System and method for evaluating insulation performance of insulation voltage transformer

Abstract

The invention relates to the technical field of electric energy metering, in particular to an insulation performance evaluation system and method for an insulation voltage transformer, and the system comprises an insulation monitoring and sensing optimization module, a central storage unit, a data processing and abnormity analysis module, and an equipment performance evaluation module. The insulation monitoring and sensing optimization module builds an intelligent sensor network and a data acquisition and processing terminal, and realizes real-time monitoring of the insulation voltage transformer; the data processing and anomaly analysis module extracts key features and analyzes the key features in real time by using a local anomaly factor algorithm, so that the abnormal change of the insulation performance can be found in time; and the equipment performance evaluation module calculates a comprehensive gain value index to carry out detailed performance evaluation on equipment with problems, so that operation and maintenance personnel can know the state of the equipment and formulate a reasonable maintenance, replacement or optimization strategy. The method is used for solving the technical problems of incomplete monitoring and insufficient evaluation of the insulation performance of the insulation voltage transformer.

Description

Technical Field

[0001] The present invention relates to the technical field of electric energy metering, and in particular to a system and method for evaluating the insulation performance of an insulating voltage transformer. Background Art

[0002] Electric energy metering technology refers to the technical means of measuring, calculating and recording electric energy to achieve monitoring, evaluation and management of electric energy use. It also provides important data support for the operation and management of power systems by accurately and reliably measuring the consumption and supply of electric energy.

[0003] With the continuous development of science and technology, electric energy metering technology will continue to innovate and progress. Introducing this technology into the insulation performance evaluation of insulated voltage transformers can solve the following problems: the insulation status is difficult to evaluate accurately. Traditional evaluation methods may not be able to fully and accurately reflect the insulation status of voltage transformers, resulting in potential insulation defects not being discovered in time; insulation monitoring is not comprehensive and real-time performance is poor. Traditional insulated voltage transformer monitoring methods may have problems such as incomplete monitoring parameters and insufficient real-time monitoring, resulting in the inability to timely detect subtle changes in insulation performance or sudden failures, thereby affecting the stable operation of the power system; unreasonable sensor selection and configuration. According to the characteristics and monitoring requirements of different insulated voltage transformers, how to reasonably select sensors and optimize their configuration is a technical problem currently faced; low intelligence and automation levels. The existing insulation monitoring and evaluation systems may lack intelligence and automation functions, and cannot realize the automated monitoring and evaluation of insulated voltage transformers, increasing manual intervention and operation and maintenance costs; insufficient data processing and abnormal analysis capabilities. The massive data generated by insulation monitoring needs to be processed and analyzed efficiently and accurately. However, existing data processing and abnormal analysis technologies may not meet this demand, resulting in false alarms or missed alarms of insulation faults. To this end, the present invention proposes a system and method for evaluating the insulation performance of an insulating voltage transformer. Summary of the invention

[0004] The purpose of the present invention is to solve the problems in the background technology and to propose an insulation performance evaluation system and method for an insulation voltage transformer.

[0005] In order to achieve the above object, the present invention adopts the following technical solutions: An insulation performance evaluation system for an insulation voltage transformer, comprising: an insulation monitoring and sensing optimization module, a central storage unit, a data processing and abnormality analysis module, and an equipment performance evaluation module; The insulation monitoring and sensor optimization module is used to clarify the monitoring parameters of the insulation voltage transformer, build an intelligent sensor network, and configure the data acquisition and processing terminal for data collection; the raw data collected by the module is transmitted to the central storage unit in real time by wireless means; The data processing and abnormality analysis module is used to extract the key features of insulation performance from the raw data stored in the central storage unit, and use the local abnormality factor algorithm to analyze the abnormal patterns in the key features in real time to identify possible precursors of insulation failure; The central storage unit is the central link of data flow, responsible for receiving and storing the original data transmitted wirelessly from the insulation monitoring and sensor optimization modules; enabling the data processing and abnormality analysis modules to access the required data resources for further analysis and processing; The equipment performance evaluation module is used to filter and identify the insulation voltage transformers in faulty or abnormal states, and to evaluate the performance of the insulation voltage transformers in faulty or abnormal states by calculating the comprehensive gain value, so as to implement the maintenance plan; wherein, the insulation voltage transformers in faulty or abnormal states have the same meaning as the equipment in faulty or abnormal states.

[0006] It should be noted that the application objects of an insulation performance evaluation system and method for an insulated voltage transformer in the embodiment of the present invention can be widely covered in equipment status management or operation and maintenance control in the power system, and can be used to monitor the insulation performance, temperature changes, electrical parameters, environmental conditions and other aspects of the insulation voltage transformer during operation. Specifically, it can be used to perform real-time monitoring of the insulation voltage transformer through advanced sensing technology and data processing technology; the present invention uses multiple links such as sensor optimization configuration and data acquisition of the insulation monitoring and sensing optimization module, data analysis and abnormality identification of the data processing and abnormality analysis module, and performance evaluation and maintenance plan formulation of the equipment performance evaluation module. The modules cooperate with each other to jointly form an efficient and intelligent insulation performance evaluation system for the insulated voltage transformer, which is of great significance for improving the automation level of the power system, reducing operation and maintenance costs, and increasing the service life of equipment.

[0007] Furthermore, the insulation monitoring and sensor optimization module clarifies the monitoring parameters of the insulation voltage transformer, builds an intelligent sensor network, and configures the data acquisition and processing terminal to collect data. The process includes: According to the model, specification and operating environment of the insulation voltage transformer, the specific parameters of the monitoring target are clarified, including voltage, current, temperature, humidity and gas concentration; among them, the monitoring target is the insulation voltage transformer, and the specific parameters are the key influencing factors of insulation performance; Select sensors based on monitoring objectives and specific parameters to ensure full coverage of the area to be monitored; Understandably, when selecting a sensor, it is also necessary to consider factors such as the sensor’s installation location, installation method, measurement range, accuracy, stability, and compatibility with other devices to ensure that the sensor can accurately and reliably measure the required physical quantity and transmit the data to the data acquisition and processing terminal for further processing and analysis; After selecting the sensors, the minimum vertex cover method is used to optimize the sensor layout, that is, the arrangement of monitoring points, to ensure that all key monitoring points are covered while minimizing the number of sensors; Use the shortest path algorithm to design the communication of the sensor network to ensure that all sensor data can be efficiently and reliably transmitted to the central storage unit; According to the determined monitoring points and sensor selection results, install sensors around the voltage transformer to ensure good contact or appropriate distance between the sensor and the monitored object to accurately obtain monitoring data; Configure the data acquisition and processing terminal for data collection, set the data collection frequency and accuracy range, and ensure the real-time and accuracy of the data for subsequent data analysis and processing.

