Estimation device, estimation method, and estimation program

Abstract

To enable more accurate cause estimation of partial discharge.SOLUTION: An estimation device is provided, comprising a fluctuation determination unit configured to determine whether to correct a cause estimation result of partial discharge on the basis of fluctuation of a partial discharge signal, and an estimation result correction unit configured to correct the estimation result when it is determined that the estimation result should be corrected.SELECTED DRAWING: Figure 4

Description

Technical Field

[0001] Embodiments of the present invention relate to an estimation device, an estimation method, and a program.

Background Art

[0002] Due to the aging deterioration of power equipment, the insulation performance of the surface and internal insulators of the power equipment decreases. It is known that partial discharge occurs from the location where the insulation performance has deteriorated. As the deterioration of the insulation performance progresses, there is a possibility of insulation breakdown in the power equipment. Therefore, efforts have been made to measure the waves (electromagnetic waves, sounds, vibrations, etc.) generated by partial discharge with sensors and grasp the deterioration status of the insulator. Since partial discharge varies over time, methods of diagnosing using past partial discharge data have also been proposed.

[0003] However, the above method mechanically uses past information in diagnosis, and the past information does not contribute to improving the accuracy of diagnosis.

Prior Art Documents

Patent Documents

[0004]

Patent Document 1

Patent Document 2

Summary of the Invention

Problems to be Solved by the Invention

[0005] The problem to be solved by the present invention is to provide an estimation device, an estimation method, and a program that can more accurately estimate the cause of partial discharge.

Means for Solving the Problems

[0006] The estimation device of the embodiment includes a fluctuation determination unit and an estimation result correction unit. The fluctuation determination unit determines whether to correct the estimation result of the cause of partial discharge based on the fluctuation of the partial discharge signal. The estimation result correction unit corrects the estimation result when it is determined that the estimation result is to be corrected.

Brief Description of the Drawings

[0007]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Mode for Carrying Out the Invention

[0008] (First Embodiment) Hereinafter, an estimation device, an estimation method, and a program according to an embodiment will be described with reference to the drawings. FIG. 1 is a diagram showing the configuration of an estimation model generation system 1 according to the first embodiment. The estimation model generation system 1 generates an estimation model for estimating the cause of partial discharge of a device based on the partial discharge signal of the device. The estimation model generation system 1 includes a partial discharge sensor 10, a teacher data generation device 11, and an estimation model generation device 12.

[0009] The partial discharge sensor 10 is provided in the device T. The partial discharge sensor 10 measures a signal generated by the partial discharge of the device T. Examples of the partial discharge sensor 10 include a TEV sensor that measures a transient ground voltage passing through the housing due to partial discharge, a vibration sensor that detects vibration caused by partial discharge, a microphone that detects sound waves caused by partial discharge, and the like.

[0010] The teacher data generation device 11 generates teacher data for generating an estimation model. The teacher data generation device 11 includes a data acquisition unit 111, a storage unit 112, and a teacher data output unit 113.

[0011] The data acquisition unit 111 acquires a partial discharge signal from the partial discharge sensor 10. The data acquisition unit 111 records the partial discharge signal in the storage unit 112. The data acquisition unit 111 acquires data indicating the cause of the partial discharge occurring in the device T (hereinafter referred to as partial discharge cause data) and data indicating the time period when the partial discharge occurred (hereinafter referred to as time period data). The cause of the partial discharge and the time period when the partial discharge occurred are confirmed by, for example, the administrator of the device T. By the administrator of the device T inputting the cause of the partial discharge in the device T and the time period when the partial discharge occurred to the teacher data generation device 11, the data acquisition unit 111 acquires the partial discharge cause data and the time period data in the device T. The data acquisition unit 111 records the partial discharge cause data and the time period data in the device T in the storage unit 112.

[0012] In the estimation model generation system 1, the cause of the partial discharge is embedded in the device T in advance, and the partial discharge is generated by applying a voltage. The partial discharge signal generated at this time is measured by the partial discharge sensor 10 and acquired by the data acquisition unit 111. Further, the data acquisition unit 111 acquires data indicating the cause of the partial discharge embedded in the device T in advance.

[0013] The memory unit 112 records the partial discharge signals measured from the device T in the time zone indicated by the time zone data and the partial discharge causes of the device T in the time zone in an associated manner. The data in which the partial discharge signals measured from the device T and the partial discharge causes of the device T are associated is teacher data. Note that the partial discharge signals included in the teacher data may be partial discharge signals within a predetermined time period among the time periods when partial discharge occurs.

