A method and system for high voltage circuit breaker contact erosion assessment

Abstract

The application relates to a high-voltage circuit breaker contact ablation evaluation method and system, and belongs to the technical field of electric power engineering. The method comprises the following steps: collecting original multi-source operation data by using sensors arranged on a circuit breaker, and obtaining filtered multi-source operation data through adaptive Kalman filtering algorithm preprocessing; based on the multi-source operation data, contact ablation characteristic parameters are calculated and a characteristic vector is constructed by combining characteristic parameter calculation rules; the characteristic vector is input into a quantitative ablation evaluation model, the parameters of a support vector regression model are optimized by using a quantum particle swarm algorithm, a nonlinear regression mapping relationship between the characteristic parameters and ablation loss is established, and real-time ablation evaluation results are output; according to a preset ablation degree threshold, corresponding ablation state grades are divided, and health state evaluation information and early warning signals of the high-voltage circuit breaker are output. The application overcomes strong electromagnetic interference and effectively improves the precision of circuit breaker contact ablation evaluation.

Description

Technical Field

[0001] This invention relates to a method and system for assessing the erosion of contacts in high-voltage circuit breakers, belonging to the field of power engineering technology. Background Technology

[0002] High-voltage circuit breakers play a crucial role in the core protection and control of power transmission and distribution systems. Their contacts, as key conductive and arc-extinguishing components, operate in extremely harsh environments. During frequent opening and closing operations, they must withstand not only the burning of electric arcs but also the combined effects of current heat and mechanical friction. This makes the contacts highly susceptible to various defects such as wear, erosion, and deformation. The degree of contact erosion plays a decisive role in the circuit breaker's conductivity, arc-extinguishing capability, and overall service life. Severe erosion can lead to a series of faults, including excessive contact resistance, overheating and burn-out, arc-extinguishing failure, and switch malfunction, ultimately resulting in serious safety accidents such as power outages and equipment damage, posing a significant threat to the stable operation of the power system.

[0003] On the one hand, traditional contact condition detection methods mainly rely on manual inspections after periodic power outages and disassembly. This method is not only time-consuming and inefficient, but also fails to capture early-stage minor ablation defects in the contacts in a timely and real-time manner. Furthermore, power outages inevitably disrupt the continuity of power supply, causing inconvenience to users and potentially damaging equipment or production processes that require extremely stable power supply. On the other hand, most existing online assessment methods rely on single methods such as arc energy accumulation or static loop resistance detection. These methods are based on overly simplistic parameters and are easily affected by factors such as grid load fluctuations, environmental interference, and mechanical errors in practical applications. This results in an inability to accurately distinguish between minor, moderate, and severe ablation states of the contacts, leading to low assessment accuracy, poor robustness, and difficulty in adapting to the complex and variable operating conditions of high-voltage circuit breakers. Moreover, current technology cannot achieve quantitative assessment of the degree of contact ablation or accurate prediction of remaining lifespan, leaving maintenance personnel without precise data for developing maintenance plans. This can easily lead to over-maintenance or delayed maintenance, hindering the improvement of intelligent operation and maintenance levels for high-voltage power equipment.

[0004] Therefore, there is an urgent need for a high-voltage circuit breaker contact condition assessment method and system that can detect contact status in real time and efficiently, is not affected by various interference factors, accurately distinguish different degrees of ablation, and realize quantitative assessment of ablation degree and prediction of remaining life, so as to improve the intelligent operation and maintenance level of high-voltage power equipment and ensure the safe and stable operation of power transmission and distribution systems. Summary of the Invention

[0005] To address the problems existing in the prior art, this invention proposes a method and system for evaluating the erosion of high-voltage circuit breaker contacts.

