Fault positioning method and system based on multi-mode acousto-optic electric signal collaborative diagnosis

Abstract

The invention provides a fault positioning method and system based on multi-mode acousto-optic electric signal collaborative diagnosis, and the method comprises the steps: firstly collecting an acoustic signal sequence, an optical signal sequence and an electric signal sequence during the operation of high-voltage electrical equipment, and then carrying out the cross-mode signal level correlation processing of a multi-mode signal, and generating a multi-mode signal correlation level chain; extracting a dynamic association feature set based on the multi-modal signal association hierarchical chain, inputting the dynamic association feature set into the fault feature evolution model to generate a fault feature identification sequence and a feature space diffusion trajectory, and finally determining a fault initial region and a fault influence boundary range of the equipment according to the fault feature identification sequence and the feature space diffusion trajectory. Therefore, the accuracy and reliability of fault positioning of the high-voltage electrical equipment can be effectively improved.

Description

Technical Field

[0001] The present invention relates to the field of electric power operation and maintenance technology, and in particular to a fault location method and system based on collaborative diagnosis of multimodal acoustic, optical and electrical signals. Background Art

[0002] As the power industry continues to develop, high-voltage electrical equipment, as a core component of the power grid, has a significant impact on the safety and reliability of the entire power system. As equipment operating time increases and the operating environment becomes increasingly complex and dynamic, the risk of failure increases.

[0003] Currently, there are many limitations to fault location methods for high-voltage electrical equipment. Traditional fault diagnosis methods often rely on a single type of signal, such as detecting equipment anomalies by analyzing electrical signals alone. However, these methods are easily affected by external interference and the complex characteristics of the equipment itself, resulting in inaccurate fault location. Although some methods attempt to combine multiple signals, they lack the ability to explore the deep correlation between different modal signals and fail to fully consider the synergistic mechanism of sound, light, and electrical signals in the process of equipment failure. Different signals have specific trigger-response relationships during fault triggering and propagation, but existing technologies have failed to effectively establish the above-mentioned relationship model, making it difficult to accurately determine the starting area and impact boundary range of the fault when faced with complex faults. Summary of the Invention

[0004] In view of the above-mentioned problems, in combination with the first aspect of the present invention, an embodiment of the present invention provides a fault location method based on multimodal acoustic, optical and electrical signal collaborative diagnosis, the method comprising: Acquiring acoustic signal sequences, optical signal sequences, and electrical signal sequences from high-voltage electrical equipment in operation. The acoustic signal sequence includes information on changes in acoustic waveforms caused by vibrations in internal components of the equipment. The optical signal sequence includes information on changes in optical radiation intensity caused by partial discharges on the equipment surface. The electrical signal sequence includes information on instantaneous fluctuations in current and voltage in the equipment circuit. Performing cross-modal signal hierarchical association processing on the acoustic signal sequence, optical signal sequence, and electrical signal sequence, establishing a trigger response hierarchical relationship between different signal sequences, and generating a multimodal signal association hierarchical chain; Extracting a dynamic correlation feature set of each signal sequence in a hierarchical response process based on the multimodal signal correlation hierarchical chain, wherein the dynamic correlation feature set includes amplitude linkage parameters, phase synchronization parameters, and waveform distortion correlation parameters of the trigger signal and the hierarchical response signal; Inputting the dynamic correlation feature set into a preset fault feature evolution model to generate a fault feature identification sequence and a feature space diffusion trajectory; The fault starting area and the fault impact boundary range of the high-voltage electrical equipment are determined based on the fault feature identification sequence and the feature space diffusion trajectory.

[0005] On the other hand, an embodiment of the present invention also provides a fault location system based on collaborative diagnosis of multimodal acoustic, optical and electrical signals, including a processor and a machine-readable storage medium, wherein the machine-readable storage medium is connected to the processor, the machine-readable storage medium is used to store programs, instructions or codes, and the processor is used to execute the programs, instructions or codes in the machine-readable storage medium to implement the above method.

[0006] Based on the above aspects, the embodiment of the present invention collects the sound, light and electrical signal sequences under the operating state of high-voltage electrical equipment to obtain multi-dimensional information such as vibration of internal components of the equipment, surface partial discharge and loop current and voltage fluctuations, performs cross-modal signal hierarchical correlation processing on the multimodal signals, establishes a trigger-response hierarchical relationship between different signal sequences, and generates a multimodal signal correlation hierarchical chain, which deeply reveals the intrinsic connection between sound, light and electrical signals in the fault occurrence process. Based on the correlation hierarchical chain, a dynamic correlation feature set is extracted, and key parameters such as amplitude linkage, phase synchronization and waveform distortion correlation between the trigger signal and the hierarchical response signal are accurately captured. The dynamic characteristics of the fault signal are further characterized, and these features are input into a preset fault feature evolution model to generate a fault feature identification sequence and a feature space diffusion trajectory, which can intuitively present the development and change process and spatial propagation path of the fault characteristics. Finally, based on these results, the fault starting area and the impact boundary range are determined, thereby improving the accuracy and reliability of fault location of high-voltage electrical equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0007] Figure 1 It is a schematic diagram of the execution flow of the fault location method based on multimodal acoustic, optical and electrical signal collaborative diagnosis provided by an embodiment of the present invention.

[0008] Figure 2 Schematic diagram of exemplary hardware and software components of a fault location system based on multimodal acoustic, optical and electrical signal collaborative diagnosis provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0009] The present invention will be described in detail below with reference to the accompanying drawings. Figure 1 This is a flow chart of a fault location method based on multimodal acoustic, optical and electrical signal collaborative diagnosis provided by an embodiment of the present invention. The fault location method based on multimodal acoustic, optical and electrical signal collaborative diagnosis is introduced in detail below.

[0010] Step S110: Collect the acoustic signal sequence, optical signal sequence and electrical signal sequence of the high-voltage electrical equipment in the operating state. The acoustic signal sequence contains the acoustic waveform change information generated by the vibration of the internal components of the equipment, the optical signal sequence contains the light radiation intensity change information generated by partial discharge on the surface of the equipment, and the electrical signal sequence contains the instantaneous fluctuation information of the current and voltage in the equipment circuit.

[0011] In this embodiment, a high-voltage circuit breaker in operation is selected as a specific object of high-voltage electrical equipment. In order to fully capture the multimodal signals during equipment operation, corresponding sensing devices need to be deployed at key locations of the circuit breaker. For the acquisition of acoustic signal sequences, acoustic sensors are installed near components that are prone to vibration, such as the operating mechanism and arc extinguishing chamber of the circuit breaker. When the circuit breaker is opened or closed, the mechanical movement of the operating mechanism and the arc extinguishing process inside the arc extinguishing chamber will generate acoustic waves of different frequencies and amplitudes. The above-mentioned acoustic waves together constitute an acoustic signal sequence, the waveform of which will change with the operation process and the state of the equipment.

[0012] To collect optical signal sequences, optical sensors are installed around potential locations of partial discharge in circuit breakers, such as insulating rods and around the moving and static contacts. When partial discharge occurs in these locations due to insulation defects or poor contact, it is accompanied by light radiation. The optical sensors detect subtle variations in light radiation intensity, which in turn form optical signal sequences. For example, when an oxide layer forms on the surface of the moving and static contacts, increasing contact resistance, this can cause a weak localized discharge, resulting in corresponding light intensity fluctuations in the optical signal sequence.

[0013] The electrical signal sequence is collected by installing current transformers and voltage transformers in the circuit breaker's incoming and outgoing lines. The current transformer monitors instantaneous current changes in the circuit, while the voltage transformer captures transient voltage fluctuations. During normal operation, the current and voltage fluctuate in a relatively stable manner. However, when faults such as contact welding or insulation breakdown occur, abnormal transient current or voltage fluctuations occur, which are recorded in the electrical signal sequence.

[0014] Step S120: performing cross-modal signal hierarchical association processing on the acoustic signal sequence, the optical signal sequence, and the electrical signal sequence, establishing a trigger response hierarchical relationship between different signal sequences, and generating a multi-modal signal association hierarchical chain.

[0015] After obtaining the acoustic signal sequence, optical signal sequence and electrical signal sequence of the high-voltage circuit breaker, it is necessary to use cross-modal signal hierarchical correlation processing to sort out the triggering and response relationship between different signals and construct a hierarchical chain that can reflect their internal connections.

