Equipment partial discharge remote comprehensive monitoring method and system combined with remote terminal

Abstract

The invention discloses an equipment partial discharge remote comprehensive monitoring method and system combined with a remote terminal, and relates to the field of equipment partial discharge monitoring, and the method comprises the steps: setting corresponding monitoring equipment in one-to-one correspondence, and receiving and recording equipment partial discharge monitoring data through the remote terminal; determining the specific position or regional position information of partial discharge generated by the equipment; according to the damage degree of the insulating material, a risk warning level is formulated; judging whether the insulating material has a damage risk or not, and giving a risk warning; setting a corresponding equipment partial discharge solution; and establishing an equipment partial discharge remote comprehensive monitoring platform, visually displaying equipment partial discharge monitoring data through a chart, and updating and optimizing a machine learning algorithm model through a field actual detection result. The method has the advantages that the position information of the partial discharge generated by the equipment is effectively identified, the risk warning level is provided, the detection process of the partial discharge of the equipment is simplified, and the remote monitoring efficiency and emergency capability of the partial discharge of the equipment are improved.

Description

Technical Field

[0001] The present invention relates to the field of equipment partial discharge monitoring, and in particular to a method and system for remote comprehensive monitoring of equipment partial discharge combined with a remote terminal. Background Art

[0002] Equipment partial discharge refers to the discharge of the insulating materials in the power equipment in a local area due to the high-intensity electric field and voltage. Since the generation of equipment partial discharge will affect the damage of the insulating materials, although the insulation effect is still there under the partial discharge of a slight degree, each partial discharge may cause irreparable damage to the insulating materials. If it is not handled in time, it may cause the insulating materials to completely lose their insulation properties in the long run, causing damage to electricity and equipment, and leading to power system failure. Therefore, it is of great significance to strengthen the monitoring of equipment partial discharge, timely handle and maintain equipment operation and safety, and ensure the normal operation of the power system.

[0003] The existing monitoring technology for partial discharge of equipment mainly focuses on analyzing the impact of partial discharge signals on equipment status through monitoring data of partial discharge monitoring equipment, but lacks the determination of location information of partial discharge of equipment. During field inspection, this leads to a wide inspection range and complex inspection process, which is not conducive to the rapid processing of partial discharge of equipment. Secondly, the existing partial discharge processing technology cannot monitor the impact of long-term accumulation of partial discharge, resulting in inaccurate judgment of the impact of long-term partial discharge on power equipment, thereby causing waste of resources and damage to electrical equipment. Summary of the invention

[0004] In order to solve the above technical problems, a method and system for remote comprehensive monitoring of partial discharge of equipment combined with a remote terminal are provided. The technical solution solves the problem that the location information of partial discharge of equipment is lacking in the above background technology. During the field detection process, the detection range is wide and the detection process is complicated, which is not conducive to the rapid processing of partial discharge of equipment. Secondly, the existing partial discharge processing technology cannot monitor the impact of long-term accumulation of partial discharge, resulting in inaccurate judgment of the impact of long-term partial discharge on power equipment, thereby causing waste of resources and damage to electrical equipment.

[0005] In order to achieve the above purpose, the technical solution adopted by the present invention is:

[0006] A remote comprehensive monitoring method for partial discharge of equipment combined with a remote terminal, comprising:

[0007] According to the partial discharge environment to be monitored, corresponding monitoring equipment is set up to correspond to it, and the monitoring data of partial discharge of the equipment is received and recorded through the remote terminal;

[0008] Based on the UWB positioning principle, determine the specific location or regional location information where the device generates partial discharge;

[0009] Based on test experiments and big data analysis, risk warning levels are formulated according to the degree of damage to the insulation materials;

[0010] Based on the machine learning algorithm model, determine whether the insulation material is at risk of damage and issue a risk warning;

[0011] According to the damage degree of the insulation material, combined with the location information of the equipment generating partial discharge, set up the corresponding equipment partial discharge solution;

[0012] Establish a remote comprehensive monitoring platform for equipment partial discharge, intuitively display the monitoring data of equipment partial discharge through charts, and update and optimize the machine learning algorithm model through actual on-site detection results.

[0013] Preferably, the step of setting corresponding monitoring equipment to correspond to the partial discharge environment to be monitored, and receiving and recording the monitoring data of the partial discharge of the equipment through the remote terminal specifically includes:

[0014] According to the partial discharge environment to be monitored, corresponding monitoring equipment is set up to correspond to it, and is used to monitor the amplitude, frequency, period, location area and temperature data of the partial discharge generated by the equipment;

[0015] Among them, amplitude refers to the intensity of partial discharge generated by the device, frequency refers to the number of times the device generates partial discharge per unit time, and period refers to the time period during which the device continuously generates partial discharge;

[0016] The monitoring data of partial discharge of the equipment is received and recorded through the remote terminal, and the corresponding data channels are set up to display the monitoring data transmitted by the monitoring equipment in real time through different channels.

