Detection system, parameter update method, detection program, verification server, verification method, and verification program

Abstract

To provide a detection system that makes it possible to detect partial discharges even if measurement data includes noise that differs depending on the environment, a parameter update system, a detection program, a verification server, a verification method, and a verification program.SOLUTION: The detection system includes an acquiring unit, a processing unit, a determining unit, and an updating unit. The acquiring unit acquires measurement data from a sensor attached to a power device to be monitored. The processing unit processes the measurement data on the basis of parameters associated with the power device. The determining unit determines whether a partial discharge is occurring in the monitored target on the basis of the processed measurement data. The updating unit updates the parameters on the basis of the same determination result on whether partial discharge is occurring among a plurality of pieces of reference measurement data, which is measurement data acquired in the past.SELECTED DRAWING: Figure 1

Description

Technical Field

[0001] Embodiments of the present invention relate to a detection system, a parameter update method, a detection program, a verification server, a verification method, and a verification program.

Background Art

[0002] Due to the aging deterioration of power equipment, the insulation performance of the surface or internal insulators of the power equipment decreases. Partial discharge (PD) occurs from the location where the insulation performance has deteriorated. Partial discharge is detected by analyzing the measurement data of sensors (for example, TEV sensors) attached to the power equipment. On the other hand, the measurement data of the sensors includes noise generated in the environment of the power equipment. Such noise may include noise specific to sites such as substations where the power equipment is installed, and it is difficult to uniformly determine partial discharge.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] The problem to be solved by the present invention is to provide a detection system, a parameter update method, a detection program, a verification server, a verification method, and a verification program that can detect partial discharge even when the measurement data includes noise that varies depending on the environment.

Means for Solving the Problems

[0005] According to one embodiment of the present invention, the detection system comprises an acquisition unit, a processing unit, a determination unit, and an update unit. The acquisition unit acquires measurement data from a sensor attached to the power equipment to be monitored. The processing unit processes the measurement data based on parameters associated with the power equipment. The determination unit determines whether or not a partial discharge is occurring in the equipment to be monitored based on the processed measurement data. The update unit updates the parameters based on reference measurement data, which are measurement data acquired in the past, that have the same determination result as whether or not a partial discharge is occurring. [Brief explanation of the drawing]

[0006] [Figure 1] A schematic diagram showing the configuration of the detection system according to the first embodiment. [Figure 2] A functional block diagram showing the functional configuration of the detection device according to the first embodiment. [Figure 3] A functional block diagram showing the functional configuration of the verification server according to the first embodiment. [Figure 4] A functional block diagram illustrating the operation of the detection device according to the first embodiment. [Figure 5] A flowchart illustrating the operation of the verification server according to the first embodiment. [Figure 6] A flowchart illustrating the analysis process of processed data according to the first embodiment. [Figure 7] A flowchart illustrating the analysis process of measurement data according to the first embodiment. [Modes for carrying out the invention]

[0007] The following describes the detection system, parameter update method, detection program, verification server, verification method, and verification program of the embodiment with reference to the drawings. (First Embodiment) Figure 1 is a schematic diagram showing the configuration of the detection system 1 according to the first embodiment. Detection system 1 detects partial discharges of power equipment M installed at multiple sites S, such as substations. Detect. Examples of power equipment M include gas-insulated switchgear, switchgear, cubicles and distribution boards, as well as the circuit breakers, disconnectors, instrument transformers, grounded instrument transformers, and current transformers that make them up. Other examples of power equipment M include transformers, gas-insulated switchgear, generators, motors, and reactors. Power equipment M receives high voltage and high current from the outside via power cables. Some power equipment M has a function to cut off the power supply in the event of a malfunction. Power equipment M is connected to a grounding cable to which a grounding electrode is connected.

[0008] The detection system 1 comprises detection devices 10 installed at multiple sites S and a verification server 20. The multiple detection devices 10 and the verification server 20 are connected via a wide-area network N such as the Internet.

