Fault diagnosis method and system for high-voltage frequency conversion and speed regulation all-in-one machine

Abstract

The invention relates to the technical field of data processing, and discloses a high-voltage frequency conversion and speed regulation all-in-one machine fault diagnosis method and system, and the method comprises the steps: injecting a voltage signal with a preset characteristic frequency into a frequency converter control loop, and obtaining a mixed voltage signal of the frequency converter control loop; separating a common-mode current characteristic waveform of a current signal in the mixed voltage signal in an excitation state; performing high-frequency resonance analysis on the vibration signal of the end part of the stator winding to obtain an insulation defect characteristic frequency spectrum of the end part of the stator winding; performing time-frequency domain correlation analysis on the common-mode current characteristic waveform and the insulation defect characteristic frequency spectrum to obtain an insulation defect characteristic matrix of the high-voltage frequency conversion and speed regulation all-in-one machine; performing degradation degree evaluation on amplitude change and distribution modes of characteristic frequency components in the insulation defect characteristic matrix to obtain a winding insulation degradation level of the high-voltage frequency conversion and speed regulation all-in-one machine; according to the invention, the fault diagnosis accuracy of the high-voltage frequency conversion and speed regulation all-in-one machine can be improved.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a fault diagnosis method and system for a high-voltage variable-frequency speed regulation integrated machine. Background Art

[0002] In the field of fault diagnosis for high-voltage variable-speed inverters, existing technologies often struggle to accurately capture subtle characteristic changes in the detection of insulation defects, resulting in a lag in fault identification. This lack of effective correlation mechanisms in signal processing and analysis prevents the deep integration of multi-dimensional feature information, resulting in unreliable diagnostic results and a struggle to meet the demands of efficient equipment operation and maintenance.

[0003] At the same time, the existing technology for evaluating the degree of winding insulation degradation is relatively simple, relying mostly on the judgment of a single characteristic parameter, and failing to fully consider key factors such as the amplitude change and distribution pattern of the characteristic frequency component. As a result, the accuracy of the judgment of the degradation level is low, and it is easy to make misjudgments or missed judgments, which in turn affects the normal operation of the equipment and the timeliness of maintenance decisions. Summary of the Invention

[0004] The present invention provides a fault diagnosis method and system for a high-voltage variable-frequency speed regulation integrated machine, the main purpose of which is to solve the problems raised in the above-mentioned background technology.

[0005] To achieve the above objectives, the present invention provides a method for diagnosing faults in a high-voltage variable-frequency speed regulating integrated machine, comprising:

[0006] S1. Inject a voltage signal of a preset characteristic frequency into the inverter control loop to obtain a mixed voltage signal of the inverter control loop;

[0007] S2 separates the common-mode current characteristic waveform of the current signal in the mixed voltage signal under the excitation state;

[0008] S3. Perform high-frequency resonance analysis on the vibration signal of the stator winding end to obtain a characteristic spectrum of insulation defects of the stator winding end;

[0009] S4. The common-mode current characteristic waveform and the insulation defect characteristic spectrum are subjected to time-frequency domain correlation analysis to obtain the insulation defect characteristic matrix of the high-voltage variable frequency speed regulating machine;

[0010] S5. Evaluate the degradation degree of the amplitude change and distribution pattern of the characteristic frequency components in the insulation defect characteristic matrix to obtain the winding insulation degradation level of the high-voltage variable frequency speed regulation integrated machine.

[0011] In a preferred embodiment, injecting a voltage signal of a preset characteristic frequency into the inverter control loop to obtain a mixed voltage signal of the inverter control loop includes:

[0012] Modulating the fundamental voltage signal based on the preset characteristic frequency to obtain a modulated voltage signal of the inverter control loop;

[0013] The modulation voltage signal and the operating voltage signal are modulated to obtain a mixed voltage signal of the inverter control loop.

[0014] In a preferred embodiment, separating the common-mode current characteristic waveform of the current signal in the mixed voltage signal under the excitation state includes:

[0015] Extracting a common-mode component of the current signal based on the mixed voltage signal to obtain an original common-mode current of the mixed voltage signal;

[0016] Performing frequency domain bandpass filtering on the original common-mode current to obtain an enhanced common-mode current of the mixed voltage signal;

[0017] The enhanced common-mode current is subjected to time-domain waveform reconstruction to obtain a common-mode current characteristic waveform of the current signal in the mixed voltage signal.

[0018] In a preferred embodiment, the performing of high-frequency resonance analysis on the vibration signal of the stator winding end to obtain the insulation defect characteristic spectrum of the stator winding end includes:

[0019] Performing a short-time Fourier transform on the vibration signal of the stator winding end to obtain a vibration spectrum diagram of the stator winding end;

[0020] Identifying resonance peaks on the vibration spectrum based on an insulation defect feature library to obtain a characteristic peak group of the stator winding end;

[0021] A characteristic spectrum of insulation defects of the stator winding end is constructed based on the frequency offset of the characteristic peak group.

[0022] In a preferred embodiment, constructing the insulation defect characteristic spectrum of the stator winding end based on the frequency offset of the characteristic peak group includes:

[0023] Performing a discrete Fourier transform on the frequency offset of the characteristic peak group to obtain a complex spectrum value of the characteristic peak group, wherein the discrete Fourier transform calculation formula is as follows:

[0024]

[0025] Where, For the The complex spectrum value of the frequency point, The first values, is the total length of the input sequence, is the imaginary unit, is the frequency index, is the sequence index, is the base of natural logarithms, is pi;

[0026] Aggregating the complex spectrum values ​​of the frequency points is the original spectrum signal of the characteristic peak group;

[0027] Performing Butterworth low-pass filtering on the original spectrum signal to obtain a filtered spectrum signal of the characteristic peak group;

[0028] Recombining characteristic frequency points in the filtered spectrum signal to obtain an ordered frequency point sequence of the filtered spectrum signal;

[0029] A characteristic spectrum of insulation defects of the stator winding end is constructed based on the amplitude distribution of the ordered frequency point sequence.

[0030] In a preferred embodiment, the time-frequency domain correlation analysis of the common-mode current characteristic waveform and the insulation defect characteristic spectrum to obtain the insulation defect characteristic matrix of the high-voltage variable frequency speed regulating integrated machine includes:

[0031] Performing a short-time Fourier transform on the common-mode current characteristic waveform to obtain a time-frequency spectrum of the common-mode current characteristic waveform;

[0032] Performing a Hilbert transform on the insulation defect characteristic spectrum to obtain an instantaneous frequency curve of the insulation defect characteristic spectrum;

[0033] Performing frequency domain feature correlation analysis on the time-frequency spectrum and the instantaneous frequency curve to obtain a correlation coefficient matrix of the high-voltage variable frequency speed regulation integrated machine;

[0034] An insulation defect characteristic matrix of the high-voltage variable frequency speed regulation integrated machine is constructed based on the correlation coefficient matrix.

[0035] In a preferred embodiment, the frequency domain feature correlation analysis is performed on the time-frequency spectrum and the instantaneous frequency curve to obtain a correlation coefficient matrix of the high-voltage variable frequency speed regulating integrated machine, including:

[0036] Dividing the time-frequency spectrum into sub-band time-domain graphs according to preset frequency bands;

[0037] Extracting instantaneous frequency segment features corresponding to the sub-band time domain graph in the instantaneous frequency curve;

[0038] Cross-comparing the sub-band time domain graph with the instantaneous frequency segmentation feature to obtain a frequency domain correlation feature set of the high-voltage variable frequency speed regulation integrated machine;

[0039] The frequency domain correlation feature set is structuredly arranged to obtain a correlation coefficient matrix of the high-voltage variable frequency speed regulation integrated machine.