[0017] Preferably, the determining the location of the area where the device generates partial discharge based on the UWB positioning principle specifically includes:

[0018] According to the partial discharge environment to be monitored, ultrasonic sensors are set at fixed positions in three directions and accurate position information is obtained;

[0019] Based on the UWB positioning principle, a circle is drawn with the distance detected by the three ultrasonic sensors as the radius. The coordinates of the common intersection of the three circles are calculated to determine the specific location information where the device generates partial discharge.

[0020] Optimize the UWB positioning algorithm, calculate the location area where the device generates partial discharge, and reduce the distance error caused by influencing factors;

[0021] The expression based on the UWB positioning principle is:

[0022]

[0023] In the formula, is the propagation speed of ultrasonic waves from the ultrasonic sensor, which is a fixed value. is the total time for the ultrasonic sensor to travel back and forth. They are the fixed position information of the ultrasonic sensor in three directions. The coordinates of the common intersection of a circle with the distance detected by the three ultrasonic sensors as the radius are the actual position information of the device.

[0024] The optimized UWB positioning algorithm expression is:

[0025]

[0026] In the formula, The coordinate information of the three intersection points of the central area is generated respectively, wherein the location area where the device generates partial discharge can be determined in a triangular form according to the coordinate information of the three intersection points.

[0027] Preferably, based on the test experiments and big data analysis, a risk warning level is formulated according to the degree of damage to the insulating material:

[0028] Based on the product description of the insulation material and big data analysis, the interval thresholds of each degree edge are set according to the degree of damage of the insulation material, where the degree of damage of the insulation material is divided into low, medium and severe;

[0029] According to the degree of damage of the insulating material, combined with the data of partial discharge monitoring, test experiments are carried out through the control variable method to record the impact of different partial discharge monitoring data on the degree of damage of the insulating material;

[0030] Based on the test results, a list of impacts of the degree of damage to the insulating materials is established, in which the amplitude, frequency, and period of partial discharge generated by the equipment are used as input items, and the degree of damage to the insulating materials is used as an output item.

[0031] Preferably, the method is based on a machine learning algorithm model to determine whether the insulating material is at risk of damage and issue a risk warning;

[0032] According to the monitoring data type of the equipment partial discharge, establish The input matrix and parameter term matrix;

[0033] according to The input matrix and Parameter item matrix, establish the linear regression equation of the damage degree of the insulation material;

[0034] According to the linear regression equation of the damage degree of the insulating material, the error relationship between the calculated value and the actual value is established;

[0035] Based on the likelihood function algorithm, a loss function of the damage degree of the insulation material is established;

[0036] Based on the mini-batch gradient descent algorithm, the parameter update equation of the monitoring data of the partial discharge of each device is established;

[0037] Import the data in the list of damage impacts of insulation materials, use the algorithm to perform iterative calculations, and establish a machine learning algorithm model based on linear regression. By inputting the corresponding equipment partial discharge monitoring data, determine whether there is a risk of insulation material damage and the degree of damage, and issue a risk warning;

[0038] Said The input matrix and The parameter matrix expression is:

[0039]

[0040] In the formula, For equipment partial discharge monitoring data The parameter matrix, is the error constant term, , , are the parameters of the amplitude, frequency and period of partial discharge generated by the equipment, For equipment partial discharge monitoring data The input matrix, is a constant term with a value of 1, , , They are the input values ​​of the amplitude, frequency and period of partial discharge generated by the equipment respectively;

[0041] The linear regression equation for the degree of damage of the insulating material is expressed as:

[0042]

[0043] In the formula, is the calculated value matrix of the damage degree of the insulation material, The error matrix between the calculated value and the actual value of the damage degree of the insulation material;

[0044] The error relationship between the calculated value and the actual value is:

[0045]

[0046] In the formula, The error between the calculated value and the actual value of the damage degree of the insulation material. is the actual value of the damage degree of the insulation material, where To obey Gaussian distribution, and ;

[0047] The loss function expression of the damage degree of the insulating material is:

[0048]

[0049] In the formula, The error loss deviation between the calculated value and the actual value of the damage degree of the insulation material, The number of sample groups for the damage degree of the insulation materials affecting the inventory;

[0050] The parameter update equation expression of the monitoring data of the partial discharge of each device is:

[0051]

[0052] In the formula, For the Update parameters of partial discharge monitoring data of each device in the group, For the Parameters of partial discharge monitoring data of each device in the group, is the learning rate, For the The first Group monitoring data.

