Partial discharge detection method, device and equipment for power equipment
By dividing partial discharge signals into time-series groups and adjusting the threshold using a training model, the problem of existing technologies being unable to adapt to different devices and cope with interference changes is solved, thus achieving accuracy and adaptability in partial discharge detection of power equipment.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-12-29
- Publication Date
- 2026-04-03
AI Technical Summary
Existing partial discharge detection methods cannot adapt to the differences in discharge characteristics of different devices, nor can they cope with the dynamic changes in field interference, resulting in inaccurate detection results.
The partial discharge signal to be detected is divided into multiple time series according to the received time sequence. The threshold is adjusted by determining the model through pre-trained threshold. The filtering parameters are dynamically adjusted by combining the dependence and transmission relationship between the time series signals to perform noise reduction and analysis.
It achieves accurate partial discharge detection results for different power equipment, can adapt to complex on-site interference environments, and provides a stable detection basis.
Smart Images
Figure CN121784478A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of partial discharge detection technology, and in particular to a method, apparatus and equipment for detecting partial discharge in power equipment. Background Technology
[0002] Partial discharge is an early sign of insulation degradation in high-voltage power equipment, such as transformers. If not detected in time, it will gradually worsen the insulation damage, eventually leading to major accidents such as equipment breakdown and power outages. Therefore, detecting early fault signals through partial discharge detection is of crucial significance for ensuring the safe and stable operation of the power grid.
[0003] Currently, mainstream partial discharge detection methods include pulsed current method, ultrasonic method, and very high frequency (VHF) radio frequency detection method. Among them, VHF band detection has become an important means of online monitoring because it can capture the high-frequency characteristic signals of internal discharge in equipment. However, the electromagnetic environment in industrial sites is complex, and signals in this band are susceptible to multiple interferences: broadband radiation generated by frequency converters and radio frequency equipment, baseline drift caused by geomagnetic field fluctuations, and noise in the measurement system's own circuitry can all mask weak discharge signals.
[0004] Existing anti-interference methods have significant limitations. When filtering, fixed parameters are used, the filtering mode is rigid and it is difficult to adapt to different equipment, such as the difference in discharge characteristics between oil-paper insulated transformers and gas-insulated switchgear (GIS). They also cannot cope with the dynamic changes of field interference. Summary of the Invention
[0005] This invention provides a method, apparatus, and device for detecting partial discharge in power equipment, which solves the problem that the parameters used in current partial discharge detection are filtered and cannot be adapted to different equipment, and cannot cope with the dynamic changes of field interference.
[0006] In a first aspect, embodiments of the present invention provide a method for detecting partial discharge in power equipment, comprising: Receive the partial discharge signal to be detected from the target power equipment; The partial discharge signal to be detected is divided into multiple timing groups according to the receiving timing sequence; For any signal in a time series group, noise reduction is performed using the current threshold to obtain the reconstructed signal of that group; the reconstructed signal of that group is then input into a pre-trained threshold determination model to obtain a new threshold, and this new threshold is used as the threshold of the next time series group after that time series group, until the reconstructed signals corresponding to all time series groups are obtained; The reconstructed signal is analyzed to obtain the partial discharge detection results of the target power equipment.
[0007] In one possible implementation, the partial discharge signal to be detected includes a first partial discharge signal to be detected and a second partial discharge signal to be detected; the reconstructed signal includes a first reconstructed signal and a second reconstructed signal; the reconstructed signal is analyzed to obtain the partial discharge detection result of the target power equipment, including: The time-domain features of the first reconstructed signal and the second reconstructed signal are extracted respectively; Based on the time-domain characteristics of the first and second reconstructed signals, the partial discharge detection results of the target power equipment are obtained.
