Intelligent monitoring and early warning method and device for ring network cabinet

Abstract

The present invention discloses an intelligent monitoring and early warning method and device for a ring main unit, and relates to the technical field related to ring main unit monitoring. The method comprises: setting a data acquisition module on a target ring main unit, and acquiring the working status data stream of the ring main unit through the data acquisition module in real time monitoring; wirelessly transmitting the working status data stream of the ring main unit to an analysis and processing module for feature extraction and processing, and obtaining the working feature set of the ring main unit; constructing a fault identification model for the ring main unit, and obtaining fault diagnosis information of the ring main unit; obtaining fault location information of the ring main unit; and performing early warning and operation management on the target ring main unit based on the fault diagnosis information of the ring main unit and the fault location information of the ring main unit. The method solves the technical problems existing in the prior art of inaccurate fault diagnosis and positioning of the ring main unit, and difficulty in real-time monitoring and accurate early warning, and realizes accurate fault identification, real-time diagnosis and rapid positioning, and achieves the technical effect of improving the operation and maintenance management efficiency of the ring main unit and the stability of the power equipment.

Description

Technical Field

[0001] The present application relates to the technical field related to ring main unit monitoring, and specifically to an intelligent monitoring and early warning method and device for a ring main unit. Background Art

[0002] Ring Main Unit (RMU) is one of the important distribution equipment in the power system and is widely used in power distribution networks such as urban power grids and industrial parks. It is usually used for load switching, fault isolation, protection control and other functions in the distribution network to ensure the stable operation and power supply reliability of the power system. The fault diagnosis, positioning and early warning operation and maintenance management of the ring main unit has become a key link. However, the traditional monitoring and operation of the ring main unit relies on the operation and maintenance personnel to regularly check the working status of the ring main unit, such as temperature, current, voltage and other parameters. The work is heavy and there is a risk of missed detection and false detection. It is difficult to comprehensively monitor various types of information on changes in the internal and external environment of the ring main unit, lacks real-time dynamic grasp of the equipment status, and the diagnosis process is cumbersome and the positioning accuracy is low, which affects the timeliness of fault repair.

[0003] Therefore, in the current relevant technologies, there are technical problems such as inaccurate fault diagnosis and positioning of ring network cabinets, and difficulty in real-time monitoring and accurate early warning. Summary of the invention

[0004] The present application solves the technical problems in the prior art of inaccurate fault diagnosis and positioning of ring main units, and difficulty in real-time monitoring and precise early warning by providing an intelligent monitoring and early warning method and device for ring main units, thereby achieving accurate fault identification, real-time diagnosis and rapid positioning, and achieving the technical effect of improving the operation and maintenance management efficiency of ring main units and the stability of power equipment.

[0005] The present application provides an intelligent monitoring and early warning method for a ring network cabinet, which includes: setting a data acquisition module on a target ring network cabinet, and acquiring a working status data stream of the ring network cabinet through the data acquisition module in real time monitoring, wherein the working status data stream of the ring network cabinet includes equipment data and environmental data; wirelessly transmitting the working status data stream of the ring network cabinet to an analysis and processing module for feature extraction processing to obtain a working feature set of the ring network cabinet; constructing a ring network cabinet fault identification model, and performing fault identification on the working feature set of the ring network cabinet based on the ring network cabinet fault identification model to obtain ring network cabinet fault diagnosis information; performing fault location on the target ring network cabinet based on the ring network cabinet fault diagnosis information to obtain ring network cabinet fault location information; and performing early warning operation and maintenance management on the target ring network cabinet based on the ring network cabinet fault diagnosis information and the ring network cabinet fault location information.

[0006] In a possible implementation, the obtaining of the ring main unit working characteristic set also performs the following processing: performing encryption level evaluation on the ring main unit working status data stream through the ring main unit data application standard to obtain the ring main unit data encryption evaluation level; selecting and determining the data encryption algorithm according to the ring main unit data encryption evaluation level; performing encryption processing on the ring main unit working status data stream based on the data encryption algorithm, and wirelessly transmitting the encrypted ring main unit working status data stream to the analysis and processing module; performing feature extraction processing on the ring main unit working status data stream through the wireless transmission to the analysis and processing module to obtain the ring main unit working characteristic set.

[0007] In a possible implementation, the obtaining of the ring main unit working feature set further performs the following processing: extracting associated features from the working status data stream of the ring main unit to obtain the ring main unit associated working feature set; performing operation correlation analysis on each working feature in the ring main unit associated working feature set to obtain a working feature correlation set; setting a correlation threshold, performing feature screening on the working feature correlation set based on the correlation threshold to obtain the ring main unit working feature set.

[0008] In a possible implementation, the construction of the ring main unit fault identification model also performs the following processing: collecting and acquiring a ring main unit fault operation data set, preprocessing the ring main unit fault operation data set, and obtaining a standard ring main unit fault operation data set; obtaining a ring main unit fault diagnosis requirement, the ring main unit fault diagnosis requirement including a fault type, a fault level, and a fault generation cause; classifying, training, and fusing the standard ring main unit fault operation data set according to the ring main unit fault diagnosis requirement, and constructing a ring main unit fault identification model.

