Real-time monitoring and early warning system for partial discharge based on multi-source data fusion

Abstract

The present application relates to the technical field of discharge monitoring and early warning, in particular to a local discharge real-time monitoring and early warning system based on multi-source data fusion, in the present application, a mixed transient signal stream is classified by a signal physical separation module to separate pure electromagnetic wave speed type and mechanical wave speed type signal sources; a feature marking module extracts feature points with a unified time reference and marks physical property categories; a dual-path credibility fusion module performs time difference logical verification on the two types of feature points, and only when the electromagnetic wave verification result and the mechanical wave verification result are both logical value 1, a credible discharge event is marked, and an event confidence parameter is generated through dynamic confidence fusion to realize physical interlocking verification and unique locking; an anti-interference response module dynamically adjusts a response threshold based on the event confidence parameter, and only triggers a targeted response to a threat whose physical nature is confirmed as a real discharge and whose confidence meets the standard; the present application solves the problem of distinguishing real discharge events from multi-source interference and reliably identifies real discharge events.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of discharge monitoring and early warning, in particular to a local discharge real-time monitoring and early warning system based on multi-source data fusion. BACKGROUND

[0002] The field of local discharge monitoring of power equipment has long been plagued by the bottleneck problem of multi-source interference coupling. Traditional monitoring systems rely on a single type of sensor (such as ultra-high frequency or ultrasonic wave) to capture transient signals, but in actual working conditions, electromagnetic noise, mechanical vibration and environmental interference will mix with real discharge signals, forming a mixed transient signal stream with similar time-frequency characteristics. Existing technologies cannot effectively distinguish between electromagnetic wave signals (such as ultra-high frequency radiation) and mechanical wave signals (such as ultrasonic wave propagation), resulting in a risk of physical nature misjudgment in the feature extraction process.

[0003] In addition, the single-path verification mechanism (such as relying only on spatial time difference or structure propagation model) cannot verify the physical consistency of the signal propagation path, and is easily affected by multi-path reflection, medium attenuation distortion and other factors, resulting in false alarms. More importantly, a fixed response threshold cannot adapt to complex working conditions such as changes in device load, fluctuations in environmental temperature and humidity, and often needs to sacrifice monitoring sensitivity to suppress false positives, ultimately leading to an increased rate of missed detection of early weak discharge. SUMMARY

[0004] The purpose of the present application is to provide a local discharge real-time monitoring and early warning system based on multi-source data fusion to solve the problems raised in the background art. The specific technical problems include how to realize double-path cross-verification and dynamic confidence fusion of electromagnetic wave signals and mechanical wave signals to solve the physical nature distinction problem of real discharge events and multi-source interference in mixed transient signal streams.

[0005] To achieve the above purpose, the present application provides the following technical solutions:

[0006] The local discharge real-time monitoring and early warning system based on multi-source data fusion includes a signal physical separation module, a feature marking module, a double-path credibility fusion module and an anti-interference response module, wherein:

[0007] The signal physical separation module obtains the original waveform of the mixed transient signal stream, uses a classification engine to extract the key feature attributes of the mixed transient signal stream, including the signal initial rising edge time, the main frequency band concentration area and the relative arrival time difference between multiple sensors; According to the key feature attributes, a multi-level decision node is established by a decision tree algorithm, and the signal initial rising edge time, the main frequency band concentration area and the relative arrival time difference between multiple sensors are used for three-level physical feature verification in turn, When the three-dimensional features meet the physical law of the same type of wave, the classification is completed; The decision-making process of the decision tree algorithm specifically includes:

[0008] The first level node is based on the comparison of the initial rising edge time of the signal and the preset time threshold, wherein if the initial rising edge time of the signal is lower than the preset time threshold, the electromagnetic wave speed type branch is entered, otherwise the mechanical wave speed type branch is entered;

[0009] The second level node is based on the energy distribution proportion of the signal energy in the preset frequency band threshold in the main frequency band concentrated area, wherein if the signal energy exceeds the preset frequency band threshold, the electromagnetic wave speed type candidate signal is taken, otherwise the reinforced mechanical wave speed type candidate signal is taken;

[0010] The third level node verifies the physical consistency of the determination conclusions of the previous two levels based on the deviation tolerance of the relative arrival time difference between the multiple sensors and the theoretical wave speed propagation model.

[0011] The signal physical separation module is used to separate the physical attributes of the electromagnetic wave speed and the mechanical wave speed signals, and eliminate the aliasing of the interference signals in a single feature dimension; through three-level physical law verification (rising edge speed, spectral energy, multi-source time difference correlation), it is ensured that the two types of signals input into the subsequent module meet the respective propagation nature, and pure electromagnetic wave speed type and mechanical wave speed type signal sources are provided for double-path cross verification.

