GIS combined electric appliance operation monitoring and state evaluation system based on multi-feature fusion

By deploying multiple sensors and IoT devices on electrical equipment, performing data cleaning and feature fusion, establishing a multimodal data fusion model, and obtaining a comprehensive evaluation index, the limitations of traditional electrical equipment monitoring methods are overcome. This enables accurate assessment and timely early warning of electrical equipment operating status, ensuring the stability and reliability of the power system.

CN119046830APending Publication Date: 2024-11-29LIAOYUAN POWER SUPPLY COMPANY STATE GRID JILIN ELECTRIC POWER +1

Patent Information

Application Number
CN202411049672.1
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-01
Publication Date
2024-11-29

AI Technical Summary

Technical Problem

Traditional electrical monitoring methods use only one or a few parameters, which cannot fully reflect the operating status of electrical equipment. This makes it difficult to provide timely warnings of potential faults, affecting the stability and reliability of the power system and increasing maintenance costs and downtime.

Method used

A GIS-based combined electrical appliance operation monitoring and status assessment system based on multi-feature fusion is adopted. By deploying various types of sensors and IoT devices inside and outside the GIS equipment, the system collects electrical appliance operation parameters in real time, performs data cleaning, interpolation and smoothing, extracts time domain features, uses data fusion algorithms to establish a multimodal data fusion model, obtains a comprehensive evaluation index, and performs status assessment and display.

Benefits of technology

It enables comprehensive monitoring and accurate assessment of the operating status of electrical appliances, timely warning of abnormal situations, ensures safe and stable operation of electrical appliances, reduces failure risks and maintenance costs, and improves the accuracy and comprehensiveness of assessments.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119046830A_ABST
    Figure CN119046830A_ABST
Patent Text Reader

Abstract

The invention discloses a GIS combined electric appliance operation monitoring and state evaluation system based on multi-feature fusion, and relates to the technical field of electric appliance monitoring. When the system operates, comprehensive monitoring and accurate evaluation are carried out on the operation state of an electric appliance, multiple types of sensors and Internet of Things equipment are deployed inside and outside GIS equipment, and the operation state parameters of the equipment are collected in real time; the feature fusion module is used for establishing a multi-modal data fusion model by using a data fusion algorithm, acquiring a comprehensive evaluation index Pgzs, matching the comprehensive evaluation index Pgzs with a preset equipment operation state evaluation threshold P, generating an electric appliance operation state evaluation scheme, and performing data fusion on the electric appliance operation state evaluation scheme; and then, display and notification are carried out in various modes, so that subtle changes of various parameters in the operation process of the electric appliance can be captured and analyzed in real time, the accuracy and comprehensiveness of evaluation are improved through multi-modal data fusion, and early warning of abnormal conditions is carried out in time.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of electrical appliance monitoring, and in particular to a GIS combined electrical appliance operation monitoring and status evaluation system based on multi-feature fusion. Background Art

[0002] In the traditional electrical appliance monitoring process, a single or a few parameters are usually monitored, including current, voltage and temperature. However, this single-feature data monitoring method has great limitations and cannot fully reflect the operating status of electrical equipment. For example, single current or temperature monitoring can only provide partial information on the operation of the equipment, making it difficult to detect potential faults and hidden dangers.

[0003] These current situations are mainly due to the limitations of traditional electrical equipment monitoring technology and the insufficient application of data fusion methods. The single feature monitoring system cannot capture the correlation between multiple parameters, resulting in incomplete and inaccurate judgment of the equipment operating status. When problems occur in the operation of electrical equipment, it is often difficult to issue early warnings in a timely manner, which may lead to serious equipment failures and downtime events, affecting the stability and reliability of the power system. In addition, the lack of comprehensive status assessment and fault prediction methods may increase maintenance costs and equipment downtime, bringing great challenges to the operation and maintenance of the power system. Summary of the invention

[0004] In view of the deficiencies in the prior art, the present invention provides a GIS combined electrical appliance operation monitoring and status assessment system based on multi-feature fusion, which solves the problems mentioned in the background technology.

