Fault type identification method based on circuit breaker intelligent algorithm

Abstract

The invention relates to the technical field of circuit breaker equipment, in particular to a fault type identification method based on a circuit breaker intelligent algorithm. Comprising the steps of collecting environment temperature data of an environment where the circuit breaker is located in real time through a temperature sensor, dynamically monitoring mechanical wear degree data of a contact and an operating mechanism of the circuit breaker through a displacement sensor, and obtaining surrounding electromagnetic interference intensity data through an electromagnetic interference detection module; inputting the environment temperature data, the mechanical wear degree data and the electromagnetic interference intensity data to a processor integrated with a multi-factor dynamic coupling model, wherein the processor calculates actual contact resistance, interfered actual current and fault characteristic values based on the multi-factor dynamic coupling model; the processor identifies the fault type of the circuit breaker according to the size and the change range of the fault characteristic value in combination with a preset fault type judgment rule; the method can effectively cope with the influence of the factors, and improves the fault type recognition accuracy.

Description

Technical Field

[0001] This invention relates to the field of circuit breaker equipment technology, and more specifically to a fault type identification method based on a circuit breaker intelligent algorithm. Background Technology

[0002] During circuit breaker operation, fault type identification is crucial for ensuring power system stability. Existing circuit breaker fault type identification methods typically rely on conventional electrical parameters such as current and voltage as the core judgment criteria, identifying faults such as short circuits and overloads by monitoring abnormal changes in these parameters. However, existing technologies have significant limitations: they do not fully consider the impact of non-traditional factors such as ambient temperature, the degree of mechanical wear of the circuit breaker, and the intensity of surrounding electromagnetic interference, as well as their synergistic effects on fault identification. Changes in ambient temperature alter the resistance characteristics of the circuit breaker's conductive components, mechanical wear affects the contact state and operational response performance, and electromagnetic interference distorts fault signal transmission. When these factors act individually or in combination, they can cause non-fault-related abnormal changes in conventional electrical parameters or mask true fault signals. This makes it difficult for existing methods to accurately distinguish fault types from normal parameter fluctuations under complex operating conditions, leading to misjudgments or omissions, which could potentially trigger power system accidents in severe cases.

[0003] Based on the above problems, there is an urgent need for a technical solution that can effectively address the impact of the above factors and improve the accuracy of fault type identification. Summary of the Invention

[0004] The purpose of this invention is to provide a fault type identification method based on a circuit breaker intelligent algorithm, comprising: The circuit breaker's ambient temperature data is collected in real time by a temperature sensor, the mechanical wear data of the circuit breaker's contacts and operating mechanism is dynamically monitored by a displacement sensor, and the intensity data of the surrounding electromagnetic interference is obtained by an electromagnetic interference detection module. The ambient temperature data, mechanical wear data, and electromagnetic interference intensity data are input into a processor that integrates a multi-factor dynamic coupling model. The processor calculates the actual contact resistance, the actual interference current, and the fault characteristic value based on the multi-factor dynamic coupling model. The processor identifies the fault type of the circuit breaker based on the magnitude and range of the fault characteristic value, combined with preset fault type determination rules. The multi-factor dynamic coupling model incorporates the progressive linkage effects of ambient temperature, mechanical wear degree, and electromagnetic interference intensity. It achieves data fusion and feature extraction through three interrelated mathematical models. The parameters of the mathematical models are obtained by training and optimization using historical fault data, and can dynamically adjust the weight coefficients of each factor to adapt to different working conditions.

[0005] Preferably, the acquisition of ambient temperature data includes real-time temperature value and temperature change rate; the mechanical wear data includes contact wear amount and operating mechanism action delay time; and the electromagnetic interference intensity data includes interference signal amplitude and interference frequency distribution.

[0006] More preferably, the multi-factor dynamic coupling model includes an actual contact resistance calculation model, an actual disturbance current calculation model, and a fault characteristic value calculation model. The output of the actual contact resistance calculation model is used as the input parameter of the actual disturbance current calculation model, and the output of the actual disturbance current calculation model is used as the input parameter of the fault characteristic value calculation model.

[0007] More preferably, the preset fault type determination rule is constructed by a machine learning algorithm, which is trained based on fault feature value samples of historical fault cases and can automatically divide the feature value range of different fault types.

[0008] A further preferred embodiment is the actual contact resistance calculation model: ; Where R is the actual contact resistance, R0 is the contact resistance under reference conditions, α is the temperature coefficient of resistance, β is the wear influence coefficient, γ is the temperature-wear coupling influence coefficient, T is the actual ambient temperature, T0 is the reference temperature, and W is the degree of mechanical wear, with a value ranging from 0 to 1.

