Fault prediction and maintenance method and system for safe operation of power equipment

Abstract

The invention is suitable for the field of electric power safety, and provides a fault prediction and maintenance method and system for safe operation of electric power equipment, and the system comprises a data collection module, a data analysis and abnormity identification module, a dynamic alarm and response module, a geographic information system integration module, and a maintenance path optimization module. The system adopts a non-contact dynamic electric field monitoring system to monitor power equipment, can identify potential insulation failures or electrical faults in real time, and significantly reduces the risk of contact between operation and maintenance personnel and high-voltage equipment. And in combination with an intelligent alarm system, real-time data are analyzed through machine learning, an alarm is automatically triggered, and the accuracy and response speed of fault identification are improved. In addition, the monitoring system is integrated with a geographic information system, automatic optimization of an optimal maintenance response path is achieved, and it is ensured that faults are rapidly processed. According to the comprehensive method, the safety of the power equipment is improved, the fault risk is reduced, the maintenance efficiency is optimized, and the comprehensive method has important practical value.

Description

Technical Field

[0001] The present invention belongs to the field of power safety, and in particular relates to a fault prediction and maintenance method and system for safe operation of power equipment. Background Art

[0002] The field of power equipment safety technology focuses on ensuring the reliability and safety of equipment in power systems to prevent failures and accidents. This field covers a variety of technologies and methods aimed at improving the monitoring, maintenance and operation efficiency of power equipment. Key technologies include online monitoring technology, fault diagnosis and prediction technology, improvements in insulation materials, intelligent operation and maintenance systems, and safety protection measures. Through real-time monitoring and data analysis, operation and maintenance personnel can identify potential equipment problems in a timely manner and take appropriate measures to intervene, thereby reducing the risk of failure and ensuring the stable operation of the power system.

[0003] With the development of science and technology, power equipment safety technology is gradually developing towards intelligence and automation, such as the introduction of artificial intelligence and machine learning algorithms to improve the accuracy and response speed of fault detection. In addition, the application of non-contact monitoring technology is also being promoted, which can perform efficient electric field monitoring and analysis without interfering with the operation of equipment, thereby enhancing the safety of equipment. Overall, the field of power equipment safety technology is developing in a more efficient, safer and smarter direction to cope with the increasingly complex power system and increasing safety needs.

[0004] Traditional monitoring methods usually require maintenance personnel to be close to high-voltage equipment, which not only increases the risk of electric shock and other safety accidents, but also limits the flexibility of monitoring. Secondly, existing technologies often rely on manual operation and experience judgment, resulting in low efficiency in fault identification and being easily affected by human factors, increasing the probability of faults. In addition, there is usually a time delay in the acquisition and analysis of monitoring data, making it impossible to respond to faults in a timely manner, which may cause equipment damage or trigger more serious accidents.

[0005] At the same time, traditional monitoring systems lack intelligence and cannot analyze complex data in real time. Instead, they often rely on manual processing, resulting in insufficient fault prediction and response capabilities. Complex environmental factors (such as high temperature, humidity, and dust) around high-voltage power equipment affect monitoring accuracy, making traditional methods challenging in practical applications. At the same time, existing technologies also have shortcomings in fault response. After a fault occurs, operation and maintenance personnel often need to manually find and determine the best response path, which is inefficient and often delays processing time. Summary of the invention

[0006] The purpose of the present invention is to provide a fault prediction and maintenance method for safe operation of power equipment, aiming to solve the technical problems existing in the prior art identified in the background technology.

[0007] The present invention is implemented as follows: a fault prediction and maintenance method for safe operation of electric power equipment, the method comprising: Set up electric field sensors and environmental sensors to sense and record the electric field strength and change pattern data around the power equipment, record the time series data of the electric field, and environmental parameters; Analyze the collected electric field data, identify abnormal modes that deviate from the normal working mode, and classify the fault types of the identified abnormal modes, identify potential insulation failure and electrical fault characteristics, and record them as fault prediction results; Set dynamic alarm threshold conditions and generate alarms when the fault prediction results reach the alarm threshold conditions; Real-time geography of data collected by electric field sensors and environmental sensors, and automatic update of GIS system maps, marking the locations of potential faults and affected areas in the GIS system map; Collect current geographic data, traffic conditions, and equipment maintenance history information, calculate and output maintenance response paths.