[0008] In one possible implementation, the partial discharge detection result of the target power equipment is obtained based on the time-domain characteristics of the first reconstructed signal and the second reconstructed signal, including: Based on the time-domain characteristics of the first reconstructed signal and the second reconstructed signal, the arrival times of the corresponding signals are determined respectively. Calculate the signal arrival time difference based on the arrival times of the first and second reconstructed signals; If the signal arrival time difference is greater than the preset arrival time, it is determined that the partial discharge of the target power equipment is caused by external interference. If the signal arrival time difference is less than or equal to the preset arrival time, then the partial discharge of the target power equipment is determined to be caused by an internal fault.
[0009] In one possible implementation, after analyzing the reconstructed signal to obtain the partial discharge detection result of the target power equipment, the method further includes: The coordinates of the interference source are reconstructed based on the signal arrival time difference and a preset algorithm.
[0010] In one possible implementation, after analyzing the reconstructed signal to obtain the partial discharge detection result of the target power equipment, the method further includes: The minimum signal arrival time difference is calculated when there is external interference within the preset number of detections, and the maximum signal arrival time difference is calculated when there is an internal fault. The minimum and maximum signal arrival time differences are averaged, and the result is used as the preset arrival time.
[0011] In one possible implementation, after obtaining the reconstructed signals corresponding to all time series groups, the method further includes: Generate a spectrogram based on the reconstructed signal; Based on the spectrum, identify the discharge type and determine the threshold adjustment coefficient according to the discharge type; Based on the threshold adjustment coefficient, the current threshold is adjusted, and the steps for denoising the signal in any time series group using the current threshold are returned to obtain the reconstructed signal of that group.
[0012] In one possible implementation, before receiving the partial discharge signal to be detected from the target electrical device, the method includes: Acquire initial partial discharge signals from the target power equipment; The initial partial discharge signal is filtered to obtain the partial discharge signal to be detected; Calculate the standing wave ratio (SWR) based on the partial discharge signal to be detected, and adjust the network parameters of the transmission link according to the SWR. The partial discharge signal to be detected is transmitted through the adjusted transmission link.
[0013] In one possible implementation, the initial partial discharge signal is filtered to obtain the partial discharge signal to be detected, including: The initial partial discharge signal is filtered sequentially through a three-stage filter to obtain the partial discharge signal to be detected. The three-stage filter includes a first-stage bandpass filter, a second-stage low-pass filter, and a third-stage adaptive notch filter.
[0014] Secondly, embodiments of the present invention provide a partial discharge detection device for power equipment, comprising: The receiving module is used to receive the partial discharge signal to be detected from the target power equipment; The segmentation module is used to divide the partial discharge signal to be detected into multiple timing groups according to the receiving timing sequence; The noise reduction module is used to reduce the noise of the signal in any time series group by the current threshold to obtain the reconstructed signal of the group; the reconstructed signal of the group is input into the pre-trained threshold determination model to obtain a new threshold, and the new threshold is used as the threshold of the next time series group after the current time series group, until the reconstructed signals corresponding to all time series groups are obtained; The identification module is used to analyze the reconstructed signal to obtain the partial discharge detection results of the target power equipment.
[0015] Thirdly, embodiments of the present invention provide an electronic device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the method described in the first aspect or any possible implementation thereof.
[0016] Current methods use fixed parameters for filtering, which cannot adapt to different devices and cannot cope with dynamic changes in field interference. To address this issue, this invention considers the dependencies and transmission relationships between time-series signals during the filtering process. Therefore, this invention divides the partial discharge signal to be detected into multiple time-series groups according to the received timing. Based on the noise reduction result of the current time-series group, the noise reduction parameters for the next time-series group, i.e., the current parameters, are determined. In this way, the filtering method can be adapted to different power equipment and can cope with dynamic changes in field interference, providing an accurate data foundation for the partial discharge detection of power equipment. Attached Figure Description
[0017] Figure 1 This is a flowchart illustrating the implementation of the partial discharge detection method for power equipment provided in this embodiment of the invention. Figure 2 This is a schematic diagram of the partial discharge detection device for power equipment provided in an embodiment of the present invention; Figure 3 This is a schematic diagram of an electronic device provided in an embodiment of the present invention. Detailed Implementation
[0018] The embodiments of the present invention will now be described in detail with reference to the accompanying drawings.
