Insulation monitoring method and device for stator winding of hydro-generator and computer equipment

Abstract

The invention relates to an insulation monitoring method and device for a stator winding of a hydraulic generator and computer equipment. The method comprises the following steps: acquiring an initial partial discharge signal acquired by a capacitive coupler arranged on each branch of a stator winding of the hydro-generator; for any two capacitive couplers having a pairing relationship in the capacitive couplers, performing cross-correlation calculation on the initial partial discharge signals of the two capacitive couplers, and extracting noise features; stripping the noise features from the initial partial discharge signals of the two capacitive couplers to obtain a target partial discharge signal; and extracting pulse characteristics of a target partial discharge signal corresponding to each capacitive coupler of the stator winding, and inputting each pulse characteristic into a trained classifier to obtain a discharge type of each target partial discharge signal so as to determine the insulation state of the stator winding. The method can improve the accuracy of the stator winding insulation monitoring result.

Description

Technical Field

[0001] The present application relates to the technical field of power equipment status monitoring, and in particular to a method, device, computer equipment, computer-readable storage medium, and computer program product for monitoring the insulation of a hydro-generator stator winding. Background Art

[0002] Deterioration of insulation in the stator windings of hydro-turbine generators is a primary cause of major equipment failures, necessitating insulation monitoring. Traditional monitoring systems utilize a ceramic coupler (100kHz-30MHz) connected in parallel to the output busbar for monitoring. However, when collecting partial discharge signals, the ceramic coupler is susceptible to contamination from electromagnetic noise from the generator itself (such as brush sparks and thyristor operation) and external environmental interference (such as overvoltage from GIS equipment operation), which can affect monitoring results. Summary of the Invention

[0003] Based on this, it is necessary to provide a method, device, computer equipment, computer-readable storage medium and computer program product for insulation monitoring of a stator winding of a hydro-generator to address the technical problem of inaccurate insulation monitoring results in the above method.

[0004] In a first aspect, the present application provides a method for monitoring the insulation of a stator winding of a hydro-generator, comprising:

[0005] Acquiring an initial partial discharge signal collected by a capacitive coupler provided on each branch of a stator winding of a hydro-generator; wherein a capacitive coupler is provided on each branch of the stator winding;

[0006] For any two capacitive couplers that have a paired relationship among the capacitive couplers, performing cross-correlation calculation on initial partial discharge signals of the two capacitive couplers to extract noise characteristics;

[0007] stripping the noise feature from the initial partial discharge signals of the two capacitive couplers to obtain a target partial discharge signal;

[0008] Extracting pulse features of a target partial discharge signal corresponding to each capacitive coupler of the stator winding, inputting each pulse feature into a trained classifier to obtain a discharge type of each target partial discharge signal, so as to determine the insulation state of the stator winding.

[0009] In one embodiment, the initial partial discharge signal obtained from the capacitive coupler of each branch carries an identifier of the capacitive coupler; the method further includes:

[0010] When it is determined that an insulation fault occurs in the stator winding according to the discharge type of each target partial discharge signal, determining an identifier of a capacitive coupler carried by the target partial discharge signal having the insulation fault;

[0011] The fault branch in the stator winding is located according to the identifier of the capacitive coupler.

[0012] In one embodiment, the capacitive couplers determine the pairing relationship in the following manner:

[0013] For each phase of the hydro-generator, determining the number of capacitive couplers belonging to the phase;

[0014] If the number is an even number, pair the capacitive couplers in pairs;

[0015] If the number is an odd number, one of the capacitive couplers is selected as a common coupler to be paired with the two couplers.

[0016] In one embodiment, an oscilloscope is further provided after the capacitive coupler provided on each branch, and the capacitive coupler of each branch is connected to the oscilloscope via a coaxial cable; before obtaining the initial partial discharge signal collected by the capacitive coupler provided on each branch of the stator winding of the hydro-generator, the method further includes:

[0017] injecting a calibration pulse into a busbar terminal of the stator winding and measuring the signal propagation delay of each branch;

[0018] According to the signal propagation delay of each branch, the cable length of each branch is adjusted so that the signals of the two paired branches arrive at the oscilloscope synchronously.

[0019] In one embodiment, the capacitive coupler is fixed by an arc-shaped clamping plate, at least one epoxy mica block and a stainless steel base block;

[0020] The at least one epoxy mica block is located between the stainless steel base block and the arc-shaped clamping plate; the arc-shaped clamping plate includes two separate arc-shaped structures;

[0021] The arc-shaped clamping plate, the at least one epoxy mica block and the stainless steel base block are connected by a fixed structure.

