Hydro-generator ultrahigh frequency partial discharge fault online intelligent diagnosis method and device

Abstract

The invention provides a hydro-generator ultrahigh frequency partial discharge fault online intelligent diagnosis method and device, and belongs to the technical field of partial discharge monitoring. The method comprises the following steps: acquiring a monitoring signal acquired by a coupling device in a current monitoring period; if an interference signal library starting condition is met, inputting an amplitude sequence obtained after discretization of the monitoring signal into a pre-constructed machine learning model, and generating a diagnosis result indicating whether the hydro-generator works normally, when it is diagnosed that the working state of the water turbine generator is abnormal and it is determined that the monitoring signal is not an interference signal by using the constructed interference signal library, skipping to the next step, otherwise, accumulating the types of the interference signals in the interference signal library, and skipping to the next step; if the amplitude of the monitoring signal collected in the current monitoring period is greater than an amplitude threshold value and the number of monitoring periods with the amplitude of the corresponding monitoring signal greater than the amplitude threshold value is continuously accumulated to reach a period accumulation threshold value, skipping to the next step; a partial discharge event is identified.

Description

Technical Field

[0001] The present application belongs to the technical field of partial discharge monitoring, and specifically relates to an online intelligent diagnosis method for ultra-high frequency partial discharge faults of a hydro-turbine generator, an online intelligent diagnosis device for ultra-high frequency partial discharge faults of a hydro-turbine generator, a machine-readable storage medium, and a computer device. Background Art

[0002] As the core equipment of hydropower stations, the health of the insulation system of hydroelectric generators is directly related to the safety and stability of the entire power system. In actual production, the detection of partial discharge (PD) signals is an important means to reflect the insulation status of large-scale power equipment. With the continuous expansion of hydropower installed capacity, higher requirements are put forward for the monitoring and evaluation of the insulation status of hydroelectric generators. In recent years, compared with low-frequency (100kHz~500kHz) PD monitoring technology, ultra-high frequency (300MHz~3GHz) PD monitoring technology has been gradually adopted due to its following advantages: 1) It has higher sensitivity and can effectively capture early PD signals and detect insulation defects in advance; 2) It can filter out more low-frequency interference, so it has stronger anti-interference ability and can detect PD signals more accurately in complex electromagnetic environments; 3) It can provide higher fault location accuracy; 4) The ultra-high frequency PD antenna is used as a coupling device to collect PD signals. This non-contact signal collection method ensures online PD monitoring under normal operation of hydroelectric generators. Therefore, ultra-high frequency PD monitoring technology provides data support for online preventive maintenance of hydroelectric generators. However, the complex operating conditions of hydro-turbine generators result in a lot of interference in the partial discharge data collected using ultra-high frequency partial discharge monitoring technology, making it difficult to quantitatively analyze the partial discharge data through thresholds. At present, partial discharge identification mainly relies on the qualitative analysis method of single-machine trend comparison. However, single-machine trend comparison has high requirements on the professional skills of on-site technicians, has low identification efficiency, and is affected by subjective factors.

[0003] In summary, how to effectively utilize the partial discharge data collected by ultra-high frequency partial discharge monitoring technology to achieve accurate online diagnosis of partial discharge faults is still a technical difficulty that needs to be overcome in this technical field. Summary of the invention

[0004] In view of this, the purpose of the embodiments of the present application is to provide an online intelligent diagnosis method for ultra-high frequency partial discharge faults of a hydro-turbine generator, an online intelligent diagnosis device for ultra-high frequency partial discharge faults of a hydro-turbine generator, a machine-readable storage medium and a computer device, so as to effectively utilize the partial discharge data collected using ultra-high frequency partial discharge monitoring technology, so as to accurately diagnose partial discharge faults online.

[0005] To achieve the above-mentioned purpose, the first aspect of the present application provides an online intelligent diagnosis method for ultra-high frequency partial discharge fault of a hydro-generator, comprising: Obtaining the monitoring signal collected by the ultra-high frequency partial discharge coupling device during the current monitoring period; If the activation condition of the interference signal library is met, the amplitude sequence obtained after discretizing the monitoring signal is input into the pre-built machine learning model to generate a diagnosis result of whether the hydro-generator is working normally, and when it is diagnosed that the working state of the hydro-generator is abnormal and the built interference signal library is used to determine that the monitoring signal is not an interference signal, jump to trigger the next step, otherwise accumulate the interference signal types in the interference signal library, and jump to trigger the next step; Determine whether the amplitude of the monitoring signal collected in the current monitoring cycle is greater than the amplitude threshold. If so, and when the number of monitoring cycles in which the amplitude of the corresponding monitoring signal is greater than the amplitude threshold continuously accumulates to reach the cycle accumulation threshold, jump to trigger the next step. Otherwise, enter the next monitoring cycle and jump to trigger the execution of obtaining the monitoring signal collected by the ultra-high frequency partial discharge coupling device in the current monitoring cycle; Identify the partial discharge event to which the monitoring signal collected in the current monitoring period belongs.

[0006] In a specific embodiment of the present application, identifying the partial discharge event to which the monitoring signal collected in the current monitoring period belongs includes: The characteristic parameters of the monitoring signal collected in the current monitoring period are extracted, and the partial discharge events corresponding to the extracted characteristic parameters of the monitoring signal are matched from the constructed partial discharge case library, wherein each partial discharge event in the partial discharge case library has its own corresponding characteristic parameters.

[0007] In a specific embodiment of the present application, the interference signal library activation condition includes one of the number of interference signal types in the interference signal library reaching a first preset value and the cumulative number of monitoring cycles executed reaching a second preset value.

[0008] In a specific embodiment of the present application, based on a first matching process, the monitoring signal is determined to be not an interference signal using a constructed interference signal library, and the first matching process includes: Extracting a first feature of the monitoring signal, wherein the first feature at least includes an energy feature; Determine whether the difference between the first statistical value and the first feature of the extracted monitoring signal is within a preset range; if not, determine that the monitoring signal is not an interference signal, wherein the first statistical value is a statistical value of the first feature of each interference signal in the constructed interference signal library, and the type of the first statistical value includes at least one of the average value of the first features of all types of interference signals in the interference signal library, the maximum value of the first features of all types of interference signals in the interference signal library, and the minimum value of the first features of all types of interference signals in the interference signal library.