[0016] Step S121: intercept the signal segments of the acoustic signal sequence, optical signal sequence and electrical signal sequence within the same monitoring period, and the signal segments include continuous signal fluctuation units and signal stable units, wherein the signal fluctuation unit is a signal segment in which the amplitude or frequency fluctuates, and the signal stable unit is a signal segment in which the amplitude and frequency remain stable.

[0017] In this embodiment, a fixed monitoring period is set. A signal segment within this monitoring period is extracted from the acoustic signal sequence. This signal segment contains multiple signal fluctuation units and signal stability units. For example, when the circuit breaker is opening, the action of the operating mechanism causes significant fluctuations in the amplitude and frequency of the acoustic signal, generating a signal fluctuation unit. Conversely, when the circuit breaker is in a stable closed state, the amplitude and frequency of the acoustic signal are relatively stable, generating a signal stability unit.

[0018] Similarly, a signal segment within the same monitoring cycle is intercepted from the optical signal sequence. If a brief partial discharge occurs in the circuit breaker's insulating rod during the monitoring cycle, the optical signal intensity will fluctuate, generating a signal fluctuation unit. During periods without partial discharge, the optical signal intensity remains stable, generating a signal stability unit.

[0019] For electrical signal sequences, signal segments with the same monitoring period are intercepted. When the circuit breaker is carrying current normally, the amplitude and frequency of the current and voltage are relatively stable, generating a stable signal unit. When the circuit breaker is closed and the circuit is connected, the current suddenly changes, generating a fluctuating signal unit.

[0020] Step S122: Identify the acoustic wave mutation segment in the signal segment of the acoustic signal sequence whose amplitude change rate exceeds a preset change rate threshold, record the starting time mark of the acoustic wave mutation segment as the starting point of the acoustic trigger level, and the amplitude change rate is the change in amplitude per unit time.

[0021] After obtaining the acoustic signal segment, it needs to be analyzed to identify the acoustic wave mutation segment. First, according to the amplitude change characteristics of the acoustic signal during normal operation of the circuit breaker, an appropriate amplitude change rate threshold is set.

[0022] Step S1221: traverse each signal sampling point in the signal segment of the acoustic signal sequence, calculate the amplitude change and change time interval between the current sampling point and the previous sampling point, the amplitude change is the difference between the amplitude of the current sampling point and the amplitude of the previous sampling point, and the change time interval is the time difference between the two sampling points.

[0023] Traverse all sampling points in the acoustic signal segment. For each current sampling point, subtract the amplitude of the previous sampling point from its current amplitude to obtain the amplitude change. The time difference between two adjacent sampling points is the change interval, which is determined by the sampling frequency.

[0024] Step S1222: Calculate the amplitude change rate based on the amplitude change and the change time interval. The amplitude change rate is the ratio of the amplitude change to the change time interval. A positive value of the ratio indicates an increase in amplitude, and a negative value indicates a decrease in amplitude.

[0025] Divide the calculated amplitude change by the change interval to get the amplitude change rate. If the ratio is positive, it means the amplitude of the sound signal is increasing; if it is negative, it means the amplitude is decreasing.

[0026] Step S1223: When the amplitude change rate of a plurality of consecutive sampling points exceeds a preset change rate threshold, the signal segment consisting of the plurality of consecutive sampling points is marked as a candidate acoustic wave mutation segment.

[0027] During the traversal process, if the amplitude change rate exceeds the preset change rate threshold for multiple consecutive sampling points, the signal segment consisting of these consecutive sampling points is marked as a candidate acoustic wave mutation segment. For example, if the operating mechanism of a circuit breaker is stuck, the amplitude change rate of the acoustic wave generated during its movement will exceed the threshold for multiple consecutive sampling points, thus forming a candidate acoustic wave mutation segment.

[0028] Step S1224: Locate the starting sampling point of the candidate sound wave mutation segment, and extract the time coordinate of the starting sampling point in the sound signal segment.

[0029] For each candidate acoustic wave mutation segment, its first sampling point, i.e., the starting sampling point, is determined. The corresponding time coordinate is determined based on the position of the sampling point in the acoustic signal segment.

[0030] Step S1225: Take the time coordinate as the sound triggering level starting point, repeat the above operation for all qualified candidate sound wave mutation segments in the signal segment of the sound signal sequence, and generate a sound triggering level starting point set. Each starting point in the sound triggering level starting point set is arranged in chronological order and is accompanied by corresponding signal amplitude information.

[0031] The time coordinate of the initial sampling point is used as the acoustic trigger level starting point. All candidate acoustic wave mutation segments that meet the conditions in the acoustic signal segment are processed in the same way to obtain multiple acoustic trigger level starting points. These starting points are arranged in chronological order, and each starting point is accompanied by corresponding signal amplitude information to form the acoustic trigger level starting point set.

[0032] Step S123: Identify the light radiation mutation segment in the signal segment of the light signal sequence whose light intensity change rate exceeds the preset change rate threshold, and record the starting time mark of the light radiation mutation segment as the starting point of the light trigger level. The light intensity change rate is the change in light radiation intensity per unit time.

[0033] When processing the optical signal segment, firstly, a preset threshold value of the light intensity change rate is set according to the light intensity change of the optical signal during normal operation of the circuit breaker.

[0034] Traverse each sampling point in the optical signal segment and calculate the change in light intensity between the current sampling point and the previous sampling point (the current sampling point's light intensity minus the previous sampling point's light intensity) and the time interval between the changes. Then, calculate the light intensity change rate, which is the ratio of the light intensity change to the time interval between the changes. If the light intensity change rate exceeds a preset threshold for multiple consecutive sampling points, the signal segment is marked as a candidate light radiation mutation segment.

[0035] The starting sampling point of the candidate optical radiation mutation segment is located and its time coordinate is extracted as the optical triggering hierarchical starting point. All eligible candidate optical radiation mutation segments are processed to generate a set of optical triggering hierarchical starting points arranged in chronological order and accompanied by light intensity information. For example, when a circuit breaker's moving and static contacts generate partial discharge due to poor contact, the rate of change of the optical signal's light intensity will exceed the threshold, generating an optical triggering hierarchical starting point.

[0036] Step S124: Identify the electrical parameter mutation segment in the signal segment of the electrical signal sequence in which the current and voltage change rates exceed the preset change rate threshold, and record the starting time mark of the electrical parameter mutation segment as the starting point of the electrical trigger level. The current and voltage change rates are the changes in current or voltage per unit time.

[0037] When processing electrical signal segments, corresponding change rate preset thresholds are set for current and voltage respectively.

[0038] For the current signal, we traverse each sampling point and calculate the current change and the time interval between the current sampling point and the previous sampling point, thereby obtaining the current change rate. If the current change rate exceeds the preset threshold for multiple consecutive sampling points, it is marked as a candidate current mutation segment.

[0039] For voltage signals, the same method is used to calculate the voltage change rate. When the voltage change rate exceeds the preset threshold for multiple consecutive sampling points, it is marked as a candidate voltage mutation segment.

[0040] Candidate current and voltage mutation segments are collectively referred to as electrical parameter mutation segments. Their starting sampling points are located, and their time coordinates are extracted as electrical triggering hierarchy starting points. All eligible electrical parameter mutation segments are processed to generate a chronologically ordered set of electrical triggering hierarchy starting points accompanied by current or voltage information. For example, when a circuit breaker experiences contact welding, the current will fluctuate abnormally, and the current change rate will exceed a threshold, generating an electrical triggering hierarchy starting point.

[0041] Step S125: Arrange the sound trigger level starting point, the light trigger level starting point, and the electrical trigger level starting point in chronological order to generate a trigger level sequence, wherein each starting point in the trigger level sequence is accompanied by a corresponding signal type identifier.

[0042] All trigger level starting points obtained in steps S122, S123, and S124 are collected and sorted by their time coordinates to generate a trigger level sequence. Each starting point in the sequence is clearly labeled with its corresponding signal type, namely, acoustic, optical, or electrical. For example, the sequence may first include an electrical trigger level starting point (due to a sudden current change), followed by an acoustic trigger level starting point (due to abnormal vibration of the operating mechanism), and finally a optical trigger level starting point (due to partial discharge). These starting points are arranged in chronological order.