[0014] The teacher data output unit 113 outputs the teacher data to the estimation model generation device 12. FIG. 2 is a diagram showing an example of teacher data. In the example shown in FIG. 2, the teacher data includes partial discharge signals generated due to voids from 12:00 to 13:00 on January 1st and partial discharge signals generated due to metal foreign objects from 13:00 to 14:00 on January 3rd.

[0015] The partial discharge signal may be, for example, data of time vs. signal intensity, or image data of a graph showing time vs. signal intensity. Further, the partial discharge signal may be a ΦQN pattern of the partial discharge signal. The ΦQN pattern is data showing the relationship between the generation phase Φ, the charge amount Q, and the generation frequency N of the partial discharge signal. The ΦQN pattern is represented by a two-dimensional table, image data, etc. For example, the ΦQN pattern may be image data with the generation phase Φ on the horizontal axis, the charge amount Q on the vertical axis, and the pixel value as the generation frequency N.

[0016] Examples of the causes of partial discharge include voids in the device, metal foreign objects, and windings.

[0017] The estimation model generation device 12 generates an estimation model based on the teacher data acquired from the teacher data generation device 11. The estimation model generation device 12 includes a teacher data acquisition unit 121, an estimation model generation unit 122, and an estimation model output unit 123. The teacher data acquisition unit 121 acquires the teacher data from the teacher data generation device 11.

[0018] The estimation model generation unit 122 generates an estimation model based on the teacher data. The estimation model generation unit 122 generates an estimation model by inputting the teacher data into a machine learning algorithm such as a neural network. The estimation model is a model that takes a partial discharge signal at a predetermined length of time as an input and outputs an estimation result of the cause of the partial discharge. The output estimation result indicates each cause of the partial discharge by probability. For a specific example, the output estimation result is that the probability that the cause is a metal foreign object is 55%, the probability that the cause is a void is 30%, and the probability that the cause is a winding is 15%.

[0019] The estimation model output unit 123 outputs the generated estimation model. The output estimation model is stored in the estimation device 21 described later.

[0020] FIG. 3 is a flowchart showing the operation of the estimation model generation device 12 according to the first embodiment. The teacher data acquisition unit 121 acquires teacher data (step S11). The estimation model generation unit 122 generates an estimation model based on the teacher data (step S12). The estimation model output unit 123 outputs the generated estimation model (step S13).

[0021] As described above, the estimation model generation system 1 generates an estimation model that takes a partial discharge signal at a predetermined length of time as an input and outputs an estimation result of the cause of the partial discharge.

[0022] FIG. 4 is a diagram showing the configuration of the estimation system 2 according to the first embodiment. The estimation system 2 estimates the cause of partial discharge in the device to be estimated based on the partial discharge signal of the device E to be estimated. The estimation system 2 includes a partial discharge sensor 20 and an estimation device 21.

[0023] The partial discharge sensor 20 is provided in the device E to be estimated and measures a signal generated by the partial discharge of the device E to be estimated. The partial discharge sensor 20 may be the same sensor as the partial discharge sensor 10 in the estimation model generation system 1.

[0024] Based on the partial discharge signal measured by the partial discharge sensor 20, the estimation device 21 estimates the cause of the partial discharge. The estimation device 21 includes a measurement data acquisition unit 211, an estimation unit 212, a variation determination unit 213, an estimation result correction unit 214, an output unit 215, and a storage unit 219. The storage unit 219 stores an estimation model.

[0025] The measurement data acquisition unit 211 acquires the partial discharge signal measured by the partial discharge sensor 20. The measurement data acquisition unit 211 stores the acquired signal in the storage unit 219.

[0026] Based on the partial discharge signal acquired by the measurement data acquisition unit 211, the estimation unit 212 estimates the cause of the partial discharge. The measurement time of the partial discharge signal used by the estimation unit 212 is the time determined by the estimation model, that is, preferably the same as the measurement time of the partial discharge signal included in the training data. Based on the latest partial discharge signal acquired by the measurement data acquisition unit 211, the estimation unit 212 estimates the cause of the partial discharge. The estimation unit 212 estimates the cause of the partial discharge by inputting the partial discharge signal at a predetermined time into the estimation model. The estimation result by the estimation unit 212 is that each cause of the partial discharge is indicated by a probability as described above in the estimation model.

