, all the characteristic ratios are added together. Let the total characteristic value be : ; The total characteristic values of different circuit breaker parameter information are calculated through the above formula. After sorting the total characteristic values in ascending order, a sorting table of characteristic indices of all circuit breakers is obtained.

[0012] As a further solution of the present invention: after obtaining the three-dimensional visualization model in the evaluation module, according to the sorting result of the total characteristic values, the circuit breaker status is divided into 6 levels, which are represented by red, yellow, green, dark red, orange, and light green in sequence. The brightness increases with the level, and the upper limit of the color value is 255.

[0013] It also includes a fault location function: It is designed by integrating into the FTU in an integrated manner. The secondary acquisition and processing of current and voltage signals, the communication unit, and the safety protection are designed in an integrated manner; Supports Beidou satellite synchronous positioning; It can automatically identify fault traveling wave current, power frequency current, and power frequency voltage signals, has data acquisition and waveform storage functions, supports the calling of information such as faults and loads, and sends the information to the master station; It has a fault recording function. When a fault occurs, it automatically performs fault recording for fault judgment. The fault recording start conditions can include current mutation, voltage mutation, etc., and the threshold can be set; It uses a State Grid encryption chip for hard encryption. The data accesses the master station through two-way encryption authentication and an APN intranet channel independent of the FTU. The data is transmitted using MQTT, 101, and 104 protocols; For a small current grounding system, such as ungrounded and arc suppression coil grounded systems, it can achieve fault location under grounding faults such as metallic grounding, arc grounding, low-resistance grounding, and high-resistance grounding; It has a remote maintenance function, including: having self-protection and self-check functions, being able to actively alarm in case of abnormal situations, automatically resetting and recovering for possible deadlock problems, having local and remote maintenance functions, and supporting remote program downloading and upgrading; It has an anti-mis-alarm logic and does not mis-alarm under conditions such as load fluctuations, large load switching, closing (including reclosing) inrush current, and FTU live disassembly.

[0014] Adopting the above technical solutions, compared with the prior art, the beneficial effects of the present invention are as follows: 1. The present invention can automatically match communication protocols according to device types through the information collection module, achieving unified data formats for heterogeneous devices. This breaks down the communication barriers between different devices, enables the system to be compatible with multiple devices, improves the comprehensiveness and compatibility of data collection, ensures that data from various devices can be effectively collected and integrated, guarantees the accuracy and reliability of the data. Compressed transmission reduces the amount of data transmitted, improves transmission efficiency, reduces network bandwidth pressure, ensures that critical fault information can be transmitted in a timely manner, facilitates rapid response and handling by maintenance personnel, reduces the scope and duration of the impact of faults, and can accurately extract key information according to actual needs using the feature extraction module, improving the pertinence and accuracy of fault diagnosis; 2. The present invention can process according to the standard sequence list specification through the feature extraction module, avoiding data processing errors caused by missing information, enabling the system to better process incomplete data, and ensuring that subsequent analysis and diagnosis results based on this data are more reliable. The evaluation module can accurately quantify the degree of difference between the current breaker parameter characteristics and the retrieved characteristics in the case information, providing an accurate numerical basis for evaluating the operating state of the breaker, helping maintenance personnel quickly judge the similarity between the current breaker and historical fault cases, quickly locking in key monitoring objects, and further refining the evaluation process; 3. The present invention can reflect the actual operating conditions of the breaker through the evaluation module, providing more accurate data support for fault diagnosis and prediction. It can directly compare the operating states of different breakers, quickly identify breakers with poor operating states and high fault risks, provide a clear basis for maintenance decisions, facilitate the reasonable arrangement of maintenance resources and maintenance plans, is easy for users to understand and identify, avoids misreading information caused by chaotic color settings, and ensures that the display color can accurately reflect the relative states of each breaker. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 It is the working flow chart of the system of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0016] The following further describes the specific embodiments of the present invention in conjunction with the drawings. It should be noted here that the description of these embodiments is used to help understand the present invention, but does not constitute a limitation to the present invention.

[0017] In addition, the technical features involved in the various embodiments of the present invention described below can be combined with each other as long as they do not conflict with each other.