[0006] The technical solution of the present invention is as follows: On the one hand, this invention proposes a method for evaluating the erosion of contacts in high-voltage circuit breakers, comprising the following steps: Collect raw multi-source operational data during the opening and closing operations of high-voltage circuit breakers; The raw multi-source operational data is preprocessed to obtain standard multi-source operational data; Based on standard multi-source operating data and combined with the preset calculation rules for contact erosion characteristic parameters, the contact erosion characteristic parameters of high-voltage circuit breakers are calculated, and a contact erosion characteristic vector is constructed. The contact ablation feature vector is input into a pre-trained quantitative ablation assessment model. The support vector regression model is optimized using the quantum particle swarm optimization algorithm. A nonlinear regression mapping between the feature parameters in the contact ablation feature vector and the contact ablation loss is established, and the real-time ablation assessment results of the high-voltage circuit breaker contacts are output. Based on the preset ablation degree threshold, the real-time ablation assessment results are divided into multiple ablation state levels, and the corresponding high-voltage circuit breaker equipment health report is output. When the ablation state level exceeds the preset ablation limit level, an early warning signal is issued.

[0007] Preferably, the method utilizes multiple sensors to collect raw multi-source operational data during the opening and closing operation of the high-voltage circuit breaker, including a dynamic resistance sensor, an arc monitoring sensor, and a mechanical travel sensor, wherein: The dynamic resistance sensor is used to collect dynamic voltage signals between moving and stationary contacts and current signals through the contacts during the opening and closing operations of a high-voltage circuit breaker, and to calculate a dynamic resistance curve reflecting the deterioration state of the contact surface by using the ratio of the two. The arc monitoring sensor is used to collect the arc light signal generated at the moment of contact breakage, and simultaneously collect the arc voltage signal and arc current signal during the arcing process; The mechanical stroke sensor is used to monitor the displacement curve of the moving contact in real time during the opening and closing process, and calculates the opening and closing speed, movement stroke and contact overtravel of the moving contact based on the displacement curve.

[0008] Preferably, the method utilizes an adaptive Kalman filter algorithm to preprocess the original multi-source running data, and the specific steps include: Initialize the state vector and covariance matrix based on historical multi-source operational data; At each sampling time, a state prediction is performed based on the optimal state estimate of the previous time to obtain the predicted state vector and the prediction covariance matrix at the current time. Based on the measurement residual at the current moment, the process noise covariance matrix and measurement noise covariance matrix of the Kalman filter are adaptively adjusted in real time. The Kalman gain is calculated using the adjusted covariance matrix, and the state is updated by combining the current measurement values ​​collected by multiple sensors. The output is standard multi-source operating data after filtering out high-frequency noise and electromagnetic interference.

[0009] Preferably, the contact ablation characteristic parameters include the average steady-state contact resistance, arc duration, single-break arc energy, contact travel deviation, and resistance fluctuation amplitude, wherein: The mean steady-state contact resistance is the arithmetic mean of the resistance values ​​in the steady segment of the dynamic resistance curve after the moving and stationary contacts have made full contact and stabilized. The duration of the electric arc is the time difference between when the electric arc monitoring sensor detects the start of the electric arc and when the electric arc is completely extinguished. The single-break arc energy is the integral of the product of arc voltage and arc current over time during the arc duration. The contact travel deviation is the absolute difference between the actual total travel of the moving contact and the standard design travel. The resistance fluctuation amplitude is the difference between the maximum and minimum values ​​of the dynamic resistance curve in the transition section.

[0010] Preferably, the quantitative ablation assessment model is trained through the following steps: Obtain historical characteristic parameters and actual physical erosion loss of contacts corresponding to multiple sets of historical high-voltage circuit breaker opening and closing operations, and construct a training sample set; When optimizing the support vector regression algorithm using quantum particle swarm regression, the penalty parameters and kernel parameters of the support vector regression model are used as search variables to initialize the position and velocity of the particle swarm within the optimization space. In each iteration, the current particle parameters are substituted into the support vector regression model, and the minimum cross-validation mean square error of the training sample set is used as the fitness function to calculate the current fitness value of each particle and update the global optimal position. When the maximum number of iterations is reached or the preset convergence accuracy is met, the optimization stops, the optimal penalty parameter and kernel parameter are output, and the support vector regression model is trained using the optimal penalty parameter and kernel parameter to construct the quantitative ablation evaluation model.

