Circuit breaker safety management method based on operating environment data

Abstract

The invention provides a circuit breaker safety management method based on operating environment data, and the method is characterized in that the method comprises the steps: carrying out the sampling monitoring of n power utilization modules YD in a circuit, enabling the power utilization modules YDi to trigger the outage of a circuit breaker to have m types of operating parameters IW, setting the function weight of the jth type of operating parameters IWj to be lambdaj, the power-off value of the circuit breaker for triggering the power-off of the jth type of operation parameter IWj is Wj-max; obtaining a parameter value Pj of an operation parameter IWj of the power utilization module YDi in the T1 monitoring time, and calculating to obtain a monitoring score of the power utilization module YDi; obtaining a circuit risk score of the T1 monitoring time; k power utilization modules included in the power utilization risk list L are obtained, the power utilization risk list L is arranged in a descending order according to the circuit risk scores, and the first power utilization module is closed; obtaining the circuit risk score again at a second monitoring time T2 after the first power utilization module is turned off; and performing evaluation and judgment according to the circuit risk score. According to the invention, the circuit safety is improved, and the performance of the circuit breaker is optimized.

Description

Technical Field

[0001] This application relates to the field of circuit breaker safety management, and particularly to a circuit breaker safety management method based on operating environment data. Background Art

[0002] The design of existing circuit breakers is based on intelligent control technology. Through various sensors, parameters such as the load, temperature, and current of the circuit are monitored in real time, and intelligent judgment and processing can be performed according to the actual situation to achieve the effect of safety protection for load devices such as wires and electrical appliances. By using a microprocessor chip and intelligent control algorithms, various parameters can be analyzed and processed to achieve intelligent judgment and control. The circuit breaker can also automatically cut off the power supply through self-checking and automatic fault repair functions to better protect the load device. At the same time, through network communication or Internet of Things technology, remote communication with external devices is realized, improving the manageability and convenience. Therefore, for analyzing and processing the data obtained by sensors, judging the circuit state, and performing contact control according to the judgment result to protect the load device is the current design direction of circuit breakers. However, the current design idea is mainly to cut off the power supply to avoid risks when the risk occurs. When monitoring some important power consumption modules, if the circuit is easily cut off due to the occurrence of risks, it may cause economic losses. Therefore, a method is needed that can provide prior data guidance and prediction basis for safety management personnel, avoid being caught off guard when judging and repairing when the circuit actually has risks, and reduce the power-off time of power consumption modules. Summary of the Invention

[0003] The following description is used to disclose the present invention so that those skilled in the art can implement the present invention. The preferred embodiments described below are only examples, and those skilled in the art can think of other obvious variations. The basic principles defined in the following description can be applied to other implementation schemes, variant schemes, improvement schemes, equivalent schemes, and other technical schemes that do not deviate from the spirit and scope of the present invention.

[0004] To solve the technical problems, this application provides a circuit breaker safety management method based on operating environment data. The steps include: S1. Sample and monitor n power consumption modules YD in the circuit, YD = [YD1, YD2, YD3,..., YD n , where the operating parameters IW that trigger the circuit breaker to cut off the power for the i-th power consumption module YD i include m categories, IW = [IW1, IW2, IW3,..., IW m , and set the function weight of the j-th category of operating parameter IW j as λ j The circuit breaker triggers the j-th category of operating parameter IWj The power-off value of the power-off is W j-max ; S2. Obtain the operating parameter IW of the power consumption module YD at the monitoring time T1 i of j the parameter value P j , calculate the monitoring score of YD i ; Among them, P ’ is the normalized value of the parameter value P j of the operating parameter IW j ; j Set the monitoring score threshold IQ0 for the power consumption module YD; Set the monitoring score threshold IQ0 for the power consumption module YD i ; When IQ i ≥IQ0, add the power consumption module YD i to the power consumption risk list L; S3. Obtain the circuit risk score at the monitoring time T1 ; Among them, ξ is the initially set circuit risk coefficient, and the circuit risk coefficient at the monitoring time T1 is obtained , where F min is the minimum value of the circuit risk score in the historical data, and F max is the maximum value of the circuit risk score in the historical data; Set the circuit risk score threshold F0; When F1≥F0, transfer to step S4; S4. Obtain the k power consumption modules included in the power consumption risk list L, sort the power consumption risk list L in descending order according to the circuit risk score, and turn off the power consumption module at the top of the sorting; Obtain the circuit risk score again at the second monitoring time T2 after turning off the power consumption module at the top ; Among them, e is the natural constant, and obtain ; When F2≥F1, it is judged that there may be a risk of continuous increase in the circuit, and an early warning is sent to the safety management personnel; When F0<F2<F1, continue to obtain the circuit risk score and circuit risk coefficient at the monitoring time T3, and turn off the power consumption modules in sequence according to the order of the power consumption risk list, and loop this step until the circuit risk score does not exceed F1; When F2≤F0, regard the turned-off power consumption module as a safety risk module, and give a warning prompt of the safety risk module to the safety management personnel.

