Artificial intelligence-based circuit breaker action characteristic detection system

Abstract

The application relates to the technical field of circuit breaker detection, and specifically discloses a circuit breaker action characteristic detection system based on artificial intelligence, which comprises a data acquisition layer, a data preprocessing layer, a data analysis layer, a decision warning layer and a system management layer; the data acquisition layer is responsible for collecting the action characteristic parameters of the circuit breaker. Through filtering, normalization and feature extraction, the data quality and availability are improved, laying a foundation for subsequent analysis; the data analysis layer uses comprehensive calculation and analysis to evaluate multidimensional parameters in mechanical action, obtains a mechanical action state evaluation coefficient, and accurately grasps the operation state of the circuit breaker; the decision warning layer accurately determines the operation state and timely warns according to the evaluation result and a threshold value, helping operation and maintenance personnel to quickly respond; and the system management layer is used for dynamically optimizing a feedback determination threshold value, so that the overall scheme effectively improves the accuracy, reliability and intelligent level of circuit breaker detection, reduces fault risks, and guarantees the safe and stable operation of a power system.

Description

Technical Field

[0001] This invention relates to the field of circuit breaker testing technology, specifically to a circuit breaker operating characteristic testing system based on artificial intelligence. Background Technology

[0002] In modern power systems, circuit breakers are crucial devices for ensuring the safe and stable transmission of electricity, and their reliable operation is of paramount importance. With the continuous expansion of power grids and their increasing intelligence, higher demands are placed on the accurate detection of circuit breaker operating characteristics and fault early warning. Accurately understanding the operating status of circuit breakers and promptly identifying potential faults can effectively prevent power accidents and ensure the continuity and stability of power supply; therefore, advanced and reliable detection technologies are urgently needed.

[0003] Traditional circuit breaker testing methods have relatively simple preprocessing techniques for raw data, making it difficult to effectively remove noise interference and unify the dimensions of different types of data. This affects the accuracy of subsequent analysis. Furthermore, the threshold settings of existing testing systems are usually fixed and cannot be dynamically adjusted according to changes in environmental parameters and equipment aging, which can easily lead to misjudgments or omissions and make it impossible to provide timely and accurate early warnings of circuit breaker failure risks. Summary of the Invention

[0004] In order to overcome the shortcomings of the prior art, the present invention provides an artificial intelligence-based circuit breaker operation characteristic detection system to address the aforementioned technical deficiencies.

[0005] To achieve the above objectives, the present invention provides the following technical solution: an artificial intelligence-based circuit breaker operating characteristic detection system, comprising: a data acquisition layer, a data preprocessing layer, a data analysis layer, a decision-making and early warning layer, and a system management layer; the data acquisition layer is responsible for acquiring the operating characteristic parameters of the circuit breaker; the data preprocessing layer is used to filter the acquired raw data to remove noise interference, normalize data of different types and dimensions, and finally extract key features from the processed data; the data analysis layer is used to comprehensively calculate and analyze the contact wear rate change rate and the opening and closing time change rate in the operating characteristic parameters to obtain the mechanical operating state evaluation coefficient; the decision-making and early warning layer evaluates the operating state of the circuit breaker based on the mechanical operating state evaluation coefficient combined with pre-set evaluation standards and thresholds, determines whether the circuit breaker is in a normal, warning, alert, or emergency state, and issues an early warning signal according to the corresponding state; the system management layer is used to configure various system parameters, dynamically optimize and provide feedback on the operating state judgment threshold, and store and manage the acquired raw data, processed data, and analysis results.

[0006] Furthermore, the method for comprehensively calculating and analyzing the change rate of contact wear rate and the change rate of opening and closing time in the action characteristic parameters to obtain the mechanical action state evaluation coefficient is as follows:

[0007] The preprocessed operating characteristic parameters are obtained from the data preprocessing layer, and the cumulative wear of the circuit breaker contacts at each detection moment in each detection cycle is extracted from the operating characteristic parameters and denoted as . Simultaneously, the time interval between two adjacent detection moments of the circuit breaker in each detection cycle is obtained and denoted as Δt;

[0008] Depend on The result divided by Δt yields the contact wear rate of the circuit breaker at each detection moment in each detection cycle, denoted as .

