A machine learning based circuit breaker life prediction system

Abstract

The application relates to the technical field of a circuit breaker life prediction system, in particular to a circuit breaker life prediction system based on machine learning, which comprises a circuit breaker body analysis module, an environment analysis module, a control module, a performance judgment module and a communication module; the circuit breaker body analysis module is used for analyzing and obtaining relevant information of a circuit breaker body; the environment analysis module is used for analyzing and obtaining relevant information of an environment; the control module obtains a real-time health index of the circuit breaker according to the relevant information of the circuit breaker body and the relevant information of the environment; the performance judgment module obtains information that the performance of the circuit breaker is good or poor according to the real-time health index of the circuit breaker, and transmits the information that the performance of the circuit breaker is good or poor to the communication module; and the communication module transmits the information that the performance of the circuit breaker is good or poor to a user end. The above-mentioned implementation comprehensively monitors the running state of the circuit breaker, provides accurate data basis for subsequent health assessment, and has high practicability.

Description

Technical Field

[0001] This invention relates to the technical field of circuit breaker life prediction systems, and more specifically to a circuit breaker life prediction system based on machine learning. Background Technology

[0002] Circuit breakers are "smart insurance" in power systems. They can both switch circuits on and off and automatically cut off power for protection, making them a core component of electrical safety.

[0003] Application document CN116413589A discloses a method and device for predicting the electrical life of a circuit breaker. The method includes the following steps: Step S1: Simulating the arc-contact coupling ablation model using simulation software to obtain a correlation dataset between contact parameters and contact ablation thickness; Step S2: Conducting an electrical life test on the circuit breaker to obtain a correlation dataset between contact ablation thickness and the remaining life of the circuit breaker; Step S3: Performing machine learning training based on the correlation dataset between contact parameters and contact ablation thickness obtained in Step S1 and the correlation dataset between ablation thickness and remaining life of the circuit breaker obtained in Step S2 to obtain an electrical life prediction model between contact parameters and the remaining life of the circuit breaker; Step S4: Inputting the contact parameters of the circuit breaker to be tested into the trained electrical life prediction model to obtain the remaining life of the circuit breaker to be tested; The device executes a computer program to implement the above method.

[0004] Existing technologies lack a complete closed loop of status assessment, performance evaluation, and user feedback, resulting in poor overall usability. Summary of the Invention

[0005] The purpose of this invention is to address the aforementioned shortcomings by proposing a circuit breaker life prediction system based on machine learning.

[0006] The present invention adopts the following technical solution:

[0007] A machine learning-based circuit breaker life prediction system includes a circuit breaker body analysis module, an environmental analysis module, a control module, a performance judgment module, and a communication module. The circuit breaker body analysis module analyzes and derives relevant information about the circuit breaker body and transmits it to the control module. The environmental analysis module analyzes and derives relevant environmental information and transmits it to the control module. The control module derives a real-time health index for the circuit breaker based on the relevant information about the circuit breaker body and the environmental information, and transmits the real-time health index to the performance judgment module. The performance judgment module determines whether the circuit breaker's performance is good or poor based on the real-time health index and transmits this information to the communication module. The communication module transmits the good or poor performance information to the user terminal.

[0008] Optionally, the circuit breaker body analysis module is used to analyze and obtain rated current, rated service life, maximum allowable wear, rated temperature rise, calculation time interval, real-time operating current, real-time cumulative operating time, real-time contact wear, and real-time internal temperature rise, and transmits these data to the control module; the environmental analysis module is used to analyze and obtain real-time ambient humidity, real-time dust concentration, rated allowable humidity, and rated allowable dust concentration, and transmit these data to the control module; the control module derives the real-time environmental stress influence factor based on the real-time ambient humidity, real-time dust concentration, rated allowable humidity, and rated allowable dust concentration, and derives the real-time basic health index and the previous moment's basic health index based on the rated current, rated service life, maximum allowable wear, rated temperature rise, real-time operating current, real-time cumulative operating time, real-time contact wear, and real-time internal temperature rise; and derives the circuit breaker's real-time health index based on the real-time basic health index, the previous moment's basic health index, the calculation time interval, and the real-time environmental stress influence factor.

[0009] Optionally, the circuit breaker body analysis module includes an information setting submodule and a real-time detection submodule; the information setting submodule is used to set the calculation time interval, rated current, rated operating life, maximum allowable wear, and rated temperature rise, and transmit them to the control module; the real-time detection submodule is used to detect and obtain the real-time operating current, real-time cumulative operating time, real-time contact wear, and real-time internal temperature rise, and transmit them to the control module.

[0010] Optionally, the real-time detection submodule includes a current detection unit, a time detection unit, a wear detection unit, and a temperature detection unit; the current detection unit is used to detect and obtain the real-time operating current and transmit it to the control module; the time detection unit is used to detect and obtain the real-time cumulative running time and transmit it to the control module; the wear detection unit is used to detect and obtain the real-time contact wear amount and transmit it to the control module; the temperature detection unit is used to detect and obtain the real-time internal temperature rise and transmit it to the control module.

