Electrical equipment fault monitoring and positioning system based on data analysis

Abstract

The invention discloses an electrical equipment fault monitoring and positioning system based on data analysis, and relates to the technical field of electrical equipment monitoring. The problem that in the prior art, the comprehensiveness of data processing, the intelligence of fault detection, the accuracy of fault positioning and the like are insufficient is solved. According to the method, the sensor acquisition frequency is dynamically adjusted according to the equipment operation state, the effectiveness and pertinence of data are ensured, the accuracy and reliability of fault feature extraction are improved by combining time domain and frequency domain analysis with network model training, the known fault type is quickly and accurately judged by calculating the similarity and performing partition positioning, and the fault diagnosis accuracy is improved. Meanwhile, unknown fault features are analyzed and predicted, determined unknown fault information is updated to a database, fault types, equipment topological structures and structural information are combined, fault propagation paths and influence ranges are simulated, fault position ranges are determined, evaluation optimization is carried out, accurate information is provided for fault maintenance, and the fault maintenance efficiency is improved. And the equipment maintenance cost and the downtime are reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of electrical equipment monitoring, and in particular to an electrical equipment fault monitoring and positioning system based on data analysis. Background Art

[0002] Traditional electrical equipment fault monitoring and positioning methods mostly rely on manual inspections, which are inefficient and difficult to detect potential faults; for example, a Chinese patent with publication number CN104833894A discloses an electrical equipment fault monitoring system and fault monitoring method, including an intelligent temperature sensing device, a remote processor and an alarm terminal; the intelligent temperature sensing device is connected to the remote processor via remote communication; the remote processor is connected to the alarm terminal; the intelligent temperature sensing device is adsorbed and fixed on the connecting part of the electrical equipment, and is used to collect the temperature signal of the connecting part according to a preset first time interval, and send the temperature signal to the remote processor; the remote processor is used to determine whether the temperature signal is greater than a preset first threshold, and if so, send an alarm signal to the alarm terminal; the alarm terminal is used to sound an alarm when an alarm signal is received.

[0003] However, in the prior art, faults are judged only by monitoring the temperature signals of the connectors, and the monitoring parameters are single, which cannot fully reflect the operating status of the electrical equipment. There are still deficiencies in the comprehensiveness of data processing, the intelligence of fault detection, and the accuracy of fault location. The specific location and cause of the fault cannot be accurately determined, and the increasingly complex needs of electrical equipment fault monitoring and location cannot be met. Summary of the invention

[0004] The purpose of the present invention is to provide an electrical equipment fault monitoring and positioning system based on data analysis, which collects rich data through multiple types of sensors and combines data processing and analysis to achieve fault detection and positioning, ensure the safe and stable operation of electrical equipment, and solve the problems raised in the above background technology.

[0005] To achieve the above object, the present invention provides the following technical solutions: The electrical equipment fault monitoring and positioning system based on data analysis includes: A data acquisition module is configured to perform multi-source data acquisition based on various types of sensors, obtain monitoring data of electrical equipment during operation in real time, and adjust the acquisition frequency of various types of sensors according to the operating status of the equipment; A data processing module is configured to pre-process the collected monitoring data, and at the same time, obtain the operating data of each category of sensors, correct the acquired monitoring data based on the operating data of each category of sensors, and extract fault features from the corrected monitoring data; Among them, the acquired monitoring data is corrected, and the evaluation of the sensor operation status correction data is also included, and the historical operation data is screened. After power comparison and time slice division, the historical data for building the sensor performance evaluation model is determined by waveform feature comparison and screening; A fault detection module is configured to match the extracted fault features with the fault database, determine the known fault type corresponding to the fault features according to the matching results, and analyze the unknown fault features and update them into the fault database; The fault location module is configured to analyze the propagation path and impact range of the fault in the device based on the fault characteristics and the corresponding fault type, and determine the location of the fault in combination with the device structure information.

[0006] Furthermore, the data processing module includes: A data preprocessing unit is configured to identify and remove abnormal data based on sensor categories, obtain corresponding noise characteristics, remove noise, and standardize monitoring data obtained by sensors of different categories; A data correction unit is configured to evaluate the operating status of each type of sensor, perform error correction on the preprocessed monitoring data based on the operating status of the sensor, and obtain corrected monitoring data; The data correction unit further includes screening the historical operation data to obtain the historical operation data capable of constructing the sensor performance evaluation model, and extracting features from the historical operation data capable of constructing the sensor performance evaluation model to obtain data features of the historical operation data as input data for constructing the sensor performance evaluation model; The feature extraction unit is configured to calculate the time domain statistical features and waveform features of the corrected monitoring data, construct a time domain feature vector, convert the time domain monitoring data through Fourier transform, calculate the frequency domain features, construct a frequency domain feature vector, input the time domain feature vector and the frequency domain feature vector into the network model for training, and mine the fault features in the data.

[0007] Furthermore, the data correction sheet obtains the data features of the historical operation data as the input data for building the sensor performance evaluation model. The specific execution steps are as follows: Real-time monitoring of the average power per unit time during the operation of electrical equipment, wherein the value range of the unit time is 12 hours to 36 hours; Compare the average power corresponding to each unit time with a preset power reference value, and extract the power value corresponding to the average power exceeding the preset power reference value as the target reference power value; When the target reference power value is one, the time slice is set using a preset basic time length; wherein the basic time length has a value range of 5 min-10 min; When there are multiple target reference power values, the target reference power standard deviation is obtained according to the average power value of the multiple target reference power values; The time length is set by using the target reference power standard deviation combined with an average power value of a plurality of target reference power values; Using the time length, the time length corresponding to the historical operation data is divided to obtain multiple time slices; Divide the operation time experienced by the historical operation data according to the time length to obtain multiple time slices; Data is filtered according to the historical operation data corresponding to each time slice to obtain the historical operation data that can be used to build a sensor performance evaluation model; Feature extraction is performed on historical operating data that can be used to build a sensor performance evaluation model, and data features of the historical operating data are obtained as input data for building the sensor performance evaluation model.

[0008] Furthermore, the data preprocessing unit specifically includes: Determine the data fluctuation range of different categories of sensor data according to the sensor category, extract the abnormal data that does not meet the fluctuation range of the sensor data of this category, and perform jump anomaly and missing anomaly detection, remove duplicate labeled data, and eliminate abnormal data; Based on the sensor category, the noise characteristics of different types of sensor data after removing abnormal data are obtained, and the filter parameters are dynamically adjusted according to the real-time changes of the monitoring data to remove high-frequency noise and low-frequency interference; Establish standardized data format conversion rules, convert the monitoring data collected by various types of sensors with different encoding formats and storage structures into a unified format, and perform dimension normalization on various types of monitoring data through pre-set dimension conversion coefficients.