[0053] Preferably, the setting of a corresponding equipment partial discharge solution based on the result of judging the degree of damage of the insulating material and combining the location information of the equipment generating partial discharge specifically includes:

[0054] According to the damage degree of the insulation material, if it is judged to be low damage, a blue warning is issued, and it is necessary to strengthen the online monitoring and power distribution intensity of the area;

[0055] If it is judged to be moderately damaged, a yellow warning will be issued, requiring on-site testing of the partial discharge environment of the monitored equipment, and replacement and maintenance of the insulation materials will be carried out based on the actual test results;

[0056] If it is judged to be severely damaged, it means that the insulation material of the monitoring equipment will completely lose its insulation performance, and a red warning will be issued. It is necessary to test the performance of the regional equipment and completely replace the insulation material.

[0057] Preferably, the establishment of a remote comprehensive monitoring platform for partial discharge of equipment, visually displaying the monitoring data of partial discharge of equipment through charts, and updating and optimizing the machine learning algorithm model through actual on-site detection results specifically includes:

[0058] Establish a remote comprehensive monitoring platform for partial discharge of equipment to receive and record the monitoring data of partial discharge of equipment that needs to be monitored, and display the partial discharge monitoring data of equipment in different areas through different channels;

[0059] Establish a histogram of equipment partial discharge monitoring data, visually display the monitoring data and change trend of equipment partial discharge through charts, and display the degree of damage of insulation materials through color indicator lights;

[0060] Based on the comparison model judgment results and actual on-site detection results, the machine learning algorithm model is updated and optimized.

[0061] Furthermore, a remote comprehensive monitoring system for partial discharge of equipment combined with a remote terminal is proposed, which is used to implement the above-mentioned remote comprehensive monitoring method for partial discharge of equipment combined with a remote terminal, including:

[0062] A data acquisition module, which is used to set corresponding monitoring equipment to correspond to the partial discharge environment to be monitored, and receive and record the monitoring data of the partial discharge of the equipment through a remote terminal;

[0063] A partial discharge positioning module, which is used to determine the specific location or regional location information of the device generating partial discharge based on the UWB positioning principle;

[0064] A risk warning module, which is used to formulate a risk warning level based on the degree of damage to the insulating material based on test experiments and big data analysis; based on a machine learning algorithm model, determine whether the insulating material has a risk of damage and issue a risk warning;

[0065] A monitoring and processing module, which is used to determine the results according to the degree of damage of the insulating material and set the corresponding partial discharge solution for the equipment in combination with the location information of the partial discharge generated by the equipment; establish a remote comprehensive monitoring platform for partial discharge of the equipment, intuitively display the monitoring data of partial discharge of the equipment through charts, and update and optimize the machine learning algorithm model through actual on-site detection results;

[0066] Preferably, the risk warning module specifically includes:

[0067] A warning level unit, which is used to formulate a risk warning level according to the degree of damage of the insulating material based on test experiments and big data analysis;

[0068] A risk warning unit, which is used to determine whether the insulating material has a risk of damage based on a machine learning algorithm model and issue a risk warning;

[0069] Preferably, the monitoring and processing module specifically includes:

[0070] A partial discharge processing unit, the partial discharge processing unit is used to set a corresponding device partial discharge solution according to the result of the judgment of the degree of damage of the insulating material and the location information of the partial discharge generated by the device;

[0071] The partial discharge monitoring unit is used to establish a remote comprehensive monitoring platform for partial discharge of equipment, intuitively display the monitoring data of partial discharge of equipment through charts, and update and optimize the machine learning algorithm model through actual on-site detection results.

[0072] Compared with the prior art, the present invention has the following beneficial effects:

[0073] The location information of the partial discharge of the equipment is determined according to the UWB positioning algorithm, and the attenuation and interference of the transmission of ultrasound due to the influence of external factors are analyzed, thereby extending the round-trip time of ultrasound transmission and increasing the distance between the ultrasonic sensor and the partial discharge position, resulting in a non-unique partial discharge position and generating a closed area. Secondly, the machine learning algorithm model is used to analyze the influence of the amplitude, frequency and period of the partial discharge of the equipment on the degree of damage to the insulating material. According to the amplitude, frequency and period data of the partial discharge of the equipment received in real time, the degree of damage to the insulating material is judged, and corresponding treatment measures are taken according to the degree of damage to the insulating material, so as to effectively identify the location information of the partial discharge of the equipment and provide the risk warning level, simplify the detection process of the partial discharge of the equipment, and improve the remote monitoring efficiency and emergency response capability of the partial discharge of the equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0074] Figure 1 It is a flow chart of a method for remote comprehensive monitoring of partial discharge of equipment combined with a remote terminal of the present invention;