[0008] As a further solution of the present invention, the electric field sensor and the environmental sensor are set to sense and record the electric field strength and change pattern data around the power equipment, record the time series data of the electric field, and the environmental parameters, specifically including: Set the sampling frequency and data update frequency for the electric field sensor and environmental sensor respectively, as well as the trigger conditions for different sampling frequencies; Automatically record the electric field strength and change pattern around the power equipment, store the data in the database for time serialization, and synchronously collect data from environmental sensors to record the temperature, humidity, and wind speed around the power equipment; The change modes include: Extract the spectrum of the electric field signal and identify the changes in frequency components; Detecting amplitude fluctuations in electric field strength; Identify long-term trends, periodic changes, and sudden changes in electric field intensity through time series analysis; The time serialization comprises: Each time the sensor samples, a timestamp is associated to record the time point of data collection; The data collected in real time is written to the database in real time, and abnormal data directly identified during collection is marked.

[0009] As a further solution of the present invention, the identification of abnormal modes that deviate from the normal working mode, and classification of the fault types of the identified abnormal modes, identifying potential insulation failure and electrical fault characteristics, and recording them as fault prediction results, specifically include: Establish a baseline model, based on the historical normal operation data of power equipment, to establish the normal operating mode benchmark of power equipment, including the statistical characteristics and change patterns of electric field strength; Continuously monitor real-time data and identify abnormal signals that deviate from normal patterns by comparing them with the baseline model. At the same time, establish an abnormality scoring model to quantify the degree of abnormality. Perform feature extraction on the identified abnormal data to extract key features indicating different fault categories, including frequency features and timing features, and classify the extracted features to assign the anomalies to different fault types; The probability of occurrence is calculated for each identified failure mode, risk assessment is performed based on the severity of the failure, and the failure prediction results are stored in a database.

[0010] As a further solution of the present invention, the calculation of the occurrence probability for each identified fault mode and the risk assessment based on the severity of the fault specifically include: Quantify the degree to which the electric field data of power equipment deviates from the normal pattern and calculate the anomaly score: ; in, is the real-time data point value, is the mean of historical normal data, is the standard deviation of historical normal data; The probability of a fault occurring is calculated using the anomaly score: ; in, is the failure probability, is the cumulative distribution function; The risk value is calculated by combining the probability of occurrence and the severity of the failure to conduct risk assessment: ; in, Indicates the severity rating of the fault.

[0011] As a further solution of the present invention, the setting of dynamic alarm threshold conditions and generating an alarm when the fault prediction result reaches the alarm threshold conditions specifically includes: Based on historical data analysis, determine the range and change pattern of the electric field strength under normal working conditions, calculate the threshold based on the standard deviation, identify the boundary between normal fluctuations and abnormal fluctuations, and recalculate the severity score under each critical condition based on the calculated results and record it as the alarm threshold; Determine the alarm thresholds for different severity levels, which are divided into level 1 alarm threshold, level 2 alarm threshold and level 3 alarm threshold according to the severity, and assign response processing methods to each level; Based on the risk assessment results of the severity of the fault, determine whether the alarm threshold conditions are met, and if so, execute the corresponding response processing method.

[0012] As a further solution of the present invention, the data collected by the electric field sensor and the environmental sensor are geographically mapped in real time, and the GIS system map is automatically updated to mark the location of potential faults and the affected area in the GIS system map, specifically including: Define data groups. Each data group consists of real-time monitoring data from electric field sensors and environmental sensors, including timestamp, electric field strength, waveform change, environmental parameters, and device location information, and is grouped according to the collection time. Determine the geographic location of power equipment and convert the electric field strength and environmental data into a data format that matches the GIS system; Generate a GIS map and attach each set of data to the corresponding coordinate point in the GIS map according to the location of the power equipment; Convert different failure modes and their severity scores into visual markers on a map; Create an automatic update mechanism to automatically update the GIS map when new data arrives; Implement the addition and deletion of alarm layers, and display alarm information and potential fault location information on the GIS map.

[0013] As a further solution of the present invention, the collecting of current geographic data, traffic conditions and equipment maintenance history information, and calculating and outputting the maintenance response path specifically include: Use GPS and sensors to collect real-time geographic information of the current device and its surrounding area; Divide the area around the equipment into several geometric areas and set priorities based on the severity score of the fault; Obtain real-time traffic flow data and calculate the best response path from the maintenance personnel's current location to the fault site based on the collected real-time geographic data, traffic flow data and geometric area priorities.

