Power equipment abnormity early warning system for mobile terminal

Abstract

The invention relates to the technical field of organic electroluminescence adjustment, and provides a power equipment abnormity early warning system for a mobile terminal, which integrates a real-time monitoring module, an early warning identification module and a data detection module. By monitoring operation data of the power equipment in real time, combining with a random forest model to carry out abnormity early warning, sending early warning information to a mobile terminal in real time and receiving user feedback to optimize an early warning strategy, a data detection module carries out grouping processing on the power equipment based on a time period, so that the data processing efficiency is improved; the system achieves the comprehensive monitoring of the operation state of the power equipment, remarkably improves the early warning accuracy, response speed and user interaction experience, effectively guarantees the safe and stable operation of a power system, promotes the scientific maintenance and management of the power equipment, is suitable for various types of power equipment, and improves the safety and reliability of the power equipment. The method has a wide application prospect and an important practical value, and provides powerful support for intelligent and safe operation of an electric power system.

Description

Technical Field

[0001] The present invention relates to the technical field of power equipment data processing, and in particular to a power equipment abnormality early warning system for a mobile terminal. Background Art

[0002] The abnormal warning system for power equipment on the mobile terminal integrates intelligent management systems based on technologies such as smart sensors, the Internet of Things, cloud computing, big data, and artificial intelligence. It monitors the operating status of power equipment in real time, including parameters such as current, voltage, temperature, humidity, and leakage, and pushes monitoring data in real time through mobile devices such as mobile APP. When the equipment parameters exceed the preset threshold, the system will immediately issue an early warning signal to remind the operation and maintenance personnel to deal with it in time, thereby effectively preventing equipment failures and power accidents. The abnormal warning system for power equipment on the mobile terminal also has functions such as fault warning, data analysis, remote control, and intelligent operation and maintenance, providing users with comprehensive power management services and improving the safety of power equipment operation.

[0003] The abnormal warning system for power equipment at the mobile terminal has the following technical pain points in the data processing process. The abnormal warning system for power equipment at each end of the power supply needs to collect data of the power equipment at the power supply end during actual use. When engineering and technical personnel use the abnormal warning system for power equipment at the mobile terminal, if the abnormal warning of the power equipment is inaccurate, the engineering and technical personnel will not be able to accurately judge the fault. Since the accuracy of the data of the power equipment at each end of the power supply cannot be detected, the engineering and technical personnel cannot correct the power equipment data on site. In order to solve this technical pain point, the present invention provides an abnormal warning system for power equipment at the mobile terminal. Summary of the invention

[0004] In view of the deficiencies in the prior art, the present invention provides an abnormal warning system for electric power equipment for mobile terminals, which solves the problem that when the abnormal warning of electric power equipment is inaccurate, it will cause engineering and technical personnel to be unable to accurately judge the fault. Since it is impossible to detect the accuracy of the data of the electric power equipment at each end of the power supply, the engineering and technical personnel cannot correct the electric power equipment data on site.

[0005] In order to solve the above technical problems, the specific technical solutions of the present invention are as follows: The present invention provides an abnormal warning system for electric power equipment for a mobile terminal, comprising: a server terminal, a mobile terminal and a background control terminal, wherein the server terminal establishes a communication connection with the mobile terminal and the background control terminal, and the server terminal comprises: A data acquisition module is used to acquire the operating parameters of the power equipment, the preset thresholds of the power equipment, the information of the power equipment and the historical operating data of the power equipment, and to train the random forest model using the operating parameters of the power equipment, the preset thresholds of the power equipment, the information of the power equipment and the historical data of the power equipment to obtain an abnormal warning model for the power equipment; The real-time monitoring module collects real-time power equipment operation data, substitutes the real-time power equipment operation data into the power equipment abnormal warning model, and obtains power equipment abnormal warning information; The early warning identification module sends the abnormal early warning information of the power equipment to the mobile terminal, receives the data fed back by the mobile terminal, and if the fed back data shows that the abnormal early warning information of the power equipment is inaccurate, extracts the power equipment in the abnormal early warning information of the power equipment, obtains the power equipment included in the abnormal early warning information of the power equipment, and uses the power equipment included in the abnormal early warning information of the power equipment as the power equipment to be detected; a data detection module, which groups the power equipment to be detected according to time periods to obtain grouped data of the power equipment to be detected, wherein the grouped data of the power equipment to be detected includes a first data group of the power equipment to be detected, a second data group of the power equipment to be detected, a third data group of the power equipment to be detected, and a fourth data group of the power equipment to be detected, and sequentially substitutes the first data group of the power equipment to be detected, the second data group of the power equipment to be detected, the third data group of the power equipment to be detected, and the fourth data group of the power equipment to be detected into the power equipment abnormality early warning model to obtain the first data result of the power equipment to be detected, the second data result of the power equipment to be detected, the third data result of the power equipment to be detected, and the fourth data result of the power equipment to be detected; The data processing module transmits the data results of the first power equipment to be detected, the data results of the second power equipment to be detected, the data results of the third power equipment to be detected, and the data results of the fourth power equipment to be detected to the mobile terminal in sequence, receives feedback information of the data results of the power equipment to be detected from the mobile terminal, generates an optimized power equipment abnormality warning model based on the feedback information of the data results of the power equipment to be detected from the mobile terminal, and deploys the optimized power equipment abnormality warning model in the power equipment abnormality warning system.

[0006] Furthermore, in the power equipment abnormality early warning system for a mobile terminal of the present invention, the data processing module is also used for: The feedback information of the data results of the power equipment to be detected includes whether the data results of the power equipment to be detected are accurate and whether the data results of the power equipment to be detected are inaccurate. Data features are extracted from the data corresponding to the inaccurate data results of the power equipment to be detected to obtain the data features of the power equipment corresponding to the inaccurate data results of the power equipment to be detected. The data features of the power equipment corresponding to the inaccurate data results of the power equipment to be detected are sequentially substituted into a preset data detection model to obtain data feature detection results. The data feature detection results include qualified data and unqualified data feature detection data. The data corresponding to the unqualified data feature detection data are retrieved, and the data corresponding to the unqualified data feature detection data are substituted into a preset data simulation model to output simulation data corresponding to the unqualified data feature detection data.

[0007] Furthermore, in the power equipment abnormality early warning system for a mobile terminal of the present invention, the data processing module is also used for: The simulation data corresponding to the data that fails the data feature detection is replaced in the grouped data of the power equipment to be detected to generate a corrected data group, and the corrected data group is substituted into the power equipment abnormal warning model to obtain the power equipment warning information corresponding to the corrected data, and the power equipment warning information corresponding to the corrected data is sent to the mobile terminal. If the data fed back by the mobile terminal is that the power equipment warning information corresponding to the corrected data is inaccurate, the power equipment abnormal warning model is optimized using a genetic algorithm based on the data generated by the data acquisition module, the real-time monitoring module, the warning identification module, the data detection module and the data processing module to obtain the optimized power equipment abnormal warning model, and the optimized power equipment abnormal warning model is deployed in the power equipment abnormal warning system.