[0009] The average wear rate of the circuit breaker in each testing cycle is obtained by summing the contact wear rates at each testing moment and dividing by T. This average wear rate is denoted as T. Divide the squared deviations of the contact wear rate and average wear rate of the circuit breaker in each testing cycle by T to obtain the standard deviation of the wear rate of the circuit breaker in each testing cycle, denoted as T.

[0010] According to the formula The rate of change of contact wear rate of the circuit breaker at each detection time in each detection cycle was calculated. The rate of change of contact wear rate of the circuit breaker at each detection moment in each detection cycle was calculated. and average wear rate The difference is divided by the standard deviation of the wear rate. The normalized rate of change of contact wear rate of the circuit breaker at each detection time in each detection cycle is denoted as .

[0011] Furthermore, the duration of each opening and closing operation of the circuit breaker in each detection cycle is obtained from the system management layer and recorded as follows: and Simultaneously, the rated opening time and rated closing time of the circuit breaker design are obtained, and denoted as follows: and The average opening time and average closing time of the circuit breaker in each detection cycle are obtained using the mean value calculation formula, and are denoted as follows: and The average opening time and average closing time of the circuit breaker in each detection cycle are obtained using the standard deviation calculation formula, and are denoted as follows: and

[0012] According to the formula The rate of change of the circuit breaker's opening time in each detection cycle was calculated. According to the formula The rate of change of closing time of the circuit breaker in each detection cycle was calculated. Then, by normalizing the change rate of contact wear rate, the normalized change rates of opening and closing time of the circuit breaker in each detection cycle were calculated and denoted as follows: and

[0013] Furthermore, according to the formula The information entropy e of each index of the circuit breaker in each detection cycle is calculated. j ;

[0014] According to the formula The weighting index w of each indicator of the circuit breaker in each detection cycle is calculated. j ;

[0015] Based on the normalized indicators and the weighted indices of each indicator for the circuit breaker in each testing cycle, the mechanical operating condition evaluation coefficient JD of the circuit breaker in each testing cycle is calculated using a weighted summation method. z The specific calculation formula is as follows:

[0016] Furthermore, based on historical data statistical analysis, thresholds for low impact, medium impact, and high impact are pre-set. The specific threshold setting method is as follows: collect historical data of circuit breakers under different combinations of environmental parameters and operating conditions, and statistically analyze the parameter values ​​corresponding to normal fluctuations and faults or significant performance degradation. The comprehensive index corresponding to most normal operating data is used as the threshold for low impact; the comprehensive index when some minor fault signs begin to appear is determined as the threshold for medium impact; and the comprehensive index when a serious fault risk occurs is used as the threshold for high impact.

[0017] Furthermore, the system management layer is used to dynamically optimize the feedback judgment threshold. By dynamically adjusting the setting of the influence degree threshold, the judgment of the mechanical action fault detection result of the circuit breaker is made more accurate. The specific dynamic adjustment method is as follows:

[0018] Suppose that the circuit breaker has n environmental parameters, denoted as E. i Let i = 1, 2, ..., n, where i represents the number of each environmental parameter, and let V be the threshold value for the rate of change of each environmental parameter. i The cumulative change threshold is C. i Environmental parameters include, but are not limited to, temperature, humidity, and corrosive gas concentrations, which are acquired by detecting data through corresponding detection sensors installed on one side of the circuit breaker.

[0019] For each environmental parameter E i The rate of change over the time interval Δt is Define the rate of change exceeding the limit coefficient.

[0020] Each environmental parameter E i The difference between the current value and the initial value is taken as the cumulative change, denoted as ΔEc. i Define the coefficient for cumulative change exceeding the standard.

[0021] Define the overall exceedance coefficient of environmental parameters The value of R ranges from [0,1]. The closer R is to 1, the more severe the environmental parameter exceedance. Preset thresholds for moderate and low impact are obtained, denoted as SY. mid and SY low According to the formula ΔSY=(SY mid -SY low The threshold adjustment amount ΔSY is obtained by calculating ΔSY × R.

[0022] The adjusted moderate impact threshold SY mid ′=SY mid -ΔSY, the adjusted low-impact threshold SY low ′=SY low -ΔSY.

