Hydrogenerator ultra-high frequency partial discharge fault early warning method, device and computer equipment

Abstract

The present application provides a method, device and computer equipment for early warning of ultra-high frequency partial discharge faults of hydro-turbine generators, which belongs to the field of partial discharge monitoring technology. The method comprises: obtaining the monitoring signal collected by the ultra-high frequency partial discharge coupling device in the current monitoring period; discretizing the monitoring signal to obtain an amplitude sequence; inputting the amplitude sequence into a partial discharge diagnosis model to generate a diagnosis result of whether the monitoring signal is a partial discharge signal; if the diagnosis result shows that the monitoring signal is a partial discharge signal, extracting the characteristic parameters of the monitoring signal; using the characteristic parameters to match the partial discharge event corresponding to the characteristic parameters from the constructed case library, and issuing an early warning of the partial discharge event occurring in the current monitoring period. The above method uses a partial discharge diagnosis model based on a classification network to identify partial discharge signals, and then combines the case library to perform partial discharge fault early warning, thereby improving the efficiency and accuracy of partial discharge fault early warning.

Description

Technical Field

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

[0002] As the core equipment of hydropower stations, the stator windings of hydroelectric generators are subject to constantly changing mechanical forces, electric fields, and thermal stresses during operation, gradually changing the insulation properties of the stator windings. Insulation defects in the stator windings include discharges within the wire slots, defects in the winding ends, and surface corona contamination. Accurate monitoring and early warning of these insulation defects are critical to the safety and stability of power systems. In recent years, ultra-high frequency (UHF) PD monitoring has been gradually adopted due to its higher sensitivity and improved anti-interference performance compared to low-frequency (LF) PD monitoring. However, due to the complex operating conditions of hydroelectric generators, the PD signals detected by UHF PD monitoring remain subject to significant interference. Furthermore, the sheer volume of data generated by UHF PD monitoring makes fault early warning solely based on qualitative analysis based on single-unit trend comparisons inefficient and subject to significant subjective factors.

[0003] At present, with the continuous development of artificial intelligence and deep learning technologies, the application of fault warning systems driven by massive data has become more extensive, but there are few application solutions in the field of ultra-high frequency partial discharge fault warning of hydro-generators. Summary of the Invention

[0004] In view of this, the purpose of the embodiments of the present application is to provide a hydro-generator ultra-high frequency partial discharge fault warning method, a hydro-generator ultra-high frequency partial discharge fault warning device, a computer device and a machine-readable storage medium, so as to overcome the technical problems in the prior art of the hydro-generator ultra-high frequency partial discharge fault warning method, such as low warning efficiency and being greatly affected by subjective factors.

[0005] To achieve the above objectives, the first aspect of the present application provides a method for early warning of ultra-high frequency partial discharge faults in a hydro-generator, the method comprising:

[0006] Obtaining the monitoring signal collected by the ultra-high frequency partial discharge coupling device during the current monitoring period;

[0007] Discretizing the monitoring signal to obtain an amplitude sequence;

[0008] Inputting the amplitude sequence into a pre-built partial discharge diagnostic model to generate a diagnosis result of whether the monitoring signal is a partial discharge signal, wherein the partial discharge diagnostic model is obtained by training and optimizing parameters of an initial classification network;

[0009] If the diagnosis result indicates that the monitoring signal is a partial discharge signal, extracting characteristic parameters of the monitoring signal;

[0010] The characteristic parameters are used to match partial discharge events corresponding to the characteristic parameters from a constructed case library, and an early warning of the partial discharge event occurring within the current monitoring period is issued, wherein each partial discharge event has its own corresponding characteristic parameters.

[0011] In a specific embodiment of the present application, the characteristic parameters include at least one of phase, amplitude, spectrum characteristics, waveform characteristics, and amplitude statistical characteristics.

[0012] In a specific embodiment of the present application, the waveform feature includes at least one of a rise time, a fall time, a duration, and a pulse width.

[0013] In a specific embodiment of the present application, the amplitude statistical feature includes at least one of an amplitude mean value and an amplitude standard deviation.