[0008] Furthermore, in the power equipment abnormality early warning system for a mobile terminal of the present invention, the data processing module is also used for: The data acquired from the data acquisition module, the real-time monitoring module, the early warning identification module, the data detection module and the data processing module are used to obtain a basic data set of the power equipment, which includes power equipment operating parameters, preset thresholds, historical data, real-time data, early warning information, feedback data and data feature detection results; receiving an objective and a fitness function optimized according to the abnormal warning model of the power equipment, wherein the objective of the abnormal warning model of the power equipment is the false alarm rate, and the fitness function is used to evaluate the quality of each solution; According to the parameter space of the abnormal warning model of the power equipment, an initial solution is randomly generated. The solution is the parameter of the abnormal warning model of the power equipment. The initial solution is evaluated using the fitness function as the population of the genetic algorithm to obtain the result of the fitness function. Selection operation, based on the result of the fitness function, selects the best solution as the parent generation to generate the next generation; Crossover operation: Perform a crossover operation on the selected parent generation to generate a new solution; Mutation operation: Perform mutation operation on the newly generated solution to introduce new genes, that is, introduce new solutions; The selection, crossover, and mutation operations are repeated until a preset number of iterations or optimization goal is reached.

[0009] Furthermore, in the power equipment abnormality early warning system for a mobile terminal of the present invention, the real-time monitoring module is also used for: The real-time monitoring module collects the operating data of the power equipment in real time through sensors. The operating data of the power equipment includes current, voltage, temperature, power factor and vibration; Preprocess the collected real-time data, extract features related to abnormal warning of power equipment from the preprocessed data, and load the trained abnormal warning model of power equipment. The abnormal warning model of power equipment is built based on random forest and is used to identify abnormal patterns in the operation data of power equipment; The extracted features are used as input and substituted into the power equipment abnormality warning model. The power equipment abnormality warning model calculates the score of the power equipment abnormality based on the features. According to the output of the power equipment abnormality warning model, the power equipment abnormality warning information is generated. The power equipment abnormality warning information includes the type, severity, occurrence time and equipment information of the abnormality.

[0010] Furthermore, in the abnormal warning system for electric power equipment used in a mobile terminal of the present invention, the warning identification module is also used for: The early warning identification module sends the abnormal early warning information of the power equipment received from the real-time monitoring module to the mobile terminal through the wireless network; Waiting for and receiving feedback from mobile users on the warning information. The user's feedback on the warning information includes confirming that the warning is accurate or inaccurate; judging the accuracy of the feedback: Analyze the feedback received from the mobile user on the warning information to determine whether the user believes that the warning information is accurate. If the user feedbacks that the warning information is inaccurate, proceed to the next step. If the user confirms that the warning information is accurate, end the current process. If the warning information is judged to be inaccurate, the warning identification module will extract the power equipment included in the warning information, identify and extract the warning power equipment identification, which includes the equipment number, equipment name and equipment type; The extracted power equipment information is sorted into a list to form a list of power equipment to be detected, and the list of power equipment to be detected includes power equipment that is determined to have inaccurate warnings.

[0011] Furthermore, in the power equipment abnormality early warning system for a mobile terminal of the present invention, the data detection module is also used for: The grouping is based on the time period, based on the time unit of hour, day, week or month, to obtain the data of the power equipment to be detected, the data of the power equipment to be detected includes the identification information of the power equipment and the corresponding operation timestamp, the identification information of the power equipment includes the equipment number and the equipment name; According to the timestamp in the data, all the data of the power equipment to be detected are sorted, and according to the preset rules, the time interval of each group is calculated according to the total time range of the data and the number of groups. According to the calculated time interval, the data is allocated to different groups. The first data group of the power equipment to be detected includes all the data in the first time period, the second data group of the power equipment to be detected includes all the data in the second time period, the third data group of the power equipment to be detected includes all the data in the third time period, and the fourth data group of the power equipment to be detected includes all the data in the fourth time period.

[0012] The beneficial effects of the present invention are mainly reflected in the following aspects: The abnormal warning system for electric power equipment used in a mobile terminal of the present invention realizes comprehensive monitoring and abnormal warning of the operating status of electric power equipment by integrating multiple modules such as real-time monitoring, early warning identification and data detection. Its beneficial effects are mainly reflected in the following aspects: The system adopts advanced real-time monitoring technology to collect the operating data of power equipment in real time. Through preprocessing and feature extraction, combined with an abnormal warning model based on random forest, it can accurately identify abnormal patterns in the operation of power equipment and significantly improve the accuracy of warning.

[0013] The system sends warning information to the mobile terminal instantly via the wireless network, allowing users to quickly learn about abnormal conditions of power equipment and take corresponding measures, effectively shortening the time from discovering the abnormality to handling the abnormality and enhancing the response speed.

[0014] The data detection module organizes the power equipment data to be detected in an orderly manner through time-based grouping processing, providing a structured data basis for subsequent analysis and anomaly detection, optimizing data processing efficiency and reducing system burden.

[0015] The early warning identification module interacts with users, receives user feedback on early warning information, and adjusts the early warning strategy based on the feedback, which improves the intelligence level of the system and also improves the user's interactive experience, making users trust and use the system more.

[0016] Through real-time monitoring and abnormal early warning, the system can promptly detect potential problems in the operation of power equipment and avoid power outages or safety accidents caused by equipment failure, thereby ensuring the safe and stable operation of the power system and reducing economic losses and social impacts.

[0017] To sum up, the power equipment abnormality warning system for mobile terminals described in the present invention shows significant beneficial effects in improving warning accuracy, enhancing response speed, optimizing data processing efficiency, enhancing user interaction experience, ensuring safe and stable operation of the power system, and promoting power equipment maintenance and management. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solution of the present invention, the following briefly introduces the drawings required for use in the embodiments. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0019] Figure 1 A schematic diagram of functional modules in an abnormal warning system for electric power equipment for a mobile terminal provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0020] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described in conjunction with the specific embodiments of the present invention and the corresponding drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention. The technical solutions provided by the embodiments of the present invention are described in detail below in conjunction with the drawings.

[0021] In order to better understand the purpose of the present invention, the present invention is described in further detail below.

[0022] The present invention provides an abnormal warning system for electric power equipment for a mobile terminal, comprising: a server terminal, a mobile terminal and a background control terminal, wherein the server terminal establishes a communication connection with the mobile terminal and the background control terminal, and the server terminal comprises: A data acquisition module is used to acquire the operating parameters of the power equipment, the preset thresholds of the power equipment, the information of the power equipment and the historical operating data of the power equipment, and to train the random forest model using the operating parameters of the power equipment, the preset thresholds of the power equipment, the information of the power equipment and the historical data of the power equipment to obtain an abnormal warning model for the power equipment; Power equipment operating parameters: including current, voltage, temperature, humidity, power factor, vibration, etc., which are real-time data reflecting the current operating status of the power equipment.