[0009] In a possible implementation, the construction of the ring main unit fault identification model also performs the following processing: classifying and marking the standard ring main unit fault operation data set according to the ring main unit fault diagnosis requirements to obtain a ring main unit fault clustering data set; performing model selection training on the ring main unit fault clustering data set to obtain a fault type identification model, a fault level identification model and a fault generation cause identification model; integrating the fault type identification model, the fault level identification model and the fault generation cause identification model to obtain a ring main unit fault identification model.

[0010] In a possible implementation, the fault type identification model, the fault level identification model and the fault generation cause identification model are obtained, and the following processing is also performed: characteristic analysis and model selection are performed on the ring network cabinet fault clustering data set respectively to determine the machine learning model architecture set; the machine learning model architecture set is used to perform identification training on the ring network cabinet fault clustering data set respectively to obtain the initial fault type model, the initial fault level model and the fault generation cause model; the initial fault type model, the initial fault level model and the fault generation cause model are verified, evaluated and optimized to obtain the fault type identification model, the fault level identification model and the fault generation cause identification model.

[0011] In a possible implementation, the early warning operation and maintenance management of the target ring main unit also performs the following processing: generating a ring main unit fault monitoring and diagnosis report based on the ring main unit fault diagnosis information and the ring main unit fault location information; constructing a ring main unit fault operation and maintenance knowledge base; analyzing the ring main unit fault monitoring and diagnosis report based on the ring main unit fault operation and maintenance knowledge base to obtain a ring main unit fault operation and maintenance plan; and performing early warning operation and maintenance management on the target ring main unit based on the ring main unit fault operation and maintenance plan.

[0012] The present application also provides an intelligent monitoring and early warning device for a ring network cabinet, including: a real-time data stream monitoring unit, used to set a data acquisition module on a target ring network cabinet, and to acquire the working status data stream of the ring network cabinet in real time through the data acquisition module, wherein the working status data stream of the ring network cabinet includes equipment data and environmental data; a feature extraction and processing unit, used to wirelessly transmit the working status data stream of the ring network cabinet to an analysis and processing module for feature extraction processing, and obtain a working feature set of the ring network cabinet; a fault identification unit, used to construct a ring network cabinet fault identification model, and to identify faults on the working feature set of the ring network cabinet based on the ring network cabinet fault identification model, and obtain fault diagnosis information of the ring network cabinet; a fault location unit, used to locate the fault of the target ring network cabinet based on the fault diagnosis information of the ring network cabinet, and obtain the fault location information of the ring network cabinet; an early warning and operation and maintenance management unit, used to perform early warning and operation and maintenance management on the target ring network cabinet based on the fault diagnosis information of the ring network cabinet and the fault location information of the ring network cabinet.

[0013] It is proposed that the intelligent monitoring and early warning method and device for ring network cabinets proposed in this application be used to set a data acquisition module on the target ring network cabinet, and obtain the ring network cabinet working status data stream through the data acquisition module in real time monitoring; the ring network cabinet working status data stream is wirelessly transmitted to the analysis and processing module for feature extraction and processing to obtain the ring network cabinet working feature set; a ring network cabinet fault identification model is constructed to obtain the ring network cabinet fault diagnosis information; the ring network cabinet fault location information is obtained; based on the ring network cabinet fault diagnosis information and the ring network cabinet fault location information, the target ring network cabinet is early warning and operated. The technical problems of inaccurate fault diagnosis and positioning of ring network cabinets, difficulty in real-time monitoring and accurate early warning in the prior art are solved, and accurate fault identification, real-time diagnosis and rapid positioning are achieved, achieving the technical effect of improving the operation and maintenance management efficiency of ring network cabinets and the stability of power equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] In order to more clearly illustrate the technical solution of the embodiment of the present disclosure, the accompanying drawings of the embodiment of the present disclosure will be briefly introduced below. A flow chart is used in the present application to illustrate the operations performed by the device according to the embodiment of the present application. It should be understood that the previous or following operations are not necessarily performed precisely in order. On the contrary, various steps can be processed in reverse order or simultaneously as needed. At the same time, other operations can also be added to these processes, or one or more operations can be removed from these processes.

[0015] Figure 1 A schematic flow chart of an intelligent monitoring and early warning method for a ring main unit provided in an embodiment of the present application;

[0016] Figure 2 A schematic diagram of the structure of an intelligent monitoring and early warning device for a ring main unit provided in an embodiment of the present application.

[0017] Explanation of the reference numerals: data flow real-time monitoring unit 10 , feature extraction and processing unit 20 , fault identification unit 30 , fault location unit 40 , early warning and operation and maintenance management unit 50 . DETAILED DESCRIPTION

[0018] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below.

[0019] In order to make the objectives, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings. The described embodiments should not be regarded as limiting the present application. All other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of this application.

[0020] In the following description, reference is made to "some embodiments", which describe a subset of all possible embodiments, but it is understood that "some embodiments" may be the same subset or different subsets of all possible embodiments, and may be combined with each other without conflict, and the terms "first\second" involved are merely to distinguish similar objects and do not represent a specific ordering of objects. The terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, device, product, or server that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or modules that are not clearly listed or inherent to these processes, methods, products, or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those generally understood by technicians in the technical field of this application. The terms used herein are for the purpose of describing the embodiments of the present application only.