[0040] In a preferred embodiment, the degradation degree evaluation of the amplitude change and distribution pattern of the characteristic frequency components in the insulation defect characteristic matrix to obtain the winding insulation degradation level of the high-voltage variable frequency speed regulating integrated machine includes:

[0041] Performing a spectrum cluster analysis on the amplitude change of the characteristic frequency component to obtain a characteristic frequency cluster of the high-voltage variable frequency speed regulation integrated machine;

[0042] Performing spatial density weighting on the spatial distribution density of the characteristic frequency components in the characteristic frequency cluster to obtain a degradation weight coefficient of the characteristic frequency cluster;

[0043] A multi-parameter evaluation of insulation degradation is performed on the degradation weight coefficient and the amplitude variation of the characteristic frequency cluster to obtain the winding insulation degradation level of the high-voltage variable frequency speed regulation integrated machine.

[0044] In a preferred embodiment, the spectrum clustering analysis of the amplitude change of the characteristic frequency component to obtain the characteristic frequency cluster of the high-voltage variable frequency speed regulating integrated machine includes:

[0045] constructing an amplitude-time variation curve of the characteristic frequency component based on the amplitude time series data of the characteristic frequency component;

[0046] performing cluster analysis on the characteristic frequency components based on the amplitude-time variation curve to obtain an initial cluster of the characteristic frequency components;

[0047] Dynamic clustering optimization is performed on the initial cluster to obtain a characteristic frequency cluster of the high-voltage variable frequency speed regulation integrated machine.

[0048] In order to solve the above problems, the present invention also provides a high-voltage variable frequency speed regulation integrated machine fault diagnosis system, the system comprising:

[0049] A mixed voltage signal acquisition module is used to inject a voltage signal of a preset characteristic frequency into the inverter control loop to obtain a mixed voltage signal of the inverter control loop;

[0050] A comprehensive common-mode current characteristic waveform module, used to separate the common-mode current characteristic waveform of the current signal in the mixed voltage signal under the excitation state;

[0051] An insulation defect characteristic spectrum acquisition module is used to perform high-frequency resonance analysis on the vibration signal of the stator winding end to obtain the insulation defect characteristic spectrum of the stator winding end;

[0052] An insulation defect characteristic matrix construction module is used to perform time-frequency domain correlation analysis on the common-mode current characteristic waveform and the insulation defect characteristic spectrum to obtain the insulation defect characteristic matrix of the high-voltage variable frequency speed regulation integrated machine;

[0053] The winding insulation degradation level assessment module is used to assess the degradation degree of the amplitude change and distribution pattern of the characteristic frequency component in the insulation defect characteristic matrix to obtain the winding insulation degradation level of the high-voltage variable frequency speed regulation integrated machine.

[0054] Compared with the prior art, the present invention has the following beneficial effects:

[0055] 1. The high-voltage variable-frequency speed regulation integrated machine fault diagnosis method and system provided by the present invention constructs an insulation defect characteristic matrix and performs degradation degree assessment by injecting a voltage signal of a preset characteristic frequency into the inverter control loop, combining the time-frequency domain correlation analysis of the common-mode current characteristic waveform and the characteristic spectrum of the stator winding end insulation defect. This method and system can accurately capture subtle changes in winding insulation, greatly improving the accuracy and pertinence of fault diagnosis, and making the diagnostic process more scientific and effective.

[0056] 2. This technology accurately determines the level of winding insulation degradation by performing a multi-dimensional analysis of the amplitude changes and distribution patterns of characteristic frequency components. This allows for early detection of insulation defects and assessment of their degree of degradation, facilitating timely maintenance measures, reducing troubleshooting time, and improving equipment reliability. This in turn enhances overall fault diagnosis efficiency, providing strong support for the stable operation of high-voltage variable-frequency speed control systems. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] Figure 1 A schematic flow chart of a method for diagnosing a fault of a high-voltage variable-frequency speed regulating integrated machine provided by one embodiment of the present invention;

[0058] Figure 2 A functional module diagram of a high-voltage variable-frequency speed regulation integrated machine fault diagnosis system provided by one embodiment of the present invention;

[0059] The purpose, features and advantages of the present invention will be further described with reference to the accompanying drawings and in conjunction with the embodiments. DETAILED DESCRIPTION

[0060] It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0061] An embodiment of the present application provides a method for diagnosing faults of a high-voltage variable frequency speed regulating integrated machine. The execution subject of the method for diagnosing faults of a high-voltage variable frequency speed regulating integrated machine includes but is not limited to at least one of the electronic devices such as a server and a terminal that can be configured to execute the method provided by the embodiment of the present application. In other words, the method for diagnosing faults of a high-voltage variable frequency speed regulating integrated machine can be executed by software or hardware installed on a terminal device or a server device. The server includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, etc. The server can be an independent server, or it can be a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (CDNs), and big data and artificial intelligence platforms.

[0062] Reference Figure 1 FIG. 1 is a flow chart of a method for diagnosing a fault of a high-voltage variable-frequency speed regulating integrated machine provided by an embodiment of the present invention. In this embodiment, the method for diagnosing a fault of a high-voltage variable-frequency speed regulating integrated machine includes:

[0063] S1. Inject a voltage signal of a preset characteristic frequency into the inverter control loop to obtain a mixed voltage signal of the inverter control loop;

[0064] In an embodiment of the present invention, injecting a voltage signal of a preset characteristic frequency into the inverter control loop to obtain a mixed voltage signal of the inverter control loop includes:

[0065] Modulating the fundamental voltage signal based on the preset characteristic frequency to obtain a modulated voltage signal of the inverter control loop;

[0066] The modulation voltage signal and the operating voltage signal are modulated to obtain a mixed voltage signal of the inverter control loop.

[0067] Specifically, the fundamental voltage signal is modulated based on the preset characteristic frequency to obtain the modulated voltage signal of the inverter control loop.

[0068] Furthermore, according to the changing rule of the preset characteristic frequency, the amplitude of the fundamental voltage signal is adjusted so that the amplitude of the fundamental voltage signal changes with the change of the preset characteristic frequency, keeping the frequency of the fundamental voltage signal unchanged and only changing its amplitude. The voltage signal obtained after such amplitude modulation is the modulated voltage signal of the inverter control loop.

[0069] Furthermore, the modulation voltage signal and the operating voltage signal are modulated to obtain a mixed voltage signal of the inverter control loop.

[0070] Furthermore, the modulated voltage signal and the working voltage signal are superimposed in time so that they exist simultaneously in the same circuit. During the superposition process, the waveform and frequency characteristics of the modulated voltage signal and the working voltage signal are kept unchanged, and their voltage values ​​are added to obtain a new voltage signal. This new voltage signal contains all the characteristics of the modulated voltage signal and the working voltage signal, which is the mixed voltage signal of the inverter control loop.

[0071] In general, the fundamental voltage signal is modulated based on the preset characteristic frequency to obtain the modulated voltage signal of the inverter control loop, which can make the injected voltage signal carry a specific frequency identification, enhance the characteristic response related to insulation defects, provide a clear basis for the subsequent accurate capture of fault signals, improve the identifiability of fault characteristics, and thus improve the diagnostic accuracy.