[0023] Preset thresholds for power equipment: Parameter limits set according to the normal operating range and safety standards of the power equipment are used to determine whether the equipment is in an abnormal state.

[0024] Power equipment information: basic information such as equipment model, specifications, manufacturer, installation location, etc., which helps to monitor and manage the equipment more accurately.

[0025] Historical operation data of power equipment: Long-term accumulated equipment operation records, including past operating status, fault records, maintenance history, etc., are very valuable for analyzing equipment performance and predicting potential failures.

[0026] Clean and preprocess the collected raw data to remove noise, outliers and missing values ​​to ensure data accuracy and consistency. Format the data to meet the requirements of model input.

[0027] Use the processed data to train the random forest model. Random forest is an ensemble learning method that improves the accuracy and stability of the model by building multiple decision trees and combining their prediction results. During the training process, the model learns how to identify abnormal patterns from the input data, which will be used for subsequent abnormal warnings.

[0028] After training is completed, the data acquisition module will output an abnormal warning model for power equipment. This model can receive new power equipment operation data as input and output the judgment result of whether the equipment is in an abnormal state.

[0029] As new data is continuously collected and processed, the data acquisition module can also regularly update and optimize the trained random forest model to improve the accuracy and timeliness of early warnings. This can be achieved through incremental learning or online learning, so that the model can adapt to the dynamic changes in the operating status of power equipment.

[0030] The data acquisition module comprehensively collects the operating parameters, preset thresholds, equipment information and historical operating data of the power equipment, and uses these data to train the random forest model, thereby building an early warning model that can accurately judge the abnormal status of the power equipment.

[0031] The real-time monitoring module collects real-time power equipment operation data, substitutes the real-time power equipment operation data into the power equipment abnormal warning model, and obtains power equipment abnormal warning information; The real-time monitoring module is a key component of the present invention for collecting and analyzing real-time operation data of power equipment. The specific workflow and functions are as follows: The real-time monitoring module collects the operation data of the power equipment in real time through various sensors installed on the power equipment (such as current sensors, voltage sensors, temperature sensors, humidity sensors, etc.). These data include key parameters such as current, voltage, temperature, humidity, power factor, vibration, etc., which can fully reflect the current operation status of the power equipment.

[0032] The collected raw data may contain noise, outliers or missing values, which will affect the accuracy of the early warning model. Therefore, the real-time monitoring module will pre-process the data, including denoising, filling missing values, smoothing, etc., to ensure the accuracy and consistency of the data.

[0033] Extract features related to abnormal warning of power equipment from the preprocessed data. These features may include sudden changes in certain parameters, values ​​outside the normal range, abnormal correlations between parameters, etc.

[0034] The extracted features are used as input to the trained power equipment abnormality warning model. This model is built based on random forest or other machine learning algorithms and can automatically identify abnormal patterns in the data.

[0035] According to the output of the model, the real-time monitoring module will generate corresponding abnormal warning information of power equipment. This information may include the type of abnormality (such as overheating, overcurrent, overvoltage, etc.), severity, occurrence time, and involved equipment information.

[0036] The generated warning information is transmitted in real time to the mobile terminal or background control terminal via wireless network or other communication methods, so that engineering and technical personnel can understand the operating status of the equipment in time and take necessary measures.

[0037] It can collect and process the operation data of power equipment in real time to ensure the timeliness and accuracy of early warning information. By integrating sensors and machine learning models, it realizes the automatic monitoring and early warning of the operation status of power equipment. It can be customized and expanded according to different power equipment types and monitoring requirements to adapt to different application scenarios. It adopts advanced data preprocessing and feature extraction technology to improve the reliability and accuracy of early warning information.

[0038] To sum up, the real-time monitoring module is one of the core components for realizing abnormal warning of power equipment in the present invention. It provides timely and accurate warning information for engineering and technical personnel by real-time collection and processing of operating data of power equipment and using trained warning models for abnormal detection, which helps to reduce equipment failure rate and improve the operating safety and stability of the power system.

[0039] The early warning identification module sends the abnormal early warning information of the power equipment to the mobile terminal, receives the data fed back by the mobile terminal, and if the fed back data shows that the abnormal early warning information of the power equipment is inaccurate, extracts the power equipment in the abnormal early warning information of the power equipment, obtains the power equipment included in the abnormal early warning information of the power equipment, and uses the power equipment included in the abnormal early warning information of the power equipment as the power equipment to be detected; The early warning identification module is responsible for transmitting the abnormal warning information generated by the real-time monitoring module to engineering and technical personnel in the entire power equipment abnormal warning system, and collecting their feedback on the warning information so that the system can be continuously optimized and improved. The following is the specific workflow and function analysis of the early warning identification module: The early warning identification module first receives the abnormal warning information of power equipment from the real-time monitoring module. This information includes the type, severity, occurrence time and specific equipment information of the abnormality. The early warning identification module will send this warning information to the mobile devices (such as mobile phones, tablets, etc.) of engineering and technical personnel in real time through wireless networks or other communication methods.

[0040] After receiving the warning information, the engineering and technical personnel will judge the accuracy of the warning according to the actual situation and feedback their judgment results to the system through the mobile device. The warning identification module is responsible for receiving this feedback data and processing and analyzing it.

[0041] Based on the feedback from the engineers, the early warning identification module will determine the accuracy of the early warning information. If the engineers believe that the early warning information is inaccurate, the early warning identification module will proceed to the next step of the processing flow. If the early warning information is confirmed to be accurate, the early warning identification module will end the current process and continue to monitor the operating status of other equipment.

[0042] For power equipment whose warnings are considered inaccurate, the warning identification module will extract them and identify specific information such as equipment number, equipment name and equipment type. This information will be used in subsequent data detection and model optimization processes.

[0043] The early warning identification module can effectively transmit early warning information to engineering and technical personnel, and collect their feedback on the accuracy of early warnings, providing data support for the continuous optimization of the system. Through the feedback of engineering and technical personnel, the early warning identification module can judge the accuracy of early warning information, thereby avoiding unnecessary panic and misunderstanding. For equipment with inaccurate early warnings, the early warning identification module can accurately extract its relevant information, providing a basis for subsequent data detection and model optimization. The early warning identification module plays a connecting role in the entire system. It connects the real-time monitoring module and the data processing module to ensure the effective transmission and processing of early warning information.

[0044] In summary, the early warning identification module provides strong support for the continuous optimization and improvement of the abnormal early warning system of power equipment by transmitting early warning information, collecting feedback data, judging the accuracy of early warning, and extracting power equipment to be detected.