[0009] Furthermore, the data correction unit specifically includes: Obtain the historical operation data of various types of sensors during the operation of electrical equipment, including the original data collected by the sensors under different working conditions and at different times and the corresponding equipment operation status information, where the equipment operation status information corresponds to the historical operation data one by one; Extract the data features of historical operation data, take the historical operation data features as input and the sensor measurement error as output, and build a sensor performance evaluation model; Input the sensor operation data collected in real time into the sensor performance evaluation model for evaluation, and obtain the evaluation result of the current operation status of the sensor; According to the sensor performance evaluation results, analyze the error characteristics of the sensor data, determine the sensor error type, and select the corresponding error correction strategy from the strategy library; The collected monitoring data is subjected to error correction operation according to the error correction strategy. During the correction process, the correction effect is monitored in real time until the error of the monitoring data is controlled within the preset error threshold, thereby obtaining the corrected monitoring data.

[0010] Furthermore, data screening is performed based on the historical operation data corresponding to each time slice to obtain historical operation data that can be used to build a sensor performance evaluation model. The specific execution steps are as follows: Extracting the overall waveform of normal sensor operation of each sensor stored in the database; Extracting the sensor waveform of each sensor of the historical operation data of each time slice as a sensor sub-waveform; Extracting waveform features of the sensor sub-waveform corresponding to each time slice; Compare the waveform characteristics of the sensor sub-waveform corresponding to each time slice with the waveform characteristics of the overall waveform of the normal operation of the sensor, determine the waveform position where the characteristic attribute of the waveform characteristic of the overall waveform of the normal operation of the sensor is the same as the waveform characteristic attribute of the sensor sub-waveform corresponding to the time slice, and intercept to obtain a reference waveform; Compare the sensor sub-waveform corresponding to each time slice with its corresponding reference waveform for similarity, and obtain a similarity value; Comparing the similarity value with a preset similarity threshold; Retrieving the time slice corresponding to the similarity value lower than the preset similarity threshold as the target time slice; The historical operation data contained in the target time slice is extracted as the historical operation data capable of constructing a sensor performance evaluation model.

[0011] Furthermore, the fault detection module includes: A fault matching unit is configured to calculate the similarity between the fault feature and the known fault feature vector stored in the fault database, quantify the matching degree of the fault feature, compare the calculated similarity value with a preset similarity threshold interval, and determine the fault type corresponding to the fault feature; The fault matching unit also includes building a partition positioning rule based on the main features of the fault characteristics, dividing the fault database into multiple data subsets, extracting key feature parameters of the fault feature vector, and locating the corresponding fault database subset based on the extraction result; A fault analysis unit is configured to analyze the fault characteristics of the unidentified fault type based on the judgment result of the fault matching unit, mine the associated characteristic data with the unknown fault characteristics based on the historical monitoring data, and predict the possible corresponding fault type of the unknown fault characteristics based on the associated characteristic data, and evaluate the confidence of each prediction result; The database updating unit is configured to update the determined unknown fault features and their corresponding fault types and prediction credibility into the fault database according to the preset data format and storage rules based on the prediction confidence evaluation result.

[0012] Furthermore, the fault detection module further includes: The extraction data correction unit corrects the monitoring data collected by each sensor during the correction process to a data correction amplitude ratio corresponding to an error at a preset error threshold; Comparing the data correction amplitude ratio with a preset amplitude ratio threshold; Extracting the data correction amplitude ratios corresponding to the amplitude ratios exceeding a preset threshold value to form a data correction amplitude ratio set; Comparing the number of data of the data correction amplitude ratios included in the data correction amplitude ratio set with a preset data number threshold; When the number of data of the data correction amplitude ratios included in the data correction amplitude ratio set exceeds a preset data number threshold, the lower limit value of the preset similarity threshold interval is adjusted using the data correction amplitude ratios included in the data correction amplitude ratio set to obtain the adjusted lower limit value; Each time the lower limit of the preset similarity threshold interval is adjusted, the data correction amplitude ratios contained in the data correction amplitude ratio set are cleared, and the data correction amplitude ratios corresponding to the amplitude ratio threshold exceeding the preset are re-recorded; Real-time monitoring of the lower limit of the similarity threshold interval; When the lower limit value of the similarity threshold interval is lower than the preset lower limit value threshold, an abnormal operation alarm of the device sensor is issued.

[0013] Furthermore, the fault location module includes: A fault propagation analysis unit is configured to describe the operating state of the electrical equipment based on the fault type corresponding to the fault feature and in combination with the topological structure of the electrical equipment, and simulate the propagation path and impact range of the fault in the electrical equipment; A fault location determination unit is configured to determine the location range of the fault based on the propagation path and impact range simulation results, combined with equipment structure information, working principles and common failure modes; The positioning result evaluation unit is configured to evaluate the location range of the fault, determine the accuracy and reliability of the location range, optimize the location range according to the evaluation result, and determine the location coordinates of the fault.

[0014] Furthermore, the fault location determination unit further includes: Based on the simulation results of fault propagation path and impact range, the regional range formed by abnormal changes in physical quantities when the fault occurs is obtained, and the boundary of the fault impact is determined; According to the boundary shape characteristics of the fault area, the fault area is equivalent to a standard geometric figure that is closest to the boundary shape; The center position of the standard geometric figure is obtained, and the position where the physical quantity changes the most due to the fault is taken as the critical reference point of the fault, and the straight-line distance between the center position of the standard geometric figure and the critical reference point of the fault is obtained; Based on the calculated straight-line distance between the center position of the standard geometric figure and the critical reference point of the fault, a line segment with a length times the preset proportional coefficient of the straight-line distance is intercepted in the direction close to the critical reference point of the fault, and the end point position of the line segment close to the critical reference point of the fault is taken as the center position of the fault area; The installation position of the sensor is used as a reference point to obtain the effective monitoring range boundary line of the sensor closest to the fault center position, and the shortest straight-line distance between the fault center position and the effective monitoring range boundary line is calculated.

[0015] Compared with the prior art, the present invention has the following beneficial effects: Rich data is collected by multiple types of sensors to make up for the incomplete monitoring of a single sensor; data preprocessing, multiple feature extraction methods and deep learning technology are used to effectively process and analyze complex data, improving the accuracy of fault feature extraction; known faults are identified through similarity calculation and partition positioning, and unknown fault-related features are mined and the database is updated to improve system adaptability. The propagation path and range are simulated by combining multiple information, and the fault location is determined through evaluation and optimization, achieving accurate positioning of the fault; the efficiency and accuracy of electrical equipment fault monitoring and positioning are improved, equipment maintenance costs are reduced, downtime is reduced, and stable operation of electrical equipment is ensured. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 This is a module diagram of the electrical equipment fault monitoring and positioning system based on data analysis of the present invention. DETAILED DESCRIPTION

[0017] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. 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.

