Transformer partial discharge pattern recognition method and system based on multi-source data fusion

Abstract

The application discloses a transformer partial discharge mode recognition method and system based on multi-source data fusion, relates to the technical field of transformer maintenance, and comprises a recognition execution module, a multi-source data fusion module and a discharge recognition module. The recognition execution module is used for collecting ultrahigh frequency electromagnetic waves, ultrasonic waves and high-frequency pulse current partial discharge signals, and performing multi-dimensional detection in combination with gas content in oil. The multi-source data fusion module is used for performing unified time reference and intensity normalization processing on a detection period and a sampling resolution, dynamically adjusting two output parameter characteristics according to subsequent detection results, and performing multi-source data fusion processing. The discharge recognition module is used for comprehensively judging a partial discharge mode according to processed data. The recognition execution module comprises an UHF detection unit, an AE detection unit, an HFCT detection unit, a gas component detection unit and an ultrahigh frequency electromagnetic wave analysis module, and the application has the characteristic of unified modeling.

Description

Technical Field

[0001] This invention relates to the field of transformer maintenance technology, specifically to a method and system for identifying transformer partial discharge patterns based on multi-source data fusion. Background Technology

[0002] In addition to the electrical measurement method integrated into the transformer body, the partial discharge detection methods for transformers include the external sensor method, which includes ultra-high frequency electromagnetic wave (UHF) detection, ultrasonic (AE) detection, and high frequency pulse current (HFCT) detection. Combined with dissolved gas analysis for auxiliary judgment, these methods are used to detect common discharge types such as corona discharge, metal tip discharge, surface discharge, gap discharge, and oil discharge.

[0003] Existing technologies often employ a single discharge detection method to correspond to one or more discharge types. Relying on a single method is susceptible to noise interference, leading to a certain false positive rate. If data fusion is directly applied, the suitable detection period and sampling resolution vary greatly among different sensors when detecting different discharge modes. The lack of a unified acquisition and modeling architecture can easily cause data distortion during normalization. Forcibly unifying the time reference and intensity normalization will cause the detection period and sampling resolution to deviate from the requirements of normal acquisition. Therefore, it is essential to design a unified modeling method and system for transformer partial discharge pattern recognition based on multi-source data fusion. Summary of the Invention

[0004] The purpose of this invention is to provide a method and system for identifying transformer partial discharge patterns based on multi-source data fusion, so as to solve the problems mentioned in the background art.

[0005] To address the aforementioned technical problems, this invention provides the following technical solution: a transformer partial discharge pattern recognition system based on multi-source data fusion, comprising a recognition execution module, a multi-source data fusion module, and a discharge recognition module. The recognition execution module is used to acquire ultra-high frequency electromagnetic waves, ultrasonic waves, and high-frequency pulse current partial discharge signals, and to perform multi-dimensional detection in conjunction with the gas content in the oil. The multi-source data fusion module is used to perform unified time reference and intensity normalization processing on the detection cycle and sampling resolution, dynamically adjust the characteristics of the two output parameters based on subsequent detection results, and perform multi-source data fusion processing. The discharge recognition module is used to comprehensively determine the partial discharge mode based on the processed data.

[0006] According to the above technical solution, the identification execution module includes a UHF detection unit, an AE detection unit, an HFCT detection unit, a gas composition detection unit, an ultra-high frequency electromagnetic wave analysis module, an ultrasonic wave analysis module, a high-frequency pulse current analysis module, and a gas composition analysis module. The UHF detection unit is electrically connected to the ultra-high frequency electromagnetic wave analysis module, the AE detection unit is electrically connected to the ultrasonic wave analysis module, the HFCT detection unit is electrically connected to the high-frequency pulse current analysis module, and the gas composition detection unit is electrically connected to the gas composition analysis module. The UHF detection unit, AE detection unit, and HFCT detection unit are respectively used to acquire ultra-high frequency electromagnetic wave, ultrasonic wave, and high-frequency pulse current partial discharge signals. The gas composition detection unit is used to detect the gas composition precipitated in the insulating oil. The ultra-high frequency electromagnetic wave analysis module, ultrasonic wave analysis module, and high-frequency pulse current analysis module are respectively used to analyze the partial discharge signal, and the gas composition analysis module is used to analyze the composition of various gases.