[0043] Step S126: Analyze the signal response relationship between adjacent trigger level starting points in the trigger level sequence, and establish a level response connection between adjacent trigger level starting points when a signal change corresponding to a previous trigger level starting point triggers a signal change corresponding to a subsequent trigger level starting point.

[0044] For two adjacent trigger level starting points in a trigger level sequence, it is necessary to determine whether there is a signal response relationship between them.

[0045] Step S1261: Select two adjacent trigger level starting points from the trigger level sequence and mark them as an upper trigger starting point and a lower trigger starting point respectively.

[0046] In the trigger hierarchy sequence, two adjacent starting points are selected in order, the front one is used as the upper trigger starting point, and the back one is used as the lower trigger starting point.

[0047] Step S1262: Extract the amplitude fluctuation curve of the signal segment corresponding to the upper trigger starting point before and after the trigger, and determine the peak interval and fluctuation duration of the amplitude fluctuation. The peak interval is the time range when the amplitude reaches the maximum value, and the fluctuation duration is the time range from the beginning of the signal change to the restoration of stability.

[0048] Using the triggering point as a reference, extract the amplitude fluctuation curve of the corresponding signal segment before and after the trigger. By analyzing this curve, determine the time range when the amplitude reaches its maximum value (peak interval) and the time range from when the signal begins to fluctuate to when it returns to stability (fluctuation duration).

[0049] Step S1263: extracting the amplitude fluctuation curve of the signal segment corresponding to the lower-level trigger starting point before and after the trigger, and determining the peak interval and fluctuation duration of the amplitude fluctuation.

[0050] Using the same method as step S1262, the amplitude fluctuation curve of the signal segment corresponding to the lower-level trigger starting point before and after the trigger is extracted to determine its peak interval and fluctuation duration period.

[0051] Step S1264: Compare the peak interval of the upper signal with the peak interval of the lower signal, and calculate the ratio of the overlapping duration to the total duration of the peak interval of the lower signal, where the overlapping duration is the intersection of the two peak intervals, and the total duration is the time span of the peak interval of the lower signal.

[0052] Compare the peak intervals of the upper-level signal and the lower-level signal, find the overlapping parts, calculate the overlapping duration, and then divide the overlapping duration by the total duration of the peak interval of the lower-level signal to obtain the overlapping duration ratio.

[0053] Step S1265: Calculate the time interval between the upper trigger start point and the lower trigger start point, and determine a reasonable response time range in combination with the signal conduction characteristics of the device components.

[0054] Calculate the time interval between the upper and lower trigger starting points, and then determine a reasonable response time range based on the signal conduction characteristics of each component inside the circuit breaker, such as the propagation characteristics of sound waves in air and solids, the conduction speed of electrical signals in conductors, etc.

[0055] Step S1266: When the overlapping duration ratio exceeds a preset ratio threshold and the time interval is within a reasonable response time range, it is determined that the change in the lower-level signal is caused by the change in the upper-level signal.

[0056] A ratio threshold is set. If the overlap duration ratio exceeds the threshold and the time interval is within a reasonable response time range, it is determined that the change in the lower-level signal is caused by the change in the upper-level signal.

[0057] Step S1267: Establish a hierarchical response connection between the upper trigger starting point and the lower trigger starting point, and record the response strength coefficient and signal conduction path identifier of the connection. The response strength coefficient is positively correlated with the overlap duration ratio, and the signal conduction path identifier reflects the signal propagation path inside the device.

[0058] Once a response relationship is determined, a hierarchical response connection is established between the upper and lower triggering points. The response strength coefficient is determined by the overlap duration ratio; the higher the ratio, the larger the coefficient. The signal transmission path identification is determined by the signal type and device structure, such as the acoustic wave transmission path from the operating mechanism to the arc extinguishing chamber.

[0059] Step S127: A multimodal signal association hierarchical chain including a trigger hierarchical sequence, a hierarchical response delay parameter and an amplitude linkage coefficient is formed through multiple hierarchical response connections. The trigger hierarchical sequence reflects the sequence logic of each signal trigger, the hierarchical response delay parameter is the time difference between adjacent trigger starting points, and the amplitude linkage coefficient reflects the degree of correlation between the amplitude changes of the previous and subsequent signals.

[0060] All hierarchical response connections are integrated to generate a multimodal signal correlation hierarchical chain. This multimodal signal correlation hierarchical chain records the trigger hierarchical order, hierarchical response delay parameters (the time difference between adjacent trigger start points), and amplitude linkage coefficient (calculated by the ratio of the amplitude changes of the upper and lower level signals, reflecting the degree of correlation between the amplitude changes of the two).

[0061] Step S130: extracting a dynamic correlation feature set of each signal sequence in the hierarchical response process based on the multimodal signal correlation hierarchical chain, wherein the dynamic correlation feature set includes amplitude linkage parameters, phase synchronization parameters and waveform distortion correlation parameters of the trigger signal and the hierarchical response signal.

[0062] A feature set that reflects the dynamic correlation of each signal sequence in the hierarchical response process is extracted from the multimodal signal association hierarchical chain. The above features will be used for subsequent fault diagnosis.

[0063] Step S131: extracting trigger signal segments and hierarchical response signal segments corresponding to all hierarchical response connections from the multimodal signal association hierarchical chain.

[0064] Step S1311: parsing the structure of the multimodal signal association hierarchical chain, determining the upper node and lower node of each hierarchical response connection, wherein the upper node corresponds to the trigger signal, and the lower node corresponds to the hierarchical response signal.

[0065] Analyze the structure of the multimodal signal association hierarchical chain and clarify the upper and lower nodes in each hierarchical response connection. The upper node corresponds to the trigger signal, and the lower node corresponds to the hierarchical response signal.

[0066] Step S1312: According to the time stamp of the upper node, a signal segment of a preset length before and after the time stamp is intercepted as a trigger signal segment, wherein the trigger signal segment includes a stable segment before the trigger, a sudden change segment during the trigger, and an attenuation segment after the trigger.

[0067] According to the time mark of the upper node, the signals of the preset time length before and after it are intercepted as the trigger signal segment, which includes the stable segment before the trigger, the sudden change segment during the trigger, and the attenuation segment after the trigger.

[0068] Step S1313: According to the time stamp of the lower-level node, a signal segment of a preset length before and after the time stamp is intercepted as a hierarchical response signal segment, wherein the hierarchical response signal segment includes a preparatory segment before response, a sudden change segment during response, and a stable segment after response.

[0069] According to the time mark of the lower-level node, the signals of the preset time length before and after it are intercepted as the hierarchical response signal segment, which includes the preparatory segment before the response, the sudden change segment during the response, and the stable segment after the response.

[0070] Step S1314: After performing a signal integrity check on the extracted trigger signal segments and hierarchical response signal segments, the trigger signal segments and hierarchical response signal segments belonging to the same hierarchical response connection are associated and stored to generate a hierarchical associated signal segment pair set.

[0071] The extracted trigger signal segments and hierarchical response signal segments are checked for integrity to ensure that the signals are not missing or damaged. The two signal segments belonging to the same hierarchical response connection are then associated and stored to generate a set of hierarchical associated signal segment pairs.

[0072] Step S1315: Add a corresponding hierarchical response connection identifier for each hierarchical association signal segment pair, wherein the information of the hierarchical response connection identifier includes an upper-level node ID, a lower-level node ID, and a connection sequence number.

[0073] Add an identifier to each hierarchical associated signal segment pair, including the upper node ID, lower node ID and connection sequence number, for subsequent identification and processing.

[0074] Step S132: Calculate the ratio of the peak amplitude of the trigger signal segment to the peak amplitude of the hierarchical response signal segment in each hierarchical response connection, and use the ratio as the amplitude linkage parameter, where the peak amplitude is the maximum amplitude in the signal segment.

[0075] For each hierarchical response connection, find the maximum amplitude value (amplitude peak) in the trigger signal segment and the maximum amplitude value in the hierarchical response signal segment, calculate the ratio between the two, and use the ratio as the amplitude linkage parameter.

[0076] Step S133: performing spectrum analysis on the trigger signal segment and the hierarchical response signal segment, extracting the phase spectrum curves of the trigger signal segment and the hierarchical response signal segment, and calculating the absolute value of the phase difference of the phase spectrum curves in the same frequency range.