[0027] Based on the variation of the partial discharge signal stored in the storage unit 219, the variation determination unit 213 determines whether to correct the estimation result. The variation determination unit 213 determines whether to correct the estimation result based on the feature amount of the variation of the partial discharge signal. The feature amount of the variation of the partial discharge signal is information including at least one of, for example, the discharge intensity, discharge phase, and change of the number of discharges over time. The measurement time of the partial discharge signal used by the variation determination unit 213 for determination is longer than the measurement time of the partial discharge signal used by the estimation unit 212 for estimation. By making a determination based on the partial discharge signal measured for a longer time, the variation determination unit 213 can make a determination from a long-term perspective.

[0028] The variation determination unit 213 determines, for example, whether the variation of the partial discharge signal stored in the storage unit 219 is larger than a predetermined variation. More specifically, the variation determination unit 213 determines whether the variation is large by determining whether the ratio of the maximum value to the minimum value of the partial discharge signal stored in the storage unit 219 is equal to or greater than a predetermined value. The variation determination unit 213 may determine whether to correct the estimation result based on the variation of the partial discharge signal in a predetermined length of time determined in advance. More specifically, the variation determination unit 213 determines whether the variation is large by determining whether the maximum value of the rate of change of the intensity of the partial discharge signal stored in the storage unit 219 with respect to time (the maximum value of the slope of the tangent in the graph showing the intensity of the partial discharge signal and time) is equal to or greater than a predetermined value. The variation determination unit 213 may determine whether the rate of change of the intensity of the partial discharge signal with respect to time in a predetermined length of time determined in advance is equal to or greater than a predetermined value. The predetermined value serving as the determination criterion and the predetermined length of time for measuring the partial discharge signal are determined in advance by a technician or the like.

[0029] The estimation result correction unit 214 corrects the estimation result by the estimation unit 212 based on the determination result by the variation determination unit 213. For example, when the variation determination unit 213 determines that the variation is large, the estimation result correction unit 214 sets the probability that the cause in the estimation result is a metal foreign object to a value smaller than the probability of other causes. This is because the variation of the partial discharge signal when the cause of the partial discharge is a metal foreign object is smaller than the variation of the partial discharge signal when the cause of the partial discharge is other causes. More specifically, for example, when it is determined that the ratio of the maximum value to the minimum value of the partial discharge signal is equal to or greater than a predetermined value, the estimation result correction unit 214 sets the probability that the cause in the estimation result is a metal foreign object to a value smaller than the probability of other causes. The estimation result shows that the probability that the cause is a metal foreign object is 55%, the probability that the cause is a void is 30%, and the probability that the cause is a winding is 15%. When the estimation result correction unit 214 corrects the probability that the cause is a metal foreign object to 0, the corrected estimation result shows that the probability that the cause is a void is 30% and the probability that the cause is a winding is 15%. That is, the corrected estimation result shows that the ratio of the probability that the cause is a void to the probability that the cause is a winding is 2:1. The estimation result correction unit 214 may allocate the corrected estimation result so that the total probability is 100%. When the corrected estimation result shows that the probability that the cause is a void is 30% and the probability that the cause is a winding is 15% as in the above example, after allocation, the corrected estimation result shows that the probability that the cause is a void is 66.6% and the probability that the cause is a winding is 33.3%.

[0030] More specifically, when the maximum value of the change rate of the partial discharge signal intensity stored in the storage unit 219 with respect to time is equal to or greater than a predetermined value, for example, the estimation result correction unit 214 sets the probability that the cause is a metal foreign object in the estimation result to a value smaller than the probability of other causes. The greater the maximum value of the change rate of the partial discharge signal intensity with respect to time, the greater the decrease in the probability that the cause is a metal foreign object in the estimation result. For example, when the maximum value of the change rate of the partial discharge signal intensity with respect to time is a, the correction term for the cause of the partial discharge being a metal foreign object is 1 / (3 + 2a), the correction term for being a void is (1 + a) / (3 + 2a), and the correction term for being a winding is (1 + a) / (3 + 2a). The estimation result is corrected by multiplying the correction term by the estimation result. For example, if a = 3, the correction term for the cause of the partial discharge being a metal foreign object is 1 / 9, the correction term for being a void is 4 / 9, and the correction term for being a winding is 4 / 9. When the estimation result shows that the probability that the cause of the partial discharge is a metal foreign object is 55%, the probability of being a void is 30%, and the probability of being a winding is 15%, the corrected estimation result shows that the probability that the cause of the partial discharge is a metal foreign object is 55%×1 / 9, the probability of being a void is 30%×4 / 9, and the probability of being a winding is 15%×4 / 9. The estimation result correction unit 214 may allocate the corrected estimation results so that the sum of their probabilities is 100%. When the estimated results corrected as in the above example indicate that the probability that the cause of partial discharge is a metal foreign object is 55%×1 / 9, the probability that it is a void is 30%×4 / 9, and the probability that it is a winding is 15%×4 / 9, the allocation results in the probability that the cause of partial discharge is a metal foreign object being 1100 / 47%≈23.4%, the probability that it is a void being 2400 / 47%≈51.1%, and the probability that it is a winding being 1200 / 47%≈25.5%.

