Intelligent evaluation system for residual life of high-voltage circuit breaker

Abstract

The invention relates to the technical field of circuit breaker service life evaluation, in particular to a high-voltage circuit breaker residual service life intelligent evaluation system, which comprises an operation data acquisition module for acquiring operation data of a high-voltage circuit breaker; the degradation degree feature extraction module is used for extracting degradation degree features from the processed operation data; the residual life calculation module is used for constructing a residual life prediction model by utilizing the degradation degree characteristics and adopting a generalized regression neural network algorithm, and calculating the residual life of the residual life prediction model; the early warning and maintenance strategy module is used for formulating a predictive maintenance strategy of the high-voltage circuit breaker based on the residual life calculation result in combination with the residual life probability density function and the expected loss rate of the circuit breaker, and balancing the economical efficiency and the reliability; according to the method, the degradation process of the circuit breaker is reflected in real time, potential faults of equipment are predicted in time, and delay and inaccuracy caused by traditional experience judgment and regular inspection are avoided.

Description

Technical Field

[0001] The present invention relates to the technical field of circuit breaker life assessment, and in particular to an intelligent assessment system for the remaining life of a high-voltage circuit breaker. Background Art

[0002] At present, traditional methods for assessing the health status of high-voltage circuit breakers rely on regular maintenance and empirical judgment. These methods are usually unable to accurately reflect the operating status of circuit breakers in real time, and are difficult to cope with the complex situation of gradual degradation of circuit breakers. Regular maintenance is often based on set time intervals, which may lead to premature or late maintenance decisions, thereby increasing maintenance costs and the risk of equipment failure. In addition, traditional methods cannot be dynamically adjusted according to actual operating data under different working conditions, thus limiting the accuracy of remaining life prediction.

[0003] In recent years, with the development of intelligent sensing technology and big data analysis technology, online monitoring methods based on sensor data have gradually become a trend. These methods can evaluate the health status of circuit breakers by collecting operating data of high-voltage circuit breakers (such as current, voltage, temperature, and pressure, etc.) in real time and combining them with data analysis models. However, existing monitoring methods based on sensor data still face several challenges:

[0004] Real-time dynamic assessment of degradation status: Although existing systems are able to collect real-time data, it remains a challenge to combine this real-time data with the complex changes in the equipment degradation process and accurately predict the remaining life.

[0005] The balance between economy and reliability: Existing maintenance strategies usually focus on one aspect, namely cost or safety, and lack an optimization plan that comprehensively considers factors such as the remaining life of the equipment and maintenance costs and failure risks.

[0006] Therefore, there is an urgent need for a new method that can dynamically evaluate the health status of high-voltage circuit breakers and accurately predict the remaining life based on real-time monitoring data, while taking into account both economy and reliability, and proposing a reasonable predictive maintenance strategy. Summary of the invention

[0007] Based on the above objectives, the present invention provides an intelligent evaluation system for the remaining life of a high-voltage circuit breaker.

[0008] A high-voltage circuit breaker remaining life intelligent assessment system, comprising:

[0009] Operation data acquisition module: collects the operation data of the high-voltage circuit breaker, including current data, voltage data, temperature data, and pressure data, and normalizes the collected high-voltage circuit breaker status data;

[0010] The degradation degree feature extraction module extracts the degradation degree features from the processed operation data, including the current fluctuation amplitude features and voltage frequency features, the temperature change rate, and the pressure abnormal fluctuation features;

[0011] Remaining life calculation module: Based on the degradation characteristics and the generalized regression neural network (GRNN) algorithm, a remaining life prediction model is constructed. Combined with the real-time updated working status, the status of the circuit breaker is evaluated and its remaining life is calculated;

[0012] Early warning and maintenance strategy module: Based on the remaining life calculation results, combined with the remaining life probability density function and expected loss rate of the circuit breaker, a predictive maintenance strategy for high-voltage circuit breakers is formulated to balance economy and reliability.

[0013] Furthermore, the operation data acquisition module arranges current sensors, voltage sensors, temperature sensors and pressure sensors (oil-immersed circuit breakers) on key components of the high-voltage circuit breaker, collects current data, voltage data, temperature data and pressure data of the circuit breaker under different working conditions in real time, normalizes the collected operation data, and transmits them to the degradation degree feature extraction module.