[0011] Optionally, the temperature detection unit includes an internal temperature detector, an external temperature detector, and a calculator; the internal temperature detector is used to detect and obtain the real-time internal temperature of the circuit breaker and transmit it to the calculator; the external temperature detector is used to detect and obtain the real-time ambient temperature and transmit it to the calculator; the calculator calculates the real-time internal temperature rise based on the real-time internal temperature of the circuit breaker and the real-time ambient temperature and transmits it to the control module.

[0012] Optionally, the environmental analysis module includes a humidity detection submodule, a dust detection submodule, and a rated value setting submodule; the humidity detection submodule is used to detect and obtain the real-time ambient humidity and transmit it to the control module; the dust detection submodule is used to detect and obtain the real-time dust concentration and transmit it to the control module; the rated value setting submodule is used to set the rated allowable humidity and the rated allowable dust concentration and transmit them to the control module.

[0013] Optionally, when calculating the real-time health index of the circuit breaker, the control module satisfies the following formula:

[0014] ;

[0015] in, This refers to the real-time health index of the circuit breaker. For real-time basic health index, The baseline health index at the previous moment. To calculate the time interval, This represents the real-time environmental stress influence factor.

[0016] The beneficial effects achieved by this invention are:

[0017] 1. This invention, by setting up a circuit breaker body analysis module, can collect and analyze key operating parameters of the circuit breaker in real time (including operating current, cumulative operating time, contact wear, temperature rise, etc.), realize comprehensive monitoring of the circuit breaker's operating status, provide an accurate data foundation for subsequent health assessment, and has strong practicality.

[0018] 2. By setting up an environmental analysis module, real-time monitoring of external environmental stresses such as humidity and dust concentration is realized, which makes up for the deficiency of ignoring the impact of environmental factors on circuit breaker life in the existing technology, and improves the accuracy of life prediction and the adaptability of the model.

[0019] 3. By setting up a control module, integrating circuit breaker body data and environmental data, and outputting the real-time health index of the circuit breaker based on the health index calculation model, this index can dynamically reflect the operating status of the equipment and has stronger real-time performance and intelligence compared with the traditional fixed threshold judgment method.

[0020] 4. A performance judgment module is set up, which can evaluate the current performance status of the circuit breaker based on the health index, realize the intelligent identification of information such as "good status / poor status", and provide a basis for fault warning and maintenance decision-making.

[0021] 5. A communication module is set up to transmit the analysis results to the user terminal in real time, realizing a closed loop of information from collection, calculation, evaluation to alarm push, improving the timeliness and response efficiency of operation and maintenance, and is suitable for remote monitoring and intelligent management scenarios.

[0022] To further understand the features and technical content of the present invention, please refer to the following detailed description and drawings of the present invention. However, the drawings provided are for reference and illustration only and are not intended to limit the present invention. Attached Figure Description

[0023] Figure 1 This is a schematic diagram of the overall structure of the present invention;

[0024] Figure 2 This is a schematic diagram of the temperature detection unit in this invention;

[0025] Figure 3 This is a schematic diagram of the real-time detection submodule in this invention;

[0026] Figure 4 This is a diagram illustrating the effect of the real-time environmental stress influence factor of this invention.

[0027] Figure 5 This is a schematic diagram of the overall structure of Embodiment 2 of the present invention;

[0028] Figure 6 This is a diagram illustrating the effect of the real-time remaining life of the circuit breaker in Embodiment 2 of the present invention. Detailed Implementation

[0029] The following specific embodiments illustrate the implementation of the present invention. Those skilled in the art can understand the advantages and effects of the present invention from the content disclosed in this specification. The present invention can be implemented or applied through other different specific embodiments, and various details in this specification can also be modified and changed based on different viewpoints and applications without departing from the spirit of the present invention. Furthermore, the accompanying drawings of the present invention are for simple illustrative purposes only and are not depictions of actual dimensions; this is stated in advance. The following embodiments will further describe the relevant technical content of the present invention in detail, but the disclosed content is not intended to limit the scope of protection of the present invention.

[0030] Example 1: This example provides a circuit breaker life prediction system based on machine learning, combined with... Figures 1 to 4 As shown.

[0031] A machine learning-based circuit breaker life prediction system includes a circuit breaker body analysis module, an environmental analysis module, a control module, a performance judgment module, and a communication module. The circuit breaker body analysis module analyzes and derives relevant information about the circuit breaker body and transmits it to the control module. The environmental analysis module analyzes and derives relevant environmental information and transmits it to the control module. The control module derives a real-time health index for the circuit breaker based on the relevant information about the circuit breaker body and the environmental information, and transmits the real-time health index to the performance judgment module. The performance judgment module determines whether the circuit breaker's performance is good or poor based on the real-time health index and transmits this information to the communication module. The communication module transmits the good or poor performance information to the user terminal.