[0075] Figure 2 This is a flow chart of determining the location of the area where the device generates partial discharge based on the UWB positioning principle of the present invention;

[0076] Figure 3 The machine learning algorithm model of the present invention is used to determine whether the insulating material has a risk of damage and make a risk warning flow chart;

[0077] Figure 4 According to the present invention, according to the result of judging the degree of damage of the insulating material and combining the location information of the partial discharge generated by the equipment, a corresponding equipment partial discharge solution flow chart is set. DETAILED DESCRIPTION

[0078] The following description is used to disclose the present invention so that those skilled in the art can implement the present invention. The preferred embodiments described below are only examples, and those skilled in the art may think of other obvious variations.

[0079] Reference Figure 1 As shown, a remote comprehensive monitoring method for partial discharge of equipment combined with a remote terminal includes:

[0080] According to the partial discharge environment to be monitored, corresponding monitoring equipment is set up to correspond to it, and the monitoring data of partial discharge of the equipment is received and recorded through the remote terminal;

[0081] Based on the UWB positioning principle, determine the specific location or regional location information where the device generates partial discharge;

[0082] Based on test experiments and big data analysis, risk warning levels are formulated according to the degree of damage to the insulation materials;

[0083] Based on the machine learning algorithm model, determine whether the insulation material is at risk of damage and issue a risk warning;

[0084] According to the damage degree of the insulation material, combined with the location information of the equipment generating partial discharge, set up the corresponding equipment partial discharge solution;

[0085] Establish a remote comprehensive monitoring platform for equipment partial discharge, intuitively display the monitoring data of equipment partial discharge through charts, and update and optimize the machine learning algorithm model through actual on-site detection results.

[0086] It can be explained that this solution determines the location information of the partial discharge of the equipment according to the UWB positioning algorithm, and calculates the location area where the partial discharge of the equipment occurs under the influence of the external environment, so as to facilitate on-site detection and improve detection efficiency. Secondly, the machine learning algorithm model is used to analyze the influence of the amplitude, frequency and period of the partial discharge of the equipment on the degree of damage to the insulating material. According to the amplitude, frequency and period data of the partial discharge of the equipment received in real time, the degree of damage to the insulating material is judged and corresponding risk warning prompts are made, and corresponding processing measures are taken according to the received risk warning prompts, so as to effectively identify the location information of the partial discharge generated by the equipment and provide the risk warning level.

[0087] Reference Figure 2 As shown, the method of determining the location of the area where the device generates partial discharge based on the UWB positioning principle specifically includes:

[0088] According to the partial discharge environment to be monitored, ultrasonic sensors are set at fixed positions in three directions and accurate position information is obtained;

[0089] Based on the UWB positioning principle, a circle is drawn with the distance detected by the three ultrasonic sensors as the radius. The coordinates of the common intersection of the three circles are calculated to determine the specific location information where the device generates partial discharge.

[0090] Optimize the UWB positioning algorithm, calculate the location area where the device generates partial discharge, and reduce the distance error caused by influencing factors;

[0091] The expression based on the UWB positioning principle is:

[0092]

[0093] In the formula, is the propagation speed of ultrasonic waves from the ultrasonic sensor, which is a fixed value. is the total time for the ultrasonic sensor to travel back and forth. They are the fixed position information of the ultrasonic sensor in three directions. The coordinates of the common intersection of a circle with the distance detected by the three ultrasonic sensors as the radius are the actual position information of the device.

[0094] The optimized UWB positioning algorithm expression is:

[0095]

[0096] In the formula, The coordinate information of the three intersection points of the central area is generated respectively, wherein the location area where the device generates partial discharge can be determined in a triangular form according to the coordinate information of the three intersection points.