[0009] The detection device 10 comprises a sensor 11 and a computing device 12, each installed for each power equipment M. The detection device 10 is located near the power equipment M. The sensor 11 measures waves generated by the operation of the power equipment M, such as electromagnetic waves, sound waves, transient ground currents, and currents originating from electromagnetic waves, flowing through the metal casing surface and body of the power equipment M. The computing device 12 detects partial discharges generated from the power equipment M based on the measurement data from the sensor 11. The measurement data represents the waveform of the waves. The computing device 12 processes the measurement data and determines the presence or absence of partial discharges according to predetermined parameters. Examples of parameters include detection thresholds, matching thresholds, and measurement periods. The computing device 12 transmits the measurement data and the determination results to the verification server 20.

[0010] The verification server 20 receives and stores measurement data and judgment results from detection devices 10 installed at multiple sites S. Based on the stored measurement data, the verification server 20 verifies the correctness of the partial discharge judgment results made by the detection devices 10. The verification server 20 transmits the verification results to the detection devices 10.

[0011] Figure 2 is a functional block diagram showing the functional configuration of the detection device 10 in the first embodiment. Sensor 11 is composed of metal electrodes. Sensor 11 measures the waves generated by the operation of power equipment M. In other words, sensor 11 generates an electrical signal in accordance with the phenomena generated by the operation of power equipment M. The electrical signal generated by sensor 11 is converted using AD conversion by sensor 11 or an AD converter (not shown) and output to the computing device 12 as measurement data. The AD converter (not shown) may be provided by the computing device 12. Sensor 11 is mounted on the surface of the housing or main body that houses the power equipment M. Sensor 11 mounted on each power equipment M is connected to the detection device 10 via a signal line. Examples of sensors 11 include CT (Current Transformer) sensors, TEV (Transient Earth Voltage) sensors, AE (Acoustic Emission) sensors, antennas, and other sensors that measure waves originating from the operation of power equipment M. In the first embodiment, a TEV sensor is used as sensor 11.

[0012] The computing device 12 is an information processing device such as a PC (Personal Computer), smartphone, or tablet computer. Based on the measurement data from the sensor 11, the computing device 12 determines whether or not partial discharge has occurred in the power equipment M. The computing device 12 includes an acquisition unit 121, a storage unit 122, a processing unit 123, a determination unit 124, a communication unit 125, an update unit 126, and an output unit 127.

[0013] The acquisition unit 121 acquires measurement data from the sensor 11. The memory unit 122 stores parameters used for processing measurement data and determining the presence or absence of partial discharge. For example, the memory unit 122 stores the amplification gain of the measurement data, detection threshold, matching threshold, phase resolution, bandpass frequency bandwidth, etc. The processing unit 123 processes the measurement data acquired by the acquisition unit 121 based on the parameters stored in the storage unit 122, in order to remove noise and determine the presence or absence of partial discharge. Hereinafter, the processed measurement data will also be referred to as processed data. The processing by the processing unit 123 may be a denoising process to remove noise from the measurement data. Hereinafter, in this embodiment, the processing unit 123 will be described as performing a denoising process. Other examples of processing by the processing unit 123 include signal gain adjustment, zero point adjustment, and phase detection.

[0014] The determination unit 124 determines whether or not a partial discharge signal is included in the processed data generated by the processing unit 123, based on the parameters stored in the storage unit 122. If the determination unit 124 determines that a partial discharge signal is included in the processed data, it detects the phase, discharge charge amount, and frequency of the partial discharge based on the processed data. Based on this, the determination unit 124 determines whether or not there is a partial discharge in the power equipment M using the processed data. For example, if sensor 11 is a TEV sensor, when a partial discharge occurs, generally, the surface potential signal detected by sensor 11 will simultaneously generate a low-frequency signal originating from ground current with a main component in the frequency band of several MHz to several tens of MHz, and a high-frequency signal originating from electromagnetic waves with a main component in the frequency band of 100 MHz or higher. Here, the low-frequency signal originating from ground current propagates through the ground bus of the power equipment M and has low detection sensitivity because it competes with background noise in the ground field (dashed line in the figure). On the other hand, the high-frequency signal has high detection sensitivity against background noise in the ground field. That is, the S / N ratio is low for the low-frequency signal and high for the high-frequency signal. Therefore, the determination unit 124 can determine the presence or absence of a partial discharge by matching the amplitude waveforms of the high-frequency signal and the low-frequency signal and detecting locations where a potential difference above a threshold occurs at the same timing. Alternatively, the determination unit 124 may determine whether or not the processed data contains a partial discharge signal by obtaining the phase characteristics of the signal through clustering of the processed data.