[0009] More preferably, the calculation model for the actual current affected by the disturbance is as follows: ; Where I is the actual current affected by the disturbance, and U is the power supply voltage. Here, E is the coefficient representing the effect of electromagnetic interference on voltage, and E is the intensity of electromagnetic interference. The coupling coefficient between electromagnetic interference and the rate of temperature change is denoted as . R is the rate of change of ambient temperature, and R is the actual contact resistance.

[0010] More preferably, the fault characteristic value calculation model is as follows: ; Where F is the fault characteristic value, The rate of change of current, The comprehensive impact coefficient of environmental, mechanical, and electromagnetic interference. The rate of change of mechanical wear, Electromagnetic interference rate of change Where is the coupling coefficient between wear and electromagnetic interference rate of change, I is the actual current affected by interference, and R is the actual contact resistance.

[0011] More preferably, the processor is a digital signal processor or field-programmable gate array with parallel computing capabilities, which can process multi-sensor data and perform complex mathematical operations in real time.

[0012] Further preferably, the system also includes a fault early warning module, which issues an early warning signal in advance based on the changing trend of the fault characteristic value. The early warning signal includes three forms: sound, light, and electricity, and is transmitted to a remote monitoring center through a wireless communication module.

[0013] More preferably, the method further includes a self-calibration step, which periodically performs zero-point drift and range calibration on the temperature sensor, displacement sensor, and electromagnetic interference detection module to ensure the accuracy of the collected data.

[0014] Compared with the prior art, the present invention has the following advantages: This invention creatively introduces three factors—ambient temperature, mechanical wear, and electromagnetic interference intensity—to construct a multi-factor dynamic coupling model. Data fusion and feature extraction are achieved through a progressively correlated mathematical model. This technology effectively solves the problem of misjudgment and missed judgment in fault identification under complex operating conditions caused by existing technologies that do not consider these factors and their interrelationships, significantly improving the accuracy of fault type identification. Attached Figure Description

[0015] To more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are merely exemplary, and those skilled in the art can derive other embodiments based on the provided drawings without creative effort.

[0016] Figure 1 This is a flowchart of the fault type identification method based on the intelligent algorithm of circuit breakers according to the present invention. Detailed Implementation

[0017] 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.

[0018] The concepts involved in this application will first be described with reference to the accompanying drawings. It should be noted that the following descriptions of various concepts are only for the purpose of making the content of this application easier to understand and do not constitute a limitation on the scope of protection of this application; furthermore, the embodiments and features in the embodiments of this application can be combined with each other unless otherwise specified. This application will now be described in detail with reference to the accompanying drawings and embodiments.

[0019] Traditional circuit breaker fault type identification methods suffer from the following technical problems: they rely solely on conventional electrical parameters such as current and voltage, neglecting key influencing factors such as ambient temperature, mechanical wear, and electromagnetic interference intensity, and lacking consideration of the synergistic effects of these factors. Changes in ambient temperature alter the resistance characteristics of conductive components, mechanical wear affects contact status and operational response, and electromagnetic interference distorts signal transmission. When these factors act individually or in combination, they can easily lead to fault signal distortion, making it difficult for existing methods to accurately identify fault types under complex operating conditions, especially with significant errors in identifying early-stage, latent faults.

[0020] Based on this, please refer to Figure 1 This embodiment provides a fault type identification method based on a circuit breaker intelligent algorithm, including the following steps: Real-time acquisition of ambient temperature data of the circuit breaker's environment using a temperature sensor; dynamic monitoring of mechanical wear data of the circuit breaker contacts and operating mechanism using a displacement sensor; acquisition of surrounding electromagnetic interference intensity data using an electromagnetic interference detection module; inputting the ambient temperature data, mechanical wear data, and electromagnetic interference intensity data into a processor integrating a multi-factor dynamic coupling model; the processor calculating the actual contact resistance, the actual current affected by interference, and fault characteristic values ​​based on the multi-factor dynamic coupling model; the processor identifying the fault type of the circuit breaker based on the magnitude and range of the fault characteristic values, combined with preset fault type determination rules; wherein, the multi-factor dynamic coupling model collaboratively incorporates the progressive linkage effects of ambient temperature, mechanical wear, and electromagnetic interference intensity, achieving data fusion and feature extraction through three interrelated mathematical models; the parameters of the mathematical models are obtained through training and optimization using historical fault data, and can dynamically adjust the weight coefficients of each factor to adapt to different operating conditions.