[0021] The present application embodiment provides an intelligent monitoring and early warning method for a ring main unit, such as Figure 1 As shown, the method includes:

[0022] Step S100, setting a data acquisition module on the target ring main unit, and acquiring the ring main unit working status data stream through the data acquisition module in real time monitoring, wherein the ring main unit working status data stream includes equipment data and environment data.

[0023] Preferably, a data acquisition module is provided on the target ring network cabinet, and various data related to the ring network cabinet are acquired through real-time monitoring by the data acquisition module to form a working status data stream, including equipment data and environmental data. Specifically, equipment data refers to data related to the internal equipment status and operating conditions of the ring network cabinet, usually including but not limited to the current and voltage values ​​of the electrical equipment in the ring network cabinet, the temperature of each equipment in the ring network cabinet (such as switches, cables, transformers, etc.), the relevant data of the power transmission efficiency of the ring network cabinet, the switch position or status (on / off) of the switch or circuit breaker in the ring network cabinet, etc. Environmental data refers to data related to the external environment of the ring network cabinet and the equipment operating environment, usually including temperature and humidity data of the environment where the ring network cabinet is located. In specific places, the ring network cabinet may be affected by external environmental factors such as air pressure, wind speed, etc., vibration data of the ring network cabinet or its components, etc.

[0024] Step S200: wirelessly transmit the ring main unit working status data stream to an analysis and processing module for feature extraction processing to obtain a ring main unit working feature set.

[0025] Preferably, the working status data stream is first sent to the analysis and processing module via wireless transmission, and the analysis and processing module is used to extract features from the working status data stream to obtain the working feature set of the ring main unit. Specifically, wireless transmission refers to the transmission of equipment data and environmental data (i.e., working status data stream) collected from the ring main unit to a remote or centralized analysis and processing module via wireless communication (such as Wi-Fi, Bluetooth, Zigbee, LoRaWAN, 5G and other wireless technologies), which can avoid wiring complexity and improve flexibility, so that data can be transmitted in real time and can be easily monitored and analyzed remotely; the analysis and processing module refers to a module that performs data analysis and processing after receiving the working status data stream from the ring main unit, usually receives the real-time data stream sent from the ring main unit, stores the received data in a database, manages it effectively, and uses a model to process, filter and analyze the real-time data; feature extraction refers to Representative key features that can reflect the operating status of the equipment or system are extracted from the raw data. Specifically, the feature extraction process includes extracting statistical characteristics reflecting the operating status from the equipment data, extracting features such as periodicity, trend, and rate of change to help determine whether the equipment is in normal operating condition. The raw data is converted into frequency domain data through Fourier transform and other methods, and frequency, vibration and other information are extracted to identify whether the equipment has abnormal vibration or signs of failure. The data is then subjected to pattern recognition through machine learning, artificial intelligence and other technologies to extract characteristic patterns that may indicate equipment abnormality or failure. The final result is the ring main unit working feature set, which is a collection of all key data features that have been analyzed and processed, reflecting the status information of various types of equipment and environment during the operation of the ring main unit, and can be used for further fault identification, performance prediction, trend analysis and other tasks, which may include electrical performance characteristics, environmental change characteristics and equipment status characteristics.

[0026] Furthermore, step S200 also includes step S210, performing encryption level evaluation on the ring main unit working status data stream through the ring main unit data application standard to obtain the ring main unit data encryption evaluation level; step S220, selecting and determining the data encryption algorithm according to the ring main unit data encryption evaluation level; step S230, encrypting the ring main unit working status data stream based on the data encryption algorithm, and wirelessly transmitting the encrypted ring main unit working status data stream to the analysis and processing module; step S240, performing feature extraction processing on the ring main unit working status data stream through the wireless transmission to the analysis and processing module to obtain the ring main unit working feature set.

[0027] Preferably, according to the content of the working status data stream of the ring main unit, a specific data application standard (for example, based on the data sensitivity and the encryption specification used) is used to evaluate the data stream. The ring main unit data application standard can determine the encryption level based on factors such as the sensitivity of the data, the security requirements of the transmission process, and the importance of the equipment in the power system. For example, low-sensitivity data such as temperature and humidity data of the ring main unit may not require a particularly high encryption level, and high-sensitivity data such as the current, voltage and equipment status of the ring main unit may require a higher encryption level to prevent data leakage or tampering; according to the evaluation results, an encryption evaluation level is assigned to the data stream, such as "low level", "medium level" or "high level"; according to the evaluated encryption level, an appropriate encryption level is selected. An encryption algorithm of this level is selected to ensure data security while avoiding excessive consumption of computing resources or increased delays, such as AES (Advanced Encryption Standard) symmetric encryption algorithm, RSA asymmetric encryption algorithm, etc. The working status data stream of the ring main unit is then encrypted using the selected encryption algorithm to ensure data confidentiality and integrity, and sent to the analysis and processing module through wireless transmission technology (such as Wi-Fi, Bluetooth, LoRaWAN, etc.) to process the encrypted data stream. Although the data has been encrypted, at the receiving end, the analysis and processing module can decrypt the data and extract features, that is, use a specific algorithm to extract key features reflecting the operating status of the equipment, so as to identify feature data that can be used for equipment health diagnosis and fault warning, and constitute the working feature set of the ring main unit.