[0012] The feature marking module is configured to extract feature points with a unified time reference from the original waveforms of the electromagnetic wave speed type signal and the mechanical wave speed type signal, and mark the electromagnetic wave speed type and the mechanical wave speed type for each feature point. Specifically, a unified time reference is established by using a high-precision time unified signal source, three types of feature points, i.e. pulse starting point, amplitude extreme point and oscillation decay inflection point, are extracted by using a method combining adaptive threshold detection and multi-scale morphological analysis, and a time stamp is assigned to each type of feature point.

[0013] The feature marking module constructs a space-time reference system across sensors, and the unified time reference ensures that the time stamps of the feature points of the electromagnetic wave speed and the mechanical wave speed signals are strictly comparable; the three types of feature points form standardized space-time markers (pulse starting point positioning propagation starting point, amplitude extreme point quantifying energy release, and oscillation decay inflection point revealing path characteristics), which provide synchronized and correlatable input data for the time difference logic verification of the double paths, and support accurate time difference comparison of electromagnetic wave spatial propagation and mechanical wave structure propagation.

[0014] The verification unit in the double-path credibility fusion module performs space propagation time difference logic verification on the electromagnetic wave speed type feature points, calculates the multi-sensor measured time difference based on the device three-dimensional coordinate model and the electromagnetic wave theoretical propagation model, verifies the consistency of the measured time difference and the theoretical time difference to generate an electromagnetic wave verification result (logical value 1 / 0), and generates an electromagnetic credible value by comprehensively considering the amplitude spatial distribution of the amplitude extreme point and the frequency damping characteristics of the oscillation decay inflection point.

[0015] The verification unit performs structural travel-time logic verification on the mechanical wave velocity type feature point, calculates the predicted travel-time through the device entity material acoustic model, verifies the consistency between the measured travel-time and the predicted value to generate the mechanical wave verification result (logical value 1 / 0); and generates the mechanical credible value by combining the amplitude gradient distribution of the amplitude extreme point and the oscillation decay inflection point boundary reflection effect.

[0016] The verification unit is used to realize the physical interlocking verification of the electromagnetic wave and mechanical wave propagation path. When the electromagnetic wave verification result is 1, it indicates that the signal conforms to the law of spatial light speed propagation, excluding slow conduction interference; when the mechanical wave verification result is 1, it indicates that the signal fits the structure acoustic propagation model, suppressing non-discharge vibration noise; only when the double-path verification result is 1 at the same time, mark the credible discharge event, from the essence of physical propagation, lock the uniqueness of the real discharge (such as only the real discharge event can produce electromagnetic radiation conforming to the law of spatial light speed propagation and mechanical vibration conforming to the law of solid sound speed propagation at the same time).

[0017] The fusion unit marks the current signal as a credible discharge event when the electromagnetic wave verification result is logical value 1 and the mechanical wave verification result is logical value 1; and assigns the electromagnetic credible value and the mechanical credible value to the reference weight of the final parameter based on the device type preset basic weight; introduces a feature correction mechanism on the reference weight, dynamically adjusts the double-path weight distribution using the energy release intensity ratio represented by the amplitude extreme point, and simultaneously performs reverse compensation adjustment on the corresponding path weight according to the propagation path complexity reflected by the oscillation decay inflection point, and outputs the event confidence parameter of continuous scale after normalization processing.

[0018] The fusion unit is used to dynamically fuse the confidence contribution of the double path. The energy intensity ratio adjustment gives higher weight to the strong energy release path (reflecting the main factor of discharge hazard); the path complexity compensation suppresses the interference of medium distortion on the credibility of a single propagation path (such as the influence of sound wave attenuation in oil-immersed equipment); makes the confidence parameter objectively quantify the joint credibility of the real discharge event in the electromagnetic and mechanical double paths, and solves the misjudgment caused by local interference (such as sensor failure, medium unevenness) in traditional single-path verification.

[0019] The anti-interference response module dynamically adjusts the response threshold based on the event confidence parameter: first match it to the preset three-level static reference interval, dynamically adjust the response threshold proportion coefficient according to the confidence interval to generate a dynamic response threshold; only when the credible discharge event is marked as true and the event confidence parameter exceeds the dynamic threshold, the alarm response is triggered, the process includes dividing multiple alarm levels according to the event confidence parameter value, generating early warning escalation decision combining historical confidence trend, recording confidence parameter change trajectory and response time sequence.

[0020] The anti-interference response module is used for driving a dynamic response based on a confidence parameter of double-path fusion, and a dynamic threshold mechanism automatically increases a response threshold in a strong interference environment (such as a lightning electromagnetic pulse), to avoid false alarms; early discharge (such as a corona on the surface of an insulator) with weak but slowly rising confidence is pre-warned through historical trend analysis to reduce missed alarms; and finally, only a threat confirmed as real discharge in physical nature and meeting the confidence standard triggers a targeted response, to distinguish multiple-source interference from real discharge events.