[0005] To achieve the above objectives, the present invention is implemented through the following technical solutions: a GIS combined electrical appliance operation monitoring and status evaluation system based on multi-feature fusion, including an equipment acquisition module, a data preprocessing module, a feature extraction module, a feature fusion module and a status evaluation module;

[0006] The equipment collection module collects equipment operation status parameters in real time by deploying several types of sensors and IoT devices inside and outside the GIS equipment to form a real-time equipment operation data group;

[0007] The data preprocessing module preprocesses the equipment real-time operation data group, including data cleaning, data interpolation and data smoothing, to form a processed equipment real-time operation data group;

[0008] The feature extraction module extracts time domain features from the processed device real-time operation data group to form a feature extraction data set;

[0009] The feature fusion module establishes a multimodal data fusion model for the feature extraction data set by using a data fusion algorithm, and obtains a comprehensive evaluation index Pgzs by training and fitting the multimodal data fusion model;

[0010] The status assessment module matches the preset equipment operation status assessment threshold value P with the comprehensive assessment index Pgzs, obtains the electrical equipment operation status assessment plan, and performs specific display and notification according to the electrical equipment operation status assessment plan.

[0011] Preferably, the device acquisition module includes a sensor acquisition unit and an Internet of Things acquisition unit;

[0012] The sensor acquisition unit collects equipment operating parameters, including electrical parameters, environmental parameters, mechanical parameters, and gas parameters, by installing several types of sensors, including current sensors, voltage sensors, temperature sensors, humidity sensors, vibration sensors, and SF6 gas sensors, at internal and external locations of the GIS equipment;

[0013] The Internet of Things acquisition unit is used to transmit and centrally manage the data acquired by the sensor acquisition unit, and synchronously integrate the data from different sensors to form a real-time operation data group of the equipment. The transmission includes the Internet of Things device transmitting the data collected by several sensors to the data preprocessing module through the gateway and router.

[0014] Preferably, the data preprocessing module includes a cleaning unit, an interpolation unit and a smoothing unit;

[0015] The cleaning unit cleans the collected equipment operation data to remove outliers and noise, including outlier detection, noise filtering, data verification and data cleaning;

[0016] The interpolation unit detects and fills in missing points of the equipment operation data after data cleaning, including using linear interpolation, spline interpolation and Lagrange interpolation to fill in the gaps in the data;

[0017] The smoothing unit performs smoothing processing on the equipment operation data after data cleaning, including using moving average, exponential smoothing and low-pass filtering smoothing processing;

[0018] The processed real-time operation data group of the equipment includes current value I, voltage value V, power, temperature value T, humidity, air pressure and vibration frequency.

[0019] Preferably, the feature extraction module includes an extraction unit;

[0020] The extraction unit extracts time domain feature information related to mean, variance, peak, skewness and kurtosis from the processed device real-time operation data group, and then forms a feature extraction data set with the extracted time domain feature information;

[0021] The feature extraction data set includes a current mean value Jdl, a voltage mean value Jdy, a temperature mean value Jwd, a current variance Fdl, a voltage variance Fdy, a temperature variance Fwd, a current peak value Dlmax, a voltage peak value Dymax and a temperature peak value Wdmax;

[0022] The current mean value Jdl is obtained by In the formula, N represents the total number of sampling times, i represents the i-th sampling, I represents the current value, and I i Represents the current value I of the i-th sampling;

[0023] The voltage mean Jdy is obtained by In the formula, V represents the voltage value, V i Represents the voltage value V of the i-th sampling;

[0024] The temperature mean Jwd is obtained by In the formula, T represents the temperature value, T i Represents the temperature value T of the i-th sampling;

[0025] The current variance Fdl is Wherein, the current variance Fdl is obtained by calculating the current value I and the current mean Jdl of the total number of sampling times N;

[0026] The voltage variance Fdy is In the formula, the voltage variance Fdy is obtained by calculating the voltage value V and the voltage mean Jdy of the total number of sampling times N;

[0027] The temperature variance Fwd is given by In the formula, the temperature variance Fwd is obtained by calculating the temperature value T of the total sampling times N and the temperature mean Jwd;

[0028] The current peak value Dlmax, the voltage peak value Dymax and the temperature peak value Wdmax are all obtained by statistically sorting and obtaining the maximum values ​​among the total number of sampling times N.

[0029] Preferably, the feature fusion module includes a modeling unit and a fitting unit;

[0030] The modeling unit establishes a multimodal data fusion model for the feature extraction data set by using a data fusion algorithm, and obtains the operation fluctuation factor Yxyz and the environment fluctuation factor Hjyz by training the established multimodal data fusion model;

[0031] The fitting unit obtains the comprehensive evaluation index Pgzs by fitting the operation fluctuation factor Yxyz and the environment fluctuation factor Hjyz obtained through model training.