[0018] Embodiment 1: Please refer to the appendix Figure 1, in the present invention, an intelligent fault diagnosis and monitoring system for a primary-secondary integrated pole-mounted circuit breaker. In a city, the distribution network is like the "power blood vessels" of the city, delivering electric energy to various users. Pole-mounted circuit breakers are widely distributed in the streets and alleys of the city, connecting power lines in different areas. Taking a bustling commercial district as an example, there are dense commercial facilities such as shopping malls, office buildings, and hotels here, with extremely high requirements for the stability and reliability of power supply. Once a pole-mounted circuit breaker fails, even a short power outage may cause huge economic losses to businesses. Traditional monitoring technologies mainly rely on manual regular inspections and discrete secondary devices, with significant limitations: poor timeliness and high costs of manual inspections, and it is difficult to cover concealed faults. Due to data isolation between primary and secondary devices in discrete monitoring systems, information is fragmented, and multi-source data fusion analysis cannot be achieved, resulting in a high false alarm rate of faults; Therefore, in order to effectively solve the above problems, this application proposes an intelligent fault diagnosis and monitoring system for a primary-secondary integrated pole-mounted circuit breaker. As shown in the Figure 1 specification drawings, the intelligent fault diagnosis and monitoring system includes: An information acquisition module that collects fault information and corresponding environmental information of the primary-secondary integrated pole-mounted circuit breaker from the Internet and regards them as case information. A perception monitoring module that collects electrical parameters, mechanical parameters, and environmental indices of the circuit breaker to obtain circuit breaker parameter information. Design an integrated intelligent monitoring terminal that integrates an edge computing unit and a multi-protocol communication module; Table 1 Communication Protocol Table Design an integrated intelligent monitoring terminal that integrates an edge computing unit and a multi-protocol communication module, supports local data processing and multi-protocol compatibility. The communication protocol table is applicable to the design of an integrated intelligent monitoring terminal that integrates an edge computing unit and a multi-protocol communication module; Collect the Modbus-TCP, IEC61850, and MQTT protocol stacks, and use the Modbus-TCP, IEC61850, and MQTT protocol stacks to enable the circuit breaker to have the function of multi-protocol conversion. Automatically match the communication protocol according to the device type to unify the data formats of heterogeneous devices. Perform real-time verification through CRC check codes during the data acquisition stage, and collect the sliding window algorithm. Use the sliding window algorithm to filter outlier data. The window size in the sliding window algorithm is set to 10 sampling points. After removing the noise data, compress and transmit it. Collect the priority queue to manage the data stream, and use the priority queue to manage the data stream and time-sensitive network technology to make the data delay 50 ms, and set the priority of the fault alarm data to the highest level; The feature extraction module collects the types of information in the case information, arranges the types of information in sequence. The user has the permission to edit the order of the types of information to obtain a standard sequence list, adapts the output standardized data according to the dynamic protocol adaptation layer, and sorts the features according to the standard sequence list, and uses the edge computing algorithm to extract parameter features and fault features; The diagnosis and prediction module collects the deep learning framework to train the time series diagnosis model to obtain a basic model. The case information and the breaker parameter information form a training set. A subset of the training set is randomly selected as the test set, and the remaining subsets are used as the training set to train the basic model to obtain a training result set; The evaluation module evaluates the breaker effect according to different case information and parameter features; The intelligent fault diagnosis and monitoring system further includes: The optimization module uses the training results to optimize the basic model to obtain an optimized model, constructs a hierarchical computing architecture. The hierarchical computing architecture includes an edge side and a cloud platform. The edge side is used for real-time data analysis and primary decision-making, so as to analyze different case information and record it on the cloud platform. The cloud platform iterates and optimizes the optimized model, develops a visual monitoring interface, integrates functions such as device status display, fault alarm, and maintenance suggestion generation, supports multi-terminal access, docks with the power grid management system, realizes automatic push of fault information, work order dispatch and resource scheduling, and forms an intelligent operation and maintenance closed loop; The standard sequence list is preset by the system with common types of information (such as current, voltage, temperature). The user can drag and adjust the order through the visual interface to generate a custom sequence list; Electrical parameters refer to current and voltage, mechanical parameters refer to vibration and displacement, and environmental parameters refer to temperature and humidity; Design an integrated intelligent monitoring terminal. The integrated edge computing unit and multi-protocol communication module can support local data processing and remote interaction, eliminating the physical isolation and communication barriers of traditional discrete devices; The edge computing unit is located at the edge of the network, close to the data source or the place where data is generated, such as Internet of Things devices, sensors, cameras, etc. Different from traditional cloud computing that transmits data to a remote data center for processing, the edge computing unit sinks some or all of the data processing functions to the edge of the network, reducing the transmission distance and delay of data in the network; Multi-protocol communication is to enable devices or systems with different protocols to communicate and work together, break down the barriers between protocols, and achieve a wider range of device interconnection and data sharing; Edge computing algorithms refer to various data processing and analysis algorithms that run in edge computing scenarios. These algorithms aim to make full use of the computing power of edge computing units to perform real-time data processing and analysis near the data source to meet the needs of specific applications. The following are some common types and characteristics of edge computing algorithms; The training results in the training result set include diagnostic information and prediction information; When collecting and training a time-series diagnostic model using a deep learning framework, high-precision classification and pattern recognition are achieved for typical fault types such as short circuits, overloads, and mechanical jams. At the same time, historical fault data and simulation scenarios are used to optimize the model's generalization ability to adapt to complex working conditions and environmental changes and improve diagnostic robustness; The deep learning framework provides a series of tools and algorithms for building and training neural network models. The time-series diagnostic model is a model specifically designed for time-series data. It can capture the characteristics and patterns of data in the time dimension. Its basic principle is to learn a large amount of time-series data, automatically extract the features in the data, and establish the mapping relationship between the input sequence and the output result. For example, in the power system, the operating data of power equipment collected at different times is used as the input, and through model learning, diagnostic results such as whether the equipment has a fault and the type of fault are output; The optimization module also supports the function of self-healing faults, establishes a communication unit, and uses the communication unit to link the power grid dispatching system to achieve automated operations such as fault isolation and standby line switching, reducing manual intervention; The function of self-healing faults and automated decision-making reduce the power outage time and energy loss, meeting the development goals of a green power grid. The predictive maintenance mechanism reduces the frequency of manual inspections, optimizes resource allocation, and significantly saves operation and maintenance investment; The edge side refers to computing devices or nodes located at the edge of the network, close to the data source or users. The cloud platform is a centralized computing and storage environment based on cloud computing technology, consisting of a large number of servers, storage devices, and network resources, usually located in the data center; Multi-terminal access means that users can access the same application program, service, or data resource through various different types of terminal devices; Modbus-TCP encapsulates the Modbus protocol in TCP data packets and uses the IP network for data transmission, enabling devices to communicate and control remotely through the network; IEC61850 is a communication standard for substation automation systems developed by the International Electrotechnical Commission; The MQTT protocol stack uses an asynchronous communication method and realizes message transfer through a message queue, allowing loose-coupled communication between devices; CRC checksum The CRC checksum is obtained by appending a checksum of a certain number of bits to the data to be transmitted, so that the entire data frame can be divisible by a specific generating polynomial; The sliding window algorithm slides over a data sequence by maintaining a window of fixed or dynamic size, and performs corresponding calculations and judgments based on the elements within the window. During the sliding process, the position and size of the window are continuously updated to find the optimal subsequence or substring that meets specific conditions; Priority queue management of data flow is a special data structure that can sort elements according to their priorities and has many application scenarios in managing data flow, such as processing task scheduling, event handling, etc.; Time-Sensitive Networking (TSN) technology is a network technology that supports real-time communication and time-sensitive applications, aiming to meet the requirements for precise synchronization and low latency in fields such as industrial automation, vehicle-to-everything (V2X) communication, and smart grid; Specifically, collect the fault information of the primary-secondary integrated pole-mounted circuit breaker and the corresponding environmental information, collect the electrical parameters, mechanical parameters, and environmental indices of the circuit breaker, design an integrated intelligent monitoring terminal, integrate an edge computing unit and a multi-protocol communication module, collect the Modbus-TCP, IEC 61850, and MQTT protocol stacks, and use the Modbus-TCP, IEC 61850, and MQTT protocol stacks to enable the circuit breaker to have the function of multi-protocol conversion, automatically match the communication protocol according to the device type, unify the data formats of heterogeneous devices, perform real-time verification through CRC checksum verification during the data collection stage, collect the sliding window algorithm, use the sliding window algorithm for outlier filtering, set the window size in the sliding window algorithm to 10 sampling points, remove the noise data and then perform compressed transmission, collect the priority queue management of data flow, and use the priority queue management of data flow and Time-Sensitive Networking (TSN) technology to reduce the data latency 50 ms, and set the priority of the fault alarm data to the highest level. Collect the information types in the case information and arrange them in order. Adapt the output of the dynamic protocol adaptation layer to standardized data and sort its features according to the standard sequence list. Use the edge computing algorithm to extract parameter features and fault features. Collect the training time series diagnosis model of the deep learning framework. The case information and the circuit breaker parameter information form a training set. Randomly select a subset of the training set as the test set, and the remaining subsets as the training set to train the basic model. Evaluate the effect of the circuit breaker, use the training results to optimize the basic model to obtain an optimized model, build a hierarchical computing architecture, where the hierarchical computing architecture includes an edge side and a cloud platform. Use the edge side for real-time data analysis and primary decision-making to analyze different case information and record it on the cloud platform. Iterate and optimize the optimized model through the cloud platform, develop a visual monitoring interface, integrate functions such as device status display, fault alarm, and maintenance suggestion generation, support multi-terminal access, connect to the power grid management system, realize automatic push of fault information, work order dispatch, and resource scheduling, and form an intelligent operation and maintenance closed loop.