[0014] In a specific embodiment of the present application, there are multiple partial discharge diagnostic models, and the method further includes:

[0015] If the diagnosis result indicates that the number of partial discharge diagnosis models for which the monitoring signal is a partial discharge signal reaches a first preset value, obtaining a final diagnosis result that the monitoring signal is a partial discharge signal, so as to trigger the execution of extracting characteristic parameters of the monitoring signal if the diagnosis result indicates that the monitoring signal is a partial discharge signal;

[0016] If the diagnosis result indicates that the number of partial discharge diagnosis models whose monitoring signals are signals of the normal working state of the hydro-generator reaches a second preset value, a final diagnosis result is obtained that the monitoring signal is a signal of the normal working state of the hydro-generator.

[0017] In a specific embodiment of the present application, the hydro-generator ultra-high frequency partial discharge fault early warning method according to claim 1 is characterized in that the classification network is an RBF neural network.

[0018] In a specific embodiment of the present application, the characteristic parameters are used to match partial discharge events corresponding to the characteristic parameters from a constructed case library, and an early warning of the partial discharge event occurring in the current monitoring period is issued, including:

[0019] If the characteristic parameters corresponding to a partial discharge event in the constructed case library match the characteristic parameters of the monitoring signal, an early warning is issued indicating that the partial discharge event has occurred in the current monitoring period;

[0020] If the characteristic parameters of the monitoring signal do not match the characteristic parameters corresponding to each partial discharge event in the established case library, then obtaining offline partial discharge test data, the offline partial discharge test data including each partial discharge signal collected by each ultra-high frequency partial discharge coupling device after performing offline partial discharge tests on each partial discharge collection point of the stator winding of the hydro-generator, each partial discharge collection point being equipped with the ultra-high frequency partial discharge coupling device;

[0021] Extract characteristic parameters of each partial discharge signal from offline partial discharge test data;

[0022] For any partial discharge signal, if the characteristic parameters corresponding to the partial discharge signal are consistent with the characteristic parameters of the monitoring signal, the partial discharge event type of the monitoring signal is determined to be the partial discharge event type generated by the partial discharge source at the partial discharge collection point corresponding to the partial discharge signal, and the partial discharge event of this type is added to the case library and an early warning is issued that a partial discharge event of this type has occurred in the current monitoring period.

[0023] A second aspect of the present application provides a hydro-generator ultra-high frequency partial discharge fault warning device, the device comprising:

[0024] An acquisition module is used to obtain the monitoring signal collected by the ultra-high frequency partial discharge coupling device during the current monitoring period;

[0025] A signal processing module, configured to discretize the monitoring signal to obtain an amplitude sequence;

[0026] a partial discharge diagnosis module, configured to input the amplitude sequence into a pre-built partial discharge diagnosis model to generate a diagnosis result of whether the monitoring signal is a partial discharge signal, wherein the partial discharge diagnosis model is obtained by training and parameter optimization of an initial classification network;

[0027] A feature extraction module, configured to extract feature parameters of the monitoring signal when the diagnosis result indicates that the monitoring signal is a partial discharge signal;

[0028] A fault warning module is used to use the characteristic parameters to match partial discharge events corresponding to the characteristic parameters from a constructed case library, and issue a warning of the partial discharge event occurring in the current monitoring period, wherein each partial discharge event has its own corresponding characteristic parameters.

[0029] A third aspect of the present application provides a computer device, comprising:

[0030] a memory configured to store instructions; and

[0031] The processor is configured to call the instruction from the memory and implement the hydro-generator ultra-high frequency partial discharge fault early warning method according to the first aspect of the present application when executing the instruction.

[0032] A 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 hydro-generator ultra-high frequency partial discharge fault warning method according to the first aspect of the present application.

[0033] In the above technical solution, a partial discharge diagnosis model based on a classification network is used to identify partial discharge signals, and then a case library is combined to perform partial discharge fault warning, thereby improving the efficiency and accuracy of partial discharge fault warning.

[0034] Other features and advantages of the embodiments of the present application will be described in detail in the subsequent detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] 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 detailed description, 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:

[0036] Figure 1 A flowchart of a method for early warning of ultra-high frequency partial discharge faults in a hydro-turbine generator according to an embodiment of the present application is schematically shown;

[0037] Figure 2 A schematic block diagram of a hydro-generator ultra-high frequency partial discharge fault warning device according to an embodiment of the present application is shown;

[0038] Figure 3 The structural block diagram of a computer device according to an embodiment of the present application is schematically shown. DETAILED DESCRIPTION

[0039] The following describes the specific implementation of the embodiment of the present application in detail with reference to the accompanying drawings. It should be understood that the specific implementation described herein is only used to illustrate and explain the embodiment of the present application and is not intended to limit the embodiment of the present application.