[0007] The multi-source data fusion module includes a detection cycle adjustment module, a sampling resolution adjustment module, a data alignment processing module, a discharge type correspondence module, and a timing module. The detection cycle adjustment module and the sampling resolution adjustment module are both electrically connected to the UHF detection unit, the AE detection unit, and the HFCT detection unit. The data alignment processing module and the discharge type correspondence module are both electrically connected to the UHF detection unit, the AE detection unit, and the HFCT detection unit. The timing module is used to count the duration after a certain discharge form occurs. The detection cycle adjustment module and the sampling resolution adjustment module are used to adjust the detection cycle and sampling resolution of each detection unit, respectively. The data alignment processing module is used to normalize the sampling cycle and sampling resolution of each detection unit.

[0008] The discharge identification module includes a gas-assisted judgment module and a discharge mode judgment module. The timing module is electrically connected to the data alignment processing module. The gas-assisted judgment module is electrically connected to the discharge mode judgment module. The gas-assisted judgment module is used to analyze the changes in the gas composition of the transformer insulating oil to assist in the judgment of the discharge mode. The discharge mode judgment module is used to determine the discharge mode with the highest probability.

[0009] A transformer partial discharge pattern recognition method based on multi-source data fusion includes the following steps:

[0010] S0. Place UHF detection units on the oil valves and inspection holes on the side wall of the main oil tank of the transformer, place AE detection units in the middle section of the tank wall near the high voltage bushing lead-out side and the winding, install HFCT detection units on the grounding circuit, and install gas composition detection units on the inner wall of the main oil tank of the transformer to determine which detection method corresponds to each discharge mode.

[0011] S1. Each detection unit works and detects partial discharge signals. Each detection unit outputs detection results with the initial detection cycle and sampling resolution, and detects whether a partial discharge phenomenon has occurred through the corresponding analysis module.

[0012] S2. When a detection unit detects a certain form of discharge, the detection period and sampling resolution of other detection units that are closest to the current detection unit are adjusted so that the detection units that need to be adjusted are consistent with the current detection unit in terms of detection period and sampling resolution.

[0013] S3. As time goes on, the detection cycle and sampling resolution of the detection unit that needs to be adjusted are dynamically adjusted based on whether the same partial discharge signal continues to be detected.

[0014] S4. When the detection cycle and sampling resolution of each detection unit are not uniform, the data alignment processing module is used to process the detection data and normalize the detection cycle and sampling resolution.

[0015] S5. Based on the analysis results of the gas composition released from the transformer oil, the mode of partial discharge is determined.

[0016] According to the above technical solution, in S0, it is specified that each discharge mode corresponds to a specific detection method as follows:

[0017] S0-1. Gap discharge generates high-frequency electromagnetic pulses, local breakdown leading to acoustic emission, and pulse charges. These can be detected by UHF, AE, and HFCT. UHF has the highest sensitivity and is used as the primary judgment method, while AE and HFCT are used as auxiliary judgment methods.

[0018] S0-2, metal tip discharge and corona discharge all generate high-frequency electromagnetic radiation and pulse current signals, which can be effectively detected by UHF and HFCT. HFCT is the primary judgment method and UHF is the auxiliary judgment method.

[0019] S0-3. When surface discharge develops along the surface of the insulating surface, it will generate mechanical shock waves and pulse currents, which can be detected by AE and HFCT. UHF can also capture it when it is strong. AE is used as the main judgment method, and HFCT and UHF are used as auxiliary judgment methods.

[0020] S0-4. Discharge in oil will produce obvious bubble oscillation and sound wave impact. AE is more sensitive and is used as the primary judgment method, while UHF is used as an auxiliary judgment method.

[0021] According to the above technical solution, the unification of detection period and sampling resolution in S2 specifically involves:

[0022] S2-1. Each detection unit defaults to detecting the discharge mode corresponding to its dominant judgment method, and uses its default detection cycle. and sampling resolution Output the detection results, where The number of detection units is such that when a certain detection unit detects a partial discharge signal of a certain mode that it dominates the judgment of, it is necessary to adjust the detection unit corresponding to this mode of partial discharge signal as an auxiliary judgment method.

[0023] S2-2, Order No. Each detection unit detected a partial discharge signal, and its default detection period was [missing information]. The default sampling resolution is The initial probability of this type of partial discharge signal occurring is: At this point, it is necessary to... The detection cycle and sampling resolution of each detection unit were adjusted. The default detection cycle and sampling resolution before the adjustment were as follows: and This leads to its adjusted detection cycle. Adjusted sampling resolution , making the first The and the first Each detection unit has its detection cycle and sampling resolution adjusted to be consistent.