[0019] Figure 1 This is a flowchart illustrating the implementation of the partial discharge detection method for power equipment provided in this embodiment of the invention. Figure 1 As shown, the method may include: Step 110: Receive the partial discharge signal to be detected from the target power equipment.
[0020] In this embodiment, the partial discharge signal to be detected can be acquired by a partial discharge signal sensor, such as an ultra-high frequency sensor, a Rogowski coil, a high-frequency current transformer, a capacitive coupler, an electromagnetic coupling antenna, or a piezoelectric sensor. The partial discharge signal sensor is installed near the target power equipment to acquire the VHF band electrical signal generated by the partial discharge of the target power equipment, which is the partial discharge signal to be detected.
[0021] After the partial discharge signal sensor collects the signal, it sends the corresponding partial discharge signal to be detected to the data processing center. After receiving the partial discharge signal, the data processing center obtains the partial discharge detection result of the target power equipment based on steps 110 to 140.
[0022] Step 120: Divide the partial discharge signal to be detected into multiple timing groups according to the receiving timing sequence.
[0023] In this embodiment, the timing module's reference clock can be used as the time axis to set the duration of the timing group, for example, 10ms / group; the partial discharge signal to be detected is automatically divided into timing groups according to the group duration, and each group includes the acquisition timestamp and the partial discharge signal to be detected.
[0024] Step 130: For any signal in a time series group, perform noise reduction using the current threshold to obtain the reconstructed signal of that group; input the reconstructed signal of that group into a pre-trained threshold determination model to obtain a new threshold, and use this new threshold as the threshold of the next time series group after that time series group, until the reconstructed signals corresponding to all time series groups are obtained.
[0025] Considering that fixed-parameter filtering in traditional methods is difficult to adapt to the discharge characteristics and variations of different devices, this embodiment uses different thresholds for noise reduction in each time series signal during filtering. Since there are dependencies and transitive relationships between time series signals, this embodiment determines the threshold of subsequent signals based on preceding signals.
[0026] The pre-trained threshold determination model can be a neural network model that is trained using historical data.
[0027] This noise reduction method ensures that the determined filtering threshold can adapt to changes in equipment and environment in real time.
[0028] For example, for any signal in a time series group, the Daubechies 4 basis function can be used to perform an 8-level wavelet decomposition on the signal, and noise reduction can be performed using the current hard threshold to remove white noise. The current hard threshold can be three times the standard deviation of the noise, resulting in the reconstructed signal of that group, which is the wavelet reconstructed signal.
[0029] The wavelet reconstruction signal of the current time series group is input into a pre-trained neural network model to obtain a new threshold, and this new threshold is used as the threshold of the next time series group after this time series group.
[0030] The above methods can remove random interference such as white noise and highlight the pulse characteristics difference between the PD signal and external interference.
[0031] Step 140: Analyze the reconstructed signal to obtain the partial discharge detection results of the target power equipment.
[0032] In this embodiment, feature extraction can be performed on the reconstructed signal, and the partial discharge detection result of the target power equipment can be determined based on the identified features.
[0033] In summary, the embodiments of the present invention address the problem that current methods use fixed parameters during filtering, which cannot adapt to different devices and cannot cope with dynamic changes in field interference. To solve this problem, the embodiments of the present invention consider the dependencies and transmission relationships between time-series signals during the filtering process. Therefore, the partial discharge signal to be detected is divided into multiple time-series groups according to the receiving time sequence. Based on the noise reduction result of the current time-series group, the noise reduction parameters in the next time-series group are determined, i.e., the current parameters. In this way, the filtering method can be adapted to different power equipment and can cope with dynamic changes in field interference, providing an accurate data foundation for the partial discharge detection of power equipment.