[0011] Preferably, the method divides the real-time ablation assessment results into multiple ablation state levels, specifically as follows: Pre-set thresholds for mild ablation, moderate ablation, and severe ablation. When real-time ablation assessment results When the light ablation threshold is reached, the high-voltage circuit breaker contacts are considered to be in a normal state. When the mild ablation threshold Real-time ablation assessment results When the moderate ablation threshold is reached, the high-voltage circuit breaker contacts are determined to be in a state of slight ablation. When the moderate ablation threshold Real-time ablation assessment results When the severe ablation threshold is reached, the high-voltage circuit breaker contacts are determined to be in a moderate ablation state. When the severe ablation threshold When the real-time ablation assessment results are obtained, it is determined that the high-voltage circuit breaker contacts are in a state of severe ablation and the preset ablation limit level is activated, triggering an early warning signal.

[0012] Preferably, the method outputs a corresponding high-voltage circuit breaker equipment health report, specifically including the following steps: The real-time ablation assessment results, ablation status level, and ablation characteristic parameters of high-voltage circuit breaker contacts are correlated according to the acquisition time to construct a time-series trajectory of health status characteristics. Based on the time-series trajectory of health status characteristics, a health assessment chart containing the evolution trend of contact erosion is generated, and the health assessment chart is output as the equipment health report of the high-voltage circuit breaker to the preset operation and maintenance platform.

[0013] On the other hand, the present invention also proposes a high-voltage circuit breaker contact erosion assessment system, comprising the following modules: The data acquisition module is used to collect raw multi-source operating data during the opening and closing operation of the high-voltage circuit breaker; The data preprocessing module is used to preprocess the raw multi-source operational data to obtain standard multi-source operational data; The feature construction module is used to calculate the contact ablation feature parameters of high-voltage circuit breakers based on standard multi-source operating data and in combination with preset contact ablation feature parameter calculation rules, and to construct the contact ablation feature vector. The ablation assessment module is used to input the contact ablation feature vector into the pre-trained quantitative ablation assessment model, optimize the support vector regression model using the quantum particle swarm optimization algorithm, establish a nonlinear regression mapping between the feature parameters in the contact ablation feature vector and the contact ablation loss, and output the real-time ablation assessment results of the high-voltage circuit breaker contacts. The status classification and early warning module is used to divide the real-time ablation assessment results into multiple ablation status levels according to the preset ablation degree threshold, output the corresponding high-voltage circuit breaker equipment health report, and issue an early warning signal when the ablation status level exceeds the preset ablation limit level.

[0014] In another aspect, the present invention also proposes an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the method as described in any embodiment of the present invention.

[0015] In another aspect, the present invention also proposes a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method described in any embodiment of the present invention.

[0016] The present invention has the following beneficial effects; 1. This invention proposes a method and system for evaluating the contact erosion of high-voltage circuit breakers. By deploying dynamic resistance sensors, arc monitoring sensors, and mechanical stroke sensors, it achieves collaborative acquisition of multi-source operating data. Furthermore, by utilizing an adaptive Kalman filter algorithm, it adjusts the noise covariance matrix in real time based on the measurement residuals at the current moment, effectively eliminating strong electromagnetic interference and high-frequency pulse noise accompanying the opening and closing operations of high-voltage circuit breakers. This significantly improves the signal-to-noise ratio and phase integrity of the original multi-source operating data, providing a high-fidelity data source for accurate identification of contact status.

[0017] 2. This invention proposes a method and system for evaluating the erosion of high-voltage circuit breaker contacts. By extracting multi-dimensional feature parameters, including the mean steady-state contact resistance, arc duration, single-break arc energy, contact travel deviation, and resistance fluctuation amplitude, and constructing an erosion feature vector, it not only integrates the electrical resistance characteristics and thermal ablation energy characteristics that reflect the degree of contact degradation between moving and stationary contacts, but also introduces features at the motion mechanism level, such as mechanical travel deviation. This overcomes the shortcomings of traditional evaluation methods that rely on a single feature, resulting in incomplete characterization, and greatly enhances the ability to characterize the complex wear mechanism of contacts through multi-physics field collaboration.