[0009] In a specific embodiment of the present application, the energy characteristic is power spectral density.

[0010] In a specific embodiment of the present application, determining whether the amplitude of the monitoring signal collected in the current monitoring period is greater than the amplitude threshold includes: Learning the interference status of the production site where the ultra-high frequency partial discharge coupling device is located; Analyze the interference status to obtain the number of interference sources collected at the production site; If the number of interference sources is greater than the third preset value, an amplitude threshold is adaptively generated, and it is determined whether the amplitude of the monitoring signal collected in the current monitoring period is greater than the amplitude threshold; otherwise, a preset amplitude threshold based on expert experience is obtained, and it is determined whether the amplitude of the monitoring signal collected in the current monitoring period is greater than the amplitude threshold.

[0011] In a specific embodiment of the present application, extracting characteristic parameters of the monitoring signal collected in the current monitoring period includes: Discretizing the monitoring signal to obtain a pulse sequence; Removing pulses with amplitudes lower than the amplitude threshold in the pulse sequence to obtain a target pulse sequence, and using the target pulse sequence as a discretized monitoring signal; Extract the characteristic parameters of the discretized monitoring signal.

[0012] In a specific embodiment of the present application, the characteristic parameter includes at least one of phase, amplitude, waveform characteristics, amplitude statistical characteristics, and spectrum characteristics.

[0013] In a specific embodiment of the present application, the method further includes: Determine whether the amplitude of the monitoring signal meets the shutdown condition; if so, issue a control signal that the hydro-generator needs to shut down, and then jump to trigger execution. If the interference signal library activation condition is met, the amplitude sequence obtained after discretizing the monitoring signal is input into a pre-built machine learning model; otherwise, jump to trigger execution. If the interference signal library activation condition is met, the amplitude sequence obtained after discretizing the monitoring signal is input into a pre-built machine learning model; The shutdown condition at least includes that the amplitude of the monitoring signal is greater than the second statistical value, and the amplitude of the monitoring signal is greater than one of a plurality of maximum partial discharge amplitudes; Among them, the maximum partial discharge amplitude is the maximum value of the partial discharge amplitudes of the partial discharge events in the corresponding laboratory severe partial discharge case library that has been constructed, each partial discharge event in the laboratory severe partial discharge case library has its own corresponding maximum partial discharge amplitude, the second statistical value is the statistical value of each maximum partial discharge amplitude, the type of the second statistical value at least includes one of the maximum value of each maximum partial discharge amplitude and the average value of each maximum partial discharge amplitude, and the laboratory severe partial discharge case library at least includes partial discharge events that occur when the turbine generator operates under extreme conditions.

[0014] A second aspect of the present application provides an online intelligent diagnosis device for ultra-high frequency partial discharge faults of a hydro-turbine generator, comprising: An acquisition module is used to acquire the monitoring signal collected by the ultra-high frequency partial discharge coupling device in the current monitoring period; The first judgment module is used to judge whether the activation condition of the interference signal library is met. If so, the amplitude sequence obtained after discretizing the monitoring signal is input into the pre-built machine learning model to generate a diagnosis result of whether the hydro-generator is working normally. When it is diagnosed that the working state of the hydro-generator is abnormal and the built interference signal library is used to determine that the monitoring signal is not an interference signal, jump to trigger the execution of judging whether the amplitude of the monitoring signal collected in the current monitoring period is greater than the amplitude threshold, otherwise, the interference signal types in the interference signal library are accumulated, and jump to trigger the execution of judging whether the amplitude of the monitoring signal collected in the current monitoring period is greater than the amplitude threshold; The second judgment module is used to judge whether the amplitude of the monitoring signal collected in the current monitoring period is greater than the amplitude threshold. If so, and when the number of monitoring periods in which the amplitude of the corresponding monitoring signal is greater than the amplitude threshold continuously accumulates to reach the period accumulation threshold, jump to trigger the execution of identifying the partial discharge event to which the monitoring signal collected in the current monitoring period belongs, otherwise enter the next monitoring period and jump to trigger the execution of obtaining the monitoring signal collected by the ultra-high frequency partial discharge coupling device in the current monitoring period; The identification module is used to identify the partial discharge event to which the monitoring signal collected in the current monitoring period belongs.

[0015] A third aspect of the present application provides a computer device, comprising: a memory configured to store instructions; and The processor is configured to call the instructions from the memory and implement the online intelligent diagnosis method for ultra-high frequency partial discharge fault of the hydro-turbine generator according to the first aspect of the present application when executing the instructions.

[0016] The fourth aspect of the present application provides a machine-readable storage medium having instructions stored thereon, the instructions being used to enable a machine to execute the online intelligent diagnosis method for ultra-high frequency partial discharge faults of a hydro-turbine generator according to the first aspect of the present application.

[0017] The above technical solution realizes fast and accurate identification of partial discharge signals by combining machine learning models, interference signal libraries, amplitude thresholds, and utilizing the periodic recurrence characteristics of partial discharge signals, thereby realizing fast and accurate online diagnosis of partial discharge faults.

[0018] Other features and advantages of the embodiments of the present application will be described in detail in the subsequent specific implementation section. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The accompanying drawings are used to provide a further understanding of the embodiments of the present application and constitute a part of the specification. Together with the following specific implementations, they are used to explain the embodiments of the present application, but do not constitute a limitation on the embodiments of the present application. In the accompanying drawings: Figure 1 A flow chart schematically shows a method for online intelligent diagnosis of ultra-high frequency partial discharge faults of a hydro-turbine generator according to an embodiment of the present application; Figure 2 Another flow chart of the online intelligent diagnosis method for ultra-high frequency partial discharge fault of a hydro-turbine generator according to an embodiment of the present application is schematically shown; Figure 3 A block diagram schematically shows a composition of an online intelligent diagnostic device for ultra-high frequency partial discharge fault of a hydro-turbine generator according to an embodiment of the present application; Figure 4 The structural block diagram of a computer device according to an embodiment of the present application is schematically shown. DETAILED DESCRIPTION

[0020] The specific implementation of the embodiment of the present application is described in detail below in conjunction with the accompanying drawings. It should be understood that the specific implementation described here is only used to illustrate and explain the embodiment of the present application, and is not used to limit the embodiment of the present application.