[0040] If there are descriptions involving "first", "second", etc. in the embodiments of this application, the descriptions of "first", "second", etc. are only 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 such features. In addition, the technical solutions between the various embodiments can be combined with each other, but they must be based on the fact that they can be implemented by ordinary technicians in this field. 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.

[0041] To overcome the many shortcomings of hydro-generator partial discharge fault warning based on single-machine trend comparison and qualitative analysis, the present invention implements a hydro-generator ultra-high frequency partial discharge fault warning method in the following manner:

[0042] Obtaining the monitoring signal collected by the ultra-high frequency partial discharge coupling device during the current monitoring period;

[0043] Discretize the collected monitoring signal to obtain an amplitude sequence;

[0044] The amplitude sequence is input into a pre-built partial discharge diagnosis model to generate a diagnosis result of whether the monitoring signal is a partial discharge signal. The partial discharge diagnosis model is obtained by training and optimizing the parameters of the initial classification network.

[0045] If the diagnosis result indicates that the monitoring signal collected in the current monitoring period is a partial discharge signal, characteristic parameters of the monitoring signal are extracted;

[0046] The extracted characteristic parameters are used to match the partial discharge events corresponding to the characteristic parameters from the constructed case library, and an early warning is issued when the partial discharge event occurs during the current monitoring period. Each partial discharge event has its own corresponding characteristic parameters.

[0047] It should be understood that, in the present application, the collected monitoring signal is discretized to obtain a pulse sequence, and the amplitude sequence is a sequence composed of the amplitudes of each pulse in the pulse sequence.

[0048] As shown in the above embodiment, a partial discharge diagnosis model based on a classification network is used to classify and identify partial discharge signals and normal working status signals of hydro-generators. The classification network itself has the characteristic of high recognition accuracy, which makes the classification of partial discharge signals and normal working status signals of hydro-generators have high accuracy. After the partial discharge signal is identified, the partial discharge event corresponding to the current monitoring signal is matched from the case library through feature parameter extraction, avoiding the highly subjective single-machine trend comparison analysis and partial discharge event judgment performed by on-site technicians, thereby improving the efficiency and accuracy of partial discharge fault warning.

[0049] Figure 1 The flowchart of the method for early warning of ultra-high frequency partial discharge fault of a hydro-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 warning method may include the following steps 102 to 110. It is understandable that the above hydro-generator ultra-high frequency partial discharge fault warning method may include all steps from step 102 to step 110, or may include only some of them.

[0050] Step 102: Acquire the monitoring signal collected by the ultra-high frequency partial discharge coupling device in the current monitoring period.

[0051] Step 104: discretize the collected monitoring signal to obtain an amplitude sequence. As is known, the monitoring signal is usually pre-processed, including band-pass filtering, normalization, and the like.

[0052] For example, the normalization process is performed as follows:

[0053] ;

[0054] Among them, x(t) represents the monitoring signal after bandpass filtering, max (|x(t)|) is the maximum absolute value amplitude of the signal x(t), and the normalized signal x b The range of (t) is [-1,1].

[0055] Step 106 : Input the amplitude sequence obtained in step 104 into a pre-built partial discharge diagnosis model to generate a diagnosis result of whether the monitoring signal is a partial discharge signal.

[0056] Specifically, in this application, the partial discharge diagnosis model is obtained by training and optimizing the parameters of the initial classification network.

[0057] As an example, the classification network may be a machine learning classification network, a neural network, etc. For example, the classification network is an RBF network.

[0058] As an improved embodiment of the present application, there are multiple partial discharge diagnostic models, and each partial discharge diagnostic model constitutes a combined diagnostic model. Accordingly, step 106 further includes the following contents:

[0059] If the diagnosis result indicates that the number of partial discharge diagnosis models for which the monitoring signal is a partial discharge signal reaches a first preset value, obtaining a final diagnosis result that the monitoring signal is a partial discharge signal, so as to trigger the execution of extracting characteristic parameters of the monitoring signal if the diagnosis result indicates that the monitoring signal is a partial discharge signal;

[0060] If the diagnosis result shows that the number of partial discharge diagnosis models whose monitoring signals are signals of the normal working state of the hydro-generator reaches a second preset value, a diagnosis result that the monitoring signal is a signal of the normal working state of the hydro-generator is obtained to trigger the execution of extracting characteristic parameters of the monitoring signal if the diagnosis result shows that the monitoring signal is a partial discharge signal.