[0005] Among them, in step S2, obtain the parameter value P j of the operating parameter IW j after normalization , where represents rounding up.

[0006] Among them, the operating parameters for triggering the circuit breaker to cut off power include current, voltage, power, and temperature.

[0007] Among them, the power-off value refers to the threshold value when the circuit breaker monitors that the operating parameter value of the power-consuming module reaches the trigger for power-off, and the threshold value is set according to the historical data in the circuit.

[0008] Among them, the obtained operating parameter features are put into the trained SVM model for analysis to judge whether the currently set threshold is appropriate. The SVM algorithm is as follows: Objective function:

[0009] Among them, W and b are plane coefficients, represents the classification label of the sample, = [-1, 1], then it is the training sample; W is the plane coefficient, and when extended to the n-dimensional space, it is an n-dimensional vector such as: W = [W1, W2,..., Wn], is the transpose of W, and ||W|| is the norm of the hyperplane.

[0010] Since the SVM objective function assumes that the data is linearly separable, but in fact there will be noisy data, so slack variables and penalty parameters are added to increase the tolerance of the model through the slack variables: , Among them, is the penalty coefficient, is the slack variable, which is represented by the distance from the misclassified point to the plane where the support vector of the corresponding category is located. For the correctly classified sample points , the penalty term is determined by all the outlier points. This optimization problem is transformed into a dual problem using the Lagrange multiplier method and the KKT conditions, and the SMO method is used for solution; among them is the Lagrange multiplier; the form of the dual problem obtained by mapping this model to a high-dimensional space is: ,

[0011] The kernel function selected in this article is the Gaussian function:

[0012] It is analyzed by the SVM classifier to obtain whether the current threshold meets the requirements. -1 means yes, and 1 means no.

[0013] Among them, in step S4, the initial time interval between adjacent monitoring times is set to △T0. According to the power-consuming module YD that has been turned offi has a weight of ω i ; The times of the first monitoring time T1 and the second monitoring time T2 are preferably .

[0014] The beneficial effects achieved by this application are as follows: This application monitors parameters such as the load, temperature, and current of the circuit in real time through sensors of environmental data, and can make intelligent judgments and processing according to the actual situation to achieve the effect of pre-judging the safety protection of load devices such as wires and electrical appliances. This application uses advanced microprocessor chips and intelligent control algorithms, and can perform pre-judging analysis and processing on various parameters. Before the circuit generates risks, this application first evaluates the possible risks, and can provide pre-data guidance and pre-judging basis for safety management personnel, avoiding situations where judgments and repairs are too late when the circuit actually has risks. Especially when monitoring some important power consumption modules, if the circuit is easily powered off due to risks, it may cause economic losses. Through the principle of pre-judging first, corresponding and processing early, and can minimize the power-off time of the power consumption module to the greatest extent. This algorithm is integrated inside the circuit breaker, which is convenient for setting and operation, and is easy to install and maintain.

[0015] This application overcomes the fact that most mechanism models are only simplified linear systems, can judge complex situations with non-linearity, high degrees of freedom, and multi-variable coupling, has a fast triggering speed, low cost, and both the start and recovery of early warnings are very rapid, and has a wide application range. Description of the Drawings

[0016] In order to more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments recorded in this application. For those skilled in the art, other drawings can also be obtained according to these drawings.

[0017] Figure 1 is the step flow chart for this application. Detailed Embodiments

[0018] The following clearly and completely describes the technical solutions in the embodiments of the present application in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are some, but not all, of the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative efforts belong to the scope of protection of the present application. It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned accompanying drawings are used to distinguish similar objects, and do not necessarily need to describe a specific order or sequence. It should be understood that such used data can be interchanged under appropriate circumstances so that the embodiments of the present application described here can be implemented in an order other than those illustrated or described here. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that includes a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products, or devices.

[0019] The present application provides sampling and monitoring of n power-consuming modules YD in a circuit, YD = [YD1, YD2, YD3, …, YD n , where the i-th power-consuming module YD i The operating parameters IW that trigger the circuit breaker to cut off power include m categories, IW = [IW1, IW2, IW3, …, IW m , where the function coefficient of the j-th operating parameter IW j is λ j , and the power-off value at which the circuit breaker triggers the power-off of the j-th operating parameter IW j is W j-max ; Specifically, in this embodiment, the operating parameters that trigger the circuit breaker to cut off power include current, voltage, power, and temperature. Different power-off values are set for the current, voltage, power, and temperature of the power-consuming module according to the functions and weights of the power-consuming modules. The power-off value refers to the threshold value when the circuit breaker monitors that the operating parameter value of the power-consuming module reaches the trigger for power-off, and the threshold value can be set according to the historical data in the circuit.