[0019] Embodiment 2: When sorting the circuit breaker parameter information in the feature extraction module, a blank processing unit is established. When the information type recorded in the standard sequence list is not available in the circuit breaker parameter information, the corresponding position in the parameter sequence list is left blank. Here, blank processing means leaving blank the position where the information type fills in the value. When collecting the circuit breaker parameter information, sort the circuit breaker parameter information according to the order of the standard sequence list to obtain the parameter sequence list; When evaluating the effect of the circuit breaker in the evaluation module, convert the fault features of different case information into retrieval features, extract parameter features, analyze the retrieval feature values and parameter feature values, calculate the ratio and the total number of ratios of the parameter feature values to the retrieval feature values of all case information to obtain the feature ratio and the total feature value. Sort the total feature value in ascending order, collect the position of the circuit breaker, build a three-dimensional visualization model, and input the position of the circuit breaker into the three-dimensional visualization model to obtain the circuit breaker model; When extracting the parameter features corresponding to the retrieval features in the evaluation module, synchronously screen the retrieval features corresponding to the parameter features to make the information types corresponding to the retrieval feature values and the parameter feature values the same. At the same time, count the fluctuation range of the parameter feature values of the same type of circuit breaker in historical fault cases, calculate the standard deviation of the parameter feature values, let the parameter feature value be Let the number of parameter feature values be Let the mean value of the parameter feature values be : ; Calculate the mean value of the parameter feature values through the above formula; After the mean value of the parameter characteristic values is calculated, let the standard deviation of the parameter characteristic values be : ; Calculate the standard deviation of the parameter characteristic values through the above formula; Specifically, establish a blank processing unit. When there is no information type recorded in the standard sequence list but there is breaker parameter information, blank the corresponding positions in the parameter sequence list. When collecting breaker parameter information, sort the breaker parameter information according to the order of the standard sequence list to obtain a parameter sequence list. Convert the fault characteristics of different case information into retrieval characteristics, extract parameter characteristics, analyze the retrieval characteristic values and parameter characteristic values, calculate the ratio and total number of ratios of the parameter characteristic values to the retrieval characteristic values of all case information, obtain the characteristic ratio and total characteristic value, sort the total characteristic value in ascending order, collect the position of the breaker, establish a three-dimensional visualization model, input the position of the breaker into the three-dimensional visualization model to obtain a breaker model, screen the retrieval characteristics corresponding to the parameter characteristics to make the information types corresponding to the retrieval characteristic values and parameter characteristic values the same, and at the same time count the fluctuation range of the parameter characteristic values of the same type of breaker in historical fault cases, and calculate the standard deviation of the parameter characteristic values.