[0014] Another object of the present invention is to provide a fault prediction and maintenance system for safe operation of power equipment, the system comprising: The data acquisition module is used to set the electric field sensor and the environmental sensor to sense and record the electric field strength and change pattern data around the power equipment, record the time series data of the electric field, and the environmental parameters; The data analysis and abnormality identification module is used to analyze the collected electric field data, identify abnormal modes that deviate from the normal working mode, and classify the fault types of the identified abnormal modes, identify potential insulation failure and electrical fault characteristics, and record them as fault prediction results; A dynamic alarm and response module, which is used to set dynamic alarm threshold conditions and generate an alarm when the fault prediction result reaches the alarm threshold conditions; Geographic Information System Integration Module, which is used to geo-map the data collected by electric field sensors and environmental sensors in real time, and automatically update the GIS system map, marking the location of potential faults and the affected area in the GIS system map; The maintenance path optimization module is used to collect current geographic data, traffic conditions and equipment maintenance history information, calculate and output the maintenance response path.

[0015] The beneficial effects of the present invention are: This method uses a non-contact dynamic electric field monitoring system to monitor power equipment, which not only reduces the risk of physical contact between operation and maintenance personnel and high-voltage equipment, but also monitors the changes in the electric field around the power equipment in real time, thereby promptly identifying potential insulation failures or electrical faults. This system can quickly detect hidden dangers of electrical faults by conducting in-depth analysis of the monitored electric field strength and patterns, ensuring the safe operation of equipment and reducing the risk of large-scale power outages or equipment damage.

[0016] An intelligent alarm system based on non-contact monitoring data is established, integrating machine learning technology, so that the system can autonomously analyze real-time data and automatically trigger alarms. This intelligent alarm mechanism not only improves the accuracy of fault identification, but also significantly shortens the response time, allowing the operation and maintenance team to take measures more quickly, thereby reducing the economic losses and safety hazards caused by faults. Through the automated alarm system, operation and maintenance personnel can obtain relevant information as soon as the fault occurs, ensuring timely handling of the problem.

[0017] At the same time, the non-contact monitoring system is combined with the geographic information system (GIS) to further optimize the maintenance personnel's response path. When a device fails, the system can automatically calculate the best maintenance response path based on real-time monitoring data, geographic information and traffic conditions. This intelligent path optimization not only improves operation and maintenance efficiency, but also minimizes fault response time to ensure that the equipment quickly resumes normal operation. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 A flowchart of a method for fault prediction and maintenance of safe operation of electric power equipment provided by an embodiment of the present invention; Figure 2 A flowchart for sensing and recording electric field strength and change pattern data, time series data, and environmental parameters around electric power equipment provided by an embodiment of the present invention; Figure 3 A flow chart for identifying an abnormal mode that deviates from a normal working mode provided by an embodiment of the present invention; Figure 4A flowchart of setting dynamic alarm threshold conditions provided by an embodiment of the present invention; Figure 5 A flowchart for marking the location and affected area of ​​potential faults in a GIS system provided by an embodiment of the present invention; Figure 6 A flowchart for calculating and outputting a maintenance response path provided by an embodiment of the present invention; Figure 7 A structural block diagram of a fault prediction and maintenance system for safe operation of electric power equipment provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0019] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0020] It is understood that the terms "first", "second", etc. used in this application may be used herein to describe various elements, but unless otherwise specified, these elements are not limited by these terms. These terms are only used to distinguish a first element from another element. For example, without departing from the scope of this application, a first xx script may be referred to as a second xx script, and similarly, a second xx script may be referred to as a first xx script.

[0021] Figure 1 A flowchart of a fault prediction and maintenance method for safe operation of electric power equipment provided by an embodiment of the present invention, such as Figure 1 As shown, the method includes: S100, setting an electric field sensor and an environmental sensor to sense and record the electric field strength and change pattern data around the power equipment, record the time series data of the electric field, and environmental parameters; This step takes into account the type of power equipment, the operating environment, and its fault characteristics to ensure that the acquired electric field signals reflect the true status of the equipment. High-frequency sampling can capture rapidly changing electric field signals, while low-frequency sampling helps analyze long-term trends. In addition, these frequencies are dynamically adjustable according to changes in the operating status of the equipment, drastic fluctuations in environmental conditions, or identification of potential anomalies to ensure real-time and accurate data.