[0032] Specifically, the performance judgment module refers to the following principles when making judgments: when the real-time health index of the circuit breaker is greater than or equal to the selection threshold of the real-time health index of the circuit breaker, it indicates that the circuit breaker performance is good; when the real-time health index of the circuit breaker is less than the selection threshold of the real-time health index of the circuit breaker, it indicates that the circuit breaker performance is poor. The selection threshold of the real-time health index of the circuit breaker is set by those skilled in the art. In this embodiment, the selection threshold of the real-time health index of the circuit breaker is set to 0.7. The value of "0.7" is obtained by collecting historical monitoring data of the equipment (the real-time health index of the circuit breaker measured each time, the fault type, and whether a fault occurred), and then dividing all the data according to the health status. For example, the real-time health index of the circuit breaker is divided into several segments (such as 0.9~1, 0.8~0.9, 0.7~0.8, ..., 0~0.1), and then the fault rate (number of faults / total number of faults) in each segment is calculated. By plotting a curve (horizontal axis: real-time health index of the circuit breaker, from 1 to 0; vertical axis: fault rate %), an inflection point is found at the value of 0.7.

[0033] Further, the real-time health index of circuit breakers can be categorized. For example, when the real-time health index is less than 0.5, it indicates severe degradation of the circuit breaker, posing significant safety hazards, and should be prioritized for repair or replacement; this is considered high-risk equipment. When the real-time health index is greater than or equal to 0.5 but less than 0.7, it indicates moderate aging of the circuit breaker, posing some risks, requiring early warning, and mid-term maintenance or replacement is recommended. When the real-time health index is greater than or equal to 0.7 but less than 0.9, it indicates mild aging of the circuit breaker, with equipment performance beginning to decline but still capable of normal operation; planned maintenance is recommended. When the real-time health index is greater than or equal to 0.9, it indicates good health of the circuit breaker, which is in near-new condition, with all parameters within safe ranges and environmental impact acceptable.

[0034] The control module integrates a machine learning prediction model to intelligently assess the current state of the circuit breaker based on relevant information about the circuit breaker itself and the environment. The machine learning prediction model receives relevant information about the circuit breaker and the environment as input feature variables and outputs a real-time health index of the circuit breaker based on these input features. The machine learning prediction model can be a decision tree model, a random forest model, a support vector machine model, a neural network model, or other algorithmic models with nonlinear mapping and fitting capabilities to achieve high-precision intelligent prediction of the circuit breaker's state. In this embodiment, the machine learning prediction model is a random forest model, which consists of multiple decision trees and can perform nonlinear feature fitting and classification prediction of the circuit breaker's health state, achieving highly robust and accurate intelligent judgment of the circuit breaker's operating state.

[0035] Optionally, the circuit breaker body analysis module is used to analyze and obtain rated current, rated service life, maximum allowable wear, rated temperature rise, calculation time interval, real-time operating current, real-time cumulative operating time, real-time contact wear, and real-time internal temperature rise, and transmits these data to the control module; the environmental analysis module is used to analyze and obtain real-time ambient humidity, real-time dust concentration, rated allowable humidity, and rated allowable dust concentration, and transmit these data to the control module; the control module derives the real-time environmental stress influence factor based on the real-time ambient humidity, real-time dust concentration, rated allowable humidity, and rated allowable dust concentration, and derives the real-time basic health index and the previous moment's basic health index based on the rated current, rated service life, maximum allowable wear, rated temperature rise, real-time operating current, real-time cumulative operating time, real-time contact wear, and real-time internal temperature rise; and derives the circuit breaker's real-time health index based on the real-time basic health index, the previous moment's basic health index, the calculation time interval, and the real-time environmental stress influence factor.

[0036] Optionally, the circuit breaker body analysis module includes an information setting submodule and a real-time detection submodule; the information setting submodule is used to set the calculation time interval, rated current, rated operating life, maximum allowable wear, and rated temperature rise, and transmit them to the control module; the real-time detection submodule is used to detect and obtain the real-time operating current, real-time cumulative operating time, real-time contact wear, and real-time internal temperature rise, and transmit them to the control module.

[0037] Optionally, the real-time detection submodule includes a current detection unit, a time detection unit, a wear detection unit, and a temperature detection unit; the current detection unit is used to detect and obtain the real-time operating current and transmit it to the control module; the time detection unit is used to detect and obtain the real-time cumulative running time and transmit it to the control module; the wear detection unit is used to detect and obtain the real-time contact wear amount and transmit it to the control module; the temperature detection unit is used to detect and obtain the real-time internal temperature rise and transmit it to the control module.

