A multi-source signal fusion high-voltage switch cabinet intelligent monitoring and fault adaptive protection system

Abstract

The application discloses a kind of multi-source signal fusion's high-voltage switch cabinet intelligent monitoring and fault adaptive protection system, relating to switch cabinet technical field, including multi-source perception module, state evaluation module, adaptive protection module, the multi-source perception module synchronously collects UHF, AE, arc light and primary loop current, completes front-end conditioning and unified time reference, as the basis for subsequent correlation and calculation, the state evaluation module is based on double threshold+Trend completes grading, and establishes and calls non-linear relationship of partial discharge and overcurrent according to the same model baseline, residual and persistence are calculated online, output grade, high-risk flag and auxiliary criterion, the adaptive protection module executes arc light associated partial discharge and arc light overcurrent fusion trigger, meets fusion criterion, i.e. trip, and when residual continues to exceed threshold, correlation threshold and pre-window are sensitized, the application has the characteristics of accurate determination.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of switch cabinet, in particular to a multi-source signal fusion high-voltage switch cabinet intelligent monitoring and fault adaptive protection system. BACKGROUND

[0002] The high-voltage switch cabinet is the core equipment of the power distribution network, and its internal fault, especially insulation fault, is the main cause of serious accidents. In-depth analysis shows that the cabinet arc fault mainly comes from two reasons: one is the insulation breakdown caused by long-term deterioration of insulation materials; the other is the instantaneous short circuit caused by non-insulation material problems such as mechanical connection loosening and foreign matter intrusion.

[0003] The existing technology has partial discharge online monitoring system focusing on monitoring the early signs of the first type of fault (insulation deterioration) through ultra-high frequency (UHF), ultrasonic wave (AE) and other sensors to realize predictive maintenance, and arc light + overcurrent dual criterion is generally used to quickly cut off the power supply after the fault arc occurs, which belongs to the arc light protection device for post-protection, but the former cannot realize rapid tripping protection at the moment of fault and is powerless to the second type of sudden fault, and sometimes it may misjudge the similar characteristics of corona, external electromagnetic radiation, machinery and airflow noise as partial discharge, thus causing misoperation; the latter cannot distinguish the cause of arc light, and for the first type of fault, it is prone to misoperation due to light interference, and for the second type of fault with high impedance, it may be rejected due to insufficient current. Therefore, it is necessary to design a multi-source signal fusion high-voltage switch cabinet intelligent monitoring and fault adaptive protection system. SUMMARY

[0004] The purpose of the present application is to provide a multi-source signal fusion high-voltage switch cabinet intelligent monitoring and fault adaptive protection system to solve the problems raised in the background technology.

[0005] In order to solve the above technical problems, the present application provides the following technical scheme: a multi-source signal fusion high-voltage switch cabinet intelligent monitoring and fault adaptive protection system, comprising a multi-source perception module, a state evaluation module and an adaptive protection module, the multi-source perception module synchronously collects UHF, AE, arc light and primary circuit current, completes front-end conditioning and unified time reference, and serves as the basis for subsequent correlation and calculation, the state evaluation module completes grading based on double threshold + trend, and establishes and calls the nonlinear relationship between partial discharge and overcurrent according to the same type baseline, and outputs the level, high-risk flag and auxiliary criterion by online calculation of residual error and persistence, the adaptive protection module executes arc light associated partial discharge and arc light overcurrent fusion trigger, meets the fusion criterion to trip, and increases the sensitivity of the correlation threshold and the pre-window when the residual error continues to exceed the threshold.

[0006] According to the technical scheme, the multi-source perception module comprises a multi-source sensing unit and a fusion judgment module, the multi-source sensing unit is composed of a UHF sensor, an ultrasonic sensor, an arc sensor and a current sampling module, is used for collecting UHF, AE, arc light and current four-way signals, the fusion judgment module performs PRPD spectrum analysis on the partial discharge signal, and extracts the characteristics of the discharge quantity and discharge frequency; and the effective value of the current signal is calculated.