[0022] In one embodiment, the capacitive coupler is made of epoxy mica material.

[0023] In a second aspect, the present application further provides an insulation monitoring device for a stator winding of a hydro-generator, comprising:

[0024] An acquisition module is used to acquire an initial partial discharge signal collected by a capacitive coupler provided on each branch of the stator winding of the hydro-generator; wherein a capacitive coupler is provided on each branch of the stator winding;

[0025] a calculation module, configured to perform cross-correlation calculation on initial partial discharge signals of any two capacitive couplers that are paired among the capacitive couplers, and extract noise characteristics;

[0026] a stripping module, configured to strip the noise feature from the initial partial discharge signals of the two capacitive couplers to obtain a target partial discharge signal;

[0027] A classification module is configured to extract pulse features of a target partial discharge signal corresponding to each capacitive coupler of the stator winding, input each of the pulse features into a trained classifier, and obtain a discharge type of each target partial discharge signal to determine the insulation state of the stator winding.

[0028] In a third aspect, the present application further provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0029] Acquiring an initial partial discharge signal collected by a capacitive coupler provided on each branch of a stator winding of a hydro-generator; wherein a capacitive coupler is provided on each branch of the stator winding;

[0030] For any two capacitive couplers that have a paired relationship among the capacitive couplers, performing cross-correlation calculation on initial partial discharge signals of the two capacitive couplers to extract noise characteristics;

[0031] stripping the noise feature from the initial partial discharge signals of the two capacitive couplers to obtain a target partial discharge signal;

[0032] Extracting pulse features of a target partial discharge signal corresponding to each capacitive coupler of the stator winding, inputting each pulse feature into a trained classifier to obtain a discharge type of each target partial discharge signal, so as to determine the insulation state of the stator winding.

[0033] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the following steps are implemented:

[0034] Acquiring an initial partial discharge signal collected by a capacitive coupler provided on each branch of a stator winding of a hydro-generator; wherein a capacitive coupler is provided on each branch of the stator winding;

[0035] For any two capacitive couplers that have a paired relationship among the capacitive couplers, performing cross-correlation calculation on initial partial discharge signals of the two capacitive couplers to extract noise characteristics;

[0036] stripping the noise feature from the initial partial discharge signals of the two capacitive couplers to obtain a target partial discharge signal;

[0037] Extracting pulse features of a target partial discharge signal corresponding to each capacitive coupler of the stator winding, inputting each pulse feature into a trained classifier to obtain a discharge type of each target partial discharge signal, so as to determine the insulation state of the stator winding.

[0038] In a fifth aspect, the present application further provides a computer program product, comprising a computer program, which, when executed by a processor, implements the following steps:

[0039] Acquiring an initial partial discharge signal collected by a capacitive coupler provided on each branch of a stator winding of a hydro-generator; wherein a capacitive coupler is provided on each branch of the stator winding;

[0040] For any two capacitive couplers that have a paired relationship among the capacitive couplers, performing cross-correlation calculation on initial partial discharge signals of the two capacitive couplers to extract noise characteristics;

[0041] stripping the noise feature from the initial partial discharge signals of the two capacitive couplers to obtain a target partial discharge signal;

[0042] Extracting pulse features of a target partial discharge signal corresponding to each capacitive coupler of the stator winding, inputting each pulse feature into a trained classifier to obtain a discharge type of each target partial discharge signal, so as to determine the insulation state of the stator winding.

[0043] The above-mentioned method, apparatus, computer device, computer-readable storage medium, and computer program product for monitoring the insulation of a hydro-turbine generator stator winding acquire an initial partial discharge signal collected by a capacitive coupler provided on each branch of the hydro-turbine generator stator winding; perform a cross-correlation calculation on the initial partial discharge signals of any two paired capacitive couplers to extract noise features; strip the noise features from the initial partial discharge signals of the two capacitive couplers to obtain a target partial discharge signal; extract the pulse features of the target partial discharge signal corresponding to each capacitive coupler of the stator winding, input each pulse feature into a trained classifier, and obtain the discharge type of each target partial discharge signal to determine the insulation state of the stator winding. This method addresses the structural characteristics of stator bar branches by providing a capacitive coupler for each branch to implement a distributed capacitive coupler network, which can adapt to the structural characteristics of windings with multiple branches connected in parallel. By extracting and stripping the noise features of the partial discharge signals of the paired branches, the quality of the partial discharge signals of each branch is improved, thereby improving the accuracy of the stator winding insulation monitoring results. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the following briefly introduces the drawings required for use in the embodiments of the present application or related technical descriptions. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying any creative work.