[0021] This solution addresses the shortcomings of traditional methods, which suffer from insufficient accuracy due to single parameters and lack of consideration for inter-factor interaction, by introducing three key factors: ambient temperature, mechanical wear, and electromagnetic interference, and constructing a multi-factor dynamic coupling model. At the hardware level, the solution clarifies the data source roles of temperature sensors, displacement sensors, and electromagnetic interference detection modules, ensuring the relevance of the raw data. Displacement sensors can utilize miniature strain gauges, patch-type miniature laser displacement sensors, miniature integrated Hall effect sensors, and piezoelectric thin-film sensors, prioritizing smaller sensors to ensure the overall quality of the equipment used and facilitate portability and mobility. At the software level, the multi-factor coupling model achieves data fusion through a progressively correlated mathematical model. Parameters optimized using historical data training dynamically adapt to the influence weights of factors under different operating conditions. This "hardware acquisition-software modeling-dynamic optimization" approach enables comprehensive capture and accurate analysis of fault signals, particularly effectively identifying latent faults caused by temperature fluctuations, mechanical aging, and electromagnetic interference, providing more reliable technical support for fault type determination.

[0022] Traditional fault-related data acquisition has the following technical problems: for ambient temperature, only static temperature values ​​are collected, without obtaining the rate of temperature change; for mechanical wear, only the degree of wear is described in general terms, without specifying specific parameters such as the amount of wear on contacts and the delay time of the operating mechanism; for electromagnetic interference, only the intensity of interference is monitored, without involving the frequency distribution of interference. As a result, the collected data has insufficient dimensions and lacks details, which cannot provide sufficient support for subsequent fault analysis, and thus affects the accuracy of fault identification.

[0023] Based on this, the acquisition of ambient temperature data includes real-time temperature values ​​and temperature change rates; the mechanical wear data includes contact wear and operating mechanism delay time; and the electromagnetic interference intensity data includes interference signal amplitude and interference frequency distribution. This scheme addresses the problems of "single parameters and insufficient information" in traditional data acquisition by refining the acquisition dimensions of these three types of data. Real-time ambient temperature values ​​and change rates can respectively reflect static resistance characteristics and dynamic resistance trends; contact wear is directly related to contact resistance, and operating mechanism delay time reflects mechanical response performance; combining these two aspects provides a more comprehensive characterization of the impact of mechanical wear on circuit breaker operation; interference signal amplitude and frequency distribution can quantify interference intensity and type, providing a targeted basis for subsequent signal noise reduction.

[0024] This multi-dimensional data acquisition method ensures that the raw data can fully map the circuit breaker's operating status and external influences, providing rich and accurate input for the calculation of the multi-factor dynamic coupling model, and improving the basic reliability of fault identification from the data source.

[0025] Traditional fault feature calculation models have the following technical problems: the calculation of each parameter is independent of each other. For example, the calculation of contact resistance is not related to the change of current, and the calculation of current does not consider the linkage between resistance and electromagnetic interference. As a result, the model cannot reflect the progressive influence relationship between factors, resulting in a large deviation between the calculation results and the actual working conditions, which in turn affects the accuracy of fault feature extraction.

[0026] Based on this, the multi-factor dynamic coupling model includes an actual contact resistance calculation model, an actual disturbance current calculation model, and a fault characteristic value calculation model. The output of the actual contact resistance calculation model is used as the input parameter of the actual disturbance current calculation model, and the output of the actual disturbance current calculation model is used as the input parameter of the fault characteristic value calculation model.

[0027] This solution addresses the problems of isolated parameter calculations and lack of factor linkage in traditional models by constructing a progressive model structure that integrates contact resistance, actual current, and fault characteristic values. The resistance value output by the actual contact resistance calculation model serves as the core parameter for calculating the actual current under interference, ensuring that the current calculation reflects the influence of temperature and mechanical wear on the resistance. The current value output by the actual current calculation model under interference, in turn, serves as the basis for calculating fault characteristic values, enabling the fault characteristics to incorporate the influence of electromagnetic interference.

[0028] This interconnected structure of preceding outputs and subsequent inputs fully maps the transmission path of environmental temperature, mechanical wear, and electromagnetic interference from basic physical quantities to fault characteristics, making the model calculations more closely resemble actual physical processes. Simultaneously, this correlation ensures that the influence of each factor is gradually transmitted and centrally reflected in the fault characteristic values, providing more accurate feature basis for subsequent fault type identification.