[0021] Compared with the prior art, the present application has the following beneficial effects:

[0022] The double-path credibility fusion module is used for realizing physical interlocking verification of electromagnetic wave and mechanical wave propagation paths, and when the double-path verification results are both logical value 1, a credible discharge event is marked, to lock the uniqueness of real discharge from the physical propagation nature; meanwhile, event confidence parameters are dynamically fused based on the energy release intensity ratio and the propagation path complexity, and finally, only a threat confirmed as real discharge in physical nature and meeting the confidence standard triggers a targeted response by the anti-interference response module, to solve the problem of distinguishing real discharge events from multiple-source interference in mixed transient signal flow, and to reliably identify real discharge events. BRIEF DESCRIPTION OF DRAWINGS

[0023] Figure 1 It is a schematic diagram of the overall module of the present application;

[0024] Figure 2 It is a schematic diagram of the double-path credibility fusion module unit of the present application;

[0025] Figure 3 It is a schematic diagram of the verification unit flow of the present application;

[0026] Figure 4 It is a schematic diagram of the fusion unit flow of the present application.

[0027] In the figure: 100, signal physical separation module; 200, feature marking module; 300, double-path credibility fusion module; 301, verification unit; 302, fusion unit; 400, anti-interference response module. DETAILED DESCRIPTION

[0028] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the protection scope of the present application.

[0029] Next, please refer to Figure 1The application provides a technical scheme: a partial discharge real-time monitoring and early warning system based on multi-source data fusion, comprising a signal physical separation module 100, a feature marking module 200, a double-path credibility fusion module 300 and an anti-interference response module 400.

[0030] The signal physical separation module 100 is the physical basis for the entire system to realize preliminary information processing, and its core task is to classify and synchronously record the original mixed signals collected from multiple measuring points of electrical equipment based on the differences in different propagation media and wave speed characteristics caused by partial discharge phenomena; the specific technical process is as follows:

[0031] Receiving the original waveform of each mixed transient signal stream detected by a sensor array (such as a very high frequency sensor, an ultrasonic sensor, a high-frequency current transformer, etc.);

[0032] Scanning each mixed transient signal stream using a classification engine (which may include methods such as wavelet packet analysis, multi-resolution spectrum analysis or other feature extraction methods) to extract its key feature attributes, including signal initial rising edge time, main frequency band concentration area and relative arrival time difference between multiple sensors;

[0033] Based on the key feature attributes corresponding to each mixed transient signal stream, the mixed transient signal stream is classified into electromagnetic wave speed type signals and mechanical wave speed type signals using a decision tree algorithm, wherein the classification process specifically includes:

[0034] First, a multi-level decision node is established, each node corresponding to a key physical feature attribute, and the first level node focuses on the signal initial rising edge time. Since the electromagnetic wave propagates at a speed close to the speed of light, the transient pulse it triggers usually presents a sub-microsecond or even shorter steep front edge. The propagation speed of mechanical waves (such as ultrasonic waves) is restricted by the density and elastic modulus of the medium, and the typical value is about kilometers per second, corresponding to a pulse front edge broadening to more than a microsecond. Therefore, by extracting the actual duration of the pulse rising edge through high-precision time domain analysis, when the value is lower than the preset time threshold, it is determined that the signal enters the electromagnetic wave speed type branch, otherwise it enters the mechanical wave speed type branch;

[0035] The second level node analyzes the main frequency band concentration area. The electromagnetic wave signal is mainly distributed in the hundreds of megahertz to gigahertz frequency band due to the high frequency characteristics of the discharge source and the electromagnetic coupling effect. The main frequency band of the mechanical wave signal is concentrated in the tens of kilohertz to hundreds of kilohertz interval due to the frequency response and propagation attenuation of the transducer. Therefore, by using real-time spectrum analysis technology, the signal energy in the main frequency band concentration area is compared with the preset frequency band threshold. If the signal energy exceeds the preset frequency band threshold, it is considered as an electromagnetic wave speed type candidate signal, otherwise it is considered as a reinforced mechanical wave speed type candidate signal;

[0036] The third level node verifies the relative time difference between multiple sensors, and based on the known spatial coordinates of the sensors, the algorithm constructs a theoretical wave propagation model. For electromagnetic wave speed candidate signals, the algorithm checks whether the time difference between the signals of each sensor conforms to the propagation delay of the order of light speed. For mechanical wave speed candidate signals, the algorithm checks whether the time difference conforms to the propagation delay of the order of sound speed. The node performs strict physical consistency verification. If the measured time difference deviates from the theoretical model by more than the tolerance, the previous two levels of judgment are overturned, and a reclassification mechanism is triggered. The process of the reclassification mechanism specifically includes:

[0037] Returning to the second level node, the energy distribution proportion of the main frequency band concentrated region is used to reclassify the candidate signal class. If the reclassification still cannot pass the third level verification, an auxiliary judgment node is activated. By analyzing the oscillation modal damping ratio of the signal waveform, the characteristics of electromagnetic oscillation decay and mechanical resonance decay are further distinguished, and the physical nature classification is finally completed.