[0020] Embodiment 3: After the standard deviation of the parameter characteristic values is calculated, extract one-tenth of the standard deviation of the parameter characteristic values as the characteristic threshold, let the retrieval characteristic value be , let the characteristic ratio of different case information be , and at the same time set weight coefficients for different parameter characteristics. Let the weight coefficients set for different parameter characteristics be ; ; Calculate the characteristic ratio of different case information through the above formula; After the characteristic ratio in the evaluation module is calculated, add up all the characteristic ratios. Let the total characteristic value be : ; Calculate the total characteristic value of different breaker parameter information through the above formula. After sorting the total characteristic value in ascending order, obtain the characteristic index sorting table of all breakers; After the three-dimensional visualization model in the evaluation module is obtained, according to the sorting result of the total characteristic value, divide the breaker status into 6 levels, which are represented by red, yellow, green, dark red, orange, and light green in turn. The brightness increases with the level, and the upper limit of the color value is 255; Screen the retrieval features corresponding to the parameter features to make the information types corresponding to the retrieval feature values and the parameter feature values the same. At the same time, count the fluctuation range of the parameter feature values of the same type of circuit breakers in historical fault cases, and calculate the standard deviation of the parameter feature values. Specifically, after calculating the feature ratios, add up all the feature ratios to calculate the total feature value of the parameter information of different circuit breakers. After sorting the total feature values in ascending order, obtain the feature index sorting table of all circuit breakers. According to the sorting result of the total feature values, divide the circuit breaker status into 6 levels, which are represented by red, yellow, green, dark red, orange, and light green in turn. The brightness increases with the level, and the upper limit of the color value is 255.