[0072] In general, the modulated voltage signal and the working voltage signal are modulated to obtain a mixed voltage signal of the inverter control loop, which can introduce a characteristic signal when the equipment is in normal working condition, without affecting the operation of the equipment. At the same time, the mixed signal can contain both working status information and preset characteristic information, making fault diagnosis more in line with actual operating scenarios, reducing misjudgments caused by signal distortion, and further improving the accuracy of fault diagnosis.

[0073] S2 separates the common-mode current characteristic waveform of the current signal in the mixed voltage signal under the excitation state;

[0074] In an embodiment of the present invention, separating the common-mode current characteristic waveform of the current signal in the mixed voltage signal in the excitation state includes:

[0075] Extracting a common-mode component of the current signal based on the mixed voltage signal to obtain an original common-mode current of the mixed voltage signal;

[0076] Performing frequency domain bandpass filtering on the original common-mode current to obtain an enhanced common-mode current of the mixed voltage signal;

[0077] The enhanced common-mode current is subjected to time-domain waveform reconstruction to obtain a common-mode current characteristic waveform of the current signal in the mixed voltage signal.

[0078] Specifically, the common-mode component of the current signal is extracted based on the mixed voltage signal to obtain the original common-mode current of the mixed voltage signal. Specifically, the current signal value at each time point in the mixed voltage signal is added, and then the sum is divided by the number of channels of the signal to obtain the average current value at each time point. These average current values ​​are arranged in chronological order, and the current sequence formed is the original common-mode current of the mixed voltage signal.

[0079] Furthermore, the original common-mode current is subjected to frequency-domain bandpass filtering to obtain an enhanced common-mode current of the mixed voltage signal.

[0080] Furthermore, the original common-mode current is converted to the frequency domain, and the signal components with frequencies within a preset range are identified. The signal components within these frequency ranges are retained, and the signal components at other frequencies are removed. The processed frequency domain signal is then converted back to the time domain, and the resulting current signal is the enhanced common-mode current of the mixed voltage signal.

[0081] Furthermore, the enhanced common-mode current is subjected to time-domain waveform reconstruction to obtain a common-mode current characteristic waveform of the current signal in the mixed voltage signal.

[0082] Furthermore, the value of each time point of the enhanced common-mode current is interpolated to increase the density of data points to make the waveform smoother, and the peak, valley, period and other characteristics of the waveform are analyzed. The waveform is adjusted and optimized based on these characteristics to make the characteristics of the waveform more obvious and prominent.

[0083] Furthermore, the waveform obtained after such processing is the common-mode current characteristic waveform of the current signal in the mixed voltage signal.

[0084] In general, the common-mode component of the current signal is extracted based on the mixed voltage signal to obtain the original common-mode current of the mixed voltage signal. This can accurately separate the common-mode component from the mixed signal, focus on the current characteristics related to insulation defects, lay a reliable foundation for subsequent analysis, reduce irrelevant signal interference, and improve the targeted diagnosis.

[0085] In general, the original common-mode current is subjected to frequency domain bandpass filtering to obtain the enhanced common-mode current of the mixed voltage signal, which can filter out noise and non-target frequency components, strengthen the common-mode current characteristics related to the fault, make the effective signal more prominent, reduce the impact of noise on the diagnostic results, and improve the accuracy of feature recognition.

[0086] In general, the time domain waveform of the enhanced common-mode current is reconstructed to obtain the common-mode current characteristic waveform of the current signal in the mixed voltage signal, which can optimize the waveform shape and clearly present the characteristic details of the common-mode current, facilitate subsequent correlation analysis with the insulation defect spectrum, enhance the accuracy of feature matching, and thus improve the accuracy of fault diagnosis.

[0087] S3. Perform high-frequency resonance analysis on the vibration signal of the stator winding end to obtain a characteristic spectrum of insulation defects of the stator winding end;

[0088] In an embodiment of the present invention, performing high-frequency resonance analysis on the vibration signal of the stator winding end to obtain the insulation defect characteristic spectrum of the stator winding end includes:

[0089] Performing a short-time Fourier transform on the vibration signal of the stator winding end to obtain a vibration spectrum diagram of the stator winding end;

[0090] Identifying resonance peaks on the vibration spectrum based on an insulation defect feature library to obtain a characteristic peak group of the stator winding end;

[0091] A characteristic spectrum of insulation defects of the stator winding end is constructed based on the frequency offset of the characteristic peak group.

[0092] The step of constructing the insulation defect characteristic spectrum of the stator winding end based on the frequency offset of the characteristic peak group includes:

[0093] Performing a discrete Fourier transform on the frequency offset of the characteristic peak group to obtain a complex spectrum value of the characteristic peak group, wherein the discrete Fourier transform calculation formula is as follows:

[0094]

[0095] Where, For the The complex spectrum value of the frequency point, The first values, is the total length of the input sequence, is the imaginary unit, is the frequency index, is the sequence index, is the base of natural logarithms, is pi;

[0096] Aggregating the complex spectrum values ​​of the frequency points is the original spectrum signal of the characteristic peak group;

[0097] Performing Butterworth low-pass filtering on the original spectrum signal to obtain a filtered spectrum signal of the characteristic peak group;

[0098] Recombining characteristic frequency points in the filtered spectrum signal to obtain an ordered frequency point sequence of the filtered spectrum signal;

[0099] A characteristic spectrum of insulation defects of the stator winding end is constructed based on the amplitude distribution of the ordered frequency point sequence.

[0100] Specifically, a short-time Fourier transform is performed on the vibration signal of the stator winding end to obtain a vibration spectrum diagram of the stator winding end.

[0101] Furthermore, the vibration signal at the end of the stator winding is divided into multiple continuous time periods of equal length in chronological order, and the vibration signal in each time period is subjected to Fourier transform to calculate the different frequency components contained in the signal in the time period and their corresponding amplitudes.

[0102] Furthermore, the frequency components and amplitude information of each time period are organized into a two-dimensional spectrum, where the horizontal axis represents time and the vertical axis represents frequency. The brightness or color of each point in the spectrum represents the amplitude of the frequency component at that time point. The two-dimensional spectrum formed is the vibration spectrum diagram of the stator winding end.

[0103] Furthermore, the resonance peak of the vibration spectrum diagram is identified based on the insulation defect feature library to obtain the characteristic peak group of the stator winding end. Specifically, each frequency component and amplitude of the vibration spectrum diagram are compared with the standard insulation defect characteristics pre-stored in the insulation defect feature library to find the peak value in the vibration spectrum diagram whose amplitude is significantly higher than the surrounding frequency components.

[0104] Furthermore, it is determined whether the frequency and amplitude characteristics of these peaks match the standard characteristics in the insulation defect feature library, and the peaks that are successfully matched are selected and grouped. Each group of peak sets formed is the characteristic peak group of the stator winding end.

[0105] Furthermore, based on the frequency offset of the characteristic peak group, the insulation defect characteristic spectrum of the stator winding end is constructed. Specifically, for each characteristic peak group, the difference between the actual frequency of each peak and the corresponding standard frequency in the insulation defect characteristic library is calculated. This difference is the frequency offset.