[0045] Figure 1 FIG. 1 is an application environment diagram of a method for monitoring insulation of a stator winding of a hydro-generator according to an embodiment;

[0046] Figure 2 1 is a flow chart of a method for monitoring insulation of a stator winding of a hydro-generator in one embodiment;

[0047] Figure 3 A schematic diagram of a flow chart of a time difference calibration connection of a hydro-generator stator winding in one embodiment;

[0048] Figure 4 1 is a flow chart of the steps for locating a fault of a stator winding of a hydro-generator in one embodiment;

[0049] Figure 5 is a schematic diagram of a capacitive coupler fixing principle in one embodiment;

[0050] Figure 6 1 is a structural block diagram of an insulation monitoring device for a hydro-generator stator winding according to an embodiment;

[0051] Figure 7 FIG. 1 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0052] In order to make the purpose, technical solutions and advantages of this application more clearly understood, this application is further described in detail below in conjunction with the accompanying drawings and examples. It should be understood that the specific embodiments described herein are merely used to explain this application and are not intended to limit this application. It should be noted that the terms "including" and "having" and any variations thereof used in this application are intended to cover non-exclusive inclusions.

[0053] The insulation monitoring method of the stator winding of the hydro-generator provided in the embodiment of the present application can be applied to Figure 1 In the application environment shown. Among them, the processing device 102 obtains the data collected by the capacitor coupler 106 through the data transfer device 104. The processing device 102 can be a server or a terminal. The data storage system can store the data that the processing device 102 needs to process. The data storage system can be integrated on the processing device 102, or it can be placed on the cloud or other devices. In the application scenario of the present application, the processing device 102 obtains the initial partial discharge signal collected by the capacitor coupler 106 through the data transfer device 104; for any two capacitor couplers with a pairing relationship in each capacitor coupler 106, the initial partial discharge signals of the two capacitor couplers are cross-correlated and noise features are extracted; the noise features are stripped from the initial partial discharge signals of the two capacitor couplers to obtain the target partial discharge signal; the pulse features of the target partial discharge signal corresponding to each capacitor coupler of the stator winding are extracted, and each pulse feature is input into the trained classifier to obtain the discharge type of each target partial discharge signal, thereby determining the insulation state of the stator winding and realizing insulation monitoring of the stator winding of the hydro-turbine generator. The terminal may be, but is not limited to, various personal computers, laptops, smart phones, tablet computers, etc. The server may be an independent physical server, a server cluster or distributed system consisting of multiple physical servers, or a cloud server providing cloud computing services.

[0054] In an exemplary embodiment, Figure 2 As shown, a method for monitoring the insulation of a stator winding of a hydro-generator is provided. Figure 1 Taking the processing device 102 in FIG. 1 as an example, the process includes the following steps:

[0055] Step S210 , obtaining an initial partial discharge signal collected by a capacitive coupler provided on each branch of the stator winding of the hydro-generator; wherein a capacitive coupler is provided on each branch of the stator winding.

[0056] It is understandable that the traditional method of using a ceramic coupler in parallel with the output busbar has the problems of large signal attenuation and insufficient spatial resolution. Therefore, this method takes advantage of the multi-branch structure of the stator bar and sets a capacitive coupler on each branch to achieve distributed coupler network deployment. Figure 3 As shown, the capacitive coupler of each branch can be set at a preset distance from the end of the electronic rod, and the preset distance is less than or equal to 1 meter, so as to reduce signal attenuation.

[0057] In a specific implementation, the capacitive coupler on each branch collects the partial discharge signal of the branch, and the processing device 102 obtains the partial discharge signal as the initial partial discharge signal. It should be noted that each capacitive coupler collects the partial discharge signal synchronously to ensure time alignment of all branches.

[0058] In some embodiments, data collection of partial discharge signals may be performed at a preset sampling rate (greater than 1 GS / s, meeting the Nyquist criterion for a 350 MHz signal).

[0059] Step S220 : for any two capacitive couplers that are paired among the capacitive couplers, perform cross-correlation calculation on the initial partial discharge signals of the two capacitive couplers to extract noise characteristics.

[0060] The two capacitive couplers have a pairing relationship, which means that the two capacitive couplers belong to the same phase. For example, the capacitive couplers of branch 1 of phase A are paired with the capacitive couplers of branch 2 of phase A.