[0008] Furthermore, the process of optimizing the sensor layout using the minimum vertex cover method includes: Define the coverage of the sensor as , all monitoring points are considered as graphs The vertices in ; among them, represents the set of all monitoring points, represents the possible set of connected edges; For each monitoring point , define an indicator variable ;when , it means that Position the sensor, when , it means that no sensor is placed; among them, Represents an index; For each monitoring point , there is at least one monitoring point cover , that is, existence So that: In the formula, Is the element identifier, used to indicate the coverage state. represents an index; express exist Within the coverage area, Indicates that it is not within the coverage area; Minimize the total number of sensors required, i.e. ; The sensor layout problem is transformed into a graph search problem. A vertex set in , so that The radius of any vertex in All vertices in The value of is the minimum value, that is, to find a minimum vertex subset so that Each vertex in covers at least one monitoring point; It is understandable that the layout planning of sensor nodes should be carried out in combination with the structure and insulation performance requirements of the voltage transformer to obtain all possible monitoring points in the network. This includes determining the key locations that need to be monitored and considering the installation position, angle, direction and relative position of the sensor to other equipment when arranging the monitoring points to ensure the accuracy and reliability of the monitoring data.

[0009] Furthermore, the process of designing the communication of the sensor network using the shortest path algorithm includes: Modeling sensor networks as weighted graphs ;in, represents the set of sensor nodes, Represents the set of communication paths connecting sensor nodes, for each path Assign a weight , represents communication delay or energy consumption; It is understandable that the topology of the sensor network and the data transmission method are designed based on the actual layout of the voltage transformer, the monitoring requirements, and the communication method between sensors. When designing the topology diagram, it is necessary to clarify the location, number, communication path, and connection relationship of each sensor node with other nodes to ensure that the data can be transmitted efficiently and accurately; Get the source node and the target node ,from arrive Among all possible paths, select a path with the smallest total weight; let the source node To the target node The distance is 0, the source node The distance to all other nodes is infinite; At the beginning of the shortest path algorithm, the source node Add to the determined set; then, filter out the distance source node from the undetermined set each time The nearest node, add it to the determined set, and update all its neighbors to the source node The distance (if the neighbor can reach the source node through this node The distance is shorter), and this process is repeated until all nodes are added to the determined set, that is, the shortest distances of all nodes are determined.

[0010] Furthermore, the process of configuring the data acquisition processing terminal to collect data and setting the data acquisition frequency and accuracy range includes: Determine the frequency and accuracy range of data collection; It is understandable that the required data acquisition frequency and accuracy range are determined based on the characteristics of the insulation voltage transformer, the test requirements, and the expected data analysis accuracy; Select and configure the data acquisition and processing terminal, use a data acquisition and processing terminal with corresponding processing capacity and accuracy, ensure that the terminal can support the set data acquisition frequency and has sufficient resolution to meet the accuracy requirements; The acquisition frequency value is obtained through the frequency acquisition formula: acquisition frequency value = required number of data points / test cycle; where the acquisition frequency value represents the number of data points collected per second, in Hz, and the test cycle can be converted to seconds according to actual conditions; according to the test cycle (such as one day, one week, etc.) and the total number of required data points, the appropriate acquisition frequency value can be deduced; Using ADC resolution to determine accuracy range: Assume that the ADC resolution is , then the accuracy At least meet ; Among them, accuracy is usually measured by quantization error or resolution. Determine the required accuracy level, such as the minimum resolvable value of voltage measurement; Check the analog-to-digital converter (ADC) specifications of the data acquisition and processing terminal to ensure that its resolution meets or exceeds the required accuracy requirements; In the terminal configuration, select or set the corresponding ADC resolution and gain to ensure the accuracy of data acquisition; It is understandable that after the configuration is completed, a preliminary data collection test is carried out to verify whether the actual collection frequency and accuracy meet the set requirements. If there is a deviation, the configuration parameters can be adjusted according to the test results until the requirements are met.

[0011] Furthermore, the data processing and abnormality analysis module extracts the key features of the insulation performance from the raw data stored in the central storage unit, and uses the local abnormality factor algorithm to analyze the abnormal patterns in the key features in real time, including: Through the constructed sensor wireless communication network, each sensor data stream is obtained: , where Indicates sensor In time Data flow; Indicates sensor No. Measurement in time The readings; represents the observation dimension; Integrate all sensor data streams to obtain sensor monitoring data sets, i.e. ;in, represents the total number of sensors, and ; Sensor monitoring dataset Perform preprocessing to identify indicators related to insulation performance and obtain preprocessed monitoring data sets :Remove invalid or deviated measurements, use the sliding window method to detect and remove outliers, for ,make In time arrive The average value within , the standard deviation is , then the outlier point is defined as ; Remove outliers, collect the preprocessed monitoring data set, and mark it as ; Based on the preprocessed monitoring data set , extract the key features of insulation performance, and obtain the first key feature, the second key feature and the third key feature; Combine the first key feature, the second key feature and the third key feature to obtain a feature set ,in, Indicates the number of extracted features; Using local outlier factors Real-time analysis of unusual patterns in key features: H1. Calculate the local density deviation of each sample feature relative to its neighbors, assuming Any sample feature in ,That The values ​​are defined as follows: ; In the formula, express The nearest neighbor set of ; Indicates density; H2, based on the calculated value of the local density deviation, use it as the anomaly score; H3. Set an abnormal threshold, compare and analyze the abnormal score with the abnormal threshold. If the abnormal score is less than the abnormal threshold, the sample feature is determined. is the normal value; if the anomaly score is not less than the anomaly threshold, the sample feature is determined as potential anomalies and are marked as abnormal features; It is understood that for the features marked as abnormal, in-depth analysis is performed to identify precursors that may lead to insulation failure.