[0014] Furthermore, the degradation degree feature extraction module specifically includes:

[0015] The current fluctuation amplitude feature extraction unit is used to extract the fluctuation amplitude feature from the processed current data, including calculating the standard deviation σ of the current signal I , calculate the peak-to-peak difference ΔI of the current signal based on the sliding window peak , to evaluate the load fluctuation of the circuit breaker under different operating conditions;

[0016] A voltage fluctuation frequency feature extraction unit is used to extract frequency features from the processed voltage data, including analyzing the frequency spectrum in the voltage signal through Fourier transform, calculating the frequency distribution of the voltage signal and its power spectrum density, so as to evaluate the frequency component P(f) of the voltage fluctuation;

[0017] The temperature change rate feature extraction unit is used to extract the temperature change rate feature from the processed temperature data by calculating the change rate of the temperature signal per unit time. (such as first-order difference), analyze the thermal load changes of the circuit breaker under different working conditions;

[0018] The pressure abnormal fluctuation feature extraction unit is used to extract abnormal fluctuation features from the processed pressure data, and use abnormal fluctuation detection to identify abnormal fluctuations ΔP in the pressure data, so as to evaluate the leakage and pressure instability of the equipment.

[0019] Furthermore, the standard deviation of the current signal in the current fluctuation amplitude feature extraction unit is calculated as:

[0020] Among them, I i represents the current data at the i-th moment, represents the average value of current data, N is the total number of sampling data points; standard deviation σ I Describes the fluctuation amplitude of the current signal. A large standard deviation indicates a large current fluctuation, indicating a load fluctuation or a fault in the equipment.

[0021] The peak-to-peak difference is calculated as: ΔI peak =I max -I min , where I max is the maximum value of the current signal, I min is the minimum value of the current signal, ΔI peak Measures the maximum fluctuation range of the current signal.

[0022] Furthermore, the Fourier transform analysis in the voltage fluctuation frequency feature extraction unit is expressed as:

[0023] Among them, x n is the voltage data at the nth moment, X(f) is the frequency domain component at frequency f, N is the number of sampling points, f is the frequency, and Fourier transform converts the voltage signal from the time domain to the frequency domain to analyze its frequency components;

[0024] The power spectral density is expressed as: P(f)=|X(f)| 2 , where P(f) is the power spectral density at frequency f, and X(f) is the frequency domain component after Fourier transform.

[0025] Furthermore, in the temperature change rate feature extraction unit:

[0026] The rate of change is calculated as: Where T(t) represents the temperature data at time t, Δt is the time interval, usually the sampling period, and the temperature change rate Describes how quickly temperature changes over time.

[0027] Furthermore, the abnormal pressure fluctuation feature extraction unit includes a deviation detection method:

[0028] Among them, P i represents the pressure data at the i-th moment, represents the average value of pressure data, N is the total number of sampled data points, and the standard deviation of pressure σ P Indicates the amplitude of pressure fluctuation;

[0029] The abnormal fluctuation detection is expressed as: Among them, α is the threshold coefficient, which is set to 3, indicating that the pressure data exceeding the range of 3 times the standard deviation is an abnormal fluctuation, P i is the pressure data at the i-th moment, is the average value of pressure data, σ P is the standard deviation of the pressure data.

[0030] Furthermore, the construction of the remaining life prediction model specifically includes:

[0031] Degradation feature input unit: The degradation degree features, including the standard deviation σ of the current signal I , the peak-to-peak difference of the current signal ΔP abnormal , the frequency component of voltage fluctuation P(f), the temperature change rate and the abnormal fluctuation ΔP in the pressure data as input, which is provided to the generalized regression neural network GRNN model for remaining life prediction;

[0032] Generalized regression neural network GRNN model: Based on the degradation degree characteristics, a remaining life prediction model is constructed through a supervised learning method. The training process of the GRNN model includes the following:

[0033] Use historical data sets for training, which include actual working data of circuit breakers and corresponding remaining life data;

[0034] During training, according to the degraded features σ of the input I ,ΔI peak ,P(f), Mapping learning is performed between ΔP and the corresponding remaining life, and the weights and parameters in the GRNN model are adjusted so that the model can predict the remaining life of the circuit breaker under given feature inputs;