[0061] In the specific implementation, considering the spatial correlation of noise (highly similar waveforms when propagating on the same-phase winding) and the local differences in partial discharge signals, this step uses the cross-correlation method to extract the noise characteristics of the initial partial discharge signals of the two in-phase paired capacitive couplers, which can avoid out-of-phase power frequency interference.

[0062] Specifically, the initial partial discharge signals of two in-phase paired capacitive couplers can be cross-correlated with each other to obtain the global maximum value of the function value and its position. The noise delay can be further estimated based on the position, and the noise amplitude can be obtained by least squares fitting. The noise amplitude, noise position, etc. can be used as noise features.

[0063] In some embodiments, the initial partial discharge signal can be segmented according to a preset window width (≤10ns), for example, each segment length = 10ns (i.e., one window). A cross-correlation calculation is performed on the signal in each window, and a final value is determined from the global maximum corresponding to each window. This is then used to determine the noise signature. This method enables high-fidelity extraction of weak partial discharge signals in a noisy background, providing reliable data for insulation condition assessment.

[0064] Step S230 , removing noise features from the initial partial discharge signals of the two capacitive couplers to obtain target partial discharge signals.

[0065] In a specific implementation, after determining the noise signature, noise reconstruction can be performed based on the noise amplitude and noise location in the noise signature and one of the two initial partial discharge signals to generate an estimated noise. The estimated noise is then subtracted from the initial partial discharge signals of the two capacitive couplers to obtain a noise-reduced partial discharge signal, which serves as the target partial discharge signal.

[0066] This step utilizes the differences in the cross-correlation characteristics of the partial discharge signals from different branches of the same phase to locate and remove the noise components, thereby improving the quality of the target partial discharge signal and thus increasing the credibility and accuracy of the stator winding insulation monitoring results based on the target partial discharge signal.

[0067] Step S240 , extracting the pulse features of the target partial discharge signal corresponding to each capacitive coupler of the stator winding, inputting each pulse feature into a trained classifier, and obtaining the discharge type of each target partial discharge signal to determine the insulation state of the stator winding.

[0068] Among them, the pulse characteristics may include the number of discharges, pulse amplitude, phase, etc.

[0069] Among them, the discharge types may include interphase discharge, internal insulation discharge, surface corona discharge, etc.

[0070] In a specific implementation, a support vector machine (SVM) can be pre-built as a classifier with a kernel function of σ = 0.5. A simulated dataset is constructed, and the SVM is trained using the pulse characteristics of the PD signal samples in the simulated dataset as input variables and the discharge type as supervisory information. Specifically, the difference between the predicted discharge type and the actual discharge type is calculated, with minimizing this difference as the training objective. Training is terminated until a preset number of training cycles is reached or the loss converges, resulting in a trained classifier. Furthermore, in practical applications, the pulse characteristics of the target PD signal corresponding to each capacitive coupler in the stator winding are extracted and input into the trained classifier, which then outputs the discharge type of the target PD signal. The discharge type reflects the insulation condition of the stator winding and can be used to determine the insulation status of the stator winding. For example, interphase discharge indicates possible problems with the interphase insulation material (such as cracking, electrothermal aging, or contamination), leading to the formation of surface conductive channels. Insulation internal discharge indicates internal separation of the insulation layer, which may be caused by manufacturing defects or mechanical stress. Surface corona discharge indicates contamination of the insulation surface.

[0071] In the above-mentioned method for monitoring the insulation of a hydro-turbine generator stator winding, an initial partial discharge signal collected by a capacitive coupler provided on each branch of the hydro-turbine generator stator winding is obtained; for any two paired capacitive couplers among the capacitive couplers, a cross-correlation calculation is performed on the initial partial discharge signals of the two capacitive couplers to extract noise features; the noise features are stripped from the initial partial discharge signals of the two capacitive couplers to obtain a target partial discharge signal; the pulse features of the target partial discharge signal corresponding to each capacitive coupler of the stator winding are extracted, and each pulse feature is input into a trained classifier to obtain the discharge type of each target partial discharge signal to determine the insulation state of the stator winding. This method targets the structural characteristics of stator bar branches and implements a distributed capacitive coupler network by providing a capacitive coupler on each branch. This method can adapt to the structural characteristics of windings with multiple branches connected in parallel. By extracting and stripping the noise features of the partial discharge signals of the paired branches, the quality of the partial discharge signals of each branch is improved, thereby improving the accuracy of the stator winding insulation monitoring results.

[0072] It is understandable that when the traditional method uses a ceramic coupler (100kHz-30MHz) in parallel with the outlet bus for monitoring, the single bus coupling architecture will cause signal aliasing and will not be able to distinguish the partial discharge sources of multiple parallel branches. Based on this, this application also proposes a method for achieving branch-level positioning.