[0032] Preferably, the comprehensive evaluation index Pgzs is obtained by the following calculation formula:

[0033]

[0034] In the formula, Pgzs represents the comprehensive evaluation index, Yxyz represents the operation fluctuation factor, Hjyz represents the environmental fluctuation factor, p1 and p2 represent the proportional coefficients of the operation fluctuation factor Yxyz and the environmental fluctuation factor Hjyz respectively;

[0035] Among them, 0≤p1≤1, 0≤p2≤1, and p1+p2=1, and K represents the first correction constant.

[0036] Preferably, the operation fluctuation factor Yxyz is obtained by the following calculation formula:

[0037]

[0038] Wherein, Yxyz represents the operation fluctuation factor, Jdl represents the current mean, Jdy represents the voltage mean, Jwd represents the temperature mean, Dlmax represents the current peak, Dymax represents the voltage peak, Wdmax represents the temperature peak, y1 represents the proportional coefficient of the calculation result of the current mean Jdl and the current peak Dlmax, y2 represents the proportional coefficient of the calculation result of the voltage mean Jdy and the voltage peak Dymax, y3 represents the proportional coefficient of the calculation result of the temperature mean Jwd and the temperature peak Wdmax;

[0039] Among them, 0≤y1≤1, 0≤y2≤1, 0≤y3≤1, and y1+y2+y3=1, and U represents the second correction constant.

[0040] Preferably, the environmental fluctuation factor Hjyz is obtained by the following calculation formula:

[0041]

[0042] Wherein, Hjyz represents the environmental fluctuation factor, Fdl represents the current variance, Fdy represents the voltage variance, Jwd represents the temperature mean, Wdmax represents the temperature peak, Fwd represents the temperature variance, h1 and h2 represent the proportionality coefficients of the calculation results of the current variance Fdl, the voltage variance Fdy and the temperature mean Jwd, h3 represents the proportionality coefficient of the calculation results of the temperature mean Jwd and the temperature peak Wdmax, and h4 represents the proportionality coefficient of the temperature variance Fwd and the temperature mean Jwd;

[0043] Among them, 0≤h1≤1, 0≤h2≤1, 0≤h3≤1, 0≤h4≤1, and h1+h2+h3+h4=1, and L represents the third correction constant.

[0044] Preferably, the state evaluation module includes a matching unit and an execution unit;

[0045] The matching unit matches the preset relevant information with the required comparison value, including matching the preset equipment operation status evaluation threshold P with the comprehensive evaluation index Pgzs to obtain the electrical equipment operation status evaluation scheme;

[0046] The execution unit performs specific display and notification according to the appliance operation status evaluation plan. The display includes real-time status dashboard display and fault warning panel display. The notification includes interface pop-up alarm window notification, automatic email notification through configuration of mail server and recipient list, and automatic SMS notification through integrated SMS gateway service.

[0047] Preferably, the electrical appliance operation status evaluation scheme is obtained by the following matching method:

[0048] The comprehensive evaluation index Pgzs is less than the equipment operation status evaluation threshold P, and the electrical equipment is in good condition. No notification will be given to relevant personnel, and the electrical equipment will be marked as in good condition on the visual interface, including a green mark.

[0049] The comprehensive evaluation index Pgzs ≥ the equipment operation status evaluation threshold P, and the electrical appliance operation status is unqualified. The unqualified items include current, voltage, power, temperature, humidity, air pressure and vibration frequency. Relevant personnel will be notified of the unqualified items at the same time, and the abnormal items of the abnormal appliances will be displayed on the visual interface at the same time, and the unqualified status will be marked, including yellow and red marks.

[0050] The present invention provides a GIS combined electrical appliance operation monitoring and status assessment system based on multi-feature fusion, which has the following beneficial effects:

[0051] (1) When the system is running, the comprehensive monitoring and accurate evaluation of the operating status of electrical appliances are realized through the combination of equipment acquisition module, data preprocessing module, feature extraction module, feature fusion module and status evaluation module. By deploying various types of sensors and IoT devices inside and outside the GIS equipment, the equipment operating status parameters are collected in real time, and the data is cleaned, interpolated and smoothed to ensure the accuracy and integrity of the data. The feature extraction module extracts time domain features from the processed data. The feature fusion module uses the data fusion algorithm to establish a multimodal data fusion model. After training and fitting, the comprehensive evaluation index Pgzs is obtained. The status evaluation module matches the preset equipment operating status evaluation threshold P with Pgzs to generate an electrical appliance operating status evaluation plan, and displays and notifies it in various ways. It can capture and analyze the subtle changes of various parameters in the operation process of the electrical appliance in real time. The accuracy and comprehensiveness of the evaluation are improved through multimodal data fusion, and abnormal situations are warned in time, which effectively solves the limitations and lack of real-time performance of the traditional monitoring system caused by single feature monitoring, ensures the safe and stable operation of electrical appliances, and reduces the risk of failure and maintenance costs.