[0045] a data detection module, which groups the power equipment to be detected according to time periods to obtain grouped data of the power equipment to be detected, wherein the grouped data of the power equipment to be detected includes a first data group of the power equipment to be detected, a second data group of the power equipment to be detected, a third data group of the power equipment to be detected, and a fourth data group of the power equipment to be detected, and sequentially substitutes the first data group of the power equipment to be detected, the second data group of the power equipment to be detected, the third data group of the power equipment to be detected, and the fourth data group of the power equipment to be detected into the power equipment abnormality early warning model to obtain the first data result of the power equipment to be detected, the second data result of the power equipment to be detected, the third data result of the power equipment to be detected, and the fourth data result of the power equipment to be detected; The data detection module is a key part of the present invention for further verifying and analyzing the accuracy of abnormal warning information of power equipment. By grouping the data of the power equipment to be detected by time period and substituting them into the abnormal warning model of the power equipment for detection, the system can more accurately judge the accuracy of the warning information. The following is the specific workflow and function analysis of the data detection module: The data detection module first receives the list of power devices to be detected from the early warning identification module. These devices are considered to be power devices for which the early warning information may be inaccurate. The data detection module groups the operating data of these devices by time period. The grouping can be based on different time units such as hours, days, weeks or months, depending on the system configuration and requirements. The grouped data will form multiple data groups of power devices to be detected, such as the first data group of power devices to be detected, the second data group of power devices to be detected, etc. Each data group includes the equipment operation data within a specific time period.

[0046] For each data group of power equipment to be detected, the data detection module will sequentially substitute it into the trained power equipment abnormal warning model. The model will run its internal algorithms and logic based on the input data group to generate corresponding data results. These data results will reflect the operating status and abnormal warning of the power equipment in that time period. The data detection module will organize and summarize the data results obtained after substituting each data group into the model, including the warning status, abnormal parameters, abnormal types and other information of the power equipment in each time period, providing a basis for subsequent data processing and model optimization.

[0047] By grouping the operating data of the power equipment to be tested by time period, the data detection module can analyze the operating status and abnormal conditions of the equipment in different time periods in more detail, thereby improving the accuracy of the early warning information. By substituting the abnormal early warning model of the power equipment for detection, the data detection module can verify the accuracy of the early warning information and discover possible false alarms or omissions. The data detection module organizes and summarizes the test results and outputs them, providing important data support for subsequent data processing and model optimization.

[0048] Through the above-mentioned work flow and functions of the data detection module, the present invention can more accurately determine the accuracy of abnormal warning information of power equipment and provide strong data support for the continuous optimization and improvement of the system.

[0049] The data processing module transmits the data results of the first power equipment to be detected, the data results of the second power equipment to be detected, the data results of the third power equipment to be detected, and the data results of the fourth power equipment to be detected to the mobile terminal in sequence, receives feedback information of the data results of the power equipment to be detected from the mobile terminal, generates an optimized power equipment abnormality warning model based on the feedback information of the data results of the power equipment to be detected from the mobile terminal, and deploys the optimized power equipment abnormality warning model in the power equipment abnormality warning system.

[0050] The data processing module is the key part of the present invention responsible for processing and analyzing the results output by the data detection module, and generating an optimized abnormal warning model for power equipment based on these results. The following is the specific workflow and functional analysis of the data processing module: The data processing module first receives the data results of the first power equipment to be detected, the second power equipment to be detected, the third power equipment to be detected, and the fourth power equipment to be detected from the data detection module. The data results include information such as the operating status, abnormal parameters, and abnormal types of the power equipment in each time period. The data processing module transmits these data results to the mobile devices of engineering and technical personnel through wireless networks or other communication methods for them to view and analyze.

[0051] After viewing the data results on the mobile device, the engineering and technical personnel will judge the accuracy of the data results based on their professional knowledge and practical experience, and feedback their opinions and suggestions to the data processing module through the mobile device.

[0052] Based on the feedback from engineers and technicians, the data processing module will optimize the abnormal warning model for power equipment. The optimization may include adjusting the parameters of the model, improving the logic of the algorithm, adding new feature variables, etc., to improve the accuracy and stability of the model. The optimized model will be able to better identify the abnormal status of power equipment and reduce false positives and false negatives.

[0053] The data processing module packages and encapsulates the optimized power equipment abnormal warning model so that it can be deployed in the power equipment abnormal warning system. The deployed model will receive the operation data of the power equipment in real time, and perform abnormal detection and warning, providing strong guarantee for the safe operation of the power system.

[0054] Data result transmission function: Ensure that the output results of the data detection module can be transmitted to the mobile devices of engineering and technical personnel in a timely and accurate manner so that they can view and analyze them. Collect feedback and suggestions from engineering and technical personnel to provide important data support for model optimization. Optimize the power equipment abnormal warning model based on feedback information to improve the accuracy and stability of the model. Deploy the optimized model in the power equipment abnormal warning system to realize the functions of real-time abnormal detection and warning.

[0055] In summary, the data processing module provides strong support for the continuous optimization and improvement of the abnormal early warning system for power equipment through the work processes and functions such as data result transmission, feedback information reception, model optimization and model deployment. By continuously optimizing the model, the present invention can more accurately identify the abnormal state of power equipment and improve the operational safety and stability of the power system.

[0056] Specifically, in the power equipment abnormality early warning system for a mobile terminal of the present invention, the data processing module is also used for: The feedback information of the data results of the power equipment to be detected includes whether the data results of the power equipment to be detected are accurate and whether the data results of the power equipment to be detected are inaccurate. Data features are extracted from the data corresponding to the inaccurate data results of the power equipment to be detected to obtain the data features of the power equipment corresponding to the inaccurate data results of the power equipment to be detected. The data features of the power equipment corresponding to the inaccurate data results of the power equipment to be detected are sequentially substituted into a preset data detection model to obtain data feature detection results. The data feature detection results include qualified data and unqualified data feature detection data. The data corresponding to the unqualified data feature detection data are retrieved, and the data corresponding to the unqualified data feature detection data are substituted into a preset data simulation model to output simulation data corresponding to the unqualified data feature detection data.

[0057] In the abnormal warning system for electric power equipment for mobile terminals described in the present invention, the data processing module undertakes the important tasks of in-depth analysis, processing and simulation of detection data. The following is the workflow and function analysis of the newly added functions of the data processing module: The data processing module first receives the feedback information of the data results of the power equipment to be detected from the mobile terminal. The feedback information is divided into two categories: accurate detection of the power equipment data results and inaccurate detection of the power equipment data results. For the information of inaccurate detection of the power equipment data results, the module will perform further processing.

[0058] For information about inaccurate data results of power equipment detection, the data processing module will extract data features. The extracted features may include the numerical range of abnormal data, change trend, correlation with other parameters, etc. These features help to understand the reasons for inaccurate data.

[0059] The extracted data features will be sequentially substituted into the preset data detection model. The data detection model will analyze these features to determine whether they meet the feature range of normal data. The detection results are divided into qualified data and unqualified data.

[0060] Unqualified data processing,For data that fails the data feature detection, the data processing module will further process it.,Data that fails the data feature detection includes the key factors that lead to inaccurate warning information,,so it needs special attention.