[0073] In an exemplary embodiment, the initial partial discharge signal obtained from the capacitive coupler of each branch carries the identifier of the capacitive coupler; Figure 4 As shown, the method further includes:

[0074] Step S410, when it is determined that an insulation fault occurs in the stator winding according to the discharge type of each target partial discharge signal, determining an identifier of a capacitive coupler carried by the target partial discharge signal where the insulation fault occurs;

[0075] Step S420: locating the fault branch in the stator winding according to the identifier of the capacitive coupler.

[0076] In the implementation, each branch coupler is assigned a unique identifier. When synchronously collecting partial discharge signals from each coupler, an identifier field is added to the data frame. If a target partial discharge signal is classified as an insulation fault, the identifier of the capacitive coupler carried by it is extracted. The binding relationship between the capacitive coupler and the branch is queried to determine the faulty branch, for example, ID_003 to phase B branch 2.

[0077] In this embodiment, dedicated couplers are installed on the high-voltage side of each stator bar branch (≤1m from the outgoing line), creating an N-type monitoring network (N is the number of parallel branches). This surpasses the spatial resolution limitations of traditional centralized monitoring. Each branch's capacitive coupler is assigned a unique identifier, enabling branch-level location of partial discharge signals. This branch-level monitoring capability reduces fault location time from the traditional eight hours to under 30 minutes, significantly reducing operation and maintenance costs.

[0078] In an exemplary embodiment, the pairing relationship of each capacitive coupler is determined in the following manner: for each phase of the hydro-generator, the number of capacitive couplers belonging to that phase is determined; if the number is an even number, the capacitive couplers are paired in pairs; if the number is an odd number, one of the capacitive couplers is selected as a common coupler and paired with two couplers.

[0079] In the specific implementation, a capacitive coupler is installed in each branch of each phase of the stator winding (such as 6 in phase A, 5 in phase B, and 6 in phase C). When pairing, if the number of couplers in a phase is even (such as 6 in phase A), the two pairs are paired in a non-overlapping combination. For example, the pairing group of phase A is: [ID_A1, ID_A2], [ID_A3, ID_A4], [ID_A5, ID_A6]. And when pairing, physical distance and signal strength are used as pairing priority considerations, that is, the closest physical distance (such as adjacent branch couplers are paired first) and the closest signal strength (amplitude difference <3dB) is paired first. If the number of couplers in a phase is odd (such as 5 in phase B), perform the following steps: (1) Select a coupler as a common node (such as selecting ID_B4). (2) The common node is paired with two adjacent couplers, and the rest are paired with each other, such as the B-phase pairing group: [ID_B1, ID_B2], [ID_B3, ID_B4], [ID_B4, ID_B5].

[0080] In this embodiment, the pairing relationship of in-phase capacitive couplers in stator winding partial discharge monitoring directly affects the accuracy of cross-correlation noise reduction. Traditional fixed pairing methods cannot adapt to dynamic changes in branch number (such as when some branches are out of service for maintenance). Therefore, the adaptive pairing strategy proposed in this embodiment dynamically generates the optimal pairing combination based on the actual number of couplers per phase, enabling dynamic pairing.

[0081] In an exemplary embodiment, an oscilloscope is further provided after the capacitive coupler provided in each branch, and the capacitive coupler of each branch is connected to the oscilloscope via a coaxial cable; before obtaining the initial partial discharge signal collected by the capacitive coupler provided on each branch of the stator winding of the hydro-generator, it also includes: injecting a calibration pulse into the busbar end point of the stator winding to measure the signal propagation delay of each branch; according to the signal propagation delay of each branch, adjusting the cable length of each branch so that the signals of the two branches with a paired relationship arrive at the oscilloscope synchronously.

[0082] In specific implementation, such as Figure 3 As shown, an oscilloscope is installed after the capacitive coupler in each branch. The capacitive couplers in each branch are connected to the oscilloscope via a coaxial cable. A pulse generator injects a calibration pulse (rise time tr = 1ns, amplitude 1Vpp) at the busbar endpoint of the stator winding, and the signal propagation delay of each branch is measured using the oscilloscope. Based on the signal propagation delay of each branch, the cable length of each branch is adjusted so that the signals of the two paired branches arrive at the oscilloscope synchronously, that is, L1 + R1 = L2 + R2. Here, L1 and L2 represent the lengths of the coaxial cables of the two branches, and R1 and R2 represent the lengths of the slip rings of the two branches.