[0021] If there are descriptions involving "first", "second", etc. in the embodiments of the present application, the descriptions of "first", "second", etc. are only used for descriptive purposes and cannot be understood as indicating or suggesting their relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In addition, the technical solutions between the various embodiments can be combined with each other, but they must be based on the ability of ordinary technicians in the field to implement them. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such a combination of technical solutions does not exist and is not within the scope of protection required by this application.

[0022] Ultra-high frequency partial discharge monitoring technology can provide data support for online preventive maintenance of hydro-turbine generators. However, the difficulty in its application lies in how to use ultra-high frequency partial discharge data to accurately identify partial discharge signals and judge partial discharge events.

[0023] In order to apply the ultra-high frequency partial discharge monitoring technology to perform online diagnosis of partial discharge faults of hydro-turbine generators, the embodiment of the present application proposes an online intelligent diagnosis method for ultra-high frequency partial discharge faults of hydro-turbine generators, and the method includes: Obtaining the monitoring signal collected by the ultra-high frequency partial discharge coupling device during the current monitoring period; If the activation condition of the interference signal library is met, the amplitude sequence obtained after discretizing the monitoring signal is input into the pre-built machine learning model to generate a diagnosis result of whether the hydro-generator is working normally, and when it is diagnosed that the working state of the hydro-generator is abnormal and the built interference signal library is used to determine that the monitoring signal is not an interference signal, jump to trigger the next step, otherwise the interference signal type in the interference signal library is accumulated, and jump to trigger the next step; Determine whether the amplitude of the monitoring signal collected in the current monitoring cycle is greater than the amplitude threshold. If so, and when the number of monitoring cycles in which the amplitude of the corresponding monitoring signal is greater than the amplitude threshold continuously accumulates to reach the cycle accumulation threshold, jump to trigger the next step. Otherwise, enter the next monitoring cycle and jump to trigger the execution of obtaining the monitoring signal collected by the ultra-high frequency partial discharge coupling device in the current monitoring building; Identify the partial discharge event to which the monitoring signal collected in the current monitoring period belongs.

[0024] In the present application, discretizing the monitoring signal to obtain an amplitude sequence specifically refers to: discretizing the monitoring signal to obtain a pulse sequence, wherein the amplitude of each pulse in the pulse sequence constitutes the amplitude sequence.

[0025] As in the above embodiment, when the activation condition of the interference signal library is not reached, while accumulating the interference signal types in the interference signal library, based on the characteristic of the periodic repetition of the partial discharge signal, it is judged whether the monitoring signals collected in multiple consecutive monitoring cycles are all greater than the amplitude threshold value, so as to determine whether the monitoring signal is a partial discharge signal. When the activation condition of the interference signal library is reached, the machine learning model is used to diagnose whether the hydro-generator is working normally in the current monitoring cycle, and when the abnormal working state of the hydro-generator is diagnosed, the interference signal library is used to judge whether the monitoring signal is a partial discharge signal or an interference signal. When it is identified that the monitoring signal collected in the current monitoring cycle is not an interference signal, the characteristic of the periodic repetition of the partial discharge signal and the amplitude threshold value are further used to judge whether the monitoring signal is a partial discharge signal, and finally the identification of the partial discharge signal is realized, and then the partial discharge fault is judged. It can be seen that the embodiment of the present application combines the machine learning model, the interference signal library, the amplitude threshold value and the characteristic of the periodic repetition of the partial discharge signal to realize the rapid and accurate identification of different diagnosis periods of partial discharge faults.

[0026] It should be understood that the ultra-high frequency partial discharge fault diagnosis in different diagnosis periods specifically refers to: because the types of interference signals in the interference signal library need to be gradually accumulated, in the early stage of ultra-high frequency partial discharge fault diagnosis, it is difficult to distinguish between partial discharge signals and interference signals through the interference signal library after the machine learning model is used to determine that the working state of the turbine generator is abnormal, so the amplitude threshold and the periodic repetition of the partial discharge signal are combined to realize the partial discharge signal identification; after the types of interference signals in the interference signal library are accumulated to a certain extent, the interference signal library is enabled. At this time, the machine learning model and the interference signal library are used to preliminarily identify whether the monitoring signal is a partial discharge signal, because the monitoring signal still has interference such as periodic pulse interference after preprocessing, that is, when the machine learning model is used to diagnose that the working state of the turbine generator in the current monitoring period is abnormal, the monitoring signal collected in the current monitoring period can be the power frequency cycle carrying the interference signal, the power frequency cycle that is interfered and carries the partial discharge pulse, and the power frequency cycle that is not interfered and carries the partial discharge pulse, and then the amplitude threshold and the periodic repetition of the partial discharge signal are combined to finally identify whether the monitoring signal is a partial discharge signal.

[0027] Figure 1 The flowchart of the method for online intelligent diagnosis of ultra-high frequency partial discharge fault of a hydro-turbine generator according to an embodiment of the present application is schematically shown. Figure 1 As shown, the hydro-generator ultra-high frequency partial discharge fault online intelligent diagnosis method may include the following steps 102 to 110. It can be understood that the above hydro-generator ultra-high frequency partial discharge fault online intelligent diagnosis method may include all steps from step 102 to step 110, or may only include some of the steps.

[0028] Step 102, obtaining the monitoring signal collected by the ultra-high frequency partial discharge coupling device in the current monitoring period.

[0029] Specifically, in the present application, the UHF partial discharge coupling device may be an UHF partial discharge sensor, an UHF partial discharge antenna, or a coupler composed of a transformer and a coupling capacitor.

[0030] Step 104, executing a first judgment process, the first judgment process is specifically: Determine whether the conditions for enabling the interference signal library are met; if so, preprocess and discretize the collected monitoring signals to obtain an amplitude sequence, input the amplitude sequence into a pre-built machine learning model, generate a diagnostic result of whether the hydro-generator is working properly, and jump to trigger the execution of step 106, otherwise accumulate the interference signal types in the interference signal library, and jump to trigger the execution of step 108.