[0077] Perform spectrum analysis on the trigger signal segment and the level response signal segment to obtain their respective phase spectrum curves. Calculate the absolute value of the phase difference between the two phase spectrum curves within the same frequency range.

[0078] Step S134: Count the proportion of frequency intervals whose absolute phase difference values ​​are less than a preset phase difference threshold in the total analyzed frequency intervals, and use the proportion as a phase synchronization parameter.

[0079] A phase difference threshold is set, and the proportion of frequency intervals whose absolute phase difference is less than the threshold to the total analyzed frequency intervals is counted, and this proportion is used as the phase synchronization parameter.

[0080] Step S135: Compare the waveform features of the trigger signal segment and the hierarchical response signal segment, extract the number of waveform distortion points and the degree of distortion, calculate the ratio of the number of distortion points and the correlation coefficient of the degree of distortion, and use it as the waveform distortion correlation parameter. The waveform distortion point is the position that deviates from the normal waveform trend.

[0081] Step S1351: extract waveform features from the trigger signal segment and identify distortion points in the waveform. The distortion points are sampling points that deviate from the normal waveform trend. The normal waveform trend is obtained by fitting the stable part of the signal segment.

[0082] The waveform features of the trigger signal segment are extracted, and the normal waveform trend is obtained by fitting the stable part of the signal segment. The sampling points that deviate from the trend are identified as distortion points.

[0083] Step S1352: Count the total number of distortion points in the trigger signal segment, and calculate the ratio of the distortion points to the total length of the trigger signal segment as the trigger distortion ratio. The total length of the trigger signal segment is the total number of sampling points contained in the trigger signal segment.

[0084] In the trigger signal segment, all identified distortion points are counted to obtain the total number of distortion points. The total number of sampling points in the trigger signal segment is also counted, and the total number of distortion points is divided by the total number of sampling points. The result is the trigger distortion ratio. This trigger distortion ratio reflects the overall degree of waveform distortion in the trigger signal segment. A higher ratio indicates more severe waveform distortion in the trigger signal segment. For example, if a trigger signal segment has a number of sampling points, and a certain number of them are identified as distortion points, the trigger distortion ratio is the ratio of these two numbers.

[0085] Step S1353: extract waveform features from the hierarchical response signal segment, identify distortion points in the waveform, and count the total number of distortion points in the hierarchical response signal segment.

[0086] The hierarchical response signal segment is processed using the same method as step S1351. First, the normal waveform trend of the stable portion of the hierarchical response signal segment is fitted. Then, sampling points that deviate from this trend are identified as distortion points. Finally, the total number of distortion points in the hierarchical response signal segment is counted. This process can accurately capture abnormal changes in the waveform of the hierarchical response signal segment.

[0087] Step S1354: Calculate the ratio of the total number of distortion points in the hierarchical response signal segment to the total number of distortion points in the trigger signal segment as the ratio of the number of distortion points. A ratio greater than 1 indicates that the response signal is more severely distorted, and a ratio less than 1 indicates that the trigger signal is more severely distorted.

[0088] The total number of distortion points in the hierarchical response signal segment obtained in step S1353 is divided by the total number of distortion points in the trigger signal segment in step S1352 to obtain the ratio of the number of distortion points. This ratio can be used to intuitively compare the degree of waveform distortion of the trigger signal segment and the hierarchical response signal segment. When the ratio is greater than 1, it means that the hierarchical response signal segment has more distortion points, that is, the distortion of the response signal is more serious; when the ratio is less than 1, it means that the distortion of the trigger signal segment is more serious. For example, if the total number of distortion points in the hierarchical response signal segment is a certain number, and the total number of distortion points in the trigger signal segment is a certain number, then the ratio of the two can clearly reflect which signal segment has more serious distortion.

[0089] Step S1355: performing pairwise analysis on the corresponding distortion points in the trigger signal segment and the hierarchical response signal segment, and calculating the difference in distortion degree of each pair of distortion points. The corresponding distortion points are distortion points that are temporally correlated.

[0090] In the trigger signal segment and the hierarchical response signal segment, find distortion points that are temporally correlated, i.e., corresponding distortion points. For example, a distortion point that appears at a certain time point in the trigger signal segment and a distortion point that appears a short time later in the hierarchical response signal segment can be considered a pair of corresponding distortion points. For each pair of corresponding distortion points, calculate their degree of distortion. Then, subtract the degree of distortion of the corresponding distortion point in the trigger signal segment from the degree of distortion of the distortion point in the hierarchical response signal segment to obtain the difference in the degree of distortion for each pair of distortion points. The degree of distortion can be calculated based on the magnitude of the deviation from the normal waveform trend. The greater the deviation, the higher the degree of distortion.

[0091] Step S1356: Calculating the correlation coefficient of the overall distortion degree based on the distortion degree difference. The closer the correlation coefficient is to a preset reference value, the more significant the distortion degree correlation is.

[0092] The distortion differences between all paired distortion points are collected and statistical analysis is used to calculate the correlation coefficient of the overall distortion degree. For example, the correlation coefficient can be obtained by calculating statistics such as the variance and covariance of these differences. A baseline value is preset. The closer the correlation coefficient is to this baseline value, the more significant the correlation between the distortion degrees of the trigger signal segment and the hierarchical response signal segment, indicating a strong correlation in the degree of waveform distortion between the two. Conversely, the correlation is weaker.

[0093] Step S136: Integrate the amplitude linkage parameters, phase synchronization parameters and waveform distortion correlation parameters to generate a dynamic correlation feature set. During the integration, the features need to be grouped according to the hierarchical response connections, and each set of features corresponds to one connection.

[0094] The amplitude linkage parameters obtained in step S132, the phase synchronization parameters obtained in step S134, and the waveform distortion correlation parameters (including the ratio of the number of distortion points and the correlation coefficient of the degree of distortion) obtained in step S135 are integrated. During the integration process, the hierarchical response connections are grouped, with each hierarchical response connection corresponding to a set of the above parameters, thus forming a dynamic correlation feature set. The purpose of this grouping is to ensure that the characteristics of each hierarchical response connection can be clearly and independently presented, facilitating their subsequent input into the fault feature evolution model for processing. For example, a set of features corresponding to a hierarchical response connection includes the amplitude linkage parameters, phase synchronization parameters, the ratio of the number of distortion points, and the correlation coefficient of the degree of distortion.

[0095] Step S140: inputting the dynamic correlation feature set into a preset fault feature evolution model to generate a fault feature identification sequence and a feature space diffusion trajectory.

[0096] After obtaining the dynamic correlation feature set, it is input into the pre-built fault feature evolution model. Through model processing, a fault feature identification sequence that can reflect the fault feature change process and the feature space diffusion trajectory of the fault feature propagation path in the device space are generated.

[0097] Step S141: converting the dynamic correlation feature set into a feature matrix that meets the input requirements of the fault feature evolution model, wherein the row dimension of the feature matrix corresponds to different hierarchical response connections, the column dimension corresponds to different dynamic correlation features, and the matrix elements are the quantized values ​​of the feature parameters.

[0098] The various parameters in the dynamic correlation feature set are quantified and converted into numerical form. Then, according to the requirements of the fault feature evolution model for the input data format, a feature matrix is ​​constructed. The rows of the feature matrix represent different hierarchical response connections, and each row corresponds to all the features of a hierarchical response connection; the columns represent different dynamic correlation features, such as amplitude linkage parameters, phase synchronization parameters, etc.; each element in the matrix is ​​the quantized value of the corresponding hierarchical response connection on the corresponding dynamic correlation feature. Through the above conversion, the dynamic correlation feature set can be input in a form that can be recognized by the model. For example, assuming there are several hierarchical response connections and several dynamic correlation features, the feature matrix will be a matrix with the number of rows equal to the number of hierarchical response connections and the number of columns equal to the number of dynamic correlation features, and each element is a specific quantized value.

[0099] Step S142: Call the feature mapping module of the fault feature evolution model, map and match the feature matrix with multiple fault evolution pattern templates stored in the fault feature evolution model, calculate the pattern matching degree between the feature matrix and each fault evolution pattern template, and select the fault evolution pattern template with the highest pattern matching degree as the target evolution template.