[0023] Furthermore, the circuit breaker's service life and design service life are obtained and denoted as Y and Y', respectively. max The number of operations and the expected maximum number of operations are denoted as N and Nmax, respectively. max α and β are weighting coefficients, and α + β = 1;

[0024] Obtain the preset threshold for high-level influence, denoted as SY. max According to the formula SY max ′=SY max -γ·I o The adjusted higher-level influence threshold SY was calculated. max ′, where γ represents the adjustment coefficient.

[0025] Furthermore, the decision-making and early warning layer calculates the mechanical action state evaluation coefficient JD of the circuit breaker in each detection cycle. z The impact of mechanical action faults of the circuit breaker in each detection cycle is determined by comparing the results with the set impact threshold. The specific comparison and analysis method is as follows:

[0026] 0 <JD z ≤SY lowIf the circuit breaker is deemed to be in normal mechanical operation status during the detection cycle, the green warning light indicating normal mechanical operation status will remain on.

[0027] If the mechanical operation status of the circuit breaker in this detection cycle is assessed as "caution", a corresponding text warning will be issued through a system pop-up reminder, and the green warning light indicating normal mechanical operation status will be changed to a blue warning light indicating "caution" status.

[0028] If the mechanical operation status of the circuit breaker in this detection cycle is assessed as a warning, a corresponding text warning will be issued through a system pop-up reminder, and the blue warning light indicating the mechanical operation status will be changed to a yellow warning light indicating the warning status.

[0029] If the mechanical operation status of the circuit breaker in this detection cycle is assessed as emergency, a corresponding text warning will be issued through a system pop-up reminder, and the yellow warning light indicating the mechanical operation status will be changed to a red warning light indicating an emergency.

[0030] The beneficial effects of this invention are:

[0031] 1. In this invention, the data acquisition layer comprehensively collects action characteristic parameters to ensure complete information on circuit breaker operation; the data preprocessing layer improves data quality and usability through filtering, normalization, and feature extraction, laying the foundation for subsequent analysis; the data analysis layer uses comprehensive calculation and analysis to evaluate multi-dimensional parameters in mechanical actions, obtaining mechanical action state evaluation coefficients to accurately grasp the circuit breaker's operating status; the decision-making and early warning layer accurately determines the operating status and provides timely warnings based on the evaluation results and thresholds, assisting maintenance personnel in rapid response; the system management layer is used to dynamically optimize feedback judgment thresholds, store and manage various types of data, ensure flexible and stable system operation, and facilitate data query and traceability. The overall solution effectively improves the accuracy, reliability, and intelligence level of circuit breaker detection, reduces fault risks, and ensures the safe and stable operation of the power system.

[0032] 2. This invention comprehensively analyzes the mechanical action characteristics of circuit breakers from dimensions such as contact wear and opening / closing time. It uses laser displacement sensors and vibration sensors to accurately collect data, and processes it through normalization, information entropy, and weight calculation to obtain mechanical action status evaluation coefficients, making the evaluation more scientific and accurate. By setting thresholds based on historical data, the circuit breaker status can be clearly judged based on the evaluation coefficients. This helps operation and maintenance personnel to grasp the overall status of circuit breakers in a timely manner, discover potential fault risks in advance, rationally arrange maintenance, reduce the probability of fault occurrence, ensure the stable operation of the power system, and improve the intelligence and refinement of equipment management.

[0033] 3. This invention significantly improves the accuracy of circuit breaker mechanical action fault detection by dynamically adjusting the judgment threshold. On the one hand, for environmental parameters, a comprehensive exceeding coefficient R is obtained by calculating the exceeding coefficient of the rate of change and the exceeding coefficient of the cumulative change, and the thresholds for medium and low impact are adjusted accordingly to adapt the thresholds to environmental changes and avoid misjudgments caused by environmental fluctuations. On the other hand, considering the degree of equipment aging, the threshold for high impact is adjusted through the aging degree index to compensate for the assessment bias of the impact of equipment aging on performance. This two-dimensional dynamic threshold optimization mechanism, combined with a hierarchical early warning system, enables accurate identification and timely response to circuit breaker status, effectively reducing false alarms and missed alarms, providing a reliable basis for operation and maintenance decisions, extending equipment service life, and reducing operation and maintenance costs. Attached Figure Description

[0034] The invention will now be further described with reference to the accompanying drawings.