[0083] In this embodiment, the propagation path time difference calibration technology (delay controlled within 2ns) is used with the help of an oscilloscope to calibrate the simultaneous arrival of signals from the two branches, providing a basis for subsequent feature extraction of noise signals from the two branches through a cross-correlation algorithm.

[0084] In an exemplary embodiment, the capacitive coupler is fixed by an arc-shaped clip, at least one epoxy mica block and a stainless steel base block; the at least one epoxy mica block is located between the stainless steel base block and the arc-shaped clip; the arc-shaped clip includes two separate arc-shaped structures; the arc-shaped clip, at least one epoxy mica block and the stainless steel base block are connected by a fixed structure.

[0085] In specific implementation, such as Figure 5 The schematic diagram shows the principle of securing a capacitive coupler. The capacitive coupler is secured via a curved clip, at least one epoxy mica block, and a stainless steel base block, with the at least one epoxy mica block positioned between the stainless steel base block and the curved clip. The curved clip comprises two separate curved structures. Through holes are provided at the four corners of the curved clip, the at least one epoxy mica block, and the stainless steel base block, and securing structures, such as bolts, are provided in these through holes. Specifically, the stainless steel base block is first punched, tapped, and welded in place. A selected number of epoxy mica blocks are then added, followed by the annular clip. The stainless steel base block, epoxy mica block, and curved clip are then secured with bolts. Finally, the capacitive coupler is placed and secured with screws.

[0086] Among them, the electrical parameters are: coupling capacitance C = 80pF, satisfying: Zc = 1 / (2πfC) = 56Ω@100MHz (matching the characteristic impedance of the coaxial cable).

[0087] In some embodiments, the stainless steel base block is made of 316 material, which has low magnetic permeability, good welding performance and high corrosion resistance.

[0088] In some embodiments, the epoxy mica blocks are of standard size, and their number can be increased or decreased according to the actual generator stator bar structure, voltage level, etc. to meet installation and electrical safety distance requirements.

[0089] In some embodiments, the capacitive coupler is made of epoxy mica material, which may be a composite material, and meets the following requirements: (1) volume resistivity > 1×10^16Ω·cm; (2) thermal aging life > 100,000h (155°C accelerated test); and (3) partial discharge < 5pC (tested at 1.5Ur).

[0090] The capacitive coupler uses epoxy mica capacitors (C = 80pF ± 5%, frequency response 40-350MHz), whose high-frequency characteristics meet the following requirements: (1) insertion loss < 1dB @ 100MHz; (2) VSWR < 1.5:1 (full frequency band); (3) pulse rise time tr < 2ns (corresponding to 350MHz cutoff frequency).

[0091] In some embodiments, the curved card plate is made of epoxy mica material.

[0092] It is understandable that the existing technology uses a ceramic coupler (100kHz-30MHz) in parallel with the outlet bus for insulation monitoring. This method has the following problems:

[0093] (1) Inaccurate positioning: The single busbar coupling architecture causes signal aliasing and cannot distinguish the partial discharge sources of multiple parallel branches.

[0094] (2) Noise pollution: The traditional frequency band below 30MHz contains more than 80% of switching operation interference (SNR measured in the laboratory is less than 6dB).

[0095] (3) Band limitation: The equivalent series resistance (ESR) of ceramic materials increases sharply when the frequency is greater than 30 MHz (ESR > 200 Ω at 350 MHz), resulting in attenuation of very high frequency signals.

[0096] (4) Reliability risk: Microcracks are easily generated at the ceramic-metal interface under temperature cycling (ΔT=60K), and the average annual failure rate is >3%.

[0097] Moreover, the high-frequency loss tangent value of the ceramic material is tanδ>0.01 (@100MHz), while the tanδ of the epoxy mica material of the present application is <0.002, that is, the high-frequency loss tangent value of the epoxy mica material used in the present application is much smaller than that of the ceramic material, and the energy loss is less.

[0098] By comparing the method of the present application with the prior art, the comparison results are shown in Table 1 below.

[0099] Table 1

[0100]

[0101] As can be seen from Table 1, the method of the present application can achieve accurate single-branch positioning in terms of positioning accuracy. Through noise separation, the signal-to-noise ratio of the present application is also better than the existing technology. The monitoring frequency can reach 350MHz, and the life of the stator winding and the monitoring false alarm rate are also better than the existing technology.

[0102] Therefore, this method can reduce downtime (saving maintenance costs) and extend the overhaul cycle from 4 years to 8 years (based on insulation condition trend analysis).