[0022] In terms of recording and analyzing data, automatic recording of electric field strength and change patterns is particularly important. High-precision electric field sensors are used to measure electric field strength in real time, ensuring high data accuracy. Analysis of change patterns is achieved through spectrum analysis, amplitude fluctuation detection, and time series analysis. Spectrum analysis uses methods such as Fourier transform to extract signal spectra to identify changes in frequency components; amplitude fluctuation detection calculates the amplitude changes of the signal to identify abnormal fluctuations; time series analysis uses statistical methods to identify long-term trends, periodic changes, and sudden changes in electric field strength. At the same time, environmental data is synchronously collected and recorded, including environmental parameters such as temperature, humidity, and wind speed. These data help understand the environmental factors of electric field changes and improve the accuracy of fault prediction through multivariate analysis.

[0023] For time serialization and database management, each time the sensor samples, the data is accompanied by a high-precision timestamp to ensure time consistency. Real-time data is written to an efficient database system to support fast query and analysis, and abnormal data is identified in real time for subsequent analysis and processing. This detailed data processing method shows significant advantages in high-precision monitoring. Through high-frequency sampling and precise timestamps, electric field and environmental changes can be captured in real time to ensure the accuracy and timeliness of monitoring. In addition, by combining electric field and environmental data and using a variety of analysis methods, potential faults can be more comprehensively identified and the ability to provide early warning can be provided. Flexible sampling strategies can adapt to monitoring needs under different equipment and environments by dynamically adjusting frequency and trigger conditions, effectively balancing data volume and monitoring accuracy. Real-time data integration and analysis enhance rapid response and decision-making capabilities, and improve maintenance efficiency and response speed.

[0024] like Figure 2 As shown, the electric field sensor and the environmental sensor are set to sense and record the electric field strength and change pattern data around the power equipment, record the time series data of the electric field, and the environmental parameters, specifically including: S110, respectively setting a sampling frequency and a data update frequency for the electric field sensor and the environmental sensor, as well as trigger conditions for different sampling frequencies; S120, automatically record the electric field strength and change pattern around the power equipment, store the data in a database for time serialization, and synchronously collect data from environmental sensors to record the temperature, humidity, and wind speed around the power equipment; The change modes include: Extract the spectrum of the electric field signal and identify the changes in frequency components; Detecting amplitude fluctuations in electric field strength; Identify long-term trends, periodic changes, and sudden changes in electric field intensity through time series analysis; The time serialization comprises: Each time the sensor samples, a timestamp is associated to record the time point of data collection; The data collected in real time is written to the database in real time, and abnormal data directly identified during collection is marked.

[0025] S200, analyzing the collected electric field data, identifying abnormal modes that deviate from the normal working mode, and classifying the identified abnormal modes into fault types, identifying potential insulation failure and electrical fault characteristics, and recording them as fault prediction results; This step will establish a baseline model, which is based on the historical normal operation data of the power equipment and aims to build a normal working mode baseline for the power equipment. This includes analyzing the statistical characteristics and change patterns of the electric field strength to lay the foundation for subsequent real-time monitoring. By continuously monitoring the real-time data and comparing it with the baseline model, abnormal signals that deviate from the normal mode can be effectively identified. In addition, establishing an anomaly score model to quantify the degree of anomaly is an important part of this step. In this way, the degree of deviation between the real-time data and the normal mode can be accurately evaluated, thereby identifying potential faults.

[0026] Feature extraction of the identified abnormal data is another key step in this step. In this process, key features indicating different fault categories are extracted, including frequency features and timing features, which can help clarify the fault type. Subsequently, the extracted features are classified and the abnormal signals are assigned to different fault types. In order to further assess the risk, it is essential to calculate the probability of occurrence for each identified fault mode. This process combines the severity of the fault for a comprehensive risk assessment. Specifically, the calculation of the probability of occurrence is based on the distribution of the anomaly score, combined with the evaluation of the probability of occurrence and the severity of the fault, and finally forms the risk assessment result.

[0027] By establishing a baseline model and anomaly scoring model, it is possible to achieve real-time monitoring and dynamic evaluation of the equipment's operating status, quickly identify potential faults and quantify their severity. This not only improves the accuracy of fault prediction, but also enhances the ability to ensure the safe operation of equipment. The ability to compare historical data with current data in real time enables equipment managers to take preventive measures before a fault occurs, thereby reducing downtime and maintenance costs. In addition, through feature extraction and classification, it is possible to formulate corresponding maintenance strategies for different fault types, optimize resource allocation, and improve the operating efficiency and reliability of power equipment.