[0028] Furthermore, step S240 also includes step S241, extracting associated features of the working status data stream of the ring main unit to obtain an associated working feature set of the ring main unit; step S242, performing operation correlation analysis on each working feature in the associated working feature set of the ring main unit to obtain a working feature correlation set; step S243, setting a correlation threshold, performing feature screening on the working feature correlation set based on the correlation threshold, and obtaining the working feature set of the ring main unit.

[0029] Preferably, multiple features with interrelated relationships are extracted from the working status data stream of the ring network cabinet, not just a single device data (such as temperature, current, voltage, etc.), but a feature combination with a common change trend and mutual influence is identified through data analysis. For example, in the operation process of the ring network cabinet, parameters such as current, voltage and temperature are usually interrelated. An increase in current may cause an increase in temperature, and an increase in temperature may affect the efficiency and life of the equipment. After extracting the associated working feature set of the ring network cabinet, the next step is to perform an operation correlation analysis, that is, to calculate and analyze the correlation between each feature, such as using the Pearson correlation coefficient to calculate and measure the strength of the linear relationship between two features. The numerical range The range is [-1, 1], where 1 indicates a complete positive correlation, -1 indicates a complete negative correlation, and 0 indicates no linear relationship. This reveals the relationship between the various working characteristics of the ring network cabinet (such as current, voltage, temperature, humidity, etc.). By presetting a correlation threshold, only those feature pairs with a correlation higher than the threshold will be retained. For example, if the correlation threshold is selected as 0.8, only when the correlation between current and temperature is greater than 0.8, will the two features be considered to have a strong relationship. All working characteristics will be screened according to the correlation threshold, and those feature pairs that have a strong correlation with other characteristics will be retained. Finally, the working feature set of the ring network cabinet is obtained, which reflects the working status of the ring network cabinet and the characteristics of equipment health.

[0030] Step S300, constructing a ring main unit fault identification model, performing fault identification on the ring main unit working feature set based on the ring main unit fault identification model, and obtaining ring main unit fault diagnosis information.

[0031] Preferably, the extracted working feature set of the ring main unit is used to construct a fault identification model through machine learning, and the fault identification model is used to perform fault diagnosis on the working state of the ring main unit, and finally the fault diagnosis information of the ring main unit is obtained. Specifically, a large amount of historical data is collected, including data of normal working state and equipment feature data when a fault occurs, and a fault identification model is constructed using machine learning, such as support vector machine SVM, decision tree, random forest, convolutional neural network (CNN) or long short-term memory network (LSTM). The model is trained using historical data, and the model can learn the difference between different working states and fault states. For example, the characteristic data such as current, voltage, temperature, etc. of the equipment in a normal state will be different, and when a fault occurs (such as overload, short circuit, equipment damage, etc.), these data will change significantly, and a ring main unit fault identification model is obtained, which can identify potential faults based on real-time data.

[0032] Preferably, the fault identification model is used to identify the working feature set collected by the ring network cabinet in real time. Specifically, when the working status data stream (working feature set) of the ring network cabinet is transmitted to the fault identification model in real time, the model will evaluate the device status according to these real-time features, and judge whether the device has failed by comparing the fault mode in the real-time data with the historical data, and identify the fault type. If the model detects that the temperature of the device is too high, the load is abnormal, and the current fluctuation is unstable, it may be judged as an overload or short circuit fault. If some characteristic values ​​are abnormal (such as too high temperature and humidity), it may indicate that the device is overheated or affected by the external environment; finally, the fault diagnosis information is obtained, which usually includes the fault type, fault severity, etc., such as identifying the type of fault, such as equipment overload, short circuit, abnormal temperature, switch failure, equipment aging, etc., evaluating the severity of the fault, judging whether it is a minor fault, warning state, or a major fault that needs to be repaired immediately, which can help to timely discover problems in equipment operation, reduce the time and effort of manual troubleshooting, and improve the efficiency of equipment operation and maintenance. Through accurate fault identification and diagnosis, early warning can be given and targeted fault solutions can be provided, further improving the reliability and safety of the ring main unit and power system.

[0033] Furthermore, step S300 also includes step S310, collecting and acquiring a ring main unit fault operation data set, preprocessing the ring main unit fault operation data set, and obtaining a standard ring main unit fault operation data set; step S320, acquiring a ring main unit fault diagnosis requirement, the ring main unit fault diagnosis requirement including a fault type, a fault level, and a fault generation cause; step S330, classifying, training, and fusing the standard ring main unit fault operation data set according to the ring main unit fault diagnosis requirement, and constructing a ring main unit fault identification model.