[0012] Furthermore, based on the preprocessed monitoring data set, the key features of the insulation performance are extracted to obtain the first key feature, the second key feature and the third key feature, including: The current and voltage signals are analyzed by Fourier transform, and the harmonic component features are extracted and marked as the first key feature: ; In the formula, is the representation of the signal in the frequency domain; represents the original signal; represents the relationship between frequency and time, that is, rotation and oscillation in the complex plane, is an imaginary unit used to ensure the rotation direction of the vector on the complex plane. represents a frequency variable, Determines the rotation speed, that is, the frequency; Indicates the integral operation The integral element of By calculating the ratio of the temperature difference between two points to the distance, the temperature gradient feature is obtained and marked as the second key feature: ; In the formula, Represents the temperature value of two points, Indicates the distance between two points; By calculating the pulse amplitude and discharge repetition rate of the discharge, the local discharge characteristics are obtained and marked as the third key feature: ; In the formula, Indicates the pulse amplitude; Respectively, in time The maximum and minimum voltage values; Indicates the discharge repetition rate; Indicates the number of discharges; Indicates unit time.

[0013] Furthermore, the equipment performance evaluation module filters and identifies the insulation voltage transformer with faults or abnormal conditions, and the process of evaluating the performance of the insulation voltage transformer with faults or abnormal conditions by calculating the comprehensive gain value includes: Based on the abnormal characteristic value output by the data processing and abnormal analysis module, determine and identify the insulation voltage transformer with fault or abnormal state; For equipment with confirmed faults or abnormal conditions, extract its historical operation data and maintenance records from the database; It is understandable that these data include but are not limited to: historical operating data: voltage fluctuations, current changes, temperature curves, humidity records, gas concentration monitoring, etc., which reflect the operating status and environmental conditions of the equipment at different time points; maintenance records: the time, content, replaced parts, test results after maintenance, etc. of all previous maintenance, which are crucial for analyzing the cause and speed of equipment performance degradation; After obtaining the historical operation data and maintenance records of the faulty or abnormal equipment, enter the performance analysis phase: The overall performance of the equipment in faulty or abnormal state is evaluated by the comprehensive gain value, where the calculation formula of the comprehensive gain is: ; In the formula, Indicates the comprehensive gain value, which is a quantitative parameter that combines multiple performance indicators and is used to reflect the overall performance of the device under different conditions; Indicates the stability gain value; Indicates the efficiency gain value; represents the reliability gain value; represent the weights of stability gain, efficiency gain, and reliability gain respectively, and ,The weight allocation depends on the importance of each performance indicator to the overall performance evaluation; It is understandable that the stability gain can be calculated based on the fluctuation of the key parameters of the equipment. The better the stability, the higher the gain value. The efficiency gain reflects the efficiency of the equipment in the process of energy conversion or transmission. For the insulated voltage transformer, it may involve the accuracy and efficiency of voltage conversion. The reliability gain is calculated based on the failure rate and maintenance cycle of the equipment. The lower the failure rate and the longer the maintenance cycle, the higher the reliability gain. When classifying the faulty or abnormal state equipment in combination with the comprehensive gain value, the comprehensive gain value of the faulty or abnormal state equipment is matched with a preset gain threshold to obtain a normal maintenance label, an important maintenance label or an emergency maintenance label; If the comprehensive gain value is less than the preset gain threshold, the performance of the faulty or abnormal state device is judged to be extremely poor, a first maintenance signal is generated, and the corresponding faulty or abnormal state device is associated with an emergency maintenance tag; if the comprehensive gain value is not less than the preset gain threshold and not greater than the preset gain threshold, , is a real number greater than 100, the performance of the faulty or abnormal state device is judged to be poor, a second maintenance signal is generated, and the corresponding faulty or abnormal state device is associated with an important maintenance tag; if the comprehensive gain value is greater than the preset gain threshold , it is determined that the performance of the faulty or abnormal state device is normal, a third maintenance signal is generated, and the corresponding faulty or abnormal state device is associated with a normal maintenance tag; An equipment maintenance plan is formulated based on the results of the comprehensive gain value evaluation: for the first maintenance signal generated, the equipment performance is severely degraded and cannot be restored through maintenance, and needs to be upgraded or replaced to improve the reliability and efficiency of the entire system; for the second maintenance signal generated, the equipment has already failed and corrective maintenance is required to ensure that the equipment returns to normal operation; for the third maintenance signal generated, the equipment performance has declined but no serious failure has occurred, and preventive maintenance is required, such as replacing aging parts, adjusting operating parameters, etc., to prevent failures from occurring.

[0014] A method for evaluating insulation performance of an insulating voltage transformer, comprising: Define the monitoring parameters of the insulation voltage transformer, build an intelligent sensor network, and configure the data acquisition and processing terminal for data collection; wirelessly transmit the collected raw data to the central storage unit in real time; Extracting key features of insulation performance from raw data stored in a central storage unit and analyzing abnormal patterns in the key features in real time using a local anomaly factor algorithm; The insulation voltage transformer with fault or abnormal state is filtered and identified, and the performance of the insulation voltage transformer with fault or abnormal state is evaluated by calculating the comprehensive gain value.