[0038] Optionally, the temperature detection unit includes an internal temperature detector, an external temperature detector, and a calculator; the internal temperature detector detects and obtains the real-time internal temperature of the circuit breaker and transmits it to the calculator; the external temperature detector detects and obtains the real-time ambient temperature and transmits it to the calculator; the calculator calculates the real-time internal temperature rise based on the real-time internal temperature of the circuit breaker and the real-time ambient temperature and transmits it to the control module. High temperatures can cause the insulating materials (such as plastics and rubber) inside the circuit breaker to gradually harden, become brittle, or decompose, reducing their insulation performance.

[0039] Optionally, the environmental analysis module includes a humidity detection submodule, a dust detection submodule, and a rated value setting submodule; the humidity detection submodule is used to detect and obtain the real-time ambient humidity and transmit it to the control module; the dust detection submodule is used to detect and obtain the real-time dust concentration and transmit it to the control module; the rated value setting submodule is used to set the rated allowable humidity and the rated allowable dust concentration and transmit them to the control module.

[0040] Optionally, when calculating the real-time health index of the circuit breaker, the control module satisfies the following formula:

[0041] ;

[0042] in, This refers to the real-time health index of the circuit breaker. For real-time basic health index, The baseline health index at the previous moment. To calculate the time interval, This represents the real-time environmental stress influence factor. The 0.1 in the formula is set to avoid negative values ​​for the health index and is based on the minimum acceptable condition of the equipment.

[0043] Optionally, the control module may perform calculations that satisfy the following formula:

[0044] ;

[0045] ;

[0046] in, For real-time operating current, Rated current, To accumulate running time in real time, For rated operating life, This represents the real-time contact wear. For the maximum allowable wear, For real-time internal temperature rise, Rated temperature rise;

[0047] For real-time ambient humidity, The rated allowable humidity, Real-time dust concentration, This refers to the rated permissible dust concentration.

[0048] When calculating the real-time health index of a circuit breaker, you can refer to the following program code:

[0049] import numpy as np

[0050] # √ Environmental stress factor S_env(t)

[0051] def calc_S_env(H_t, H_rated, D_t, D_rated):

[0052] """

[0053] Calculate the environmental stress factor S_env(t)

[0054] Parameters:

[0055] - H_t: real-time ambient humidity

[0056] - H_rated: rated humidity

[0057] - D_t: real-time dust concentration

[0058] - D_rated: rated dust concentration

[0059] Returns:

[0060] - S_env(t): environmental stress factor

[0061] """

[0062] return 0.5 * (H_t / H_rated)**2 + 0.5 * (D_t / D_rated)**2

[0063] # √ Base health index HI_base(t)

[0064] def calc_HI_base(I_oper, I_rated, t_oper, t_rated, V_wear, V_max, T_temp, T_rated):

[0065] """

[0066] Calculate the base health index HI_base(t)

[0067] Parameters:

[0068] - I_oper: real-time operating current

[0069] - I_rated: rated current

[0070] - t_oper: accumulated operating time

[0071] - t_rated: rated service life

[0072] - V_wear: real-time contact wear

[0073] - V_max: maximum allowable wear

[0074] - T_temp: real-time internal temperature rise

[0075] - T_rated: rated temperature rise

[0076] Returns:

[0077] - HI_base(t): base health index

[0078] """

[0079] exponent = -0.8 * (

[0080] 0.35 * (I_oper / I_rated)**2 +

[0081] 0.25 * (t_oper / t_rated)**2 +

[0082] 0.2 * (V_wear / V_max)**2 +

[0083] 0.2 * (T_temp / T_rated)**2 )

[0085] return np.exp(exponent)

[0086] # √ Real-time health index HI(t)

[0087] def calc_HI(HI_base_t, HI_base_t_prev, dt, S_env_t):

[0088] """

[0089] Calculate the real-time health index HI(t)

[0090] Parameters:

[0091] - HI_base_t: current base health index

[0092] - HI_base_t_prev: previous base health index

[0093] - dt: time interval between current and previous step

[0094] - S_env_t: environmental stress factor at time t

[0095] Returns:

[0096] - HI(t): real-time health index

[0097] """

[0098] derivative = (HI_base_t - HI_base_t_prev) / dt

[0099] HI_t = max(0.1, HI_base_t * (1 + 0.3 * derivative + 0.4 * S_env_t))

[0100] return HI_t

[0101] Specifically, the circuit breaker real-time health index can be understood as a comprehensive real-time health status assessment of the circuit breaker, used to guide operation and maintenance decisions. It refers to a dimensionless index that quantitatively assesses the current operating status of the circuit breaker at a certain time t by integrating multiple dimensions such as electrical parameters, mechanical wear, temperature rise, and environmental stress.