[0031] The output unit 215 outputs the estimation result. When the estimation result is corrected by the estimation result correction unit 214, the output unit 215 outputs the corrected estimation result. The output unit 215 may output the cause with the highest probability in the estimation result as the estimation result. The output unit 215 may also output the estimation result by the estimation unit 212, the determination result by the fluctuation determination unit 213, and the correction content by the estimation result correction unit 214. The output from the output unit 215 is displayed, for example, by a display device. FIG. 5 is a diagram showing a display example of the output by the output unit 215. FIG. 5 shows the latest partial discharge signal, the estimation result of the cause of partial discharge based on the latest partial discharge signal by the estimation unit 212 (estimation result based on the current waveform), the fluctuation of the intensity of the partial discharge signal, the correction content by the estimation result correction unit 214 (correction content based on the fluctuation), and the corrected estimation result (comprehensive estimation result). In the comprehensive estimation result, the void with the highest probability is displayed as the cause of partial discharge (partial discharge source).

[0032] FIG. 6 is a flowchart showing the operation of the estimation device 21 according to the first embodiment. The measurement data acquisition unit 211 acquires the partial discharge signal measured by the partial discharge sensor 20 (step S21). The estimation unit 212 estimates the cause of the partial discharge based on the partial discharge signal at a predetermined time acquired by the measurement data acquisition unit 211 (step S22). The fluctuation determination unit 213 determines whether to correct the estimation result based on the fluctuation of the partial discharge signal stored in the storage unit 219 (step S23). When the fluctuation determination unit 213 determines to correct the estimation result (step S23: YES), the estimation result correction unit 214 corrects the estimation result by the estimation unit 212 based on the determination result by the fluctuation determination unit 213 (step S24). The output unit 215 outputs the corrected estimation result (step S25). When the fluctuation determination unit 213 determines not to correct the estimation result (step S23: NO), the output unit 215 outputs the estimation result by the estimation unit 212 without correction (step S26).

[0033] As described above, the estimation device 21 can correct the estimation result. Since the estimation unit 212 performs estimation based on the partial discharge signal at a predetermined time, the partial discharge signal before that time is not included, and the information regarding the fluctuation of the partial discharge signal is insufficient. Therefore, the fluctuation of the partial discharge signal is not considered in the estimation result by the estimation unit 212. The estimation device 21 can estimate the cause of the partial discharge in consideration of the fluctuation of the partial discharge signal by correcting the estimation result based on the fluctuation of the partial discharge signal by the estimation result correction unit 214.

[0034] (Second Embodiment) FIG. 7 is a diagram showing the configuration of the estimation model generation device 12 according to the second embodiment. The estimation model generation device 12 according to the second embodiment includes a correction rule generation unit 124 in addition to the estimation model generation device 12 according to the first embodiment. The correction rule generation unit 124 generates the determination criteria by the fluctuation determination unit 213 and the correction rules by the estimation result correction unit 214. The correction rule generation unit 124 generates correction rules based on teacher data in which the fluctuation of the partial discharge signal is associated with the cause of the partial discharge. For example, the correction rule generation unit 124 adjusts the determination criteria for the ratio of the maximum value to the minimum value of the partial discharge signal and the apportioned value of the probability of the cause in the estimation result based on the relationship between the ratio of the maximum value to the minimum value of the partial discharge signal and the cause of the partial discharge. For example, the correction rule generation unit 124 adjusts the determination criteria for the change rate of the intensity of the partial discharge signal with respect to time and the apportioned value of the probability of the cause in the estimation result. The correction rule generation unit 124 generates determination criteria and correction rules by, for example, association analysis. Further, the correction rules and determination criteria generated by the correction rule generation unit 124 may be manually corrected by a technician after checking the content in light of the findings.