[0007] The state evaluation module comprises a double-threshold trend enhancement grading module, a nonlinear baseline modeling module and a residual judgment module, the double-threshold trend enhancement grading module is used for outputting normal, first-level and second-level grades according to the low and high threshold superposition trend and persistence rules, focusing on sensitive identification of continuous degradation, the nonlinear baseline modeling module establishes and calls the nonlinear mapping of partial discharge and overcurrent for each model, and provides expected changes of load interpretability, and the residual judgment module calculates whether the residual judgment of actual and expected changes is continuously deviated;

[0008] The adaptive protection module comprises an associated threshold adjustment module, a trip control module and an event packaging reporting module, the associated threshold adjustment module adjusts the partial discharge associated threshold according to the coefficient when the nonlinear inconsistency occurs, the event packaging reporting module uploads each data as structured evidence together with the grade and action result, and the trip control module is used for tripping when a fault occurs.

[0009] According to the technical scheme, the working method of the system is as follows:

[0010] S1, synchronously collecting UHF, AE, arc light and current four-way signals, and completing front-end analog and digital conditioning, forming a pulse sequence and amplitude statistics that can be used for PRPD analysis for the partial discharge channel, calculating the effective value and over-limit mark of the current, aligning the time stamps of each channel, and establishing a consistent time reference for subsequent associated partial discharge, arc light and overcurrent, wherein the current is a primary loop operating current;

[0011] S2, according to the partial discharge characteristic value and trend, classifying into normal, first-level warning and second-level alarm, respectively corresponding to prompt attention, strengthening maintenance suggestion and local sound and light reporting, the threshold adopts a double-threshold structure, and the sensitivity of continuous deterioration is combined with trend enhancement, when entering the second-level alarm state, the system marks high-risk insulation, and provides a prior condition for the sensitive switching of the protection logic;

[0012] S3, the trigger criterion adopts a configurable logic of arc light associated partial discharge and arc light associated overcurrent, realizes the consideration of anti-maloperation and anti-refusal, the insulation degradation type fault is triggered by the arc light associated partial discharge signal, the maloperation caused by pure light interference is suppressed, the non-insulation degradation type sudden short circuit takes the arc light and overcurrent as a backup, and it is ensured that the fault is not missed when the fusion criterion is met, and a trip command is immediately output to remove the fault;

[0013] S4. For the same type of switchgear, based on the collected partial discharge signal and current RMS value, establish a nonlinear correspondence between the time change rate of the partial discharge comprehensive index and the time change rate of the current RMS value, and form a baseline for this type of switchgear.

[0014] S5. During operation, both are calculated synchronously at the same time step and substituted into the baseline relationship to obtain the expected change. If the deviation between the actual change and the expected value continues to exceed the threshold, it is judged as an abnormal sign that is inconsistent with simple load fluctuations, and is used as an auxiliary criterion for alarm and protection triggering.

[0015] According to the above technical solution, the alarm classification in S2 is specifically as follows:

[0016] The device provides amplitude statistics for the UHF and AE channels of the partial discharge channel. With pulse statistics Threshold discrimination is performed in a sliding window. The amplitudes of AE and UHF are taken respectively. With pulse counting ,calculate , ,in , These are the normal amplitude threshold and the high amplitude threshold, respectively. , These represent the normal and high thresholds for pulse counting, and the comprehensive partial discharge index. , For the linear contribution of the pulse, The amplification factor is used to classify the system into three levels: normal, first-level warning, and second-level alarm. A value below the preset alarm threshold is marked as normal; a value exceeding the lower threshold is marked as... However, a Level 1 warning is issued when the development trend is stable; otherwise, a high threshold is exceeded. And when it shows a continuous increasing trend, that is The system triggers a level 2 alarm when the value increases within multiple consecutive sliding windows.

[0017] According to the above technical solution, the triggering criterion in S3 is specifically as follows:

[0018] S3-1. For insulation degradation type, arc-related partial discharge is used, making... This is the moment when the arc begins. For arc event indication, This indicates that it has been confirmed as an arc light. For the arc light pre-correlation time window, when and At that time, i.e., before the arc light Significant partial discharge was observed within a short period of time, indicating insulation degradation and triggering a trip.

[0019] S3-2, for non-insulation deterioration type, arc light correlation overcurrent is adopted, the sliding window length is determined according to the sampling rate and system power frequency , the discrete value of the current sampling sequence is , the window mean value is , wherein is the sample number corresponding to the current calculation time, the current effective value is , when and , the arc light appears and the current exceeds the overcurrent threshold in the correlation window, it is judged as non-insulation deterioration type and tripped, wherein is the overcurrent setting value, is the overcurrent correlation window.