[0061] The data processing module retrieves the data corresponding to the data that failed the data feature detection. These data are substituted into the preset data simulation model to simulate the possible performance of the data in the operation of the power equipment. The simulation data is output, which helps to understand the reasons for the failure of the data feature detection and provides a basis for subsequent data processing and model optimization.

[0062] The feedback information classification and processing function can efficiently classify and process the information fed back by the mobile terminal, and quickly identify the data that needs further processing. The data feature extraction function can extract key features from complex data, providing strong support for subsequent data analysis and processing. Through the preset data detection model, the eligibility of data features can be accurately judged, providing strong guarantee for data quality control. Special processing of data that fails data feature detection helps to deeply explore problems in the data and improve the accuracy of the early warning system. Through the data simulation model, simulated data can be generated to provide strong support for understanding the reasons for unqualified data feature detection and subsequent data processing.

[0063] In summary, the data processing module further improves the accuracy and stability of the power equipment abnormality warning system through the newly added functions of feedback information classification processing, data feature extraction, data feature detection, unqualified data processing, and data simulation and output.

[0064] Specifically, in the power equipment abnormality early warning system for a mobile terminal of the present invention, the data processing module is also used for: The simulation data corresponding to the data that fails the data feature detection is replaced in the grouped data of the power equipment to be detected to generate a corrected data group, and the corrected data group is substituted into the power equipment abnormal warning model to obtain the power equipment warning information corresponding to the corrected data, and the power equipment warning information corresponding to the corrected data is sent to the mobile terminal. If the data fed back by the mobile terminal is that the power equipment warning information corresponding to the corrected data is inaccurate, the power equipment abnormal warning model is optimized using a genetic algorithm based on the data generated by the data acquisition module, the real-time monitoring module, the warning identification module, the data detection module and the data processing module to obtain the optimized power equipment abnormal warning model, and the optimized power equipment abnormal warning model is deployed in the power equipment abnormal warning system.

[0065] In the abnormal warning system for electric power equipment for mobile terminals described in the present invention, the data processing module is not only responsible for processing and analyzing data, but also undertakes the important task of optimizing and iterating the warning model. The following is a detailed workflow and functional analysis of the new functions of the data processing module, especially the part about model optimization and deployment: For data that fails the data feature detection, the data processing module has generated corresponding simulation data through the data simulation model. The module will replace these simulation data with the original group data of the power equipment to be detected to generate a revised data group. The revised data group more accurately reflects the actual operating status of the power equipment, which helps to improve the accuracy of the early warning information.

[0066] The data processing module substitutes the corrected data set into the power equipment abnormal warning model. The model will generate new power equipment warning information based on the corrected data set. These warning information are more accurate and can more effectively reflect the abnormal status of the power equipment.

[0067] The data processing module sends the power equipment warning information corresponding to the corrected data to the mobile terminal for engineering and technical personnel to view and verify. The engineering and technical personnel will judge the accuracy of the warning information based on their professional knowledge and practical experience, and feedback their opinions and suggestions to the data processing module through the mobile terminal device.

[0068] If the data fed back by the mobile terminal indicates that the power equipment warning information corresponding to the corrected data is still inaccurate, the data processing module will start the model optimization process. The module will optimize the power equipment abnormal warning model based on all the data generated by the data acquisition module, real-time monitoring module, warning identification module, data detection module and data processing module using optimization techniques such as genetic algorithms. By simulating natural selection and genetic mechanisms, genetic algorithms can find approximate optimal solutions in complex search spaces, thereby improving the accuracy and stability of the model. The optimized power equipment abnormal warning model will be redeployed in the power equipment abnormal warning system to replace the original model.

[0069] Simulation data replacement and correction data group generation function: by replacing unqualified data, more accurate correction data groups are generated to provide higher quality data input for the model. Correction data group substitution model and warning information generation function: Substitute the corrected data group into the model to generate more accurate warning information and improve the reliability of the warning system.

[0070] Warning information sending and mobile feedback function: ensure that warning information can be conveyed to engineering and technical personnel in a timely and accurate manner, and collect their feedback to provide important basis for model optimization.

[0071] Model optimization and deployment function: Use optimization techniques such as genetic algorithms to optimize the model, improve the accuracy and stability of the model, and deploy the optimized model in the early warning system to achieve continuous iteration and improvement.

[0072] In summary, the data processing module not only improves the accuracy of the power equipment abnormality early warning system, but also realizes the continuous optimization and iteration of the model through the newly added functions of simulation data replacement and correction data group generation, correction data group substitution into the model and early warning information generation, early warning information sending and mobile terminal feedback, and model optimization and deployment, which provides a more powerful guarantee for the safe operation of the power system.

[0073] Specifically, in the power equipment abnormality early warning system for a mobile terminal of the present invention, the data processing module is also used for: The data acquired from the data acquisition module, the real-time monitoring module, the early warning identification module, the data detection module and the data processing module are used to obtain a basic data set of the power equipment, which includes power equipment operating parameters, preset thresholds, historical data, real-time data, early warning information, feedback data and data feature detection results; receiving an objective and a fitness function optimized according to the abnormal warning model of the power equipment, wherein the objective of the abnormal warning model of the power equipment is the false alarm rate, and the fitness function is used to evaluate the quality of each solution; According to the parameter space of the abnormal warning model of the power equipment, an initial solution is randomly generated. The solution is the parameter of the abnormal warning model of the power equipment. The initial solution is evaluated using the fitness function as the population of the genetic algorithm to obtain the result of the fitness function. Selection operation, based on the result of the fitness function, selects the best solution as the parent generation to generate the next generation; Crossover operation: Perform a crossover operation on the selected parent generation to generate a new solution; Mutation operation: Perform mutation operation on the newly generated solution to introduce new genes, that is, introduce new solutions; The selection, crossover, and mutation operations are repeated until a preset number of iterations or optimization goal is reached.

[0074] In the power equipment abnormality warning system for mobile terminals described in the present invention, the data processing module is not only responsible for data processing and analysis, but also undertakes the key task of optimizing the power equipment abnormality warning model using genetic algorithms. The following is a detailed workflow and functional analysis of the data processing module in the model optimization process: The data processing module first integrates the basic data set of power equipment from the data acquisition module, real-time monitoring module, early warning identification module, data detection module and its own acquired data. The data set includes comprehensive information such as power equipment operating parameters, preset thresholds, historical data, real-time data, early warning information, feedback data and data feature detection results, providing a rich data foundation for model optimization.

[0075] The data processing module receives the target optimized according to the abnormal warning model of power equipment, i.e., the false alarm rate, and the fitness function used to evaluate the quality of each solution. The false alarm rate is an important indicator for model optimization. By reducing the false alarm rate, the accuracy and reliability of the warning system can be improved. The fitness function is used to quantify the performance of each solution (i.e., model parameter combination) in reducing the false alarm rate.

[0076] The data processing module randomly generates a set of initial solutions according to the parameter space of the abnormal warning model of power equipment. Each solution represents a set of model parameters. The initial solutions are used as the population of the genetic algorithm and are evaluated using the fitness function to obtain the fitness function results of each solution and its performance in reducing the false alarm rate.