[0018] In order to solve the technical problems of incomplete monitoring, inaccurate positioning and low efficiency in the existing technology, please refer to Figure 1 , this embodiment provides the following technical solutions: The electrical equipment fault monitoring and positioning system based on data analysis includes: The data acquisition module is configured to collect multi-source data based on various types of sensors, including current sensors, voltage sensors, temperature sensors, and vibration sensors. The distributed deployment method is adopted to reasonably set the sensor positions according to the different components and key parts of the electrical equipment to ensure that the operation data of various parts of the equipment can be fully collected, the monitoring data of the electrical equipment during operation can be obtained in real time, and the collection frequency of various types of sensors can be adjusted according to the operation status of the equipment; A data processing module is configured to pre-process the collected monitoring data, unify the format and dimension of the data collected by different sensors, and then use the principal component analysis method to reduce the dimension of the data. At the same time, the operating data of each category of sensors is obtained, and the acquired monitoring data is corrected based on the operating data of each category of sensors, and the fault characteristics in the corrected monitoring data are extracted, and the characteristics in the time domain are analyzed, and the characteristics of the data in the frequency domain are analyzed by Fourier transform, and the complex characteristics in the data are automatically learned and extracted by deep learning technology; A fault detection module is configured to match the extracted fault features with the fault database, determine the known fault type corresponding to the fault features according to the matching results, and analyze the unknown fault features and update them into the fault database; The fault location module is configured to analyze the propagation path and impact range of the fault in the equipment based on the fault characteristics and the corresponding fault type, determine the location of the fault in combination with the equipment structure information, and use an intelligent optimization algorithm to optimize the fault location process to improve the positioning accuracy. At the same time, it can generate a fault impact assessment report based on the severity and impact range of the fault.

[0019] In this embodiment, the data acquisition module adjusts the acquisition frequency of each type of sensor, specifically including: Obtain feedback data from the data processing module, extract characteristic parameters of the monitoring data in the time domain and frequency domain in real time, such as current amplitude fluctuation, voltage harmonic content, temperature change gradient, vibration main frequency component, etc., and construct the equipment operation status feature vector to comprehensively reflect the equipment operation status; The equipment operation status feature vector is input into the trained equipment operation status assessment model for assessment, and the assessment result is compared with the preset assessment level threshold to determine the current operation status level of the electrical equipment, including normal operation, slight abnormality, and severe abnormality; When electrical equipment is at normal operating level, reduce the acquisition frequency of each type of sensor to reduce data redundancy and storage pressure, and set a lower frequency limit to ensure effective collection of key data; When the electrical equipment is at a mild abnormal level, the current acquisition frequency of each category of sensors is maintained, and the abnormal data marking mechanism is activated to mark abnormal features in the subsequent collected data; When electrical equipment is at a severe abnormality level, the collection frequency of each category of sensors is increased, and the collection frequency of sensors corresponding to key parts of the electrical equipment is adjusted at a high frequency to obtain more detailed operating data.

[0020] In this embodiment, the data acquisition module implements differentiated sensor acquisition frequency adjustment strategies according to different status levels, reduces the frequency when the equipment is operating normally to reduce data redundancy and storage pressure, effectively improves the efficiency and quality of data acquisition, enhances the timeliness and accuracy of fault warning, and optimizes resource utilization and system performance.

[0021] In this embodiment, the data processing module includes: A data preprocessing unit is configured to identify and remove abnormal data based on sensor categories, obtain corresponding noise characteristics, remove noise, and standardize monitoring data obtained by sensors of different categories; A data correction unit is configured to evaluate the operating status of each type of sensor, perform error correction on the preprocessed monitoring data based on the operating status of the sensor, and obtain corrected monitoring data; The feature extraction unit is configured to calculate the time domain statistical features such as mean, peak, root mean square value, kurtosis, skewness, etc. of the corrected monitoring data, as well as waveform features such as rise time, fall time, and pulse width, construct a time domain feature vector, and convert the time domain monitoring data through Fourier transform, calculate frequency domain features such as spectrum amplitude, frequency distribution, and energy spectrum density, construct a frequency domain feature vector, input the time domain feature vector and the frequency domain feature vector into the network model for training, and mine the fault features in the data.

[0022] In this embodiment, the data preprocessing unit specifically includes: Determine the data fluctuation range of different categories of sensor data according to the sensor category, extract the abnormal data that does not meet the fluctuation range of the sensor data of this category, and perform jump anomaly and missing anomaly detection, remove duplicate labeled data, and eliminate abnormal data; Based on the sensor category, the noise characteristics of different types of sensor data after removing abnormal data are obtained, and the filtering parameters are dynamically adjusted according to the real-time changes of the monitoring data to remove high-frequency noise and low-frequency interference and retain the effective characteristics of the data; Establish standardized data format conversion rules, convert the monitoring data collected by various types of sensors with different coding formats and storage structures into a unified format, and normalize the dimensions of various types of monitoring data through pre-set dimension conversion coefficients to make the data comparable.

[0023] In this embodiment, the data correction unit specifically includes: Obtain the historical operation data of various types of sensors during the operation of electrical equipment, including the original data collected by the sensors under different working conditions and at different times and the corresponding equipment operation status information, where the equipment operation status information corresponds to the historical operation data one by one; Extract the data features of historical operation data, take the historical operation data features as input and the sensor measurement error as output, and build a sensor performance evaluation model; Input the real-time collected sensor operation data into the sensor performance evaluation model for evaluation, and obtain the evaluation results of the current sensor operation status, including whether the sensor is in normal working condition, whether there are drift, nonlinear error and other problems, and the current measurement accuracy level; According to the sensor performance evaluation results, analyze the error characteristics of the sensor data and determine the error type of the sensor. If the evaluation results show that the sensor data has a systematic deviation, it is determined to be a drift error; if the data shows a nonlinear change trend within the measurement range, it is determined to be a nonlinear error; if the data has random abnormal fluctuations, it is determined to be a random error, and the corresponding error correction strategy is selected from the strategy library. For example, for drift errors, a linear compensation strategy based on the calibration curve is adopted; for nonlinear errors, a polynomial fitting or piecewise linearization correction method is adopted; for random errors, a filtering algorithm is used for smoothing; The collected monitoring data is subjected to error correction operation according to the error correction strategy. During the correction process, the correction effect is monitored in real time until the error of the monitoring data is controlled within the preset error threshold, thereby obtaining the corrected monitoring data.