[0103] It should be understood that, although the various steps in the flowcharts involved in the various embodiments described above are displayed in sequence according to the instructions of the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and these steps can be executed in other orders. Moreover, at least a portion of the steps in the flowcharts involved in the various embodiments described above can include multiple steps or multiple stages, and these steps or stages are not necessarily executed and completed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a portion of steps or stages in other steps.

[0104] Based on the same inventive concept, embodiments of the present application also provide a device for monitoring the insulation of a hydro-generator stator winding for implementing the aforementioned method for monitoring the insulation of a hydro-generator stator winding. The solution provided by this device is similar to the solution described in the aforementioned method. Therefore, the specific limitations of one or more embodiments of the device for monitoring the insulation of a hydro-generator stator winding provided below can be found in the aforementioned definition of the method for monitoring the insulation of a hydro-generator stator winding, and will not be further elaborated here.

[0105] In an exemplary embodiment, Figure 6 As shown, an insulation monitoring device for a stator winding of a hydro-generator is provided, comprising:

[0106] An acquisition module 610 is configured to acquire an initial partial discharge signal collected by a capacitive coupler provided on each branch of a stator winding of a hydro-generator; wherein each branch of a stator winding is provided with a capacitive coupler;

[0107] A calculation module 620 is configured to perform cross-correlation calculation on initial partial discharge signals of any two paired capacitive couplers among the capacitive couplers to extract noise characteristics;

[0108] a stripping module 630 for stripping noise features from the initial partial discharge signals of the two capacitive couplers to obtain target partial discharge signals;

[0109] The classification module 640 is used to extract the pulse characteristics of the target partial discharge signal corresponding to each capacitive coupler of the stator winding, input each pulse characteristic into a trained classifier, and obtain the discharge type of each target partial discharge signal to determine the insulation state of the stator winding.

[0110] In one embodiment, the initial partial discharge signal obtained from the capacitive coupler of each branch carries an identifier of the capacitive coupler. The apparatus further includes a positioning module for, when it is determined based on the discharge type of each target partial discharge signal that an insulation fault has occurred in the stator winding, determining the identifier of the capacitive coupler carried by the target partial discharge signal where the insulation fault has occurred; and locating the faulty branch in the stator winding based on the identifier of the capacitive coupler.

[0111] In one embodiment, the device further includes a pairing module for determining, for each phase of the hydro-generator, the number of capacitive couplers belonging to the phase; if the number is an even number, pairing the capacitive couplers in pairs; if the number is an odd number, selecting one of the capacitive couplers as a common coupler to be paired with the two couplers.

[0112] In one embodiment, an oscilloscope is provided after the capacitive coupler provided in each branch, and the capacitive coupler of each branch is connected to the oscilloscope via a coaxial cable; the device also includes a calibration module for injecting a calibration pulse into the busbar end of the stator winding to measure the signal propagation delay of each branch; according to the signal propagation delay of each branch, the cable length of each branch is adjusted so that the signals of two paired branches arrive at the oscilloscope synchronously.

[0113] In one embodiment, the capacitive coupler is fixed by an arc-shaped clip, at least one epoxy mica block and a stainless steel base block; at least one epoxy mica block is located between the stainless steel base block and the arc-shaped clip; the arc-shaped clip includes two separate arc-shaped structures; the arc-shaped clip, at least one epoxy mica block and the stainless steel base block are connected by a fixed structure.

[0114] In one embodiment, the capacitive coupler is made of epoxy mica material.

[0115] Each module in the aforementioned device for monitoring insulation of a hydro-generator stator winding may be implemented in whole or in part through software, hardware, or a combination thereof. Each module may be embedded in or independent of a processor in a computer device in the form of hardware, or may be stored in a memory in the computer device in the form of software, so that the processor can call and execute the corresponding operations of each module.

[0116] In an exemplary embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as shown in FIG. Figure 7 As shown. The computer device includes a processor, memory, an input / output interface, a communication interface, a display unit, and an input device. The processor, memory, and input / output interface are connected via a system bus, and the communication interface, display unit, and input device are connected to the system bus via the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and external devices. The communication interface of the computer device is used to communicate with external terminals via wired or wireless communication, and the wireless communication can be achieved via Wi-Fi, a mobile cellular network, near-field communication (NFC), or other technologies. When executed by the processor, the computer program implements a method for monitoring the insulation of a hydro-turbine generator stator winding. The display unit of the computer device is used to produce a visually visible image and can be a display screen, a projection device, or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad set on the computer device casing, or an external keyboard, touchpad or mouse.