[0029] Traditional fault type determination rules have the following technical problems: they are mostly based on fixed empirical thresholds or simple logical relationships, without dynamic optimization by combining historical fault data, making it difficult to adapt to changes in operating conditions under different ambient temperatures, mechanical wear states, and electromagnetic interference intensities. Under complex operating conditions, the determination rules are prone to being inapplicable, leading to a decrease in fault identification accuracy.

[0030] Based on this, the preset fault type determination rule is constructed through a machine learning algorithm. The machine learning algorithm is trained based on fault feature value samples of historical fault cases and can automatically divide the feature value range of different fault types.

[0031] This solution addresses the limitations of traditional rules, which are often "fixed and lack adaptability," by constructing judgment rules using machine learning algorithms. The machine learning algorithm uses feature values ​​from a large number of historical fault cases as samples, automatically learning the characteristic patterns of different fault types under various operating conditions through training, and then defining dynamically adaptable feature value ranges. This rule construction method can capture subtle differences in fault characteristics under the combined effects of ambient temperature, mechanical wear, and electromagnetic interference. For example, under high-temperature and high-wear conditions, the difference in feature value ranges for the same fault type compared to those under normal-temperature, no-wear conditions can be identified by the algorithm and incorporated into the rules. Compared to fixed thresholds, this rule can automatically adjust the judgment criteria as operating conditions change. Under new operating conditions, the rule can be optimized through iterations with a small number of samples, significantly improving the adaptability and accuracy of fault type identification under complex and variable conditions.

[0032] Traditional contact resistance calculation methods have the following technical problems: they only consider the single effect of ambient temperature or mechanical wear, without taking into account the coupling effect between the two. For example, they do not consider that high temperature will aggravate the resistance change of worn parts, resulting in a large deviation between the calculated results and the actual contact resistance, which in turn affects the accuracy of fault feature extraction based on resistance parameters.

[0033] Based on this, the actual contact resistance calculation model is as follows: ; Where R is the actual contact resistance, R0 is the contact resistance under reference conditions, α is the temperature coefficient of resistance, β is the wear influence coefficient, γ is the temperature-wear coupling influence coefficient, T is the actual ambient temperature, T0 is the reference temperature, and W is the degree of mechanical wear, with a value ranging from 0 to 1.

[0034] In this formula, R0 serves as a baseline value, representing the contact resistance of the circuit breaker under ideal conditions, without temperature changes or mechanical wear, providing a basic reference for subsequent calculations.

[0035] The α(T-T0) term reflects the linear effect of temperature on resistance. When the actual temperature T deviates from the reference temperature T0, the contact resistance changes due to the thermal expansion and contraction characteristics of the material. α quantifies the sensitivity to this change. βW 2 The influence of mechanical wear is introduced, and a square form is used to reflect the nonlinear effect of wear—as contact wear intensifies, the contact area decreases, and the resistance increases nonlinearly. The β coefficient is determined based on material properties and wear mechanism.

[0036] It is worth noting that, The term is one of the innovative aspects of this formula, as it captures the coupling effect between temperature and wear. In actual working conditions, high-temperature environments accelerate the oxidation and deformation of worn parts, while wear itself increases the local temperature at the contact point, with the two factors mutually reinforcing each other.

[0037] For example, when there is some wear on the circuit breaker contacts (W>0), a temperature increase (T>T0) will further increase the resistance through this coupling term. This quantitative relationship is highly consistent with actual physical phenomena. The coefficients determined through fitting a large amount of experimental data ensure that the formula accurately reflects the changing law of actual contact resistance, providing precise basic parameters for subsequent calculations of actual current under interference.

[0038] This scheme addresses the problem of traditional contact resistance calculations neglecting the interplay of factors by introducing a coupling term between temperature and wear. In the formula, the α(T-T0) term quantifies the individual effect of temperature on resistance, and βW... 2 The item reflects the nonlinear effect of wear, while The term accurately captures the synergistic effect of high temperature and wear—for example, when there is a certain amount of wear on the circuit breaker (W>0), the temperature rise (T>T0) will further increase the resistance through the coupling term, which is consistent with the physical law that worn parts have a worse contact state at high temperatures in reality.

[0039] Each coefficient was calibrated experimentally to ensure the accuracy of the quantitative relationships. The contact resistance calculated by this formula can accurately reflect the resistance characteristics under temperature, wear, and their combined effects, providing accurate basic parameters for subsequent calculations of actual current under interference, and improving the reliability of fault-related physical quantity calculations from the source.