[0061] As in the above embodiment, by integrating the classification results of multiple partial discharge diagnosis models, the classification accuracy is higher, thereby improving the accuracy of partial discharge fault monitoring.

[0062] As an example, various partial discharge diagnostic models can be constructed based on different types of classification networks. For example, some partial discharge diagnostic models are random forest models, some partial discharge diagnostic models are RBF models, and some partial discharge diagnostic models are XGBoost models.

[0063] As an example, the number of partial discharge diagnostic models is 5, the first preset value may be 3, and the second preset value may be 3.

[0064] Step 108: If the diagnosis result indicates that the monitoring signal is a partial discharge signal, characteristic parameters of the monitoring signal are extracted.

[0065] It can be seen that the PD signals corresponding to different types of PD events differ in the time domain and / or frequency domain. Specifically, the amplitude, frequency, and waveform of the PD signal vary with the PD location and PD intensity.

[0066] In an optional embodiment of the present application, the characteristic parameters of the partial discharge signal include at least one of phase, amplitude, spectral characteristics, waveform characteristics, and amplitude statistical characteristics. The waveform characteristics include at least one of rise time, fall time, duration, and pulse width. The amplitude statistical characteristics include at least one of amplitude mean value and amplitude standard deviation.

[0067] Specifically, different types of partial discharges will produce different spectrum distributions. As mentioned above, the spectrum characteristics can be the intensity and frequency distribution of different frequency components in the spectrum.

[0068] As an example, characteristic parameters of a partial discharge signal include phase, amplitude, spectrum characteristics, waveform characteristics, and amplitude statistical characteristics.

[0069] Step 110 , using the characteristic parameters extracted in step 108 , matches a partial discharge event associated with the characteristic parameters from the constructed case library, and issues an early warning of the partial discharge event occurring within the current monitoring period.

[0070] It's important to understand that each PD event in the case library has corresponding characteristic parameters. PD events in the case library can be collected through PD simulation experiments. For example, PD events in the case library can be divided into typical PD events and common PD events. Typical PD events are those occurring in the stator windings of a hydro-turbine generator under extreme conditions, while common PD events occur under non-extreme conditions.

[0071] As an example, a typical PD event is a PD case under extreme humidity conditions. Specifically, this refers to simulating partial discharge in a high-humidity environment. Because moisture can significantly alter the properties of insulation materials, increasing the probability of PD, PD simulations under these conditions yield PD events under these conditions. Another typical PD event is a PD case under high-temperature conditions. Specifically, this refers to simulating PD under conditions above normal operating temperature. Because high temperatures can accelerate the aging of insulation materials, leading to PD, PD simulations under these conditions yield PD events under these conditions. Another typical PD event is a PD case under strong electromagnetic interference. Specifically, this refers to simulating PD in the presence of strong electromagnetic interference. In specific applications, this simulates the complex electromagnetic interference environment found in actual power systems to yield PD events under these conditions. Another typical PD event is a PD case after insulation material aging. Specifically, this refers to using aged insulation materials or accelerated aging experiments to simulate the long-term operation of a hydro-turbine generator, examining the impact of insulation aging on PD, yielding PD events under these conditions. Another typical PD event is the PD case caused by mechanical stress on a hydro-turbine generator. Specifically, during PD testing, mechanical vibration or shock is applied to the generator. Mechanical stress or shock can damage the insulation structure, leading to PD. By examining the PD caused by this insulation damage, PD events under these conditions are identified. Another typical PD event is the PD case caused by different types of insulation defects. Specifically, models of insulation defects of different types and sizes, such as bubbles, cracks, and impurities, are constructed, and their effects on PD are examined to identify PD events under these conditions. Another typical PD event is the PD case caused by a hydro-turbine generator under extreme operating conditions. Specifically, extreme operating conditions such as rapid voltage increase, rapid voltage decrease, and overload are simulated. These extreme operating conditions can exacerbate PD phenomena. PD simulations under these extreme operating conditions are used to identify PD events under these conditions. Another typical PD event is the PD case under compound fault conditions. Specifically, this involves conducting PD simulation tests on a hydro-generator under multiple extreme conditions simultaneously, such as high temperature, high humidity, and mechanical stress. The combined impact of compound fault conditions on PD is examined, and the PD events under these conditions are identified.