[0100] The fault feature evolution model includes a feature mapping module, which compares the input feature matrix with multiple pre-stored fault evolution pattern templates in the model. Each fault evolution pattern template corresponds to a specific fault evolution process and contains the typical change patterns of the dynamic correlation features during that process. The feature mapping module measures the similarity between the feature matrix and each template by calculating the pattern matching degree between the two. The pattern matching degree can be calculated based on similarity algorithms between features, such as cosine similarity and Euclidean distance. After the calculation is completed, the fault evolution pattern template with the highest pattern matching degree is selected as the target evolution template. This target evolution template best reflects the fault evolution corresponding to the current dynamic correlation feature set. For example, the model stores multiple evolution pattern templates for contact overheating faults and insulation aging faults. By calculating the matching degree between the feature matrix and these templates, the template with the highest matching degree with the contact overheating fault evolution pattern template is selected as the target evolution template.

[0101] Step S143: extracting the fault type identification sequence corresponding to the target evolution template and using it as a fault feature identification sequence, wherein the fault feature identification sequence reflects the characteristics of the fault at different stages from the initial stage to the development stage.

[0102] Each fault evolution pattern template corresponds to a fault type identification sequence, which consists of a series of identifiers, each of which represents the characteristics of the fault from its initial occurrence to a certain stage of gradual development. For example, for the target evolution template of a contact overheating fault, its corresponding fault characteristic identification sequence may include identifiers such as "initial abnormal increase in contact resistance," "slow increase in local temperature," "heat accumulation causing slight aging of surrounding insulation materials," "partial discharge," and "sharp temperature rise causing obvious faults." The fault type identification sequence corresponding to the target evolution template is extracted and used as the fault characteristic identification sequence for the current fault. This fault characteristic identification sequence can clearly show the characteristic changes of the fault at different stages.

[0103] Step S144: Based on the spatial distribution information contained in the feature matrix and in combination with the spatial diffusion model of the target evolution template, a diffusion trajectory of the fault feature in the equipment structure space is generated, and the spatial distribution information is associated with the signal acquisition position.

[0104] The spatial distribution information contained in the feature matrix comes from the signal acquisition location, that is, the locations of the equipment from which the signals corresponding to the response connections at different levels are collected. The above location information reflects the spatial location where the fault characteristics may appear. The spatial diffusion model of the target evolution template describes the common propagation mode and path of the characteristics of this type of fault in the equipment structure space. Combining these two aspects of information, the diffusion trajectory of the fault characteristics in the equipment structure space is generated. For example, if the spatial distribution information indicates that the initial signal acquisition location is at the moving and static contacts of the circuit breaker, and the spatial diffusion model of the target evolution template shows that this type of fault characteristics will diffuse from the contacts to the surrounding insulating components, then the generated feature space diffusion trajectory will show a path starting from the moving and static contacts and gradually spreading to nearby insulating pull rods, arc extinguishing chambers and other components.

[0105] Step S145: performing correlation verification on the fault feature identification sequence and the feature space diffusion trajectory, so that each identification in the identification sequence forms a one-to-one correspondence with the corresponding position on the diffusion trajectory.

[0106] To ensure that the fault signature sequence and the feature space diffusion trajectory accurately reflect the fault's evolution, a correlation check is required between the two. During the verification process, each identifier in the fault signature sequence is associated with a specific position on the feature space diffusion trajectory based on the chronological order of the fault's development and the spatial propagation pattern, generating a one-to-one correspondence. For example, the identifier "initial abnormal increase in contact resistance" corresponds to the initial position of the moving and static contacts on the diffusion trajectory; "slow increase in local temperature" corresponds to the position on the trajectory where the temperature slightly diffuses from the initial position to the surrounding area; and "occurrence of partial discharge" corresponds to the position on the trajectory where the temperature has diffused to the vicinity of the insulating component. Through this correlation check, the temporal evolution characteristics and spatial propagation characteristics of the fault can be mutually verified, improving the reliability of the results.

[0107] Step S150: determining the fault starting area and fault impact boundary range of the high-voltage electrical equipment based on the fault feature identification sequence and feature space diffusion trajectory.

[0108] By using the generated fault feature identification sequence and feature space diffusion trajectory, a comprehensive analysis is conducted to determine the starting area of ​​the high-voltage electrical equipment fault and the boundary range affected by the fault.

[0109] Step S151: parsing the initial identifier in the fault feature identifier sequence to obtain the initial fault feature information corresponding to the initial identifier. The initial identifier is the earliest identifier in the fault feature identifier sequence, reflecting the initial state of the fault.

[0110] The first identifier in the fault signature sequence is the initial identifier. Parsing this identifier yields characteristic information about the initial fault occurrence, including signal characteristics and possible abnormal conditions of affected components. For example, if the initial identifier is "initial local electric field distortion of the insulating rod," the corresponding initial fault characteristics might include the initial abnormal electric field distribution near the insulating rod and the subtle fluctuations in the associated acoustic, optical, and electrical signals.

[0111] Step S152: combining the starting coordinates of the feature space diffusion trajectory and the initial direction of the trajectory to locate the spatial coordinates of the fault initiation, wherein the starting coordinates are the first point of the feature space diffusion trajectory, and the initial direction of the trajectory is the tangent direction of the trajectory starting point.

[0112] The starting coordinates of the feature space diffusion trajectory correspond to the spatial location where the fault feature first appears, while the initial direction of the trajectory indicates the direction in which the fault feature initially diffuses. The initial fault feature information corresponding to the initial identifier is combined with the starting coordinates and initial direction of the trajectory. Through spatial coordinate transformation and positioning algorithms, the specific spatial coordinates of the fault's origin are determined. For example, if the starting coordinates of the trajectory are located at a specific location on an insulating rod, and the initial direction of the trajectory points to the connection between the rod and the contact, combined with the local electric field distortion information of the insulating rod reflected by the initial identifier, the spatial coordinates of the fault's origin can be located at a specific location on the insulating rod.

[0113] Step S153: Determine the core area affected by the fault based on the fault feature identification strength corresponding to each trajectory point on the feature space diffusion trajectory. The core area is the area where the identification strength is in a preset high intensity range. The identification strength reflects the significance of the fault feature.

[0114] Each trajectory point on the feature space diffusion trajectory corresponds to a fault feature identifier, and each identifier has a corresponding identifier strength. The identifier strength reflects the significance of the fault feature at that trajectory point. The higher the strength, the more obvious the fault feature. A high-intensity interval is preset, and the area formed by the trajectory points whose identifier strength is within this interval is determined as the core area affected by the fault. For example, if the high-intensity interval is preset to a certain range, and the points on the trajectory whose identifier strength is within this range are concentrated at the connection between the insulating pull rod and the contact and its surrounding area, then this area is the core area affected by the fault.

[0115] Step S154: Analyze the attenuation law of the marker strength during the trajectory extension process. When the marker strength drops to a preset boundary strength, the corresponding coordinate point constitutes the fault impact boundary. The marker strength attenuation law is obtained by fitting the strength change trend.

[0116] As the trajectory extends, the strength of the fault signature will show a certain attenuation trend. By analyzing the signature strength of each point on the trajectory, the attenuation pattern of the signature strength can be fitted, such as linear attenuation, exponential attenuation, etc. A boundary strength value is preset. When the signature strength decays to this boundary strength along the extension direction of the trajectory, the contour formed by the corresponding trajectory points is the fault impact boundary. For example, if the signature strength shows an exponential decay pattern, when it decays to the preset boundary strength, the closed curve formed by connecting the corresponding coordinate points constitutes the fault impact boundary.

[0117] Step S155: Calculate the geometric center coordinates of the fault starting area and the maximum extension distance of the affected boundary, and generate fault location information including the center coordinates, boundary outline and range size. The geometric center coordinates are the center of gravity position of the core area.

[0118] The geometric center coordinates of the fault starting area are determined by geometric calculation methods. The geometric center coordinates are the center of gravity of the fault core area and can be obtained by calculating the average value of the coordinates of all trajectory points in the core area. At the same time, the distance from each point on the fault impact boundary to the geometric center coordinates is calculated, where the largest distance is the maximum extension distance of the impact boundary. The geometric center coordinates, the contour shape of the fault impact boundary, and the range size (such as the maximum extension distance, the area of ​​the area enclosed by the boundary, etc.) are integrated to generate complete fault location information. For example, the geometric center coordinates of the fault starting area are a specific coordinate value, the maximum extension distance of the impact boundary is a certain length, and the boundary contour is an irregular polygon. The above information together constitutes the fault location information.