[0024] Specifically, the data correction unit further specifically includes screening the historical operation data to obtain the historical operation data that can build the sensor performance evaluation model, and extracting features of the historical operation data that can build the sensor performance evaluation model to obtain data features of the historical operation data as input data for building the sensor performance evaluation model. The specific execution steps are as follows: Real-time monitoring of the average power per unit time during the operation of electrical equipment, wherein the value range of the unit time is 12 hours to 36 hours; Compare the average power corresponding to each unit time with a preset power reference value, and extract the power value corresponding to the average power exceeding the preset power reference value as the target reference power value; When the target reference power value is one, the time slice is set using a preset basic time length; wherein the basic time length has a value range of 5 min-10 min; When there are multiple target reference power values, the target reference power standard deviation is obtained according to the average power value of the multiple target reference power values; The time length is set by using the target reference power standard deviation combined with an average power value of a plurality of target reference power values; The time length is obtained by the following formula: ; Where T represents the time length, T base represents the basic time length; P represents the average power of the target reference power value; σ p represents the target reference power standard deviation; T gp Indicates the average value of the time intervals between the unit times to which multiple target reference power values ​​belong; specifically, The ratio of power fluctuation to average power is calculated to characterize the relative amplitude of power change. This ratio reflects the relative stability of the target reference power value. The larger the ratio, the more drastic the power fluctuation; the smaller the ratio, the more stable the power. It is an important basis for reflecting the impact of power fluctuation on time length in subsequent calculations. This part reflects the influence of the distribution of the target reference power value in time on the result. gp The larger the value, the larger the unit time interval, the sparser the power data distribution in time, the smaller the exponential function value, and the smaller the adjustment effect on the final time length; on the contrary, T gp The smaller it is, the denser the power data is distributed in time, the larger the exponential function value is, and the greater the adjustment effect on the time length is. First multiply the results of the first two parts, and then take the square root. The square root operation is to normalize the result of the product of the two parts so that the final result is within an appropriate numerical range. At the same time, it also comprehensively considers the combined influence of the power fluctuation amplitude and time distribution on the result. This formula comprehensively reflects the combined effect of the two factors of power fluctuation and time distribution on the adjustment of time length. Through this operation, the influence of the two factors is integrated together to provide a basis for the subsequent adjustment of the basic time length. The above formula is based on the basic time length T base Based on the above calculation, it is adjusted. When the power fluctuation is large and the time distribution is dense, the value of the adjustment item is large, which will increase the final time length T; conversely, when the power fluctuation is small and the time distribution is sparse, the value of the adjustment item is small, and the final time length T is relatively small. The final time length T is the result of a reasonable adjustment to the basic time length after comprehensively considering the fluctuation of the target reference power value, the average level and the distribution over time. It is more in line with the time characteristics related to power in actual operation, and is used to make a reasonable time division of historical operation data.

[0025] Using the time length, the time length corresponding to the historical operation data is divided to obtain multiple time slices; Divide the operation time experienced by the historical operation data according to the time length to obtain multiple time slices; Data is filtered according to the historical operation data corresponding to each time slice to obtain the historical operation data that can be used to build a sensor performance evaluation model; Feature extraction is performed on historical operating data that can be used to build a sensor performance evaluation model, and data features of the historical operating data are obtained as input data for building the sensor performance evaluation model.

[0026] The technical effect of the above technical solution is: by real-time monitoring of the average power of electrical equipment per unit time (12-36 hours), and comparing it with the preset power reference value, the target reference power value exceeding the reference value is extracted. In this way, the abnormally low power situation can be screened out, and data that can better reflect the normal or typical operating status of the equipment can be retained, reducing the error caused by power abnormality in the data, and improving the accuracy of the data used to build the model. Set the time slice according to the target reference power value. When the target reference power value is one, set it with the preset basic time length (5-10min); when it is multiple, set the time length in combination with the target reference power standard deviation and the average power value. Reasonable time slice division makes the segmentation of historical operation data in the time dimension more scientific, ensures that the data in each time slice has similarity and coherence, further improves the data accuracy, and provides a reliable data basis for subsequent model construction. Screening the historical operation data according to the time slice can quickly and accurately find data that meets the requirements and can be used to build the sensor performance evaluation model, avoid blindly searching in a large amount of useless data, greatly reduce the workload and time cost of data processing, and improve the efficiency of data processing and model construction. Feature extraction is performed on the screened data, and the obtained data features are used as model input data. Due to the accurate screening of the previous data, the extracted features are more representative and targeted, which can better reflect the information related to sensor performance, speed up the model training speed, and improve the efficiency of model construction. The screened and processed data can better represent the situation related to sensor performance in the actual operation of electrical equipment. When input into the model, the model can be trained and evaluated based on more real and effective data, obtain more reliable sensor performance evaluation results, and reduce evaluation errors caused by data bias. The extracted targeted data features can enable the model to better learn the laws related to sensor performance, make the model's evaluation of sensor performance more accurate and stable, enhance the reliability of the model in practical applications, and provide strong support for model-based decision-making.

[0027] On the other hand, the formula proposed in the above technical solution comprehensively considers multiple factors such as the average power, standard deviation and average value of the target reference power value per unit time interval. It fully reflects the characteristics and time distribution of the power data. Compared with considering only a single factor, it can more accurately determine the appropriate time length according to the actual power situation, avoiding inaccurate calculation of the time length due to ignoring certain important factors. The nonlinear adjustment mechanism introduced by the exponential function can more flexibly reflect the impact of the average value of the time interval on the result. For different time distribution characteristics, nonlinear adjustment can give an adjustment range that is more in line with the actual physical process, rather than a simple linear adjustment, which further improves the matching degree of the time length calculation with the actual situation and enhances the accuracy. According to the ratio of the power standard deviation to the average power, it can effectively adapt to different degrees of power fluctuation. When the power fluctuation is large, the calculated time length will be adjusted accordingly to better match the frequent power changes; when the power fluctuation is small, the time length can also be reasonably adjusted to make the time division more suitable for the actual power stability. By calculating the average value of the unit time interval and adjusting the exponential function, the calculation of the time length can adapt to the different distribution of the target reference power value in time. Regardless of whether the power data is densely or sparsely distributed, the appropriate time length can be calculated through the formula to ensure that the time division is compatible with the actual power-time characteristics, thereby improving the applicability of the time length calculation method in different operating scenarios.

[0028] Specifically, data screening is performed based on the historical operation data corresponding to each time slice to obtain historical operation data that can be used to build a sensor performance evaluation model. The specific execution steps are as follows: Extracting the overall waveform of normal sensor operation of each sensor stored in the database; Extracting the sensor waveform of each sensor of the historical operation data of each time slice as a sensor sub-waveform; Extracting waveform features of the sensor sub-waveform corresponding to each time slice; wherein the waveform features include but are not limited to rising edges, falling edges, etc.; Compare the waveform characteristics of the sensor sub-waveform corresponding to each time slice with the waveform characteristics of the overall waveform of the normal operation of the sensor, determine the waveform position where the characteristic attribute of the waveform characteristic of the overall waveform of the normal operation of the sensor is the same as the waveform characteristic attribute of the sensor sub-waveform corresponding to the time slice, and intercept to obtain a reference waveform; Compare the sensor sub-waveform corresponding to each time slice with its corresponding reference waveform for similarity, and obtain a similarity value; Comparing the similarity value with a preset similarity threshold; Retrieving the time slice corresponding to the similarity value lower than the preset similarity threshold as the target time slice; The historical operation data contained in the target time slice is extracted as the historical operation data capable of constructing a sensor performance evaluation model.