[0031] Specifically, in the present application, in the early stage of online diagnosis of partial discharge faults, because the interference signal is highly random and accidental, there are fewer types of interference signals in the interference signal library. When there are fewer types of interference signals, the partial discharge signal identification using the combination of the machine learning model and the interference signal library is ineffective, that is, the credibility of the distinction between the partial discharge signal and the interference signal is not high at this time. Therefore, it is first determined whether the conditions for enabling the interference signal library are met. The conditions for enabling the interference signal library described in step 104 can be set specifically according to specific needs.

[0032] As an example, the interference signal library activation condition includes one of the number of interference signal types in the interference signal library reaching a first preset value and the cumulative number of monitoring cycles executed reaching a second preset value.

[0033] As an example, the following process can be used to accumulate interference signal types in the interference signal library: discretize the monitoring signals collected during the monitoring period, input the amplitude sequence obtained after discretization into the machine learning model, and when the diagnosis result generated by the machine learning model indicates that the working state of the hydro-generator is abnormal, judge whether the monitoring signal is an interference signal based on the energy characteristics of the extracted monitoring signal; if this type of interference signal is not matched in the interference signal library of the current state, manually mark and classify this type of interference signal, thereby achieving the accumulation of interference signal types.

[0034] Under the operating conditions of the hydro-generator, the types of interference signals in the interference signal library may include corona discharge generated from the outside of the hydro-generator, electromagnetic interference, pulse interference, interference signals caused by poor grounding during monitoring signal acquisition, electronic noise of the acquisition equipment itself during monitoring signal acquisition, environmental noise, false signals generated by the acquisition equipment caused by temperature changes during monitoring signal acquisition, false discharge signals caused by humidity changes, signal transmission interference and human interference, etc. The sources of these interference signals are shown in Table 1 below.

[0035] Table 1

[0036] As an example, the machine learning model can be obtained by training and optimizing hyperparameters of an initial classification network. The classification network can be a RBF network, an extreme learning machine, a random forest, etc.

[0037] As an example, the preprocessing may include bandpass filtering, normalization processing, etc.

[0038] For example, the normalization process is performed as follows: ; in, x(t) represents the monitoring signal after bandpass filtering, max(|x(t)|)is the signal x(t) The maximum absolute amplitude of the normalized signal x b (t) The range is [-1,1].

[0039] Step 106, executing the second judgment process, the second judgment process is specifically: When the diagnosis result generated by the machine learning model indicates that the working state of the hydro-generator is abnormal, the constructed interference signal library is used to determine whether the monitoring signal collected in the current monitoring period is an interference signal; if so, the partial discharge fault diagnosis of the current monitoring period is ended and enters the next monitoring period, otherwise jump to trigger the execution of step 108.

[0040] As an optional embodiment of the present application, based on the first matching process, the built interference signal library is used to determine that the monitoring signal collected in the current monitoring period is not an interference signal. The first matching process specifically refers to: Extracting a first feature of a monitoring signal collected during a current monitoring period; It is determined whether the difference between the first statistical value and the first feature of the extracted monitoring signal is within a preset range; if not, it is determined that the monitoring signal collected in the current monitoring period is not an interference signal.

[0041] Specifically, in the present application, the first feature at least includes an energy feature. For example, the energy feature is a power spectrum density, and the energy feature is used to distinguish between the partial discharge signal and the interference signal, which utilizes the principle that the energy density of the partial discharge signal and the interference signal is quite different. The first statistical value is the statistical value of the first feature corresponding to each interference signal in the constructed interference signal library, and the type of the first statistical value includes at least one of the average value of the first feature of all types of interference signals in the interference signal library, the maximum value of the first feature of all types of interference signals in the interference signal library, and the minimum value of the first feature of all types of interference signals in the interference signal library. For example, as an example, the first statistical value is the maximum value of the first feature corresponding to each interference signal in the constructed interference signal library.

[0042] Step 108, executing the third judgment process, the third judgment process is specifically: Determine whether the amplitude of the monitoring signal collected in the current monitoring period is greater than the amplitude threshold; if the amplitude of the monitoring signal collected in the current monitoring period is greater than the amplitude threshold, and the number of monitoring periods in which the amplitude of the corresponding monitoring signal is greater than the amplitude threshold continuously accumulates to reach the period accumulation threshold, jump to trigger the execution of step 110, otherwise enter the next monitoring period and jump to trigger the execution of step 102.

[0043] In a preferred embodiment of the present application, the amplitude threshold can be a preset fixed amplitude threshold or an adaptive amplitude threshold. The selection of the preset fixed amplitude threshold and the adaptive amplitude threshold can be determined in combination with the number of interference sources under the specific operating conditions of the hydro-generator. When the number of interference sources is relatively single, the preset fixed amplitude threshold is selected. In the context of complex interference sources, the adaptive amplitude threshold is selected.

[0044] For example, as an example, judging whether the amplitude of the monitoring signal collected in the current monitoring period is greater than the amplitude threshold value specifically includes the following steps: Learn about the interference status of the production site where the UHF PD coupling device is located; Analyze the interference status to determine the number of interference sources collected at the production site; If the number of interference sources collected at the production site is greater than the third preset value, the amplitude threshold is adaptively generated, otherwise the preset amplitude threshold based on expert experience is learned; Determine whether the amplitude of the monitoring signal collected in the current monitoring period is greater than the amplitude threshold.

[0045] In the above embodiments of the present application, the amplitude threshold based on expert experience refers to the empirical amplitude threshold, which improves the accuracy of partial discharge signal identification by determining whether to use a preset fixed amplitude threshold or an adaptively generated amplitude threshold according to the interference source status at the production site.

[0046] As an example, the amplitude threshold may be adaptively generated using an unsupervised clustering method.

[0047] As another example, the Ostu threshold method can be used to adaptively generate the amplitude threshold. The specific process is as follows: Discretize the monitoring signal collected in the current monitoring period to obtain a pulse sequence; The amplitude threshold that maximizes the inter-class variance is obtained. The amplitude threshold divides the amplitudes of the pulses in the pulse sequence as described above into two categories, that is, into two classes. The inter-class variance is the inter-class variance of the two classes.