[0038] Finally, the decision tree algorithm forms a classification conclusion through three layers of physical feature verification. Only when the signal initial rising edge time, the main frequency band concentrated region, and the relative time difference between multiple sensors all meet the physical law of the same type of wave, the signal is determined as an electromagnetic wave speed signal or a mechanical wave speed signal. The whole process is executed in real time in the embedded system with a pipeline architecture, ensuring that each transient event completes the physical nature classification within milliseconds. For transition state signals that cannot simultaneously satisfy the three-dimensional physical law, they are marked as to-be-processed signals and execute a buffering mechanism. By temporarily caching them in an independent queue, the dynamic reclassification is performed by combining the feature change trend of the subsequent continuous sampling period (such as the shortening or lengthening of the rising edge time). If it still cannot be classified, the diagnostic support mechanism is triggered, and the original waveform data is preserved. The process of the diagnostic support mechanism specifically includes:

[0039] The key feature attributes (signal initial rising edge time, main frequency band concentrated region, and relative time difference between multiple sensors) extracted in the signal physical separation module 100 are called, and the oscillation decay inflection point feature in the dual-path credibility fusion module is combined to generate a multi-dimensional feature comparison graph. The graph is compared with the waveform features marked as typical interference in the historical cache (based on the Euclidean distance to calculate the difference degree of the key feature vector). If the difference degree is lower than the preset threshold, it is classified as interference. Otherwise, the original waveform data is preserved, and an artificial review interface is activated.

[0040] The feature labeling module 200 is a direct successor processing link of the signal physical separation module 100. Its core function is to extract key points with physical representation significance from the original waveforms of the two classified signals, and assign strict class identification and time reference. The specific implementation process is as follows:

[0041] Receive two parallel data streams output from the signal physical separation module 100, namely the original waveform of the electromagnetic wave speed type signal and the original waveform of the mechanical wave speed type signal; for each type of signal, first perform feature point extraction with unified time reference; this process relies on the global clock system established by high-precision time signal source (such as GPS timing or crystal oscillator synchronization), and ensures strict time synchronization of waveforms collected by different sensors through trigger alignment mechanism; the process of trigger alignment mechanism is as follows:

[0042] Synchronization pulse generated by high-precision time signal source, hardware trigger mode is used to control the synchronous start of all sensor acquisition channels; for transmission delay, the relative delay of each channel is inversely deduced by using the timestamp of the pulse starting point in the feature marking module 200, and the timestamp is linearly compensated and calibrated in the data preprocessing stage.

[0043] The feature extraction engine uses a method combining adaptive threshold detection and multi-scale morphological analysis to identify feature points from the time domain sequence of each original waveform, including pulse starting point (corresponding to discharge initiation time), amplitude extreme point (representing energy release intensity) and oscillation decay inflection point (reflecting propagation decay characteristics); each extracted feature point is assigned a timestamp accurate to nanoseconds, which is derived from the clock reference source of the unified time reference, thereby realizing absolute time alignment across sensors and across signal types;

[0044] After completing the feature point extraction, perform generic identification labeling; this step automatically inherits the classification conclusion of the original waveform by the signal physical separation module 100, and automatically labels electromagnetic wave speed type identification for the feature points extracted from the electromagnetic wave speed type signal waveform; for the feature points extracted from the mechanical wave speed type signal waveform, mechanical wave speed type identification is labeled; such identification is bound to the timestamp and amplitude feature vector of each feature point as metadata, forming a structured feature data set; in this process, the data pipeline architecture is used to maintain processing timeliness, ensuring that the feature point set with unified time reference and clear physical generic identification is transmitted in real time to the subsequent dual-path credibility fusion module 300 under the premise of preserving the complete details of the original waveform, providing standardized input for spatial / structural propagation time difference logic verification.