[0015] Compared with the existing technology, the advantages of the insulation performance evaluation system and method of an insulation voltage transformer provided by the present invention are: The present invention defines the monitoring parameters of the insulation voltage transformer, selects sensors according to the monitoring parameters of the insulation voltage transformer, builds and optimizes the intelligent sensor network, and configures the data acquisition and processing terminal at the same time, thereby avoiding data redundancy and invalid monitoring, improving the pertinence and effectiveness of monitoring, and the intelligent characteristics of the sensor network also enable the system to automatically adapt to environmental changes, thereby improving the stability and reliability of monitoring; the original data collected by the module is transmitted to the central storage unit in real time by wireless means, effectively reducing the delay and error of data transmission; The present invention extracts key features of insulation performance and uses a local abnormal factor algorithm to analyze abnormal patterns in key features in real time, identifies possible precursors of insulation failures, provides a valuable data basis for subsequent analysis, reduces the complexity and workload of data analysis, and can promptly detect subtle changes in insulation performance. The present invention improves the accuracy of fault identification by filtering and identifying the insulated voltage transformers with faults or abnormal conditions, and calculates the gain value to perform performance evaluation on the insulated voltage transformers with faults or abnormal conditions, so as to formulate corresponding equipment maintenance plans, provide scientific basis and decision support for operation and maintenance personnel, and make the operation and maintenance work more scientific, reasonable and efficient.

[0016] To sum up, the present invention can improve the real-time and accuracy of insulation performance monitoring and enhance the reliability and stability of the system through comprehensive data processing and analysis according to actual conditions. The entire data monitoring and performance evaluation process is highly automated, which reduces the frequency and intensity of manual inspections, reduces operation and maintenance costs, and jointly improves the efficiency and accuracy of monitoring, analysis and evaluation of the insulation performance of the insulating voltage transformer, thereby ensuring the normal operation of a subsequent insulating voltage transformer insulation performance evaluation system and method. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 This is a module diagram of an insulation performance evaluation system for an insulation voltage transformer proposed by the present invention.

[0018] Figure 2 The present invention provides a flow chart of a method for evaluating the insulation performance of an insulating voltage transformer. DETAILED DESCRIPTION

[0019] 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 implementation regulations described 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.

[0020] Reference Figure 1 , an insulation performance evaluation system for an insulation voltage transformer, the system comprising an insulation monitoring and sensing optimization module, a central storage unit, a data processing and abnormality analysis module, and an equipment performance evaluation module; The insulation monitoring and sensor optimization module is used to clarify the monitoring parameters of the insulation voltage transformer, build an intelligent sensor network, and configure the data acquisition and processing terminal for data collection; the raw data collected by the module is transmitted to the central storage unit in real time by wireless means; The data processing and abnormality analysis module is used to extract the key features of insulation performance from the raw data stored in the central storage unit, and use the local abnormality factor algorithm to analyze the abnormal patterns in the key features in real time to identify possible precursors of insulation failure; The central storage unit is the central link of data flow, responsible for receiving and storing the original data transmitted wirelessly from the insulation monitoring and sensor optimization modules; enabling the data processing and abnormality analysis modules to access the required data resources for further analysis and processing; The equipment performance evaluation module is used to filter and identify the insulation voltage transformers in faulty or abnormal states, and to evaluate the performance of the insulation voltage transformers in faulty or abnormal states by calculating the comprehensive gain value, so as to implement the maintenance plan; wherein, the insulation voltage transformers in faulty or abnormal states have the same meaning as the equipment in faulty or abnormal states.

[0021] It should be noted that the application objects of an insulation performance evaluation system and method for an insulated voltage transformer in the embodiment of the present invention can be widely covered in equipment status management or operation and maintenance control in the power system, and can be used to monitor the insulation performance, temperature changes, electrical parameters, environmental conditions and other aspects of the insulation voltage transformer during operation. Specifically, it can be used to perform real-time monitoring of the insulation voltage transformer through advanced sensing technology and data processing technology; the present invention uses multiple links such as sensor optimization configuration and data acquisition of the insulation monitoring and sensing optimization module, data analysis and abnormality identification of the data processing and abnormality analysis module, and performance evaluation and maintenance plan formulation of the equipment performance evaluation module. The modules cooperate with each other to jointly form an efficient and intelligent insulation performance evaluation system for the insulated voltage transformer, which is of great significance for improving the automation level of the power system, reducing operation and maintenance costs, and increasing the service life of equipment.