[0077] Selection operation: Based on the results of the fitness function, the data processing module selects solutions with excellent performance as parents to generate the next generation of solutions. The selection operation ensures that excellent genes can be passed on to the next generation, thereby improving the fitness of the overall population.

[0078] Crossover operation: Perform a crossover operation on the selected parent generation, that is, exchange some genes in the parent generation solution in a certain way to generate a new solution. The crossover operation helps to combine the advantages of different parent generations and generate new solutions with more potential.

[0079] Mutation operation: Perform mutation operation on the newly generated solution, that is, randomly change some genes in the solution to introduce new genes and solutions. Mutation operation increases the diversity of the population, helps to jump out of the local optimal solution and explore a wider solution space.

[0080] Iterative optimization: The data processing module repeatedly performs selection, crossover and mutation operations to form an iterative process of the genetic algorithm.

[0081] Through continuous iterations, the solutions in the population gradually approach the optimization goal, that is, reducing the false alarm rate.

[0082] When the preset number of iterations or optimization target is reached, the iteration process is terminated and the optimized power equipment abnormal warning model parameters are obtained.

[0083] Data set construction function: Integrate the data of each module to provide a comprehensive and accurate data basis for model optimization. Optimization target and fitness function setting function: Clarify the optimization target, set the fitness function, and provide evaluation criteria for the genetic algorithm.

[0084] Initial solution generation and evaluation function: Randomly generate initial solutions and use fitness functions to evaluate them to provide a starting population for the genetic algorithm.

[0085] Selection operation function: select excellent solutions as parents to ensure excellent gene transmission.

[0086] Crossover operation function: Combine the advantages of different parents through crossover operation to generate new solutions.

[0087] Mutation operation function: introduce new genes and solutions, increase population diversity, and explore a broader solution space.

[0088] Iterative optimization function: Through continuous iterative selection, crossover and mutation operations, the optimization target is gradually approached to obtain the optimized model parameters.

[0089] In summary, the data processing module plays a vital role in the model optimization process of the power equipment abnormal warning system. By integrating data, setting optimization goals, generating and evaluating initial solutions, performing selection, crossover and mutation operations, and iterative optimization, the data processing module can use genetic algorithms to effectively optimize the power equipment abnormal warning model and improve the accuracy and reliability of the warning system. Specifically, the abnormal warning system for electric power equipment used in a mobile terminal of the present invention, the real-time monitoring module is also used for: The real-time monitoring module collects the operating data of the power equipment in real time through sensors. The operating data of the power equipment includes current, voltage, temperature, power factor and vibration; Preprocess the collected real-time data, extract features related to abnormal warning of power equipment from the preprocessed data, and load the trained abnormal warning model of power equipment. The abnormal warning model of power equipment is built based on random forest and is used to identify abnormal patterns in the operation data of power equipment; The extracted features are used as input and substituted into the power equipment abnormality warning model. The power equipment abnormality warning model calculates the score of the power equipment abnormality based on the features. According to the output of the power equipment abnormality warning model, the power equipment abnormality warning information is generated. The power equipment abnormality warning information includes the type, severity, occurrence time and equipment information of the abnormality.

[0090] The abnormal warning system for electric power equipment used on a mobile terminal of the present invention is responsible for real-time collection of operating data of electric power equipment and generating abnormal warning information through a series of processing. The following is a detailed workflow and functional analysis of this function of the real-time monitoring module: The real-time monitoring module collects the operating data of the power equipment in real time through various sensors installed on the power equipment.

[0091] These data include but are not limited to current, voltage, temperature, power factor and vibration, which can fully reflect the operating status of power equipment.

[0092] Preprocess the collected real-time data, including data cleaning, data conversion, and data normalization.

[0093] The purpose of preprocessing is to eliminate noise and outliers in the data and improve the quality and usability of the data.

[0094] Extract features related to abnormal warning of power equipment from the preprocessed data. These features may be based on statistics, time domain or frequency domain, and can reflect the abnormal patterns of power equipment operation data.

[0095] Load the trained power equipment abnormality warning model. The power equipment abnormality warning model is built based on random forests. It has powerful classification and prediction capabilities and can identify abnormal patterns in power equipment operation data.

[0096] The extracted features are used as input and substituted into the power equipment abnormality warning model. The power equipment abnormality warning model calculates the power equipment abnormality score based on these features. This score reflects the degree to which the power equipment operation data deviates from the normal state. According to the output of the power equipment abnormality warning model, the power equipment abnormality warning information is generated. The warning information includes the type, severity, occurrence time and equipment information of the abnormality, providing timely abnormality alarm and diagnosis basis for engineering and technical personnel.

[0097] Specifically, in the abnormal warning system for electric power equipment used in a mobile terminal of the present invention, the warning identification module is also used for: The early warning identification module sends the abnormal early warning information of the power equipment received from the real-time monitoring module to the mobile terminal through the wireless network; Waiting for and receiving feedback from mobile users on the warning information. The user's feedback on the warning information includes confirming that the warning is accurate or inaccurate; judging the accuracy of the feedback: Analyze the feedback received from the mobile user on the warning information to determine whether the user believes that the warning information is accurate. If the user feedbacks that the warning information is inaccurate, proceed to the next step. If the user confirms that the warning information is accurate, end the current process. If the warning information is judged to be inaccurate, the warning identification module will extract the power equipment included in the warning information, identify and extract the warning power equipment identification, which includes the equipment number, equipment name and equipment type; The extracted power equipment information is sorted into a list to form a list of power equipment to be detected, and the list of power equipment to be detected includes power equipment that is determined to have inaccurate warnings.

[0098] The abnormal warning system for electric power equipment used on a mobile terminal of the present invention is responsible for processing the abnormal warning information received from the real-time monitoring module, interacting with the mobile terminal user to verify the accuracy of the warning, and further processing the inaccurate warning. The following is the workflow and function analysis of the warning identification module: The early warning identification module receives the abnormal early warning information of the power equipment sent by the real-time monitoring module and sends these early warning information to the mobile terminal through the wireless network so that the user can view and process them in real time.

[0099] The warning identification module waits for the mobile user's feedback on the warning information. User feedback includes two situations: confirming that the warning is accurate or inaccurate.

[0100] The warning identification module analyzes the received user feedback to determine whether the user believes that the warning information is accurate. If the user confirms that the warning information is accurate, the current process ends, indicating that the warning has been correctly processed. If the user feedback indicates that the warning information is inaccurate, the next step is entered for further processing.

[0101] For the early warning information that is judged to be inaccurate, the early warning identification module extracts the power equipment information therein, identifies and extracts the identification of the early warning power equipment, including key information such as equipment number, equipment name and equipment type.

[0102] The extracted power equipment information is sorted into a list form to form a list of power equipment to be detected, which includes all power equipment that are determined to have inaccurate warnings.

[0103] The warning information sending function enables abnormal warning information to be sent to mobile users in a timely and accurate manner, improving user response speed and processing efficiency.