[0015] The communication unit 125 transmits data to be verified to the verification server 20 and receives the verification result. Specifically, the communication unit 125 transmits the partial discharge determination result, the processed data serving as the basis for the determination, the measurement data before processing, and the parameters (parameters stored in the storage unit 122) used for processing the measurement data to the verification server 20. Note that when there is no partial discharge, the measurement data only contains noise and does not contain partial discharge signals.

[0016] The update unit 126 updates the parameters stored in the storage unit 122 based on the verification result received by the communication unit 125. The verification result indicates, for example, whether parameter update is necessary. When the verification result indicates that the parameters should be updated, the update unit 126 updates the parameters so that the processed data does not contain noise.

[0017] The output unit 127 outputs the determination result by the determination unit 124. For example, the output unit 127 generates and outputs display data for displaying the determination result. The output unit 127 may output the display data to a display terminal such as a tablet connected via an interface, or may output the display data to a terminal connected via the wide area network N.

[0018] FIG. 3 is a functional block diagram showing the functional configuration of the verification server 20 according to the first embodiment. The verification server 20 includes a communication unit 201, a storage unit 202, a verification unit 203, a first analysis unit 204, a second analysis unit 205, and a recording unit 206.

[0019] The communication unit 201 communicates with a plurality of detection devices 10 via the wide area network N. The memory unit 202 stores waveform data collected from multiple power devices M at multiple sites S. The memory unit 202 stores the ID of the power device M that generated the signal, the ID of the site S, the measurement time, and the partial discharge determination result in association with the measurement data and processed data. The memory unit 202 may also store partial discharge signals obtained in the laboratory as processed data. Furthermore, for data collected from sites S, only those with high accuracy (e.g., 99% or higher) obtained by comparison with partial discharge signals obtained in the laboratory may be stored. Accuracy can be determined, for example, by comparing the maximum discharge intensity, intensity distribution, and frequency for each phase.

[0020] The verification unit 203 compares the received processed data with multiple waveform data representing partial discharges stored in the memory unit 202 to determine whether the waveform represented by the processed data is similar to the waveform of a partial discharge. For example, the memory unit 202 generates a probability density function representing the probability distribution of processed data that has been determined to have a partial discharge, and calculates the similarity to the waveform of a partial discharge based on the probability obtained by substituting the received processed data into this probability density function. The verification unit 203 determines that the waveform represented by the processed data is similar to the waveform of a partial discharge if, for example, the similarity is above a predetermined threshold. For example, the verification unit 203 can obtain a probability density function using multiple processed data using an unsupervised learning method such as a Gaussian mixture model. In another embodiment, the data recorded in the memory unit 202 may be used as a training dataset, and the similarity to the waveform of a partial discharge may be calculated based on the probability of including a partial discharge obtained by inputting the received processed data into a discriminant function obtained by a supervised learning method such as a neural network model. In this case, the discriminant function is trained to output the probability of containing a partial discharge signal when processed data is input, based on the assumption that processed data is used as the input sample and the judgment result is used as the output sample.

[0021] The first analysis unit 204 determines whether or not to update the parameters of processed data that has been determined to have no partial discharge and to be similar to the waveform of a partial discharge, based on other processed data stored in the storage unit 202. The second analysis unit 205 determines whether or not to update the parameters for measurement data that has been determined to have partial discharge and is not similar to the waveform of partial discharge, based on other measurement data stored in the storage unit 202.

[0022] If the first analysis unit 204 or the second analysis unit 205 determines that there is no need to update the parameters, the recording unit 206 records the measurement data and processed data in the storage unit 202, associating them with the ID of the power equipment M that generated the signal, the ID of the site S, the measurement time, and the result of the partial discharge determination.

[0023] Figure 4 is a functional block diagram showing the operation of the detection device 10 in the first embodiment. The detection device 10 performs the following detection process for each measurement cycle stored in the storage unit 202. The acquisition unit 121 of the detection device 10 acquires measurement data of the power equipment M to be monitored from the sensor 11 (step S1). The measurement data shows a waveform for a period of several cycles stored in the storage unit 202. Next, the processing unit 123 filters the measurement data according to the bandpass frequency band stored in the storage unit 122 and generates processed data by obtaining the average value of the measurement data for N cycles (step S2).