[0024] According to the above technical solution, the dynamic adjustment in S3 specifically includes:

[0025] S3-1, Order No. Each detection unit maintains the detection cycle. and sampling resolution continued During the time period, if Within the time period When the detection unit detects the same partial discharge signal pattern again, observe the first... If each detection unit simultaneously detects a partial discharge signal of the same mode, and if so, increases the probability of this mode of partial discharge signal occurring, with the adjusted probability being... ,in For the first When the first detection unit is used as an auxiliary judgment method, it is related to the first... The probability increment brought about by the detection unit detecting the same mode of partial discharge signal, if the first detection unit detects the same mode of partial discharge signal, If none of the detection units simultaneously detect partial discharge signals of the same mode, then... ;

[0026] S3-2, If in Within the time period When the first detection unit does not detect a partial discharge signal of the same pattern, the second detection unit... The detection cycle and sampling resolution of each detection unit are determined by and To its initial value and Gradually recovering, making the current distance The elapsed time of the end of the time period is Then the detection cycle at this time and sampling resolution The calculation formulas are as follows: when hour, ,when hour, ,when hour, ,when hour, ,in , For time conversion factors, until and Adjust to and No further adjustments will be made.

[0027] According to the above technical solution, in step S4, the normalization processing of the detection period and sampling resolution specifically involves:

[0028] S4-1, Firstly in When the time period ends, the first The and the first The first sampling time of each detection unit is aligned, at which point both detection units sample simultaneously. The next sampling only collects samples that meet the following criteria. and The detection data is collected only at the least common multiple of the time; other data are not collected.

[0029] S4-2, the first The and the first The maximum and minimum values ​​of the detection data of each detection unit are mapped to... Within the range, the dimensional differences in sampling resolution between different detection units are eliminated, so that the output signals of the two can be compared and fused at a unified scale.

[0030] According to the above technical solution, in step S5, the determination of the partial discharge mode specifically involves: setting the content of various gases detected by the gas composition detection unit before each detection of a partial discharge phenomenon to be as follows: ,in This refers to the number and types of gases involved in partial discharge. When a certain mode of partial discharge is detected, if this discharge mode leads to... Changes have occurred, and Actual detection The probability of this partial discharge mode occurring is increased by an incremental change. ,in This is the gas increment influence coefficient; if no gas increment is detected... Incremental changes occur Combined with S3-1 The final probability is calculated when hour, The probability threshold is used to determine if this discharge mode is valid, and maintenance is required.

[0031] Compared with existing technologies, the beneficial effects achieved by this invention are as follows: This invention collects ultra-high frequency electromagnetic waves, ultrasonic waves, and high frequency pulse current partial discharge signals, and combines them with the gas content in oil for multi-dimensional detection. It also introduces an attention mechanism. When a certain detection method detects a partial discharge signal, it adjusts the detection cycle and sampling resolution of other corresponding detection methods, performs unified time reference and intensity normalization processing, and dynamically adjusts the characteristics of the two output parameters based on subsequent detection results. This allows the detection cycle and sampling resolution to be optimized within a suitable time period without affecting the normal acquisition work of various detection methods as much as possible. The combination of multiple detection methods can effectively reduce the false judgment rate. Attached Figure Description

[0032] The accompanying drawings are provided to further illustrate the invention and form part of the specification. They are used in conjunction with embodiments of the invention to explain the invention and do not constitute a limitation thereof. In the drawings:

[0033] Figure 1 This is a schematic diagram of the overall modular structure of the present invention. Detailed Implementation

[0034] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0035] Please see Figure 1The present invention provides a technical solution: a transformer partial discharge pattern recognition system based on multi-source data fusion, including a recognition execution module, a multi-source data fusion module, and a discharge recognition module. The recognition execution module is used to collect ultra-high frequency electromagnetic waves, ultrasonic waves, and high frequency pulse current partial discharge signals, and to perform multi-dimensional detection in combination with the gas content in the oil. The multi-source data fusion module is used to perform unified time reference and intensity normalization processing on the detection cycle and sampling resolution, dynamically adjust the characteristics of the two output parameters according to the subsequent detection results, and perform multi-source data fusion processing. The discharge recognition module is used to comprehensively determine the partial discharge mode based on the processed data.