[0022] The insulation monitoring and sensor optimization module clarifies the monitoring parameters of the insulation voltage transformer, builds an intelligent sensor network, and configures the data acquisition and processing terminal for data acquisition. The steps include: Step 101: according to the model, specification and operating environment of the insulation voltage transformer, specify the specific parameters of the monitoring target, including voltage, current, temperature, humidity and gas concentration; wherein the monitoring target is the insulation voltage transformer, and the specific parameters are key influencing factors of insulation performance; Step 102: Select sensors according to monitoring targets and specific parameters to ensure that the area to be monitored can be fully covered; In step 102, when selecting a sensor, factors such as the sensor's installation position, installation method, measurement range, accuracy, stability, and compatibility with other devices need to be considered to ensure that the sensor can accurately and reliably measure the required physical quantity and transmit the data to the data acquisition and processing terminal for further processing and analysis; at the same time, for different types of sensors, the control method of their distance or contact range may be different. For example, the measurement range of a non-contact sensor is controlled by adjusting the measurement distance and angle. When arranging, it is necessary to ensure that the distance between the sensor and the object to be measured is moderate to avoid measurement errors or overheating damage to the sensor due to being too close, and to avoid signal attenuation or inability to measure due to being too far; a contact sensor needs to be in close contact with the object to be measured to obtain accurate measurement data. When arranging, it is necessary to ensure that the contact surface of the sensor is in full contact with the surface of the object to be measured to avoid measurement errors due to gaps or looseness; Step 103: After selecting the sensors, the minimum vertex cover method is used to optimize the sensor layout, that is, the arrangement of the monitoring points, to ensure that all key monitoring points are covered while minimizing the number of sensors: Define the coverage of the sensor as , all monitoring points are considered as graphs The vertices in ; among them, represents the set of all monitoring points, represents the possible set of connected edges; For each monitoring point , define an indicator variable ;when , it means that Position the sensor, when , it means that no sensor is placed; among them, Represents an index; For each monitoring point , there is at least one monitoring point cover , that is, existence So that: In the formula, Is the element identifier, used to indicate the coverage state. represents an index; express exist Within the coverage area, Indicates that it is not within the coverage area; Minimize the total number of sensors required, i.e. ; The sensor layout problem is transformed into a graph search problem. A vertex set in , so that The radius of any vertex in All vertices in The value of is the minimum value, that is, to find a minimum vertex subset so that Each vertex in covers at least one monitoring point; In step 103, the layout planning of sensor nodes is carried out in combination with the structure and insulation performance requirements of the voltage transformer, and all possible monitoring points in the network are obtained, which includes determining the key positions that need to be monitored, and when arranging the monitoring points, considering the installation position, angle, direction and relative position of the sensor with other equipment to ensure the accuracy and reliability of the monitoring data; Step 104: Use the shortest path algorithm to design the communication of the sensor network to ensure that all sensor data can be efficiently and reliably transmitted to the central storage unit: Modeling sensor networks as weighted graphs ;in, represents the set of sensor nodes, Represents the set of communication paths connecting sensor nodes, for each path Assign a weight , represents communication delay or energy consumption; It is understandable that the topology of the sensor network and the data transmission method are designed based on the actual layout of the voltage transformer, the monitoring requirements, and the communication method between sensors. When designing the topology diagram, it is necessary to clarify the location, number, communication path, and connection relationship of each sensor node with other nodes to ensure that the data can be transmitted efficiently and accurately; Get the source node and the target node ,from arrive Among all possible paths, select a path with the smallest total weight; let the source node To the target node The distance is 0, the source node The distance to all other nodes is infinite; At the beginning of the shortest path algorithm, the source node Add to the determined set; then, filter out the distance source node from the undetermined set each time The nearest node, add it to the determined set, and update all its neighbors to the source node The distance (if the neighbor can reach the source node through this node The distance is shorter), repeat this process until all nodes are added to the determined set, that is, the shortest distance of all nodes is determined; Step 105: Install sensors around the voltage transformer according to the determined monitoring points and sensor selection results, ensuring good contact or appropriate distance between the sensor and the monitored object to accurately obtain monitoring data; Step 106: Configure the data acquisition and processing terminal to collect data, set the data acquisition frequency and accuracy range, and ensure the real-time and accuracy of the data for subsequent data analysis and processing: Determine the data acquisition frequency and accuracy range. It is understandable that the required data acquisition frequency and accuracy range are determined based on the characteristics of the insulation voltage transformer, the test requirements, and the expected data analysis accuracy. For example, if you need to capture rapidly changing insulation performance parameters, you may need a higher acquisition frequency, while if you focus on long-term trends, the acquisition frequency can be appropriately reduced. Select and configure the data acquisition and processing terminal, use a data acquisition and processing terminal with corresponding processing capacity and accuracy, ensure that the terminal can support the set data acquisition frequency and has sufficient resolution to meet the accuracy requirements; The acquisition frequency value is obtained through the frequency acquisition formula: acquisition frequency value = required number of data points / test cycle; where the acquisition frequency value indicates the number of data points collected per second, in Hz, and the test cycle can be converted into seconds according to the actual situation; according to the test cycle (such as one day, one week, etc.) and the total number of required data points, the appropriate acquisition frequency value can be deduced; for example, if 1000 data points need to be collected within one hour, the acquisition frequency value = 1000 / 3600≈0.28Hz; enter and save the acquisition frequency value in the setting interface of the data acquisition processing terminal or through the configuration software; Using ADC resolution to determine accuracy range: Assume that the ADC resolution is , then the accuracy At least meet ; Among them, accuracy is usually measured by quantization error or resolution. Determine the required accuracy level, such as the minimum resolvable value of voltage measurement; Check the specifications of the analog-to-digital converter (ADC) of the data acquisition and processing terminal to ensure that its resolution meets or exceeds the required accuracy requirements; for example, if 1mV accuracy is required, the ADC resolution should be at least 1mV or lower; In the terminal configuration, select or set the corresponding ADC resolution and gain to ensure the accuracy of data acquisition; In step 106, after the configuration is completed, a preliminary data acquisition test is performed to verify whether the actual acquisition frequency and accuracy meet the set requirements. If there is a deviation, the configuration parameters can be adjusted according to the test results until the requirements are met. In actual applications, the impact of factors such as signal amplification factor and noise level on the final accuracy must also be considered.

[0023] The steps of extracting the key features of insulation performance from the raw data stored in the central storage unit and analyzing the abnormal patterns in the key features in real time using the local abnormal factor algorithm include: Step 201: Obtain each sensor data stream through the constructed sensor wireless communication network: , where Indicates sensor In time Data flow; Indicates sensor No. Measurement in time The readings; represents the observation dimension; Step 202: Integrate all sensor data streams to obtain sensor monitoring data sets, i.e. ;in, represents the total number of sensors, and ; Step 203: Sensor monitoring data set Perform preprocessing to identify indicators related to insulation performance and obtain preprocessed monitoring data sets :Remove invalid or deviated measurements, use the sliding window method to detect and remove outliers, for ,make In time arrive The average value within , the standard deviation is , then the outlier point is defined as ; Remove outliers, collect the preprocessed monitoring data set, and mark it as ; Step 204: Based on the preprocessed monitoring data set , extract the key features of insulation performance, and obtain the first key feature, the second key feature and the third key feature: The current and voltage signals are analyzed by Fourier transform, and the harmonic component features are extracted and marked as the first key feature: ; In the formula, is the representation of the signal in the frequency domain; represents the original signal; represents the relationship between frequency and time, that is, rotation and oscillation in the complex plane, is an imaginary unit used to ensure the rotation direction of the vector on the complex plane. represents a frequency variable, Determines the rotation speed, that is, the frequency; Indicates the integral operation The integral element of By calculating the ratio of the temperature difference between two points to the distance, the temperature gradient feature is obtained and marked as the second key feature: ; In the formula, Represents the temperature value of two points, Indicates the distance between two points; By calculating the pulse amplitude and discharge repetition rate of the discharge, the local discharge characteristics are obtained and marked as the third key feature: ; In the formula, Indicates the pulse amplitude; Respectively expressed in time The maximum and minimum voltage values; Indicates the discharge repetition rate; Indicates the number of discharges; Indicates unit time; Step 205: Combine the first key feature, the second key feature and the third key feature to obtain a feature set ,in, Indicates the number of extracted features; Step 206: Use local anomaly factor Real-time analysis of unusual patterns in key features: H1. Calculate the local density deviation of each sample feature relative to its neighbors, assuming Any sample feature in ,That The values ​​are defined as follows: ; In the formula, express The nearest neighbor set of ; Indicates density; H2, based on the calculated value of the local density deviation, use it as the anomaly score; H3. Set an abnormal threshold, compare and analyze the abnormal score with the abnormal threshold. If the abnormal score is less than the abnormal threshold, the sample feature is determined. is the normal value; if the anomaly score is not less than the anomaly threshold, the sample feature is determined as potential anomalies and are marked as abnormal features; In step H3, for the features marked as abnormal, in-depth analysis is performed to identify possible precursors to insulation failure. For example, if the temperature of multiple sensors rises abnormally and is accompanied by increased current fluctuations, the problem may be caused by overheating of the insulation material. In this case, the maintenance team should be notified immediately and the timestamp and related feature values ​​of the abnormal event should be recorded.