[0106] Furthermore, the frequency offset distribution of all characteristic peak groups is analyzed, and peaks with similar frequency offsets are classified into one category. The number and amplitude of peaks corresponding to each type of frequency offset are counted, and each type of frequency offset and its corresponding number and amplitude of peaks are sorted into a spectrum diagram in order from small to large frequency offset. This spectrum diagram is the characteristic spectrum of the insulation defect at the end of the stator winding.

[0107] Specifically, a discrete Fourier transform is performed on the frequency offset of the characteristic peak group to obtain the complex spectrum value of the characteristic peak group. Specifically, all the frequency offsets in the characteristic peak group are arranged into a sequence in chronological order, and this sequence is decomposed into a combination of sine waves and cosine waves of different frequencies. The amplitude and phase of the sine wave and cosine wave corresponding to each frequency are represented by a complex number. These complex numbers correspond to the spectrum values ​​of each frequency point, and these values ​​are the complex spectrum values ​​of the characteristic peak group.

[0108] Furthermore, the complex spectrum values ​​of the frequency points are collected as the original spectrum signal of the characteristic peak group. Specifically, the complex spectrum values ​​corresponding to each frequency point are arranged in order from low to high frequency points, so that these values ​​form a continuous signal sequence containing all frequency point information. This sequence fully reflects the spectrum characteristics of the characteristic peak group at each frequency. This sequence is the original spectrum signal of the characteristic peak group.

[0109] Furthermore, the original spectrum signal is subjected to Butterworth low-pass filtering to obtain the filtered spectrum signal of the characteristic peak group. Specifically, a fixed cutoff frequency is set and the original spectrum signal is processed to allow signal components with frequencies lower than the cutoff frequency to pass through, while preventing signal components with frequencies higher than the cutoff frequency from passing through. After such processing, the high-frequency noise components in the original spectrum signal are removed, and the retained signal is the filtered spectrum signal of the characteristic peak group.

[0110] Furthermore, the characteristic frequency points in the filtered spectrum signal are recombined to obtain an ordered frequency point sequence of the filtered spectrum signal.

[0111] Furthermore, characteristic frequency points with amplitudes significantly higher than those of the surrounding frequency points are selected from the filtered spectrum signal, and the frequency value and corresponding amplitude of each characteristic frequency point are recorded. These characteristic frequency points are arranged in order from low to high frequency values ​​to form a list arranged in order by frequency. This list is the ordered frequency point sequence of the filtered spectrum signal.

[0112] Furthermore, a characteristic spectrum of insulation defects of the stator winding end is constructed based on the amplitude distribution of the ordered frequency point sequence.

[0113] Furthermore, with the frequency value in the ordered frequency point sequence as the horizontal axis and the amplitude corresponding to each frequency value as the vertical axis, the position of each characteristic frequency point is marked one by one in the coordinate system, and these points are connected in sequence with lines to form a continuous curve. The ups and downs of the curve reflect the amplitude distribution at different frequencies. The spectrum formed by this curve is the characteristic spectrum of the insulation defect at the end of the stator winding.

[0114] Specifically, It is through the input sequence The result obtained by combining and calculating each value in the frequency index according to a specific rule is that each input value is multiplied by a and sequence index The relevant complex factors, then add all the products together, and the sum is the corresponding frequency point The complex spectrum value of . is the first numerical values, and the sequence is obtained by arranging the frequency offsets of the characteristic peak groups in chronological order. is the input sequence The total number of values ​​contained in . It is the symbol for the imaginary unit in mathematics and is used to construct complex numbers. It is used to identify the index of different frequency points, starting from 0 and increasing in sequence until , each The value corresponds to a specific frequency point. It is used to identify the index of each numerical position in the input sequence, starting from 0 and increasing in sequence until . It is the base of natural logarithms and is a fixed mathematical constant. It is pi, which is also a fixed mathematical constant.

[0115] Furthermore, the meaning of this formula is to transform the input sequence in the time domain into Convert to the frequency domain and get a series of complex spectrum values , each complex spectral value Represents the original sequence at the corresponding frequency point Through this conversion, we can analyze which frequency components are contained in the original sequence and the strength of each frequency component, so as to understand the frequency characteristics of the signal more clearly.

[0116] Furthermore, when the input sequence When the value in changes rapidly, the complex spectrum value obtained by calculation The amplitude in the high-frequency region is relatively large, which indicates that the original sequence contains more high-frequency components; when the input sequence When the value in changes slowly, the complex spectrum value The amplitude in the low-frequency region is relatively large, which indicates that the original sequence mainly contains low-frequency components; if the input sequence The values ​​in hardly change with time, so most of the complex spectrum values It will be concentrated in the low-frequency area with a larger amplitude, while the amplitude in the high-frequency area is very small.

[0117] In general, performing a short-time Fourier transform on the vibration signal at the end of the stator winding to obtain a vibration spectrum diagram of the end of the stator winding can convert the vibration signal into a two-dimensional time-frequency spectrum, clearly presenting the frequency components and amplitude changes at different times, accurately capturing the high-frequency resonance characteristics related to insulation defects, providing a detailed signal basis for fault diagnosis, and improving the accuracy of feature recognition.

[0118] In general, the resonance peaks of the vibration spectrum are identified based on the insulation defect feature library to obtain the characteristic peak group of the stator winding end. The key peaks in the spectrum can be screened with the help of known defect characteristics to eliminate irrelevant peak interference and focus on the characteristic peaks directly related to the insulation defects, ensuring that the extracted features have clear directionality and reducing the impact of invalid information on diagnosis.

[0119] In general, constructing the insulation defect characteristic spectrum of the stator winding end based on the frequency offset of the characteristic peak group can reflect subtle changes in the insulation defect through the quantitative indicator of frequency offset, convert the scattered characteristic peaks into a structured spectrum, clearly present the distribution pattern of the defect characteristics, make the diagnosis basis more systematic and quantitative, and further improve the accuracy of fault diagnosis.

[0120] In general, performing a discrete Fourier transform on the frequency offset of the characteristic peak group can obtain the complex spectrum value of the characteristic peak group, which can convert the time domain signal of the frequency offset into a complex representation in the frequency domain, completely retain the amplitude and phase information of the frequency component, accurately capture the frequency domain characteristics of the characteristic peak group, provide comprehensive basic data for subsequent analysis, and improve the accuracy of diagnosis.

[0121] In general, the complex spectrum values ​​of the frequency points are aggregated as the original spectrum signals of the characteristic peak group, which can integrate the information of each frequency point to form a continuous spectrum signal, fully present the overall frequency domain distribution of the characteristic peak group, avoid feature omissions caused by scattered information, ensure that subsequent processing is based on a complete feature set, and reduce diagnostic bias.

[0122] In general, performing Butterworth low-pass filtering on the original spectrum signal to obtain the filtered spectrum signal of the characteristic peak group can effectively filter out high-frequency noise interference, retain the low-frequency characteristic signals related to insulation defects, make the spectrum signal purer, reduce the interference of noise on feature recognition, and improve the accuracy of feature extraction.

[0123] In general, the characteristic frequency points in the filtered spectrum signal are reorganized to obtain an ordered frequency point sequence of the filtered spectrum signal. The characteristic frequency points can be sorted out according to a regular pattern, the frequency points are arranged in an orderly manner, and the distribution logic of the characteristic frequencies is clearly presented, which facilitates the rapid positioning of key defect features and enhances the targeted diagnosis.