[0036] The three discharge modes have overlapping areas. The discharge mode matching each detection unit is determined based on the detection sensitivity and accuracy obtained from a large number of experiments.

[0037] The identification and execution module includes a UHF detection unit, an AE detection unit, an HFCT detection unit, a gas composition detection unit, an ultra-high frequency electromagnetic wave analysis module, an ultrasonic analysis module, a high-frequency pulse current analysis module, and a gas composition analysis module. The UHF detection unit is electrically connected to the ultra-high frequency electromagnetic wave analysis module, the AE detection unit is electrically connected to the ultrasonic analysis module, the HFCT detection unit is electrically connected to the high-frequency pulse current analysis module, and the gas composition detection unit is electrically connected to the gas composition analysis module. The UHF detection unit, AE detection unit, and HFCT detection unit are used to acquire ultra-high frequency electromagnetic wave, ultrasonic wave, and high-frequency pulse current partial discharge signals, respectively. The gas composition detection unit is used to detect the gas composition released from the insulating oil. The ultra-high frequency electromagnetic wave analysis module, ultrasonic wave analysis module, and high-frequency pulse current analysis module are used to analyze the partial discharge signal, respectively. The gas composition analysis module is used to analyze the composition of various gases.

[0038] The multi-source data fusion module includes a detection cycle adjustment module, a sampling resolution adjustment module, a data alignment processing module, a discharge type correspondence module, and a timing module. The detection cycle adjustment module and the sampling resolution adjustment module are both electrically connected to the UHF detection unit, the AE detection unit, and the HFCT detection unit. The data alignment processing module and the discharge type correspondence module are both electrically connected to the UHF detection unit, the AE detection unit, and the HFCT detection unit. The timing module is used to count the duration after a certain discharge form occurs. The detection cycle adjustment module and the sampling resolution adjustment module are used to adjust the detection cycle and sampling resolution of each detection unit, respectively. The data alignment processing module is used to normalize the sampling cycle and sampling resolution of each detection unit.

[0039] The discharge identification module includes a gas-assisted judgment module and a discharge mode judgment module. The timing module and the data alignment processing module are electrically connected. The gas-assisted judgment module and the discharge mode judgment module are electrically connected. The gas-assisted judgment module is used to analyze the changes in the gas composition of the transformer insulating oil to assist in the judgment of the discharge mode. The discharge mode judgment module is used to determine the discharge mode with the highest probability.

[0040] A transformer partial discharge pattern recognition method based on multi-source data fusion includes the following steps:

[0041] S0. Place UHF detection units on the oil valves and inspection holes on the side wall of the main oil tank of the transformer, place AE detection units in the middle section of the tank wall near the high voltage bushing lead-out side and the winding, install HFCT detection units on the grounding circuit, and install gas composition detection units on the inner wall of the main oil tank of the transformer to determine which detection method corresponds to each discharge mode.

[0042] S1. Each detection unit works and detects partial discharge signals. Each detection unit outputs detection results with the initial detection cycle and sampling resolution, and detects whether a partial discharge phenomenon has occurred through the corresponding analysis module.

[0043] S2. When a detection unit detects a certain form of discharge, the detection period and sampling resolution of other detection units that are closest to the current detection unit are adjusted so that the detection units that need to be adjusted are consistent with the current detection unit in terms of detection period and sampling resolution.

[0044] S3. As time goes on, the detection cycle and sampling resolution of the detection unit that needs to be adjusted are dynamically adjusted based on whether the same partial discharge signal continues to be detected.

[0045] S4. When the detection cycle and sampling resolution of each detection unit are not uniform, the data alignment processing module is used to process the detection data and normalize the detection cycle and sampling resolution.

[0046] S5. Based on the analysis results of the gas composition released from the transformer oil, determine the mode of partial discharge;

[0047] In S0, it is clearly stated which detection method corresponds to each discharge mode:

[0048] S0-1. Gap discharge generates high-frequency electromagnetic pulses, local breakdown leading to acoustic emission, and pulse charges. These can be detected by UHF, AE, and HFCT. UHF has the highest sensitivity and is used as the primary judgment method, while AE and HFCT are used as auxiliary judgment methods.

[0049] S0-2, metal tip discharge and corona discharge all generate high-frequency electromagnetic radiation and pulse current signals, which can be effectively detected by UHF and HFCT. HFCT is the primary judgment method and UHF is the auxiliary judgment method.