[0035] The estimation model output unit 123 according to the second embodiment outputs an estimation model and correction rules. The estimation model and correction rules are stored in the storage unit 219 of the estimation device 21. The fluctuation determination unit 213 according to the second embodiment makes a determination based on the correction rules, and the estimation result correction unit 214 performs correction based on the correction rules.

[0036] In the second embodiment, the correction rule generation unit 124 generates the determination criteria by the fluctuation determination unit 213 and the correction rules by the estimation result correction unit 214. In the first embodiment, the determination criteria and correction rules had to be manually set by a technician, but in the second embodiment, there is no need for manual setting, and the estimation device 21 can more easily correct the estimation result.

[0037] (Third Embodiment) FIG. 8 is a diagram showing the configuration of the estimation device 21 according to the third embodiment. The estimation device 21 according to the third embodiment includes a signal extraction unit 216 in addition to the estimation device 21 according to the first embodiment. The signal extraction unit 216 extracts a partial discharge signal having the same characteristics as the latest partial discharge signal from the past partial discharge signals stored in the storage unit 219. The latest partial discharge signal is a partial discharge signal acquired from a predetermined time before the current time. The feature amount indicating the characteristics of the partial discharge signal is, for example, discharge intensity, discharge phase, number of discharges, average intensity, or a combination thereof. The signal extraction unit 216 uses, for example, an algorithm that performs clustering to cluster the latest partial discharge signal and the data including the latest partial discharge signal, and extracts the data of the cluster including the latest partial discharge signal, thereby extracting a partial discharge signal having the same characteristics as the latest partial discharge signal.

[0038] FIG. 9 is a diagram showing an example of the extracted partial discharge signal. In FIG. 9, the partial discharge signals measured from 0:00 to 7:00 are shown separately for each hour. The latest partial discharge signal is the partial discharge signal from 6:00 to 7:00. The partial discharge signal from 6:00 to 7:00 has the same characteristics as the partial discharge signal from 0:00 to 1:00 and the partial discharge signal from 2:00 to 3:00. The signal extraction unit 216 extracts the partial discharge signal from 0:00 to 1:00 and the partial discharge signal from 2:00 to 3:00.

[0039] The fluctuation determination unit 213 according to the third embodiment determines fluctuations based on the partial discharge signal extracted by the signal extraction unit 216.

[0040] In the device, the discharge that has been continuing suddenly stops, or occurs concentratedly in a short period of time. Also, various environmental noises are mixed in during the measurement of the partial discharge signal. Therefore, various signals are mixed in the measured partial discharge signal. Therefore, when determining fluctuations from the measured partial discharge signal, there is a possibility that the fluctuations of the partial discharge signal cannot be accurately determined. The fluctuation determination unit 213 according to the third embodiment determines whether to correct the estimation result based on the fluctuation of the partial discharge signal extracted by the signal extraction unit 216. Therefore, in the third embodiment, the estimation device 21 determines whether to correct the estimation result based on the fluctuation of the partial discharge signal excluding the partial discharge signal having other characteristics and noise, and can more accurately determine the fluctuation of the partial discharge signal.

[0041] According to at least one of the embodiments described above, the estimation device includes a fluctuation determination unit and an estimation result correction unit. The fluctuation determination unit determines whether to correct the estimation result of the cause of partial discharge based on the fluctuation of the partial discharge signal. The estimation result correction unit corrects the estimation result when it is determined that the estimation result is to be corrected. Thereby, the cause of partial discharge can be estimated with high accuracy.

[0042] The teacher data may include data of the time versus voltage magnitude of the voltage applied to the device T. At this time, the estimation model generation device 12 generates an estimation model that outputs data indicating the cause of partial discharge of the device when the partial discharge signal of the device and the data of the time versus voltage magnitude of the voltage are input. Further, the estimation device 21 acquires the data of the time versus voltage magnitude of the voltage applied to the device E to be estimated in addition to the latest partial discharge signal, and outputs an estimation result of the cause of partial discharge.