[0034] In an optional embodiment, before receiving the partial discharge signal to be detected from the target power device in step 110, the method includes: Initial partial discharge signal acquisition is performed on the target power equipment.
[0035] The initial partial discharge signal is filtered to obtain the partial discharge signal to be detected.
[0036] Calculate the standing wave ratio (SWR) based on the partial discharge signal to be detected, and adjust the network parameters of the transmission link accordingly.
[0037] The partial discharge signal to be detected is transmitted through the adjusted transmission link.
[0038] In this embodiment, initial partial discharge signals can be acquired through the target power equipment. After acquisition, the initial partial discharge signals are subjected to three-stage wideband radio frequency filtering by a photoelectric detection module to obtain the partial discharge signal to be detected. The three-stage wideband radio frequency filtering is implemented through a three-stage filter, including a first-stage bandpass filter, a second-stage low-pass filter, and a third-stage adaptive notch filter. The bandpass filter has a range of 30~300MHz and a Q value >100; the low-pass filter has a range of 300MHz~1.5GHz and a cutoff frequency of 1.5GHz; the adaptive notch filter tracks the 50Hz power frequency and its harmonics (such as 100Hz and 150Hz) through real-time spectrum analysis and automatically adjusts the notch center frequency to achieve attenuation >40dB.
[0039] Through three-stage filtering, broadband interference is initially suppressed while retaining target signals in the VHF band, such as PD signals and residual interference.
[0040] The adjusted transmission link is determined in the following way: Based on the Smith chart algorithm, the system dynamically switches between 50Ω and 75Ω impedance modes via RF switches, such as those with a rise time of <10ns; it uses varactor diodes, such as those with a capacitance range of 1~100pF, to adjust the matching network parameters and monitors the standing wave ratio (VSWR) in real time, triggering automatic correction when VSWR >1.2; and it integrates a power detector to provide real-time feedback on signal reflection loss, optimizing the matching efficiency to >95%.
[0041] By establishing a defined transmission link, signal transmission efficiency can be improved, ensuring that both PD signals and interference signals can be effectively captured, thus avoiding signal distortion caused by poor matching.
[0042] Then, the partial discharge signal to be detected is transmitted through the adjusted transmission link to the corresponding data processing center.
[0043] In an optional embodiment, the partial discharge signal to be detected includes a first partial discharge signal to be detected and a second partial discharge signal to be detected; the reconstructed signal includes a first reconstructed signal and a second reconstructed signal; the analysis of the reconstructed signal in step 140 to obtain the partial discharge detection result of the target power equipment may include: Step 141: Extract the time-domain features of the first reconstructed signal and the second reconstructed signal respectively.
[0044] Step 142: Based on the time-domain characteristics of the first reconstructed signal and the second reconstructed signal, obtain the partial discharge detection result of the target power equipment.
[0045] In this embodiment, two couplers can be set up to collect the partial discharge signal to be detected. The first coupler can be installed near the coil / winding of the target power equipment, such as the bus interface of the GIS equipment or the bushing terminal of the transformer, to directly collect the VHF band signal generated by the partial discharge inside the target power equipment, which is the first partial discharge signal to be detected.
[0046] The second coupler can be installed near the connection point of the power supply, such as in the middle of the connection line between the test power supply and the device under test, to collect external electromagnetic interference signals, such as power grid harmonics and industrial equipment radiation, which is also the second partial discharge signal to be detected.
[0047] The spacing between the first coupler and the second coupler must meet the following conditions: ≥2 meters when connected by air-insulated wires and ≥1.5 meters when connected by shielded cables, to ensure that the signal arrival time difference can be accurately identified.
[0048] Accordingly, the reconstructed signal includes a first reconstructed signal and a second reconstructed signal.
[0049] During the analysis, S-transforms were performed on the first and second reconstructed signals respectively to extract time-domain features. This was then used to determine the partial discharge detection results of the target power equipment.