[0035] Figure 1 This is a schematic diagram of the circuit breaker operating characteristic detection system based on artificial intelligence, according to an embodiment of the present invention.

[0036] Figure 2 This is a flowchart illustrating the data acquisition and preprocessing logic of an embodiment of the present invention. Detailed Implementation

[0037] Hereinafter, exemplary embodiments according to the present invention will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are merely some embodiments of the present invention, and not all embodiments of the present invention. It should be understood that the present invention is not limited to the exemplary embodiments described herein.

[0038] Example 1

[0039] Please see Figure 1 and Figure 2As shown, the AI-based circuit breaker operating characteristic detection system includes: a data acquisition layer, a data preprocessing layer, a data analysis layer, a decision and early warning layer, and a system management layer. The data acquisition layer is responsible for collecting the operating characteristic parameters of the circuit breaker, including operating characteristic parameters, electrical parameters, and mechanical vibration parameters. The data preprocessing layer filters the collected raw data to remove noise interference and normalizes data of different types and dimensions, finally extracting key features from the processed data. The data analysis layer comprehensively calculates and analyzes the contact wear rate change rate and the opening and closing time change rate in the operating characteristic parameters to obtain the mechanical operating state evaluation coefficient. The decision and early warning layer evaluates the circuit breaker's operating state based on the mechanical operating state evaluation coefficient combined with pre-set evaluation standards and thresholds, determining whether the circuit breaker is in a normal, caution, warning, or emergency state, and issuing early warning signals accordingly. The system management layer configures various system parameters, dynamically optimizes and provides feedback on the operating state judgment threshold, and stores and manages the collected raw data, processed data, and analysis results.

[0040] In one specific embodiment, this invention comprehensively collects action characteristic parameters through a data acquisition layer to ensure complete information on circuit breaker operation; a data preprocessing layer improves data quality and usability through filtering, normalization, and feature extraction, laying the foundation for subsequent analysis; a data analysis layer uses comprehensive calculation and analysis to evaluate multi-dimensional parameters in mechanical actions, obtaining mechanical action state evaluation coefficients to accurately grasp the circuit breaker's operating status; a decision-making and early warning layer accurately determines the operating status and provides timely warnings based on the evaluation results and thresholds, assisting maintenance personnel in rapid response; and a system management layer dynamically optimizes feedback judgment thresholds, stores and manages various types of data, ensuring flexible and stable system operation, and facilitating data query and traceability. The overall solution effectively improves the accuracy, reliability, and intelligence level of circuit breaker detection, reduces fault risks, and ensures the safe and stable operation of the power system.

[0041] As a further explanation of the scheme in this embodiment, the method for comprehensively calculating and analyzing the change rate of contact wear rate and the change rate of opening and closing time in the action characteristic parameters to obtain the mechanical action state evaluation coefficient is as follows:

[0042] The preprocessed operating characteristic parameters are obtained from the data preprocessing layer, and the cumulative wear of the circuit breaker contacts at each detection moment in each detection cycle is extracted from the operating characteristic parameters and denoted as . Simultaneously, the time interval between two adjacent detection moments of the circuit breaker in each detection cycle is obtained, denoted as Δt; where z represents the number of each detection cycle, z = 1, 2, ..., Z, Z represents the total number of detection cycle numbers, and t represents the number of each detection moment, t = 1, 2, ..., T, T represents the total number of detection moment numbers.

[0043] Specifically, a contact wear measurement structure installed on one side of the circuit breaker is used to measure changes in the contact position of the contacts using a laser displacement sensor.

[0044] Depend on The result divided by Δt yields the contact wear rate of the circuit breaker at each detection moment in each detection cycle, denoted as .

[0045] The average wear rate of the circuit breaker in each testing cycle is obtained by summing the contact wear rates at each testing moment and dividing by T. This average wear rate is denoted as T. Divide the squared deviations of the contact wear rate and average wear rate of the circuit breaker in each testing cycle by T to obtain the standard deviation of the wear rate of the circuit breaker in each testing cycle, denoted as T.

[0046] According to the formula The rate of change of contact wear rate of the circuit breaker at each detection time in each detection cycle was calculated. The rate of change of contact wear rate of the circuit breaker at each detection moment in each detection cycle was calculated. and average wear rate The difference is divided by the standard deviation of the wear rate. The normalized rate of change of contact wear rate of the circuit breaker at each detection time in each detection cycle is denoted as .