[0097] It can be explained that the principle of UWB positioning is to set up UWB base stations with fixed position information in three directions, calculate the distance at which the electromagnetic wave encounters the obstacle, and make a circle with this distance as the radius. By finding the common intersection of the three circles, the position coordinates of the obstacle are obtained. This solution is based on the UWB positioning principle. By setting up ultrasonic sensors in three different directions, and utilizing the ultrasonic waves generated when the equipment is partially discharged, the position of the equipment partial discharge can be determined based on the propagation time and relative distance of the ultrasonic waves received by the three ultrasonic sensors. Secondly, since the ultrasonic wave is affected by external factors such as the medium and temperature during the propagation process, the transmission of the ultrasonic wave is attenuated and interfered, thereby extending the round-trip time of the ultrasonic wave transmission and increasing the distance between the ultrasonic sensor and the partial discharge position, resulting in a non-unique partial discharge position and generating a closed area. This solution calculates the three corner points of the closed area to determine the position of the equipment partial discharge area.

[0098] Reference Figure 3 As shown, the method based on the machine learning algorithm model to judge whether there is a risk of damage to the insulating material and to issue a risk warning specifically includes:

[0099] According to the monitoring data type of the equipment partial discharge, establish The input matrix and parameter term matrix;

[0100] according to The input matrix and Parameter item matrix, establish the linear regression equation of the damage degree of the insulation material;

[0101] According to the linear regression equation of the damage degree of the insulating material, the error relationship between the calculated value and the actual value is established;

[0102] Based on the likelihood function algorithm, a loss function of the damage degree of the insulation material is established;

[0103] Based on the mini-batch gradient descent algorithm, the parameter update equation of the monitoring data of the partial discharge of each device is established;

[0104] Import the data in the list of damage impacts of insulation materials, use the algorithm to perform iterative calculations, and establish a machine learning algorithm model based on linear regression. By inputting the corresponding equipment partial discharge monitoring data, determine whether there is a risk of insulation material damage and the degree of damage, and issue a risk warning;

[0105] Said The input matrix and The parameter matrix expression is:

[0106]

[0107] In the formula, For equipment partial discharge monitoring data The parameter matrix, is the error constant term, , , are the parameters of the amplitude, frequency and period of partial discharge generated by the equipment, For equipment partial discharge monitoring data The input matrix, is a constant term with a value of 1, , , They are the input values ​​of the amplitude, frequency and period of partial discharge generated by the equipment respectively;

[0108] The linear regression equation for the degree of damage of the insulating material is expressed as:

[0109]

[0110] In the formula, is the calculated value matrix of the damage degree of the insulation material, The error matrix between the calculated value and the actual value of the damage degree of the insulation material;

[0111] The error relationship between the calculated value and the actual value is:

[0112]

[0113] In the formula, The error between the calculated value and the actual value of the damage degree of the insulation material. is the actual value of the damage degree of the insulation material, where To obey Gaussian distribution, and ;

[0114] The loss function expression of the damage degree of the insulating material is:

[0115]

[0116] In the formula, The error loss deviation between the calculated value and the actual value of the damage degree of the insulation material, The number of sample groups for the damage degree of the insulation materials affecting the inventory;

[0117] The parameter update equation expression of the monitoring data of the partial discharge of each device is:

[0118]

[0119] In the formula, For the Update parameters of partial discharge monitoring data of each device in the group, For the Parameters of partial discharge monitoring data of each device in the group, is the learning rate, For the The first Group monitoring data.

[0120] It can be explained that mild partial discharge can still ensure the functionality of the insulating material. If field inspection and maintenance measures are taken every time partial discharge is detected, it will not only be time-consuming and labor-intensive, but also inefficient. However, each partial discharge may cause irreparable damage to the insulating material. If it is not monitored in time, it may cause the insulating material to completely lose its insulating properties in the long run, causing damage to electricity and equipment, and leading to power system failure. Therefore, this solution analyzes the impact of the amplitude, frequency, and period of partial discharge generated by the equipment on the degree of damage to the insulating material, and determines the degree of damage to the insulating material based on the machine learning algorithm model, so as to take corresponding treatment measures according to the received risk warning prompts, thereby improving the efficiency and convenience of equipment partial discharge monitoring. At the same time, it can monitor the long-term cumulative impact of equipment partial discharge and improve the stability and reliability of the power system.

[0121] Reference Figure 4 As shown, the determination result of the degree of damage of the insulating material and the location information of the partial discharge generated by the equipment are combined to set a corresponding partial discharge solution for the equipment, which specifically includes:

[0122] According to the damage degree of the insulation material, if it is judged to be low damage, a blue warning is issued, and it is necessary to strengthen the online monitoring and power distribution intensity of the area;

[0123] If it is judged to be moderately damaged, a yellow warning will be issued, requiring on-site testing of the partial discharge environment of the monitored equipment, and replacement and maintenance of the insulation materials will be carried out based on the actual test results;

[0124] If it is judged to be severely damaged, it means that the insulation material of the monitoring equipment will completely lose its insulation performance, and a red warning will be issued. It is necessary to test the performance of the regional equipment and completely replace the insulation material.