[0040] The following is a comparison table of experimental data based on the actual contact resistance calculation model:

[0041] It should be noted that traditional methods only consider the effects of temperature or wear, neglecting the coupling term. The formula of this invention introduces a temperature-wear coupling term. The deviation rate between the calculated value and the actual measured value is significantly lower than that of the traditional single-factor method. Especially in high temperature and high wear scenarios, such as scenarios 3 and 4, the influence of coupling on contact resistance is accurately captured, verifying the quantitative accuracy of the formula for the multi-factor linkage effect.

[0042] Traditional current calculation methods have the following technical problems: they calculate current based only on an ideal circuit model, without considering the actual changes in contact resistance and the impact of electromagnetic interference on current measurement, and they also ignore the coupling effect of electromagnetic interference and temperature change rate. This results in a large deviation between the calculated current value and the interference current under actual operating conditions, making it impossible to accurately reflect the true operating state of the circuit breaker, and thus affecting the extraction of fault features and identification of fault types based on current parameters.

[0043] Based on this, the calculation model for the actual current under interference is as follows: ; Where I is the actual current affected by the disturbance, and U is the power supply voltage. The effect coefficient of electromagnetic interference on voltage, where E is the electromagnetic interference intensity. Let V be the coupling coefficient between electromagnetic interference and the rate of temperature change, V be the rate of temperature change, and R be the actual contact resistance. This scheme solves the problem of traditional current calculations not considering non-ideal factors and the interaction of factors by introducing an electromagnetic interference correction term and a temperature change rate coupling term.

[0044] This formula is based on Ohm's law, but has been significantly extended to accommodate complex operating conditions. In this term, U is the ideal power supply voltage, while This demonstrates the attenuation effect of electromagnetic interference on voltage. When the intensity of electromagnetic interference E increases, The term reduces the effective voltage value because electromagnetic interference induces a back electromotive force in the circuit, offsetting part of the power supply voltage. The square form is used because the effects of electromagnetic interference are typically non-linear; as the interference intensity increases, its voltage attenuation effect accelerates.

[0045] The core innovation of this formula lies in capturing the synergistic effect of electromagnetic interference and the rate of temperature change. In real-world environments, rapid temperature changes cause dynamic changes in the electrical properties of materials. If strong electromagnetic interference is present at this time, the two will interact and affect the current. For example, during high-frequency switching operations, rapid temperature changes may induce alterations in the local electric field distribution, which, when superimposed with external electromagnetic interference, will have an additional impact on the current. The coefficients were determined experimentally, quantifying this complex coupling relationship. By integrating various non-ideal factors, the formula makes the calculated current value closer to the actual operating conditions, providing a more reliable input for calculating fault characteristic values.

[0046] In the formula, This item reflects the attenuation effect of electromagnetic interference on voltage and the influence of actual contact resistance on current. When the electromagnetic interference intensity E increases, This reduces the effective voltage value, thus more accurately reflecting the actual current under interference conditions; while The formula captures the synergistic effect of electromagnetic interference and temperature change rate. For example, in scenarios with rapid temperature changes and strong electromagnetic interference, this coupling effect can have an additional impact on the current. All coefficients were experimentally calibrated to ensure the model accurately fits actual operating conditions. The actual disturbed current calculated by this formula can realistically reflect the current characteristics under the combined effects of multiple non-ideal factors, providing more accurate input for subsequent fault characteristic value calculations and significantly improving the basic accuracy of fault identification.

[0047] The following is a comparison table of experimental data from the actual current calculation model under interference:

[0048] It should be noted that traditional methods only consider the voltage attenuation caused by electromagnetic interference, neglecting the coupling term between electromagnetic interference and the rate of temperature change. The deviation is significant in scenarios with strong interference and rapid temperature changes. The formula of this invention captures the synergistic effect of the two through coupling terms, and the calculated value is closer to the actual measured value, which verifies the adaptability to complex electromagnetic-temperature linkage scenarios.

[0049] Traditional fault characteristic value calculation has the following technical problems: it only constructs characteristic values ​​based on a single electrical parameter or a simple combination of parameters, without fully considering the comprehensive effects of ambient temperature, mechanical wear, electromagnetic interference and their rate of change, and without reflecting the dynamic coupling relationship between the parameters. As a result, the fault characteristic values ​​cannot fully characterize the operating status of the circuit breaker, and it is difficult to effectively distinguish different types of faults under complex operating conditions.