[0020] According to the above technical scheme, in S4, the establishment process of the nonlinear correspondence relationship is: aligning the discrete sequence with the time axis, obtaining the continuous time function by means of reconfiguring interpolation, the time variation rate of the current effective value is , for the same type of switch cabinet, the and the have similarity, the paired sequence is extracted according to the unified statistical step Δ, , the fitting is in the form of order polynomial, , wherein is the regression coefficient, the corresponding relationship between the and the of the same type of switch cabinet is obtained by fitting the historical data, the sample input is converted into a polynomial feature matrix, and the size of the regression coefficient is obtained by using the least square method to solve the parameter vector, so as to determine the nonlinear correspondence relationship.

[0021] According to the above technical scheme, in S5, the deviation calculation method of the actual change and the expected value is: in a certain time , the actual change rate is calculated according to the calculation formula of in S2, the corresponding is calculated according to the actual measured time variation rate of the current effective value, then the expected change rate calculated by the nonlinear correspondence relationship of S4 is , when the residual error , it is judged that the threshold is exceeded, is the residual error threshold, if the continuous positive deviation occurs, the rise of the partial discharge comprehensive index is faster than the speed explained by the load, it is judged that one of the defect activation, surface creepage start and local discharge channel opening, if the continuous negative deviation occurs, when the load rises, the partial discharge comprehensive index does not rise correspondingly, it is judged that the energy transmission path is blocked, the sensing attenuation is abnormal, and the local discharge channel is temporarily passivated and reactivated.

[0022] According to the technical solution, in S5, when the residual error continuously exceeds the threshold, the arc light correlation partial discharge determination is sensitized, the correlation threshold is relaxed, and the arc light pre-correlation time window is widened The windows of the trigger and the post-trigger of the arc light, the partial discharge and the current key quantity are recorded synchronously to form an event segment, and the event, the level and the recommended maintenance conclusion are reported through a man-machine interface and a communication port.

[0023] Compared with the prior art, the beneficial effects achieved by the present application are: the present application fuses the partial discharge, the arc light and the overcurrent three criteria in depth, constructs an early warning + accurate protection for insulation deterioration type faults, and a reliable backup protection for non-insulation deterioration type sudden faults, realizes panoramic monitoring of two types of faults of insulation slow deterioration and sudden short circuit, avoids misoperation of single trigger through time sequence correlation and multi-source cross confirmation, upgrades the overcurrent from a single value threshold to a multi-dimensional electrical quantity alternative trigger, enables the arc light and the weak current but obvious abnormal quantity to act, and avoids the refusal to act caused by insufficient current. BRIEF DESCRIPTION OF DRAWINGS

[0024] The accompanying drawings are used to provide a further understanding of the present application, and constitute a part of the specification, and are used to explain the present application together with embodiments of the present application, and do not constitute a limitation on the present application. In the drawings:

[0025] Figure 1 is a schematic diagram of the overall module structure of the present application. DETAILED DESCRIPTION

[0026] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of 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 scope of protection of the present application.

[0027] Please refer to Figure 1 The present application provides a technical solution: a multi-source signal fusion high-voltage switch cabinet intelligent monitoring and fault adaptive protection system, comprising a multi-source sensing module, a state evaluation module and an adaptive protection module, the multi-source sensing module synchronously collects UHF, AE, arc light and primary circuit current, completes front-end conditioning and unified time reference, and serves as a basis for subsequent correlation and calculation, the state evaluation module completes grading based on double thresholds + trend, and establishes and calls the nonlinear relationship between the partial discharge and the overcurrent according to the same type baseline, online calculates the residual error and the persistence, and outputs the level, the high-risk flag and the auxiliary criterion, the adaptive protection module performs arc light correlation partial discharge and arc light overcurrent fusion trigger, meets the fusion criterion, trips, and sensitizes the correlation threshold and the pre-window when the residual error continuously exceeds the threshold.​

[0028] The multi-source perception module comprises a multi-source sensing unit and a fusion judgment module, the multi-source sensing unit is composed of a UHF sensor, an ultrasonic sensor, an arc sensor and a current sampling module, and is used for collecting UHF, AE, arc light and current four-way signals, the fusion judgment module performs PRPD spectrum analysis on the partial discharge signal, and extracts the characteristics of the discharge amount and the discharge frequency; and the effective value of the current signal is calculated;