[0050] S0-3. When surface discharge develops along the surface of the insulating surface, it will generate mechanical shock waves and pulse currents, which can be detected by AE and HFCT. UHF can also capture it when it is strong. AE is used as the main judgment method, and HFCT and UHF are used as auxiliary judgment methods.

[0051] S0-4. Discharge in oil will produce obvious bubble oscillation and sound wave impact. AE is more sensitive and is used as the primary judgment method, while UHF is used as an auxiliary judgment method.

[0052] In S2, the unification of detection period and sampling resolution is specifically as follows:

[0053] S2-1. Each detection unit defaults to detecting the discharge mode corresponding to its dominant judgment method, and uses its default detection cycle. and sampling resolution Output the detection results, where The number of detection units is such that when a certain detection unit detects a partial discharge signal of a certain mode that it dominates the judgment of, it is necessary to adjust the detection unit corresponding to this mode of partial discharge signal as an auxiliary judgment method.

[0054] S2-2, Order No. Each detection unit detected a partial discharge signal, and its default detection period was [missing information]. The default sampling resolution is The initial probability of this type of partial discharge signal occurring is: At this point, it is necessary to... The detection cycle and sampling resolution of each detection unit were adjusted. The default detection cycle and sampling resolution before the adjustment were as follows: and This leads to its adjusted detection cycle. Adjusted sampling resolution , making the first The and the first Each detection unit has its detection cycle and sampling resolution adjusted to be consistent;

[0055] In S3, the dynamic adjustment is specifically as follows:

[0056] S3-1, Order No. Each detection unit maintains the detection cycle. and sampling resolution continued During the time period, if Within the time period When the detection unit detects the same partial discharge signal pattern again, observe the first... If each detection unit simultaneously detects a partial discharge signal of the same mode, and if so, increases the probability of this mode of partial discharge signal occurring, with the adjusted probability being... ,in For the first When the first detection unit is used as an auxiliary judgment method, it is related to the first... The probability increment brought about by the detection unit detecting the same mode of partial discharge signal, if the first detection unit detects the same mode of partial discharge signal, If none of the detection units simultaneously detect partial discharge signals of the same mode, then... ;

[0057] S3-2, If in Within the time period When the first detection unit does not detect a partial discharge signal of the same pattern, the second detection unit... The detection cycle and sampling resolution of each detection unit are determined by and To its initial value and Gradually recovering, making the current distance The elapsed time of the end of the time period is Then the detection cycle at this time and sampling resolution The calculation formulas are as follows: when hour, ,when hour, ,when hour, ,when hour, ,in , For time conversion factors, until and Adjust to and No further adjustments will be made.

[0058] In S4, the normalization of the detection period and sampling resolution is performed as follows:

[0059] S4-1, Firstly in When the time period ends, the first The and the first The first sampling time of each detection unit is aligned, at which point both detection units sample simultaneously. The next sampling only collects samples that meet the following criteria. and The detection data is collected only at the least common multiple of the time; other data are not collected.

[0060] S4-2, the first The and the first The maximum and minimum values ​​of the detection data of each detection unit are mapped to... Within the range, the dimensional differences in sampling resolution between different detection units are eliminated, so that the output signals of the two can be compared and fused at a unified scale;

[0061] In S5, the determination of the partial discharge mode is specifically as follows: before each detection unit detects a partial discharge phenomenon, the contents of various gases detected by the gas composition detection unit are respectively... ,in This refers to the number and types of gases involved in partial discharge. When a certain mode of partial discharge is detected, if this discharge mode leads to... Changes have occurred, and Actual detection The probability of this partial discharge mode occurring is increased by an incremental change. ,in This is the gas increment influence coefficient; if no gas increment is detected... Incremental changes occur Combined with S3-1 The final probability is calculated when hour, The probability threshold is used to determine if this discharge mode is valid, and maintenance is required.

[0062] This invention collects ultra-high frequency electromagnetic waves, ultrasonic waves, and high-frequency pulsed current partial discharge signals, combined with the gas content in oil for multi-dimensional detection. It also introduces an attention mechanism: when a certain detection method detects a partial discharge signal, it adjusts the detection cycle and sampling resolution of other corresponding detection methods, performs unified time reference and intensity normalization processing, and dynamically adjusts the characteristics of the two output parameters based on subsequent detection results. This allows the detection cycle and sampling resolution to be optimized within a suitable time period without affecting the normal acquisition work of various detection methods as much as possible. The combination of multiple detection methods can effectively reduce the false judgment rate.