[0052] (2) The comprehensive evaluation index Pgzs is obtained by calculating and fitting the operating fluctuation factor Yxyz and the environmental fluctuation factor Hjyz. It can process multiple parameters of the electrical appliance operating status in real time to obtain the subtle changes that occur during the operation of the appliance, and then dynamically respond to fluctuations in the environment and operating status, making the status monitoring of the appliance more refined.

[0053] (3) By matching the preset equipment operation status assessment threshold P with the comprehensive assessment index Pgzs, the electrical appliance operation status assessment plan is obtained, and then the operation status of the electrical appliance is accurately assessed. The corresponding abnormal marking is displayed on the visual interface, which simplifies the monitoring process under normal conditions and ensures that problems can be identified and handled in a timely manner. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] Figure 1 It is a flowchart diagram of the GIS combined electrical equipment operation monitoring and status assessment system based on multi-feature fusion of the present invention. DETAILED DESCRIPTION

[0055] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0056] In the traditional electrical appliance monitoring process, a single or a few parameters are usually monitored, including current, voltage and temperature. However, this single-feature data monitoring method has great limitations and cannot fully reflect the operating status of electrical equipment. For example, single current or temperature monitoring can only provide partial information on the operation of the equipment, making it difficult to detect potential faults and hidden dangers.

[0057] These current situations are mainly due to the limitations of traditional electrical equipment monitoring technology and the insufficient application of data fusion methods. The single feature monitoring system cannot capture the correlation between multiple parameters, resulting in incomplete and inaccurate judgment of the equipment operating status. When problems occur in the operation of electrical equipment, it is often difficult to issue early warnings in a timely manner, which may lead to serious equipment failures and downtime events, affecting the stability and reliability of the power system. In addition, the lack of comprehensive status assessment and fault prediction methods may increase maintenance costs and equipment downtime, bringing great challenges to the operation and maintenance of the power system.

[0058] Example 1

[0059] The present invention provides a GIS combined electrical equipment operation monitoring and status assessment system based on multi-feature fusion, please refer to Figure 1 , including equipment acquisition module, data preprocessing module, feature extraction module, feature fusion module and state assessment module;

[0060] The equipment collection module collects equipment operation status parameters in real time by deploying several types of sensors and IoT devices inside and outside the GIS equipment to form a real-time equipment operation data group;

[0061] The data preprocessing module preprocesses the equipment real-time operation data group, including data cleaning, data interpolation and data smoothing, to form a processed equipment real-time operation data group;

[0062] The feature extraction module extracts time domain features from the processed device real-time operation data group to form a feature extraction data set;

[0063] The feature fusion module establishes a multimodal data fusion model for the feature extraction data set by using a data fusion algorithm, and obtains a comprehensive evaluation index Pgzs by training and fitting the multimodal data fusion model;

[0064] The status assessment module matches the preset equipment operation status assessment threshold value P with the comprehensive assessment index Pgzs, obtains the electrical equipment operation status assessment plan, and performs specific display and notification according to the electrical equipment operation status assessment plan.

[0065] In this embodiment, through the combination of the equipment acquisition module, the data preprocessing module, the feature extraction module, the feature fusion module and the state evaluation module, the comprehensive monitoring and accurate evaluation of the operation status of the electrical appliances are realized. By deploying various types of sensors and IoT devices inside and outside the GIS equipment, the equipment operation status parameters are collected in real time, and the data is cleaned, interpolated and smoothed to ensure the accuracy and integrity of the data. The feature extraction module extracts time domain features from the processed data. The feature fusion module uses the data fusion algorithm to establish a multimodal data fusion model, and obtains the comprehensive evaluation index Pgzs after training and fitting. The state evaluation module matches the preset equipment operation status evaluation threshold P with Pgzs to generate an electrical appliance operation status evaluation plan, and displays and notifies in various ways. It can capture and analyze the subtle changes of various parameters in the operation process of the electrical appliance in real time, improve the accuracy and comprehensiveness of the evaluation through multimodal data fusion, and timely warn of abnormal situations, effectively solving the limitations and lack of real-time performance of the traditional monitoring system caused by single feature monitoring, ensuring the safe and stable operation of the electrical appliances, and reducing the risk of failure and maintenance costs.