[0124] In general, constructing the insulation defect characteristic spectrum of the stator winding end based on the amplitude distribution of the ordered frequency point sequence can convert the amplitude distribution of the ordered frequency points into a structured spectrum, intuitively reflecting the frequency and amplitude correlation of the insulation defect characteristics, providing a clear and quantitative feature basis for fault diagnosis, and further improving the diagnostic accuracy.

[0125] S4. The common-mode current characteristic waveform and the insulation defect characteristic spectrum are subjected to time-frequency domain correlation analysis to obtain the insulation defect characteristic matrix of the high-voltage variable frequency speed regulating machine;

[0126] In an embodiment of the present invention, performing time-frequency domain correlation analysis on the common-mode current characteristic waveform and the insulation defect characteristic spectrum to obtain an insulation defect characteristic matrix of the high-voltage variable frequency speed regulating integrated machine includes:

[0127] Performing a short-time Fourier transform on the common-mode current characteristic waveform to obtain a time-frequency spectrum of the common-mode current characteristic waveform;

[0128] Performing a Hilbert transform on the insulation defect characteristic spectrum to obtain an instantaneous frequency curve of the insulation defect characteristic spectrum;

[0129] Performing frequency domain feature correlation analysis on the time-frequency spectrum and the instantaneous frequency curve to obtain a correlation coefficient matrix of the high-voltage variable frequency speed regulation integrated machine;

[0130] An insulation defect characteristic matrix of the high-voltage variable frequency speed regulation integrated machine is constructed based on the correlation coefficient matrix.

[0131] The frequency domain feature correlation analysis is performed on the time-frequency spectrum diagram and the instantaneous frequency curve to obtain a correlation coefficient matrix of the high-voltage variable frequency speed regulation integrated machine, including:

[0132] Dividing the time-frequency spectrum into sub-band time-domain graphs according to preset frequency bands;

[0133] Extracting instantaneous frequency segment features corresponding to the sub-band time domain graph from the instantaneous frequency curve;

[0134] Cross-comparing the sub-band time domain graph with the instantaneous frequency segmentation feature to obtain a frequency domain correlation feature set of the high-voltage variable frequency speed regulation integrated machine;

[0135] The frequency domain correlation feature set is structuredly arranged to obtain a correlation coefficient matrix of the high-voltage variable frequency speed regulation integrated machine.

[0136] Specifically, a short-time Fourier transform is performed on the common-mode current characteristic waveform to obtain a time-frequency spectrum diagram of the common-mode current characteristic waveform. Specifically, the common-mode current characteristic waveform is divided into multiple time periods of equal length, the waveform in each time period is Fourier transformed, and the different frequency components contained in the waveform in the time period and their corresponding amplitudes are calculated. The frequency components and amplitude information of each time period are organized into a two-dimensional spectrum, in which the horizontal axis represents time and the vertical axis represents frequency. The brightness or color of each point in the spectrum represents the amplitude of the frequency component at that time point. The formed two-dimensional spectrum is the time-frequency spectrum diagram of the common-mode current characteristic waveform.

[0137] Furthermore, a Hilbert transform is performed on the insulation defect characteristic spectrum to obtain an instantaneous frequency curve of the insulation defect characteristic spectrum. Specifically, an inverse Fourier transform is first performed on the insulation defect characteristic spectrum to convert it from the frequency domain back to a time domain signal. The obtained time domain signal is Hilbert transformed to construct an analytical signal of the signal. The instantaneous frequency at each time point is calculated by the phase change rate of the analytical signal. These instantaneous frequencies are connected in chronological order to form a continuous curve. This curve is the instantaneous frequency curve of the insulation defect characteristic spectrum.

[0138] Furthermore, a frequency domain feature correlation analysis is performed on the time-frequency spectrum and the instantaneous frequency curve to obtain a correlation coefficient matrix of the high-voltage variable frequency speed regulation integrated machine. Specifically, the main frequency components and their amplitudes at each time point are extracted from the time-frequency spectrum, and the instantaneous frequency values ​​at each time point are extracted from the instantaneous frequency curve. The frequency components in the time-frequency spectrum and the instantaneous frequency values ​​in the instantaneous frequency curve at the same time point are compared to evaluate the similarity and consistency of their changing trends. A numerical value is used to represent this correlation. Such a correlation evaluation is performed on the frequency components and instantaneous frequency values ​​at all time points. All the obtained correlation values ​​are organized into a matrix, and the rows and columns of the matrix correspond to different time points and frequency components, respectively. This matrix is ​​the correlation coefficient matrix of the high-voltage variable frequency speed regulation integrated machine.

[0139] Furthermore, an insulation defect characteristic matrix of the high-voltage variable frequency speed regulation integrated machine is constructed based on the correlation coefficient matrix. Specifically, the correlation coefficient matrix is ​​normalized so that all values ​​in the matrix are in the range of 0 to 1, thereby enhancing the comparability of the values. According to the size of the normalized correlation coefficient, the degree of correlation between each frequency component and the insulation defect is determined. The higher the correlation coefficient, the stronger the correlation between the frequency component and the insulation defect. The frequency components with high correlation and their corresponding correlation coefficients are arranged into a new matrix according to certain rules. This matrix is ​​the insulation defect characteristic matrix of the high-voltage variable frequency speed regulation integrated machine.

[0140] Specifically, the time-spectrogram is divided into sub-band time domain graphs according to preset frequency bands. Specifically, multiple preset frequency band ranges are determined, and each frequency band range contains a certain frequency interval. In the time-spectrogram, all frequency components belonging to the same frequency band range and their corresponding amplitude information are extracted, and recombined according to the original time sequence to form a new time domain graph that only contains frequency components within the frequency band range. Such extraction and recombination operations are performed on each preset frequency band, and the multiple new time domain graphs obtained are sub-band time domain graphs.

[0141] Furthermore, the instantaneous frequency segmentation features corresponding to the sub-band time domain diagram in the instantaneous frequency curve are extracted. Specifically, on the instantaneous frequency curve, the part with the same time range as each sub-band time domain diagram is found, this part of the curve is cut out separately, and the features of the cut-out curve segment are analyzed, including the average frequency value of the curve, the amplitude range of the frequency change, the rate of frequency change, and the trend of the frequency change, etc. The features obtained from these analyses are organized into a set of feature descriptions. This set of feature descriptions is the instantaneous frequency segmentation features corresponding to the sub-band time domain diagram.

[0142] Furthermore, the sub-band time domain diagram is cross-compared with the instantaneous frequency segmentation feature to obtain the frequency domain correlation feature set of the high-voltage variable frequency speed regulation integrated machine. Specifically, the frequency components and amplitude changes in each sub-band time domain diagram are compared in detail with the corresponding instantaneous frequency segmentation feature, and it is observed whether the frequency component changes in the sub-band time domain diagram are consistent with the frequency change trend in the instantaneous frequency segmentation feature at the same time point. The similarity and correlation strength between the two are evaluated, and the comparison results of all sub-band time domain diagrams and the corresponding instantaneous frequency segmentation features are organized into a set. This set is the frequency domain correlation feature set of the high-voltage variable frequency speed regulation integrated machine.