[0024] Next, the determination unit 124 determines whether or not a partial discharge signal is included in the processed data generated by the processing unit 123, based on the parameters stored in the storage unit 122 (step S3). Specifically, the determination unit 124 extracts portions of the high-frequency signal and the low-frequency signal that exceed the detection threshold stored in the storage unit 122, and determines that a partial discharge exists if the number of matching timings that exceed the detection threshold is equal to or greater than the matching threshold stored in the storage unit 122.

[0025] The communication unit 125 transmits to the verification server 20 the measurement data acquired in step S1, the processed data obtained in step S2, the partial discharge determination result from step S3, the parameters stored in the storage unit 122, the ID of site S, and the ID of power equipment M (step S4). Subsequently, the communication unit 125 receives the verification results from the verification server 20 (step S5). The update unit 126 updates the parameters stored in the storage unit 122 based on the verification results received in step S5 (step S6). Specifically, if the verification results received from the verification server 20 indicate that the low-frequency parameters need to be updated, the update unit 126 may narrow the low-frequency bandpass frequency or raise the low-frequency detection threshold. Also, if the verification results received from the verification server 20 indicate that the high-frequency parameters need to be updated, the update unit 126 may lower the high-frequency detection threshold.

[0026] The output unit 127 generates display data to display the determination result from step S3 and the verification result received in step S5, and outputs it to the display (step S7).

[0027] Furthermore, if the verification result received in step S5 requires a parameter update, the machining unit 123 and the determination unit 124 may re-machine the measurement data acquired in step S1 using the updated parameters in step S6 and determine whether or not there is partial discharge. In this case, the determination unit 124 can re-determine the measurement if the initial determination was inappropriate due to noise remaining in the machined data.

[0028] Figure 5 is a flowchart showing the operation of the verification server 20 according to the first embodiment. The communication unit 201 receives measurement data, processed data, partial discharge determination result, parameters used to process the measurement data, site ID S, and power equipment ID M from the detection device 10 via the wide-area network N (step S21). The verification unit 203 determines whether the received determination result indicates the presence of partial discharge (step S22).

[0029] If the judgment result indicates that there is no partial discharge (step S22: NO), the verification unit 203 verifies whether or not there is a false detection of partial discharge. The verification unit 203 compares the distribution of processed data stored in the storage unit 202 that has been determined to have partial discharge with the received processed data and determines whether or not the received processed data is similar to the waveform of partial discharge (step S23). If the verification unit 203 determines that the waveform represented by the processed data is not similar to the waveform of partial discharge (step S23: NO), it determines that the partial discharge judgment result by the detection device 10 is correct. In this case, the recording unit 206 records the data received in step S1 in the storage unit 202 (step S24). At this time, the recording unit 206 may compare the data received in step S1 with the processed data related to partial discharge stored in the storage unit and record it in the storage unit 202 if the accuracy of representing the partial discharge signal is greater than or equal to a predetermined value. The communication unit 201 then transmits a verification result to the detection device 10 indicating that no parameter update is necessary (step S25).

[0030] On the other hand, if the verification unit 203 determines that the waveform represented by the processed data is similar to the waveform of partial discharge (step S23: YES), the first analysis unit 204 determines that the determination result of partial discharge may be incorrect. This indicates that although the processed data contains a signal representing partial discharge, it may not have been detected. The first analysis unit 204 performs an analysis of the processed data as described later (step S26). Then, the communication unit 201 transmits the verification result to the detection device 10 (step S24).

[0031] If the judgment result indicates that there is partial discharge (step S22: YES), the verification unit 203 verifies whether or not there is a false detection of partial discharge. The verification unit 203 compares the distribution of processed data stored in the memory unit 202 that has been determined to have partial discharge with the received processed data and determines whether or not the received processed data is similar to the waveform of partial discharge (step S27). If the verification unit 203 determines that the waveform represented by the processed data is similar to the waveform of partial discharge (step S27: YES), it determines that the judgment result of the detection device 10 regarding partial discharge is correct. In this case, the recording unit 206 records the data received in step S1 in the recording unit 206 (step S28). Then, the communication unit 201 transmits a verification result indicating that parameter updates are unnecessary to the detection device 10 (step S24).