[0066] Example 2

[0067] This embodiment is explained in Example 1, please refer to Figure 1 ,Specifically: the device acquisition module includes a sensor acquisition unit and an Internet of Things acquisition unit;

[0068] The sensor acquisition unit collects equipment operating parameters, including electrical parameters, environmental parameters, mechanical parameters, and gas parameters, by installing several types of sensors, including current sensors, voltage sensors, temperature sensors, humidity sensors, vibration sensors, and SF6 gas sensors, at internal and external locations of the GIS equipment;

[0069] The IoT acquisition unit is used to transmit and centrally manage the data acquired by the sensor acquisition unit, and simultaneously integrate the data from different sensors to form a real-time operation data group of the equipment. The transmission includes the IoT device transmitting the data collected by several sensors to the data preprocessing module through the gateway and router. The data preprocessing module includes a cleaning unit, an interpolation unit and a smoothing unit;

[0070] The cleaning unit cleans the collected equipment operation data to remove outliers and noise, including outlier detection, noise filtering, data verification and data cleaning. By cleaning the real-time equipment operation data group, outliers and noise in the data are detected and removed to ensure the accuracy and validity of the data;

[0071] The interpolation unit detects and fills in missing points of the equipment operation data after data cleaning, including using linear interpolation, spline interpolation and Lagrange interpolation to fill in the gaps in the data, and ensures the integrity of the data by detecting and filling in the missing points in the data;

[0072] The smoothing unit performs smoothing processing on the equipment operation data after data cleaning, including using moving average, exponential smoothing and low-pass filtering smoothing processing, and makes the data more stable by smoothing the data;

[0073] The processed real-time operation data group of the equipment includes current value I, voltage value V, power, temperature value T, humidity, air pressure and vibration frequency.

[0074] Example 3

[0075] This embodiment is explained in Example 1, please refer to Figure 1 ,Specifically: the feature extraction module includes an extraction unit;

[0076] The extraction unit extracts time domain feature information related to mean, variance, peak, skewness and kurtosis from the processed device real-time operation data group, and then forms a feature extraction data set with the extracted time domain feature information;

[0077] The feature extraction data set includes a current mean value Jdl, a voltage mean value Jdy, a temperature mean value Jwd, a current variance Fdl, a voltage variance Fdy, a temperature variance Fwd, a current peak value Dlmax, a voltage peak value Dymax and a temperature peak value Wdmax;

[0078] The current mean value Jdl is obtained by In the formula, N represents the total number of sampling times, i represents the i-th sampling, I represents the current value, and I i Represents the current value I of the i-th sampling;

[0079] The voltage mean Jdy is obtained by In the formula, V represents the voltage value, V i Represents the voltage value V of the i-th sampling;

[0080] The temperature mean Jwd is obtained by In the formula, T represents the temperature value, T i Represents the temperature value T of the i-th sampling;

[0081] The current variance Fdl is Wherein, the current variance Fdl is obtained by calculating the current value I and the current mean Jdl of the total number of sampling times N;

[0082] The voltage variance Fdy is In the formula, the voltage variance Fdy is obtained by calculating the voltage value V and the voltage mean Jdy of the total number of sampling times N;

[0083] The temperature variance Fwd is given by In the formula, the temperature variance Fwd is obtained by calculating the temperature value T of the total sampling times N and the temperature mean Jwd;

[0084] The current peak value Dlmax, the voltage peak value Dymax and the temperature peak value Wdmax are all obtained by statistically sorting and obtaining the maximum values ​​among the total number of sampling times N.

[0085] The feature fusion module includes a modeling unit and a fitting unit;

[0086] The modeling unit establishes a multimodal data fusion model for the feature extraction data set by using a data fusion algorithm, and obtains the operation fluctuation factor Yxyz and the environment fluctuation factor Hjyz by training the established multimodal data fusion model;

[0087] The fitting unit obtains the comprehensive evaluation index Pgzs by fitting the operation fluctuation factor Yxyz and the environment fluctuation factor Hjyz obtained through model training.

[0088] The comprehensive evaluation index Pgzs is obtained by the following calculation formula:

[0089]

[0090] In the formula, Pgzs represents the comprehensive evaluation index, Yxyz represents the operation fluctuation factor, Hjyz represents the environmental fluctuation factor, p1 and p2 represent the proportional coefficients of the operation fluctuation factor Yxyz and the environmental fluctuation factor Hjyz respectively;

[0091] Among them, 0≤p1≤1, 0≤p2≤1, and p1+p2=1, and K represents the first correction constant.