[0125] It can be explained that the degree of damage to the insulating material and the risk warning prompts can be effectively determined based on the machine learning algorithm model. By displaying the model judgment results and setting corresponding solutions, the problems of time-consuming and labor-intensive treatment of equipment partial discharge problems and inefficient response measures can be effectively solved. The partial discharge problems of equipment under different risk warning prompts can be solved in a targeted manner, and equipment maintenance and replacement can be systematically completed to improve processing efficiency.

[0126] Furthermore, based on the same inventive concept as the above-mentioned device partial discharge remote comprehensive monitoring method combined with a remote terminal, the present solution also proposes a device partial discharge remote comprehensive monitoring system combined with a remote terminal, comprising:

[0127] A data acquisition module, which is used to set corresponding monitoring equipment to correspond to the partial discharge environment to be monitored, and receive and record the monitoring data of the partial discharge of the equipment through a remote terminal;

[0128] A partial discharge positioning module, which is used to determine the specific location or regional location information of the device generating partial discharge based on the UWB positioning principle;

[0129] A risk warning module, which is used to formulate a risk warning level based on the degree of damage to the insulating material based on test experiments and big data analysis; based on a machine learning algorithm model, determine whether the insulating material has a risk of damage and issue a risk warning;

[0130] A monitoring and processing module, which is used to determine the results according to the degree of damage of the insulating material and set the corresponding partial discharge solution for the equipment in combination with the location information of the partial discharge generated by the equipment; establish a remote comprehensive monitoring platform for partial discharge of the equipment, intuitively display the monitoring data of partial discharge of the equipment through charts, and update and optimize the machine learning algorithm model through actual on-site detection results;

[0131] The risk warning module includes:

[0132] A warning level unit, which is used to formulate a risk warning level according to the degree of damage of the insulating material based on test experiments and big data analysis;

[0133] A risk warning unit, which is used to determine whether the insulating material has a risk of damage based on a machine learning algorithm model and issue a risk warning;

[0134] The monitoring and processing modules include:

[0135] A partial discharge processing unit, the partial discharge processing unit is used to set a corresponding device partial discharge solution according to the result of the judgment of the degree of damage of the insulating material and the location information of the partial discharge generated by the device;

[0136] The partial discharge monitoring unit is used to establish a remote comprehensive monitoring platform for partial discharge of equipment, intuitively display the monitoring data of partial discharge of equipment through charts, and update and optimize the machine learning algorithm model through actual on-site detection results.

[0137] To sum up, the advantages of the present invention are: determining the location information of the partial discharge of the equipment according to the UWB positioning algorithm, and analyzing the attenuation and interference of the transmission of ultrasonic waves due to the influence of external factors, thereby extending the round-trip time of ultrasonic transmission, increasing the distance between the ultrasonic sensor and the partial discharge position, resulting in a non-unique partial discharge position, and generating a closed area; secondly, analyzing the influence of the amplitude, frequency and period of the partial discharge of the equipment on the degree of damage to the insulating material through a machine learning algorithm model, judging the degree of damage to the insulating material according to the amplitude, frequency and period data of the partial discharge of the equipment received in real time, and taking corresponding treatment measures according to the degree of damage to the insulating material, thereby effectively identifying the location information of the partial discharge generated by the equipment and providing a risk warning level, simplifying the detection process of the partial discharge of the equipment, and improving the remote monitoring efficiency and emergency response capability of the partial discharge of the equipment.

[0138] The above shows and describes the basic principles, main features and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The above embodiments and descriptions only describe the principles of the present invention. The present invention may be subject to various changes and improvements without departing from the spirit and scope of the present invention. These changes and improvements fall within the scope of the present invention. The scope of protection claimed by the present invention is defined by the attached claims and their equivalents.

Claims

1. A remote comprehensive monitoring method for partial discharge of equipment combined with a remote terminal, characterized in that: include: According to the partial discharge environment to be monitored, corresponding monitoring equipment is set up to correspond to it, and the monitoring data of partial discharge of the equipment is received and recorded through the remote terminal; Based on the UWB positioning principle, determine the specific location or regional location information where the device generates partial discharge; Based on test experiments and big data analysis, risk warning levels are formulated according to the degree of damage to the insulation materials; Based on the machine learning algorithm model, determine whether the insulation material is at risk of damage and issue a risk warning; According to the damage degree of the insulation material, combined with the location information of the equipment generating partial discharge, set up the corresponding equipment partial discharge solution; Establish a remote comprehensive monitoring platform for equipment partial discharge, intuitively display the monitoring data of equipment partial discharge through charts, and update and optimize the machine learning algorithm model through actual on-site detection results.