[0018] 3. This invention proposes a method and system for evaluating the erosion of high-voltage circuit breaker contacts. By utilizing the quantum particle swarm optimization algorithm to adaptively iteratively optimize the penalty parameters and kernel parameters of the support vector regression model, a strong nonlinear mapping relationship is established between the multidimensional feature vector and the actual physical erosion loss of the contacts. This greatly improves the generalization performance and evaluation accuracy of the model under small sample or unbalanced operating data. At the same time, by combining the preset erosion threshold for level classification and constructing a time-series health status feature trajectory, the erosion degradation trend of the circuit breaker contacts can be intuitively displayed and accurate over-limit warnings can be achieved, significantly improving the efficiency of predictive maintenance and refined operation and maintenance of circuit breakers. Attached Figure Description

[0019] Figure 1 This is a flowchart of the high-voltage circuit breaker contact erosion assessment method proposed in this invention. Detailed Implementation

[0020] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0021] It should be understood that the step numbers used in the text are for ease of description only and are not intended to limit the order in which the steps are performed.

[0022] It should be understood that the terminology used in this specification is for the purpose of describing particular embodiments only and is not intended to limit the invention. As used in this specification and the appended claims, the singular forms “a,” “an,” and “the” are intended to include the plural forms unless the context clearly indicates otherwise.

[0023] The terms “comprising” and “including” indicate the presence of the described feature, whole, step, operation, element and / or component, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or collections thereof.

[0024] The term “and / or” refers to any combination of one or more of the associated listed items, as well as all possible combinations, and includes these combinations.

[0025] Example 1: See Figure 1 This embodiment proposes a method for evaluating the erosion of high-voltage circuit breaker contacts, including the following steps: S100: Utilizes multiple sensors deployed on the high-voltage circuit breaker to collect raw multi-source operating data during the circuit breaker's opening and closing operations; The various sensors include dynamic resistance sensors, arc monitoring sensors, and mechanical stroke sensors, wherein: The dynamic resistance sensor is used to collect dynamic voltage signals between moving and stationary contacts and current signals through the contacts during the opening and closing operations of a high-voltage circuit breaker, and to calculate a dynamic resistance curve reflecting the deterioration state of the contact surface by using the ratio of the two. The arc monitoring sensor is used to collect the arc light signal generated at the moment of contact breakage, and simultaneously collect the arc voltage signal and arc current signal during the arcing process; The mechanical stroke sensor is used to monitor the displacement curve of the moving contact in real time during the opening and closing process, and calculates the opening and closing speed, movement stroke and contact overtravel of the moving contact based on the displacement curve.

[0026] S200. The raw multi-source running data is input into the adaptive Kalman filter algorithm for data preprocessing to obtain standard multi-source running data. Specifically: Initialize the state vector and covariance matrix based on historical multi-source operational data; At each sampling time, a state prediction is performed based on the optimal state estimate from the previous time step, resulting in the predicted state vector and prediction covariance matrix for the current time step, expressed by the formula: ; ; In the formula, Indicates the time index. express The predicted state vector at time t. Represents the state transition matrix. express The optimal state estimate at time t. express The prediction covariance matrix at time 1, express The error covariance matrix at time t. express The process noise covariance matrix at time step 1. Indicates the transpose operation; Furthermore, the measurement residual at the current moment is calculated, expressed by the formula: ; In the formula, express Measurement residuals at time, Indicates the data collected by the sensor The measured value at time, Represents the measurement matrix; Based on the measurement residual at the current moment, the process noise covariance matrix and measurement noise covariance matrix of the Kalman filter are adaptively adjusted in real time. The Kalman gain is calculated using the adjusted covariance matrix, and the state is updated by combining the current measurements from multiple sensors. The output is standard multi-source operating data after filtering out high-frequency noise and electromagnetic interference. The Kalman gain is expressed by the formula: ; In the formula, Indicates Kalman gain, This represents the adaptively adjusted measurement noise covariance matrix; Furthermore, the state is updated based on the measured values, expressed by the formula: ; ; In the formula, express The optimal update estimate at time t. express The error covariance matrix at time t. Represents the identity matrix; The updated optimal state estimate constitutes the high signal-to-noise ratio standard multi-source operating data after filtering out interference.