[0050] Based on this, the fault characteristic value calculation model is as follows: ; Where F is the fault characteristic value, The rate of change of current, The comprehensive impact coefficient of environmental, mechanical, and electromagnetic interference. The rate of change of mechanical wear, The rate of change of electromagnetic interference. Where is the coupling coefficient between wear and electromagnetic interference rate of change, I is the actual current affected by interference, and R is the actual contact resistance.

[0051] This formula constructs fault characteristic values ​​by fusing multi-dimensional parameters. The item integrates information on current, resistance, and their rate of change, I 2 R essentially reflects the thermal power characteristics of the circuit, and divided by the rate of change of current This leads to the introduction of dynamic characteristic analysis.

[0052] When a fault occurs, the rate of change of current often becomes abnormal. For example, a short circuit fault will cause the current to rise sharply, and this value will increase significantly, thus highlighting the fault characteristics.

[0053] The term incorporates the nonlinear effects of ambient temperature, mechanical wear, and electromagnetic interference intensity into the eigenvalues. The use of square or cubic forms is to amplify the influence of outliers; for example, when temperature T or electromagnetic interference intensity E increases significantly, the square term will significantly increase their contribution to the eigenvalues. Mechanical wear W is presented in cubic form because severe wear is more critical for indicating faults, and the cubic form can more effectively amplify this effect.

[0054] This term is the key innovation of the formula, capturing the coupling effect between the rate of change of mechanical wear and the rate of change of electromagnetic interference. In actual operating conditions, when mechanical wear intensifies rapidly and electromagnetic interference also changes rapidly, their synergistic effect often foreshadows serious faults. For example, rapid wear of the circuit breaker operating mechanism may lead to arcing, which in turn triggers strong electromagnetic interference. This vicious cycle is prominently reflected in the fault characteristic values ​​through this term. The coefficients are determined through machine learning analysis of a large amount of historical fault data, ensuring that the fault characteristic values ​​most effectively reflect different types of faults.

[0055] This scheme solves the problem of traditional feature values ​​being singular and failing to reflect the interaction of factors by constructing a multi-parameter, multi-dimensional feature value calculation model. In the formula, This item integrates information on current, resistance, and their rate of change, reflecting the dynamic characteristics of the circuit; The term incorporates the nonlinear effects of ambient temperature, mechanical wear, and electromagnetic interference intensity into the eigenvalues ​​through a sum of squares; while The method captures the coupling effect between the rate of change of mechanical wear and the rate of change of electromagnetic interference. For example, in scenarios where wear intensifies and electromagnetic interference changes rapidly, this coupling produces unique fault characteristics.

[0056] Exponential settings for each parameter (such as W) 3 This model reflects the nonlinear influence of different factors on fault characteristics. Through multi-parameter fusion and coupling analysis, the fault characteristic values ​​can comprehensively and dynamically reflect the operating status of the circuit breaker, significantly improving the feature differentiation between different fault types and providing solid technical support for accurate fault type identification.

[0057] The following is a comparison table of experimental data for the fault characteristic value calculation model:

[0058] It should be noted that traditional methods do not consider the coupling between the rate of change of mechanical wear and the rate of change of electromagnetic interference (ν·dW / dt·dE / dt), resulting in low accuracy in identifying early signs of faults where wear rapidly intensifies and interference rapidly increases. The formula of this invention amplifies the feature differences in such scenarios through the coupling term, significantly improving the identification accuracy, especially for early identification of severe fault precursors.

[0059] Traditional fault identification systems suffer from the following technical problems: when using general-purpose processors to process fault identification algorithms, they are slow and have poor real-time performance when faced with real-time acquisition of multi-sensor data and calculation of complex mathematical models. This can easily lead to data processing delays, make it impossible to respond to sudden faults in a timely manner, and cause system crashes in high-concurrency data processing scenarios, thus affecting the reliability and practicality of fault identification.

[0060] Based on this, the processor employs a digital signal processor (DSP) or a field-programmable gate array (FPGA) with parallel computing capabilities, enabling real-time processing of multi-sensor data and execution of complex mathematical operations. This solution addresses the insufficient processing power of traditional processors by employing dedicated parallel computing hardware. DSPs possess high-speed data processing capabilities and a rich set of digital signal processing instructions, making them suitable for performing complex mathematical operations; FPGAs, on the other hand, implement a parallel computing architecture through hardware programming, allowing for optimized design for specific algorithms.

[0061] In this fault identification system, the DSP or FPGA can simultaneously process data from multiple sensors, such as temperature, mechanical wear, and electromagnetic interference, and perform parallel calculations of actual contact resistance, actual interference current, and fault characteristic values, significantly improving data processing speed.