2. According to claim 1, a method for remote comprehensive monitoring of partial discharge of equipment combined with a remote terminal is characterized in that: The method of setting corresponding monitoring equipment to correspond to the partial discharge environment to be monitored, and receiving and recording the monitoring data of the partial discharge of the equipment through the remote terminal specifically includes: According to the partial discharge environment to be monitored, corresponding monitoring equipment is set up to correspond to it, and is used to monitor the amplitude, frequency, period, location area and temperature data of the partial discharge generated by the equipment; Among them, amplitude refers to the intensity of partial discharge generated by the device, frequency refers to the number of times the device generates partial discharge per unit time, and period refers to the time period during which the device continuously generates partial discharge; The monitoring data of partial discharge of the equipment is received and recorded through the remote terminal, and the corresponding data channels are set up to display the monitoring data transmitted by the monitoring equipment in real time through different channels.

3. According to claim 2, a method for remote comprehensive monitoring of partial discharge of equipment combined with a remote terminal is characterized in that: The method of determining the location of the area where the device generates partial discharge based on the UWB positioning principle specifically includes: According to the partial discharge environment to be monitored, ultrasonic sensors are set at fixed positions in three directions and accurate position information is obtained; Based on the UWB positioning principle, a circle is drawn with the distance detected by the three ultrasonic sensors as the radius. The coordinates of the common intersection of the three circles are calculated to determine the specific location information where the device generates partial discharge. Optimize the UWB positioning algorithm, calculate the location area where the device generates partial discharge, and reduce the distance error caused by influencing factors; The expression based on the UWB positioning principle is: In the formula, is the propagation speed of ultrasonic waves from the ultrasonic sensor, which is a fixed value. is the total time for the ultrasonic sensor to travel back and forth. They are the fixed position information of the ultrasonic sensor in three directions. The coordinates of the common intersection of a circle with the distance detected by the three ultrasonic sensors as the radius are the actual position information of the device. The optimized UWB positioning algorithm expression is: In the formula, The coordinate information of the three intersection points of the central area is generated respectively, wherein the location area where the device generates partial discharge can be determined in a triangular form according to the coordinate information of the three intersection points.

4. According to claim 3, a method for remote comprehensive monitoring of partial discharge of equipment combined with a remote terminal is characterized in that: Based on the test experiments and big data analysis, the risk warning level is formulated according to the degree of damage to the insulation material: Based on the product description of the insulation material and big data analysis, the interval thresholds of each degree edge are set according to the degree of damage of the insulation material, where the degree of damage of the insulation material is divided into low, medium and severe; According to the degree of damage of the insulating material, combined with the data of partial discharge monitoring, test experiments are carried out through the control variable method to record the impact of different partial discharge monitoring data on the degree of damage of the insulating material; Based on the test results, a list of the impact of the degree of damage to the insulating materials is established, in which the amplitude, frequency and period of the partial discharge generated by the equipment are used as input items, and the degree of damage to the insulating materials is used as an output item.

5. According to claim 4, a method for remote comprehensive monitoring of partial discharge of equipment combined with a remote terminal is characterized in that: The machine learning algorithm model is used to determine whether the insulating material has a risk of damage and issue a risk warning; According to the monitoring data type of the equipment partial discharge, establish The input matrix and parameter term matrix; according to The input matrix and Parameter item matrix, establish the linear regression equation of the damage degree of the insulation material; According to the linear regression equation of the damage degree of the insulating material, the error relationship between the calculated value and the actual value is established; Based on the likelihood function algorithm, a loss function of the damage degree of the insulation material is established; Based on the mini-batch gradient descent algorithm, the parameter update equation of the monitoring data of the partial discharge of each device is established; Import the data in the list of damage impacts of insulation materials, use the algorithm to perform iterative calculations, and establish a machine learning algorithm model based on linear regression. By inputting the corresponding equipment partial discharge monitoring data, determine whether there is a risk of insulation material damage and the degree of damage, and issue a risk warning; Said The input matrix and The parameter matrix expression is: In the formula, For equipment partial discharge monitoring data The parameter matrix, is the error constant term, , , are the parameters of the amplitude, frequency and period of partial discharge generated by the equipment, For equipment partial discharge monitoring data The input matrix, is a constant term with a value of 1, , , They are the input values ​​of the amplitude, frequency and period of partial discharge generated by the equipment respectively; The linear regression equation for the degree of damage of the insulating material is expressed as: In the formula, is the calculated value matrix of the damage degree of the insulation material, The error matrix between the calculated value and the actual value of the damage degree of the insulation material; The error relationship between the calculated value and the actual value is: In the formula, The error between the calculated value and the actual value of the damage degree of the insulation material. is the actual value of the damage degree of the insulation material, where To obey Gaussian distribution, and ; The loss function expression of the damage degree of the insulating material is: In the formula, The error loss deviation between the calculated value and the actual value of the damage degree of the insulation material, The number of sample groups for the damage degree of the insulation materials affecting the inventory; The parameter update equation expression of the monitoring data of the partial discharge of each device is: In the formula, For the Update parameters of partial discharge monitoring data of each device in the group, For the Parameters of partial discharge monitoring data of each device in the group, is the learning rate, For the The first Group monitoring data.