[0119] Step S156: spatially map the fault location information with the three-dimensional structural model of the high-voltage electrical equipment to obtain the specific location of the fault in the physical structure of the equipment and the information of the components involved. The spatial mapping is achieved based on the coordinate system transformation of the equipment.

[0120] Each high-voltage electrical device has a corresponding three-dimensional structural model, which contains the detailed structure and spatial coordinate information of each component of the device. The generated fault location information is spatially mapped with the three-dimensional structural model, that is, the coordinates of the fault location information are converted into coordinates in the three-dimensional structural model through the coordinate system transformation of the device. Through the above mapping, the specific location of the fault in the physical structure of the device and the device components involved in this location can be determined. For example, after spatial mapping, it is found that the fault starting area corresponds to the middle section of the insulating pull rod in the three-dimensional structural model, and the components involved include the insulating pull rod body and the contact components connected to it.

[0121] In order to enable the fault feature evolution model to accurately process the dynamic correlation feature set and generate reliable results, the fault feature evolution model needs to be trained in advance.

[0122] Step S211: Collect multimodal signal data of high-voltage electrical equipment under different fault states and corresponding fault diagnosis results to construct a training data set.

[0123] We extensively collect acoustic, optical, and electrical signal sequences from high-voltage electrical equipment under various fault conditions (such as contact welding, insulation aging, and operating mechanism jamming). We also collect detailed diagnostic results corresponding to these faults, including information such as fault type, stage of development, and location. We compile this multimodal signal data and the corresponding diagnostic results into a training dataset. During the data collection process, we ensure that the data is diverse and representative, covering equipment of different models and ages under different fault conditions, to improve the model's generalization capabilities.

[0124] Step S212: Process the multimodal signal data in the training data set according to the method of steps S120 to S136 to generate a dynamic association feature set for training.

[0125] Using the same methods used to process actual fault signals, the multimodal signal data in the training dataset is subjected to cross-modal signal hierarchical correlation processing and dynamic correlation feature extraction to generate dynamic correlation feature sets for training. These training feature sets have the same data format and feature types as the dynamic correlation feature sets generated in actual applications, making them suitable for model training.

[0126] Step S213: Based on the fault diagnosis results in the training data set, a corresponding fault feature identification sequence and feature space diffusion trajectory are constructed as training labels.

[0127] Based on the diagnostic results of each fault case in the training dataset, a corresponding fault feature identification sequence and feature spatial diffusion trajectory are constructed manually or automatically through annotation and used as training labels. The training labels must accurately reflect the feature evolution process and spatial diffusion of the fault case and have a one-to-one correspondence with the dynamic association feature set used for training.

[0128] Step S214: Input the training dynamic association feature set and the corresponding training labels into the initial fault feature evolution model, and adjust the model parameters through the back propagation algorithm so that the error between the fault feature identification sequence and feature space diffusion trajectory output by the model and the training label is within a preset range.

[0129] The initial fault feature evolution model is an untrained model with initial parameter settings. The training dynamic association feature set is input into the initial fault feature evolution model, which then outputs the corresponding fault feature identification sequence and feature spatial diffusion trajectory. These output results are compared with the corresponding training labels, and the error between the two is calculated. Then, using the backpropagation algorithm, the various parameters of the fault feature evolution model (such as the weight coefficients in the feature mapping module and the parameters in the spatial diffusion model) are adjusted based on the error. This process is repeated until the error between the model output and the training label is reduced to within a preset range. At this point, the fault feature evolution model is trained and can effectively process the input feature set and generate results that conform to the actual situation.

[0130] During the model parameter adjustment process, fine-tuning is required on a module-by-module basis. The feature mapping module contains multiple sub-layers for feature matching, and each sub-layer has a corresponding weight coefficient. When the calculated error is large, starting from the output layer, the degree of influence of the error on the weight coefficient of each layer is reversely deduced layer by layer. For example, if the matching degree between the feature matrix and the fault evolution pattern template is low, resulting in an error, the weight of the sub-layer responsible for pattern comparison in the feature mapping module can be adjusted to increase the weight ratio of the high-matching template and reduce the influence of the low-matching template.

[0131] For spatial diffusion models, parameters include factors describing fault diffusion speed and directional preference. When the feature space diffusion trajectory output by the model deviates significantly from the actual trajectory in the training labels, a backpropagation algorithm is used to analyze whether the deviation primarily stems from an error in the estimated diffusion speed or a deviation in the direction, and the corresponding parameters are adjusted accordingly. For example, if the trajectory extends too slowly, the diffusion speed factor can be increased; if the trajectory direction deviates from the actual one, the directional preference parameter can be adjusted to make the model more consistent with the actual fault diffusion pattern.

[0132] During the entire training process, it's important to set an appropriate number of iterations. Each iteration uses the entire training dynamic correlation feature set for a complete forward calculation and backward parameter adjustment. To prevent model overfitting, the training data can be divided into a training set and a validation set. The validation set is used to test model performance after each iteration. If the error on the training set continues to decrease but the error on the validation set begins to increase, the current parameter adjustment is stopped and the model parameters that achieved optimal performance on the previous validation set are used. This ensures that the fault signature evolution model maintains good generalization capabilities even on the new dynamic correlation feature set.

[0133] After model training is complete, it needs to be tested for stability. A subset of dynamic correlation feature sets that were not used in training is selected as a test set and fed into the trained fault feature evolution model. The stability of the fault feature identification sequence and feature space diffusion trajectory output by the fault feature evolution model is observed. If the model output fluctuates within the preset fluctuation range after multiple inputs of the same test set, the fault feature evolution model training is stable and can be used for subsequent fault diagnosis.

[0134] Therefore, the trained fault feature evolution model is encapsulated and stored so that it can be called in the actual diagnosis process.

[0135] The trained fault signature evolution model needs to be encapsulated to generate a independently callable module. During the encapsulation process, the input and output interfaces of the fault signature evolution model are clearly defined. The input interface must match the format of the dynamically associated feature set used in the actual diagnostic process, while the output interface specifies the output format of the fault signature identification sequence and feature space diffusion trajectory. At the same time, necessary metadata is added to the model, including model training time, training data size, and model performance metrics (such as error range and accuracy) to facilitate subsequent maintenance and version management.

[0136] The encapsulated fault signature evolution model is stored in a dedicated model library using a distributed storage method to ensure rapid response when multiple diagnostic terminals need to call it. During storage, the model file is encrypted, allowing only authorized diagnostic systems to access and call it, preventing the model from being tampered with or misused. Furthermore, a model version update mechanism is established. When new fault cases and corresponding dynamically associated feature sets are collected, incremental training can be performed based on the original model to generate a new model version and replace the old one, ensuring that the model always maintains its diagnostic capabilities for new faults.

[0137] Figure 2 A schematic diagram illustrates exemplary hardware and software components of a fault location system 100 based on multimodal acoustic, optical, and electrical signal collaborative diagnosis, as provided in some embodiments of the present application, that can implement the principles of the present application. For example, processor 120 can be used in fault location system 100 based on multimodal acoustic, optical, and electrical signal collaborative diagnosis to perform the functions described in the present application.

[0138] The fault location system 100 based on multimodal acoustic, optical, and electrical signal collaborative diagnosis can be a general-purpose server or a special-purpose server, both of which can be used to implement the fault location method based on multimodal acoustic, optical, and electrical signal collaborative diagnosis of this application. Although only one server is shown in this application, for convenience, the functions described in this application can be implemented in a distributed manner on multiple similar platforms to balance the processing load.

[0139] For example, the fault location system 100 based on the collaborative diagnosis of multimodal acoustic, optical and electrical signals may include a network port 110 connected to a network, one or more processors 120 for executing program instructions, a communication bus 130, and storage media 140 in different forms, such as a disk, ROM, or RAM, or any combination thereof. Exemplarily, the fault location system 100 based on the collaborative diagnosis of multimodal acoustic, optical and electrical signals may also include program instructions stored in ROM, RAM, or other types of non-transitory storage media, or any combination thereof. The method of the present application may be implemented according to these program instructions. The fault location system 100 based on the collaborative diagnosis of multimodal acoustic, optical and electrical signals also includes an I / O interface 150 between the computer and other input and output devices.