[0027] S300. Based on standard multi-source operating data and combined with preset calculation rules for contact erosion characteristic parameters, calculate the contact erosion characteristic parameters of the high-voltage circuit breaker and construct a contact erosion characteristic vector. The high-voltage circuit breaker contact erosion characteristic parameters include the average steady-state contact resistance, arc duration, single-break arc energy, contact travel deviation, and resistance fluctuation amplitude, wherein: The mean steady-state contact resistance is the arithmetic mean of the resistance values ​​in the steady segment of the dynamic resistance curve after the moving and stationary contacts have fully contacted and stabilized, expressed by the formula: ; In the formula, Indicates the sampling point index. This represents the average steady-state contact resistance. This represents the total number of sampling points in the stationary phase. Indicates the first level of the steady segment The resistance value at each sampling point; The duration of the electric arc is the time difference between when the arc monitoring sensor detects the start of the arc and when the arc is completely extinguished, expressed by the formula: ; In the formula, Indicates the duration of the electric arc. Indicates the moment when the electric arc is completely extinguished. Indicates the starting moment of the electric arc; The single-time arc breaking energy is the integral of the product of arc voltage and arc current over time during the arc's duration, expressed by the formula: ; In the formula, This represents the energy of a single arc interruption. This represents the arc voltage signal that varies over time. This represents the arc current signal that varies over time. The contact travel deviation is the absolute difference between the actual total travel of the moving contact and the standard design travel, expressed by the formula: ; In the formula, This indicates the contact travel deviation. This indicates the total actual travel distance of the moving contact. Indicates the standard design stroke; The resistance fluctuation amplitude is the difference between the maximum and minimum values ​​of the dynamic resistance curve in the transition section, expressed by the formula: ; In the formula, Indicates the resistance fluctuation amplitude. This indicates the maximum value of the dynamic resistance of the transition section. This represents the minimum dynamic resistance of the transition section; By combining the calculated steady-state average contact resistance, arc duration, single arc energy, contact travel deviation, and resistance fluctuation amplitude, a contact ablation characteristic vector is constructed, expressed by the formula: ; In the formula, This represents the contact ablation feature vector.

[0028] S400. Input the contact ablation feature vector into the pre-trained quantitative ablation assessment model, use the quantum particle swarm optimization support vector regression algorithm QPSO-SVR to establish a nonlinear regression mapping between the feature parameters in the contact ablation feature vector and the contact ablation loss, and output the real-time ablation assessment results of the high-voltage circuit breaker contacts. The nonlinear regression prediction of the support vector regression model is expressed by the formula: ; ; In the formula, This indicates the real-time ablation assessment results. Indicates the index of historical training samples. This represents the total number of historical training samples. Indicates the relationship with the first The first Lagrange multiplier corresponding to each historical training sample Indicates the first The second Lagrange multiplier corresponding to each historical training sample Represents the kernel function. Indicates the first Feature vectors of historical training samples Indicates the bias term. Represents kernel parameters, This represents an exponential function with the natural constant as its base. This represents the second-order norm operator.