[0032] On the other hand, if the verification unit 203 determines that the waveform represented by the processed data is not similar to the waveform of partial discharge (step S26: NO), the second analysis unit 205 determines that the determination result of partial discharge may be incorrect. This indicates that although the processed data contains a signal representing partial discharge, it may not have been detected. The first analysis unit 204 performs an analysis of the measurement data, which will be described later (step S29). Then, the communication unit 201 transmits the verification result to the detection device 10 (step S24).

[0033] Figure 6 is a flowchart showing the analysis process of processed data according to the first embodiment. The first analysis unit 204 determines whether the maximum amplitude of the processed data received in step S1 is greater than or equal to a predetermined amplitude threshold (step S41). The first analysis unit 204 also determines whether the difference between the maximum and average amplitudes of the processed data received in step S1 is greater than or equal to a predetermined deviation threshold (step S42). The amplitude threshold and deviation threshold may be obtained, for example, by statistical processing based on other processed data representing partial discharges stored in the storage unit 202.

[0034] The first analysis unit 204 determines whether the determination result received in step S1 matches the determination result of other power equipment M at the same site S (step S43). The first analysis unit 204 also determines whether the processed data received in step S1 is similar to the processed data of power equipment M at other sites S (step S44). The first analysis unit 204 may determine similarity using the same method as the verification unit 203. If the determination result is the same as that of other power equipment M at the same site S, or if the processed data is not similar to that of power equipment M at different sites S, it indicates that the signal contained in the processed data may be noise specific to site S.

[0035] The first analysis unit 204 determines that it is necessary to change the parameters related to the high-frequency signal if the maximum value of the amplitude of the processed data is greater than or equal to the amplitude threshold (step S41: YES), the difference between the maximum and average values ​​of the amplitude of the processed data is greater than or equal to the deviation threshold (step S42: YES), the judgment result matches the judgment result of other power equipment M at the same site S (step S43: YES), and the processed data is not similar to processed data at other sites S (step S44: NO) (step S45). In other words, the first analysis unit 204 determines that the parameters should be changed so that partial discharge can be detected from similar processed data, because the processed data may contain partial discharge.

[0036] The first analysis unit 204 determines that it is not necessary to change the parameters related to the high-frequency signal if the maximum amplitude of the processed data is less than the amplitude threshold (step S41: NO), if the difference between the maximum and average amplitude of the processed data is less than the deviation threshold (step S42: NO), if the determination result does not match the determination result of other power equipment M at the same site S (step S43: NO), or if the processed data is similar to processed data from another site S (step S44: YES) (step S45). In other words, the first analysis unit 204 determines that it is possible to maintain the parameters because there is a high possibility that the signal appearing in the processed data is noise.

[0037] Figure 7 is a flowchart showing the analysis process of measurement data according to the first embodiment. The detection device 10 determines that there is no partial discharge in the measurement data to be analyzed. Therefore, only noise should be present in the measurement data.

[0038] The second analysis unit 205 determines whether the measurement data received in step S1 is similar to measurement data for the same power equipment M stored in the storage unit 202 that was measured in the same month (step S61). The second analysis unit 205 determines whether the measurement data received in step S1 is similar to measurement data for the same power equipment M stored in the storage unit 202 that was measured on the same day of the week (step S62). The second analysis unit 205 determines whether the measurement data received in step S1 is similar to measurement data for the same power equipment M stored in the storage unit 202 that was measured during the same time period (step S63). In other words, the second analysis unit 205 determines whether the noise appearing in the measurement data is one that frequently occurs under predetermined conditions. If noise that frequently occurs under predetermined conditions is included, it is possible that the environment of site S has changed and the amount of noise that needs to be removed has increased.

[0039] The second analysis unit 205 determines whether the noise appearing in the measurement data received in step S1 is abnormal noise in the power supply cycle (step S64). Since the partial discharge signal is generated in synchronization with the power supply cycle, the presence of noise in the power supply cycle can easily lead to misjudgment.

[0040] The second analysis unit 205 determines that it is necessary to change the parameters related to the low-frequency signal if the received measurement data is similar to measurement data measured in the same month, measurement data measured on the same day of the week, or measurement data measured during the same time period, or if it contains abnormal noise in the power cycle (step S65).