[0045] Please refer to Figure 2 , the dual-path credibility fusion module 300 is the core link of system criterion generation, which implements physical propagation consistency verification on the feature point set input by the previous stage through parallel dual-channel verification mechanism, and generates quantitative credibility evaluation parameters, the specific execution process is as follows:

[0046] The verification unit 301 in the dual-path credibility fusion module 300 performs spatial travel time difference logical verification on the feature points marked with electromagnetic wave speed type identifiers, extracts the pulse start point timestamp in the feature points (corresponding to the discharge excitation time) to calculate the multi-sensor absolute arrival time difference, verifies the consistency of the measured time difference and the model theoretical time difference, and if the consistency is met, the electromagnetic wave verification result is set to logical value 1, otherwise 0; the amplitude spatial distribution of the amplitude extreme point (representing the energy release intensity) is simultaneously used to verify the electromagnetic wave attenuation law, and the oscillation mode of the oscillation attenuation inflection point (reflecting the propagation attenuation characteristic) is used to supplement the verification of the propagation path characteristic; the electromagnetic credibility value is generated by comprehensively integrating the information of multiple feature points, wherein the generation of the electromagnetic credibility value integrates the verification results of three-dimensional feature points, specifically including:

[0047] Firstly, the credibility basic value is calculated by using the time difference matching degree of the pulse start point timestamp, and the smaller the time difference deviation is, the higher the basic value is; secondly, the amplitude spatial distribution of the amplitude extreme point representing the energy release intensity is used to verify whether it conforms to the electromagnetic wave inverse square law to generate an attenuation compliance coefficient; finally, the frequency damping characteristics of the oscillation attenuation inflection point reflecting the propagation attenuation characteristics are combined to analyze the uniformity of the propagation path medium; the quantization results of the above three types of feature points are fused according to the preset weight, wherein the time difference matching contributes mainly to the basic value, and the attenuation gradient and the oscillation mode characteristics are respectively used as the core supplement and auxiliary correction terms to finally generate an electromagnetic credibility value of 0 to 100%; wherein the quantization results of the above three types of feature points are fused according to the preset weight, the pulse start point time difference matching degree weight α (for example, the reference value is 0.6), the amplitude extreme point attenuation gradient weight β (for example, the reference value is 0.3), and the oscillation attenuation inflection point damping feature weight γ (for example, the reference value is 0.1) are set, which satisfy the normalization condition α+β+γ=1; the fusion formula is:

[0048] The electromagnetic credibility value = α × time difference matching degree + β × attenuation compliance coefficient + γ × oscillation mode score, wherein the time difference matching degree is determined by the deviation degree of the measured time difference and the theoretical time difference, the attenuation compliance coefficient is obtained by logarithmic operation of the measured and theoretical attenuation ratios, and the oscillation mode score is calculated according to the chi-square test result of the frequency damping ratio and the standard value.

[0049] The verification unit 301 performs structural travel time difference logical verification on the feature points marked with mechanical wave speed type identifiers, calculates the structural travel time difference through the feature point pulse start point timestamp according to the equipment entity material acoustic model, verifies the consistency of the time difference and the predicted value in the equipment entity material acoustic model, and if the consistency is met, the mechanical wave verification result is set to logical value 1, otherwise 0; meanwhile, the amplitude gradient distribution of the amplitude extreme point is extracted to verify the energy attenuation characteristics of the mechanical wave in the structure, and the damping oscillation characteristics of the oscillation attenuation inflection point (reflecting the structure boundary reflection effect) are analyzed to enhance the credibility judgment of the propagation path; the mechanical credibility value is generated by integrating multiple features, specifically including:

[0050] The measured time difference of the pulse starting point timestamp is converted into a basic reliable value according to the coincidence degree with the theoretical value; the amplitude change gradient of the amplitude extreme point representing the energy release intensity is verified to have an exponential mechanical vibration attenuation characteristic in the equipment entity structure; further, the echo interval and amplitude attenuation rate reflecting the propagation attenuation characteristic of the oscillation attenuation inflection point are extracted to analyze the structure boundary reflection effect and material impedance characteristic; the verification data of the three types of feature points are given different weights according to the equipment structure characteristics, the time difference coincidence rate constitutes the core reference, the attenuation characteristic and the boundary effect are respectively used as the key supplement and special correction factor, and finally the mechanical reliable value of 0 to 100% is synthesized.