[0048] Step 110, identifying the partial discharge event to which the monitoring signal collected in the current monitoring period belongs.

[0049] It should be understood that the monitoring signals collected by the UHF PD coupling device under different PD events are different, and the PD event to which the monitoring signal belongs specifically refers to the PD event in which the monitoring signal is generated.

[0050] As an optional embodiment of the present application, the constructed partial discharge case library can be used to identify the partial discharge event to which the monitoring signal belongs. Accordingly, step 110 includes the following sub-steps: The characteristic parameters of the monitoring signal collected in the current monitoring period are extracted, and the partial discharge events corresponding to the extracted characteristic parameters of the monitoring signal are matched from the constructed partial discharge case library, wherein each partial discharge event in the partial discharge case library has its own corresponding characteristic parameters.

[0051] Specifically, the partial discharge signals corresponding to different types of partial discharge events are differentiated in the time domain and / or frequency domain, specifically, the amplitude, frequency and waveform of the partial discharge signal change with the change of the partial discharge position and the partial discharge intensity. Therefore, as mentioned above, the characteristic parameters refer to these characteristics that can reflect the differences in the partial discharge signal in the time domain or frequency domain. The above embodiment does not limit the specific time domain characteristics and / or frequency domain characteristics used, and the feasible time domain characteristics and / or frequency domain characteristics need to be determined in combination with the specific type of turbine generator unit in the hydropower station.

[0052] For example, characteristic parameters include time domain characteristics such as phase, amplitude, waveform characteristics, and amplitude statistical characteristics, wherein waveform characteristics include one or more of rise time, fall time, duration, and pulse width. Amplitude statistical characteristics include one or more of amplitude mean value and amplitude standard deviation. Characteristic parameters may also include frequency domain characteristics such as spectrum characteristics, which refer to the intensity and frequency distribution of different frequency components in the spectrum.

[0053] As an improved embodiment of the present application, the interference data points are removed by using the amplitude threshold. Accordingly, the characteristic parameters of the monitoring signal collected in the current monitoring period are extracted in the following manner: Discretize the monitoring signal to obtain a pulse sequence; The pulses with amplitudes lower than the amplitude threshold in the pulse sequence are removed to obtain a target pulse sequence, and the target pulse sequence is used as a discretized monitoring signal; Extract the characteristic parameters of the discretized monitoring signal.

[0054] In the above improved embodiment, interference data points are removed by using an amplitude threshold, thereby improving the extraction efficiency and accuracy of feature parameters.

[0055] It should be understood that the types of interference signals in the partial discharge case library are gradually improved. When the current partial discharge case library cannot classify the monitoring signal, it is necessary to classify the monitoring signal through manual analysis, and add the new partial discharge event obtained by classification to the partial discharge case library. When the new partial discharge event type is determined by manual analysis, the result can be carried out in an offline partial discharge test mode. For example, a partial discharge test is carried out at each ultra-high frequency partial discharge coupling device layout location of the stator winding through an offline test mode, and the partial discharge signals collected at each layout location are collected and the characteristic parameters of these partial discharge signals are extracted. The partial discharge event type of the monitoring signal to be classified is determined by matching and analyzing the extracted characteristic parameters with the characteristic parameters of the monitoring signal to be classified. Preferably, before extracting the characteristic parameters of these partial discharge signals, the partial discharge signals collected at each layout location are corrected using the maximum attenuation coefficient, and the maximum attenuation coefficient can be determined through the process in the ordinary embodiment.

[0056] For example, a test partial discharge signal is injected into each preset injection point of the stator winding bar of a hydro-turbine generator, and then the partial discharge signal is collected at the location of the ultra-high frequency partial discharge coupling device. The transfer function and attenuation coefficient of the stator winding bar are then determined by a network vector analyzer, thereby determining the maximum attenuation coefficient. After the partial discharge signals collected at each location are reconstructed through the transfer function, the reconstructed partial discharge signal is multiplied by the maximum attenuation coefficient to complete the correction of the partial discharge signal.

[0057] As an improved embodiment of the present application, Figure 2 Another flow chart of the online intelligent diagnosis method for ultra-high frequency partial discharge fault of a hydro-turbine generator according to an embodiment of the present application is schematically shown. Figure 2 As shown, the improved embodiment is Figure 1 The difference between the illustrated embodiment is that before step 104 , step 103 is further included.

[0058] Step 103, performing shutdown diagnosis, the shutdown diagnosis is specifically: Determine whether the amplitude of the monitoring signal collected in the current monitoring period meets the shutdown condition; if so, send a control signal that the turbine generator needs to shut down, and then jump to trigger the execution of step 104, otherwise jump directly to trigger the execution of step 104.

[0059] In the present application, the shutdown conditions include at least that the amplitude of the monitoring signal is greater than the second statistical value, and the amplitude of the monitoring signal is greater than one of multiple maximum partial discharge amplitudes, wherein the maximum partial discharge amplitude is the maximum value of the partial discharge amplitudes of the partial discharge events in the corresponding laboratory severe partial discharge case library, and each partial discharge event in the laboratory severe partial discharge case library has its own corresponding maximum partial discharge amplitude. The second statistical value is the statistical value of each maximum partial discharge amplitude, and the type of the second statistical value includes at least one of the maximum value of each maximum partial discharge amplitude and the average value of each maximum partial discharge amplitude. The laboratory severe partial discharge case library includes at least partial discharge events that occur when the turbine generator operates under extreme conditions.

[0060] In some comparative embodiments, when a partial discharge event is determined to have occurred in the current monitoring cycle through single-machine trend comparison, a control signal cannot be given to indicate whether the turbine generator needs to be shut down. In the above embodiment of the present application, by pre-building a laboratory severe partial discharge case library, the amplitude of the monitoring signal collected in the current monitoring cycle is matched with the laboratory severe partial discharge case library to determine whether the shutdown conditions are met. When the shutdown conditions are met, a control signal indicating that the turbine generator needs to be shut down is generated, thereby avoiding insulation deterioration, equipment damage, and even system collapse caused by the continued operation of the turbine generator and the failure to promptly handle the partial discharge problem, thereby avoiding production interruptions and economic losses caused by the above problems.