[0028] like Figure 3 As shown, the identification of abnormal modes that deviate from the normal working mode, and classification of the fault types of the identified abnormal modes, identify potential insulation failure and electrical fault characteristics, and record them as fault prediction results, specifically include: S210, establishing a baseline model, based on historical normal operation data of the power equipment, to establish a normal operating mode benchmark of the power equipment, including statistical characteristics and variation patterns of the electric field intensity; S220, continuously monitors real-time data and identifies abnormal signals that deviate from the normal pattern by comparing them with the baseline model, and establishes an abnormality scoring model to quantify the degree of abnormality; S230, extracting features from the identified abnormal data, extracting key features indicating different fault categories, including frequency features and timing features, and classifying the extracted features to assign the abnormalities to different fault types; S240, calculating the occurrence probability for each identified fault mode, performing risk assessment based on the severity of the fault, and storing the fault prediction results in a database.

[0029] In this step, the occurrence probability is calculated for each identified failure mode, and risk assessment is performed in combination with the severity of the failure, specifically including: Quantify the degree to which the electric field data of power equipment deviates from the normal pattern and calculate the anomaly score: ; in, is the real-time data point value, is the mean of historical normal data, is the standard deviation of historical normal data; The probability of a fault occurring is calculated using the anomaly score: ; in, is the failure probability, is the cumulative distribution function; The risk value is calculated by combining the probability of occurrence and the severity of the failure to conduct risk assessment: ; in, Indicates the severity rating of the fault.

[0030] S300, setting a dynamic alarm threshold condition, and generating an alarm when the fault prediction result reaches the alarm threshold condition; In this step, an analysis based on historical data is performed to determine the range and variation pattern of the electric field strength under normal working conditions. This analysis involves not only the average value of the electric field strength, but also the calculation of the standard deviation to establish an effective threshold system. On this basis, the boundaries between normal and abnormal fluctuations can be identified, thus providing a scientific basis for the subsequent alarm mechanism.

[0031] Next, based on the calculated standard deviation results, the severity scores under each critical condition are re-evaluated, and these scores will be used to generate alarm thresholds. By comparing the range of normal fluctuations with the limits of abnormal fluctuations, the corresponding alarm thresholds can be set. Specifically, the alarm thresholds are divided into three levels: level 1 alarm threshold, level 2 alarm threshold, and level 3 alarm threshold, and each level corresponds to a different severity. Level 1 alarms may be minor anomalies, which are usually marked as monitoring signals; level 2 alarms represent more serious anomalies that require attention and review; level 3 alarms are serious fault warnings that require immediate action. Assign corresponding response processing methods to each level to ensure that appropriate countermeasures can be taken quickly under different fault levels.

[0032] In addition, based on the risk assessment results of the severity of the fault, it is determined whether the alarm threshold conditions are met. If the preset conditions are met, the corresponding response processing method is executed. This process ensures that in the early stages of the fault, it can respond quickly and take necessary measures to reduce the risk and impact of the accident.

[0033] Through systematic threshold calculation and classification management, dynamic monitoring of equipment operation status can be achieved. Through the analysis of historical data, potential fault risks can be identified more accurately, and corresponding response strategies can be formulated according to the severity level, thereby improving the efficiency of fault handling. In addition, the hierarchical alarm mechanism enables operation and maintenance personnel to make quick judgments based on the severity of the fault, reasonably allocate resources, optimize maintenance processes, and reduce economic losses caused by equipment downtime.

[0034] like Figure 4 As shown, the dynamic alarm threshold condition is set, and an alarm is generated when the fault prediction result reaches the alarm threshold condition, specifically including: S310, based on historical data analysis, determine the range and change pattern of the electric field strength under normal working conditions, calculate a threshold based on the standard deviation, identify the boundary between normal fluctuations and abnormal fluctuations, and calculate the severity score under each critical condition again based on the calculated results, and record it as the alarm threshold; S320, determining alarm thresholds of different severity levels, which are divided into: a first-level alarm threshold, a second-level alarm threshold, and a third-level alarm threshold according to the severity, and assigning a response processing method to each level; S330, judging whether the alarm threshold condition is satisfied based on the risk assessment result of the severity of the fault, and executing a corresponding response processing method if satisfied.

[0035] S400, geo-maps the data collected by electric field sensors and environmental sensors in real time, and automatically updates the GIS system map, marking the location of potential faults and the affected areas in the GIS system map; This step defines data groups, which involves organizing real-time monitoring data from electric field sensors and environmental sensors. Each set of data includes timestamp, electric field strength, waveform changes, environmental parameters (such as temperature, humidity, wind speed, etc.), and device location information. In order to facilitate subsequent processing, these data need to be grouped according to the collection time to ensure the timeliness and relevance of the data.