[0051] Please refer to Figure 3 The verification unit 301 performs spatial propagation time difference logical verification and structure propagation time difference logical verification in a parallel manner, specifically including:

[0052] Firstly, for the electromagnetic wave speed type feature point, based on the three-dimensional coordinate model of the equipment and the theoretical propagation model of the electromagnetic wave, the multi-sensor measured time difference (obtained through the pulse starting point timestamp) is calculated and compared with the theoretical time difference for consistency; if the time difference deviation is within the tolerance, the electromagnetic wave verification result is set to logical value 1, otherwise 0;

[0053] At the same time, the amplitude space distribution of the amplitude extreme point (verifying the electromagnetic wave attenuation law) and the frequency damping characteristic of the oscillation attenuation inflection point (analyzing the uniformity of the propagation path) are combined to generate an electromagnetic reliable value of 0 to 100% (the basic value is derived from the time difference matching degree, and the attenuation gradient and the oscillation mode are used as supplements);

[0054] For the mechanical wave speed type feature point, the process uses the acoustic model of the equipment entity material to calculate the structure propagation measured time difference, verifies its consistency with the predicted value to generate a mechanical wave verification result (logical value 1 / 0), and combines the amplitude gradient distribution of the amplitude extreme point (verifying the exponential attenuation characteristic of the mechanical wave) and the boundary reflection effect of the oscillation attenuation inflection point (analyzing the structure impedance) to generate a mechanical reliable value (the time difference coincidence rate is the core, and the attenuation characteristic and the boundary effect are correction factors);

[0055] The whole process ensures the mutual locking verification of the essence of the double-path physical propagation, and only when both types of verification meet the preset law can the valid result be output, providing reliable input for the subsequent fusion unit 302.

[0056] The fusion unit 302 in the double-path reliability fusion module 300 performs a double-physical-path joint decision mechanism, specifically including:

[0057] Only when the electromagnetic wave verification result and the mechanical wave verification result are both logical value 1, that is, the pulse starting point time difference verification of the double-path passes, and the energy attenuation characteristics of the amplitude extreme point and the propagation characteristics of the oscillation attenuation inflection point all meet the preset law, is marked as a reliable discharge event;

[0058] The two types of credible values (electromagnetic credible values and mechanical credible values) are weighted and fused to generate an event confidence parameter. The event confidence parameter is generated using a dynamic weighting fusion algorithm. The electromagnetic credible values and the mechanical credible values are assigned reference weights in the final parameter based on the type of device, for example, a gas insulated device focuses on the electromagnetic wave path weight and an oil immersed device focuses on the mechanical wave path. A feature correction mechanism is introduced on the reference weight. The energy release intensity proportion represented by the amplitude extreme point is used to dynamically adjust the double path weight distribution. At the same time, the propagation path complexity reflected by the oscillation decay inflection point is used to inversely compensate and adjust the corresponding path weight. After normalization processing, an event confidence parameter with a continuous scale of 0 to 100% is output. This parameter comprehensively represents the joint credibility level of the discharge event in the electromagnetic propagation space characteristic and mechanical propagation structure characteristic dimensions. Wherein:

[0059] The process of dynamically adjusting the double path weight distribution is as follows:

[0060] According to the amplitude value of the amplitude extreme point extracted by the feature marking module 200, the amplitude ratio of the electromagnetic path and the mechanical path is calculated. The ratio is used as an adjustment factor. The weight proportion of the high amplitude value path is amplified by the same ratio according to the preset device type reference weight in the fusion unit 302 (such as a gas insulated device focusing on the electromagnetic path). The high amplitude value path is determined by comparing the preset amplitude ratio threshold value. The value greater than the preset amplitude ratio threshold value is considered as the high amplitude value path.

[0061] The process of inverse compensation adjustment is as follows:

[0062] The oscillation decay inflection point parameters (damping oscillation period number, amplitude decay rate) in the feature marking module 200 are extracted. The ratio of the damping oscillation period number and the amplitude decay rate is calculated, and the ratio is used as a path complexity factor. According to the preset complexity and weight mapping relationship in the device entity material acoustic model, the weight of the high complexity path is reduced and compensated. The high complexity path is determined by comparing the preset complexity ratio threshold value. The value greater than the preset complexity ratio threshold value is considered as the high complexity path.

[0063] Please refer to Figure 4 The fusion unit 302 executes a double physical path joint decision mechanism, which specifically includes:

[0064] First, the electromagnetic wave verification result and the mechanical wave verification result output by the verification unit 301 both need to be logical value 1 (indicating that the space propagation and the structure propagation both conform to the physical law). At this time, it is marked as a credible discharge event (the true discharge nature is uniquely locked).

[0065] Subsequently, event confidence parameters are generated, and baseline weights for electromagnetic confidence values ​​and mechanical confidence values ​​are assigned based on preset base weights for equipment type (e.g., electromagnetic path weights are emphasized for gas-insulated equipment, and mechanical path weights are emphasized for oil-immersed equipment). A dynamic feature correction mechanism is introduced, which dynamically adjusts the dual-path weight allocation by using the energy release intensity ratio represented by the amplitude extreme point (e.g., the weight of strong energy release paths is increased). In addition, reverse compensation adjustment is performed by combining the propagation path complexity reflected by the oscillation attenuation inflection point (e.g., the effect of sound wave attenuation in oil-immersed media) (the weight of high-complexity paths is reduced to suppress distortion interference).