[0140] For ease of explanation, only one processor is described in the fault location system 100 based on the collaborative diagnosis of multimodal acoustic, optical and electrical signals. However, it should be noted that the fault location system 100 based on the collaborative diagnosis of multimodal acoustic, optical and electrical signals in the present application may also include multiple processors, so the steps performed by one processor described in the present application may also be performed jointly or individually by multiple processors. For example, if the processor of the fault location system 100 based on the collaborative diagnosis of multimodal acoustic, optical and electrical signals executes step A and step B, it should be understood that step A and step B may also be executed jointly by two different processors or individually in one processor. For example, the first processor executes step A and the second processor executes step B, or the first processor and the second processor execute steps A and B jointly.

[0141] In addition, an embodiment of the present invention further provides a readable storage medium, in which computer-executable instructions are preset. When a processor executes the computer-executable instructions, the fault location method based on collaborative diagnosis of multimodal acoustic, optical and electrical signals as described above is implemented.

[0142] It should be noted that in order to simplify the description of the present invention and thus help understand one or more embodiments of the invention, in the foregoing description of the embodiments of the present invention, multiple features are sometimes combined into one embodiment, figure or description thereof.

Claims

1. A fault location method based on multimodal acoustic, optical and electrical signal collaborative diagnosis, characterized in that: The method comprises: Acquiring acoustic signal sequences, optical signal sequences, and electrical signal sequences from high-voltage electrical equipment in operation. The acoustic signal sequence includes information on changes in acoustic waveforms caused by vibrations in internal components of the equipment. The optical signal sequence includes information on changes in optical radiation intensity caused by partial discharges on the equipment surface. The electrical signal sequence includes information on instantaneous fluctuations in current and voltage in the equipment circuit. Performing cross-modal signal hierarchical association processing on the acoustic signal sequence, optical signal sequence, and electrical signal sequence, establishing a trigger response hierarchical relationship between different signal sequences, and generating a multimodal signal association hierarchical chain; Extracting a dynamic correlation feature set of each signal sequence in a hierarchical response process based on the multimodal signal correlation hierarchical chain, wherein the dynamic correlation feature set includes amplitude linkage parameters, phase synchronization parameters, and waveform distortion correlation parameters of the trigger signal and the hierarchical response signal; Inputting the dynamic correlation feature set into a preset fault feature evolution model to generate a fault feature identification sequence and a feature space diffusion trajectory; The fault starting area and the fault impact boundary range of the high-voltage electrical equipment are determined based on the fault feature identification sequence and the feature space diffusion trajectory.

2. The fault location method based on multimodal acoustic, optical and electrical signal collaborative diagnosis according to claim 1, characterized in that: The performing cross-modal signal hierarchical association processing on the acoustic signal sequence, the optical signal sequence, and the electrical signal sequence, establishing a trigger response hierarchical relationship between different signal sequences, and generating a multimodal signal association hierarchical chain includes: Intercepting signal segments of the acoustic signal sequence, optical signal sequence, and electrical signal sequence within the same monitoring period, wherein the signal segments include continuous signal fluctuation units and signal stable units, wherein the signal fluctuation units are signal segments with fluctuations in amplitude or frequency, and the signal stable units are signal segments with stable amplitude and frequency; Identifying a sudden acoustic wave segment in a signal segment of the acoustic signal sequence whose amplitude change rate exceeds a preset change rate threshold, and recording a starting time mark of the sudden acoustic wave segment as the starting point of the acoustic trigger level, wherein the amplitude change rate is the amount of change in amplitude per unit time; Identify a light radiation mutation segment in a signal segment of the light signal sequence, in which the light intensity change rate exceeds a preset change rate threshold, and record a start time mark of the light radiation mutation segment as a starting point of the light trigger level, wherein the light intensity change rate is a change in light radiation intensity per unit time; Identifying an electrical parameter mutation segment in which the current or voltage change rate exceeds a preset change rate threshold in a signal segment of the electrical signal sequence, and recording a start time mark of the electrical parameter mutation segment as a starting point of the electrical triggering level, wherein the current or voltage change rate is a change in current or voltage per unit time; Arranging the sound trigger level starting point, the light trigger level starting point, and the electrical trigger level starting point in chronological order to generate a trigger level sequence, wherein each starting point in the trigger level sequence is accompanied by a corresponding signal type identifier; Analyze the signal response relationship between adjacent trigger level starting points in the trigger level sequence, and establish a level response connection between the adjacent trigger level starting points when the signal change corresponding to the previous trigger level starting point triggers the signal change corresponding to the next trigger level starting point; A multimodal signal association hierarchical chain is formed through multiple hierarchical response connections, which includes a trigger hierarchical sequence, a hierarchical response delay parameter, and an amplitude linkage coefficient. The trigger hierarchical sequence reflects the sequence logic of each signal trigger, the hierarchical response delay parameter is the time difference between adjacent trigger starting points, and the amplitude linkage coefficient reflects the degree of correlation between the amplitude changes of the previous and subsequent signals.

3. The fault location method based on multimodal acoustic, optical and electrical signal collaborative diagnosis according to claim 2, characterized in that: The step of identifying a sound wave mutation segment in a signal segment of the sound signal sequence in which the amplitude change rate exceeds a preset change rate threshold, and recording a start time mark of the sound wave mutation segment as a sound trigger level starting point, includes: Traversing each signal sampling point in the signal segment of the acoustic signal sequence, calculating an amplitude change and a change time interval between a current sampling point and a previous sampling point, wherein the amplitude change is the difference between the amplitude of the current sampling point and the amplitude of the previous sampling point, and the change time interval is the time difference between the two sampling points; Calculating an amplitude change rate based on the amplitude change amount and the change time interval, wherein the amplitude change rate is a ratio of the amplitude change amount to the change time interval, wherein a positive value of the ratio indicates an increase in the amplitude, and a negative value indicates a decrease in the amplitude; When the amplitude change rate of a plurality of consecutive sampling points exceeds a preset change rate threshold, marking the signal segment consisting of the plurality of consecutive sampling points as a candidate acoustic wave mutation segment; Locating the starting sampling point of the candidate sound wave mutation segment and extracting the time coordinate of the starting sampling point in the sound signal segment; Taking the time coordinate as the sound triggering level starting point, repeat the above operation for all qualified candidate sound wave mutation segments in the signal segment of the sound signal sequence to generate a sound triggering level starting point set, in which each starting point is arranged in chronological order and is accompanied by corresponding signal amplitude information.

4. The fault location method based on multimodal acoustic, optical and electrical signal collaborative diagnosis according to claim 2, characterized in that: The analyzing the signal response relationship between adjacent trigger level starting points in the trigger level sequence, and establishing a level response connection between adjacent trigger level starting points when a signal change corresponding to a previous trigger level starting point triggers a signal change corresponding to a subsequent trigger level starting point, includes: Select two adjacent trigger level starting points from the trigger level sequence and mark them as the upper trigger starting point and the lower trigger starting point respectively; Extract the amplitude fluctuation curve of the signal segment corresponding to the upper trigger starting point before and after the trigger, and determine the peak interval and fluctuation duration of the amplitude fluctuation. The peak interval is the time range when the amplitude reaches the maximum value, and the fluctuation duration is the time range from the beginning of the signal change to the restoration of stability; Extract the amplitude fluctuation curve of the signal segment corresponding to the lower-level trigger starting point before and after the trigger, and determine the peak range and duration of the amplitude fluctuation; Compare the peak interval of the superior signal with the peak interval of the subordinate signal, and calculate the ratio of the overlapping duration to the total duration of the peak interval of the subordinate signal, where the overlapping duration is the intersection of the two peak intervals, and the total duration is the time span of the peak interval of the subordinate signal; Calculate the time interval between the upper trigger start point and the lower trigger start point, and determine a reasonable response time range based on the signal conduction characteristics of the device components; When the overlap duration ratio exceeds a preset ratio threshold and the time interval is within a reasonable response time range, it is determined that the change in the lower-level signal is caused by the change in the upper-level signal; A hierarchical response connection is established between the upper trigger starting point and the lower trigger starting point, and the response strength coefficient and signal conduction path identifier of the connection are recorded. The response strength coefficient is positively correlated with the overlap duration ratio, and the signal conduction path identifier reflects the propagation path of the signal inside the device.