[0029] The state evaluation module comprises a double-threshold trend enhancement grading module, a nonlinear baseline modeling module and a residual judgment module, the double-threshold trend enhancement grading module is used for outputting normal, first-level and second-level grades by superimposing the trend and persistence rules of low and high thresholds, focusing on sensitive identification of continuous degradation, the nonlinear baseline modeling module establishes and calls the nonlinear mapping of partial discharge and overcurrent for each model, and provides expected changes of load interpretability, and the residual judgment module calculates whether the residual judgment of actual and expected changes is continuously deviated;

[0030] The adaptive protection module comprises an association threshold adjustment module, a trip control module and an event packaging and reporting module, the association threshold adjustment module lowers the partial discharge association threshold according to the coefficient when nonlinear inconsistency occurs, the event packaging and reporting module uploads each item of data as structured evidence together with the grade and action result, and the trip control module is used for tripping when a fault occurs;

[0031] The working method of the system is as follows:

[0032] S1, synchronously collecting UHF, AE, arc light and current four-way signals, and completing front-end analog and digital conditioning, forming a pulse sequence and amplitude statistics that can be used for PRPD analysis for the partial discharge channel, calculating the effective value and over-limit mark of the current, aligning the time stamps of each channel, and establishing a consistent time reference for subsequent associated partial discharge, arc light and overcurrent, wherein the current is the primary loop operating current;

[0033] S2, according to the partial discharge characteristic value and the trend, classifying as normal, first-level warning and second-level alarm, respectively corresponding to prompt attention, strengthening maintenance suggestion and local sound and light reporting, the threshold adopts a double-threshold structure, and the sensitivity to continuous deterioration is combined with trend enhancement, when entering the second-level alarm state, the system marks high-risk insulation, providing a prior condition for the sensitive switching of the protection logic;

[0034] S3, the trigger criterion adopts a configurable logic of arc light associated partial discharge and arc light associated overcurrent, realizes the consideration of anti-malfunction and anti-refusal, the insulation degradation type fault is triggered by arc light associated partial discharge signal, the malfunction caused by pure light interference is suppressed, the non-insulation degradation type sudden short circuit takes arc light + overcurrent as backup, and it is ensured that the fault is not missed when the fusion criterion is met, and a trip command is immediately output to remove the fault;

[0035] S4, for the same type of switch cabinet, according to the collected partial discharge signal and current effective value, the nonlinear correspondence between the time variation rate of the partial discharge comprehensive index and the time variation rate of the current effective value is established, and the baseline of the switch cabinet of this type is formed;

[0036] S5, during operation, both are calculated synchronously according to the same time step and substituted into the baseline relationship to obtain the expected change. If the deviation between the actual change and the expected value continues to exceed the threshold, it is determined that it is an abnormal sign inconsistent with pure load fluctuation, which is used as an auxiliary criterion for alarm and protection triggering;

[0037] In S2, the alarm grading is specifically:

[0038] The device statistically analyzes the amplitude of the partial discharge channel UHF and AE and pulse statistics In the sliding window , the amplitude and pulse count of AE and UHF are taken respectively , and the characteristic value is calculated , , and , are the amplitude normal threshold and high threshold respectively, and , is the linear contribution of the pulse, and is the synergistic amplification coefficient, and it is divided into three grades of normal, first warning and second alarm according to the characteristic value: when the characteristic value is lower than the preset alarm threshold, it is marked as normal; when it exceeds the low threshold , it enters the first warning when the development trend is stable; when it exceeds the high threshold and shows a sustained increasing trend, i.e. it enters the second alarm when it grows in a plurality of consecutive sliding windows;

[0039] The grading criterion is coupled with the three elements of low threshold / high threshold + time trend + persistence, and the fusion index S(t) covers amplitude and pulse activity at the same time, so that accidental spikes and sustained degradation are clearly distinguished mathematically. This method of jointly constraining amplitude threshold, growth slope and persistence in the same criterion system can more stably identify early degradation than the existing threshold that only looks at amplitude or frequency.