[0021] Table 2 Fault Location Table Among them, the fault location table is applicable to diagnosing and predicting the electrical parameters, mechanical parameters, and environmental indexes of circuit breakers collected in the diagnostic prediction module and the acquisition module.

[0022] Working Principle: First, collect the fault information of the primary-secondary integrated pole-mounted circuit breaker and the corresponding environmental information, collect the electrical parameters, mechanical parameters, and environmental indexes of the circuit breaker, design an integrated intelligent monitoring terminal, integrate the edge computing unit and multi-protocol communication module, collect the Modbus-TCP, IEC61850, and MQTT protocol stacks, and use the Modbus-TCP, IEC61850, and MQTT protocol stacks to enable the circuit breaker to have the function of multi-protocol conversion. Automatically match the communication protocol according to the device type to unify the data formats of heterogeneous devices. Perform real-time verification through CRC checksum verification during the data acquisition stage, and collect the sliding window algorithm. Use the sliding window algorithm to filter out outliers. The window size in the sliding window algorithm is set to 10 sampling points. After removing the noise data, compress and transmit it. Collect the priority queue to manage the data stream, and use the priority queue to manage the data stream and time-sensitive network technology to make the data delay 50ms, and set the fault alarm data priority to the highest level, collect the information types in the case information, and arrange the information types in order, output standardized data according to the dynamic protocol adaptation layer, and sort it according to the standard sequence table, use the edge computing algorithm to extract parameter features and fault features, establish a blank processing unit, when the information type recorded in the standard sequence table but the circuit breaker parameter information does not exist, the corresponding position in the parameter sequence table is blanked, when the circuit breaker parameter information is collected, the circuit breaker parameter information is sorted according to the order of the standard sequence table, and the parameter sequence table is obtained, and the deep learning framework training is collected. The timing diagnosis model is trained. The case information and circuit breaker parameter information form a training set. A subset of the training set is randomly selected as a test set, and the remaining subsets are used as training sets to train the basic model. The circuit breaker effect is evaluated. The fault features of different case information are converted into retrieval features, parameter features are extracted, retrieval feature values ​​and parameter feature values ​​are analyzed, and the ratio and total ratio of the parameter feature value to the retrieval feature value of all case information are calculated to obtain the feature ratio and the total feature value. The total feature value is sorted in ascending order, the position of the circuit breaker is collected, a three-dimensional visualization model is established, and the position of the circuit breaker is entered into the three-dimensional visualization model to obtain the circuit breaker model. Type, filter the retrieval features corresponding to the parameter features, make the retrieval feature values ​​and the parameter feature values ​​corresponding to the same type of information, and at the same time count the fluctuation range of the parameter feature values ​​of the same type of circuit breakers in historical fault cases, calculate the standard deviation of the parameter feature values, and after the feature ratio is calculated, add all the feature ratios to calculate the total feature value of different circuit breaker parameter information. After sorting the total feature values ​​in ascending order, obtain the feature index sorting table of all circuit breakers. According to the sorting results of the total feature values, divide the circuit breaker status into 6 levels, represented by red, yellow, green, dark red, orange, and light green, respectively. The brightness increases with the level, and the upper limit of the color value is The training result is used to optimize the basic model, obtain the optimized model, and build a hierarchical computing architecture, which includes the edge and cloud platforms. The edge uses real-time data analysis and primary decision-making to analyze different case information and record it on the cloud platform. The optimization model is iterated and optimized through the cloud platform, and a visual monitoring interface is developed to integrate equipment status display, fault alarm, and maintenance suggestion generation functions. It supports multi-terminal access and connects to the power grid management system to realize automatic push of fault information, work order distribution, and resource scheduling, forming an intelligent operation and maintenance closed loop. At this point, the entire workflow ends.