[0035] During the prediction process, the GRNN model outputs a remaining life value based on the input degradation characteristics, which represents the health status of the circuit breaker and the expected time of failure occurrence;

[0036] Real-time status update unit: obtains the current working status of the circuit breaker in real time, including current, voltage, temperature and pressure data, and uses the real-time degradation features calculated by the degradation feature extraction module as the input of the GRNN model to update the remaining life prediction;

[0037] The remaining life calculation unit calculates the remaining life under the current working state according to the output of the GRNN model, and provides an estimated value of the remaining life by comprehensively analyzing the health status of the circuit breaker.

[0038] Furthermore, the input of the generalized regression neural network GRNN model is the degradation feature, and the output is the remaining life R. The generalized regression neural network GRNN model processes the input feature, and the predicted output value is expressed as:

[0039] in, is the predicted value of the model, indicating the remaining life of the circuit breaker, N is the number of samples in the training data set, and M is the dimension of the input feature, which is 5 here (including σ I ,ΔI peak ,P(f), ΔP), is the feature vector of the i-th sample, y i is the true remaining life value corresponding to the i-th sample, σ is the width parameter of the Gaussian kernel function, which controls the smoothness of the model, and x ij is the jth feature of the i-th sample.

[0040] Furthermore, the early warning and maintenance strategy module specifically includes:

[0041] A remaining life probability density function generating unit generates a probability density function f of the remaining life of the high-voltage circuit breaker based on the remaining life calculation result. lifespan (t), represents the probability distribution of the remaining life of the circuit breaker at different time points t, and the probability density function f lifespan (t) By statistically analyzing historical data and combining it with the output of the prediction model, the maximum likelihood estimation method is used for fitting to obtain the probability distribution of the remaining life of the circuit breaker;

[0042] The expected loss rate calculation unit is based on the remaining life probability density function f of the high-voltage circuit breaker. lifespan (t) and maintenance cost, calculate the expected loss rate L exp , that is, the expected economic loss caused by equipment failure or untimely maintenance. The expected loss rate is calculated as:

[0043] Among them, t0 is the current time, T is the expected life span of the circuit breaker, C repair is the cost of each maintenance, R(t) is the frequency or probability of maintenance or replacement at time point t, C failure is the repair cost after the failure occurs, P failure (t) is the probability of the circuit breaker failing at time t;

[0044] Maintenance strategy optimization unit, based on the expected loss rate L exp , combined with the remaining life probability density function f lifespan(t), formulate a predictive maintenance strategy for high-voltage circuit breakers. The predictive maintenance strategy balances economy and reliability by optimizing the objective function:

[0045] min τ (L exp (τ))subject toP failure (τ)≤, where τ represents the choice of maintenance timing (such as the time threshold for delayed maintenance), L exp (τ) is the expected loss rate at maintenance time τ, P failure (τ) represents the probability of circuit breaker failure at maintenance opportunity τ, which is an acceptable failure risk threshold (such as a certain maximum failure probability).

[0046] Beneficial effects of the present invention:

[0047] The present invention constructs a remaining life prediction model for high-voltage circuit breakers by introducing multi-dimensional degradation characteristics (including current fluctuation amplitude, frequency component, temperature change rate and pressure fluctuation characteristics) in combination with a generalized regression neural network (GRNN) algorithm. Compared with traditional methods, the present invention can more accurately evaluate the status of high-voltage circuit breakers based on real-time working status, accurately calculate the remaining life, reflect the degradation process of circuit breakers in real time, and timely predict potential equipment failures, thus avoiding the delays and inaccuracies caused by traditional empirical judgments and periodic inspections.

[0048] The present invention adopts a method of independently analyzing degradation characteristics, avoiding information loss and errors that may be caused by weighted fusion. In the process of extracting the fluctuation characteristics of current, voltage, temperature and pressure, the influence of each feature on the health status of the circuit breaker is deeply analyzed through multiple dimensions such as standard deviation, peak difference, frequency component, etc., thereby ensuring the independence and comprehensiveness of each feature information, being able to more carefully capture the degradation trend of the circuit breaker under different working conditions, and improving the reliability and accuracy of degradation analysis. In particular, when facing multiple potential failure modes, different degradation processes can be more effectively distinguished.