[0036] Next, by integrating the location information of the equipment, the electric field strength and environmental data can be converted into a data format suitable for the GIS system. This step ensures the compatibility of different data sources and lays the foundation for subsequent visualization processing. The process of generating a GIS map is an important step in attaching each set of data to the corresponding coordinate point on the GIS map. According to the actual geographical location of the power equipment, the real-time monitoring data is visualized using the coordinate system of the GIS system to form an informative map view. This not only helps to intuitively understand the spatial distribution of electric field and environmental data, but also provides an effective geographic reference for fault detection.

[0037] Different failure modes and their severity scores are then converted into visual markers on the map, for example, using different colors, icons or marker sizes to indicate the severity of the failure, allowing operations and maintenance personnel to quickly obtain key information and thus more effectively assess and respond to failure risks.

[0038] When new data arrives, the GIS map is automatically updated. This feature ensures that the operation and maintenance personnel can always access the latest monitoring data and make timely decisions. Finally, the alarm layer is added and subtracted to display the alarm information and potential fault location information on the GIS map. This feature not only enhances the visualization of alarm information, but also improves the efficiency of fault response. The operation and maintenance team can monitor fault information in real time and quickly locate the source of the problem, thereby reducing the time and cost of fault handling.

[0039] Through systematic data processing and visual display, the safety monitoring and fault response capabilities of power equipment have been greatly improved. The real-time monitoring capability allows operation and maintenance personnel to obtain the latest information on the equipment's surrounding environment and electric field strength at any time, improving the timeliness of monitoring. The visual management of GIS maps makes fault modes and environmental changes clear at a glance, helping users quickly identify potential problems and optimize the decision-making process. The automatic update mechanism ensures the dynamic and real-time nature of the data, allowing the operation and maintenance team to grasp the status of the equipment at any time, reducing the need for manual intervention. In addition, through the display of visual markings and alarm information, operation and maintenance personnel can quickly assess the severity of the fault and take appropriate measures to effectively reduce the fault response time.

[0040] like Figure 5As shown, the data collected by the electric field sensor and the environmental sensor are geographically mapped in real time, and the GIS system map is automatically updated, and the location and affected area of ​​the potential fault are marked in the GIS system map, specifically including: S410, defining data groups, each group of data is composed of real-time monitoring data from electric field sensors and environmental sensors, including timestamp, electric field strength, waveform change, environmental parameters and location information of the device, and grouping according to the collection time; S420, determining the geographical location of the power equipment, and converting the electric field strength and environmental data into a data format matching the GIS system; S430, generating a GIS map, and attaching each set of data to a corresponding coordinate point in the GIS map according to the location of the power equipment; S440, converts different failure modes and their severity scores into visual markers on a map; S450, creating an automatic update mechanism to automatically update the GIS map when new data arrives; S460, implement the addition and deletion of alarm layers, and display alarm information and potential fault location information on the GIS map.

[0041] S500, collecting current geographic data, traffic conditions and equipment maintenance history information, calculating and outputting a maintenance response path.

[0042] This step uses GPS and sensors to collect real-time geographic information of the current device and its surrounding area. This process includes not only the precise location of the device, but also detailed characteristics of the surrounding environment, such as road conditions, obstacles, and possible traffic control information. These real-time geographic data will provide basic information for subsequent response path planning.

[0043] Next, the area around the equipment is divided into several geometric areas. These areas can be divided according to geographical features, equipment distribution, and the possibility of failure, so as to better manage resources and optimize response time. After the division is completed, priority is set according to the severity score of the fault, which can ensure that the most serious faults will be repaired first, thereby reducing potential risks and losses.

[0044] In addition, obtaining real-time traffic flow data will directly affect the selection of maintenance response paths. By collecting traffic flow information, the operation and maintenance team can understand the traffic conditions in real time, thereby avoiding the impact of congestion or closed routes. On this basis, combined with the collected real-time geographic data, traffic flow data and geometric area priorities, the best response path from the current location of the maintenance personnel to the fault site is calculated. This calculation usually uses the shortest path algorithm or other optimization algorithms to ensure that the response time is minimized and the efficiency of fault handling is improved.

[0045] By collecting geographic information of equipment and surrounding areas in real time, maintenance personnel can obtain detailed data support, making the fault response process more scientific and systematic. Dividing the surrounding area into geometric areas and setting priorities can effectively optimize resource allocation and ensure that the most critical faults are handled in a timely manner, thereby reducing the risk of accidents. In addition, the integration of real-time traffic flow data makes route planning more flexible and practical, avoiding delays caused by traffic congestion and improving maintenance response speed.