[0143] Furthermore, the frequency domain correlation feature set is structured and arranged to obtain the correlation coefficient matrix of the high-voltage variable frequency speed regulation integrated machine. Specifically, each correlation feature in the frequency domain correlation feature set is classified and sorted according to certain rules, and the position of each correlation feature in the matrix is ​​determined. According to the similarity and correlation strength of the correlation features, a numerical value is assigned to each correlation feature to represent its correlation coefficient. The correlation coefficients corresponding to all correlation features are filled into a matrix according to the determined positions to form a regularly arranged matrix table. This matrix table is the correlation coefficient matrix of the high-voltage variable frequency speed regulation integrated machine.

[0144] In general, performing a short-time Fourier transform on the common-mode current characteristic waveform to obtain a time-frequency spectrum of the common-mode current characteristic waveform can convert the time domain characteristics of the common-mode current into a two-dimensional time-frequency characteristic, clearly present the frequency changes at different times, accurately capture the dynamic characteristics related to insulation defects, provide detailed time-frequency information for correlation analysis, and improve the accuracy of feature matching.

[0145] In general, the insulation defect characteristic spectrum is subjected to Hilbert transform to obtain the instantaneous frequency curve of the insulation defect characteristic spectrum, which can extract the instantaneous frequency characteristics of the spectrum changing with time, reflect the dynamic evolution law of the insulation defect, convert the static spectrum into a dynamic characteristic curve, enhance the correlation with the common mode current time-frequency characteristics, and provide a dynamic basis for subsequent correlation analysis.

[0146] In general, the frequency domain feature correlation analysis is performed on the time-frequency spectrum diagram and the instantaneous frequency curve to obtain the correlation coefficient matrix of the high-voltage variable frequency speed regulation integrated machine, which can quantify the degree of correlation between the two in the frequency domain, clarify the matching relationship of different frequency components, filter out irrelevant correlations, focus on the characteristic connections directly related to insulation defects, and reduce analysis deviations.

[0147] In general, the insulation defect feature matrix of the high-voltage variable frequency speed regulation integrated machine is constructed based on the correlation coefficient matrix, and the multi-dimensional correlation features can be integrated into a structured matrix. The system presents the comprehensive characteristics of the insulation defects, making the diagnosis basis more comprehensive and clearer, and effectively improving the accuracy of fault diagnosis.

[0148] Dividing the time-frequency spectrum into sub-band time-domain diagrams according to preset frequency bands can refine the complex time-frequency information into frequency bands, focus on the feature changes within each frequency band, avoid information confusion during overall analysis, lay the foundation for accurate correlation analysis, enhance the pertinence of feature extraction, and help improve diagnostic accuracy.

[0149] In general, extracting the instantaneous frequency segmentation features corresponding to the sub-band time domain diagram in the instantaneous frequency curve can make the instantaneous frequency features and the sub-band time domain diagram accurately correspond in time and frequency band, ensure that the comparison between the two is carried out in the same dimension, reduce the correlation deviation caused by feature misalignment, and enhance the accuracy of feature association.

[0150] In general, the sub-band time domain diagram is cross-compared with the instantaneous frequency segmentation characteristics to obtain the frequency domain correlation feature set of the high-voltage variable frequency speed regulation integrated machine, which can comprehensively explore the correlation relationship between the time-frequency characteristics and the instantaneous frequency characteristics in different frequency bands, capture subtle correlation differences, enrich the dimensions of the correlation features, and provide a more comprehensive basis for diagnosis.

[0151] In general, the frequency domain correlation feature set is structuredly arranged to obtain the correlation coefficient matrix of the high-voltage variable frequency speed regulation integrated machine, which can systematize and quantify the scattered correlation features, clearly reflect the correlation strength between each feature, facilitate the rapid identification of key correlations, reduce analysis errors, and further improve the accuracy of fault diagnosis.

[0152] S5. Evaluate the degradation degree of the amplitude change and distribution pattern of the characteristic frequency components in the insulation defect characteristic matrix to obtain the winding insulation degradation level of the high-voltage variable frequency speed regulation integrated machine.

[0153] In an embodiment of the present invention, the degradation degree evaluation of the amplitude change and distribution pattern of the characteristic frequency component in the insulation defect characteristic matrix to obtain the winding insulation degradation level of the high-voltage variable frequency speed regulating integrated machine includes:

[0154] Performing a spectrum cluster analysis on the amplitude change of the characteristic frequency component to obtain a characteristic frequency cluster of the high-voltage variable frequency speed regulation integrated machine;

[0155] Performing spatial density weighting on the spatial distribution density of the characteristic frequency components in the characteristic frequency cluster to obtain a degradation weight coefficient of the characteristic frequency cluster;

[0156] A multi-parameter evaluation of insulation degradation is performed on the degradation weight coefficient and the amplitude variation of the characteristic frequency cluster to obtain the winding insulation degradation level of the high-voltage variable frequency speed regulation integrated machine.

[0157] The spectrum clustering analysis of the amplitude change of the characteristic frequency component to obtain the characteristic frequency cluster of the high-voltage variable frequency speed regulating integrated machine includes:

[0158] constructing an amplitude-time variation curve of the characteristic frequency component based on the amplitude time series data of the characteristic frequency component;

[0159] performing cluster analysis on the characteristic frequency components based on the amplitude-time variation curve to obtain an initial cluster of the characteristic frequency components;

[0160] Dynamic clustering optimization is performed on the initial cluster to obtain a characteristic frequency cluster of the high-voltage variable frequency speed regulation integrated machine.

[0161] Specifically, a spectral clustering analysis is performed on the amplitude changes of the characteristic frequency components to obtain the characteristic frequency clusters of the high-voltage variable frequency speed regulation integrated machine. Specifically, the amplitude change data of all characteristic frequency components are extracted from the insulation defect characteristic matrix, and the amplitude change trend of each frequency component at different times is recorded. The frequency components with the same or similar change trends are grouped together. By comparing the amplitude change rules of the frequency components in each group, it is ensured that the change patterns of the components within the group are consistent, and there are obvious differences in the change patterns of the components between groups. Each group finally formed is the characteristic frequency cluster of the high-voltage variable frequency speed regulation integrated machine.

[0162] Furthermore, the spatial distribution density of the characteristic frequency components in the characteristic frequency cluster is spatially density-weighted to obtain the degradation weight coefficient of the characteristic frequency cluster. Specifically, the spatial distribution positions of all characteristic frequency components in each characteristic frequency cluster in the insulation structure are counted, and the number of characteristic frequency components of the cluster contained in a unit spatial range is calculated. This number is used as the spatial distribution density, and a weighting rule is set according to the size of the spatial distribution density. The higher the density of the characteristic frequency cluster, the greater the weight it occupies in the degradation assessment. According to this rule, each characteristic frequency cluster is assigned a corresponding numerical value, which is the degradation weight coefficient of the characteristic frequency cluster.

[0163] Furthermore, a multi-parameter evaluation of insulation degradation is performed on the degradation weight coefficient and the amplitude change amplitude of the characteristic frequency cluster to obtain the winding insulation degradation level of the high-voltage variable frequency speed regulation integrated machine. Specifically, the degradation weight coefficient of each characteristic frequency cluster is multiplied by the amplitude change amplitude of the cluster to obtain the insulation degradation evaluation value of each cluster. The evaluation values ​​of all characteristic frequency clusters are summarized to obtain a total evaluation result. The total evaluation result is compared with the preset winding insulation degradation level classification standard. The standard interval into which the total evaluation result falls, the corresponding interval level is the winding insulation degradation level of the high-voltage variable frequency speed regulation integrated machine.