[0029] Furthermore, to improve evaluation accuracy, the penalty and kernel parameters of the support vector regression model are optimized using the quantum particle swarm optimization algorithm. The specific training steps are as follows: A training sample set was constructed by acquiring historical characteristic parameters and actual physical erosion loss of contacts corresponding to multiple sets of historical high-voltage circuit breaker opening and closing operations. Initialize the position and velocity of the particle swarm within the optimization space. In each iteration, substitute the current particle parameters into the support vector regression model. Use the minimum cross-validation mean square error of the training sample set as the fitness function to calculate the current fitness value of each particle and update the global optimal position. The fitness function is expressed by the formula: ; In the formula, Represents the fitness value. This represents the total number of samples in the training sample set. Indicates the sample index. Indicates the first The actual physical ablation loss of the contacts in each sample. Indicates the first Predicted physical ablation loss for each sample; In the quantum particle swarm optimization process, the position update of each particle is expressed by the formula: ; ; ; In the formula, This represents the average historical best position vector for the entire particle swarm. This represents the total number of particles in the particle swarm. Indicates particle index, Indicates the first The individual historical optimal position vector of each particle. This represents the dimensional index of the feature space being optimized. Indicates the first The particle in the first Local attractor positions in 3D space Representing an interval Uniform random weighting coefficients on This indicates that the entire particle swarm is at the th... The globally optimal position in dimensional space. Indicates the first The particle in the first Current position in 3D space Indicates the first The individual historical best position of each particle is in the _th Dimension value, Indicates the coefficient of contraction and expansion. This indicates the average historical best position at the 1st rank. Dimension value, Representing an interval Uniformly random numbers; When the maximum number of iterations is reached or the preset convergence accuracy is met, the optimization is stopped, the optimal penalty parameters and kernel parameters are output, and the quantitative ablation evaluation model is constructed. During online evaluation, the contact erosion feature vector is input into the quantitative erosion evaluation model to obtain the real-time erosion evaluation results of the circuit breaker contacts.

[0030] S500. Based on a preset ablation degree threshold, the real-time ablation assessment results are divided into multiple ablation state levels, specifically: Pre-set thresholds for mild ablation, moderate ablation, and severe ablation. When real-time ablation assessment results When the light ablation threshold is reached, the high-voltage circuit breaker contacts are considered to be in a normal state. When the mild ablation threshold Real-time ablation assessment results When the moderate ablation threshold is reached, the high-voltage circuit breaker contacts are determined to be in a state of slight ablation. When the moderate ablation threshold Real-time ablation assessment results When the severe ablation threshold is reached, the high-voltage circuit breaker contacts are determined to be in a moderate ablation state. When the severe ablation threshold When the real-time erosion assessment results are obtained, it is determined that the high-voltage circuit breaker contacts are in a state of severe erosion and the preset erosion limit level is activated, triggering an early warning signal and sending it to the staff.

[0031] Furthermore, a health report for the corresponding high-voltage circuit breaker is generated and output, specifically as follows: The real-time ablation assessment results, ablation status level, and ablation characteristic parameters of high-voltage circuit breaker contacts are correlated according to the acquisition time to construct a time-series trajectory of health status characteristics. Based on the time-series trajectory of health status characteristics, feature trends are extracted to generate a health assessment chart containing the evolution trend of contact erosion. This health assessment chart is then output as the equipment health report of the high-voltage circuit breaker to the preset operation and maintenance platform, allowing operation and maintenance personnel to intuitively grasp the deterioration process of the high-voltage circuit breaker contacts and arrange predictive maintenance accordingly.

[0032] Example 2: This embodiment proposes a high-voltage circuit breaker contact erosion assessment system, which includes the following modules: The data acquisition module is used to collect raw multi-source operating data during the opening and closing operation of the high-voltage circuit breaker; The data preprocessing module is used to preprocess the raw multi-source operational data to obtain standard multi-source operational data; The feature construction module is used to calculate the contact ablation feature parameters of high-voltage circuit breakers based on standard multi-source operating data and in combination with preset contact ablation feature parameter calculation rules, and to construct the contact ablation feature vector. The ablation assessment module is used to input the contact ablation feature vector into the pre-trained quantitative ablation assessment model, optimize the support vector regression model using the quantum particle swarm optimization algorithm, establish a nonlinear regression mapping between the feature parameters in the contact ablation feature vector and the contact ablation loss, and output the real-time ablation assessment results of the high-voltage circuit breaker contacts. The status classification and early warning module is used to divide the real-time ablation assessment results into multiple ablation status levels according to the preset ablation degree threshold, output the corresponding high-voltage circuit breaker equipment health report, and issue an early warning signal when the ablation status level exceeds the preset ablation limit level.

[0033] Example 3: This embodiment proposes an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, it implements the method described in any embodiment of the present invention.

[0034] Example 4: This embodiment proposes a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the method described in any embodiment of the present invention.