[0050] In an optional embodiment, step 142, which obtains the partial discharge detection result of the target power equipment based on the time-domain characteristics of the first reconstructed signal and the second reconstructed signal, may include: Based on the time-domain characteristics of the first reconstructed signal and the second reconstructed signal, the arrival times of the corresponding signals are determined.
[0051] Calculate the signal arrival time difference based on the arrival times of the first and second reconstructed signals.
[0052] If the signal arrival time difference is greater than the preset arrival time, it is determined that the partial discharge of the target power equipment is caused by external interference.
[0053] If the signal arrival time difference is less than or equal to the preset arrival time, then the partial discharge of the target power equipment is determined to be caused by an internal fault.
[0054] In this embodiment, based on the time-domain characteristics of the first reconstructed signal and the second reconstructed signal, the discharge pulse is identified by the Field-Programmable Gate Array (FPGA) timing module, the arrival times of the first and second partial discharge signals to be detected are determined, and the signal arrival time difference is determined based on the arrival times of the two signals.
[0055] The preset arrival time can be 6ns. Accordingly, if the signal arrival time difference is greater than 6ns, it is determined that the partial discharge of the target power equipment is caused by external interference; if the signal arrival time difference is not greater than 6ns, it is determined that the partial discharge of the target power equipment is caused by an internal fault.
[0056] In an optional embodiment, after analyzing the reconstructed signal in step 140 to obtain the partial discharge detection result of the target power equipment, the method further includes: The coordinates of the interference source are reconstructed based on the signal arrival time difference and a preset algorithm.
[0057] In this embodiment, the preset algorithm can be the Time Difference of Arrival (TDoA) algorithm. Accordingly, the three-dimensional coordinates of the interference source can be reconstructed based on the signal arrival time difference algorithm, the coupler deployment location information, and the arrival time difference algorithm. During the construction, the number of positioning iterations must be greater than the preset iteration threshold, such as 10 times, to finally achieve a positioning accuracy of ±5cm, so as to effectively distinguish between the internal partial discharge of the device under test and external interference sources, such as corona discharge and levitation discharge.
[0058] In an optional embodiment, after analyzing the reconstructed signal in step 140 to obtain the partial discharge detection result of the target power equipment, the method further includes: The minimum signal arrival time difference is calculated when there is external interference within the preset number of detections, and the maximum signal arrival time difference is calculated when there is an internal fault.
[0059] The minimum and maximum signal arrival time differences are averaged, and the result is used as the preset arrival time.
[0060] This embodiment illustrates the process of updating the preset arrival time. That is, after a preset number of detections, such as 100 detections, the minimum signal arrival time difference corresponding to external interference and the maximum signal arrival time difference corresponding to internal faults are statistically analyzed. The average value of these two data points is then used to update the preset arrival time.
[0061] In an optional embodiment, after obtaining the reconstructed signals corresponding to all timing groups in step 130, the method further includes: A spectrogram is generated based on the reconstructed signal.
[0062] Based on the spectrum, the discharge type is identified, and the threshold adjustment coefficient is determined according to the discharge type.
[0063] Based on the threshold adjustment coefficient, the current threshold is adjusted, and the steps for denoising the signal in any time series group using the current threshold are returned to obtain the reconstructed signal of that group.
[0064] In this embodiment, the accuracy of the current threshold used for noise reduction can also be determined based on the reconstructed signal obtained each time.
[0065] Specifically, phase-resolved partial discharge (PRPD) maps can be used to identify the reconstructed signal and generate a spectrum.
[0066] Extract spectral features from the spectrum, such as discharge phase range, positive and negative half-cycle discharge amplitude ratio, pulse repetition rate, etc., and identify the discharge type based on the spectral features of the spectrum.
[0067] The discharge types can include internal discharge, surface discharge, corona discharge, and suspension discharge.
[0068] Based on the identified discharge type, the corresponding threshold adjustment coefficient is searched in the threshold adjustment rule base, and the threshold adjustment coefficient is used as a multiplier to adjust the current threshold.