[0049] The present invention, by combining the remaining life probability density function and the expected loss rate of high-voltage circuit breakers, proposes a predictive maintenance strategy based on actual data and fault risk assessment. This strategy not only takes into account the possible failure risk of the equipment, but also comprehensively considers the balance between economy and reliability. By calculating the expected loss rate, the best maintenance timing selection is achieved in actual maintenance, avoiding premature or late maintenance intervention, significantly reducing maintenance costs, and maximizing the service life of the equipment to ensure the safe and stable operation of the power system. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only for the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0051] Figure 1 is a schematic diagram of an evaluation system according to an embodiment of the present invention;

[0052] Figure 2 A schematic diagram of a remaining life prediction model for an embodiment of the present invention. DETAILED DESCRIPTION

[0053] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with specific embodiments.

[0054] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the present invention should be understood by people with ordinary skills in the field to which the present invention belongs. The words "first", "second" and similar words used in the present invention do not indicate any order, quantity or importance, but are only used to distinguish different components. "Include" or "comprise" and similar words mean that the elements or objects appearing before the word include the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connect" or "connected" and similar words are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0055] like Figure 1-Figure 2 As shown, a high-voltage circuit breaker remaining life intelligent assessment system includes:

[0056] Operation data acquisition module: collects the operation data of the high-voltage circuit breaker, including current data, voltage data, temperature data, and pressure data, and normalizes the collected high-voltage circuit breaker status data;

[0057] The degradation degree feature extraction module extracts the degradation degree features from the processed operation data, including the current fluctuation amplitude features and voltage frequency features, the temperature change rate, and the pressure abnormal fluctuation features;

[0058] Remaining life calculation module: Based on the degradation characteristics and the generalized regression neural network (GRNN) algorithm, a remaining life prediction model is constructed. Combined with the real-time updated working status, the status of the circuit breaker is evaluated and its remaining life is calculated;

[0059] Early warning and maintenance strategy module: Based on the remaining life calculation results, combined with the remaining life probability density function and expected loss rate of the circuit breaker, a predictive maintenance strategy for high-voltage circuit breakers is formulated to balance economy and reliability, provide operators with intelligent maintenance or replacement suggestions, and optimize maintenance cycles and operation strategies.

[0060] The operation data acquisition module arranges current sensors, voltage sensors, temperature sensors and pressure sensors (oil-immersed circuit breakers) on the key components of the high-voltage circuit breaker, collects the current data, voltage data, temperature data and pressure data of the circuit breaker under different working conditions in real time, normalizes the collected operation data, and transmits it to the degradation degree feature extraction module.

[0061] The degradation degree feature extraction module specifically includes:

[0062] The current fluctuation amplitude feature extraction unit is used to extract the fluctuation amplitude feature from the processed current data, including calculating the standard deviation σ of the current signal I , calculate the peak-to-peak difference ΔI of the current signal based on the sliding window peak , to evaluate the load fluctuation of the circuit breaker under different operating conditions;

[0063] A voltage fluctuation frequency feature extraction unit is used to extract frequency features from the processed voltage data, including analyzing the frequency spectrum in the voltage signal through Fourier transform, calculating the frequency distribution of the voltage signal and its power spectrum density, so as to evaluate the frequency component P(f) of the voltage fluctuation;

[0064] The temperature change rate feature extraction unit is used to extract the temperature change rate feature from the processed temperature data by calculating the change rate of the temperature signal per unit time. (such as first-order difference), analyze the thermal load changes of the circuit breaker under different working conditions;

[0065] The pressure abnormal fluctuation feature extraction unit is used to extract abnormal fluctuation features from the processed pressure data, and use abnormal fluctuation detection to identify abnormal fluctuations ΔP in the pressure data, so as to evaluate the leakage and pressure instability of the equipment.

[0066] The standard deviation of the current signal in the current fluctuation amplitude feature extraction unit is calculated as:

[0067] Among them, I i represents the current data at the i-th moment, represents the average value of current data, N is the total number of sampling data points; standard deviation σ IDescribes the fluctuation amplitude of the current signal. A large standard deviation indicates a large current fluctuation, indicating a load fluctuation or a fault in the equipment.