[0092] The operation fluctuation factor Yxyz is obtained by the following calculation formula:

[0093]

[0094] Wherein, Yxyz represents the operation fluctuation factor, Jdl represents the current mean, Jdy represents the voltage mean, Jwd represents the temperature mean, Dlmax represents the current peak, Dymax represents the voltage peak, Wdmax represents the temperature peak, y1 represents the proportional coefficient of the calculation result of the current mean Jdl and the current peak Dlmax, y2 represents the proportional coefficient of the calculation result of the voltage mean Jdy and the voltage peak Dymax, y3 represents the proportional coefficient of the calculation result of the temperature mean Jwd and the temperature peak Wdmax;

[0095] Among them, 0≤y1≤1, 0≤y2≤1, 0≤y3≤1, and y1+y2+y3=1, and U represents the second correction constant.

[0096] The environmental fluctuation factor Hjyz is obtained by the following calculation formula:

[0097]

[0098] Wherein, Hjyz represents the environmental fluctuation factor, Fdl represents the current variance, Fdy represents the voltage variance, Jwd represents the temperature mean, Wdmax represents the temperature peak, Fwd represents the temperature variance, h1 and h2 represent the proportionality coefficients of the calculation results of the current variance Fdl, the voltage variance Fdy and the temperature mean Jwd, h3 represents the proportionality coefficient of the calculation results of the temperature mean Jwd and the temperature peak Wdmax, and h4 represents the proportionality coefficient of the temperature variance Fwd and the temperature mean Jwd;

[0099] Among them, 0≤h1≤1, 0≤h2≤1, 0≤h3≤1, 0≤h4≤1, and h1+h2+h3+h4=1, and L represents the third correction constant.

[0100] In this embodiment, the comprehensive evaluation index Pgzs is obtained by calculating and fitting the operation fluctuation factor Yxyz and the environment fluctuation factor Hjyz, so that various parameters of the electrical appliance operation status can be processed in real time to obtain small changes occurring during the operation of the appliance, and then dynamically respond to fluctuations in the environment and operation status, making the status monitoring of the appliance more refined.

[0101] Example 4

[0102] This embodiment is explained in Example 1, please refer to Figure 1 ,Specifically: the state evaluation module includes a matching unit and an execution unit;

[0103] The matching unit matches the preset relevant information with the required comparison value, including matching the preset equipment operation status evaluation threshold P with the comprehensive evaluation index Pgzs to obtain the electrical equipment operation status evaluation scheme;

[0104] The execution unit performs specific display and notification according to the appliance operation status evaluation plan. The display includes real-time status dashboard display and fault warning panel display. The notification includes interface pop-up alarm window notification, automatic email notification through configuration of mail server and recipient list, and automatic SMS notification through integrated SMS gateway service.

[0105] The electrical appliance operation status evaluation scheme is obtained by the following matching method:

[0106] The comprehensive evaluation index Pgzs is less than the equipment operation status evaluation threshold P, and the electrical equipment is in good condition. No notification will be given to relevant personnel, and the electrical equipment will be marked as in good condition on the visual interface, including a green mark.

[0107] The comprehensive evaluation index Pgzs ≥ the equipment operation status evaluation threshold P, and the electrical appliance operation status is unqualified. The unqualified items include current, voltage, power, temperature, humidity, air pressure and vibration frequency. Relevant personnel will be notified of the unqualified items at the same time, and the abnormal items of the abnormal appliances will be displayed on the visual interface at the same time, and the unqualified status will be marked, including yellow and red marks.

[0108] In this embodiment, the preset equipment operation status assessment threshold P is matched with the comprehensive assessment index Pgzs to obtain the electrical appliance operation status assessment plan, and then the operation status of the electrical appliance is accurately assessed, and the corresponding abnormal markings are displayed on the visual interface, which simplifies the monitoring process under normal conditions and ensures that problems can be identified and handled in a timely manner.

[0109] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. GIS combined electrical equipment operation monitoring and status assessment system based on multi-feature fusion, characterized by: It includes equipment acquisition module, data preprocessing module, feature extraction module, feature fusion module and status assessment module; The equipment collection module collects equipment operation status parameters in real time by deploying several types of sensors and IoT devices inside and outside the GIS equipment to form a real-time equipment operation data group; The data preprocessing module preprocesses the equipment real-time operation data group, including data cleaning, data interpolation and data smoothing, to form a processed equipment real-time operation data group; The feature extraction module extracts time domain features from the processed device real-time operation data group to form a feature extraction data set; The feature fusion module establishes a multimodal data fusion model for the feature extraction data set by using a data fusion algorithm, and obtains a comprehensive evaluation index Pgzs by training and fitting the multimodal data fusion model; The status assessment module matches the preset equipment operation status assessment threshold value P with the comprehensive assessment index Pgzs, obtains the electrical equipment operation status assessment plan, and performs specific display and notification according to the electrical equipment operation status assessment plan.