[0072] Since each hydro-generator unit has differences in manufacturing process, materials used, operating environment, and maintenance history, these factors together lead to personalized differences in partial discharge data of different units. The case library cannot cover various personalized partial discharge events of all hydro-generator units. Therefore, in a specific embodiment of the present application, the case library of partial discharge events is improved in combination with offline partial discharge testing. Accordingly, step 110 uses the characteristic parameters extracted in step 108 to match the partial discharge events associated with the characteristic parameters from the constructed case library, and issues a warning of the partial discharge event occurring in the current monitoring period. Specifically, the following steps are included:

[0073] If the characteristics of a partial discharge event in the constructed case library match the characteristic parameters extracted in step 108, an early warning is issued indicating that the partial discharge event has occurred in the current monitoring period;

[0074] If the characteristic parameters extracted in step 108 do not match the characteristic parameters of each partial discharge event in the constructed case library, offline partial discharge test data is obtained, and the type of partial discharge event of the monitoring signal is determined based on the obtained offline partial discharge test data. The partial discharge event of this type is added to the case library, and an early warning is issued that a partial discharge event of this type has occurred in the current monitoring cycle. The offline partial discharge test data is obtained by performing offline partial discharge tests at each partial discharge collection point of the stator winding, and each partial discharge collection point is equipped with an ultra-high frequency partial discharge coupling device.

[0075] Specifically, in this application, the offline partial discharge test data includes each partial discharge signal collected by each ultra-high frequency partial discharge coupling device after performing offline partial discharge tests on each partial discharge collection point of the stator winding. Accordingly, determining the partial discharge event type of the monitoring signal based on the obtained offline partial discharge test data includes the following steps:

[0076] Extract characteristic parameters of each partial discharge signal;

[0077] For any partial discharge signal, if the characteristic parameters of the partial discharge signal are consistent with the characteristic parameters of the monitoring signal collected in the current monitoring period, the partial discharge event type of the monitoring signal collected in the current monitoring period is determined to be the partial discharge event type generated by the partial discharge source at the partial discharge collection point corresponding to the partial discharge signal.

[0078] Preferably, before extracting the characteristic parameters of these partial discharge signals, the partial discharge signals collected at each partial discharge collection point are corrected using a maximum attenuation coefficient. The maximum attenuation coefficient can be determined using the process described in conventional embodiments. For example, a test partial discharge signal is injected at each preset injection point on the stator winding bar, and then the partial discharge signal is collected at the partial discharge collection point via an ultra-high frequency partial discharge coupling device. The transfer function and attenuation coefficient of the stator winding bar are then determined using a network vector analyzer, thereby determining the maximum attenuation coefficient. The partial discharge signals collected at each distribution point are reconstructed using the transfer function, and the reconstructed partial discharge signal is multiplied by the maximum attenuation coefficient to complete the partial discharge signal correction.

[0079] 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 this application.

[0080] Corresponding to the ultra-high frequency partial discharge monitoring and analysis method for a hydro-turbine generator in the above embodiment, Figure 2 The block diagram of the ultra-high frequency partial discharge fault warning device 400 for a hydro-turbine generator provided in an embodiment of the present application is schematically shown. For ease of explanation, only the parts related to the embodiment of the present application are shown.

[0081] like Figure 2 As shown, the hydro-generator ultra-high frequency partial discharge fault warning device 400 includes:

[0082] An acquisition module 410 is configured to acquire a monitoring signal collected by the ultra-high frequency partial discharge coupling device during a current monitoring period;

[0083] The signal processing module 420 is used to discretize the monitoring signal to obtain an amplitude sequence;

[0084] a partial discharge diagnosis module 430 for inputting the amplitude sequence into a pre-built partial discharge diagnosis model to generate a diagnosis result of whether the monitoring signal is a partial discharge signal, wherein the partial discharge diagnosis model is obtained by training and parameter optimization of an initial classification network;

[0085] A feature extraction module 440 is configured to extract feature parameters of the monitoring signal when the diagnosis result indicates that the monitoring signal is a partial discharge signal;

[0086] The fault warning module 450 is used to use the characteristic parameters to match the partial discharge events corresponding to the characteristic parameters from the constructed case library, and issue a warning of the partial discharge event occurring in the current monitoring period, wherein each partial discharge event has its own corresponding characteristic parameters.