[0043] Part or all of the teacher data generation device 11, the estimation model generation device 12, and the estimation device 21 in the above-described embodiments may be implemented by a computer. In that case, a program for realizing this function may be recorded on a computer-readable recording medium, and the program recorded on this recording medium may be read into a computer system and executed to be realized. Note that the "computer system" as used herein includes an OS and the hardware of peripheral devices. Further, the "computer-readable recording medium" refers to a portable medium such as a flexible disk, a magneto-optical disk, a ROM, a CD-ROM, or the like, or a recording device such as a hard disk incorporated in a computer system. Furthermore, the "computer-readable recording medium" refers to a medium that dynamically holds a program for a short time, such as a communication line when transmitting a program via a network such as the Internet or a communication line such as a telephone line, and includes a volatile memory inside a computer system that becomes a server or a client in that case and holds a program for a certain period of time. Also, the above program may be for realizing a part of the above-described functions, and may further be realized in combination with a program already recorded in a computer system for realizing the above-described functions. Also, part or all of the teacher data generation device 11, the estimation model generation device 12, and the estimation device 21 may be realized using a programmable logic device such as an FPGA (Field Programmable Gate Array).

[0044] Although some embodiments of the present invention have been described, these embodiments are presented by way of example and are not intended to limit the scope of the invention. These embodiments can be implemented in various other forms, and various omissions, replacements, and changes can be made without departing from the gist of the invention. These embodiments and their modifications are included in the scope and gist of the invention, and are also included in the invention described in the claims and the equivalent scope thereof.

Explanation of Signs

[0045] 1 Presumed model generation system, 10 Partial discharge sensor, 11 Teacher data generation device, 111 Data acquisition unit, 112 Storage unit, 113 Teacher data output unit, 12 Presumed model generation device, 121 Teacher data acquisition unit, 122 Presumed model generation unit, 123 Presumed model output unit, 124 Correction rule generation unit, 2 Presumption system, 21 Presumption device, 211 Measurement data acquisition unit, 212 Presumption unit, 213 Fluctuation determination unit, 214 Presumed result correction unit, 215 Output unit, 216 Signal extraction unit, 219 Storage unit

Claims

1. A fluctuation determination unit that determines whether to correct an estimation result of a cause of partial discharge that generates the partial discharge signal based on fluctuations in the partial discharge signal measured in the device; An estimation result correction unit that corrects the estimation result when it is determined that the estimation result is to be corrected; An estimation device comprising:

2. A measurement data acquisition unit that acquires a partial discharge signal measured in the device; An estimation unit that estimates the cause of partial discharge based on the partial discharge signal acquired by the measurement data acquisition unit; Comprising: The estimation unit determines whether to correct the estimation result by the estimation unit based on a partial discharge signal measured for a time longer than the measurement time of the partial discharge signal used by the estimation unit for estimation. The estimation device according to claim 1.

3. The fluctuation determination unit determines whether to correct the estimation result based on a feature amount of the fluctuation of the partial discharge signal. The estimation device according to claim 1 or 2.

4. The feature amount is information including at least one of changes in discharge intensity, discharge phase, and number of discharges. The estimation device according to claim 3.

5. When the fluctuation of the partial discharge signal is larger than a predetermined fluctuation, the fluctuation determination unit determines to correct the estimation result of the cause of partial discharge. When it is determined that the estimation result of the cause of partial discharge is to be corrected, the estimation result correction unit sets the probability that the cause of partial discharge is a metal foreign object to a value smaller than the probability of other causes. The estimation device according to claim 4.

6. When the rate of change of the intensity of the partial discharge signal with respect to time is equal to or greater than a predetermined value, the fluctuation determination unit determines to correct the estimation result of the cause of partial discharge. When it is determined that the estimation result of the cause of partial discharge is to be corrected, the estimation result correction unit reduces the probability that the cause of partial discharge is a metal foreign object. The estimation device according to claim 5.

7. The correction rule is generated based on teacher data in which a partial discharge signal and the cause of partial discharge are associated. The estimation device according to claim 1.

8. Further comprising a signal extraction unit that extracts past partial discharge signals based on the feature amount of the latest partial discharge signal. The fluctuation determination unit determines whether to correct the estimation result of the estimated cause of partial discharge based on the fluctuation of the extracted partial discharge signal. The estimation device according to claim 1.

9. The signal extraction unit extracts past partial discharge signals by clustering. The estimation device according to claim 8.

10. A variation determination step of determining whether to correct an estimation result of the cause of partial discharge based on the variation of the partial discharge signal; An estimation result correction step of correcting the estimation result when it is determined to correct the estimation result; An estimation method having the above.

11. A program for causing a computer to execute the estimation method according to Claim 10.

Images