2. The GIS combined electrical appliance operation monitoring and status assessment system based on multi-feature fusion according to claim 1 is characterized in that: The device acquisition module includes a sensor acquisition unit and an Internet of Things acquisition unit; The sensor acquisition unit collects equipment operating parameters, including electrical parameters, environmental parameters, mechanical parameters, and gas parameters, by installing several types of sensors, including current sensors, voltage sensors, temperature sensors, humidity sensors, vibration sensors, and SF6 gas sensors, at internal and external locations of the GIS equipment; The Internet of Things acquisition unit is used to transmit and centrally manage the data acquired by the sensor acquisition unit, and synchronously integrate the data from different sensors to form a real-time operation data group of the equipment. The transmission includes the Internet of Things device transmitting the data collected by several sensors to the data preprocessing module through the gateway and router.

3. The GIS combined electrical equipment operation monitoring and status assessment system based on multi-feature fusion according to claim 1 is characterized in that: The data preprocessing module includes a cleaning unit, an interpolation unit and a smoothing unit; The cleaning unit cleans the collected equipment operation data to remove outliers and noise, including outlier detection, noise filtering, data verification and data cleaning; The interpolation unit detects and fills in missing points of the equipment operation data after data cleaning, including using linear interpolation, spline interpolation and Lagrange interpolation to fill in the gaps in the data; The smoothing unit performs smoothing processing on the equipment operation data after data cleaning, including using moving average, exponential smoothing and low-pass filtering smoothing processing; The processed real-time operation data group of the equipment includes current value I, voltage value V, power, temperature value T, humidity, air pressure and vibration frequency.

4. The GIS combined electrical equipment operation monitoring and status assessment system based on multi-feature fusion according to claim 3 is characterized by: The feature extraction module includes an extraction unit; The extraction unit extracts time domain feature information related to mean, variance, peak, skewness and kurtosis from the processed device real-time operation data group, and then forms a feature extraction data set with the extracted time domain feature information; The feature extraction data set includes a current mean value Jdl, a voltage mean value Jdy, a temperature mean value Jwd, a current variance Fdl, a voltage variance Fdy, a temperature variance Fwd, a current peak value Dlmax, a voltage peak value Dymax and a temperature peak value Wdmax; The current mean value Jdl is obtained by In the formula, N represents the total number of sampling times, i represents the i-th sampling, I represents the current value, and I i Represents the current value I of the i-th sampling; The voltage mean Jdy is obtained by In the formula, V represents the voltage value, V i Represents the voltage value V of the i-th sampling; The temperature mean Jwd is obtained by In the formula, T represents the temperature value, T i Represents the temperature value T of the i-th sampling; The current variance Fdl is Wherein, the current variance Fdl is obtained by calculating the current value I and the current mean Jdl of the total number of sampling times N; The voltage variance Fdy is In the formula, the voltage variance Fdy is obtained by calculating the voltage value V and the voltage mean Jdy of the total number of sampling times N; The temperature variance Fwd is given by In the formula, the temperature variance Fwd is obtained by calculating the temperature value T of the total sampling times N and the temperature mean Jwd; The current peak value Dlmax, the voltage peak value Dymax and the temperature peak value Wdmax are all obtained by statistically sorting and obtaining the maximum values ​​among the total number of sampling times N.

5. The GIS combined electrical equipment operation monitoring and status assessment system based on multi-feature fusion according to claim 1 is characterized in that: The feature fusion module includes a modeling unit and a fitting unit; The modeling unit establishes a multimodal data fusion model for the feature extraction data set by using a data fusion algorithm, and obtains the operation fluctuation factor Yxyz and the environment fluctuation factor Hjyz by training the established multimodal data fusion model; The fitting unit obtains the comprehensive evaluation index Pgzs by fitting the operation fluctuation factor Yxyz and the environment fluctuation factor Hjyz obtained through model training.