6. A remote comprehensive monitoring method for partial discharge of equipment combined with a remote terminal according to claim 5, characterized in that: The determination result of the degree of damage of the insulating material and the location information of the partial discharge generated by the equipment to set a corresponding partial discharge solution for the equipment specifically include: According to the damage degree of the insulation material, if it is judged to be low damage, a blue warning is issued, and it is necessary to strengthen the online monitoring and power distribution intensity of the area; If it is judged to be moderately damaged, a yellow warning will be issued, requiring on-site testing of the partial discharge environment of the monitored equipment, and replacement and maintenance of the insulation materials will be carried out based on the actual test results; If it is judged to be severely damaged, it means that the insulation material of the monitoring equipment will completely lose its insulation performance, and a red warning will be issued. It is necessary to test the performance of the regional equipment and completely replace the insulation material.

7. A remote comprehensive monitoring method for partial discharge of equipment combined with a remote terminal according to claim 6, characterized in that: The establishment of a remote comprehensive monitoring platform for partial discharge of equipment, visually displaying the monitoring data of partial discharge of equipment through charts, and updating and optimizing the machine learning algorithm model through actual on-site detection results specifically include: Establish a remote comprehensive monitoring platform for partial discharge of equipment to receive and record the monitoring data of partial discharge of equipment that needs to be monitored, and display the partial discharge monitoring data of equipment in different areas through different channels; Establish a histogram of equipment partial discharge monitoring data, visually display the monitoring data and change trend of equipment partial discharge through charts, and display the degree of damage of insulation materials through color indicator lights; Based on the comparison model judgment results and actual on-site detection results, the machine learning algorithm model is updated and optimized.

8. A remote comprehensive monitoring system for partial discharge of equipment combined with a remote terminal, used to implement the remote comprehensive monitoring method for partial discharge of equipment combined with a remote terminal as described in any one of claims 1 to 7, characterized in that: include: A data acquisition module, which is used to set corresponding monitoring equipment to correspond to the partial discharge environment to be monitored, and receive and record the monitoring data of the partial discharge of the equipment through a remote terminal; A partial discharge positioning module, which is used to determine the specific location or regional location information of the device generating partial discharge based on the UWB positioning principle; A risk warning module, which is used to formulate a risk warning level according to the degree of damage to the insulation material based on test experiments and big data analysis; Based on the machine learning algorithm model, determine whether the insulation material is at risk of damage and issue a risk warning; The monitoring and processing module is used to judge the results according to the degree of damage of the insulating material, and set the corresponding equipment partial discharge solution in combination with the location information of the partial discharge generated by the equipment; establish a remote comprehensive monitoring platform for equipment partial discharge, intuitively display the monitoring data of equipment partial discharge through charts, and update and optimize the machine learning algorithm model through actual on-site detection results.

9. The remote comprehensive monitoring system for partial discharge of equipment combined with a remote terminal according to claim 8, characterized in that: The risk warning module specifically includes: A warning level unit, which is used to formulate a risk warning level according to the degree of damage of the insulating material based on test experiments and big data analysis; A risk warning unit is used to determine whether there is a risk of damage to the insulating material based on a machine learning algorithm model and to issue a risk warning.

10. The remote comprehensive monitoring system for partial discharge of equipment combined with a remote terminal according to claim 9, characterized in that: The monitoring and processing module specifically includes: A partial discharge processing unit, the partial discharge processing unit is used to set a corresponding device partial discharge solution according to the result of the judgment of the degree of damage of the insulating material and the location information of the partial discharge generated by the device; The partial discharge monitoring unit is used to establish a remote comprehensive monitoring platform for partial discharge of equipment, intuitively display the monitoring data of partial discharge of equipment through charts, and update and optimize the machine learning algorithm model through actual on-site detection results.

Images