[0102] In the formula The constants involved are explained as follows: "1" can be understood as the base term, indicating that when there is no attenuation, the circuit breaker health index is directly equal to the baseline real-time base health index; "0.3" can be understood as the rate of change coefficient, which measures the proportion of the health index change rate in the overall health impact. A larger rate of change means that the equipment may be deteriorating at an accelerated rate. 0.3 indicates that the "health change rate" has a 30% weight in the total health impact; "0.4" can be understood as the environmental stress term weight, which measures the proportion of environmental factors (such as temperature, humidity, dust, etc.) in the health impact. 0.4 represents that environmental factors contribute 40% to the health impact, belonging to an additional load stress correction term. To verify the rationality of the two constants 0.3 and 0.4, this embodiment adopts a verification method based on sensitivity analysis. Combining typical equipment parameters, the comparative analysis of the contribution of influencing factors to the circuit breaker health index proves that the parameter settings meet the equipment deterioration mechanism and actual engineering application requirements. Sensitivity analysis is a common model verification method. Its basic idea is to adjust the value of a certain input factor while keeping other variables constant and observe the change range of the output result. By comparing the degree of output change caused by the adjustment of each factor, the relative importance of each factor is determined. The following are the verification steps: (1) Set a set of typical circuit breaker operating parameters and select It is 0.8. Take 0.10, We take 0.40. Substituting these parameters into the circuit breaker real-time health index calculation formula of this embodiment, we obtain the results. Based on these results, we then... and Perform individual perturbation adjustments, for example, first... Increase the baseline value by 10%, that is, adjust from 0.10 to 0.11, while maintaining... Keeping it unchanged, calculate the change in the real-time health index of the adjusted circuit breaker and observe the effect. Increased fluctuations in the real-time health index of the circuit breaker caused by the increase, followed by restoration of variable... To the baseline value of 0.10, Increase the baseline value by 10%, that is, adjust from 0.40 to 0.44, while maintaining... Recalculate the circuit breaker's real-time health index and observe. The sensitivity analysis results of the increase in the real-time health index of the circuit breaker under the above typical parameters show that... The change in the real-time health index of the circuit breaker caused by a 10% increase is approximately... The change brought about by a 10% increase is approximately five times greater, a result that intuitively reflects... The impact on the real-time health index of circuit breakers is more significant compared to... , Based on the analysis that environmental stress accounts for a higher contribution to health index assessment, this embodiment, in designing the health assessment model, reasonably sets the weight of the environmental stress term to be greater than that of the rate of change coefficient, to reflect the actual difference in their impact during the health decline process. This weight allocation not only conforms to the influence ranking relationship revealed by sensitivity analysis, but also takes into account the engineering operability and parameter adjustment flexibility of the model, making it suitable for application in online equipment monitoring and condition assessment scenarios. After obtaining the above results, it is necessary to verify the rationality of the specific numerical settings. For example, the rate of change coefficient can be set between 0.2 and 0.4, and the weight of the environmental stress term can be set between 0.3 and 0.5. Through the above range settings, multiple parameter combinations can be formed (e.g., 0.2 / 0.3, 0.2 / 0.35, 0.25 / 0.4, 0.3 / 0.4, 0.35 / 0.45, 0.4 / 0.5). The model was evaluated using a batch of circuit breaker devices with known degradation (or maintenance records) and different parameter combinations (e.g., 0.2 / 0.3, 0.2 / 0.35, 0.25 / 0.4, 0.3 / 0.4, 0.35 / 0.45, 0.4 / 0.5, etc.). The evaluation focused on whether the model could accurately identify degraded devices, whether it would falsely report healthy devices, and whether the health index stratification was clear. The results showed that when the rate of change coefficient was below 0.25 (e.g., 0.2) and the environmental stress term weight was above 0.45 (e.g., 0.45 or 0.5), the model lacked sensitivity to short-term performance changes, resulting in a decreased ability to identify devices in the accelerated degradation stage and an increased false negative rate. When the rate of change coefficient was above 0.35 (e.g., 0.4) or the environmental stress term weight was above 0.45 (e.g., 0.5), the model overreacted to the evaluation results of some healthy devices, especially regarding environmental stress fluctuations. When the degree is small, false alarms are easily generated, and the false detection rate increases significantly. When the coefficient of change is set to 0.3 and the weight of the environmental stress term is set to 0.4, the model performs best in various evaluation indicators. For example, the health index maintains good differentiation between different levels, the output results are stable, and it is not overly sensitive to small parameter perturbations. Therefore, the weight set of 0.3 / 0.4 is located in the middle of the range of the best recognition effect in multiple rounds of testing. It avoids the insufficient sensitivity caused by the coefficient of change being too low, and also prevents the over-response caused by the weight of the environmental stress term being too high. It is the configuration that achieves the optimal balance between "recognition sensitivity" and "evaluation stability".