[0034] Preferably, fault operation data is collected from the ring main unit to obtain a ring main unit fault operation data set, which is preprocessed, including denoising and cleaning, data normalization or standardization, etc., to ensure the quality of the data, and then a standard ring main unit fault operation data set is obtained; the ring main unit fault diagnosis requirement refers to the need to clearly identify the fault type, fault level and fault generation cause when performing fault diagnosis and identification. The fault type refers to different types of faults that may occur in the ring main unit, such as overload fault, short circuit fault, grounding fault, damage to electrical components, etc.; the fault level, according to the severity of the fault, the fault may be divided into different levels, such as minor fault, general fault, severe fault, etc.; the fault generation cause refers to the specific cause of the fault, such as overload, environmental factors (high temperature, high humidity), Equipment aging, etc.; According to the fault diagnosis needs, a ring main unit fault identification model is constructed using the standard ring main unit fault operation data set through classification training and fusion. Specifically, learning and training are carried out based on known fault data sets. For example, in the training data set, certain current and temperature combination data corresponds to "overload fault", while other voltage and humidity combinations correspond to "short circuit fault". Through classification training, the model can learn the relationship between these fault types and feature data, and then the classification training models are fused to obtain the ring main unit fault identification model, which can identify different types of faults, evaluate the severity of faults, and analyze the causes of faults, helping operation and maintenance personnel to promptly discover problems, diagnose faults, and implement early warnings, thereby improving the reliability and safety of the power system.

[0035] Furthermore, step S330 also includes step S331, classifying and marking the standard ring main unit fault operation data set according to the ring main unit fault diagnosis requirements to obtain a ring main unit fault clustering data set; step S332, performing model selection training on the ring main unit fault clustering data set to obtain a fault type identification model, a fault level identification model and a fault generation cause identification model; step S333, integrating the fault type identification model, the fault level identification model and the fault generation cause identification model to obtain a ring main unit fault identification model.

[0036] Preferably, the standard ring network cabinet fault operation data is labeled and classified according to the ring network cabinet fault diagnosis requirements (including fault type, fault level and fault generation cause), and each data is labeled as the corresponding fault type, fault level and fault generation cause according to its characteristics (such as current, temperature, etc.), thereby obtaining a ring network cabinet fault clustering data set, which includes multiple fault categories and related information; for different diagnostic needs, different fault identification models are trained respectively, which are used for fault type identification, fault level identification and fault generation cause identification, for example, based on classification algorithms such as decision trees, support vector machines (SVM), random forests, etc., different fault types are identified according to the labeled training data, and a regression model (such as linear regression or logistic regression) or a classification model (such as multi-classification SVM, random forest, etc.) is used to train a model that can identify the fault level; a classification model (such as decision trees, random forests, KNN, etc.) is used to train an identification model that can predict the cause of the fault, and then the fault type identification model, the fault level identification model and the fault generation cause identification model are integrated (for example, weighted average) to obtain a ring network cabinet fault identification model that can simultaneously identify the fault type, fault level and fault generation cause.

[0037] Furthermore, step S332 also includes step S332a, performing characteristic analysis and model selection on the ring main unit fault clustering data set to determine a machine learning model architecture set; step S332b, using the machine learning model architecture set to perform recognition training on the ring main unit fault clustering data set to obtain an initial fault type model, an initial fault level model and a fault generation cause model; step S332c, verifying, evaluating and optimizing the initial fault type model, the initial fault level model and the fault generation cause model to obtain the fault type identification model, the fault level identification model and the fault generation cause identification model.

[0038] Preferably, the ring main unit fault clustering data set is analyzed, data features are extracted, and a suitable machine learning model architecture is determined, that is, the most suitable model is selected for fault identification according to the characteristics of the fault data. Specifically, the data is analyzed to understand the relationship and distribution between different features, and whether there are outliers or noise, and then a suitable machine learning model is selected for training, such as decision trees, random forests, support vector machines, neural networks (deep neural networks, convolutional neural networks), etc.; then the ring main unit fault clustering data set is trained, and a fault type model, a fault level model, and a fault generation cause model are constructed respectively, and the patterns in the ring main unit fault data are learned respectively, and the relationship between different feature combinations and different fault types is judged; according to the set The operating data of the equipment (for example, the degree of current overload, voltage fluctuation, etc.) is used to determine whether the fault is a minor fault, a general fault, or a serious fault; based on these characteristics, it is determined whether the fault is caused by overload, overtemperature, damage to electrical components, or other factors; and then the initial fault type identification model, the initial fault level identification model, and the initial fault generation cause model are obtained; finally, these models are verified, evaluated, and optimized, such as hyperparameter tuning, cross-validation, etc., to improve the accuracy and robustness of the models, and ultimately efficient and accurate fault type identification models, fault level identification models, and fault generation cause identification models are obtained for real-time monitoring and fault diagnosis, which help operation and maintenance personnel to promptly discover and handle equipment failures, thereby improving the operating safety and efficiency of the ring network cabinet.

[0039] Step S400: locating the fault of the target ring main unit based on the ring main unit fault diagnosis information to obtain the fault position information of the ring main unit.