[0087] The process of each module in the hydro-generator ultra-high frequency partial discharge fault warning device 400 provided in the embodiment of the present application realizing its own 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.

[0088] 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 this application. Their specific functions and technical effects can be found in the method embodiment part and will not be repeated here.

[0089] Figure 3 The structural block diagram of the computer device according to the embodiment of the present application is schematically shown.

[0090] In one embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as shown below. Figure 3 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) connected via a system bus. The processor A01 of the computer device is used to provide computing and control capabilities. The memory of the computer device includes internal memory A03 and 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 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 via a network connection. When executed by the processor A01, the computer program implements a method for early warning of ultra-high frequency partial discharge faults in a hydro-turbine generator. The display screen A04 of the computer device can be a liquid crystal display or an electronic ink display. The input device A05 of the computer device can be a touch layer covering the display screen, or can be keys, a trackball, or a touchpad provided on the computer device housing, or can be an external keyboard, touchpad, or mouse.

[0091] Those skilled in the art will understand that Figure 3 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 shown in the figure, or combine certain components, or have a different component arrangement.

[0092] In one embodiment, the hydro-generator ultra-high frequency partial discharge fault warning device 400 provided by the present application can be implemented in the form of a computer program. The computer program can be used in Figure 3The computer device is shown. The computer device's memory may store the various program modules that comprise the hydro-generator ultra-high frequency partial discharge fault warning device 400. The computer program comprised of the various program modules causes the processor to execute the steps of the hydro-generator ultra-high frequency partial discharge fault warning method according to various embodiments of the present application as described in this specification.

[0093] In one embodiment, the present application further provides a machine-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the method for early warning of ultra-high frequency partial discharge faults of a hydro-turbine generator in the above embodiment is implemented.

[0094] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, i.e., they may be located in one location or distributed across multiple network units. Some or all of the modules may be selected based on actual needs to achieve the objectives of the present embodiment. Persons of ordinary skill in the art will be able to understand and implement the present invention without inventive effort.

[0095] 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 take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware. Furthermore, the present application may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0096] It should also be noted that the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, commodity, or apparatus that includes a series of elements includes not only those elements but also other elements not explicitly listed, or includes elements inherent to such process, method, commodity, or apparatus. In the absence of further limitations, an element defined by the phrase "comprises a ..." does not exclude the presence of other identical elements in the process, method, commodity, or apparatus that includes the element.

[0097] 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 them. 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. A method for early warning of ultra-high frequency partial discharge faults 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; Discretizing the monitoring signal to obtain an amplitude sequence; Inputting the amplitude sequence into a pre-built partial discharge diagnostic model to generate a diagnosis result of whether the monitoring signal is a partial discharge signal, wherein the partial discharge diagnostic model is obtained by training and optimizing parameters of an initial classification network; If the diagnosis result indicates that the monitoring signal is a partial discharge signal, extracting characteristic parameters of the monitoring signal; The characteristic parameters are used to match partial discharge events corresponding to the characteristic parameters from the constructed case library, and an early warning of the partial discharge event occurring in the current monitoring period is issued, where each partial discharge event has its own corresponding characteristic parameters; wherein the method specifically includes: if the characteristic parameters corresponding to a partial discharge event in the constructed case library match the characteristic parameters of the monitoring signal, an early warning of the partial discharge event occurring in the current monitoring period is issued; if the characteristic parameters of the monitoring signal do not match the characteristic parameters corresponding to each partial discharge event in the constructed case library, offline partial discharge test data is obtained, and the characteristic parameters of each partial discharge signal in the offline partial discharge test data are extracted. For any partial discharge signal, if the characteristic parameters corresponding to the partial discharge signal are consistent with the characteristic parameters of the monitoring signal, the partial discharge event type of the monitoring signal is determined to be the partial discharge event type generated by the partial discharge source at the partial discharge collection point corresponding to the partial discharge signal, and the partial discharge event of this type is added to the case library and an early warning is issued that the partial discharge event of this type has occurred in the current monitoring cycle, wherein the offline partial discharge test data includes each partial discharge signal collected by each ultra-high frequency partial discharge coupling device after performing offline partial discharge tests on each partial discharge collection point of the stator winding of the hydro-generator, and each partial discharge collection point is equipped with the ultra-high frequency partial discharge coupling device.