[0023] Although the present invention is disclosed above in a preferred embodiment, it is not intended to limit the present invention. Any person skilled in the art can make possible changes and modifications without departing from the spirit and scope of the present invention. Therefore, any modification, equivalent change, and modification made to the above embodiments based on the technical essence of the present invention without departing from the technical solution of the present invention shall fall within the protection scope defined by the claims of the present invention.

Claims

1. A primary-secondary integrated pole-mounted circuit breaker intelligent fault diagnosis and monitoring system, characterized in that The intelligent fault diagnosis and monitoring system includes: An information acquisition module that acquires primary and secondary integrated pole-mounted circuit breaker fault information and corresponding environmental information from the Internet and regards them as case information, a perception monitoring module that acquires electrical parameters, mechanical parameters, and environmental indices of the circuit breaker to obtain circuit breaker parameter information, and designs an integrated intelligent monitoring terminal that integrates an edge computing unit and a multi-protocol communication module; Collect the Modbus-TCP, IEC61850, and MQTT protocol stacks, and use the Modbus-TCP, IEC61850, and MQTT protocol stacks to enable the circuit breaker to have the function of multi-protocol conversion. Automatically match the communication protocol according to the device type to unify the data formats of heterogeneous devices. During the data collection stage, perform real-time verification through CRC checksum verification, and collect the sliding window algorithm. Use the sliding window algorithm for outlier filtering. The window size in the sliding window algorithm is set to 10 sampling points. After removing the noise data, perform compressed transmission, collect the priority queue to manage the data stream, and use the priority queue to manage the data stream and time-sensitive network technology to make the data delay 50 ms, and set the priority of the fault alarm data to the highest level; A feature extraction module that acquires the types of information in the case information, arranges the types of information in sequence, and the user has the permission to edit the order of the types of information to obtain a standard sequence list, outputs standardized data according to the dynamic protocol adaptation layer, sorts the features according to the standard sequence list, and uses edge computing algorithms to extract parameter features and fault features; A diagnosis and prediction module that acquires a timing diagnosis model trained by a deep learning framework to obtain a basic model. The case information and the circuit breaker parameter information form a training set. A subset of the training set is randomly selected as the test set, and the remaining subsets are used as the training set to train the basic model to obtain a training result set; An evaluation module that evaluates the circuit breaker effect according to different case information and parameter features.