[0041] On the other hand, the second analysis unit 205 determines that there is no need to change the parameters related to the low-frequency signal if the received measurement data is specific to measurement data measured in the same month, measurement data measured on the same day of the week, and measurement data measured during the same time period, and does not contain abnormal noise in the power cycle (step S66).

[0042] As described above, the detection system 1 according to the first embodiment updates the noise reduction parameters as follows: The acquisition unit 121 acquires measurement data from a sensor 11 attached to the power equipment M to be monitored. The processing unit 123 removes noise from the measurement data based on parameters associated with the power equipment M. The determination unit 124 determines whether or not a partial discharge is occurring in the monitored object based on the processed data. The update unit 126 updates the noise reduction parameters based on reference measurement data acquired in the past that have the same determination result as whether or not a partial discharge is occurring. In this way, the detection system 1 can remove noise that differs depending on the environment and detect partial discharge by updating parameters using reference measurement data acquired in the past.

[0043] Furthermore, in the detection system 1 according to the first embodiment, a verification server 20 connected to a plurality of detection devices 10 via a wide-area network N verifies whether or not parameter updates are necessary using reference measurement data from a plurality of power devices M. As a result, the detection system 1 can update parameters using data on partial discharge collected beyond site S.

[0044] In the first embodiment, the detection system 1 is configured such that a detection device 10 installed at site S detects the presence or absence of partial discharge, but this is not limited to this configuration. For example, in another embodiment of the detection system 1, the verification server 20 may have the function of a determination unit 124 that determines the presence or absence of partial discharge. In this case, the detection device 10 does not determine the presence or absence of partial discharge, but transmits the measurement data and processed data to the verification server 20. The verification server 20 also performs the determination processing by the determination unit 124 in step S2 shown in Figure 5. In another embodiment, both the detection device 10 and the verification server 20 may perform the determination processing. In another embodiment, the detection device 10 may have the functionality of the verification unit 203 of the verification server 20. In this case, the detection device 10 can perform verification using reference measurement data from the same site S.

[0045] Furthermore, the detection system 1 according to the first embodiment determines whether or not to update the parameters using the method shown in Figures 6 and 7, but is not limited to this. For example, in the process shown in Figure 6, the analysis is performed using the maximum value and deviation of the amplitude of the processed data in steps S41 and S42, but is not limited to this, and the first analysis unit 204 may also perform the analysis using other waveform characteristics such as peak frequency and signal-to-noise ratio. Also, in the flowchart shown in Figure 6, it is determined that no change is necessary if any one of the conditions in steps S41, S42, S43, and S44 is not met, but is not limited to this. For example, the first analysis unit 204 may determine that a change is necessary regardless of the other conditions if any one of the conditions in steps S41, S42, S43, and S44 significantly exceeds the threshold.

[0046] According to at least one embodiment described above, by updating parameters using multiple previously acquired reference measurement data, it is possible to remove noise that varies depending on the environment and detect partial discharge.

[0047] The arithmetic unit 12 and verification server 20 of the detection device 10 are each implemented by a computer. The computer of the arithmetic unit 12 is equipped with a processor, memory, auxiliary storage device, etc., connected by a bus, and functions as a device comprising an acquisition unit 121, a storage unit 122, a processing unit 123, a determination unit 124, a communication unit 125, an update unit 126, and an output unit 127 by executing a detection program. The computer of the verification server 20 functions as a device comprising a communication unit 201, a storage unit 202, a verification unit 203, a first analysis unit 204, a second analysis unit 205, and a recording unit 206 by executing a verification program. Examples of processors include CPUs (Central Processing Units), GPUs (Graphics Processing Units), and microprocessors. Programs may be recorded on computer-readable recording media. Computer-readable recording media include, for example, magnetic disks, magneto-optical disks, optical disks, and semiconductor memory. Programs may also be transmitted via telecommunications lines. Furthermore, all or part of the functions of the arithmetic unit 12 or the verification server 20 may be implemented using custom LSIs (Large Scale Integrated Circuits) such as ASICs (Application Specific Integrated Circuits) or PLDs (Programmable Logic Devices). Examples of PLDs include PALs (Programmable Array Logic), GALs (Generic Array Logic), CPLDs (Complex Programmable Logic Devices), and FPGAs (Field Programmable Gate Arrays). Such integrated circuits are also included as examples of processors.