[0035] In this application embodiment, "at least one" refers to one or more, and "more than one" refers to two or more. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent the existence of A alone, A and B simultaneously, or B alone. A and B can be singular or plural. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "At least one of the following" and similar expressions refer to any combination of these items, including any combination of singular or plural items. For example, at least one of a, b, and c can represent: a, b, c, a and b, a and c, b and c, or a and b and c, where a, b, and c can be single or multiple.

[0036] Those skilled in the art will recognize that the units and algorithm steps described in the embodiments disclosed herein can be implemented using electronic hardware, computer software, or a combination of electronic hardware and software. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0037] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0038] In the several embodiments provided in this application, any function, if implemented as a software functional unit and sold or used as an independent product, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0039] The above description is merely an embodiment of the present invention and does not limit the patent scope of the present invention. Any equivalent structural or procedural transformations made based on the content of the present invention's specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the patent protection scope of the present invention.

Claims

1. A method for evaluating the erosion of contacts in a high-voltage circuit breaker, characterized in that, Includes the following steps: Collect raw multi-source operational data during the opening and closing operations of high-voltage circuit breakers; The raw multi-source operational data is preprocessed to obtain standard multi-source operational data; Based on standard multi-source operating data and combined with the preset calculation rules for contact erosion characteristic parameters, the contact erosion characteristic parameters of high-voltage circuit breakers are calculated, and a contact erosion characteristic vector is constructed. The contact ablation feature vector is input into a pre-trained quantitative ablation assessment model. The support vector regression model is optimized using the quantum particle swarm optimization algorithm. A nonlinear regression mapping between the feature parameters in the contact ablation feature vector and the contact ablation loss is established, and the real-time ablation assessment results of the high-voltage circuit breaker contacts are output. Based on the preset ablation degree threshold, the real-time ablation assessment results are divided into multiple ablation state levels, and the corresponding high-voltage circuit breaker equipment health report is output. When the ablation state level exceeds the preset ablation limit level, an early warning signal is issued.

2. The method for evaluating the erosion of contacts in a high-voltage circuit breaker according to claim 1, characterized in that, The method utilizes multiple sensors to collect raw multi-source operational data during the opening and closing operations of high-voltage circuit breakers, including dynamic resistance sensors, arc monitoring sensors, and mechanical travel sensors. The dynamic resistance sensor is used to collect dynamic voltage signals between moving and stationary contacts and current signals through the contacts during the opening and closing operations of a high-voltage circuit breaker, and to calculate a dynamic resistance curve reflecting the deterioration state of the contact surface by using the ratio of the two. The arc monitoring sensor is used to collect the arc light signal generated at the moment of contact breakage, and simultaneously collect the arc voltage signal and arc current signal during the arcing process; The mechanical stroke sensor is used to monitor the displacement curve of the moving contact in real time during the opening and closing process, and calculates the opening and closing speed, movement stroke and contact overtravel of the moving contact based on the displacement curve.

3. The method for evaluating the erosion of high-voltage circuit breaker contacts according to claim 1, characterized in that, The method utilizes an adaptive Kalman filter algorithm to preprocess the original multi-source running data. Specific steps include: Initialize the state vector and covariance matrix based on historical multi-source operational data; At each sampling time, a state prediction is performed based on the optimal state estimate of the previous time to obtain the predicted state vector and the prediction covariance matrix at the current time. Based on the measurement residual at the current moment, the process noise covariance matrix and measurement noise covariance matrix of the Kalman filter are adaptively adjusted in real time. The Kalman gain is calculated using the adjusted covariance matrix, and the state is updated by combining the current measurement values ​​collected by multiple sensors. The output is standard multi-source operating data after filtering out high-frequency noise and electromagnetic interference.

4. The method for evaluating the erosion of contacts in a high-voltage circuit breaker according to claim 1, characterized in that, The contact erosion characteristic parameters include the steady-state average contact resistance, arc duration, single-break arc energy, contact travel deviation, and resistance fluctuation amplitude, among which: The mean steady-state contact resistance is the arithmetic mean of the resistance values ​​in the steady segment of the dynamic resistance curve after the moving and stationary contacts have made full contact and stabilized. The duration of the electric arc is the time difference between when the electric arc monitoring sensor detects the start of the electric arc and when the electric arc is completely extinguished. The single-break arc energy is the integral of the product of arc voltage and arc current over time during the arc duration. The contact travel deviation is the absolute difference between the actual total travel of the moving contact and the standard design travel. The resistance fluctuation amplitude is the difference between the maximum and minimum values ​​of the dynamic resistance curve in the transition section.