[0117] Those skilled in the art will understand that Figure 7 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.

[0118] In one embodiment, a computer device is further provided, including a memory and a processor. The memory stores a computer program, and the processor implements the steps in the above method embodiments when executing the computer program.

[0119] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0120] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0121] Those skilled in the art will understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. In particular, any reference to memory, database, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The databases involved in the various embodiments provided herein may include at least one of a relational database and a non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the various embodiments provided herein may be, but are not limited to, general-purpose processors, central processing units (CPUs), graphics processing units (GPUs), digital signal processors (DSPs), programmable logic devices (PLDs), data processing logic devices based on quantum computing, artificial intelligence (AI) processors, and the like.

[0122] The technical features of the above embodiments can be combined arbitrarily. In order to make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0123] The above-described embodiments merely represent several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present application. It should be noted that a person of ordinary skill in the art may make various modifications and improvements without departing from the spirit of the present application, and these modifications and improvements fall within the scope of protection of the present application. Therefore, the scope of protection of the present application shall be determined by the appended claims.

Claims

1. A method for monitoring the insulation of a hydro-generator stator winding, characterized in that: The method comprises: Acquiring an initial partial discharge signal collected by a capacitive coupler provided on each branch of a stator winding of a hydro-generator; wherein a capacitive coupler is provided on each branch of the stator winding; For any two capacitive couplers that have a paired relationship among the capacitive couplers, performing cross-correlation calculation on initial partial discharge signals of the two capacitive couplers to extract noise characteristics; stripping the noise feature from the initial partial discharge signals of the two capacitive couplers to obtain a target partial discharge signal; Extracting pulse features of a target partial discharge signal corresponding to each capacitive coupler of the stator winding, inputting each pulse feature into a trained classifier to obtain a discharge type of each target partial discharge signal, so as to determine the insulation state of the stator winding.

2. The method according to claim 1, characterized in that The initial partial discharge signal obtained from the capacitive coupler of each branch carries an identifier of the capacitive coupler; the method further includes: When it is determined that an insulation fault occurs in the stator winding according to the discharge type of each target partial discharge signal, determining an identifier of a capacitive coupler carried by the target partial discharge signal having the insulation fault; The fault branch in the stator winding is located according to the identifier of the capacitive coupler.

3. The method according to claim 1, characterized in that The capacitive couplers are paired in the following manner: For each phase of the hydro-generator, determining the number of capacitive couplers belonging to the phase; If the number is an even number, pair the capacitive couplers in pairs; If the number is an odd number, one of the capacitive couplers is selected as a common coupler to be paired with the two couplers.

4. The method according to claim 1, wherein An oscilloscope is further provided after the capacitive coupler provided on each branch, and the capacitive coupler of each branch is connected to the oscilloscope via a coaxial cable; before obtaining the initial partial discharge signal collected by the capacitive coupler provided on each branch of the stator winding of the hydro-generator, the method further includes: injecting a calibration pulse into a busbar terminal of the stator winding and measuring the signal propagation delay of each branch; According to the signal propagation delay of each branch, the cable length of each branch is adjusted so that the signals of the two paired branches arrive at the oscilloscope synchronously.

5. The method according to any one of claims 1 to 4, characterized in that The capacitive coupler is fixed by an arc-shaped clamping plate, at least one epoxy mica block and a stainless steel base block; The at least one epoxy mica block is located between the stainless steel base block and the arc-shaped clamping plate; the arc-shaped clamping plate includes two separate arc-shaped structures; The arc-shaped clamping plate, the at least one epoxy mica block and the stainless steel base block are connected by a fixed structure.

6. The method according to claim 5, characterized in that The capacitive coupler is made of epoxy mica material.

7. An insulation monitoring device for a hydro-generator stator winding, characterized in that: The device comprises: An acquisition module is used to acquire an initial partial discharge signal collected by a capacitive coupler provided on each branch of the stator winding of the hydro-generator; wherein a capacitive coupler is provided on each branch of the stator winding; a calculation module, configured to perform cross-correlation calculation on initial partial discharge signals of any two capacitive couplers that are paired among the capacitive couplers, and extract noise characteristics; a stripping module, configured to strip the noise feature from the initial partial discharge signals of the two capacitive couplers to obtain a target partial discharge signal; A classification module is configured to extract pulse features of a target partial discharge signal corresponding to each capacitive coupler of the stator winding, input each of the pulse features into a trained classifier, and obtain a discharge type of each target partial discharge signal to determine the insulation state of the stator winding.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images