2. The intelligent fault diagnosis and monitoring system for the primary and secondary integrated pole-mounted circuit breaker according to claim 1, characterized in that, The intelligent fault diagnosis and monitoring system further includes: An optimization module that uses the training results to optimize the basic model to obtain an optimized model, constructs a hierarchical computing architecture, where the hierarchical computing architecture includes an edge side and a cloud platform, uses real-time data analysis and primary decision-making on the edge side to analyze different case information, and records it on the cloud platform. The optimized model is iteratively optimized through the cloud platform, develops a visual monitoring interface, integrates functions such as device status display, fault alarm, and maintenance advice generation, supports multi-terminal access, docks with the power grid management system, realizes automatic push of fault information, work order dispatch, and resource scheduling, and forms an intelligent operation and maintenance closed-loop.

3. The intelligent fault diagnosis and monitoring system for the primary-secondary integrated pole-mounted circuit breaker according to claim 1, wherein: When sorting the circuit breaker parameter information in the feature extraction module, a blank processing unit is established. When the type of information recorded in the standard sequence list is not available in the circuit breaker parameter information, the corresponding position in the parameter sequence list is left blank. Here, blank processing means leaving blank the position where the value of the type of information is filled. When acquiring the circuit breaker parameter information, the circuit breaker parameter information is sorted according to the order of the standard sequence list to obtain a parameter sequence list.

4. The intelligent fault diagnosis and monitoring system for the primary-secondary integrated pole-mounted circuit breaker according to claim 3, characterized in that: When evaluating the circuit breaker effect in the evaluation module, the fault features of different case information are converted into retrieval features, parameter features are extracted, the retrieval feature values and parameter feature values are analyzed, the ratio and the total ratio of the parameter feature values to the retrieval feature values of all case information are calculated to obtain the feature ratio and the total feature value. The total feature value is sorted in ascending order, the position of the circuit breaker is acquired, a three-dimensional visualization model is established, and the position of the circuit breaker is input into the three-dimensional visualization model to obtain a circuit breaker model.

5. The intelligent fault diagnosis and monitoring system for primary and secondary integrated pole-mounted circuit breakers according to claim 4, wherein: When extracting parameter features corresponding to retrieval features in the evaluation module, retrieve features corresponding to the parameter features are screened synchronously to make the information types corresponding to the numerical values of the retrieval features and the parameter features the same. At the same time, the fluctuation range of the numerical values of the parameter features of the same type of circuit breaker in historical fault cases is statistically analyzed, and the standard deviation of the numerical values of the parameter features is calculated. Let the numerical value of the parameter feature be , let the number of numerical values of the parameter feature be , let the mean value of the numerical values of the parameter feature be : ； The mean value of the parameter feature values is calculated by the above formula.

6. The intelligent fault diagnosis and monitoring system for the primary-secondary integrated pole-mounted circuit breaker according to claim 5, characterized in that: After the mean value of the parameter characteristic values is calculated, let the standard deviation of the parameter characteristic values be :[[]]END]] ； The standard deviation of the parameter feature values is calculated by the above formula.

7. The intelligent fault diagnosis and monitoring system for primary and secondary integrated pole-mounted circuit breakers according to claim 6, wherein: After calculating the standard deviation of the parameter feature values, extract one-tenth of the standard deviation of the parameter feature values as the feature threshold, and set the retrieval feature value as , and set the feature ratio of different case information as . At the same time, set weight coefficients for different parameter features, and set the weight coefficients for different parameter features as ; ； The feature ratios of different case information are calculated by the above formula.

8. The intelligent fault diagnosis and monitoring system for primary-secondary integrated pole-mounted circuit breaker according to claim 7, wherein: After the feature ratios in the evaluation module are calculated, all the feature ratios are added together. Let the total characteristic value be :[[]]END]] ； The total characteristic values of different circuit breaker parameter information are calculated through the above formula. After sorting the total characteristic values in ascending order, a sorting table of characteristic indices for all circuit breakers is obtained.

9. The intelligent fault diagnosis and monitoring system for a primary-secondary integrated pole-mounted circuit breaker according to claim 8, wherein: After the three-dimensional visualization model in the evaluation module is obtained, according to the sorting result of the total characteristic values, the circuit breaker status is divided into 6 levels, which are represented by red, yellow, green, dark red, orange, and light green in sequence. The brightness increases with the level, and the upper limit of the color value is 255.

Images