[0047] The duration of each opening and closing operation of the circuit breaker in each detection cycle is obtained from the system management layer and denoted as follows: and Simultaneously, the rated opening time and rated closing time of the circuit breaker design are obtained, and denoted as follows: and The average opening time and average closing time of the circuit breaker in each detection cycle are obtained using the mean value calculation formula, and are denoted as follows: and The average opening time and average closing time of the circuit breaker in each detection cycle are obtained using the standard deviation calculation formula, and are denoted as follows: and

[0048] Specifically, vibration sensors are used to detect the mechanical vibration signals of the circuit breaker during the opening and closing process in each detection cycle, and the opening and closing time of the circuit breaker in each detection cycle is determined by the signal feature points.

[0049] According to the formula The rate of change of the circuit breaker's opening time in each detection cycle was calculated. According to the formula The rate of change of closing time of the circuit breaker in each detection cycle was calculated. Then, by normalizing the change rate of contact wear rate, the normalized change rates of opening and closing time of the circuit breaker in each detection cycle were calculated and denoted as follows: and

[0050] According to the formula The information entropy e of each index of the circuit breaker in each detection cycle is calculated. j Where, j represents the number of each indicator, j = 1, 2, 3; 1 represents the change rate of contact wear rate of the circuit breaker at each detection time in each detection cycle after normalization; 2 represents the change rate of opening time of the circuit breaker in each detection cycle after normalization; 3 represents the change rate of closing time of the circuit breaker in each detection cycle after normalization; pzj represents the proportion of the j-th indicator of the circuit breaker in the z-th cycle, reflecting the relative proportion of the j-th indicator in all samples of the indicator in the z-th cycle.

[0051] According to the formula The weighting index w of each indicator of the circuit breaker in each detection cycle is calculated. j .

[0052] Based on the normalized indicators and the weighted indices of each indicator for the circuit breaker in each testing cycle, the mechanical operating condition evaluation coefficient JD of the circuit breaker in each testing cycle is calculated using a weighted summation method. z The specific calculation formula is as follows: Introducing data from 5 detection cycles, the first group Group 2 Group 3 Group 4 Group 5 After calculating and analyzing the data from the five testing cycles, the following results were obtained: Mechanical operating condition evaluation coefficient JD for the first group of circuit breakers. z ≈0.28; Mechanical operating condition evaluation coefficient JD for the second group of circuit breakers z ≈0.70; Mechanical operating condition evaluation coefficient JD for the third group of circuit breakers z=0; Mechanical operating condition evaluation coefficient JD for the fourth group of circuit breakers z =1; Mechanical operating condition evaluation coefficient JD for the fifth group of circuit breakers z ≈0.48; Based on the mechanical action state evaluation coefficient results in each of the above detection cycles, the comprehensive situation of the circuit breaker under the corresponding state is further analyzed.

[0053] Based on historical data statistical analysis, thresholds for low impact, medium impact, and high impact are pre-set. The specific threshold setting method is as follows: collect historical data of circuit breakers under different combinations of environmental parameters and operating conditions, and statistically analyze the parameter values ​​corresponding to normal fluctuations and the occurrence of faults or significant performance degradation. The comprehensive index corresponding to most normal operating data is used as the threshold for low impact (e.g., 0-0.3); the comprehensive index when some minor fault signs begin to appear is determined as the threshold for medium impact (e.g., 0.3-0.7); and the comprehensive index when there is a serious fault risk is used as the threshold for high impact (e.g., 0.7-1).

[0054] In one specific embodiment, this invention comprehensively analyzes the mechanical action characteristics of circuit breakers from dimensions such as contact wear and opening / closing time. It utilizes laser displacement sensors and vibration sensors to accurately collect data, which is then processed through normalization, information entropy calculation, and weighting to obtain mechanical action status evaluation coefficients. This makes the evaluation more scientific and accurate. By combining historical data with threshold settings, the circuit breaker status can be clearly determined based on the evaluation coefficients. This helps maintenance personnel to promptly grasp the overall status of circuit breakers, identify potential fault risks in advance, rationally arrange maintenance, reduce the probability of faults, ensure the stable operation of the power system, and improve the intelligence and precision of equipment management.