5. The fault location method based on multimodal acoustic, optical and electrical signal collaborative diagnosis according to claim 1, characterized in that: The extracting of a dynamic correlation feature set of each signal sequence in a hierarchical response process based on the multimodal signal correlation hierarchical chain includes: Extracting trigger signal segments and hierarchical response signal segments corresponding to all hierarchical response connections from the multimodal signal association hierarchical chain; Calculate the ratio of the peak amplitude of the trigger signal segment to the peak amplitude of the level response signal segment in each level response connection, and use the ratio as the amplitude linkage parameter, where the peak amplitude is the maximum amplitude in the signal segment; Perform spectrum analysis on the trigger signal segment and the hierarchical response signal segment, extract the phase spectrum curves of the trigger signal segment and the hierarchical response signal segment, and calculate the absolute value of the phase difference of the phase spectrum curves in the same frequency range; Counting the proportion of frequency intervals where the absolute value of the phase difference is less than a preset phase difference threshold to the total analyzed frequency intervals, and using the proportion as a phase synchronization parameter; Comparing the waveform features of the trigger signal segment and the hierarchical response signal segment, extracting the number and degree of waveform distortion points, calculating the ratio of the number of distortion points and the correlation coefficient of the distortion degree, and using it as the waveform distortion correlation parameter; the waveform distortion point is the position that deviates from the normal waveform trend; The amplitude linkage parameters, phase synchronization parameters and waveform distortion correlation parameters are integrated to generate a dynamic correlation feature set. During the integration, the features are grouped according to the hierarchical response connections, and each set of features corresponds to one connection.

6. The fault location method based on multimodal acoustic, optical and electrical signal collaborative diagnosis according to claim 5, characterized in that: The extracting the trigger signal segments and the hierarchical response signal segments corresponding to all hierarchical response connections from the multimodal signal association hierarchical chain includes: Parsing the structure of the multimodal signal association hierarchical chain to determine the upper node and lower node of each hierarchical response connection, wherein the upper node corresponds to the trigger signal and the lower node corresponds to the hierarchical response signal; According to the time stamp of the upper-level node, a signal segment of a preset length before and after the time stamp is intercepted as a trigger signal segment, wherein the trigger signal segment includes a stable segment before the trigger, a sudden change segment during the trigger, and a decay segment after the trigger; According to the time stamp of the lower-level node, a signal segment of a preset length before and after the time stamp is intercepted as a hierarchical response signal segment, wherein the hierarchical response signal segment includes a preparatory segment before the response, a sudden change segment during the response, and a stable segment after the response; After performing a signal integrity check on the extracted trigger signal segments and hierarchical response signal segments, the trigger signal segments and hierarchical response signal segments belonging to the same hierarchical response connection are associated and stored to generate a hierarchical associated signal segment pair set; A corresponding hierarchical response connection identifier is added for each hierarchical association signal segment pair, wherein information of the hierarchical response connection identifier includes an upper-level node ID, a lower-level node ID, and a connection sequence number.

7. The fault location method based on multimodal acoustic, optical and electrical signal collaborative diagnosis according to claim 5, characterized in that: The comparing the waveform features of the trigger signal segment and the hierarchical response signal segment, extracting the number of waveform distortion points and the degree of distortion, and calculating the correlation coefficient of the ratio of the number of distortion points and the degree of distortion, includes: Extract waveform features from the trigger signal segment to identify distortion points in the waveform. The distortion points are sampling points that deviate from the normal waveform trend, which is obtained by fitting the stable portion of the signal segment. Counting the total number of distortion points in the trigger signal segment and calculating the ratio of the distortion points to the total length of the trigger signal segment as the trigger distortion ratio, where the total length of the trigger signal segment is the total number of sampling points included in the trigger signal segment; Extract waveform features of the hierarchical response signal segment, identify distortion points in the waveform, and count the total number of distortion points in the hierarchical response signal segment; Calculating a ratio of the total number of distortion points in the hierarchical response signal segment to the total number of distortion points in the trigger signal segment as the ratio of the number of distortion points, wherein a ratio greater than 1 indicates that the response signal is more severely distorted, and a ratio less than 1 indicates that the trigger signal is more severely distorted; Perform pairwise analysis on the corresponding distortion points in the trigger signal segment and the hierarchical response signal segment, and calculate the difference in distortion degree of each pair of distortion points. The corresponding distortion points are the distortion points that are temporally correlated. The correlation coefficient of the overall distortion degree is calculated according to the distortion degree difference. The closer the correlation coefficient is to a preset reference value, the more significant the distortion degree correlation is.

8. The fault location method based on multimodal acoustic, optical and electrical signal collaborative diagnosis according to claim 1, characterized in that: Inputting the dynamic correlation feature set into a preset fault feature evolution model to generate a fault feature identification sequence and a feature space diffusion trajectory includes: Converting the dynamic correlation feature set into a feature matrix that meets the input requirements of the fault feature evolution model, wherein the row dimension of the feature matrix corresponds to different hierarchical response connections, the column dimension corresponds to different dynamic correlation features, and the matrix elements are the quantized values ​​of the feature parameters; Calling the feature mapping module of the fault feature evolution model, mapping and matching the feature matrix with multiple fault evolution pattern templates stored in the fault feature evolution model, calculating the pattern matching degree between the feature matrix and each fault evolution pattern template, and selecting the fault evolution pattern template with the highest pattern matching degree as the target evolution template; Extracting the fault type identification sequence corresponding to the target evolution template and using it as a fault feature identification sequence, wherein the fault feature identification sequence reflects the characteristics of the fault at different stages from initialization to development; Based on the spatial distribution information contained in the feature matrix and combined with the spatial diffusion model of the target evolution template, a diffusion trajectory of the fault feature in the device structure space is generated, and the spatial distribution information is associated with the signal acquisition position; An association check is performed on the fault feature identifier sequence and the feature space diffusion trajectory, so that each fault feature identifier in the fault feature identifier sequence forms a one-to-one correspondence with a corresponding position on the feature space diffusion trajectory.

9. The fault location method based on multimodal acoustic, optical and electrical signal collaborative diagnosis according to claim 1, characterized in that: Determining the fault starting area and fault impact boundary range of the high-voltage electrical equipment based on the fault feature identification sequence and feature space diffusion trajectory includes: Parsing the initial identifier in the fault feature identifier sequence to obtain the initial fault feature information corresponding to the initial identifier, where the initial identifier is the earliest identifier in the fault feature identifier sequence and reflects the initial state of the fault; The spatial coordinates of the fault start are located by combining the starting point coordinates and the initial direction of the feature space diffusion trajectory, where the starting point coordinates are the first point of the feature space diffusion trajectory, and the initial direction of the trajectory is the tangent direction of the starting point of the trajectory; Determine the core area affected by the fault based on the fault feature identification strength corresponding to each trajectory point on the feature space diffusion trajectory, where the core area is an area where the identification strength is within a preset high intensity range, and the identification strength reflects the significance of the fault feature; Analyze the attenuation law of the marker strength during the trajectory extension process. When the marker strength drops to the preset boundary strength, the corresponding coordinate point constitutes the fault impact boundary. The marker strength attenuation law is obtained by fitting the strength change trend. Calculate the geometric center coordinates of the fault starting area and the maximum extension distance of the affected boundary, and generate fault location information including the center coordinates, boundary outline, and range size. The geometric center coordinates are the center of gravity of the core area. The fault location information is spatially mapped with the three-dimensional structural model of the high-voltage electrical equipment to obtain the specific location of the fault in the physical structure of the equipment and the information of the components involved. The spatial mapping is achieved based on the coordinate system conversion of the equipment.

10. A fault location system based on multimodal acoustic, optical and electrical signal collaborative diagnosis, characterized in that: It includes a processor and a memory, the memory is connected to the processor, the memory is used to store programs, instructions or codes, and the processor is used to execute the programs, instructions or codes in the memory to implement the fault location method based on multimodal acoustic, optical and electrical signal collaborative diagnosis as described in any one of claims 1 to 9.

Images