[0024] The equipment performance evaluation module filters and identifies the insulation voltage transformer with fault or abnormal state, and the steps of evaluating the performance of the insulation voltage transformer with fault or abnormal state by calculating the comprehensive gain value include: Step 301: Determine and identify an insulation voltage transformer with a fault or abnormal state based on the abnormal characteristic value output by the data processing and abnormality analysis module; Step 302: For the determined faulty or abnormal state equipment, extract its historical operation data and maintenance records from the database; In step 302, the data include but are not limited to: historical operation data: voltage fluctuation, current change, temperature curve, humidity record, gas concentration monitoring, etc., which reflect the operation status and environmental conditions of the equipment at different time points; maintenance records: the time, content, replaced parts, test results after maintenance, etc., which are crucial for analyzing the cause and speed of equipment performance degradation; Step 303: After obtaining the historical operation data and maintenance records of the faulty or abnormal state equipment, enter the performance analysis phase: evaluate the overall performance of the faulty or abnormal state equipment through the comprehensive gain value, wherein the calculation formula of the comprehensive gain is: ; In the formula, Indicates the comprehensive gain value, which is a quantitative parameter that combines multiple performance indicators and is used to reflect the overall performance of the device under different conditions; Indicates the stability gain value; Indicates the efficiency gain value; represents the reliability gain value; represent the weights of stability gain, efficiency gain, and reliability gain respectively, and ,The weight allocation depends on the importance of each performance indicator to the overall performance evaluation; In step 303, the stability gain can be calculated based on the fluctuation of the key parameters of the equipment. For example, it can be expressed by the inverse of the stability index of voltage or current (such as standard deviation or coefficient of variation). The better the stability, the higher the gain value: stability gain value = 1 / standard deviation or coefficient of variation (voltage fluctuation); the efficiency gain reflects the efficiency of the equipment in the process of energy conversion or transmission. For an insulated voltage transformer, it may involve the accuracy and efficiency of voltage conversion: efficiency gain value = actual conversion efficiency / theoretical maximum efficiency; the reliability gain is calculated based on the failure rate and maintenance cycle of the equipment. The lower the failure rate and the longer the maintenance cycle, the higher the reliability gain: ; Step 304: When classifying the faulty or abnormal state equipment in combination with the comprehensive gain value, the comprehensive gain value of the faulty or abnormal state equipment is matched with a preset gain threshold to obtain a normal maintenance label, an important maintenance label or an emergency maintenance label; If the comprehensive gain value is less than the preset gain threshold, the performance of the faulty or abnormal state device is judged to be extremely poor, a first maintenance signal is generated, and the corresponding faulty or abnormal state device is associated with an emergency maintenance tag; if the comprehensive gain value is not less than the preset gain threshold and not greater than the preset gain threshold, , is a real number greater than 100, the performance of the faulty or abnormal state device is judged to be poor, a second maintenance signal is generated, and the corresponding faulty or abnormal state device is associated with an important maintenance tag; if the comprehensive gain value is greater than the preset gain threshold , it is determined that the performance of the faulty or abnormal state device is normal, a third maintenance signal is generated, and the corresponding faulty or abnormal state device is associated with a normal maintenance tag; Step 305: formulate an equipment maintenance plan based on the result of the comprehensive gain value evaluation: for the first maintenance signal generated, the performance of the equipment is seriously degraded and cannot be restored through maintenance, and it needs to be upgraded or replaced to improve the reliability and efficiency of the entire system; for the second maintenance signal generated, the equipment has failed and corrective maintenance is required to ensure that the equipment returns to normal operation; for the third maintenance signal generated, the performance of the equipment has declined but no serious failure has occurred, and preventive maintenance is required, such as replacing aging parts, adjusting operating parameters, etc., to prevent failures from occurring.

[0025] In the embodiment of the present invention, by building an intelligent sensor network, multi-point and all-round real-time monitoring of the insulation voltage transformer is realized, the coverage and accuracy of the monitoring are improved, and by configuring an efficient data acquisition and processing terminal, the sensor data can be quickly and accurately collected and preliminarily processed, the data transmission volume is reduced, and the system efficiency is improved. By adopting a wireless method to transmit the original data to the central storage unit in real time, the complexity and limitations of the wired connection are avoided, and the flexibility and scalability of the system are enhanced. By extracting the key features of the insulation performance, a strong support is provided for subsequent analysis. By using an advanced local abnormal factor algorithm, the abnormal mode in the key features is analyzed in real time, and the insulation performance degradation or potential fault can be discovered in time. By identifying the insulation voltage transformer with a fault or abnormal state, false alarms and missed alarms are reduced. By calculating the comprehensive gain value index, the equipment with problems is evaluated in detail, and a scientific basis is provided for subsequent maintenance, replacement or optimization. In summary, the example of the present invention solves the problem of incomplete monitoring and insufficient evaluation of the insulation performance of the insulation voltage transformer. In actual situations, more data and context information may be needed to make specific decisions and optimization plans.