[0055] As a further explanation of the scheme in this implementation, the system management layer is used to dynamically optimize the feedback judgment threshold. By dynamically adjusting the setting of the influence degree threshold, the judgment of the mechanical action fault detection result of the circuit breaker is made more accurate. The specific dynamic adjustment method is as follows:

[0056] Suppose that the circuit breaker has n environmental parameters, denoted as E. i Let i = 1, 2, ..., n, where i represents the number of each environmental parameter, and let V be the threshold value for the rate of change of each environmental parameter. i The cumulative change threshold is C. i Environmental parameters include, but are not limited to, temperature, humidity, and corrosive gas concentrations, which are acquired by detecting data through corresponding detection sensors installed on one side of the circuit breaker.

[0057] For each environmental parameter E i The rate of change over the time interval Δt is Define the rate of change exceeding the limit coefficient.

[0058] Each environmental parameter E i The difference between the current value and the initial value is taken as the cumulative change, denoted as ΔEc. i Define the coefficient for cumulative change exceeding the standard.

[0059] Define the overall exceedance coefficient of environmental parameters The value of R ranges from [0,1]. The closer R is to 1, the more severe the environmental parameter exceedance. Preset thresholds for moderate and low impact are obtained, denoted as SY. mid and SY low According to the formula ΔSY=(SY mid -SY low The threshold adjustment amount ΔSY is obtained by calculating )×R.

[0060] The adjusted moderate impact threshold SY mid ′=SY mid -ΔSY, the adjusted low-impact threshold SY low ′=SY low -ΔSY.

[0061] The service life and design service life of the circuit breaker are obtained and denoted as Y and Y', respectively. max The number of operations and the expected maximum number of operations are denoted as N and Nmax, respectively. max α and β are weighting coefficients, and α + β = 1, used to adjust the contribution of operating years and number of operations to the degree of aging. Their values ​​are preset manually based on the importance of their influence; here, α = 0.6 and β = 0.4. The equipment aging degree index is defined as I. o ,

[0062] Obtain the preset threshold for high-level influence, denoted as SY. max According to the formula SY max ′=SY max -γ·I o The adjusted higher-level influence threshold SY was calculated. max ′, where γ represents the adjustment coefficient, used to control the threshold adjustment range caused by the degree of aging. Specifically, through the analysis of a large amount of historical data, it was found that as the degree of aging increases, the average decrease in the high-impact threshold shows a certain proportional relationship with the degree of aging. Based on this, the value of γ is determined, where γ = 0.05.

[0063] As a further explanation of the scheme in this implementation, the decision-making and early warning layer calculates the mechanical action state evaluation coefficient JD of the circuit breaker in each detection cycle. zBy comparing and analyzing the results with the set impact threshold, the impact of mechanical action failures of the circuit breaker in each detection cycle can be determined.

[0064] The specific comparative analysis method is as follows:

[0065] 0 <JD z ≤SY low If the circuit breaker is deemed to be in normal mechanical operation status during the detection cycle, the green warning light indicating normal mechanical operation status will remain on.

[0066] If the mechanical operation status of the circuit breaker in this detection cycle is assessed as "caution", a corresponding text warning will be issued through a system pop-up reminder, and the green warning light indicating normal mechanical operation status will be changed to a blue warning light indicating "caution" status.

[0067] If the mechanical operation status of the circuit breaker in this detection cycle is assessed as a warning, a corresponding text warning will be issued through a system pop-up reminder, and the blue warning light indicating the mechanical operation status will be changed to a yellow warning light indicating the warning status.

[0068] If the mechanical operation status of the circuit breaker in this detection cycle is assessed as emergency, a corresponding text warning will be issued through a system pop-up reminder, and the yellow warning light indicating the mechanical operation status will be changed to a red warning light indicating an emergency.

[0069] In one specific embodiment, this invention significantly improves the accuracy of circuit breaker mechanical action fault detection by dynamically adjusting the judgment threshold. On the one hand, for environmental parameters (such as temperature, humidity, and corrosive gas concentration), a comprehensive exceedance coefficient R is obtained by calculating the exceedance coefficient of the rate of change and the exceedance coefficient of the cumulative change, and the thresholds for medium and low impact are adjusted accordingly to adapt the thresholds to environmental changes and avoid misjudgments caused by environmental fluctuations. On the other hand, considering the degree of equipment aging (combining years of operation and number of operations), the threshold for high impact is adjusted through the aging degree index to compensate for the assessment bias of the impact of equipment aging on performance. This two-dimensional dynamic threshold optimization mechanism, combined with a hierarchical early warning system, enables accurate identification and timely response to circuit breaker status, effectively reducing false alarms and missed alarms, providing a reliable basis for operation and maintenance decisions, extending equipment lifespan, and reducing operation and maintenance costs.