[0062] For example, for high-frequency sampled sensor data, FPGAs can achieve continuous data processing through pipeline architecture to avoid data backlog; DSPs can efficiently execute complex operations such as exponentiation and differentiation in the model.

[0063] This hardware optimization design ensures that the system can complete the entire process from data acquisition to fault identification in a short time, respond to fault events in real time, and improve the system's practicality and reliability. It is especially suitable for industrial control, power systems and other scenarios with high real-time requirements.

[0064] Traditional fault identification systems have the following technical problems: they can only identify and alarm after a fault occurs, lack the ability to provide early warning of potential faults, and cannot take preventive measures in the early stages of a fault, resulting in an expansion of equipment damage, increased maintenance costs, and the emergency shutdown when a fault occurs may affect production continuity.

[0065] Based on this, the method also includes a fault early warning module, which issues an early warning signal in advance based on the changing trend of the fault characteristic value. The early warning signal includes multiple forms such as sound, light, and electricity, and is transmitted to a remote monitoring center through a wireless communication module.

[0066] This solution addresses the problems of traditional systems' reactive identification and lack of prevention by introducing a fault early warning mechanism. The fault early warning module analyzes the changing trends of fault characteristic values ​​in real time, such as predicting the future trend of characteristic values ​​through time series analysis. When an abnormal changing trend of characteristic values ​​is detected, such as a continuous rise or increased fluctuations but before reaching the fault threshold, an early warning signal is issued.

[0067] Multiple forms of early warning signals ensure that on-site personnel can promptly perceive potential risks, while wireless communication modules enable remote monitoring centers to simultaneously acquire early warning information, facilitating remote decision-making by management. For example, in an industrial environment, when the system predicts a potential contact failure in a circuit breaker, maintenance personnel can be scheduled to inspect it in advance, preventing the fault from escalating and causing equipment damage or production interruption. This preventative early warning mechanism transforms fault handling from a passive response to proactive prevention, effectively reducing equipment maintenance costs and production losses, and improving the reliability and stability of the entire system.

[0068] Traditional fault identification systems have the following technical problems: After long-term operation, temperature sensors, displacement sensors, and electromagnetic interference detection modules will experience zero-point drift and range changes due to environmental factors, resulting in a decrease in the accuracy of the collected data and thus affecting the reliability of fault identification. In addition, existing systems lack an automatic calibration mechanism and require manual calibration periodically, which increases maintenance costs and workload.

[0069] Based on this, the method also includes a self-calibration step, which periodically performs zero-point drift and range calibration on the temperature sensor, displacement sensor, and electromagnetic interference detection module to ensure the accuracy of the acquired data. This solution addresses the problem of long-term sensor accuracy degradation in traditional systems by introducing a self-calibration mechanism. The self-calibration step is executed periodically during system operation, for example, automatically triggered once daily or weekly. For the temperature sensor, zero-point drift is calculated and compensated by comparing with a high-precision reference temperature source; for the displacement sensor, the range coefficient is adjusted by detecting a known standard displacement; for the electromagnetic interference detection module, the gain and offset of the detection circuit are calibrated using a built-in standard signal source. The calibration process requires no manual intervention; the system automatically completes data acquisition, analysis, and parameter adjustment.

[0070] For example, when zero-point drift of the temperature sensor causes the measured value to be too high, the self-calibration step automatically adjusts the offset to bring the measured value back to the true value. This automatic calibration mechanism ensures the accuracy of the sensor during long-term operation, improves the reliability and stability of the entire fault identification system, and reduces manual maintenance costs, making it particularly suitable for unattended or difficult-to-maintain applications.

[0071] The embodiments and / or implementation methods described above are merely preferred embodiments and / or implementation methods for implementing the technology of the present invention, and are not intended to limit the implementation methods of the technology of the present invention in any way. Any person skilled in the art can make some modifications or alterations to other equivalent embodiments without departing from the scope of the technical means disclosed in the content of the present invention, but they should still be regarded as the technology or embodiments that are substantially the same as the present invention.

[0072] This document uses specific examples to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the methods and core ideas of this application. The above descriptions are only preferred embodiments of this application. It should be noted that due to the limitations of written expression, while there are objectively infinite specific structures, those skilled in the art can make several improvements, modifications, or changes without departing from the principles of this application, and can also combine the above technical features in an appropriate manner. These improvements, modifications, changes, or combinations, or the direct application of the inventive concept and technical solution to other situations without modification, should all be considered within the scope of protection of this application.