[0063] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus.

[0064] Finally, it should be noted that the above descriptions are merely preferred embodiments of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments or make equivalent substitutions for some of the technical features. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A transformer partial discharge pattern recognition method based on multi-source data fusion, characterized in that: Includes the following steps: S0. Place UHF detection units on the oil valves and inspection holes on the side wall of the main oil tank of the transformer; place AE detection units on the middle section of the tank wall near the high voltage bushing lead-out side and the tank wall at the same height as the winding; install HFCT detection units on the grounding circuit; and install gas composition detection units on the inner wall of the main oil tank of the transformer. S1. Each detection unit works and detects partial discharge signals. Each detection unit outputs detection results with the initial detection cycle and sampling resolution, and detects whether a partial discharge phenomenon has occurred through the corresponding analysis module. S2. When a detection unit detects a certain form of discharge, the detection period and sampling resolution of other detection units that are closest to the current detection unit are adjusted so that the detection units that need to be adjusted are consistent with the current detection unit in terms of detection period and sampling resolution. S3. As time goes on, the detection cycle and sampling resolution of the detection unit that needs to be adjusted are dynamically adjusted based on whether the same partial discharge signal continues to be detected. In step S3, the dynamic adjustment includes: if a detection unit detects a partial discharge signal of the same pattern again within a preset time period, and if other types of detection units simultaneously detect a partial discharge signal of the same pattern, then the probability of this type of partial discharge signal occurring is increased; otherwise, the probability of this type of partial discharge signal occurring is decreased. If a detection unit does not detect a partial discharge signal of the same pattern within the preset time period, then the detection period and sampling resolution of the other types of detection units are gradually restored to their initial values. S4. When the detection cycle and sampling resolution of each detection unit are not uniform, the data alignment processing module is used to process the detection data and normalize the detection cycle and sampling resolution. S5. Based on the analysis results of the gas composition released from the transformer oil, determine the mode of partial discharge; In step S5, determining the mode of partial discharge includes: when an incremental change in the gas content corresponding to a certain discharge mode is detected, the probability of this partial discharge mode occurring is increased; otherwise, the probability of this partial discharge mode occurring is decreased. The final probability is calculated in combination with the probability change in step S3. If the final probability is not less than the probability judgment threshold, the discharge mode is determined to be valid and maintenance is required.

2. The transformer partial discharge pattern recognition method based on multi-source data fusion according to claim 1, characterized in that: In S0, it is specified which detection method corresponds to each discharge mode: S0-1 and UHF gap discharge are used as the primary judgment methods, while AE and HFCT are used as auxiliary judgment methods. S0-2, metal tip discharge and corona discharge HFCT are the primary judgment methods, and UHF is the auxiliary judgment method; S0-3 and surface discharge AE are used as the primary judgment methods, while HFCT and UHF are used as auxiliary judgment methods. S0-4 and oil discharge AE are used as the primary judgment method, and UHF is used as the auxiliary judgment method.

3. The transformer partial discharge pattern recognition method based on multi-source data fusion according to claim 2, characterized in that: In step S2, the unification of detection period and sampling resolution specifically involves: S2-1. Each detection unit defaults to detecting the discharge mode corresponding to its dominant judgment method, and uses its default detection cycle. and sampling resolution Output the detection results, where The number of detection units; S2-2, Order No. Each detection unit detected a partial discharge signal, and its default detection period was [missing information]. The default sampling resolution is The initial probability of this type of partial discharge signal occurring is: At this point, it is necessary to... The detection cycle and sampling resolution of each detection unit were adjusted. The default detection cycle and sampling resolution before the adjustment were as follows: and This leads to its adjusted detection cycle. Adjusted sampling resolution .