[0068] The peak-to-peak difference is calculated as: ΔI peak =I max -I min , where I max is the maximum value of the current signal, I min is the minimum value of the current signal, ΔI peak Measuring the maximum fluctuation range of the current signal can reflect the current impact during load changes or switching operations.

[0069] The Fourier transform analysis in the voltage fluctuation frequency feature extraction unit is expressed as:

[0070] Among them, x n is the voltage data at the nth moment, X(f) is the frequency domain component at frequency f, N is the number of sampling points, f is the frequency, and the Fourier transform converts the voltage signal from the time domain to the frequency domain to analyze its frequency components. The low-frequency components in the spectrum are usually related to steady-state voltage fluctuations, while the high-frequency components indicate transient faults or system instability;

[0071] The power spectral density is expressed as: P(f) = |X(f)| 2 , where P(f) is the power spectral density at frequency f, X(f) is the frequency domain component after Fourier transform, and the power spectral density (PSD) characterizes the frequency distribution of the voltage signal. Analyzing the power distribution of different frequency components helps to evaluate the stability of the equipment and the fluctuation of the electrical load.

[0072] In the temperature change rate feature extraction unit:

[0073] The rate of change is calculated as: Where T(t) represents the temperature data at time t, Δt is the time interval, usually the sampling period, and the temperature change rate Describes how quickly the temperature changes over time. A large rate of change usually indicates large temperature fluctuations, which are the result of changes in equipment load or poor heat dissipation.

[0074] Also includes cumulative temperature change calculation: Among them, T(t) is the temperature data at the tth moment, and N is the total number of sampling points.

[0075] The pressure abnormal fluctuation feature extraction unit includes the deviation detection method:

[0076] Among them, P i represents the pressure data at the i-th moment, represents the average value of pressure data, N is the total number of sampled data points, and the standard deviation of pressure σ P Indicates the amplitude of pressure fluctuation. If the pressure fluctuation is too large, it indicates gas leakage or unstable system pressure, which will affect the arc extinguishing performance of the circuit breaker.

[0077] Abnormal fluctuation detection is expressed as: Among them, α is the threshold coefficient, which is set to 3, indicating that the pressure data exceeding the range of 3 times the standard deviation is an abnormal fluctuation, P i is the pressure data at the i-th moment, is the average value of pressure data, σ P is the standard deviation of the pressure data.

[0078] The construction of the remaining life prediction model specifically includes:

[0079] Degradation feature input unit: Degradation degree features, including the standard deviation σ of the current signal I , the peak-to-peak difference of the current signal ΔP abnormal , the frequency component of voltage fluctuation P(f), the temperature change rate and the abnormal fluctuation ΔP in the pressure data as input, which is provided to the generalized regression neural network GRNN model for remaining life prediction;

[0080] Generalized regression neural network GRNN model: Based on the degradation degree characteristics, the remaining life prediction model is constructed through supervised learning method. The training process of the GRNN model includes the following:

[0081] Use historical data sets for training, which include actual working data of circuit breakers and corresponding remaining life data;

[0082] During training, according to the degraded features σ of the input I ,ΔI peak ,P(f), Mapping learning is performed between ΔP and the corresponding remaining life, and the weights and parameters in the GRNN model are adjusted so that the model can predict the remaining life of the circuit breaker under given feature inputs;

[0083] During the prediction process, the GRNN model outputs a remaining life value based on the input degradation characteristics, which represents the health status of the circuit breaker and the expected time of failure occurrence;

[0084] Real-time status update unit: obtains the current working status of the circuit breaker in real time, including current, voltage, temperature and pressure data, and uses the real-time degradation features calculated by the degradation feature extraction module as the input of the GRNN model to update the remaining life prediction;

[0085] The remaining life calculation unit calculates the remaining life under the current working state according to the output of the GRNN model, and provides an estimated value of the remaining life by comprehensively analyzing the health status of the circuit breaker.