[0046] like Figure 6 As shown, the current geographic data, traffic conditions and equipment maintenance history information are collected, and the maintenance response path is calculated and output, specifically including: S510, using GPS and sensors to collect real-time geographic information of the current device and its surrounding area; S520, dividing the area around the device into a plurality of geometric areas, and setting priorities according to the severity scores of the faults; S530, acquiring real-time traffic flow data, and calculating the best response path from the current location of the maintenance personnel to the fault site based on the collected real-time geographic data, traffic flow data and geometric area priority.

[0047] Figure 7 The structural block diagram of the fault prediction and maintenance system for safe operation of power equipment provided by the embodiment of the present invention is as follows: Figure 7 As shown, the system comprises: The data acquisition module 100 is used to set the electric field sensor and the environmental sensor to sense and record the electric field strength and change pattern data around the power equipment, record the time series data of the electric field, and the environmental parameters; The data analysis and abnormality identification module 200 is used to analyze the collected electric field data, identify abnormal modes that deviate from the normal working mode, and classify the fault types of the identified abnormal modes, identify potential insulation failure and electrical fault characteristics, and record them as fault prediction results; A dynamic alarm and response module 300, for setting dynamic alarm threshold conditions and generating an alarm when the fault prediction result reaches the alarm threshold conditions; The geographic information system integration module 400 is used to geo-map the data collected by the electric field sensor and the environmental sensor in real time, and automatically update the GIS system map, marking the location of potential faults and the affected area in the GIS system map; The maintenance path optimization module 500 is used to collect current geographic data, traffic conditions and equipment maintenance history information, calculate and output a maintenance response path.

[0048] It should be understood that, although each step in the flow chart of each embodiment of the present invention is shown in sequence according to the indication of the arrow, these steps are not necessarily performed in sequence according to the order indicated by the arrow. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be performed in other orders. Moreover, at least a portion of the steps in each embodiment may include a plurality of sub-steps or a plurality of stages, and these sub-steps or stages are not necessarily performed at the same time, but can be performed at different times, and the execution order of these sub-steps or stages is not necessarily performed in sequence, but can be performed in turn or alternately with at least a portion of other steps or sub-steps or stages of other steps.

[0049] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the program can be stored in a non-volatile computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0050] The technical features of the above-described embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above-described embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0051] The above-mentioned embodiments only express several implementation methods of the present invention, and the description thereof is relatively specific and detailed, but it cannot be understood as limiting the scope of the patent of the present invention. It should be pointed out that, for ordinary technicians in this field, several variations and improvements can be made without departing from the concept of the present invention, which all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention shall be subject to the attached claims.

[0052] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A fault prediction and maintenance method for safe operation of electric power equipment, characterized in that: The method comprises: Set up electric field sensors and environmental sensors to sense and record the electric field strength and change pattern data around the power equipment, record the time series data of the electric field, and environmental parameters; Analyze the collected electric field data, identify abnormal modes that deviate from the normal working mode, and classify the fault types of the identified abnormal modes, identify potential insulation failure and electrical fault characteristics, and record them as fault prediction results; Set dynamic alarm threshold conditions and generate alarms when the fault prediction results reach the alarm threshold conditions; Real-time geography of data collected by electric field sensors and environmental sensors, and automatic update of GIS system maps, marking the locations of potential faults and affected areas in the GIS system map; Collect current geographic data, traffic conditions, and equipment maintenance history information, calculate and output maintenance response paths.

2. The method according to claim 1, characterized in that The electric field sensor and the environmental sensor are set to sense and record the electric field strength and change pattern data around the power equipment, record the time series data of the electric field, and the environmental parameters, specifically including: Set the sampling frequency and data update frequency for the electric field sensor and environmental sensor respectively, as well as the trigger conditions for different sampling frequencies; Automatically record the electric field strength and change pattern around the power equipment, store the data in the database for time serialization, and synchronously collect data from environmental sensors to record the temperature, humidity, and wind speed around the power equipment; The change modes include: Extract the spectrum of the electric field signal and identify the changes in frequency components; Detecting amplitude fluctuations in electric field strength; Identify long-term trends, periodic changes, and sudden changes in electric field intensity through time series analysis; The time serialization comprises: Each time the sensor samples, a timestamp is associated to record the time point of data collection; The data collected in real time is written to the database in real time, and abnormal data directly identified during collection is marked.