[0069] Correspondingly, the threshold adjustment coefficient for internal discharge is between 1.0 and 1.2 times. The adjustment logic is: when the pulse amplitude is stable and the noise interference is small, the threshold is slightly higher than the initial value to avoid excessive filtering that leads to loss of phase characteristics.
[0070] The threshold adjustment coefficient corresponding to surface discharge is between 0.8 and 1.0 times. The adjustment logic is as follows: the signal amplitude fluctuates greatly and contains some low-frequency interference. The threshold is slightly lower than the initial value to enhance noise suppression.
[0071] The threshold adjustment coefficient corresponding to corona discharge is between 0.6 and 0.8 times. The adjustment logic is: the signal amplitude is small and easily masked by noise, so the threshold is significantly reduced to highlight the weak pulse characteristics.
[0072] The floating discharge is dynamic, and the corresponding threshold adjustment coefficient is between 0.7 and 1.1 times. The adjustment logic is as follows: the amplitude fluctuation is irregular, the signal variance is calculated in real time, the threshold is lowered when the variance is large, and the threshold is raised when the variance is small.
[0073] In summary, current methods using fixed parameters for filtering suffer from limitations in adapting to different devices and handling dynamic changes in field interference. To address this issue, this invention considers the dependencies and transitive relationships between time-series signals during the filtering process. Therefore, this invention divides the partial discharge signal to be detected into multiple time-series groups according to the received timing. Based on the noise reduction result of the current time-series group, the noise reduction parameters for the next time-series group, i.e., the current parameters, are determined. In this way, the filtering method is adapted to different power equipment and can cope with dynamic changes in field interference, providing an accurate data foundation for partial discharge detection in power equipment.
[0074] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.
[0075] The following are device embodiments of the present invention. For details not described in detail, please refer to the corresponding method embodiments described above.
[0076] Figure 2 A schematic diagram of the partial discharge detection device for power equipment provided in an embodiment of the present invention is shown. For ease of explanation, only the parts related to the embodiment of the present invention are shown, and are described in detail below: like Figure 2 As shown, the partial discharge detection device 4 for power equipment includes: The receiving module 21 is used to receive the partial discharge signal to be detected from the target power equipment; wherein the partial discharge signal to be detected consists of two sets of signals. The segmentation module 22 is used to divide the partial discharge signal to be detected into multiple timing groups according to the receiving timing sequence; The noise reduction module 23 is used to perform noise reduction on the signal in any time series group using the current threshold to obtain the reconstructed signal of the group; input the reconstructed signal of the group into a pre-trained threshold determination model to obtain a new threshold, and use the new threshold as the threshold of the next time series group after the current time series group, until the reconstructed signals corresponding to all time series groups are obtained; The identification module 24 is used to analyze the reconstructed signal to obtain the partial discharge detection results of the target power equipment.
[0077] In one possible implementation, the partial discharge signal to be detected includes a first partial discharge signal to be detected and a second partial discharge signal to be detected; the reconstructed signal includes a first reconstructed signal and a second reconstructed signal; the identification module 24 is specifically used for: The time-domain features of the first reconstructed signal and the second reconstructed signal are extracted respectively; Based on the time-domain characteristics of the first and second reconstructed signals, the partial discharge detection results of the target power equipment are obtained.
[0078] In one possible implementation, the identification module 24 is specifically used for: Based on the time-domain characteristics of the first reconstructed signal and the second reconstructed signal, the arrival times of the corresponding signals are determined respectively. Calculate the signal arrival time difference based on the arrival times of the first and second reconstructed signals; If the signal arrival time difference is greater than the preset arrival time, it is determined that the partial discharge of the target power equipment is caused by external interference. If the signal arrival time difference is less than or equal to the preset arrival time, then the partial discharge of the target power equipment is determined to be caused by an internal fault.
[0079] In one possible implementation, the identification module 24 is further configured to: The coordinates of the interference source are reconstructed based on the signal arrival time difference and a preset algorithm.