[0061] As an example, when using the constructed partial discharge case library to identify the partial discharge event to which the monitoring signal belongs, the partial discharge case library may include all partial discharge events in the above-mentioned laboratory severe partial discharge case library and other common partial discharge events, etc. Common partial discharge events refer to partial discharge events when the hydro-turbine generator is in normal operating conditions.

[0062] As an example, one type of partial discharge event in the laboratory severe partial discharge case library is a partial discharge case under extreme humidity conditions, specifically referring to: simulating partial discharge in a high humidity environment, because moisture can significantly change the performance of insulating materials and increase the probability of partial discharge. Through the partial discharge simulation under such conditions, the maximum partial discharge amplitude of the partial discharge event under such conditions is obtained. Another typical partial discharge event in the laboratory severe partial discharge case library is a partial discharge case under high temperature environment, specifically referring to: simulating partial discharge under conditions higher than the normal operating temperature, because high temperature may cause accelerated aging of insulating materials, thereby causing partial discharge. Through the partial discharge simulation under such conditions, the maximum partial discharge amplitude of the partial discharge event under such conditions is obtained. Another type of partial discharge event in the laboratory severe partial discharge case library is a partial discharge case under strong electromagnetic interference environment, specifically referring to: simulating partial discharge in an environment with strong electromagnetic interference. In specific applications, the complex electromagnetic interference environment in the actual power system is simulated to obtain the maximum partial discharge amplitude of the partial discharge event under such conditions. Another type of partial discharge event in the laboratory severe partial discharge case library is the partial discharge case after the aging of the insulation material. Specifically, it means: using the aged insulation material or accelerated aging experiment to simulate the long-term operation effect of the turbine generator, investigating the influence of insulation aging on the partial discharge, and obtaining the maximum partial discharge amplitude of the partial discharge event under this condition. Another type of partial discharge event in the laboratory severe partial discharge case library is the partial discharge case caused by the turbine generator under mechanical stress. Specifically, it means: during the partial discharge test of the turbine generator, mechanical vibration or shock is applied to the turbine generator. Because mechanical stress or shock may cause damage to the insulation structure, partial discharge is generated. By investigating the partial discharge caused by such insulation structure damage, the maximum partial discharge amplitude of the partial discharge event under this condition is obtained. Another type of partial discharge event in the laboratory severe partial discharge case library is the partial discharge case caused by different types of insulation defects. Specifically, it means: constructing insulation defect models with different types and sizes, such as bubbles, cracks, impurities, etc., investigating the influence of these different insulation defects on partial discharge, and obtaining the maximum partial discharge amplitude of the partial discharge event under this condition. Another type of partial discharge event in the laboratory severe partial discharge case library is the partial discharge case of the turbine generator under extreme operating conditions, which specifically refers to: simulating the extreme operating conditions of the turbine generator, such as rapid voltage increase, rapid voltage reduction and overload, etc., because these extreme operating conditions may lead to aggravation of the partial discharge phenomenon, and through the partial discharge simulation under these extreme operating conditions, the maximum partial discharge amplitude of the partial discharge event under such conditions is obtained. Another type of partial discharge event in the laboratory severe partial discharge case library is the partial discharge case under compound fault conditions, which specifically refers to: conducting partial discharge simulation tests on the turbine generator under multiple extreme conditions at the same time, such as the simultaneous existence of high temperature, high humidity and mechanical stress, and investigating the comprehensive impact of compound fault conditions on partial discharge, and obtaining the maximum partial discharge amplitude of the partial discharge event under such conditions. The following Table 2 shows the types of partial discharge events in the laboratory severe partial discharge case library constructed in a specific application example.

[0063] Table 2

[0064] It is known that in actual production, the amount of signal data collected by the ultra-high frequency partial discharge online monitoring method is huge, and most of them are signals of the normal working state of the hydro-generator. Therefore, there is a lack of abundant partial discharge signal samples that can be used to train the classification network. Therefore, based on the training method in the ordinary embodiment, the model is prone to problems such as overfitting and poor generalization ability. Therefore, as an improvement of the above-mentioned embodiment of the present application, the present application proposes a method for constructing a machine learning model based on multi-stage training. Accordingly, after training the classification network and optimizing the hyperparameters, a machine learning model for signal diagnosis is obtained, which specifically includes the following steps: Step A1, using the first training set to perform the first stage training on the classification network to obtain the first diagnostic model, wherein the first training set is composed of an amplitude sequence obtained by discretizing the normal working state signal of the hydro-generator.

[0065] In this application, the samples used in the first stage of training can be called positive samples.

[0066] Step A2, using the second training set to perform the second stage training on the first diagnostic model to obtain the second diagnostic model, the second training set is composed of a specific amplitude sequence, and the historical monitoring signal corresponding to the specific amplitude sequence is an abnormal working state signal of the hydro-generator.

[0067] In this application, the samples used in the second stage of training can be called negative samples.

[0068] Step A3, performing a third stage of training on the second diagnostic model using a third training set, wherein the third training set consists of a target amplitude sequence, and the target amplitude sequence is a historical amplitude sequence that meets a preset condition.

[0069] Specifically, the preset condition described in the present application means that the diagnostic result obtained by inputting the second diagnostic model is that the working state of the hydro-generator is abnormal, and then the monitoring signal corresponding to the input amplitude sequence is manually determined to be the abnormal working state signal of the hydro-generator. The samples used in the third stage of training are samples obtained after being identified and manually marked by the second diagnostic model, and are also negative samples.

[0070] In the above improved embodiment, through multi-stage training, full use is made of positive samples and negative samples, and the third training set is an expanded negative sample obtained by identification and manual labeling by the second diagnostic model. The efficiency of sample expansion is higher than that of manually labeling negative samples directly in a large number of historical monitoring signals in the ordinary embodiment. Therefore, the construction efficiency of the machine learning model and the recognition accuracy of the constructed machine learning model are improved through multi-stage training.

[0071] In summary, the above improved embodiments improve the efficiency and accuracy of partial discharge identification.

[0072] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean 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 application.