[0070] The above formulas are all dimensionless calculations. The formulas are derived from software simulations based on a large amount of collected data to obtain the most recent real-world results. The size of the coefficients is to quantify each parameter to obtain a specific value. Regarding the size of the coefficients, it is acceptable as long as it does not affect the proportional relationship between the parameter and the quantized value.

[0071] Furthermore, those skilled in the art will understand that aspects of the present invention can be described and illustrated through several patentable types or situations, including any new and useful combination of processes, machines, products, or substances, or any new and useful improvements thereof. Accordingly, aspects of the present invention can be implemented entirely by hardware, entirely by software (including firmware, resident software, microcode, etc.), or by a combination of hardware and software. All of the above hardware or software may be referred to as a "data block," "module," "engine," "unit," "component," or "system." Furthermore, aspects of the present invention may be embodied as a computer product located on one or more computer-readable media, the product comprising computer-readable program code.

[0072] Unless otherwise defined, all terms used herein (including technical and scientific terms) shall have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. It should also be understood that terms such as those defined in a common dictionary shall be interpreted as having a meaning consistent with their meaning in the context of the relevant art, and not as having an idealized or highly formalized meaning, unless expressly defined herein.

[0073] The foregoing description is illustrative of the invention and should not be construed as limiting it. Although several exemplary embodiments of the invention have been described, those skilled in the art will readily understand that many modifications can be made to the exemplary embodiments without departing from the novel teachings and advantages of the invention. Therefore, all such modifications are intended to be included within the scope of the invention as defined in the claims. It should be understood that the foregoing description is illustrative of the invention and should not be construed as limiting it to the specific embodiments disclosed, and modifications to the disclosed embodiments and other embodiments are intended to be included within the scope of the appended claims. The invention is defined by the claims and their equivalents.

Claims

1. An artificial intelligence-based circuit breaker action characteristic detection system, characterized by, Comprise: Data acquisition layer, data preprocessing layer, data analysis layer, decision warning layer and system management layer; the data acquisition layer is responsible for collecting the action characteristic parameters of the circuit breaker, the data preprocessing layer is used for filtering processing to the collected original data, removing noise interference, and normalizing different types and different dimensions of data, and finally extracting key features from the processed data; the data analysis layer is used for comprehensive calculation and analysis of the contact wear rate change rate and the opening and closing time change rate in the action characteristic parameters, to obtain the mechanical action state evaluation coefficient; The preprocessed action characteristic parameters are obtained from the data preprocessing layer, and the contact cumulative wear amount of the circuit breaker at each detection time in each detection cycle is extracted from the action characteristic parameters, denoted as The time interval of the circuit breaker at adjacent two detection times in each detection cycle is obtained at the same time, denoted as ​ By The results of the division of The contact wear rate of the circuit breaker at each detection time in each detection cycle is calculated as ; The average wear rate of the circuit breaker in each testing cycle is obtained by summing the contact wear rates at each testing moment and dividing by T. This average wear rate is denoted as T. Divide the squared deviations of the contact wear rate and average wear rate of the circuit breaker in each testing cycle by T to obtain the standard deviation of the wear rate of the circuit breaker in each testing cycle, denoted as . According to the formula The rate of change of contact wear rate of the circuit breaker at each detection time in each detection cycle was calculated. The rate of change of contact wear rate of the circuit breaker at each detection moment in each detection cycle was calculated. and average wear rate The difference is divided by the standard deviation of the wear rate. The normalized rate of change of contact wear rate of the circuit breaker at each detection time in each detection cycle is obtained, denoted as . ; Get the duration of each opening and closing operation of the circuit breaker in each detection cycle from the system management layer, respectively recorded as and , and get the rated opening time and rated closing time of the circuit breaker design, respectively recorded as and ; The average breaking time and the average closing time of the circuit breaker in each detection cycle are obtained by using the mean value calculation formula, and are respectively denoted as and ; The average breaking time and the average closing time of the circuit breaker in each detection cycle are obtained by using the standard deviation calculation formula, and are respectively denoted as and ; According to the formula The opening time change rate of the circuit breaker in each detection cycle is calculated ; According to the formula The closing time change rate of the circuit breaker in each detection cycle is calculated ; and through the normalized calculation mode of the contact wear rate change rate, the normalized opening time change rate and the closing time change rate of the circuit breaker in each detection cycle are calculated, which are respectively denoted as and ; According to the formula The information entropy of each index of the circuit breaker in each detection cycle is calculated ; represents the proportion of the jth index of the circuit breaker in the zth cycle. According to the formula The weight index of each index of the circuit breaker in each detection cycle is calculated ; According to the normalized indexes and the weight indexes of each index of the circuit breaker in each detection cycle determined above, the mechanical action state evaluation coefficient of the circuit breaker in each detection cycle is calculated by using the weighted summation method ; The specific calculation formula is as follows: ; The decision warning layer evaluates the running state of the circuit breaker according to the mechanical action state evaluation coefficient combined with the pre-set evaluation standard and threshold, judges that the circuit breaker is in normal, attention, warning or emergency state, and sends a warning signal according to the corresponding state; the system management layer is used for configuring various parameters of the system, dynamically optimizing and feeding back the running state judgment threshold, and storing and managing the collected original data, processed data and analysis results.