[0103] In the formula The constants mentioned are explained below. "-0.8" can be understood as the attenuation rate, a factor used to adjust the rate of degradation. This form is closer to the aging mechanism of circuit breakers. In actual calculations, if this value is set to -1 or -2, the attenuation will be too rapid, leading to… If the value is set to -0.3 or -0.5, the decay is too slow and cannot reflect the health status of the circuit breaker. Therefore, the corresponding "-0.8" is an average decay rate that was adjusted after regression analysis of actual circuit breaker aging speed data, which can reflect the true decay trend of the equipment during its life cycle. The "0.35" in the figure can be understood as the current weighting coefficient. A high current load accelerates wear and is the most direct factor in degradation. The "0.2" in the figure can be understood as the runtime weighting coefficient. Time is an important dimension of degradation, but degradation is not only determined by time (it needs to work together with the load). The "0.25" in this context can be understood as a wear weighting coefficient. Wear directly reflects the condition of the mechanical structure and significantly affects contact life. The "0.2" in this context can be understood as a temperature weighting coefficient. Temperature rise is an accelerating aging factor, but it is usually environmental and its changes are relatively controllable. In summary, current load and wear are active degradation sources, which are direct factors, while time and temperature are passive or auxiliary degradation sources, which have a cumulative effect. In actual operation and maintenance, it has been found that circuit overload has a greater impact than wear, hence the corresponding current weighting coefficient has the largest value. The above combination data (0.35 / 0.2 / 0.25 / 0.2) is also obtained through sensitivity analysis. For example, multiple rounds of testing with different combinations (such as 0.2 / 0.3 / 0.3 / 0.2, 0.25 / 0.25 / 0.25 / 0.25, 0.35 / 0.15 / 0.3 / 0.2, etc.) are conducted to see which group is most effective in accurately identifying degraded equipment and distinguishing healthy equipment.

[0104] In the formula The constants involved are explained as follows, where The "0.5" in the text and The "0.5" in the figure can be understood as meaning that the deterioration intensity of humidity and dust is roughly equivalent, avoiding numerical bias during calculation. Regarding... and The square calculated in the middle is mainly controlled within a reasonable nonlinear amplification range to reflect the nonlinear acceleration characteristics of the degradation process and avoid the degradation rate being underestimated under linear estimation.

[0105] Real-time basic health index reflects the real-time basic operating status of equipment and is used for detailed analysis and diagnosis.

[0106] The calculation method for the basic health index at the previous moment is the same as that for the real-time basic health index.

[0107] Real-time environmental stress influence factor reflects the real-time impact of the environment, embodies the degree of influence of the external environment on stress, is more in line with actual operating conditions, and can truly reflect the impact of external conditions on equipment life. For example, excessive humidity can easily cause the insulation of equipment to become damp and age. In addition, dust will reduce insulation performance and accelerate wear.

[0108] The unit for calculating the time interval is seconds, which is set to 60 seconds in this embodiment.

[0109] Both real-time operating current and rated current are measured in amperes. Excessive real-time operating current will accelerate equipment aging, while rated current is the safe operating benchmark set by the manufacturer.

[0110] The units for real-time cumulative running time and rated operating life are both seconds. Real-time cumulative running time reflects the set running time. Long-term operation of equipment will cause aging accumulation. Rated operating life is the expected safe operating life specified by the equipment manufacturer.

[0111] The units for both real-time contact wear and maximum permissible wear are millimeters. The maximum permissible wear is the maximum wear limit specified in the manufacturer's safety specifications. The principle for obtaining real-time contact wear is as follows: the change in contact stroke is collected by a displacement sensor installed on the circuit breaker's closing and opening drive mechanism, and compared with the initial position for calculation, thereby achieving real-time non-contact detection during equipment operation.

[0112] The units for both real-time internal temperature rise and rated temperature rise are degrees Celsius. Rated temperature rise is the maximum temperature rise that the manufacturer specifies for safe operation. Real-time internal temperature rise is the increase in internal temperature relative to ambient temperature when the circuit breaker is in operation. It is used to reflect the heat generation and heat dissipation capacity of the equipment body due to factors such as current carrying, friction, and contact resistance.

[0113] Real-time ambient humidity and rated permissible humidity are both expressed as percentages.

[0114] The units for both real-time dust concentration and rated allowable dust concentration are milligrams per cubic meter.

[0115] The above units are just examples. Those skilled in the art can set different units according to actual needs when implementing this solution.

[0116] This embodiment solves the problem of low practicality of traditional life prediction systems. By setting up a circuit breaker body analysis module, this invention can collect and analyze key operating parameters of the circuit breaker in real time (including operating current, cumulative operating time, contact wear, temperature rise, etc.), realize comprehensive monitoring of the circuit breaker's operating status, and provide an accurate data foundation for subsequent health assessment, thus having strong practicality.

[0117] Example 2: This example includes all the content of Example 1, and provides a circuit breaker life prediction system based on machine learning, combined with... Figure 5 and Figure 6 As shown.

[0118] A machine learning-based circuit breaker life prediction system, which also includes a life storage module;

[0119] The lifespan storage module stores the rated lifespan of the circuit breaker and transmits it to the control module;

[0120] The control module calculates the real-time remaining life of the circuit breaker based on its rated life and real-time health index, and then transmits the real-time remaining life of the circuit breaker to the communication module.