[0164] Specifically, the amplitude data of each characteristic frequency component at different time points are obtained to form the amplitude time series data of the characteristic frequency component. With time as the horizontal axis and amplitude as the vertical axis, the amplitude data corresponding to each time point are marked in the coordinate system, and then these marked points are connected in chronological order. The continuous line formed is the amplitude-time change curve of the characteristic frequency component.

[0165] Furthermore, the amplitude-time variation curves of all characteristic frequency components are compared, and the overall direction, fluctuation amplitude and variation rhythm of the curves are observed. The characteristic frequency components with similar curve shapes and consistent variation trends are grouped into the same group, so that the curves of each component within the group maintain a high degree of consistency in the variation pattern, and the curves of each component between groups have significant differences in the variation pattern. Each group obtained after such grouping is the initial cluster of characteristic frequency components.

[0166] Furthermore, the characteristic frequency components in each initial cluster are checked one by one, and their amplitude-time variation curves are re-compared. If it is found that the curve of a component is significantly different from the curves of other components in the cluster, the component is removed from the initial cluster and reallocated to a more matching initial cluster. At the same time, different initial clusters with very similar curve characteristics are merged so that the curve characteristics of the components in each cluster after adjustment are completely consistent. The stable grouping finally obtained is the characteristic frequency cluster of the high-voltage variable frequency speed regulation integrated machine.

[0167] In general, by performing spectral clustering analysis on the amplitude changes of the characteristic frequency components, the characteristic frequency clusters of the high-voltage variable frequency speed regulation integrated machine are obtained. Frequency components with similar change trends can be classified, focusing on the overall change rules of similar features, avoiding interference from single features, making the analysis more targeted, and improving the accuracy of identifying insulation degradation features.

[0168] In general, the spatial distribution density of the characteristic frequency components in the characteristic frequency cluster is spatially weighted to obtain the degradation weight coefficient of the characteristic frequency cluster. Different weights can be assigned according to the distribution density of the characteristics in the insulation structure, highlighting the degradation characteristics of key areas, enhancing the rationality of the evaluation, and reducing the impact of secondary characteristics on the results.

[0169] In general, a multi-parameter evaluation of insulation degradation is performed on the degradation weight coefficient and the amplitude change range of the characteristic frequency cluster to obtain the winding insulation degradation level of the high-voltage variable-frequency speed regulation integrated machine. This can comprehensively consider the distribution importance and degree of change of the characteristics, realize multi-dimensional quantitative evaluation, avoid the limitations of single parameter judgment, and greatly improve the accuracy of winding insulation degradation level judgment.

[0170] In general, constructing the amplitude-time variation curve of the characteristic frequency component based on the amplitude time series data of the characteristic frequency component can intuitively present the amplitude fluctuation law of each frequency component over time, clearly reflect the dynamic characteristics related to insulation degradation, provide a visual basis for subsequent cluster analysis, help to accurately identify the characteristic change pattern, and improve the reliability of the basic diagnostic data.

[0171] In general, cluster analysis is performed on the characteristic frequency components based on the amplitude-time variation curve to obtain the initial cluster of the characteristic frequency components. Frequency components with similar variation trends can be grouped together to focus on the overall changes of similar features, reduce the interference of scattered features on the analysis, make the classification of insulation degradation-related features more targeted, and lay the foundation for grouping for accurate evaluation.

[0172] In general, dynamic clustering optimization is performed on the initial cluster to obtain the characteristic frequency cluster of the high-voltage variable frequency speed regulation integrated machine. The deviation in the initial grouping can be eliminated through adjustment and optimization, ensuring that the characteristic change pattern within the cluster is highly consistent and the difference between clusters is significant, so that the characteristic frequency cluster can more accurately reflect the actual characteristics of insulation degradation and further improve the accuracy of fault diagnosis.

[0173] like Figure 2 FIG. 1 is a functional module diagram of a high-voltage variable frequency speed regulation integrated machine fault diagnosis system provided by an embodiment of the present invention.

[0174] The high-voltage variable-frequency speed regulation integrated machine fault diagnosis system 100 described in the present invention can be installed in an electronic device. Depending on the functionality implemented, the high-voltage variable-frequency speed regulation integrated machine fault diagnosis system 100 can include a mixed voltage signal acquisition module 101, a comprehensive common-mode current characteristic waveform module 102, an insulation defect characteristic spectrum acquisition module 103, an insulation defect characteristic matrix construction module 104, and a winding insulation degradation level assessment module 105. The modules described in the present invention, also referred to as units, refer to a series of computer program segments that can be executed by an electronic device processor and perform a fixed function, and are stored in the memory of the electronic device.

[0175] In this embodiment, the functions of each module / unit are as follows:

[0176] The mixed voltage signal acquisition module 101 is used to inject a voltage signal of a preset characteristic frequency into the inverter control loop to obtain a mixed voltage signal of the inverter control loop;

[0177] The comprehensive common-mode current characteristic waveform module 102 is used to separate the common-mode current characteristic waveform of the current signal in the mixed voltage signal under the excitation state;

[0178] The insulation defect characteristic spectrum acquisition module 103 is used to perform high-frequency resonance analysis on the vibration signal of the stator winding end to obtain the insulation defect characteristic spectrum of the stator winding end;

[0179] The insulation defect characteristic matrix construction module is used to perform time-frequency domain correlation analysis 104 on the common-mode current characteristic waveform and the insulation defect characteristic spectrum to obtain the insulation defect characteristic matrix of the high-voltage variable frequency speed regulation integrated machine;

[0180] The winding insulation degradation level assessment module 105 is used to assess the degradation degree of the amplitude change and distribution pattern of the characteristic frequency components in the insulation defect characteristic matrix to obtain the winding insulation degradation level of the high-voltage variable frequency speed regulating integrated machine.

[0181] In the several embodiments provided by the present invention, it should be understood that the disclosed methods and systems can be implemented in other ways. For example, the system embodiments described above are merely illustrative. For example, the module division is merely a logical function division, and other division methods may be used in actual implementation.

[0182] The modules described as separate components may or may not be physically separate, and the components shown as modules may or may not be physical units, that is, they may be located in one place or distributed across multiple network elements. Some or all of the modules may be selected to achieve the purpose of the solution of this embodiment according to actual needs.

[0183] In addition, the functional modules in various embodiments of the present invention may be integrated into a single processing unit, each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or hardware plus software functional modules.

[0184] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0185] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Artificial intelligence refers to the theories, methods, technologies, and application systems that use digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use knowledge to achieve optimal results.

[0186] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not limiting. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A fault diagnosis method for a high-voltage variable-frequency speed regulating integrated machine, characterized in that: The method comprises: S1. Inject a voltage signal of a preset characteristic frequency into the inverter control loop to obtain a mixed voltage signal of the inverter control loop; S2 separates the common-mode current characteristic waveform of the current signal in the mixed voltage signal under the excitation state; S3. Perform high-frequency resonance analysis on the vibration signal of the stator winding end to obtain a characteristic spectrum of insulation defects of the stator winding end; S4. The common-mode current characteristic waveform and the insulation defect characteristic spectrum are subjected to time-frequency domain correlation analysis to obtain the insulation defect characteristic matrix of the high-voltage variable frequency speed regulating machine; S5. Evaluate the degradation degree of the amplitude change and distribution pattern of the characteristic frequency components in the insulation defect characteristic matrix to obtain the winding insulation degradation level of the high-voltage variable frequency speed regulation integrated machine.