[0086] The input of the generalized regression neural network GRNN model is the degradation feature, and the output is the remaining life R. The generalized regression neural network GRNN model processes the input features and the predicted output value is expressed as:

[0087] in, is the predicted value of the model, indicating the remaining life of the circuit breaker, N is the number of samples in the training data set, and M is the dimension of the input feature, which is 5 here (including σ I ,ΔI peak ,P(f), ΔP), is the feature vector of the i-th sample, y i is the true remaining life value corresponding to the i-th sample, σ is the width parameter of the Gaussian kernel function, which controls the smoothness of the model, and x ij is the jth feature of the i-th sample.

[0088] GRNN training process:

[0089] First, the degradation characteristics and the corresponding real remaining life data are prepared as training data sets;

[0090] Calculate the Gaussian kernel function: For each sample, calculate the distance between the input feature and other samples in the training set, and use the Gaussian kernel function for weighting;

[0091] Model training: The model is trained using the least squares method to find the appropriate weights (by adjusting σ and other hyperparameters) to minimize the error between the predicted value and the true value.

[0092] Remaining life prediction: After the model is trained, the real-time circuit breaker status (including real-time current, temperature, pressure and other data) is used as input. The GRNN model will output a predicted remaining life value based on the learned pattern. This value represents the remaining effective working time of the current circuit breaker or the expected time before a fault occurs.

[0093] Real-time status update and life prediction: By periodically or continuously acquiring the real-time operating data of the circuit breaker (such as current, voltage, temperature, pressure, etc.), the feature extraction module will update the degradation feature value and input it into the trained GRNN model to generate the latest remaining life prediction value. This can monitor the health status of the circuit breaker in real time and provide support for subsequent maintenance decisions.

[0094] The early warning and maintenance strategy module specifically includes:

[0095] The remaining life probability density function generation unit generates the probability density function f of the remaining life of the high-voltage circuit breaker based on the remaining life calculation result. lifespan (t), represents the probability distribution of the remaining life of the circuit breaker at different time points t, and the probability density function f lifespan (t) By statistically analyzing historical data and combining it with the output of the prediction model, the maximum likelihood estimation method is used for fitting to obtain the probability distribution of the remaining life of the circuit breaker;

[0096] The expected loss rate calculation unit is based on the remaining life probability density function f of the high-voltage circuit breaker. lifespan (t) and maintenance cost, calculate the expected loss rate L exp , that is, the expected economic loss caused by equipment failure or untimely maintenance. The expected loss rate is calculated as:

[0097] Among them, t0 is the current time, T is the expected life span of the circuit breaker, C repair is the cost of each maintenance, R(t) is the frequency or probability of maintenance or replacement at time point t, C failure is the repair cost after the failure occurs, P failure (t) is the probability of the circuit breaker failing at time t;

[0098] Maintenance strategy optimization unit, based on the expected loss rate L exp , combined with the remaining life probability density function f lifespan (t), formulate a predictive maintenance strategy for high-voltage circuit breakers. The predictive maintenance strategy balances economy and reliability by optimizing the objective function:

[0099] min τ (L exp (τ))subject toP failure (τ)≤, where τ represents the choice of maintenance timing (such as the time threshold for delayed maintenance), L exp (τ) is the expected loss rate at maintenance time τ, P failure (τ) represents the probability of circuit breaker failure at maintenance opportunity τ, which is an acceptable failure risk threshold (e.g., a certain maximum failure probability);

[0100] It also includes an intelligent maintenance decision-making unit, which optimizes the optimal maintenance timing output by the maintenance strategy optimization unit τ opt , providing operators with intelligent maintenance or replacement suggestions and guiding actual maintenance cycles and operating strategies.

[0101] Those skilled in the art should understand that the discussion of any of the above embodiments is merely illustrative and is not intended to imply that the scope of the present invention is limited to these examples. Under the concept of the present invention, the technical features in the above embodiments or different embodiments may be combined, the steps may be implemented in any order, and there are many other variations of the different aspects of the present invention as described above, which are not provided in detail for the sake of simplicity.