[0048] While several embodiments of the present invention have been described, these embodiments are presented as examples only and are not intended to limit the scope of the invention. These embodiments can be carried out in a variety of other forms, and various omissions, substitutions, and modifications can be made without departing from the spirit of the invention. These embodiments and their variations are included in the scope and spirit of the invention, as well as in the claims and their equivalents. [Explanation of symbols]

[0049] 1...Detection system 10...Detection device 11...Sensor 12...Calculation unit 121...Acquisition unit 122...Storage unit 123...Processing unit 124...Determination unit 125...Communication unit 126...Update unit 127...Output unit 20...Verification server 201...Communication unit 202...Storage unit 203...Verification unit 204...First analysis unit 205...Second analysis unit 206...Recording unit M...Power equipment N...Wide area network S...Site

Claims

1. An acquisition unit that acquires measurement waveform data from sensors attached to the power equipment to be monitored, A processing unit that performs denoising to remove noise from the measured waveform data based on parameters related to denoising associated with the power equipment, and obtains processed waveform data. A determination unit that determines whether or not a partial discharge is occurring in the monitored object based on the processed waveform data, A verification unit verifies the correctness of the determination result based on the comparison result between the processed waveform data and the reference measurement waveform data which is determined to be in which partial discharge has occurred among multiple reference measurement waveform data which are measurement data acquired in the past, and the determination result of whether or not partial discharge has occurred in the monitored object. If the verification result indicates that the judgment result may be incorrect, the update unit updates the parameters so that noise is not included in the processed waveform data. A detection system equipped with the following features.

2. If it is determined that a partial discharge is occurring in the monitored object, the update unit updates the parameters based on the processed waveform data and the multiple processed reference measurement waveform data in which partial discharge was previously determined to have occurred. The detection system according to claim 1.

3. If it is determined that no partial discharge has occurred in the monitored object, the update unit updates the parameters based on the measurement waveform data including noise and the plurality of reference measurement waveform data including noise in which it was previously determined that no partial discharge had occurred. The detection system according to claim 1 or claim 2.

4. The update unit updates the parameters based on the plurality of reference measurement waveform data relating to other power equipment. A detection system according to any one of claims 1 to 3.

5. The update unit updates the parameters based on the reference measurement waveform data that belong to the same seasonal period among the plurality of reference measurement waveform data. A detection system according to any one of claims 1 to 3.

6. The verification unit determines whether the reference measurement waveform data and the processed waveform data are similar, and if the reference measurement waveform data and the processed waveform data are similar and the determination result indicates that no partial discharge has occurred, it determines that the determination result may be incorrect. A detection system according to any one of claims 1 to 5.

7. Multiple detection devices are provided to correspond to multiple monitoring targets, and each device comprises a processing unit, a determination unit, and an update unit. The verification unit is provided, and the verification server is connected to the multiple monitoring targets via a network. The detection system according to claim 6, comprising:

8. The steps include acquiring measurement waveform data from a sensor attached to the power equipment to be monitored, The steps include: performing denoising to remove noise from the measured waveform data based on parameters related to denoising associated with the power equipment, thereby obtaining processed waveform data; The steps include determining whether or not a partial discharge is occurring in the monitored object based on the processed waveform data, A step to verify the correctness of the determination result based on the comparison result between the processed waveform data and the reference measurement waveform data which was determined to be causing partial discharge from among multiple reference measurement waveform data which are measurement data acquired in the past, and the determination result of whether or not partial discharge is occurring in the monitored object, If the verification result indicates that the judgment result may be incorrect, the step of updating the parameters so that the processed waveform data does not contain noise. A parameter update method comprising the following features.

9. On the computer, The steps include acquiring measurement waveform data from a sensor attached to the power equipment to be monitored, The steps include: performing denoising to remove noise from the measured waveform data based on parameters related to denoising associated with the power equipment, thereby obtaining processed waveform data; The steps include determining whether or not a partial discharge is occurring in the monitored object based on the processed waveform data, A step to verify the correctness of the determination result based on the comparison result between the processed waveform data and the reference measurement waveform data which was determined to have partial discharge among multiple reference measurement waveform data which are measurement data acquired in the past, and the determination result of whether or not partial discharge has occurred in the monitored object, If the verification result indicates that the judgment result may be incorrect, the step of updating the parameters so that the processed waveform data does not contain noise. A detection program to execute.

Images