2. The fault diagnosis method for a high-voltage variable-frequency speed regulating integrated machine according to claim 1, characterized in that: The step of injecting a voltage signal of a preset characteristic frequency into the inverter control loop to obtain a mixed voltage signal of the inverter control loop includes: Modulating the fundamental voltage signal based on the preset characteristic frequency to obtain a modulated voltage signal of the inverter control loop; The modulation voltage signal and the operating voltage signal are modulated to obtain a mixed voltage signal of the inverter control loop.

3. The fault diagnosis method for a high-voltage variable-frequency speed regulating integrated machine according to claim 1, characterized in that: The separating out of the common-mode current characteristic waveform of the current signal in the mixed voltage signal under the excitation state includes: Extracting a common-mode component of the current signal based on the mixed voltage signal to obtain an original common-mode current of the mixed voltage signal; Performing frequency domain bandpass filtering on the original common-mode current to obtain an enhanced common-mode current of the mixed voltage signal; The enhanced common-mode current is subjected to time-domain waveform reconstruction to obtain a common-mode current characteristic waveform of the current signal in the mixed voltage signal.

4. The fault diagnosis method for a high-voltage variable-frequency speed regulating integrated machine according to claim 1, wherein: The performing high-frequency resonance analysis on the vibration signal of the stator winding end to obtain the insulation defect characteristic spectrum of the stator winding end includes: Performing a short-time Fourier transform on the vibration signal of the stator winding end to obtain a vibration spectrum diagram of the stator winding end; Identifying resonance peaks on the vibration spectrum based on an insulation defect feature library to obtain a characteristic peak group of the stator winding end; A characteristic spectrum of insulation defects of the stator winding end is constructed based on the frequency offset of the characteristic peak group.

5. The fault diagnosis method for a high-voltage variable-frequency speed regulating integrated machine according to claim 4, characterized in that: The step of constructing the insulation defect characteristic spectrum of the stator winding end based on the frequency offset of the characteristic peak group includes: Performing a discrete Fourier transform on the frequency offset of the characteristic peak group to obtain a complex spectrum value of the characteristic peak group, wherein the discrete Fourier transform calculation formula is as follows: ； Where, For the The complex spectrum value of the frequency point, The first values, is the total length of the input sequence, is the imaginary unit, is the frequency index, is the sequence index, is the base of natural logarithms, is pi; Aggregating the complex spectrum values ​​of the frequency points is the original spectrum signal of the characteristic peak group; Performing Butterworth low-pass filtering on the original spectrum signal to obtain a filtered spectrum signal of the characteristic peak group; Recombining characteristic frequency points in the filtered spectrum signal to obtain an ordered frequency point sequence of the filtered spectrum signal; A characteristic spectrum of insulation defects of the stator winding end is constructed based on the amplitude distribution of the ordered frequency point sequence.

6. The fault diagnosis method for a high-voltage variable-frequency speed regulating integrated machine according to claim 1, wherein: The time-frequency domain correlation analysis of the common-mode current characteristic waveform and the insulation defect characteristic spectrum is performed to obtain the insulation defect characteristic matrix of the high-voltage variable frequency speed regulating integrated machine, including: Performing a short-time Fourier transform on the common-mode current characteristic waveform to obtain a time-frequency spectrum of the common-mode current characteristic waveform; Performing a Hilbert transform on the insulation defect characteristic spectrum to obtain an instantaneous frequency curve of the insulation defect characteristic spectrum; Performing frequency domain feature correlation analysis on the time-frequency spectrum and the instantaneous frequency curve to obtain a correlation coefficient matrix of the high-voltage variable frequency speed regulation integrated machine; An insulation defect characteristic matrix of the high-voltage variable frequency speed regulation integrated machine is constructed based on the correlation coefficient matrix.

7. The fault diagnosis method for a high-voltage variable-frequency speed regulating integrated machine according to claim 6, characterized in that: The frequency domain feature correlation analysis is performed on the time-frequency spectrum diagram and the instantaneous frequency curve to obtain a correlation coefficient matrix of the high-voltage variable frequency speed regulation integrated machine, including: Dividing the time-frequency spectrum into sub-band time-domain graphs according to preset frequency bands; Extracting instantaneous frequency segment features corresponding to the sub-band time domain graph in the instantaneous frequency curve; Cross-comparing the sub-band time domain graph with the instantaneous frequency segmentation feature to obtain a frequency domain correlation feature set of the high-voltage variable frequency speed regulation integrated machine; The frequency domain correlation feature set is structuredly arranged to obtain a correlation coefficient matrix of the high-voltage variable frequency speed regulation integrated machine.

8. The fault diagnosis method for a high-voltage variable-frequency speed regulating integrated machine according to claim 1, characterized in that: The step of evaluating the degradation degree of the amplitude change and distribution pattern of the characteristic frequency components in the insulation defect characteristic matrix to obtain the winding insulation degradation level of the high-voltage variable frequency speed regulating integrated machine includes: Performing a spectrum cluster analysis on the amplitude change of the characteristic frequency component to obtain a characteristic frequency cluster of the high-voltage variable frequency speed regulation integrated machine; Performing spatial density weighting on the spatial distribution density of the characteristic frequency components in the characteristic frequency cluster to obtain a degradation weight coefficient of the characteristic frequency cluster; A multi-parameter evaluation of insulation degradation is performed on the degradation weight coefficient and the amplitude variation of the characteristic frequency cluster to obtain the winding insulation degradation level of the high-voltage variable frequency speed regulation integrated machine.

9. The fault diagnosis method for a high-voltage variable-frequency speed regulating integrated machine according to claim 8, characterized in that: The spectrum clustering analysis of the amplitude change of the characteristic frequency component to obtain the characteristic frequency cluster of the high-voltage variable frequency speed regulating integrated machine includes: constructing an amplitude-time variation curve of the characteristic frequency component based on the amplitude time series data of the characteristic frequency component; performing cluster analysis on the characteristic frequency components based on the amplitude-time variation curve to obtain an initial cluster of the characteristic frequency components; Dynamic clustering optimization is performed on the initial cluster to obtain a characteristic frequency cluster of the high-voltage variable frequency speed regulation integrated machine.

10. A high-voltage variable frequency speed regulation integrated machine fault diagnosis system, characterized in that: The system comprises: A mixed voltage signal acquisition module is used to inject a voltage signal of a preset characteristic frequency into the inverter control loop to obtain a mixed voltage signal of the inverter control loop; A comprehensive common-mode current characteristic waveform module, used to separate the common-mode current characteristic waveform of the current signal in the mixed voltage signal under the excitation state; An insulation defect characteristic spectrum acquisition module is used to perform high-frequency resonance analysis on the vibration signal of the stator winding end to obtain the insulation defect characteristic spectrum of the stator winding end; An insulation defect characteristic matrix construction module is used to perform time-frequency domain correlation analysis on the common-mode current characteristic waveform and the insulation defect characteristic spectrum to obtain the insulation defect characteristic matrix of the high-voltage variable frequency speed regulation integrated machine; The winding insulation degradation level assessment module is used to assess the degradation degree of the amplitude change and distribution pattern of the characteristic frequency component in the insulation defect characteristic matrix to obtain the winding insulation degradation level of the high-voltage variable frequency speed regulation integrated machine.

Images