[0040] In S3, the trigger criterion is specifically:

[0041] S3-1, for insulation degradation type, adopt arc light associated partial discharge, let be the arc light starting time, be the arc light event indicator, representing confirmation of arc light, For arc light pre-association time window, when and , that is, arc light pre There is significant partial discharge in the time, and it is judged as insulation deterioration type and tripped;

[0042] S3-2, for non-insulation deterioration type, arc light association overcurrent is used, the sliding window length is determined according to the sampling rate and system power frequency , the discrete value of the current sampling sequence is , the window mean value is , wherein is the sample number corresponding to the current calculation time, and the current effective value is , when and , arc light appears and current exceeds the overcurrent threshold in the association window, it is judged as non-insulation deterioration type and tripped, wherein is the overcurrent setting value, is the overcurrent association window;

[0043] The pre-association window Tpre is introduced with arc light as the time anchor point, which requires that there is a verifiable partial discharge precursor in the short window before the arc light, forming a causal constraint of arc light associated partial discharge, and at the same time, the arc light overcurrent is reserved in parallel as a backup for non-insulation type fault; The structure of this causal association + parallel backup not only inhibits pure light interference misoperation, but also avoids high impedance fault rejection, which is essentially different from the traditional parallel double criterion of only using arc light + overcurrent.

[0044] In S4, the establishment process of the nonlinear correspondence is: align the discrete sequence with the time axis, obtain the continuous time function through the interpolation of reconstruction, and the time variation rate of the current effective value is For the same type of switch cabinet, the and have similarity, and the paired sequence is extracted according to the unified statistical step Δ, and the fitting is in the form of order polynomial, , wherein is the regression coefficient, and the corresponding relationship between the and of the same type of switch cabinet is obtained by fitting the historical data, the sample input is converted into a polynomial feature matrix, and the size of the regression coefficient is obtained by using the least square method to solve the parameter vector, so as to determine the nonlinear correspondence;

[0045] At the same time of triggering action, the arc light, partial discharge, current and other multi-channel are synchronized and recorded in the millisecond window before and after the trigger point based on the uniform time base, and the derived quantities such as ∇S / ∇I, expected ∇S and residual are additionally packaged as structured evidence for uploading, so that the protection action and traceable diagnosis are integrated; Unlike the existing method of only storing original waveform or only reporting status code, this design of fixing the key intermediate quantities in the criterion chain significantly improves the post-explanation and operation and maintenance decision efficiency.

[0046] In S5, the deviation calculation method of actual change and expected value is: at a certain time In S2, the actual change rate is calculated according to the formula According to the actual measured current effective value time change rate, the corresponding After that, the expected change rate calculated by the nonlinear correspondence of S4 is When the residual is , it is determined that the threshold is exceeded, is the residual threshold. If there is a sustained positive deviation, the partial discharge comprehensive index rises faster than the speed that can be explained by the load, and it is determined that one of the defect activation, surface creepage starting and partial discharge channel opening occurs. If there is a sustained negative deviation, when the load rises, the partial discharge comprehensive index does not rise accordingly, and it is determined that the energy transmission path is blocked, the sensing attenuation is abnormal, and the partial discharge channel is temporarily passivated and reactivated.

[0047] A nonlinear baseline of ∇S-∇I is established for the same type, and the difference between the expected change obtained by online prediction and the actual change constitutes the residual, and the double thresholds of out-of-limit and persistence are used as auxiliary criteria for inconsistency with the load. Compared with the static threshold or linear correlation test commonly used in the industry, this method models the load-explainable change first and then separates it, and the remaining deviation enters the alarm link, which reduces false positives and exposes abnormal evolution in advance.

[0048] In S5, when the residual exceeds the threshold for a long time, the sensitivity of arc light associated partial discharge determination is increased, the correlation threshold is relaxed and the arc light pre-correlation time window is widened , the window data of arc light, partial discharge and current key quantities before and after triggering are recorded synchronously to form an event segment, and the event, level and recommended maintenance conclusion are reported through the human-machine interface and communication port.

[0049] ​It is to be noted that, in the present text, relational terms such as first and second and the like can be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises", "comprising", or any other variations thereof, are intended to cover a non-exclusive inclusion such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but can include other elements not expressly listed or inherent to such process, method, article, or apparatus.