[0080] In one possible implementation, the identification module 24 is further configured to: The minimum signal arrival time difference is calculated when there is external interference within the preset number of detections, and the maximum signal arrival time difference is calculated when there is an internal fault. The minimum and maximum signal arrival time differences are averaged, and the result is used as the preset arrival time.
[0081] In one possible implementation, the identification module 24 is further configured to: Generate a spectrogram based on the reconstructed signal; Based on the spectrum, identify the discharge type and determine the threshold adjustment coefficient according to the discharge type; Based on the threshold adjustment coefficient, the current threshold is adjusted, and the steps for denoising the signal in any time series group using the current threshold are returned to obtain the reconstructed signal of that group.
[0082] In one possible implementation, the receiving module 21 is further configured to: Acquire initial partial discharge signals from the target power equipment; The initial partial discharge signal is filtered to obtain the partial discharge signal to be detected; Calculate the standing wave ratio (SWR) based on the partial discharge signal to be detected, and adjust the network parameters of the transmission link according to the SWR. The partial discharge signal to be detected is transmitted through the adjusted transmission link.
[0083] In one possible implementation, the receiving module 21 is further configured to: The initial partial discharge signal is filtered sequentially through a three-stage filter to obtain the partial discharge signal to be detected. The three-stage filter includes a first-stage bandpass filter, a second-stage low-pass filter, and a third-stage adaptive notch filter.
[0084] Figure 3 This is a schematic diagram of an electronic device provided in an embodiment of the present invention. For example... Figure 3 As shown, the electronic device 3 of this embodiment includes a processor 30 and a memory 31. The memory 31 stores a computer program 32. When the processor 30 executes the computer program 32, it implements the steps in the various method embodiments described above. Alternatively, when the processor 30 executes the computer program 32, it implements the functions of each module / unit in the various device embodiments described above.
[0085] For example, computer program 32 may be divided into one or more modules / units, which are stored in memory 31 and executed by processor 30 to complete the present invention. The one or more modules / units may be a series of computer program instruction segments capable of performing a specific function, which describe the execution process of computer program 32 in electronic device 3.
[0086] Electronic device 3 may include, but is not limited to, processor 30 and memory 31. Those skilled in the art will understand that... Figure 3 This is merely an example of electronic device 3 and does not constitute a limitation on electronic device 3. It may include more or fewer components than shown, or combine certain components, or different components. For example, electronic device 3 may also include input / output devices, network access devices, buses, etc.
[0087] For the sake of simplicity and clarity, only the above-described functional modules / units are used as examples. In practical applications, the functions described above can be assigned to different functional modules / units as needed. These modules / units can be implemented in hardware, software, or a combination of both.
[0088] In the above embodiments, the descriptions of each embodiment have their own emphasis. Parts not detailed or described in a particular embodiment can be referred to in the relevant descriptions of other embodiments. Unless otherwise specified or in conflict with logic, the terminology and / or descriptions between different embodiments are consistent and can be referenced interchangeably. Technical features in different embodiments can be combined to form new embodiments based on their inherent logical relationships.
[0089] The above-described embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included within the protection scope of the present invention.
Claims
1. A method for detecting partial discharge in power equipment, characterized in that, include: Receive the partial discharge signal to be detected from the target power equipment; The partial discharge signal to be detected is divided into multiple timing groups according to the receiving timing sequence; For any signal in a time series group, noise reduction is performed using the current threshold to obtain the reconstructed signal of that group; the reconstructed signal of that group is then input into a pre-trained threshold determination model to obtain a new threshold, and this new threshold is used as the threshold of the next time series group after that time series group, until the reconstructed signals corresponding to all time series groups are obtained; The reconstructed signal is analyzed to obtain the partial discharge detection results of the target power equipment.