[0029] The technical effect of the above technical solution is: by extracting the overall waveform of the normal operation of the sensor and the sensor sub-waveform of each time slice, and comparing the waveform features of the two, the time slice with different characteristic attributes from the normal waveform can be accurately identified. The time slice with a similarity value lower than the preset threshold is taken as the target time slice, and its historical operation data is extracted to ensure that the selected data is the part with abnormal sensor operation status or research value, and a large amount of normal and redundant data is eliminated, which greatly improves the validity of the data used to build the model. Focus on the rising edge, falling edge and other features of the waveform, which often reflect the key changes in the sensor operation status. By comparing these key features to filter the data, the acquired data can better reflect the core information of the sensor performance change, and further improve the validity of the data for sensor performance evaluation. The filtered target time slice data is data that is different from the normal operation status, which can provide a wealth of abnormal or special working condition samples for the sensor performance evaluation model. Building a model based on such data can enable the model to learn more effective information, improve the accuracy and reliability of the model for sensor performance evaluation, and avoid the model being overwhelmed by a large amount of normal data and unable to accurately capture the law of performance changes. Including a variety of abnormal state data helps the model learn a wider range of sensor performance change patterns and improve the generalization ability of the model. This enables the model to more accurately evaluate and predict performance when facing new and similar abnormal conditions, thereby improving the practicality of the model in actual applications. Filter out valid data in advance to avoid incorporating a large amount of normal data into the model building process, reducing unnecessary calculations and data processing time. During the model training phase, there is no need to calculate massive amounts of useless data, which greatly improves the efficiency of model building and evaluation and shortens the development cycle. When using the constructed model to evaluate sensor performance, since the model is trained based on valid data, it can more quickly and accurately locate possible performance problems of the sensor, improve evaluation efficiency, and facilitate timely maintenance measures to ensure the normal operation of sensors and related equipment.

[0030] In this embodiment, the data processing module effectively removes data interference, corrects errors, and deeply extracts fault features from multiple dimensions, providing a solid data foundation for electrical equipment fault monitoring and positioning, ensuring stable operation of the equipment, realizing all-round management and in-depth mining of monitoring data, and effectively improving data quality and the accuracy of fault feature extraction.

[0031] In this embodiment, the fault detection module includes: A fault matching unit is configured to calculate the similarity between the fault feature and the known fault feature vector stored in the fault database, quantify the matching degree of the fault feature, compare the calculated similarity value with a preset similarity threshold interval, and determine the fault type corresponding to the fault feature; The fault matching unit also includes building partition positioning rules based on the main features of the fault characteristics, such as partitioning based on current amplitude fluctuations, partitioning based on voltage harmonic content, etc., dividing the fault database into multiple data subsets, extracting key feature parameters of the fault feature vector, such as current amplitude fluctuations, voltage harmonic content, temperature change gradient, vibration main frequency components, etc., and locating the corresponding fault database subset based on the extraction results; A fault analysis unit is configured to analyze the fault characteristics of the unidentified fault type based on the judgment result of the fault matching unit, mine the associated characteristic data with the unknown fault characteristics based on the historical monitoring data, and predict the possible corresponding fault type of the unknown fault characteristics based on the associated characteristic data, and evaluate the confidence of each prediction result; The database updating unit is configured to update the determined unknown fault features and their corresponding fault types and prediction credibility into the fault database according to the preset data format and storage rules based on the prediction confidence evaluation result.

[0032] Specifically, the fault detection module also includes: The extraction data correction unit corrects the monitoring data collected by each sensor during the correction process to a data correction amplitude ratio corresponding to an error at a preset error threshold; Comparing the data correction amplitude ratio with a preset amplitude ratio threshold; Extracting the data correction amplitude ratios corresponding to the amplitude ratios exceeding a preset threshold value to form a data correction amplitude ratio set; Comparing the number of data of the data correction amplitude ratios included in the data correction amplitude ratio set with a preset data number threshold; When the number of data of the data correction amplitude ratios included in the data correction amplitude ratio set exceeds a preset data number threshold, the lower limit value of the preset similarity threshold interval is adjusted using the data correction amplitude ratios included in the data correction amplitude ratio set to obtain the adjusted lower limit value; The adjusted lower limit value is obtained by the following formula: ; Where X represents the lower limit after adjustment; X 0 represents the lower limit value before adjustment; n represents the number of data correction amplitude ratios contained in the data correction amplitude ratio set; σ xIndicates the standard deviation of the data correction amplitude ratio contained in the data correction amplitude ratio set; X i represents the corresponding value of the i-th data correction amplitude ratio in the data correction amplitude ratio set; X p represents the average value of the data correction amplitude ratio contained in the data correction amplitude ratio set; specifically, It means averaging all data, reflecting the comprehensive discrete and relative average characteristics of the entire data correction amplitude ratio set. This part reflects the overall fluctuation characteristics of the data correction amplitude ratio set and the distribution of data relative to the average value. The larger the value, the more drastic the fluctuation of the data correction amplitude ratio, and the more significant the difference of the data relative to the average value, which means that the deviation of the sensor data is more complex and unstable. The value range of the sine function sin() is between [−1,1]. Multiply the value reflecting the data characteristics calculated previously by Then it is used as the independent variable of the sine function. This is done by using the nonlinear characteristics of the sine function to map the data eigenvalues ​​to a new interval to achieve nonlinear control of the adjustment amplitude of the lower limit. Through the transformation of the sine function, the eigenvalue of the data correction amplitude ratio set is converted into a value between [−1,1], which is used to indicate the direction and relative amplitude of the adjustment of the lower limit according to the data characteristics. When the value is close to 1, it means that the lower limit needs to be adjusted to a large extent according to the data situation; when it is close to -1, it may mean that the adjustment direction is opposite or the adjustment amplitude is very small. The lower limit value X before the overall adjustment of the above formula 0 Based on X, the sine function value obtained by the above operation is adjusted. When the sin() value is large, the 1−sin() value is small, and the adjusted lower limit value X is relative to X 0 There will be a significant reduction; when the sin() value is small, the adjustment amplitude is small. X is the lower limit value adjusted according to the characteristics of the data correction amplitude ratio set. It comprehensively considers factors such as the number of data correction amplitude ratios, standard deviation, each data value, and average value, and realizes dynamic adjustment of the lower limit value through nonlinear transformation to adapt to the actual situation of sensor data deviation.