[0102] The present invention is intended to cover all such substitutions, modifications and variations that fall within the broad scope of the claims. Therefore, any omissions, modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A high-voltage circuit breaker remaining life intelligent assessment system, characterized in that: include: Operation data acquisition module: collects the operation data of the high-voltage circuit breaker, including current data, voltage data, temperature data, and pressure data, and normalizes the collected high-voltage circuit breaker status data; The degradation degree feature extraction module extracts the degradation degree features from the processed operation data, including the current fluctuation amplitude features and voltage frequency features, the temperature change rate, and the pressure abnormal fluctuation features; Remaining life calculation module: Based on the degradation characteristics and the generalized regression neural network algorithm, a remaining life prediction model is constructed. Combined with the real-time updated working status, the status of the circuit breaker is evaluated and its remaining life is calculated. Early warning and maintenance strategy module: Based on the remaining life calculation results, combined with the remaining life probability density function and expected loss rate of the circuit breaker, a predictive maintenance strategy for high-voltage circuit breakers is formulated to balance economy and reliability.

2. A high-voltage circuit breaker remaining life intelligent assessment system according to claim 1, characterized in that: The operation data acquisition module arranges current sensors, voltage sensors, temperature sensors and pressure sensors on key components of the high-voltage circuit breaker, collects current data, voltage data, temperature data and pressure data of the circuit breaker under different working conditions in real time, normalizes the collected operation data, and transmits them to the degradation degree feature extraction module.

3. A high-voltage circuit breaker remaining life intelligent assessment system according to claim 1, characterized in that: The degradation degree feature extraction module specifically includes: The current fluctuation amplitude feature extraction unit is used to extract the fluctuation amplitude feature from the processed current data, including calculating the standard deviation σ of the current signal I , calculate the peak-to-peak difference ΔI of the current signal based on the sliding window peak , to evaluate the load fluctuation of the circuit breaker under different operating conditions; A voltage fluctuation frequency feature extraction unit is used to extract frequency features from the processed voltage data, including analyzing the frequency spectrum in the voltage signal through Fourier transform, calculating the frequency distribution of the voltage signal and its power spectrum density, so as to evaluate the frequency component P(f) of the voltage fluctuation; The temperature change rate feature extraction unit is used to extract the temperature change rate feature from the processed temperature data by calculating the change rate of the temperature signal per unit time. Analyze the thermal load changes of circuit breakers under different working conditions; The pressure abnormal fluctuation feature extraction unit is used to extract abnormal fluctuation features from the processed pressure data, and use abnormal fluctuation detection to identify abnormal fluctuations ΔP in the pressure data, so as to evaluate the leakage and pressure instability of the equipment.

4. A high-voltage circuit breaker remaining life intelligent assessment system according to claim 3, characterized in that: The standard deviation of the current signal in the current fluctuation amplitude feature extraction unit is calculated as: Among them, I i represents the current data at the i-th moment, represents the average value of current data, N is the total number of sampling data points; standard deviation σ I Describes the fluctuation amplitude of the current signal. A large standard deviation indicates a large current fluctuation, indicating a load fluctuation or a fault in the equipment. The peak-to-peak difference is calculated as: ΔI peak =I max -I min , where I max is the maximum value of the current signal, I min is the minimum value of the current signal, ΔI peak Measures the maximum fluctuation range of the current signal.

5. A high-voltage circuit breaker remaining life intelligent assessment system according to claim 4, characterized in that: The Fourier transform analysis in the voltage fluctuation frequency feature extraction unit is expressed as: Among them, x n is the voltage data at the nth moment, X(f) is the frequency domain component at frequency f, N is the number of sampling points, f is the frequency, and Fourier transform converts the voltage signal from the time domain to the frequency domain to analyze its frequency components; The power spectral density is expressed as: P(f)=|X(f)| 2 , where P(f) is the power spectral density at frequency f, and X(f) is the frequency domain component after Fourier transform.

6. A high-voltage circuit breaker remaining life intelligent assessment system according to claim 5, characterized in that: In the temperature change rate feature extraction unit: The rate of change is calculated as: Where T(t) represents the temperature data at time t, Δt is the time interval, usually the sampling period, and the temperature change rate Describes how quickly temperature changes over time.