4. The transformer partial discharge pattern recognition method based on multi-source data fusion according to claim 3, characterized in that: In S3, the dynamic adjustment specifically refers to: S3-1, Order No. Each detection unit maintains the detection cycle. and sampling resolution continued During the time period, if Within the time period When the detection unit detects the same partial discharge signal pattern again, observe the first... If each detection unit simultaneously detects a partial discharge signal of the same mode, and if so, increases the probability of this mode of partial discharge signal occurring, with the adjusted probability being... ,in For the first When the first detection unit is used as an auxiliary judgment method, it is related to the first... The probability increment brought about by the detection unit detecting the same mode of partial discharge signal, if the first detection unit detects the same mode of partial discharge signal, If none of the detection units simultaneously detect partial discharge signals of the same mode, then... ; S3-2, If in Within the time period When the first detection unit does not detect a partial discharge signal of the same pattern, the second detection unit... The detection cycle and sampling resolution of each detection unit are determined by and To its initial value and Gradually recovering, making the current distance The elapsed time at the end of the time period is Then the detection cycle at this time and sampling resolution The calculation formulas are as follows: when hour, ,when hour, ,when hour, ,when hour, ,in , This is the time conversion factor.

5. The transformer partial discharge pattern recognition method based on multi-source data fusion according to claim 4, characterized in that: In step S4, the normalization process for the detection period and sampling resolution is specifically performed as follows: S4-1, Firstly in When the time period ends, the first The and the first The first sampling time of each detection unit is aligned, at which point both detection units sample simultaneously. The next sampling only collects samples that meet the following criteria. and The detection data is collected only at the least common multiple of the time; other data are not collected. S4-2, the first The and the first The maximum and minimum values ​​of the detection data of each detection unit are mapped to... Within the specified range, the dimensional differences in sampling resolution between different detection units are eliminated.

6. The transformer partial discharge pattern recognition method based on multi-source data fusion according to claim 5, characterized in that: In step S5, the determination of the partial discharge mode specifically involves: setting the content of various gases detected by the gas composition detection unit to be as follows before each detection unit detects a partial discharge phenomenon: ,in This refers to the number and types of gases involved in partial discharge. When a certain mode of partial discharge is detected, if this discharge mode leads to... Changes have occurred, and Actual detection The probability of this partial discharge mode occurring is increased by an incremental change. ,in This is the gas increment influence coefficient; if no gas increment is detected... Incremental changes occur Combined with S3-1 The final probability is calculated when hour, The probability threshold is used to determine if this discharge mode is valid, and maintenance is required.

7. A transformer partial discharge pattern recognition system based on the transformer partial discharge pattern recognition method based on multi-source data fusion according to any one of claims 1-6, characterized in that: The system includes an identification and execution module, a multi-source data fusion module, and a discharge identification module. The identification and execution module is used to collect ultra-high frequency electromagnetic waves, ultrasonic waves, and high frequency pulse current partial discharge signals, and perform multi-dimensional detection in combination with the gas content in the oil. The multi-source data fusion module is used to unify the time reference and intensity normalization of the detection cycle and sampling resolution, dynamically adjust the characteristics of the two output parameters according to the subsequent detection results, and perform multi-source data fusion processing. The discharge identification module is used to comprehensively determine the partial discharge mode based on the processed data. The identification execution module includes a UHF detection unit, an AE detection unit, an HFCT detection unit, a gas composition detection unit, an ultra-high frequency electromagnetic wave analysis module, an ultrasonic wave analysis module, a high-frequency pulse current analysis module, and a gas composition analysis module. The UHF detection unit, AE detection unit, and HFCT detection unit are respectively used to acquire ultra-high frequency electromagnetic waves, ultrasonic waves, and high-frequency pulse current partial discharge signals. The gas composition detection unit is used to detect the gas composition released from the insulating oil. The ultra-high frequency electromagnetic wave analysis module, ultrasonic wave analysis module, and high-frequency pulse current analysis module are respectively used to analyze the partial discharge signal. The gas composition analysis module is used to analyze the composition of various gases. The multi-source data fusion module includes a detection cycle adjustment module, a sampling resolution adjustment module, a data alignment processing module, a discharge type correspondence module, and a timing module. The timing module is used to count the duration after a certain discharge form occurs. The detection cycle adjustment module and the sampling resolution adjustment module are used to adjust the detection cycle and sampling resolution of each detection unit, respectively. The data alignment processing module is used to normalize the detection cycle and sampling resolution of each detection unit. The discharge identification module includes a gas-assisted judgment module and a discharge mode judgment module. The gas-assisted judgment module is used to analyze the changes in the gas composition released from the transformer insulating oil to assist in the judgment of the discharge mode. The discharge mode judgment module is used to determine the discharge mode with the highest probability.

Images