[0033] Each time the lower limit of the preset similarity threshold interval is adjusted, the data correction amplitude ratios contained in the data correction amplitude ratio set are cleared, and the data correction amplitude ratios corresponding to the amplitude ratio threshold exceeding the preset are re-recorded; Real-time monitoring of the lower limit of the similarity threshold interval; When the lower limit value of the similarity threshold interval is lower than the preset lower limit value threshold, an abnormal operation alarm of the device sensor is issued.

[0034] The technical effect of the above technical solution is: in the process of correcting the sensor monitoring data, the data correction unit calculates the correction amplitude ratio corresponding to the error at the preset error threshold, and this ratio reflects the degree of deviation between the sensor collected data and the accurate data. The data correction amplitude ratio is compared with the preset amplitude ratio threshold. If it exceeds the threshold, it means that the sensor collected data has a large deviation, and it is extracted to form a data correction amplitude ratio set. The number of data in the data correction amplitude ratio set is counted and compared with the preset data number threshold. If the number of data in the set exceeds the threshold, it means that the sensor has a lot of data deviation within a certain time or range, and there may be an operation abnormality. When the number of data exceeds the limit, the data correction amplitude ratio in the data correction amplitude ratio set is used to adjust the lower limit of the preset similarity threshold interval. Generally, according to the degree of data deviation, the lower limit is appropriately lowered to make subsequent judgments more stringent, so as to detect sensor abnormalities more sensitively. After adjustment, the data correction amplitude ratio set is cleared, and the data correction amplitude ratio that exceeds the preset amplitude ratio threshold is re-recorded to continuously monitor the sensor data deviation. The lower limit of the similarity threshold interval is monitored in real time. Once the lower limit is lower than the preset lower limit threshold, it indicates that the sensor is likely to be abnormal. At this time, the device sensor is abnormally alarmed and the relevant personnel are notified to take measures to investigate and solve the problem. At the same time, the data correction amplitude ratio reflects the correction amplitude required to correct the sensor monitoring data to the preset error threshold. The larger the ratio, the greater the deviation of the sensor data collection. Comparing it with the preset amplitude ratio threshold, exceeding the threshold means that the sensor data deviation exceeds the normal range. When the number of data correction amplitude ratios exceeding the threshold (that is, the number of data in the data correction amplitude ratio set) exceeds the preset data number threshold, it indicates that the sensor has a more serious or more frequent data deviation problem. Based on the above judgment, when it is determined that the sensor data deviation is more serious, the data correction amplitude ratio in the data correction amplitude ratio set is used to adjust the preset similarity threshold interval lower limit. Generally speaking, the larger the data correction amplitude ratio and the more data in the set, the more serious the deviation of the sensor data collection. At this time, the lower limit of the similarity threshold interval should be appropriately lowered. This is because when the sensor deviation is large, the originally high similarity threshold may cause some actual abnormal situations to be misjudged as normal. Lowering the lower limit value can make the judgment standard more stringent, making it easier to detect sensor operation abnormalities and ensure that the fault detection system can detect problems in a timely manner.

[0035] By comparing the data correction amplitude ratio with the preset amplitude ratio threshold, the data correction amplitude ratio that exceeds the threshold is screened out to form a set, and then compared with the preset data number threshold. When the number of data in the set exceeds the limit, it means that there are many deviations in the sensor collected data, and the lower limit of the similarity threshold interval needs to be adjusted. This multi-step judgment mechanism can accurately capture sensor operation anomalies, avoid misjudgment due to a small amount of data deviation, and do not miss a large number of deviations, thereby improving the accuracy of fault detection. The lower limit of the similarity threshold interval is dynamically adjusted according to the data correction amplitude ratio set, so that the threshold is more in line with the actual operating state of the sensor. When the sensor performance changes, the threshold can be changed accordingly to ensure that the fault detection standard is reasonable and further improve the detection accuracy. The lower limit of the similarity threshold interval is monitored in real time. Once it is lower than the preset lower limit threshold, an alarm is issued, which can quickly detect sensor operation anomalies, promptly notify relevant personnel to handle, reduce the duration of the fault, and reduce losses. When the number of data in the data correction amplitude ratio set exceeds the limit, the threshold is adjusted, the set is cleared and re-recorded, which can quickly respond to changes in sensor data deviations, so that the fault detection system is always in a sensitive state and potential faults are discovered in time. Dynamically adjust the lower limit of the similarity threshold interval to adapt to performance fluctuations caused by factors such as aging and environmental changes. Under different working conditions, the threshold can be reasonably adjusted to ensure the normal operation of the fault detection system and enhance the adaptability of the system. Judging and processing sensor data deviations based on the data correction amplitude ratio can flexibly respond to various degrees of data deviations, whether they are slow changes or sudden deviations, and can be effectively detected and processed, so that the system can adapt to different types of sensor operation anomalies.

[0036] On the other hand, the formula proposed in the above technical solution comprehensively considers multiple factors such as the number of data, standard deviation, each data value and average value of the data correction amplitude ratio set, and comprehensively reflects the characteristics and distribution of the data. Compared with considering only a single factor, the lower limit value can be adjusted more accurately according to the actual situation of the sensor data deviation, so that the adjusted lower limit value is more in line with the actual operating state of the sensor, and the accuracy of the fault detection threshold is improved. The nonlinear adjustment mechanism introduced by the sine function can more flexibly adjust the lower limit value according to the data characteristics. For different data fluctuation degrees and distribution conditions, nonlinear adjustment can give an adjustment amplitude that is more in line with the actual physical process, rather than a simple linear adjustment, which further improves the matching degree of the lower limit adjustment with the actual situation and enhances the accuracy. According to the standard deviation of the data correction amplitude ratio set and the distribution of data values, it can effectively adapt to different data fluctuation degrees. When the data fluctuation is large, the formula can adjust the lower limit value by a corresponding amplitude through relevant calculations to more strictly detect sensor abnormalities; when the data fluctuation is small, the adjustment amplitude of the lower limit value is also reduced accordingly, so that the fault detection threshold adapts to different data fluctuation states. By comprehensively considering multiple data characteristic factors, the formula can adapt to the data deviation of the sensor under different actual working conditions. Whether it is the data deviation caused by factors such as sensor aging, environmental changes, or sudden abnormal deviation, the lower limit value can be reasonably adjusted through the formula, so that the fault detection system can better adapt to the actual operating conditions of the sensor, improving the adaptability and reliability of the system.

[0037] In this embodiment, by calculating similarity and constructing partition positioning rules, known fault types can be quickly and accurately identified, the database can be partitioned, and the search scope can be narrowed. The fault analysis unit effectively improves the fault detection efficiency, enhances the system's ability to respond to unknown faults, and provides the possibility of timely discovering potential faults, and updates the determined unknown fault information to the database. This continuously enriches and improves the fault database, improves the system's self-learning ability, and ensures that the system can continue to work effectively when facing new faults.