[0040] Preferably, after obtaining the fault diagnosis information of the ring main unit, the fault is further accurately located by analyzing the information, so as to clarify the location of the fault. Fault location refers to further determining the specific location of the fault and finding the source of the fault based on the fault diagnosis information. For a ring main unit, there may be multiple components and equipment (such as switches, circuit breakers, cables, transformers, etc.). The goal of fault location is to determine which component or part has a problem. Specifically, when the fault diagnosis model identifies a certain type of fault (such as "current overload" or "switch fault"), it is inferred which component is the cause based on the fault type. A problem may have occurred, and it is further confirmed in combination with historical fault data, and then the specific location of the fault is speculated. For a larger range of power equipment, such as a ring main unit, the working status and failure mode of multiple devices may be involved. Therefore, based on the sensor location and the distribution of the working status data stream, the fault area is narrowed by comparing the fault diagnosis information, and the specific component is located, and then the fault location information of the ring main unit is obtained, that is, the component or area where the fault occurs is clearly pointed out. The operation and maintenance personnel can quickly and accurately determine the specific location and source of the fault, thereby improving maintenance efficiency, reducing downtime and improving the operation and maintenance efficiency and reliability of the entire power system.

[0041] Step S500: Based on the ring main unit fault diagnosis information and the ring main unit fault location information, early warning operation and maintenance management is performed on the target ring main unit.

[0042] Preferably, by timely identifying and warning of possible problems or failures of the equipment, early operation and maintenance measures are taken to prevent further expansion of the failure or avoid equipment shutdown, thereby ensuring the stability and safety of the power system. Specifically, based on the fault diagnosis information, the early warning device can identify the possible fault type in advance, and predict the possible future fault trend in combination with historical data and equipment status. It is determined whether the early warning mechanism needs to be activated based on the fault diagnosis information. If the fault is a high-risk fault or a major fault, a fault warning signal is issued. When the diagnostic information and the fault location are clear, this information is converted into actual operation and maintenance instructions to provide the operation and maintenance personnel with clear fault locations and processing suggestions. For example, the specific faulty components (such as transformers, switches, cables, etc.) are determined based on the fault location information, the problem area is located in time, and corresponding isolation measures are taken; in some advanced intelligent monitoring systems, based on machine learning and big data analysis, the early warning information can be automatically analyzed and the best response measures can be generated. For example, the standby ring network cabinet will be automatically switched, the power distribution strategy will be adjusted, and even partial automatic repair will be performed before the fault occurs, reducing the impact on the power supply, thereby effectively reducing the impact of equipment failures on the power system and improving the reliability and maintenance efficiency of power equipment.

[0043] Furthermore, step S500 also includes step S510, generating a ring main unit fault monitoring and diagnosis report based on the ring main unit fault diagnosis information and the ring main unit fault location information; step S520, building a ring main unit fault operation and maintenance knowledge base; step S530, analyzing the ring main unit fault monitoring and diagnosis report based on the ring main unit fault operation and maintenance knowledge base to obtain a ring main unit fault operation and maintenance plan; step S540, performing early warning operation and maintenance management on the target ring main unit based on the ring main unit fault operation and maintenance plan.

[0044] Preferably, a ring main unit fault monitoring and diagnosis report is generated based on the ring main unit fault diagnosis information and fault location information, including the type, severity, location, impact range and possible causes of the fault, and then a ring main unit fault operation and maintenance knowledge base is constructed based on all fault types, common fault modes, fault emergency responses, historical maintenance records, common problem handling methods and other information of the ring main unit, including typical modes and possible causes of various ring main unit failures, such as overload, short circuit, ground fault, equipment aging, etc., and this information is associated with fault characteristics (such as current and voltage abnormalities), as well as corresponding response plans, repair steps, replacement parts, etc.; the constructed fault operation and maintenance knowledge base is then used to analyze the report content, and a corresponding fault operation and maintenance plan is generated based on the fault information therein, for example, by consulting the knowledge base, according to the fault type, fault level, fault location and other information in the report, the relevant repair plan or preventive measures are automatically matched, and targeted operation and maintenance plans are provided for each ring main unit fault, and finally early warning operation and maintenance management measures are taken according to the fault operation and maintenance plan to prevent the fault from deteriorating and ensure the safe and stable operation of the ring main unit and the entire power system.

[0045] In the above, refer to Figure 1 The intelligent monitoring and early warning method for a ring main unit according to an embodiment of the present invention is described in detail. Figure 2 An intelligent monitoring and early warning device for a ring main unit according to an embodiment of the present invention is described.

[0046] The intelligent monitoring and early warning device for a ring main unit according to an embodiment of the present invention is used to solve the technical problems existing in the prior art of inaccurate fault diagnosis and positioning of the ring main unit, and difficulty in real-time monitoring and accurate early warning, and realizes accurate fault identification, real-time diagnosis and rapid positioning, thereby achieving the technical effect of improving the operation and maintenance management efficiency of the ring main unit and the stability of the power equipment. The intelligent monitoring and early warning device for a ring main unit includes: a data stream real-time monitoring unit 10, a feature extraction processing unit 20, a fault identification unit 30, a fault positioning unit 40, and an early warning operation and maintenance management unit 50.