[0073] Corresponding to the above-mentioned embodiment, the on-line intelligent diagnosis method for ultra-high frequency partial discharge fault of a hydro-turbine generator is: Figure 3 The block diagram schematically shows the composition of the ultra-high frequency partial discharge fault online intelligent diagnosis device 400 for a hydro-turbine generator provided in an embodiment of the present application. For the sake of convenience of explanation, only the parts related to the embodiment of the present application are shown.

[0074] like Figure 3 As shown, the hydro-generator ultra-high frequency partial discharge fault online intelligent diagnosis device 400 includes: An acquisition module 410 is used to acquire a monitoring signal collected by the ultra-high frequency partial discharge coupling device in a current monitoring period; The first judgment module 420 is used to judge whether the activation condition of the interference signal library is met. If so, the amplitude sequence obtained after discretizing the monitoring signal is input into the pre-built machine learning model to generate a diagnosis result of whether the hydro-generator is working normally. When it is diagnosed that the working state of the hydro-generator is abnormal and the monitoring signal is determined not to be an interference signal by using the built interference signal library, it jumps to trigger the execution of judging whether the amplitude of the monitoring signal collected in the current monitoring period is greater than the amplitude threshold, otherwise, the interference signal types in the interference signal library are accumulated, and the jump is triggered to judge whether the amplitude of the monitoring signal collected in the current monitoring period is greater than the amplitude threshold; The second judgment module 430 is used to judge whether the amplitude of the monitoring signal collected in the current monitoring period is greater than the amplitude threshold. If so, and when the number of monitoring periods in which the amplitude of the corresponding monitoring signal is greater than the amplitude threshold continuously accumulates to reach the period accumulation threshold, jump to trigger the execution of identifying the partial discharge event to which the monitoring signal collected in the current monitoring period belongs; otherwise, enter the next monitoring period and jump to trigger the execution of obtaining the monitoring signal collected by the ultra-high frequency partial discharge coupling device in the current monitoring period; The identification module 440 is used to identify the partial discharge event to which the monitoring signal collected in the current monitoring period belongs.

[0075] The process of each module in the ultra-high frequency partial discharge fault online intelligent diagnosis device 400 for the hydro-turbine generator provided in the embodiment of the present application realizing its respective function can be specifically referred to the aforementioned Figure 1 The description of the illustrated embodiment and other related method embodiments will not be repeated here.

[0076] It should be noted that the information interaction, execution process and other contents between the above modules are based on the same concept as the method embodiment of the present application. Their specific functions and technical effects can be found in the method embodiment part and will not be repeated here.

[0077] Figure 4 A schematic diagram of a computer device according to an embodiment of the present application is shown. In one embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as shown in FIG. Figure 4 As shown. The computer device includes a processor A01, a network interface A02, a display screen A04, an input device A05 and a memory (not shown in the figure) connected through a system bus. Among them, the processor A01 of the computer device is used to provide computing and control capabilities. The memory of the computer device includes an internal memory A03 and a non-volatile storage medium A06. The non-volatile storage medium A06 stores an operating system B01 and a computer program B02. The internal memory A03 provides an environment for the operation of the operating system B01 and the computer program B02 in the non-volatile storage medium A06. The network interface A02 of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor A01, an online intelligent diagnosis method for ultra-high frequency partial discharge faults of a hydro-turbine generator is implemented. The display screen A04 of the computer device can be a liquid crystal display screen or an electronic ink display screen, and the input device A05 of the computer device can be a touch layer covered on the display screen, or a key, trackball or touchpad set on the computer device housing, or an external keyboard, touchpad or mouse.

[0078] Those skilled in the art will understand that Figure 4 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0079] In one embodiment, the hydro-turbine generator ultra-high frequency partial discharge fault online intelligent diagnosis device 400 provided in the present application can be implemented in the form of a computer program. The computer program can be used in Figure 4 The computer device shown in the figure is run. The memory of the computer device can store various program modules constituting the online intelligent diagnosis device 400 for ultra-high frequency partial discharge fault of a hydro-turbine generator. The computer program composed of various program modules enables the processor to execute the steps of the online intelligent diagnosis method for ultra-high frequency partial discharge fault of a hydro-turbine generator in various embodiments of the present application described in this specification.

[0080] In one embodiment, the present application also provides a machine-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the online intelligent diagnosis method for ultra-high frequency partial discharge faults of hydro-turbine generators in the above-mentioned embodiment is implemented.

[0081] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0082] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0083] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0084] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. An online intelligent diagnosis method for ultra-high frequency partial discharge fault of a hydro-generator, characterized in that: include: Obtaining the monitoring signal collected by the ultra-high frequency partial discharge coupling device during the current monitoring period; If the activation condition of the interference signal library is met, the amplitude sequence obtained after discretizing the monitoring signal is input into the pre-built machine learning model to generate a diagnosis result of whether the hydro-generator is working normally, and when it is diagnosed that the working state of the hydro-generator is abnormal and the built interference signal library is used to determine that the monitoring signal is not an interference signal, jump to trigger the next step, otherwise accumulate the interference signal types in the interference signal library, and jump to trigger the next step; Determine whether the amplitude of the monitoring signal collected in the current monitoring cycle is greater than the amplitude threshold. If so, and when the number of monitoring cycles in which the amplitude of the corresponding monitoring signal is greater than the amplitude threshold continuously accumulates to reach the cycle accumulation threshold, jump to trigger the next step. Otherwise, enter the next monitoring cycle and jump to trigger the execution of obtaining the monitoring signal collected by the ultra-high frequency partial discharge coupling device in the current monitoring cycle; Identify the partial discharge event to which the monitoring signal collected in the current monitoring period belongs.

2. The method for online intelligent diagnosis of ultra-high frequency partial discharge fault of a hydro-generator according to claim 1 is characterized in that: Identify the partial discharge event to which the monitoring signal collected in the current monitoring period belongs, including: The characteristic parameters of the monitoring signal collected in the current monitoring period are extracted, and the partial discharge events corresponding to the extracted characteristic parameters of the monitoring signal are matched from the constructed partial discharge case library, wherein each partial discharge event in the partial discharge case library has its own corresponding characteristic parameters.