[0104] The user feedback receiving function receives and processes the feedback from mobile users on the warning information, providing data support for the accuracy verification of the warning.

[0105] The feedback accuracy judgment function determines the accuracy of the warning information by analyzing and judging user feedback, providing a basis for subsequent processing.

[0106] The power equipment information extraction function extracts the key identification information of the power equipment from the inaccurate warning information, providing basic data for subsequent detection and analysis.

[0107] The function of generating a list of power equipment to be tested organizes the extracted power equipment information into a list format to facilitate subsequent testing and processing.

[0108] In summary, the early warning identification module in the power equipment abnormal early warning system is not only responsible for sending abnormal early warning information to mobile users, but also responsible for receiving and processing user feedback, judging the accuracy of the early warning, and further processing inaccurate early warnings. Through this series of operations, the early warning identification module effectively improves the accuracy of the early warning system and provides a strong guarantee for the safe and stable operation of the power system.

[0109] Specifically, in the abnormal warning system for electric power equipment for a mobile terminal of the present invention, the data detection module is also used for: The grouping is based on the time period, based on the time unit of hour, day, week or month, to obtain the data of the power equipment to be detected, the data of the power equipment to be detected includes the identification information of the power equipment and the corresponding operation timestamp, the identification information of the power equipment includes the equipment number and the equipment name; According to the timestamp in the data, all the data of the power equipment to be detected are sorted, and according to the preset rules, the time interval of each group is calculated according to the total time range of the data and the number of groups. According to the calculated time interval, the data is allocated to different groups. The first data group of the power equipment to be detected includes all the data in the first time period, the second data group of the power equipment to be detected includes all the data in the second time period, the third data group of the power equipment to be detected includes all the data in the third time period, and the fourth data group of the power equipment to be detected includes all the data in the fourth time period.

[0110] In the power equipment abnormality early warning system for mobile terminals of the present invention, the data detection module is a core component responsible for grouping the power equipment data to be detected for subsequent analysis and abnormality detection. The following is the workflow and function analysis of the data detection module, especially how to group data based on time periods: The data detection module first obtains the data of the electric power equipment to be detected, and the data of the electric power equipment to be detected includes the identification information of the electric power equipment (such as the equipment number, the equipment name) and the corresponding operation timestamp.

[0111] All the power equipment data to be detected are sorted according to the timestamp in the data. The purpose of sorting is to ensure that the data can be correctly allocated to different groups in chronological order.

[0112] According to the preset rules, the data detection module determines the total time range of the data and the number of groups to be divided into. Based on this information, the time interval of each group is calculated. For example, if the total time range is one month and needs to be divided into four weeks (i.e. 4 groups), each group represents one week of time.

[0113] Data Grouping: According to the calculated time intervals, the data detection module distributes the data into different groups.

[0114] For example, the first data set of the power equipment to be detected includes all data in a first time period (such as the first week), the second data set of the power equipment to be detected includes all data in a second time period (such as the second week), and so on.

[0115] Generate a data set: Finally, the data detection module generates a series of power equipment data groups to be detected, each of which includes data within a specific time period. The data provides a basis for subsequent analysis and anomaly detection.

[0116] The data acquisition function can obtain all the power equipment data to be tested, including the equipment's identification information and operation timestamp.

[0117] The data sorting function ensures that the data can be subsequently processed in chronological order through sorting operations, thereby improving the accuracy of grouping.

[0118] The time interval calculation function accurately calculates the time interval of each group according to preset rules and the total time range of the data, providing a basis for data grouping.

[0119] The data grouping function correctly distributes the data into different groups according to the calculated time intervals, generating a series of data groups of the power equipment to be detected.

[0120] The data group generation function finally generates a data group that provides a structured and orderly data basis for subsequent analysis and anomaly detection.

[0121] In summary, the data detection module plays a vital role in the power equipment abnormal warning system, especially its grouping function based on time periods, which provides strong support for subsequent abnormal detection and analysis. Through accurate data grouping, the system can more effectively identify abnormal behavior of power equipment, issue warnings in time, and ensure the safe and stable operation of the power system.

[0122] The present invention effectively solves the problem that when the abnormal warning of power equipment is inaccurate, the engineering and technical personnel cannot accurately judge the fault and cannot correct the power equipment data on site through the following technical solutions: The system collects the operation data of power equipment in real time through the real-time monitoring module, and processes these data using the trained power equipment abnormal warning model to generate power equipment abnormal warning information. The warning identification module sends these warning information to the mobile terminal and receives feedback from engineering and technical personnel. If the feedback indicates that the warning information is inaccurate, the warning identification module will extract the power equipment involved in the warning information as the power equipment to be detected.

[0123] For power equipment marked as inaccurate warning, the data detection module will group the data of these devices by time period to generate multiple power equipment data groups to be detected (such as the first to fourth power equipment data groups to be detected). The grouped data are then sequentially substituted into the power equipment abnormal warning model for re-detection to verify the accuracy of the data in different time periods and its impact on the warning results.

[0124] The system receives and analyzes the feedback of the mobile terminal on the group detection results through the data processing module. For data groups with inaccurate feedback, the system will further extract its data features and process them through the preset data detection model and data simulation model to identify and correct possible data anomalies or errors. After correcting the data, the system will use the corrected data to run the power equipment abnormal warning model again, and send the new warning information to the mobile terminal for verification. If the warning information is still inaccurate after multiple corrections and verifications, the system will use optimization methods such as genetic algorithms to optimize the power equipment abnormal warning model based on previously collected data and feedback to improve the accuracy of the warning.

[0125] Through this real-time monitoring, early warning, feedback, detection, correction and optimization cycle mechanism, the present invention can continuously improve the accuracy of abnormal early warning of power equipment and ensure that engineering and technical personnel can quickly and accurately judge and handle faults based on reliable early warning information.

[0126] In summary, the present invention effectively solves the problems of inaccurate abnormal warning of power equipment and inability to correct data on site by comprehensively using technical means such as real-time monitoring, data grouping processing, model correction and optimization, and provides engineering and technical personnel with a more reliable and practical power equipment management tool.