2. The partial discharge detection method for power equipment according to claim 1, characterized in that, The partial discharge signal to be detected includes a first partial discharge signal to be detected and a second partial discharge signal to be detected; the reconstructed signal includes a first reconstructed signal and a second reconstructed signal; the analysis of the reconstructed signal to obtain the partial discharge detection result of the target power equipment includes: The time-domain features of the first reconstructed signal and the second reconstructed signal are extracted respectively; Based on the time-domain characteristics of the first reconstructed signal and the second reconstructed signal, the partial discharge detection result of the target power equipment is obtained.
3. The partial discharge detection method for power equipment according to claim 2, characterized in that, The step of obtaining the partial discharge detection result of the target power equipment based on the time-domain characteristics of the first reconstructed signal and the second reconstructed signal includes: Based on the time-domain characteristics of the first reconstructed signal and the second reconstructed signal, the arrival times of the corresponding signals are determined. Calculate the signal arrival time difference based on the signal arrival times corresponding to the first reconstructed signal and the second reconstructed signal; If the signal arrival time difference is greater than the preset arrival time, then it is determined that the partial discharge of the target power equipment is caused by external interference. If the signal arrival time difference is less than or equal to the preset arrival time, then the partial discharge of the target power equipment is determined to be caused by an internal fault.
4. The partial discharge detection method for power equipment according to claim 3, characterized in that, After analyzing the reconstructed signal to obtain the partial discharge detection result of the target power equipment, the method further includes: The coordinates of the interference source are reconstructed based on the signal arrival time difference and a preset algorithm.
5. The partial discharge detection method for power equipment according to claim 4, characterized in that, After analyzing the reconstructed signal to obtain the partial discharge detection result of the target power equipment, the method further includes: The minimum signal arrival time difference is calculated when there is external interference within the preset number of detections, and the maximum signal arrival time difference is calculated when there is an internal fault. The minimum signal arrival time difference and the maximum signal arrival time difference are averaged, and the result is used as the preset arrival time.
6. The partial discharge detection method for power equipment according to claim 5, characterized in that, After obtaining the reconstructed signals corresponding to all time series groups, the method further includes: Generate a spectrum diagram based on the reconstructed signal; Based on the spectrum, the discharge type is identified, and a threshold adjustment coefficient is determined based on the discharge type; Based on the threshold adjustment coefficient, the current threshold is adjusted, and the step of performing noise reduction on the signal in any time series group using the current threshold to obtain the reconstructed signal of that group is returned.
7. The partial discharge detection method for power equipment according to claim 1, characterized in that, Before receiving the partial discharge signal to be detected from the target power equipment, the method includes: Acquire initial partial discharge signals from the target power equipment; The initial partial discharge signal is filtered to obtain the partial discharge signal to be detected; Based on the partial discharge signal to be detected, the standing wave ratio (SWR) is calculated, and the network parameters of the transmission link are adjusted according to the SWR. The partial discharge signal to be detected is transmitted through the adjusted transmission link.
8. The partial discharge detection method for power equipment according to claim 7, characterized in that, The step of filtering the initial partial discharge signal to obtain the partial discharge signal to be detected includes: The initial partial discharge signal is filtered sequentially through a three-stage filter to obtain the partial discharge signal to be detected. The three-stage filter includes a first-stage bandpass filter, a second-stage low-pass filter, and a third-stage adaptive notch filter.
9. A partial discharge detection device for power equipment, characterized in that, include: The receiving module is used to receive the partial discharge signal to be detected from the target power equipment; A segmentation module is used to divide the partial discharge signal to be detected into multiple timing groups according to the receiving timing sequence; The noise reduction module is used to reduce the noise of the signal in any time series group by the current threshold to obtain the reconstructed signal of the group; the reconstructed signal of the group is input into the pre-trained threshold determination model to obtain a new threshold, and the new threshold is used as the threshold of the next time series group after the current time series group, until the reconstructed signals corresponding to all time series groups are obtained; The identification module is used to analyze the reconstructed signal to obtain the partial discharge detection result of the target power equipment.
10. An electronic device, characterized in that, It includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the method as described in any one of claims 1 to 8.