7. A high-voltage circuit breaker remaining life intelligent assessment system according to claim 6, characterized in that: The abnormal pressure fluctuation feature extraction unit includes a deviation detection method: Among them, P i represents the pressure data at the i-th moment, represents the average value of pressure data, N is the total number of sampled data points, and the standard deviation of pressure σ P Indicates the amplitude of pressure fluctuation; The abnormal fluctuation detection is expressed as: Among them, α is the threshold coefficient, P i is the pressure data at the i-th moment, is the average value of pressure data, σ P is the standard deviation of the pressure data.

8. The intelligent evaluation system for the remaining life of a high-voltage circuit breaker according to claim 7, characterized in that: The construction of the remaining life prediction model specifically includes: Degradation feature input unit: The degradation degree features, including the standard deviation σ of the current signal I , the peak-to-peak difference of the current signal ΔP abnormal , the frequency component of voltage fluctuation P(f), the temperature change rate and the abnormal fluctuation ΔP in the pressure data as input, which is provided to the generalized regression neural network GRNN model for remaining life prediction; Generalized regression neural network GRNN model: Based on the degradation degree characteristics, a remaining life prediction model is constructed through a supervised learning method. The training process of the GRNN model includes the following: Use historical data sets for training, which include actual working data of circuit breakers and corresponding remaining life data; During training, according to the degraded features σ of the input I ,ΔI peak ,P(f), Mapping learning is performed between ΔP and the corresponding remaining life, and the weights and parameters in the GRNN model are adjusted so that the model can predict the remaining life of the circuit breaker under given feature inputs; During the prediction process, the GRNN model outputs a remaining life value based on the input degradation characteristics, which represents the health status of the circuit breaker and the expected time of failure occurrence; Real-time status update unit: obtains the current working status of the circuit breaker in real time, including current, voltage, temperature and pressure data, and uses the real-time degradation features calculated by the degradation feature extraction module as the input of the GRNN model to update the remaining life prediction; The remaining life calculation unit calculates the remaining life under the current working state according to the output of the GRNN model, and provides an estimated value of the remaining life by comprehensively analyzing the health status of the circuit breaker.

9. A high-voltage circuit breaker remaining life intelligent assessment system according to claim 8, characterized in that: The input of the generalized regression neural network GRNN model is the degradation feature, and the output is the remaining life R. The generalized regression neural network GRNN model processes the input feature, and the predicted output value is expressed as: in, is the predicted value of the model, indicating the remaining life of the circuit breaker, N is the number of samples in the training data set, M is the dimension of the input feature, is the feature vector of the i-th sample, y i is the true remaining life value corresponding to the i-th sample, σ is the width parameter of the Gaussian kernel function, which controls the smoothness of the model, and x ij is the jth feature of the i-th sample.

10. A high-voltage circuit breaker remaining life intelligent assessment system according to claim 9, characterized in that: The early warning and maintenance strategy module specifically includes: A remaining life probability density function generating unit generates a probability density function f of the remaining life of the high-voltage circuit breaker based on the remaining life calculation result. lifespan (t), represents the probability distribution of the remaining life of the circuit breaker at different time points t, and the probability density function f lifespan (t) By statistically analyzing historical data and combining it with the output of the prediction model, the maximum likelihood estimation method is used for fitting to obtain the probability distribution of the remaining life of the circuit breaker; The expected loss rate calculation unit is based on the remaining life probability density function f of the high-voltage circuit breaker. lifespan (t) and maintenance cost, calculate the expected loss rate L exp , that is, the expected economic loss caused by equipment failure or untimely maintenance. The expected loss rate is calculated as: Among them, t0 is the current time, T is the expected life span of the circuit breaker, C repair is the cost of each maintenance, R(t) is the frequency or probability of maintenance or replacement at time point t, C failure is the repair cost after the failure occurs, P failure (t) is the probability of the circuit breaker failing at time t; Maintenance strategy optimization unit, based on the expected loss rate L exp , combined with the remaining life probability density function f lifespan (t), formulate a predictive maintenance strategy for high-voltage circuit breakers. The predictive maintenance strategy balances economy and reliability by optimizing the objective function: min τ (L exp (τ))subject toP failure (τ)≤, where τ represents the choice of maintenance timing, L exp (τ) is the expected loss rate at maintenance time τ, P failure (τ) represents the probability of circuit breaker failure at maintenance opportunity τ, which is the acceptable failure risk threshold.

Images