Claims

1. An abnormal warning system for electric power equipment used in a mobile terminal, characterized in that: include: The server side, mobile side and backend control side establish communication connections with the mobile side and backend control side. The server side includes: A data acquisition module is used to acquire power equipment operating parameters, power equipment preset thresholds, power equipment information, and power equipment historical operating data, and use the power equipment operating parameters, power equipment preset thresholds, power equipment information, and power equipment historical data to train a random forest model to obtain a power equipment abnormality warning model; The real-time monitoring module is used to collect real-time power equipment operation data, substitute the real-time power equipment operation data into the power equipment abnormal warning model, and obtain the power equipment abnormal warning information; The early warning identification module is used to send the abnormal early warning information of the power equipment to the mobile terminal, receive the data fed back by the mobile terminal, and if the fed back data shows that the abnormal early warning information of the power equipment is inaccurate, extract the power equipment in the abnormal early warning information of the power equipment, obtain the power equipment included in the abnormal early warning information of the power equipment, and use the power equipment included in the abnormal early warning information of the power equipment as the power equipment to be detected; A data detection module, used for grouping the power equipment to be detected according to time periods to obtain group data of the power equipment to be detected, wherein the group data of the power equipment to be detected includes a first data group of the power equipment to be detected, a second data group of the power equipment to be detected, a third data group of the power equipment to be detected, and a fourth data group of the power equipment to be detected, and the first data group of the power equipment to be detected, the second data group of the power equipment to be detected, the third data group of the power equipment to be detected, and the fourth data group of the power equipment to be detected are sequentially substituted into the power equipment abnormality early warning model to obtain the first data result of the power equipment to be detected, the second data result of the power equipment to be detected, the third data result of the power equipment to be detected, and the fourth data result of the power equipment to be detected; The data processing module is used to transmit the data results of the first power equipment to be detected, the data results of the second power equipment to be detected, the data results of the third power equipment to be detected, and the data results of the fourth power equipment to be detected to the mobile terminal in sequence, receive the feedback information of the data results of the power equipment to be detected from the mobile terminal, generate an optimized power equipment abnormality warning model according to the feedback information of the data results of the power equipment to be detected from the mobile terminal, and deploy the optimized power equipment abnormality warning model in the power equipment abnormality warning system.

2. The abnormal warning system for electric power equipment used in a mobile terminal according to claim 1, characterized in that: The data processing module is further used for: The feedback information of the data results of the power equipment to be detected includes whether the data results of the power equipment to be detected are accurate and whether the data results of the power equipment to be detected are inaccurate. Data features are extracted from the data corresponding to the inaccurate data results of the power equipment to be detected to obtain the data features of the power equipment corresponding to the inaccurate data results of the power equipment to be detected. The data features of the power equipment corresponding to the inaccurate data results of the power equipment to be detected are sequentially substituted into a preset data detection model to obtain data feature detection results. The data feature detection results include qualified data and unqualified data feature detection data. The data corresponding to the unqualified data feature detection data are retrieved, and the data corresponding to the unqualified data feature detection data are substituted into a preset data simulation model to output simulation data corresponding to the unqualified data feature detection data.

3. The abnormal warning system for electric power equipment used in a mobile terminal according to claim 2, characterized in that: The data processing module is further used for: The simulation data corresponding to the data that fails the data feature detection is replaced in the grouped data of the power equipment to be detected to generate a corrected data group, and the corrected data group is substituted into the power equipment abnormal warning model to obtain the power equipment warning information corresponding to the corrected data, and the power equipment warning information corresponding to the corrected data is sent to the mobile terminal. If the data fed back by the mobile terminal is that the power equipment warning information corresponding to the corrected data is inaccurate, the power equipment abnormal warning model is optimized using a genetic algorithm based on the data generated by the data acquisition module, the real-time monitoring module, the warning identification module, the data detection module and the data processing module to obtain the optimized power equipment abnormal warning model, and the optimized power equipment abnormal warning model is deployed in the power equipment abnormal warning system.

4. The abnormal warning system for electric power equipment used in a mobile terminal according to claim 1, characterized in that: The data processing module is further used for: The data acquired from the data acquisition module, the real-time monitoring module, the early warning identification module, the data detection module and the data processing module are used to obtain a basic data set of the power equipment, which includes power equipment operating parameters, preset thresholds, historical data, real-time data, early warning information, feedback data and data feature detection results; receiving an objective and a fitness function optimized according to the abnormal warning model of the power equipment, wherein the objective of the abnormal warning model of the power equipment is the false alarm rate, and the fitness function is used to evaluate the quality of each solution; According to the parameter space of the abnormal warning model of the power equipment, an initial solution is randomly generated. The solution is the parameter of the abnormal warning model of the power equipment. The initial solution is evaluated using the fitness function as the population of the genetic algorithm to obtain the result of the fitness function. Selection operation, based on the result of the fitness function, selects the best solution as the parent generation to generate the next generation; Crossover operation, perform crossover operation on the selected parent generation to generate a new solution; Mutation operation: mutation operation is performed on the newly generated solution to introduce new genes, that is, new solutions; The selection, crossover, and mutation operations are repeated until a preset number of iterations or optimization goal is reached.

5. The abnormal warning system for electric power equipment used in a mobile terminal according to claim 1, characterized in that: The real-time monitoring module is also used for: The real-time monitoring module collects the operating data of the power equipment in real time through sensors. The operating data of the power equipment includes current, voltage, temperature, power factor and vibration; Preprocess the collected real-time data, extract features related to abnormal warning of power equipment from the preprocessed data, and load the trained abnormal warning model of power equipment. The abnormal warning model of power equipment is built based on random forest and is used to identify abnormal patterns in the operation data of power equipment; The extracted features are used as input and substituted into the power equipment abnormality warning model. The power equipment abnormality warning model calculates the score of the power equipment abnormality based on the features. According to the output of the power equipment abnormality warning model, the power equipment abnormality warning information is generated. The power equipment abnormality warning information includes the type, severity, occurrence time and equipment information of the abnormality.

6. The abnormal warning system for electric power equipment used in a mobile terminal according to claim 1, characterized in that: The early warning identification module is also used for: The early warning identification module sends the abnormal early warning information of the power equipment received from the real-time monitoring module to the mobile terminal through the wireless network; Receive feedback from mobile users on warning information, including confirmation that the warning is accurate or inaccurate; determine the accuracy of the feedback: Analyze the feedback received from the mobile user on the warning information to determine whether the user believes that the warning information is accurate. If the user feedbacks that the warning information is inaccurate, proceed to the next step. If the user confirms that the warning information is accurate, end the current process. If the warning information is judged to be inaccurate, the warning identification module will extract the power equipment included in the warning information, identify and extract the warning power equipment identification, which includes the equipment number, equipment name and equipment type; The extracted power equipment information is sorted into a list to form a list of power equipment to be detected, and the list of power equipment to be detected includes power equipment that is determined to have inaccurate warnings.

7. The abnormal warning system for electric power equipment used in a mobile terminal according to claim 1, characterized in that: The data detection module is further used for: The grouping is based on the time period, based on the time unit of hour, day, week or month, to obtain the data of the power equipment to be detected, the data of the power equipment to be detected includes the identification information of the power equipment and the corresponding operation timestamp, the identification information of the power equipment includes the equipment number and the equipment name; According to the timestamp in the data, all the data of the power equipment to be detected are sorted, and according to the preset rules, the time interval of each group is calculated according to the total time range of the data and the number of groups. According to the calculated time interval, the data is allocated to different groups. The first data group of the power equipment to be detected includes all the data in the first time period, the second data group of the power equipment to be detected includes all the data in the second time period, the third data group of the power equipment to be detected includes all the data in the third time period, and the fourth data group of the power equipment to be detected includes all the data in the fourth time period.

Images