6. The GIS combined electrical equipment operation monitoring and status assessment system based on multi-feature fusion according to claim 5 is characterized by: The comprehensive evaluation index Pgzs is obtained by the following calculation formula: In the formula, Pgzs represents the comprehensive evaluation index, Yxyz represents the operation fluctuation factor, Hjyz represents the environmental fluctuation factor, p1 and p2 represent the proportional coefficients of the operation fluctuation factor Yxyz and the environmental fluctuation factor Hjyz respectively; Among them, 0≤p1≤1, 0≤p2≤1, and p1+p2=1, and K represents the first correction constant.

7. The GIS combined electrical equipment operation monitoring and status assessment system based on multi-feature fusion according to claim 5 is characterized by: The operation fluctuation factor Yxyz is obtained by the following calculation formula: Wherein, Yxyz represents the operation fluctuation factor, Jdl represents the current mean, Jdy represents the voltage mean, Jwd represents the temperature mean, Dlmax represents the current peak, Dymax represents the voltage peak, Wdmax represents the temperature peak, y1 represents the proportional coefficient of the calculation result of the current mean Jdl and the current peak Dlmax, y2 represents the proportional coefficient of the calculation result of the voltage mean Jdy and the voltage peak Dymax, y3 represents the proportional coefficient of the calculation result of the temperature mean Jwd and the temperature peak Wdmax; Among them, 0≤y1≤1, 0≤y2≤1, 0≤y3≤1, and y1+y2+y3=1, and U represents the second correction constant.

8. The GIS combined electrical equipment operation monitoring and status assessment system based on multi-feature fusion according to claim 5 is characterized by: The environmental fluctuation factor Hjyz is obtained by the following calculation formula: Wherein, Hjyz represents the environmental fluctuation factor, Fdl represents the current variance, Fdy represents the voltage variance, Jwd represents the temperature mean, Wdmax represents the temperature peak, Fwd represents the temperature variance, h1 and h2 represent the proportionality coefficients of the calculation results of the current variance Fdl, the voltage variance Fdy and the temperature mean Jwd, h3 represents the proportionality coefficient of the calculation results of the temperature mean Jwd and the temperature peak Wdmax, and h4 represents the proportionality coefficient of the temperature variance Fwd and the temperature mean Jwd; Among them, 0≤h1≤1, 0≤h2≤1, 0≤h3≤1, 0≤h4≤1, and h1+h2+h3+h4=1, and L represents the third correction constant.

9. The GIS combined electrical equipment operation monitoring and status assessment system based on multi-feature fusion according to claim 1 is characterized by: The state evaluation module includes a matching unit and an execution unit; The matching unit matches the preset relevant information with the required comparison value, including matching the preset equipment operation status evaluation threshold P with the comprehensive evaluation index Pgzs to obtain the electrical equipment operation status evaluation scheme; The execution unit performs specific display and notification according to the appliance operation status evaluation plan. The display includes real-time status dashboard display and fault warning panel display. The notification includes interface pop-up alarm window notification, automatic email notification through configuration of mail server and recipient list, and automatic SMS notification through integrated SMS gateway service.

10. The GIS combined electrical equipment operation monitoring and status assessment system based on multi-feature fusion according to claim 9 is characterized in that: The electrical appliance operation status evaluation scheme is obtained by the following matching method: The comprehensive evaluation index Pgzs is less than the equipment operation status evaluation threshold P, and the electrical equipment is in good condition. No notification will be given to relevant personnel, and the electrical equipment will be marked as in good condition on the visual interface, including a green mark. The comprehensive evaluation index Pgzs ≥ the equipment operation status evaluation threshold P, and the electrical appliance operation status is unqualified. The unqualified items include current, voltage, power, temperature, humidity, air pressure and vibration frequency. Relevant personnel will be notified of the unqualified items at the same time, and the abnormal items of the abnormal appliances will be displayed on the visual interface at the same time, and the unqualified status will be marked, including yellow and red marks.

Citation Information

Patent Citations

  • Evaluation method for preventing overheating of GIS equipment

    CN109459639A

  • Extra-high voltage GIS operation state comprehensive diagnosis method and system based on data fusion

    CN113591985A

  • Fault diagnosis method and device for gas insulated switchgear

    CN115017947A

  • Intelligent diagnosis system and method for power transformation equipment GIS (Geographic Information System)

    CN116859152A

  • Intelligent monitoring method and system for GIS circuit breaker

    CN117607672A

Cited By

  • Intelligent monitoring system of transformer substation channel cover plate based on Internet of Things

    CN119401658A

  • Multi-mode fusion monitoring system for intelligent switch cabinet

    CN119622664A

  • Electricity utilization safety management and control method and system based on current fingerprint identification module

    CN119740105A