3. The method according to claim 2, characterized in that The identifying of abnormal modes that deviate from the normal working mode, classifying the fault types of the identified abnormal modes, identifying potential insulation failure and electrical fault characteristics, and recording them as fault prediction results, specifically includes: Establish a baseline model, based on the historical normal operation data of power equipment, to establish the normal operating mode benchmark of power equipment, including the statistical characteristics and change patterns of electric field strength; Continuously monitor real-time data and identify abnormal signals that deviate from normal patterns by comparing them with the baseline model. At the same time, establish an abnormality scoring model to quantify the degree of abnormality. Perform feature extraction on the identified abnormal data to extract key features indicating different fault categories, including frequency features and timing features, and classify the extracted features to assign the anomalies to different fault types; The probability of occurrence is calculated for each identified failure mode, risk assessment is performed based on the severity of the failure, and the failure prediction results are stored in a database.

4. The method according to claim 3, characterized in that The above method calculates the probability of occurrence of each identified failure mode and performs risk assessment based on the severity of the failure, including: Quantify the degree to which the electric field data of power equipment deviates from the normal pattern and calculate the anomaly score: ； in, is the real-time data point value, is the mean of historical normal data, is the standard deviation of historical normal data; The probability of a failure occurring is calculated using the anomaly score: ； in, is the failure probability, is the cumulative distribution function; The risk value is calculated by combining the probability of occurrence and the severity of the failure to conduct risk assessment: ； in, Indicates the severity rating of the fault.

5. The method according to claim 3, characterized in that: The step of setting a dynamic alarm threshold condition and generating an alarm when the fault prediction result reaches the alarm threshold condition specifically includes: Based on historical data analysis, determine the range and change pattern of the electric field strength under normal working conditions, calculate the threshold based on the standard deviation, identify the boundary between normal fluctuations and abnormal fluctuations, and recalculate the severity score under each critical condition based on the calculated results and record it as the alarm threshold; Determine the alarm thresholds for different severity levels, which are divided into level 1 alarm threshold, level 2 alarm threshold and level 3 alarm threshold according to the severity, and assign response processing methods to each level; Based on the risk assessment results of the severity of the fault, determine whether the alarm threshold conditions are met, and if so, execute the corresponding response processing method.

6. The method according to claim 5, characterized in that The real-time geography of the data collected by the electric field sensor and the environmental sensor, and the automatic updating of the GIS system map, marking the location of potential faults and the affected area in the GIS system map, specifically includes: Define data groups. Each data group consists of real-time monitoring data from electric field sensors and environmental sensors, including timestamp, electric field strength, waveform changes, environmental parameters, and device location information, and is grouped according to the collection time. Determine the geographic location of power equipment and convert the electric field strength and environmental data into a data format that matches the GIS system; Generate a GIS map and attach each set of data to the corresponding coordinate point in the GIS map according to the location of the power equipment; Convert different failure modes and their severity scores into visual markers on a map; Create an automatic update mechanism to automatically update the GIS map when new data arrives; Implement the addition and deletion of alarm layers, and display alarm information and potential fault location information on the GIS map.

7. The method according to claim 6, characterized in that The collecting of current geographic data, traffic conditions and equipment maintenance history information, and calculating and outputting the maintenance response path specifically include: Use GPS and sensors to collect real-time geographic information of the current device and its surrounding area; Divide the area around the equipment into several geometric areas and set priorities based on the severity score of the fault; Obtain real-time traffic flow data and calculate the best response path from the maintenance personnel's current location to the fault site based on the collected real-time geographic data, traffic flow data and geometric area priorities.

8. A fault prediction and maintenance system for safe operation of power equipment, characterized in that: The system comprises: The data acquisition module is used to set the electric field sensor and the environmental sensor to sense and record the electric field strength and change pattern data around the power equipment, record the time series data of the electric field, and the environmental parameters; The data analysis and abnormality identification module is used to analyze the collected electric field data, identify abnormal modes that deviate from the normal working mode, and classify the fault types of the identified abnormal modes, identify potential insulation failures and electrical fault characteristics, and record them as fault prediction results; A dynamic alarm and response module, which is used to set dynamic alarm threshold conditions and generate an alarm when the fault prediction result reaches the alarm threshold conditions; Geographic Information System Integration Module, which is used to geo-map the data collected by electric field sensors and environmental sensors in real time, and automatically update the GIS system map, marking the location of potential faults and the affected area in the GIS system map; The maintenance path optimization module is used to collect current geographic data, traffic conditions and equipment maintenance history information, calculate and output the maintenance response path.

Images