5. The method for evaluating the erosion of contacts in a high-voltage circuit breaker according to claim 1, characterized in that, The quantitative ablation assessment model is trained through the following steps: Obtain historical characteristic parameters and actual physical erosion loss of contacts corresponding to multiple sets of historical high-voltage circuit breaker opening and closing operations, and construct a training sample set; When optimizing the support vector regression algorithm using quantum particle swarm regression, the penalty parameters and kernel parameters of the support vector regression model are used as search variables to initialize the position and velocity of the particle swarm within the optimization space. In each iteration, the current particle parameters are substituted into the support vector regression model, and the minimum cross-validation mean square error of the training sample set is used as the fitness function to calculate the current fitness value of each particle and update the global optimal position. When the maximum number of iterations is reached or the preset convergence accuracy is met, the optimization stops, the optimal penalty parameter and kernel parameter are output, and the support vector regression model is trained using the optimal penalty parameter and kernel parameter to construct the quantitative ablation evaluation model.

6. The method for evaluating the erosion of contacts in a high-voltage circuit breaker according to claim 1, characterized in that, The method classifies real-time ablation assessment results into multiple ablation state levels, specifically: Pre-set thresholds for mild ablation, moderate ablation, and severe ablation. When real-time ablation assessment results When the light ablation threshold is reached, the high-voltage circuit breaker contacts are considered to be in a normal state. When the mild ablation threshold Real-time ablation assessment results When the moderate erosion threshold is reached, the high-voltage circuit breaker contacts are determined to be in a state of slight erosion. When the moderate ablation threshold Real-time ablation assessment results When the severe ablation threshold is reached, the high-voltage circuit breaker contacts are determined to be in a moderate ablation state. When the severe ablation threshold When the real-time erosion assessment results are obtained, it is determined that the high-voltage circuit breaker contacts are in a state of severe erosion and the preset erosion limit level is activated, triggering an early warning signal.

7. The method for evaluating the erosion of contacts in a high-voltage circuit breaker according to claim 1, characterized in that, The method outputs a corresponding high-voltage circuit breaker equipment health report, specifically including the following steps: The real-time ablation assessment results, ablation status level, and ablation characteristic parameters of high-voltage circuit breaker contacts are correlated according to the acquisition time to construct a time-series trajectory of health status characteristics. Based on the time-series trajectory of health status characteristics, a health assessment chart containing the evolution trend of contact erosion is generated, and the health assessment chart is output as the equipment health report of the high-voltage circuit breaker to the preset operation and maintenance platform.

8. A high-voltage circuit breaker contact erosion assessment system, characterized in that, Includes the following modules: The data acquisition module is used to collect raw multi-source operating data during the opening and closing operation of the high-voltage circuit breaker; The data preprocessing module is used to preprocess the raw multi-source operational data to obtain standard multi-source operational data; The feature construction module is used to calculate the contact ablation feature parameters of high-voltage circuit breakers based on standard multi-source operating data and in combination with preset contact ablation feature parameter calculation rules, and to construct the contact ablation feature vector. The ablation assessment module is used to input the contact ablation feature vector into the pre-trained quantitative ablation assessment model, optimize the support vector regression model using the quantum particle swarm optimization algorithm, establish a nonlinear regression mapping between the feature parameters in the contact ablation feature vector and the contact ablation loss, and output the real-time ablation assessment results of the high-voltage circuit breaker contacts. The status classification and early warning module is used to divide the real-time ablation assessment results into multiple ablation status levels according to the preset ablation degree threshold, output the corresponding high-voltage circuit breaker equipment health report, and issue an early warning signal when the ablation status level exceeds the preset ablation limit level.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the method as described in any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the method as described in any one of claims 1 to 7.

Images