[0026] Reference Figure 2 , a method for evaluating insulation performance of an insulating voltage transformer, comprising: Define the monitoring parameters of the insulation voltage transformer, build an intelligent sensor network, and configure the data acquisition and processing terminal for data collection; wirelessly transmit the collected raw data to the central storage unit in real time; Extracting key features of insulation performance from raw data stored in a central storage unit and analyzing abnormal patterns in the key features in real time using a local anomaly factor algorithm; The insulation voltage transformer with fault or abnormal state is filtered and identified, and the performance of the insulation voltage transformer with fault or abnormal state is evaluated by calculating the comprehensive gain value.

[0027] In addition, the formulas involved in the above are all calculated by removing dimensions and taking their numerical values. They are a formula that is closest to the actual situation obtained by collecting a large amount of data and performing software simulation. The proportional coefficient in the formula and the various preset thresholds in the analysis process are set by technical personnel in this field according to actual conditions or obtained by simulating a large amount of data; the size of the proportional coefficient is to quantify each parameter to obtain a specific value for subsequent comparison. The size of the proportional coefficient depends on the amount of sample data and the preliminary setting of the corresponding processing coefficient for each group of sample data by technical personnel in this field; as long as it does not affect the proportional relationship between the parameter and the quantized value.

[0028] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device embodiment, since it is basically based on the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0029] For the convenience of description, the above device is described in various units according to their functions. Of course, when implementing the present application, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0030] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0031] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0032] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0033] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0034] Secondly: In the drawings of the embodiments disclosed in the present invention, only the structures related to the embodiments disclosed in the present invention are involved, and other structures can refer to the general design. In the absence of conflict, the same embodiment and different embodiments of the present invention can be combined with each other; Finally: 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 insulation performance evaluation system for an insulation voltage transformer, characterized in that: It includes insulation monitoring and sensor optimization module, central storage unit, data processing and abnormal analysis module and equipment performance evaluation module; The insulation monitoring and sensor optimization module is used to clarify the monitoring parameters of the insulation voltage transformer, build an intelligent sensor network, and configure the data acquisition and processing terminal for data collection; the raw data collected by the module is transmitted to the central storage unit in real time by wireless means; The data processing and anomaly analysis module is used to extract the key features of insulation performance from the raw data stored in the central storage unit, and use the local anomaly factor algorithm to analyze the abnormal patterns in the key features in real time; The equipment performance evaluation module is used to filter and identify the insulation voltage transformers with faults or abnormal conditions, and to perform performance evaluation on the insulation voltage transformers with faults or abnormal conditions by calculating the comprehensive gain value.

2. The insulation performance evaluation system of an insulation voltage transformer according to claim 1, characterized in that: The insulation monitoring and sensor optimization module clarifies the monitoring parameters of the insulation voltage transformer, builds an intelligent sensor network, and configures the data acquisition and processing terminal for data acquisition. The process includes: According to the model, specification and operating environment of the insulation voltage transformer, the specific parameters of the monitoring target should be clarified, including voltage, current, temperature, humidity and gas concentration; Select sensors based on monitoring objectives and specific parameters; After selecting the sensors, the minimum vertex cover method is used to optimize the sensor layout, i.e., the arrangement of monitoring points; Communication design of sensor networks using shortest path algorithms; According to the determined monitoring points and sensor selection results, install sensors around the voltage transformer; Configure the data acquisition and processing terminal for data collection, and set the data collection frequency and accuracy range.

3. The insulation performance evaluation system of an insulation voltage transformer according to claim 2, characterized in that: The process of optimizing sensor layout using the minimum vertex cover method includes: Define the coverage of the sensor as , all monitoring points are considered as graphs The vertices in ; among them, represents the set of all monitoring points, represents the possible set of connected edges; For each monitoring point , define an indicator variable ;when , it means that Position the sensor, when , it means that no sensor is placed; among them, Represents an index; For each monitoring point , there is at least one monitoring point cover , that is, existence So that: In the formula, Is the element identifier, used to indicate the coverage state. represents an index; express exist Within the coverage area, Indicates that it is not within the coverage area; Minimize the total number of sensors required, i.e. ; The sensor layout problem is transformed into a graph search problem. A vertex set in , so that The radius of any vertex in All vertices in The value of is the minimum value.

4. The insulation performance evaluation system of an insulation voltage transformer according to claim 2, characterized in that: The process of designing communication in sensor networks using the shortest path algorithm includes: Modeling sensor networks as weighted graphs ;in, represents the set of sensor nodes, Represents the set of communication paths connecting sensor nodes, for each path Assign a weight , represents communication delay or energy consumption; Get the source node and the target node ,from arrive Among all possible paths, select a path with the smallest total weight; let the source node To the target node The distance is 0, the source node The distance to all other nodes is infinite; At the beginning of the shortest path algorithm, the source node Add to the determined set; then, filter out the distance source node from the undetermined set each time The nearest node, add it to the determined set, and update all its neighbors to the source node The process is repeated until all nodes are added to the determined set, that is, the shortest distances of all nodes are determined.

5. The insulation performance evaluation system of an insulation voltage transformer according to claim 2, characterized in that: The process of configuring the data acquisition and processing terminal for data acquisition and setting the data acquisition frequency and accuracy range includes: Determine the frequency and accuracy range of data collection; Select and configure data acquisition and processing terminals; The acquisition frequency value is obtained through the frequency acquisition formula: acquisition frequency value = required number of data points / test cycle; Using ADC resolution to determine accuracy range: Assume that the ADC resolution is , then the accuracy At least meet .