Claims

1. A fault type identification method based on a circuit breaker intelligent algorithm, characterized in that, include: The circuit breaker's ambient temperature data is collected in real time by a temperature sensor, the mechanical wear data of the circuit breaker's contacts and operating mechanism is dynamically monitored by a displacement sensor, and the intensity data of the surrounding electromagnetic interference is obtained by an electromagnetic interference detection module. The ambient temperature data, mechanical wear data, and electromagnetic interference intensity data are input into a processor that integrates a multi-factor dynamic coupling model. The processor calculates the actual contact resistance, the actual interference current, and the fault characteristic value based on the multi-factor dynamic coupling model. The processor identifies the fault type of the circuit breaker based on the magnitude and range of the fault characteristic value, combined with preset fault type determination rules. The multi-factor dynamic coupling model incorporates the progressive linkage effects of ambient temperature, mechanical wear degree, and electromagnetic interference intensity. It achieves data fusion and feature extraction through three interrelated mathematical models. The parameters of the mathematical models are obtained by training and optimization using historical fault data, and can dynamically adjust the weight coefficients of each factor to adapt to different working conditions.

2. The fault type identification method based on circuit breaker intelligent algorithm according to claim 1, characterized in that, The acquisition of ambient temperature data includes real-time temperature values ​​and temperature change rates; the mechanical wear data includes contact wear and operating mechanism action delay time; and the electromagnetic interference intensity data includes interference signal amplitude and interference frequency distribution.

3. The fault type identification method based on circuit breaker intelligent algorithm according to claim 1, characterized in that, The multi-factor dynamic coupling model includes an actual contact resistance calculation model, an actual disturbance current calculation model, and a fault characteristic value calculation model. The output of the actual contact resistance calculation model is used as the input parameter of the actual disturbance current calculation model, and the output of the actual disturbance current calculation model is used as the input parameter of the fault characteristic value calculation model.

4. The fault type identification method based on circuit breaker intelligent algorithm according to claim 1, characterized in that, The preset fault type determination rules are constructed using a machine learning algorithm. This machine learning algorithm is trained based on fault feature value samples from historical fault cases and can automatically divide the feature value ranges of different fault types.

5. The fault type identification method based on circuit breaker intelligent algorithm according to claim 3, characterized in that, The actual contact resistance calculation model is as follows: ； Where R is the actual contact resistance, R0 is the contact resistance under reference conditions, α is the temperature coefficient of resistance, β is the wear influence coefficient, γ is the temperature-wear coupling influence coefficient, T is the actual ambient temperature, T0 is the reference temperature, and W is the degree of mechanical wear, ranging from 0 to 1.

6. The fault type identification method based on circuit breaker intelligent algorithm according to claim 3, characterized in that, The calculation model for the actual current under interference is as follows: ； Where I is the actual current affected by the disturbance, and U is the power supply voltage. Here, E is the coefficient representing the effect of electromagnetic interference on voltage, and E is the intensity of electromagnetic interference. The coupling coefficient between electromagnetic interference and the rate of temperature change is denoted as . R is the rate of change of ambient temperature, and R is the actual contact resistance.

7. The fault type identification method based on circuit breaker intelligent algorithm according to claim 3, characterized in that, The fault characteristic value calculation model is as follows: ； Where F is the fault characteristic value, The rate of change of current, The comprehensive impact coefficient of environmental, mechanical, and electromagnetic interference. The rate of change of mechanical wear, Electromagnetic interference rate of change Where is the coupling coefficient between wear and electromagnetic interference rate of change, I is the actual current affected by interference, and R is the actual contact resistance.

8. The fault type identification method based on circuit breaker intelligent algorithm according to claim 1, characterized in that, The processor employs a digital signal processor or field-programmable gate array with parallel computing capabilities, enabling it to process multi-sensor data and perform complex mathematical operations in real time.

9. The fault type identification method based on circuit breaker intelligent algorithm according to claim 1, characterized in that, It also includes a fault early warning module, which issues an early warning signal in advance based on the changing trend of the fault characteristic value. The early warning signal includes three forms: sound, light, and electricity, and is transmitted to the remote monitoring center through a wireless communication module.

10. The fault type identification method based on circuit breaker intelligent algorithm according to claim 1, characterized in that, The method also includes a self-calibration step, which periodically performs zero-point drift and range calibration on the temperature sensor, displacement sensor, and electromagnetic interference detection module to ensure the accuracy of the collected data.

Images