[0050] Finally, it should be noted that the above-mentioned only constitutes the preferred embodiments of the present application and is not intended to limit the present application. Although the present application has been described in detail with reference to the foregoing embodiments, it will be apparent to those skilled in the art that modifications, equivalent replacements, improvements and the like of the technical solutions described in the foregoing embodiments can still be made. Any modifications, equivalent replacements, improvements and the like made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A high-voltage switchgear intelligent monitoring and fault adaptive protection system with multi-source signal fusion, characterized in that: It includes a multi-source sensing module, a state assessment module, and an adaptive protection module. The multi-source sensing module synchronously collects UHF, AE, arc light, and primary circuit current to complete front-end conditioning and unify the time reference, which serves as the basis for subsequent correlation and calculation. The state assessment module completes the classification based on dual thresholds and trends, and establishes and calls the nonlinear relationship between partial discharge and overcurrent according to the same model baseline, calculates residuals and persistence online, and outputs the level, high-risk indicator, and auxiliary criteria. The adaptive protection module performs arc light correlation partial discharge and arc light overcurrent fusion triggering, trips when the fusion criteria are met, and enhances the sensitivity of the correlation threshold and pre-window when the residuals continue to exceed the threshold. The system works as follows: S1. Simultaneously acquire four signals: UHF, AE, arc, and current, and complete front-end analog and digital conditioning. Generate pulse sequences and amplitude statistics for the partial discharge channel that can be used for PRPD analysis. Calculate the effective value and over-limit flag for the current. Align the timestamps of each channel and establish a consistent time reference for subsequent correlation of partial discharge, arc, and overcurrent. The current is the operating current of the primary circuit. S2. Based on the partial discharge characteristic value and trend, the system is classified into normal, first-level early warning and second-level alarm levels, respectively, and corresponding prompts for attention, suggestions for enhanced maintenance and local audible and visual reporting are provided. The threshold adopts a dual-threshold structure and combines trend to enhance the sensitivity to continuous deterioration. When the second-level alarm state is entered, the system marks the insulation as high risk, providing a priori conditions for the sensitive switching of the protection logic. S3. The triggering criteria adopt configurable logic of arc-related partial discharge and arc-related overcurrent to achieve both prevention of false tripping and prevention of failure to trip. The insulation deterioration type fault is triggered by the arc-related partial discharge signal to suppress false tripping caused by pure optical interference. The non-insulation deterioration type sudden short circuit is backed by arc-related + overcurrent to ensure that the fault is cleared without missing detection. When the fusion criteria are met, a trip command is immediately output to clear the fault. S4. For the same type of switchgear, based on the collected partial discharge signal and current RMS value, establish a nonlinear correspondence between the time change rate of the partial discharge comprehensive index and the time change rate of the current RMS value, and form a baseline for this type of switchgear. S5. During operation, both are calculated synchronously at the same time step and substituted into the baseline relationship to obtain the expected change. If the deviation between the actual change and the expected value continues to exceed the threshold, it is judged as an abnormal sign that is inconsistent with simple load fluctuations, and is used as an auxiliary criterion for alarm and protection triggering.

2. The intelligent monitoring and fault adaptive protection system for high-voltage switchgear based on multi-source signal fusion as described in claim 1, characterized in that: The multi-source sensing module includes a multi-source sensing unit and a fusion judgment module. The multi-source sensing unit consists of a UHF sensor, an ultrasonic sensor, an arc light sensor, and a current sampling module, which is used to collect four signals: UHF, AE, arc light, and current. The fusion judgment module performs PRPD spectrum analysis on the partial discharge signal to extract the characteristics of discharge quantity and discharge frequency. Calculate the effective value of the current signal; The state assessment module includes a dual-threshold trend enhancement grading module, a nonlinear baseline modeling module, and a residual determination module. The dual-threshold trend enhancement grading module is used to output normal, first-level, and second-level grades with low and high threshold superimposed trends and persistence rules, focusing on sensitive identification of continuous degradation. The nonlinear baseline modeling module establishes and calls nonlinear mappings of partial discharge and overcurrent for each model, providing expected changes in load interpretability. The residual determination module calculates whether the residual determination of actual and expected changes continues to deviate. The adaptive protection module includes an association threshold adjustment module, a trip control module, and an event packaging and reporting module. The association threshold adjustment module lowers the partial discharge association threshold by a coefficient when nonlinear inconsistency occurs. The event packaging and reporting module sends various data as structured evidence along with the level and action results. The trip control module is used to trip when a fault occurs.