[0066] Finally, the event confidence parameter is output with a continuous scale from 0 to 100% through normalization. This parameter quantifies the joint confidence of the electromagnetic and mechanical dual paths, providing a basis for dynamic threshold adjustment for the anti-interference response module 400 and solving the problem of misjudgment caused by local interference in a single path.

[0067] The anti-interference response module 400 dynamically adjusts the response threshold based on event confidence parameters, triggering alarm responses only for reliable discharge events, specifically including:

[0068] The preset event confidence parameters have three levels of static baseline intervals, including a high confidence interval (e.g., preset to 80% to 100%), a medium confidence interval (50% to 80%), and a low confidence interval (0% to 50%). When the event confidence parameters fall into the high confidence interval, the response threshold is adjusted according to a high confidence ratio factor. Dynamically reduce (wherein) This is used to enhance the alarm sensitivity of high-confidence events; when the parameter falls within the middle confidence interval, the response threshold is adjusted according to a neutral scaling factor. Maintain the benchmark level (of which When the parameter falls into the low confidence interval, the response threshold is adjusted according to the low confidence ratio. Dynamically adjust upwards (of which) ), used to suppress the risk of false alarms from low-reliability signals;

[0069] On the basis of dynamic regulation of response threshold, only when the input event meets the true label of credible discharge event and its event confidence parameter exceeds the current response threshold, the alarm response process is activated; during the response process, multi-level alarm grades are divided according to the event confidence parameter value (such as high-confidence emergency alarm, medium-confidence early warning, etc.), and early warning upgrade decisions are generated in combination with historical confidence trend analysis (such as three consecutive detections of confidence parameter rising credible events); all response behaviors are transmitted to the monitoring system through standard industrial protocols, and complete event confidence parameter change trajectories and response time sequences are automatically recorded, providing a data basis for subsequent diagnosis; the whole process runs under real-time closed-loop control, effectively suppressing false positives and ensuring immediate capture of real insulation defects, ultimately realizing credible perception and risk warning of the partial discharge state of power equipment; the process of generating early warning upgrade decisions is specifically as follows:

[0070] Within the sliding time window, the event confidence parameter sequence of the credible discharge event is counted, and if the consecutive event confidence parameters meet the monotone increasing rule, or the proportion of high-confidence events (confidence parameters in the high-confidence interval) in the window exceeds the preset proportion, the alarm grade is automatically upgraded.

[0071] The above shows and describes the basic principles, main features and advantages of the present application. It should be understood by those skilled in the art that the present application is not limited by the above examples, and the above examples and descriptions in the specification are only preferred examples of the present application and are not intended to limit the present application. Without departing from the spirit and scope of the present application, various changes and improvements can be made to the present application, and these changes and improvements all fall within the scope of the present application. The scope of protection of the present application is defined by the appended claims and their equivalents.

Claims

1. A real-time monitoring and early warning system for partial discharge based on multi-source data fusion, characterized in that, It includes a signal physical separation module (100), a feature marking module (200), a dual-path reliability fusion module (300), and an anti-interference response module (400), wherein: The signal physical separation module (100) acquires the original waveform of the mixed transient signal stream and uses a decision tree algorithm to classify the mixed transient signal stream into electromagnetic wave speed signals and mechanical wave speed signals. The feature marking module (200) is configured to extract feature points with a unified time reference from the original waveforms of electromagnetic wave speed type signals and mechanical wave speed type signals, and to mark each feature point with the identification of electromagnetic wave speed type and mechanical wave speed type. The dual-path credibility fusion module (300) is configured to perform spatial propagation time difference logic verification on feature points labeled with electromagnetic wave speed, and generate electromagnetic wave verification results and electromagnetic credibility values; perform structural propagation time difference logic verification on feature points labeled with mechanical wave speed, and generate mechanical wave verification results and mechanical credibility values; mark a credible discharge event only when both types of verification results simultaneously satisfy a preset law, and weight and fuse the two types of credibility values ​​to generate event confidence parameters; The anti-interference response module (400) is configured to dynamically adjust the response threshold based on the event confidence parameter and trigger an alarm response only for trusted discharge events.

2. The partial discharge real-time monitoring and early warning system based on multi-source data fusion according to claim 1, characterized in that, The classification process of the signal physical separation module (100) includes: The classification engine is used to extract key feature attributes of the mixed transient signal stream, including the initial rise time of the signal, the concentrated region of the main frequency band, and the relative arrival time difference between multiple sensors; Based on key feature attributes, a multi-level decision node is established using a decision tree algorithm. The three-level physical feature verification is performed sequentially using the initial rise time of the signal, the concentrated area of ​​the main frequency band, and the relative arrival time difference between multiple sensors. The classification is completed when the three dimensions of features satisfy the physical laws of the same type of wave.