6. The insulation performance evaluation system of an insulation voltage transformer according to claim 1, characterized in that: The data processing and anomaly analysis module extracts the key features of insulation performance from the raw data stored in the central storage unit and uses the local anomaly factor algorithm to analyze the abnormal patterns in the key features in real time. The process includes: Through the constructed sensor wireless communication network, each sensor data stream is obtained: , where Indicates sensor In time Data flow; Indicates sensor No. Measurement in time The readings; represents the observation dimension; Integrate all sensor data streams to obtain sensor monitoring data sets, i.e. ;in, represents the total number of sensors, and ; Sensor monitoring dataset Perform preprocessing to obtain the preprocessed monitoring data set :Use the sliding window method to detect and remove outliers. ,make In time arrive The average value within , the standard deviation is , then the outlier point is defined as ; Remove outliers, collect the preprocessed monitoring data set, and mark it as ; Based on the preprocessed monitoring data set , extract the key features of insulation performance, and obtain the first key feature, the second key feature and the third key feature; Combine the first key feature, the second key feature and the third key feature to obtain a feature set ,in, Indicates the number of extracted features; Using local outlier factors Real-time analysis of unusual patterns in key features: H1. Calculate the local density deviation of each sample feature relative to its neighbors, assuming Any sample feature in ,That The values ​​are defined as follows: ; In the formula, express The nearest neighbor set of ; Indicates density; H2, based on the calculated value of the local density deviation, use it as the anomaly score; H3. Set an abnormal threshold, compare and analyze the abnormal score with the abnormal threshold. If the abnormal score is less than the abnormal threshold, the sample feature is determined. is the normal value; if the anomaly score is not less than the anomaly threshold, the sample feature is determined It is a potential anomaly and is marked as an abnormal feature.

7. The insulation performance evaluation system of an insulation voltage transformer according to claim 6, characterized in that: Based on the preprocessed monitoring data set, the key features of the insulation performance are extracted to obtain the first key feature, the second key feature and the third key feature. The process includes: The current and voltage signals are analyzed by Fourier transform, and the harmonic component features are extracted and marked as the first key feature: ; In the formula, is the representation of the signal in the frequency domain; represents the original signal; represents the relationship between frequency and time, that is, rotation and oscillation in the complex plane, is an imaginary unit used to ensure the rotation direction of the vector on the complex plane. represents a frequency variable, Determines the rotation speed, that is, the frequency; Indicates the integral operation The integral element of By calculating the ratio of the temperature difference between two points to the distance, the temperature gradient feature is obtained and marked as the second key feature: ; In the formula, Represents the temperature value of two points, Indicates the distance between two points; By calculating the pulse amplitude and discharge repetition rate of the discharge, the local discharge characteristics are obtained and marked as the third key feature: ; In the formula, Indicates the pulse amplitude; Respectively, in time The maximum and minimum voltage values; Indicates the discharge repetition rate; Indicates the number of discharges; Indicates unit time.

8. The insulation performance evaluation system of an insulation voltage transformer according to claim 1, characterized in that: The equipment performance evaluation module filters and identifies the insulation voltage transformer with faults or abnormal conditions. The process of evaluating the performance of the insulation voltage transformer with faults or abnormal conditions by calculating the comprehensive gain value includes: Based on the abnormal characteristic value output by the data processing and abnormal analysis module, determine and identify the insulation voltage transformer with fault or abnormal state; For equipment with confirmed faults or abnormal conditions, extract its historical operation data and maintenance records from the database; After obtaining the historical operation data and maintenance records of the faulty or abnormal equipment, enter the performance analysis phase: The overall performance of the equipment in faulty or abnormal state is evaluated by the comprehensive gain value, where the calculation formula of the comprehensive gain is: ; In the formula, Indicates the comprehensive gain value, which is a quantitative parameter that combines multiple performance indicators and is used to reflect the overall performance of the device under different conditions; Indicates the stability gain value; Indicates the efficiency gain value; represents the reliability gain value; represent the weights of stability gain, efficiency gain, and reliability gain respectively, and ; When classifying the faulty or abnormal state equipment in combination with the comprehensive gain value, the comprehensive gain value of the faulty or abnormal state equipment is matched with a preset gain threshold to obtain a normal maintenance label, an important maintenance label or an emergency maintenance label; If the comprehensive gain value is less than the preset gain threshold, the performance of the faulty or abnormal state device is judged to be extremely poor, a first maintenance signal is generated, and the corresponding faulty or abnormal state device is associated with an emergency maintenance tag; if the comprehensive gain value is not less than the preset gain threshold and not greater than the preset gain threshold, , is a real number greater than 100, the performance of the faulty or abnormal state device is judged to be poor, a second maintenance signal is generated, and the corresponding faulty or abnormal state device is associated with an important maintenance tag; if the comprehensive gain value is greater than the preset gain threshold , it is determined that the performance of the faulty or abnormal state device is normal, a third maintenance signal is generated, and the corresponding faulty or abnormal state device is associated with a normal maintenance tag; An equipment maintenance plan is formulated based on the results of the comprehensive gain value evaluation: for the first maintenance signal generated, the equipment performance is severely degraded and cannot be restored through maintenance, and needs to be upgraded or replaced; for the second maintenance signal generated, the equipment has already failed and requires corrective maintenance; for the third maintenance signal generated, the equipment performance has declined but has not yet suffered a serious failure, and requires preventive maintenance.

9. A method for evaluating the insulation performance of an insulating voltage transformer, characterized in that: The method for evaluating the insulation performance of an insulating voltage transformer according to any one of claims 1 to 8 comprises: Define the monitoring parameters of the insulation voltage transformer, build an intelligent sensor network, and configure the data acquisition and processing terminal for data collection; wirelessly transmit the collected raw data to the central storage unit in real time; Extracting key features of insulation performance from raw data stored in a central storage unit and analyzing abnormal patterns in the key features in real time using a local anomaly factor algorithm; The insulation voltage transformer with fault or abnormal state is filtered and identified, and the performance of the insulation voltage transformer with fault or abnormal state is evaluated by calculating the comprehensive gain value.

Images