3. The intelligent monitoring and fault adaptive protection system for high-voltage switchgear based on multi-source signal fusion according to claim 2, characterized in that: In S2, the alarm classification is specifically as follows: The device provides amplitude statistics for the UHF and AE channels of the partial discharge channel. With pulse statistics Threshold discrimination is performed in a sliding window. The amplitudes of AE and UHF are taken respectively. With pulse counting ,calculate , ,in , These are the normal amplitude threshold and the high amplitude threshold, respectively. , These represent the normal and high thresholds for pulse counting, and the comprehensive partial discharge index. , For the linear contribution of the pulse, The amplification factor is used to classify the system into three levels: normal, first-level warning, and second-level alarm. A value below the preset alarm threshold is marked as normal; a value exceeding the lower threshold is marked as... However, a Level 1 warning is issued when the development trend is stable; otherwise, a high threshold is exceeded. And when it shows a continuous increasing trend, that is The system triggers a level 2 alarm when the value increases within multiple consecutive sliding windows.

4. The intelligent monitoring and fault adaptive protection system for high-voltage switchgear based on multi-source signal fusion according to claim 3, characterized in that: In S3, the triggering criteria are specifically as follows: S3-1. For insulation degradation type, arc-related partial discharge is used, making... This is the moment when the arc begins. For arc event indication, This indicates that it has been confirmed as an arc light. For the arc light pre-correlation time window, when and At that time, i.e., before the arc light Significant partial discharge was observed within a short period of time, indicating insulation degradation and triggering a trip. S3-2. For non-insulation deterioration type, arc-correlated overcurrent is used, and the sliding window length is determined based on the sampling rate and system power frequency. Let the discrete values ​​of the current sampling sequence be... Mean within the window ,in The sample number corresponding to the current calculation time, and the effective value of the current. ,when and When an arc occurs and the current exceeds the overcurrent threshold within the associated window, it is judged as a non-insulation degradation type and trips. This is the overcurrent setting value. For overcurrent related windows.

5. The intelligent monitoring and fault adaptive protection system for high-voltage switchgear based on multi-source signal fusion according to claim 4, characterized in that: In S4, the process of establishing the nonlinear correspondence is as follows: The discrete sequence... Aligned with the time axis, the continuous-time function is obtained by reconstructing the interpolation. The time change rate of the effective value of the current For switchgear of the same model, its and Based on similarity, paired sequences are extracted using a uniform statistical step size Δ. Let the fit be polynomial form of degree. ,in The regression coefficients are obtained by fitting historical data to the same model of switchgear. and The correspondence is determined by converting the sample input into a multinomial feature matrix, using the least squares method to solve the parameter vector to obtain the magnitude of the regression coefficients, thereby determining the nonlinear correspondence.

6. The intelligent monitoring and fault adaptive protection system for high-voltage switchgear based on multi-source signal fusion according to claim 5, characterized in that: In S5, the method for calculating the deviation between the actual change and the expected value is as follows: at a certain moment... In, according to S2 The calculation formula calculates the actual rate of change. The corresponding value is calculated based on the time-varying rate of change of the actual measured effective current value. Then, the expected rate of change is calculated using the nonlinear correspondence of S4. , when the residual When the threshold is exceeded, The residual threshold is used to determine the following: If a continuous positive bias occurs, the increase in the comprehensive partial discharge index is faster than the rate at which the load can explain it, which is determined to be one of the following: defect activation, surface creepage initiation, or partial discharge channel opening. If a continuous negative bias occurs, the comprehensive partial discharge index does not increase accordingly when the load increases, which is determined to be nonlinear behavior such as blocked energy transmission path, abnormal sensing attenuation, or temporary passivation and reactivation of the partial discharge channel.

7. The intelligent monitoring and fault adaptive protection system for high-voltage switchgear based on multi-source signal fusion according to claim 6, characterized in that: In step S5, when the residual continuously exceeds the threshold, the arc-related partial discharge determination is enhanced to relax the correlation threshold. And widen the arc light pre-correlation time window It synchronously records the window data before and after the triggering of key quantities such as arcing, partial discharge, and current, forming event segments, and reports the event, level, and suggested maintenance conclusions through the human-machine interface and communication port.

Images