[0047] A data stream real-time monitoring unit 10 is used to set a data acquisition module on the target ring network cabinet, and to obtain the ring network cabinet working status data stream through the data acquisition module in real time monitoring, and the ring network cabinet working status data stream includes equipment data and environmental data; a feature extraction processing unit 20 is used to wirelessly transmit the ring network cabinet working status data stream to the analysis and processing module for feature extraction processing to obtain the ring network cabinet working feature set; a fault identification unit 30 is used to construct a ring network cabinet fault identification model, and to identify the fault of the ring network cabinet working feature set based on the ring network cabinet fault identification model to obtain the ring network cabinet fault diagnosis information; a fault location unit 40 is used to locate the fault of the target ring network cabinet based on the ring network cabinet fault diagnosis information to obtain the ring network cabinet fault location information; an early warning operation and maintenance management unit 50 is used to perform early warning operation and maintenance management on the target ring network cabinet based on the ring network cabinet fault diagnosis information and the ring network cabinet fault location information.

[0048] The specific configuration of the feature extraction processing unit 20 will be described in detail below. The feature extraction processing unit 20 may further include: performing encryption level evaluation on the ring main unit working status data stream through the ring main unit data application standard to obtain the ring main unit data encryption evaluation level; selecting and determining the data encryption algorithm according to the ring main unit data encryption evaluation level; performing encryption processing on the ring main unit working status data stream based on the data encryption algorithm, and wirelessly transmitting the encrypted ring main unit working status data stream to the analysis and processing module; performing feature extraction processing on the ring main unit working status data stream through the wireless transmission to the analysis and processing module to obtain the ring main unit working feature set.

[0049] The specific configuration of the feature extraction processing unit 20 will be described in detail below. The feature extraction processing unit 20 may further include: extracting associated features from the working status data stream of the ring main unit to obtain a ring main unit associated working feature set; performing operation correlation analysis on each working feature in the ring main unit associated working feature set to obtain a working feature correlation set; setting a correlation threshold, and performing feature screening on the working feature correlation set based on the correlation threshold to obtain the ring main unit working feature set.

[0050] The specific configuration of the fault identification unit 30 will be described in detail below. The fault identification unit 30 may further include: collecting and acquiring a ring main unit fault operation data set, preprocessing the ring main unit fault operation data set to obtain a standard ring main unit fault operation data set; acquiring a ring main unit fault diagnosis requirement, the ring main unit fault diagnosis requirement including a fault type, a fault level and a fault generation cause; classifying, training and fusing the standard ring main unit fault operation data set according to the ring main unit fault diagnosis requirement to construct a ring main unit fault identification model.

[0051] The specific configuration of the fault identification unit 30 will be described in detail below. The fault identification unit 30 may further include: classifying and marking the standard ring main unit fault operation data set according to the ring main unit fault diagnosis requirement to obtain a ring main unit fault clustering data set; performing model selection training on the ring main unit fault clustering data set to obtain a fault type identification model, a fault level identification model, and a fault generation cause identification model; integrating the fault type identification model, the fault level identification model, and the fault generation cause identification model to obtain a ring main unit fault identification model.

[0052] The specific configuration of the fault identification unit 30 will be described in detail below. The fault identification unit 30 may further include: performing characteristic analysis and model selection on the ring main unit fault clustering data set respectively to determine a machine learning model architecture set; using the machine learning model architecture set to perform identification training on the ring main unit fault clustering data set respectively to obtain an initial fault type model, an initial fault level model, and a fault generation cause model; verifying, evaluating, and optimizing the initial fault type model, the initial fault level model, and the fault generation cause model to obtain the fault type identification model, the fault level identification model, and the fault generation cause identification model.

[0053] The specific configuration of the early warning operation and maintenance management unit 50 will be described in detail below. The early warning operation and maintenance management unit 50 further includes: generating a ring main unit fault monitoring and diagnosis report according to the ring main unit fault diagnosis information and the ring main unit fault location information; building a ring main unit fault operation and maintenance knowledge base; analyzing the ring main unit fault monitoring and diagnosis report based on the ring main unit fault operation and maintenance knowledge base to obtain a ring main unit fault operation and maintenance plan; and performing early warning operation and maintenance management on the target ring main unit based on the ring main unit fault operation and maintenance plan.

[0054] The intelligent monitoring and early warning device for a ring main unit provided in an embodiment of the present invention can execute the intelligent monitoring and early warning method for a ring main unit provided in any embodiment of the present invention, and has functional modules and beneficial effects corresponding to the execution method.

[0055] Although the present application makes various references to certain modules in the device according to the embodiments of the present application, any number of different modules may be used and run on the user terminal and / or server, and the various units and modules included are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of the present invention.

[0056] The above specific implementations do not constitute a limitation on the protection scope of this application. It should be understood by those skilled in the art that various modifications, combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of this application should be included in the protection scope of this application.