[0121] The communication module transmits the circuit breaker's real-time remaining lifespan to the user terminal.

[0122] Optionally, when calculating the real-time remaining life of the circuit breaker, the control module satisfies the following formula:

[0123] ;

[0124] in, The real-time remaining life of the circuit breaker. This refers to the rated life of the circuit breaker.

[0125] When calculating the real-time remaining life of the circuit breaker, the control module should refer to the following program code:

[0126] import math

[0127] # -------------------------------

[0128] # Function 1: Calculate the basic health index HI_base(t)

[0129] # -------------------------------

[0130] def calculate_hi_base(I_oper, I_rated, t_oper, t_rated, V_wear, V_max, T_temp, T_rated,

[0131] gamma=0.8, w1=0.3, w2=0.2, w3=0.3, w4=0.2, n=2, m=2, p=2, q=2):

[0132] term1 = w1 * (I_oper / I_rated) ** n

[0133] term2 = w2 * (t_oper / t_rated) ** m

[0134] term3 = w3 * (V_wear / V_max) ** p

[0135] term4 = w4 * (T_temp / T_rated) ** q

[0136] HI_base = math.exp(-gamma * (term1 + term2 + term3 + term4))

[0137] return HI_base

[0138] # -------------------------------

[0139] # Function 2: Calculate the environmental stress factor S_env(t)

[0140] # -------------------------------

[0141] def calculate_s_env(H, H_rated, D, D_rated):

[0142] return 0.5 * (H / H_rated) ** 2 + 0.5 * (D / D_rated) ** 2

[0143] # -------------------------------

[0144] # Function 3: Calculate the real-time health index HI(t)

[0145] # -------------------------------

[0146] def calculate_hi(HI_base, HI_base_prev, delta_t, S_env, alpha=0.3, beta=0.4):

[0147] trend = (HI_base - HI_base_prev) / delta_t

[0148] return HI_base * (1 + alpha * trend + beta * S_env)

[0149] # -------------------------------

[0150] # Function 4: Calculate the remaining lifetime RUL(t)

[0151] # -------------------------------

[0152] def calculate_rul(HI, L_rated, delta=1.2, kappa=2.0):

[0153] return L_rated * (HI ** delta) * math.exp(-kappa * (1 - HI))

[0154] # -------------------------------

[0155] # Sample input data (can be replaced with real-time data)

[0156] # -------------------------------

[0157] input_data = {

[0158] 'I_oper': 80,

[0159] 'I_rated': 100,

[0160] 't_oper': 500000,

[0161] 't_rated': 1000000,

[0162] 'V_wear': 1.2,

[0163] 'V_max': 3.0,

[0164] 'T_temp': 60,

[0165] 'T_rated': 80,

[0166] 'H': 70,

[0167] 'H_rated': 85,

[0168] 'D': 0.2,

[0169] 'D_rated': 0.3,

[0170] 'HI_base_prev': 0.92,

[0171] 'delta_t': 60,

[0172] 'L_rated': 100000# Rated lifespan (unit can be hours or number of operations)

[0173] }

[0174] # -------------------------------

[0175] # Main process: Calculate HI and RUL

[0176] # -------------------------------

[0177] HI_base = calculate_hi_base(

[0178] input_data['I_oper'], input_data['I_rated'],

[0179] input_data['t_oper'], input_data['t_rated'],

[0180] input_data['V_wear'], input_data['V_max'],

[0181] input_data['T_temp'], input_data['T_rated'] )

[0183] S_env = calculate_s_env(input_data['H'], input_data['H_rated'],input_data['D'], input_data['D_rated'])

[0184] HI = calculate_hi(HI_base, input_data['HI_base_prev'], input_data['delta_t'], S_env)

[0185] RUL = calculate_rul(HI, input_data['L_rated'])

[0186] # -------------------------------

[0187] # Output Results

[0188] # -------------------------------

[0189] print(f"Basic Health Index HI_base(t): {HI_base:.4f}")

[0190] print(f"Environmental stress factor S_env(t): {S_env:.4f}")

[0191] print(f"Real-time health index HI(t): {HI:.4f}")

[0192] print(f"Real-time remaining lifetime RUL(t): {RUL:.2f}")

[0193] Specifically, the units for the real-time remaining life and the rated life of the circuit breaker are both hours. The rated life of the circuit breaker is the longest service life during which the circuit breaker can operate reliably under normal working conditions, according to the usage specifications and working environment set by the manufacturer.