3. The partial discharge real-time monitoring and early warning system based on multi-source data fusion according to claim 2, characterized in that, The decision tree algorithm's determination process specifically includes: The first-level node is based on the comparison between the initial rise time of the signal and a preset time threshold. If the initial rise time of the signal is lower than the preset time threshold, it enters the electromagnetic wave speed branch; otherwise, it enters the mechanical wave speed branch. The second-level node is based on the energy distribution ratio of signal energy in the concentrated area of ​​the main frequency band within a preset frequency band threshold. If the signal energy exceeds the preset frequency band threshold, it is regarded as a candidate signal of electromagnetic wave speed, and otherwise it is regarded as a candidate signal of enhanced mechanical wave speed. The third-level node verifies the physical consistency of the judgment conclusions of the first two levels based on the deviation tolerance between the relative arrival time difference between multiple sensors and the theoretical wave speed propagation model.

4. The partial discharge real-time monitoring and early warning system based on multi-source data fusion according to claim 1, characterized in that, The feature marking module (200) establishes a unified time reference through a high-precision time synchronization signal source, and uses a combination of adaptive threshold detection and multi-scale morphological analysis to extract three types of feature points: pulse start point, amplitude extreme point, and oscillation decay inflection point, and assigns a timestamp to each type of feature point.

5. The partial discharge real-time monitoring and early warning system based on multi-source data fusion according to claim 1, characterized in that, The dual-path reliability fusion module (300) includes a verification unit (301), which is used for spatial propagation time difference logic verification, specifically including: Based on the device's three-dimensional coordinate model and the electromagnetic wave theoretical propagation model, the measured time difference of multiple sensors is calculated by using the pulse start point timestamp. The consistency between this time difference and the theoretical time difference in the electromagnetic wave theoretical propagation model is verified to generate an electromagnetic wave verification result. If the consistency is satisfied, the electromagnetic wave verification result is set to a logic value of 1; otherwise, it is set to 0. The electromagnetic reliability value is generated by combining the amplitude spatial distribution of the amplitude extreme point and the frequency damping characteristics of the oscillation attenuation inflection point.

6. The partial discharge real-time monitoring and early warning system based on multi-source data fusion according to claim 5, characterized in that, The process of the verification unit (301) performing the structure propagation time difference logic verification specifically includes: By using the acoustic model of the equipment's physical material and the pulse start point timestamp to calculate the measured time difference of structural propagation, the consistency between this time difference and the predicted value in the acoustic model of the equipment's physical material is verified to generate a mechanical wave verification result. If the consistency is satisfied, the mechanical wave verification result is set to a logic value of 1; otherwise, it is set to 0. The mechanical reliability value is generated by combining the amplitude gradient distribution at the amplitude extreme point and the boundary reflection effect at the oscillation attenuation inflection point.

7. The partial discharge real-time monitoring and early warning system based on multi-source data fusion according to claim 1, characterized in that, The dual-path reliability fusion module (300) includes a fusion unit (302). When the fusion unit (302) obtains that the electromagnetic wave verification result is logic value 1 and the mechanical wave verification result is logic value 1, it marks the current signal as a reliable discharge event.

8. The partial discharge real-time monitoring and early warning system based on multi-source data fusion according to claim 7, characterized in that, The process by which the fusion unit (302) generates event confidence parameters specifically includes: Based on the equipment type, the electromagnetic confidence value and mechanical confidence value are assigned as the baseline weights in the final parameters. A feature correction mechanism is introduced on the baseline weights, and the energy release intensity ratio represented by the amplitude extreme point is used to dynamically adjust the dual-path weight allocation. At the same time, the corresponding path weights are adjusted in reverse compensation according to the propagation path complexity reflected by the oscillation decay inflection point. After normalization processing, the event confidence parameters with continuous scaling are output.

9. The partial discharge real-time monitoring and early warning system based on multi-source data fusion according to claim 1, characterized in that, The process by which the anti-interference response module (400) triggers an alarm response specifically includes: Match the event confidence parameters to a preset three-level static baseline range; The response threshold ratio is dynamically adjusted based on the confidence interval, and the adjusted response threshold is obtained. An alarm response is triggered only when a trusted discharge event is marked as true and the event confidence parameter exceeds the adjusted response threshold.

10. The partial discharge real-time monitoring and early warning system based on multi-source data fusion according to claim 9, characterized in that, The execution process of the alarm response specifically includes: Alarm levels are categorized into multiple levels based on event confidence parameter values; Generate early warning escalation decisions by combining historical confidence trend analysis; Record the trajectory of changes in event confidence parameters and the response time series.

Images