2. The artificial intelligence-based circuit breaker trip characteristic detection system of claim 1, wherein, According to historical data statistical analysis, the low impact degree threshold, the medium impact degree threshold and the high impact degree threshold are pre-set; the specific threshold setting method is as follows: collect the historical data of the circuit breaker under different environmental parameter combinations and operating conditions, count the corresponding parameter values when each parameter normally fluctuates and when a fault occurs or the performance obviously decreases, and take the comprehensive index corresponding to most normal operation data as the low impact degree threshold; The comprehensive index when some slight failure signs begin to appear is determined as the medium impact degree threshold; And the comprehensive index when a serious failure risk occurs is taken as the high impact degree threshold.

3. The artificial intelligence-based circuit breaker trip characteristic detection system of claim 2, wherein, The system management layer is used for dynamically optimizing and feeding back the judgment threshold, dynamically adjusts the setting of the impact degree threshold, so that the mechanical action failure detection result of the circuit breaker is more accurate, and the specific dynamic adjustment method is as follows: Suppose that the environment parameters of the circuit breaker are n, denoted as , , i represents the number of each environment parameter, and the change rate threshold of each environment parameter is set as , and the cumulative change threshold is ; the environment parameters include but are not limited to temperature and humidity, corrosive gas concentration, and the data is detected and obtained by installing the corresponding detection sensor on one side of the circuit breaker; For each environmental parameter , the rate of change of the parameter over the time interval is , and a rate of change overrun factor is defined. The difference between the current value and the initial value of each environmental parameter is taken as the cumulative change amount, denoted as , and a cumulative change amount exceeding coefficient is defined ; Define an environmental parameter comprehensive over-standard coefficient , R is in the range of [0, 1], R is closer to 1, which means that the environmental parameter is more serious, and a preset medium influence degree threshold and a low influence degree threshold are obtained, denoted as and , the threshold adjustment amount is calculated according to the formula ; the adjusted medium impact level threshold , the adjusted low impact level threshold .

4. The artificial intelligence-based circuit breaker trip characteristic detection system of claim 3, wherein, The running life and the design life of the circuit breaker are acquired, and are recorded as and , the operation times and the expected maximum operation times are recorded as and , α and β are weight coefficients, and α+β=1, and the equipment aging degree index is defined as , ; Obtain the preset threshold for high-level influence, denoted as According to the formula The adjusted higher-level influence threshold was calculated. ,in This is represented as an adjustment factor.

5. The artificial intelligence based breaker action characteristic detection system of claim 4, wherein, The decision-making and early warning layer calculates the mechanical action status evaluation coefficient of the circuit breaker in each detection cycle. By comparing and analyzing the results with the set impact threshold, the impact of mechanical action failures of the circuit breaker in each detection cycle can be determined.

Images