[0038] In this embodiment, the fault location module includes: A fault propagation analysis unit is configured to describe the operating state of the electrical equipment based on the fault type corresponding to the fault feature and in combination with the topological structure of the electrical equipment, and simulate the propagation path and impact range of the fault in the electrical equipment; A fault location determination unit is configured to determine the location range of the fault based on the propagation path and impact range simulation results, combined with equipment structure information, working principles and common failure modes; The positioning result evaluation unit is configured to evaluate the location range of the fault, determine the accuracy and reliability of the location range, optimize the location range according to the evaluation result, and determine the location coordinates of the fault.

[0039] In this embodiment, the fault location determination unit further includes: Based on the simulation results of fault propagation path and impact range, the regional range formed by abnormal changes in physical quantities when the fault occurs is obtained, and the boundary of the fault impact is determined; According to the boundary shape characteristics of the fault area, the fault area is equivalent to a standard geometric figure that is closest to the boundary shape, such as a circle, rectangle, polygon, etc. By calculating the distance distribution from each point in the area to the boundary, the standard geometric figure that best fits the area shape is selected; Obtain the center position of the standard geometric figure, and take the position where the physical quantity (such as the position with the largest current mutation amplitude, the position with the highest voltage distortion rate, the peak point of abnormal temperature increase, and the position where the vibration acceleration exceeds the threshold most obviously) caused by the fault as the key reference point of the fault, and obtain the straight-line distance between the center position of the standard geometric figure and the key reference point of the fault; Based on the calculated straight-line distance between the center position of the standard geometric figure and the critical reference point of the fault, a line segment with a length times the preset proportional coefficient of the straight-line distance is intercepted in the direction close to the critical reference point of the fault, and the end point position of the line segment close to the critical reference point of the fault is taken as the center position of the fault area, wherein the preset proportional range is obtained based on the analysis and statistics of a large number of electrical equipment failure case data, and can effectively reflect the position of the core area of ​​the fault; The installation position of the sensor is used as a reference point to obtain the effective monitoring range boundary line of the sensor closest to the fault center position, and the shortest straight-line distance between the fault center position and the effective monitoring range boundary line is calculated.

[0040] In this embodiment, by calculating the shortest straight-line distance between the boundary line of the effective monitoring range and the center position of the fault, and comparing the distance changes between the center position of the fault and the boundary line of the sensor monitoring range at different times, the rationality of the fault propagation path can be verified. If the fault propagation direction is inconsistent with the distance change trend, it may be necessary to re-examine the fault propagation model and improve the analysis of the fault propagation path; further, the rationality of the existing sensor layout can be evaluated, and the impact of the fault on the sensor monitoring data can be analyzed to provide key data support for subsequent fault impact assessment and fault location accuracy optimization. The shortest straight-line distance is the distance between the center position of the fault and the key reference point, which can help determine whether the fault is close to the sensor monitoring edge, thereby correcting and optimizing the positioning results, reducing positioning errors, and making the fault location coordinates more accurate.

[0041] The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can make equivalent replacements or changes according to the technical scheme and inventive concept of the present invention within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

Claims

1. An electrical equipment fault monitoring and positioning system based on data analysis, characterized in that: include: A data acquisition module is configured to perform multi-source data acquisition based on various types of sensors, obtain monitoring data of electrical equipment during operation in real time, and adjust the acquisition frequency of various types of sensors according to the operating status of the equipment; A data processing module is configured to pre-process the collected monitoring data, and at the same time, obtain the operating data of each category of sensors, correct the acquired monitoring data based on the operating data of each category of sensors, and extract fault features from the corrected monitoring data; Among them, the acquired monitoring data is corrected, and the evaluation of the sensor operation status correction data is also included, and the historical operation data is screened. After power comparison and time slice division, the historical data for building the sensor performance evaluation model is determined by waveform feature comparison and screening; A fault detection module is configured to match the extracted fault features with the fault database, determine the known fault type corresponding to the fault features according to the matching results, and analyze the unknown fault features and update them into the fault database; The fault location module is configured to analyze the propagation path and impact range of the fault in the device based on the fault characteristics and the corresponding fault type, and determine the location of the fault in combination with the device structure information.

2. The electrical equipment fault monitoring and positioning system based on data analysis according to claim 1, characterized in that: Data processing module, including: A data preprocessing unit is configured to identify and remove abnormal data based on sensor categories, obtain corresponding noise characteristics, remove noise, and standardize monitoring data obtained by sensors of different categories; A data correction unit is configured to evaluate the operating status of each type of sensor, perform error correction on the preprocessed monitoring data based on the operating status of the sensor, and obtain corrected monitoring data; The data correction unit further includes screening the historical operation data to obtain the historical operation data capable of constructing the sensor performance evaluation model, and extracting features from the historical operation data capable of constructing the sensor performance evaluation model to obtain data features of the historical operation data as input data for constructing the sensor performance evaluation model; The feature extraction unit is configured to calculate the time domain statistical features and waveform features of the corrected monitoring data, construct a time domain feature vector, convert the time domain monitoring data through Fourier transform, calculate the frequency domain features, construct a frequency domain feature vector, input the time domain feature vector and the frequency domain feature vector into the network model for training, and mine the fault features in the data.

3. The electrical equipment fault monitoring and positioning system based on data analysis according to claim 2, characterized in that: The data correction unit obtains the data features of the historical operation data as the input data for building the sensor performance evaluation model. The specific execution steps are as follows: Real-time monitoring of the average power per unit time during the operation of electrical equipment, wherein the value range of the unit time is 12 hours to 36 hours; Compare the average power corresponding to each unit time with a preset power reference value, and extract the power value corresponding to the average power exceeding the preset power reference value as the target reference power value; When the target reference power value is one, the time slice is set using a preset basic time length; wherein the basic time length has a value range of 5 min-10 min; When there are multiple target reference power values, the target reference power standard deviation is obtained according to the average power value of the multiple target reference power values; The time length is set by using the target reference power standard deviation combined with an average power value of a plurality of target reference power values; Using the time length, the time length corresponding to the historical operation data is divided to obtain multiple time slices; Divide the operation time experienced by the historical operation data according to the time length to obtain multiple time slices; Data is filtered according to the historical operation data corresponding to each time slice to obtain the historical operation data that can be used to build a sensor performance evaluation model; Feature extraction is performed on historical operating data that can be used to build a sensor performance evaluation model, and data features of the historical operating data are obtained as input data for building the sensor performance evaluation model.

4. The electrical equipment fault monitoring and positioning system based on data analysis according to claim 3, characterized in that: The data preprocessing unit specifically includes: Determine the data fluctuation range of different categories of sensor data according to the sensor category, extract the abnormal data that does not meet the fluctuation range of the sensor data of this category, and perform jump anomaly and missing anomaly detection, remove duplicate labeled data, and eliminate abnormal data; Based on the sensor category, the noise characteristics of different types of sensor data after removing abnormal data are obtained, and the filter parameters are dynamically adjusted according to the real-time changes of the monitoring data to remove high-frequency noise and low-frequency interference; Establish standardized data format conversion rules, convert the monitoring data collected by various types of sensors with different encoding formats and storage structures into a unified format, and perform dimension normalization on various types of monitoring data through pre-set dimension conversion coefficients.