3. The method for online intelligent diagnosis of ultra-high frequency partial discharge fault of a hydro-generator according to claim 1 is characterized in that: The interference signal library activation condition includes one of: the number of types of interference signals in the interference signal library reaches a first preset value, and the cumulative number of monitoring cycles executed reaches a second preset value.

4. The method for online intelligent diagnosis of ultra-high frequency partial discharge fault of a hydro-generator according to claim 1 is characterized in that: Based on a first matching process, the monitoring signal is determined not to be an interference signal using the constructed interference signal library, the first matching process comprising: Extracting a first feature of the monitoring signal, wherein the first feature at least includes an energy feature; Determine whether the difference between the first statistical value and the first feature of the extracted monitoring signal is within a preset range; if not, determine that the monitoring signal is not an interference signal, wherein the first statistical value is a statistical value of the first feature of each interference signal in the constructed interference signal library, and the type of the first statistical value includes at least one of the average value of the first features of all types of interference signals in the interference signal library, the maximum value of the first features of all types of interference signals in the interference signal library, and the minimum value of the first features of all types of interference signals in the interference signal library.

5. The method for online intelligent diagnosis of ultra-high frequency partial discharge fault of a hydro-generator according to claim 4 is characterized in that: The energy characteristic is power spectral density.

6. The method for online intelligent diagnosis of ultra-high frequency partial discharge fault of a hydro-generator according to claim 1 is characterized in that: Determine whether the amplitude of the monitoring signal collected in the current monitoring period is greater than the amplitude threshold, including: Learning the interference status of the production site where the ultra-high frequency partial discharge coupling device is located; Analyze the interference status to obtain the number of interference sources collected at the production site; If the number of interference sources is greater than the third preset value, an amplitude threshold is adaptively generated, and it is determined whether the amplitude of the monitoring signal collected in the current monitoring period is greater than the amplitude threshold; otherwise, a preset amplitude threshold based on expert experience is obtained, and it is determined whether the amplitude of the monitoring signal collected in the current monitoring period is greater than the amplitude threshold.

7. The method for online intelligent diagnosis of ultra-high frequency partial discharge fault of a hydro-generator according to claim 2 is characterized in that: Extract characteristic parameters of the monitoring signal collected in the current monitoring period, including: Discretizing the monitoring signal to obtain a pulse sequence; Removing pulses with amplitudes lower than the amplitude threshold in the pulse sequence to obtain a target pulse sequence, and using the target pulse sequence as a discretized monitoring signal; Extract the characteristic parameters of the discretized monitoring signal.

8. The method for online intelligent diagnosis of ultra-high frequency partial discharge fault of a hydro-generator according to claim 2 or 7, characterized in that: The characteristic parameters include at least one of phase, amplitude, waveform characteristics, amplitude statistical characteristics, and spectrum characteristics.

9. The method for online intelligent diagnosis of ultra-high frequency partial discharge fault of a hydro-generator according to claim 1, characterized in that: Also includes: Determining whether the amplitude of the monitoring signal meets the shutdown condition; If so, a control signal indicating that the hydro-generator needs to be shut down is issued, and then the process jumps to trigger the execution of: if the interference signal library activation condition is met, the amplitude sequence obtained after discretizing the monitoring signal is input into the pre-built machine learning model; otherwise, the process jumps to trigger the execution of: if the interference signal library activation condition is met, the amplitude sequence obtained after discretizing the monitoring signal is input into the pre-built machine learning model; The shutdown condition at least includes that the amplitude of the monitoring signal is greater than the second statistical value, and the amplitude of the monitoring signal is greater than one of a plurality of maximum partial discharge amplitudes; Among them, the maximum partial discharge amplitude is the maximum value of the partial discharge amplitudes of the partial discharge events in the corresponding laboratory severe partial discharge case library that has been constructed, each partial discharge event in the laboratory severe partial discharge case library has its own corresponding maximum partial discharge amplitude, the second statistical value is the statistical value of each maximum partial discharge amplitude, the type of the second statistical value at least includes one of the maximum value of each maximum partial discharge amplitude and the average value of each maximum partial discharge amplitude, and the laboratory severe partial discharge case library at least includes partial discharge events that occur when the turbine generator operates under extreme conditions.

10. An online intelligent diagnostic device for ultra-high frequency partial discharge faults of a hydro-generator, characterized in that: include: An acquisition module is used to acquire the monitoring signal collected by the ultra-high frequency partial discharge coupling device in the current monitoring period; The first judgment module is used to judge whether the activation condition of the interference signal library is met. If so, the amplitude sequence obtained after discretizing the monitoring signal is input into the pre-built machine learning model to generate a diagnosis result of whether the hydro-generator is working normally. When it is diagnosed that the working state of the hydro-generator is abnormal and the built interference signal library is used to determine that the monitoring signal is not an interference signal, jump to trigger the execution of judging whether the amplitude of the monitoring signal collected in the current monitoring period is greater than the amplitude threshold, otherwise, the interference signal types in the interference signal library are accumulated, and jump to trigger the execution of judging whether the amplitude of the monitoring signal collected in the current monitoring period is greater than the amplitude threshold; The second judgment module is used to judge whether the amplitude of the monitoring signal collected in the current monitoring period is greater than the amplitude threshold. If so, and when the number of monitoring periods in which the amplitude of the corresponding monitoring signal is greater than the amplitude threshold continuously accumulates to reach the period accumulation threshold, jump to trigger the execution of identifying the partial discharge event to which the monitoring signal collected in the current monitoring period belongs, otherwise enter the next monitoring period and jump to trigger the execution of obtaining the monitoring signal collected by the ultra-high frequency partial discharge coupling device in the current monitoring period; The identification module is used to identify the partial discharge event to which the monitoring signal collected in the current monitoring period belongs.

11. A computer device, characterized in that: include: a memory configured to store instructions; as well as A processor is configured to call the instruction from the memory and to implement the online intelligent diagnosis method for ultra-high frequency partial discharge fault of a hydro-turbine generator according to any one of claims 1 to 9 when executing the instruction.

12. A machine-readable storage medium, characterized in that: The machine-readable storage medium stores instructions for enabling the machine to execute the online intelligent diagnosis method for ultra-high frequency partial discharge faults of a hydro-turbine generator according to any one of claims 1 to 9.

Images