[0194] In the formula The constants involved are explained as follows, for example, The control is a "non-linear amplification" of the linear impact of the circuit breaker's real-time health index on its lifespan. "1.2" indicates that it is slightly higher than the linear range, but not as aggressive as the square, which is in line with the actual law. The choice of "-2" is a balance point. If this coefficient is set to -1, the decay will be very smooth. If this coefficient is set to -3, the decay will be very fast. "in "The design logic is to invert the circuit breaker's real-time health index; the higher the real-time health index, the faster it will degrade. When..." When the value equals 1, it can be understood as perfectly healthy, and the exponent becomes... The real-time remaining life of a circuit breaker is equal to its rated life, which is understood as not decreasing. "in Replace with " The calculated result contradicts reality, therefore the formula "" is set. The value in the text is "1".

[0195] The above units are just examples. Those skilled in the art can set different units according to actual needs when implementing this solution.

[0196] This embodiment addresses the problem of traditional life prediction systems being relatively simple. The system introduces a life storage module, which can centrally manage and store the rated life information of circuit breakers for a long time, providing a reliable data foundation for calculating the remaining life and improving the accuracy and traceability of the system.

[0197] The content disclosed above is only a preferred and feasible embodiment of the present invention, and is not intended to limit the scope of protection of the present invention. Therefore, all equivalent technical changes made based on the content of the present invention specification and drawings are included within the scope of protection of the present invention. Furthermore, the elements therein can be updated as technology develops.

Claims

1. A circuit breaker life prediction system based on machine learning, characterized in that, The system includes a circuit breaker body analysis module, an environmental analysis module, a control module, a performance judgment module, and a communication module; The circuit breaker body analysis module is used to analyze and obtain the rated current, rated service life, maximum allowable wear, rated temperature rise, calculation time interval, real-time operating current, real-time cumulative operating time, real-time contact wear, and real-time internal temperature rise, and transmit them to the control module. The environmental analysis module is used to analyze and obtain real-time ambient humidity, real-time dust concentration, rated allowable humidity, and rated allowable dust concentration, and transmit them to the control module; The control module derives the real-time environmental stress influence factor based on real-time ambient humidity, real-time dust concentration, rated allowable humidity, and rated allowable dust concentration. It also derives the real-time basic health index and the previous basic health index based on rated current, rated operating life, maximum allowable wear, rated temperature rise, real-time operating current, real-time cumulative operating time, real-time contact wear, and real-time internal temperature rise. Finally, it derives the circuit breaker's real-time health index based on the real-time basic health index, the previous basic health index, the calculation time interval, and the real-time environmental stress influence factor, and transmits the circuit breaker's real-time health index to the performance judgment module. The performance judgment module determines whether the circuit breaker's performance is good or bad based on the circuit breaker's real-time health index, and transmits the information about the circuit breaker's performance to the communication module. The communication module transmits information about the circuit breaker's performance, whether it is good or bad, to the user terminal. The control module calculates the real-time health index of the circuit breaker according to the following formula: ； in, This refers to the real-time health index of the circuit breaker. For real-time basic health index, The baseline health index at the previous moment. To calculate the time interval, This represents the real-time environmental stress influence factor.

2. The circuit breaker life prediction system based on machine learning as described in claim 1, characterized in that, The circuit breaker body analysis module includes an information setting submodule and a real-time detection submodule; The information setting submodule is used to set the calculation time interval, rated current, rated operating life, maximum allowable wear, and rated temperature rise, and transmit them to the control module; The real-time detection submodule is used to detect and obtain real-time operating current, real-time cumulative running time, real-time contact wear, and real-time internal temperature rise, and transmit them to the control module.

3. The circuit breaker life prediction system based on machine learning as described in claim 2, characterized in that, The real-time detection submodule includes a current detection unit, a time detection unit, a wear detection unit, and a temperature detection unit; The current detection unit is used to detect and obtain the real-time operating current, and transmit it to the control module; The time detection unit is used to detect and obtain the real-time cumulative running time, and transmit it to the control module; The wear detection unit is used to detect and obtain the real-time wear amount of the contact, and transmit it to the control module; The temperature detection unit is used to detect and obtain the real-time internal temperature rise, and transmit it to the control module.

4. The circuit breaker life prediction system based on machine learning as described in claim 3, characterized in that, The temperature detection unit includes an internal temperature detector, an external temperature detector, and a calculator; The internal temperature detector is used to detect and obtain the real-time internal temperature of the circuit breaker and transmit it to the calculator; The external temperature detector is used to detect and obtain the real-time ambient temperature, and transmit it to the calculator; The calculator calculates the real-time internal temperature rise based on the real-time internal temperature of the circuit breaker and the real-time ambient temperature, and transmits the result to the control module.

5. The circuit breaker life prediction system based on machine learning as described in claim 1, characterized in that, The environmental analysis module includes a humidity detection submodule, a dust detection submodule, and a rated value setting submodule; The humidity detection submodule is used to detect and obtain the real-time ambient humidity and transmit it to the control module; The dust detection submodule is used to detect and obtain the real-time dust concentration, and transmit it to the control module; The rated value setting submodule is used to set the rated allowable humidity and rated allowable dust concentration, and transmit them to the control module.

Images