Claims

1. An intelligent monitoring and early warning method for a ring main unit, characterized in that: The method comprises: A data acquisition module is set on the target ring main unit, and the data acquisition module is used to monitor and acquire the working status data stream of the ring main unit in real time, wherein the working status data stream of the ring main unit includes equipment data and environmental data; Wirelessly transmitting the ring main unit working status data stream to the analysis and processing module for feature extraction processing to obtain a ring main unit working feature set; Constructing a ring main unit fault identification model, performing fault identification on the ring main unit working feature set based on the ring main unit fault identification model, and obtaining ring main unit fault diagnosis information; Based on the ring main unit fault diagnosis information, the fault location of the target ring main unit is located to obtain the fault location information of the ring main unit; Based on the ring main unit fault diagnosis information and the ring main unit fault location information, early warning operation and maintenance management is performed on the target ring main unit.

2. The intelligent monitoring and early warning method for ring main unit according to claim 1, characterized in that: The obtaining of the ring main unit working characteristic set comprises: Perform encryption level evaluation on the ring main unit working status data stream according to the ring main unit data application standard to obtain the ring main unit data encryption evaluation level; According to the data encryption assessment level of the ring main unit, select and determine the data encryption algorithm; Encrypting the ring main unit working status data stream based on the data encryption algorithm, and wirelessly transmitting the encrypted ring main unit working status data stream to the analysis and processing module; The working status data stream of the ring main unit is subjected to feature extraction processing via the wireless transmission to the analysis and processing module to obtain a working feature set of the ring main unit.

3. The intelligent monitoring and early warning method for ring main unit according to claim 1, characterized in that: The obtaining of the ring main unit working characteristic set comprises: Extracting associated features from the ring main unit working status data stream to obtain a ring main unit associated working feature set; Performing operation correlation analysis on each working feature in the ring main unit associated working feature set respectively to obtain a working feature correlation set; A correlation threshold is set, and feature screening is performed on the working feature correlation set based on the correlation threshold to obtain the working feature set of the ring main unit.

4. The intelligent monitoring and early warning method for ring main unit according to claim 1, characterized in that: The construction of the ring main unit fault identification model includes: Acquire a ring main unit fault operation data set, pre-process the ring main unit fault operation data set, and obtain a standard ring main unit fault operation data set; Acquire the ring main unit fault diagnosis requirement, wherein the ring main unit fault diagnosis requirement includes the fault type, fault level and fault generation cause; According to the ring main unit fault diagnosis requirements, the standard ring main unit fault operation data set is classified, trained and integrated to build a ring main unit fault identification model.

5. The intelligent monitoring and early warning method for ring main unit according to claim 4, characterized in that: The construction of the ring main unit fault identification model includes: Classify and mark the standard ring main unit fault operation data set according to the ring main unit fault diagnosis requirements to obtain a ring main unit fault clustering data set; Performing model selection training on the ring main unit fault clustering data set respectively to obtain a fault type identification model, a fault level identification model and a fault generation cause identification model; The fault type identification model, the fault level identification model and the fault generation cause identification model are integrated to obtain a ring main unit fault identification model.

6. The intelligent monitoring and early warning method for ring main unit according to claim 5, characterized in that: The method of obtaining a fault type identification model, a fault level identification model and a fault generation cause identification model includes: Performing characteristic analysis and model selection on the ring main unit fault clustering data set respectively to determine a machine learning model architecture set; The machine learning model architecture set is used to perform identification training on the ring main unit fault clustering data set to obtain an initial fault type model, an initial fault level model and a fault generation cause model; The initial fault type model, the initial fault level model and the fault generation cause model are verified, evaluated and optimized to obtain the fault type identification model, the fault level identification model and the fault generation cause identification model.

7. The intelligent monitoring and early warning method for ring main unit according to claim 6, characterized in that: The performing early warning operation and maintenance management on the target ring main unit includes: Generate a ring main unit fault monitoring and diagnosis report according to the ring main unit fault diagnosis information and the ring main unit fault location information; Build a knowledge base for ring main unit fault operation and maintenance; Analyze the ring main unit fault monitoring and diagnosis report based on the ring main unit fault operation and maintenance knowledge base to obtain a ring main unit fault operation and maintenance solution; Based on the ring main unit fault operation and maintenance plan, early warning operation and maintenance management is performed on the target ring main unit.

8. An intelligent monitoring and early warning device for a ring main unit, characterized in that: The device is used to implement the intelligent monitoring and early warning method for a ring main unit according to any one of claims 1 to 7, and the device comprises: A data stream real-time monitoring unit, used to set a data acquisition module on the target ring main unit, and to acquire the ring main unit working status data stream in real time through the data acquisition module, wherein the ring main unit working status data stream includes equipment data and environmental data; A feature extraction and processing unit, used for wirelessly transmitting the ring main unit working status data stream to the analysis and processing module for feature extraction and processing to obtain a ring main unit working feature set; A fault identification unit is used to construct a ring main unit fault identification model, perform fault identification on the ring main unit working feature set based on the ring main unit fault identification model, and obtain ring main unit fault diagnosis information; A fault locating unit, used to locate the fault of the target ring main unit based on the fault diagnosis information of the ring main unit, and obtain the fault position information of the ring main unit; The early warning operation and maintenance management unit is used to perform early warning operation and maintenance management on the target ring main unit based on the fault diagnosis information of the ring main unit and the fault location information of the ring main unit.

Images