2. The hydro-generator ultra-high frequency partial discharge fault early warning method according to claim 1 is characterized in that: The characteristic parameters include at least one of phase, amplitude, spectrum characteristics, waveform characteristics, and amplitude statistical characteristics.

3. The hydro-generator ultra-high frequency partial discharge fault early warning method according to claim 2 is characterized in that: The waveform characteristics include at least one of a rise time, a fall time, a duration, and a pulse width.

4. The method for early warning of ultra-high frequency partial discharge fault of a hydro-generator according to claim 2, characterized in that: The amplitude statistical feature includes at least one of an amplitude mean value and an amplitude standard deviation.

5. The method for early warning of ultra-high frequency partial discharge fault of a hydro-generator according to claim 1, characterized in that: There are multiple partial discharge diagnostic models, and the method further includes: If the diagnosis result indicates that the number of partial discharge diagnosis models for which the monitoring signal is a partial discharge signal reaches a first preset value, obtaining a final diagnosis result that the monitoring signal is a partial discharge signal, so as to trigger the execution of extracting characteristic parameters of the monitoring signal if the diagnosis result indicates that the monitoring signal is a partial discharge signal; If the diagnosis result indicates that the number of partial discharge diagnosis models whose monitoring signals are signals of the normal working state of the hydro-generator reaches a second preset value, a final diagnosis result is obtained that the monitoring signal is a signal of the normal working state of the hydro-generator.

6. The hydro-generator ultra-high frequency partial discharge fault early warning method according to claim 1, characterized in that: The classification network is an RBF neural network.

7. A hydro-generator ultra-high frequency partial discharge fault warning device, characterized in that: include: An acquisition module is used to obtain the monitoring signal collected by the ultra-high frequency partial discharge coupling device during the current monitoring period; A signal processing module, configured to discretize the monitoring signal to obtain an amplitude sequence; a partial discharge diagnosis module, configured to input the amplitude sequence into a pre-built partial discharge diagnosis model to generate a diagnosis result of whether the monitoring signal is a partial discharge signal, wherein the partial discharge diagnosis model is obtained by training and parameter optimization of an initial classification network; A feature extraction module, configured to extract feature parameters of the monitoring signal when the diagnosis result indicates that the monitoring signal is a partial discharge signal; A fault warning module is used to match a partial discharge event corresponding to the characteristic parameters from a constructed case library using the characteristic parameters, and issue a warning that the partial discharge event has occurred in the current monitoring period, and each partial discharge event has its own corresponding characteristic parameters; wherein, specifically, if the characteristic parameters corresponding to a partial discharge event in the constructed case library match the characteristic parameters of the monitoring signal, then issue a warning that the partial discharge event has occurred in the current monitoring period; if the characteristic parameters of the monitoring signal do not match the characteristic parameters corresponding to each partial discharge event in the constructed case library, then obtain offline partial discharge test data, extract the characteristic parameters of each partial discharge signal in the offline partial discharge test data, and For any partial discharge signal, if the characteristic parameter corresponding to the partial discharge signal is consistent with the characteristic parameter of the monitoring signal, then the partial discharge event type of the monitoring signal is determined to be the partial discharge event type generated by the partial discharge source at the partial discharge collection point corresponding to the partial discharge signal, and the partial discharge event of this type is added to the case library, and an early warning is issued that the partial discharge event of this type has occurred in the current monitoring cycle, wherein the offline partial discharge test data includes each partial discharge signal collected by each ultra-high frequency partial discharge coupling device after performing offline partial discharge tests on each partial discharge collection point of the stator winding of the hydro-generator, and each partial discharge collection point is equipped with the ultra-high frequency partial discharge coupling device.

8. A computer device, characterized in that: include: a memory configured to store instructions; as well as The processor is configured to call the instruction from the memory and implement the hydro-generator ultra-high frequency partial discharge fault early warning method according to any one of claims 1 to 6 when executing the instruction.

9. A machine-readable storage medium, characterized in that The machine-readable storage medium stores instructions for enabling a machine to execute the hydro-generator ultra-high frequency partial discharge fault early warning method according to any one of claims 1 to 6.

Images