5. The electrical equipment fault monitoring and positioning system based on data analysis according to claim 4, characterized in that: The data correction unit specifically comprises: Obtain the historical operation data of various types of sensors during the operation of electrical equipment, including the original data collected by the sensors under different working conditions and at different times and the corresponding equipment operation status information, where the equipment operation status information corresponds to the historical operation data one by one; Extract the data features of historical operation data, take the historical operation data features as input and the sensor measurement error as output, and build a sensor performance evaluation model; Input the sensor operation data collected in real time into the sensor performance evaluation model for evaluation, and obtain the evaluation result of the current operation status of the sensor; According to the sensor performance evaluation results, analyze the error characteristics of the sensor data, determine the sensor error type, and select the corresponding error correction strategy from the strategy library; The collected monitoring data is subjected to error correction operation according to the error correction strategy. During the correction process, the correction effect is monitored in real time until the error of the monitoring data is controlled within the preset error threshold, thereby obtaining the corrected monitoring data.

6. The electrical equipment fault monitoring and positioning system based on data analysis according to claim 3, characterized in that: According to the historical operation data corresponding to each time slice, data is screened to obtain the historical operation data that can be used to build the sensor performance evaluation model. The specific execution steps are as follows: Extracting the overall waveform of normal sensor operation of each sensor stored in the database; Extracting the sensor waveform of each sensor of the historical operation data of each time slice as a sensor sub-waveform; Extracting waveform features of the sensor sub-waveform corresponding to each time slice; Compare the waveform characteristics of the sensor sub-waveform corresponding to each time slice with the waveform characteristics of the overall waveform of the normal operation of the sensor, determine the waveform position where the characteristic attribute of the waveform characteristic of the overall waveform of the normal operation of the sensor is the same as the waveform characteristic attribute of the sensor sub-waveform corresponding to the time slice, and intercept to obtain a reference waveform; Compare the sensor sub-waveform corresponding to each time slice with its corresponding reference waveform for similarity, and obtain a similarity value; Comparing the similarity value with a preset similarity threshold; Retrieving the time slice corresponding to the similarity value lower than the preset similarity threshold as the target time slice; The historical operation data contained in the target time slice is extracted as the historical operation data capable of constructing a sensor performance evaluation model.

7. The electrical equipment fault monitoring and positioning system based on data analysis according to claim 6, characterized in that: Fault detection module, including: A fault matching unit is configured to calculate the similarity between the fault feature and the known fault feature vector stored in the fault database, quantify the matching degree of the fault feature, compare the calculated similarity value with a preset similarity threshold interval, and determine the fault type corresponding to the fault feature; The fault matching unit also includes building a partition positioning rule based on the main features of the fault characteristics, dividing the fault database into multiple data subsets, extracting key feature parameters of the fault feature vector, and locating the corresponding fault database subset based on the extraction result; A fault analysis unit is configured to analyze the fault characteristics of the unidentified fault type based on the judgment result of the fault matching unit, mine the associated characteristic data with the unknown fault characteristics based on the historical monitoring data, and predict the possible corresponding fault type of the unknown fault characteristics based on the associated characteristic data, and evaluate the confidence of each prediction result; The database updating unit is configured to update the determined unknown fault features and their corresponding fault types and prediction credibility into the fault database according to the preset data format and storage rules based on the prediction confidence evaluation result.

8. The electrical equipment fault monitoring and positioning system based on data analysis according to claim 5, characterized in that: The fault detection module also includes: The extraction data correction unit corrects the monitoring data collected by each sensor during the correction process to a data correction amplitude ratio corresponding to an error at a preset error threshold; Comparing the data correction amplitude ratio with a preset amplitude ratio threshold; Extracting the data correction amplitude ratios corresponding to the amplitude ratios exceeding a preset threshold value to form a data correction amplitude ratio set; Comparing the number of data of the data correction amplitude ratios included in the data correction amplitude ratio set with a preset data number threshold; When the number of data of the data correction amplitude ratios included in the data correction amplitude ratio set exceeds a preset data number threshold, the lower limit value of the preset similarity threshold interval is adjusted using the data correction amplitude ratios included in the data correction amplitude ratio set to obtain the adjusted lower limit value; Each time the lower limit of the preset similarity threshold interval is adjusted, the data correction amplitude ratios contained in the data correction amplitude ratio set are cleared, and the data correction amplitude ratios corresponding to the amplitude ratio threshold exceeding the preset are re-recorded; Real-time monitoring of the lower limit of the similarity threshold interval; When the lower limit value of the similarity threshold interval is lower than the preset lower limit value threshold, an abnormal operation alarm of the device sensor is issued.

9. The electrical equipment fault monitoring and positioning system based on data analysis according to claim 7, characterized in that: Fault location module, including: A fault propagation analysis unit is configured to describe the operating state of the electrical equipment based on the fault type corresponding to the fault feature and in combination with the topological structure of the electrical equipment, and simulate the propagation path and impact range of the fault in the electrical equipment; A fault location determination unit is configured to determine the location range of the fault based on the propagation path and impact range simulation results, combined with equipment structure information, working principle and common failure modes, and generate a fault impact assessment report; The positioning result evaluation unit is configured to evaluate the location range of the fault, determine the accuracy and reliability of the location range, optimize the location range according to the evaluation result, and determine the location coordinates of the fault.

10. The electrical equipment fault monitoring and positioning system based on data analysis according to claim 9, characterized in that: The fault location determination unit further includes: Based on the simulation results of fault propagation path and impact range, the regional range formed by abnormal changes in physical quantities when the fault occurs is obtained, and the boundary of the fault impact is determined; According to the boundary shape characteristics of the fault area, the fault area is equivalent to a standard geometric figure that is closest to the boundary shape; The center position of the standard geometric figure is obtained, and the position where the physical quantity changes the most due to the fault is taken as the critical reference point of the fault, and the straight-line distance between the center position of the standard geometric figure and the critical reference point of the fault is obtained; Based on the calculated straight-line distance between the center position of the standard geometric figure and the critical reference point of the fault, a line segment with a length times the preset proportional coefficient of the straight-line distance is intercepted in the direction close to the critical reference point of the fault, and the end point position of the line segment close to the critical reference point of the fault is taken as the center position of the fault area; The installation position of the sensor is used as a reference point to obtain the effective monitoring range boundary line of the sensor closest to the fault center position, and the shortest straight-line distance between the fault center position and the effective monitoring range boundary line is calculated.

Images