[0020] Specifically, the threshold data in the initially set threshold array can be placed into a neural network model for evaluation. For example, in one embodiment, the obtained operating parameter features can be put into a trained SVM model for analysis to determine whether the currently set threshold is appropriate. The SVM algorithm is as follows: Objective function:

[0021] where W and b are plane coefficients, The classification label representing the sample, =[-1, 1], then it is a training sample; W is the plane coefficient, and when extended to the n-dimensional space, it is an n-dimensional vector such as: W = [W1, W2,..., Wn], is the transpose of W, and ||W|| is the norm of the hyperplane.

[0022] Since the SVM objective function assumes that the data is linearly separable, but in fact there will be noisy data, so slack variables and penalty parameters are added. By adding slack variables, the tolerance of the model is increased: ,

[0023] Among them, is the penalty coefficient, is the slack variable, which is represented by the distance from the misclassified point to the plane where the support vector of the corresponding category is located. For the correctly classified sample points , the penalty term is determined by all the outliers. This optimization problem is transformed into a dual problem using the Lagrange multiplier method and the KKT conditions, and the SMO method is used for solution; among them is the Lagrange multiplier; the form of the dual problem obtained by mapping this model to a high-dimensional space is: ,

[0024] The kernel function selected in this paper is the Gaussian function:

[0025] After analysis by the SVM classifier, it is determined whether the current threshold meets the requirements. -1 means yes, and 1 means no. In a specific application app or web page, the user can be recommended or the customer can select the appropriate threshold given.

[0026] At the monitoring time T1, the operating parameters IW of the power consumption module YD i are obtained j and the parameter value P j . At this time, it is necessary to calculate the circuit risk score, but due to different parameter categories, normalization needs to be carried out first: The parameter value P of the operating parameter IW is obtained j and the normalized value j is obtained , among which, represents rounding up; The monitoring score of the power consumption module YD i can be obtained ; At this time, the circuit risk score at the monitoring time T1 is obtained ; Among them, ξ is the initially set circuit risk coefficient, and the circuit risk coefficient at the monitoring time T1 is obtained. , where F min is the minimum value of the circuit risk scores in historical data, and F max is the maximum value of the circuit risk scores in historical data. According to the circuit risk score threshold F0; When F1 > F0, the power consumption module YD i is added to the first power consumption risk list L1; It is obtained that the first power consumption risk list L1 includes k power consumption modules. The first power consumption risk list is sorted in descending order according to the circuit risk scores, and the power consumption module at the top of the sorting is turned off. At the second monitoring time T2 after turning off the top power consumption module, the circuit risk score is obtained again. ;

[0027] Among them, e is the natural constant, and the circuit risk coefficient at the monitoring time T2 is obtained. , When F2 > F1, it is determined that the circuit is in a high-risk state, and an early warning is sent to the safety management personnel, or the circuit is automatically temporarily turned off and waits for the next instruction to start.

[0028] When F0 < F2 < F1, the circuit risk score and the circuit risk coefficient are continuously obtained at the monitoring time T3, and the power consumption modules are turned off in sequence according to the order of the power consumption risk list, and this step is cycled until the circuit risk score does not exceed F1.

[0029] When F2 < F0, the turned-off power consumption module is used as a safety risk module, and a warning prompt is sent to the safety management personnel, waiting for the safety management personnel to handle it, or automatically performing the next higher-risk monitoring.

[0030] In addition, the time interval △T1 = T2 - T1 between the first monitoring time T1 and the second monitoring time T2 is set. At this time, considering that the power consumption module is already in the off state, due to the different importance of the power consumption modules, some power consumption modules with higher importance cannot be turned off for a long time, but if the interval time is too short, it is not conducive to collecting better-quality data. Therefore, the time interval is optimized: the initial time interval between adjacent monitoring times is set as △T0, and according to the weight ω i of the turned-off power consumption module YD i ; The time between the first monitoring time T1 and the second monitoring time T2 is preferably .

[0031] Furthermore, the present invention also provides a computer-readable storage medium. The computer-readable storage medium includes a stored program, wherein the program executes the method described in the above method embodiment when running.

[0032] Furthermore, the present invention also provides an electronic device, including a memory and a processor, where a computer program is stored in the memory, and the processor is configured to execute the method described in the above method embodiment through the computer program.

[0033] Furthermore, it should be understood that since the setting of each module is only to illustrate the functional units of the device of the present invention, the physical devices corresponding to these modules can be the processor itself, or a part of the software in the processor, a part of the hardware, or a part of the combination of software and hardware. Therefore, the number of each module in the figure is only illustrative.

[0034] Those skilled in the art can understand that all or part of the processes in the methods of the above embodiments of the present invention can also be completed by instructing relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, the steps of the above method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file or some intermediate form, etc. The computer-readable storage medium can include: any entity or device, medium, USB flash drive, mobile hard disk, magnetic disk, optical disc, computer memory, read-only memory, random access memory, electrical carrier signal, telecommunication signal, and software distribution medium that can carry the computer program code.

[0035] The computer device can be a terminal. The computer device includes a processor, a memory, a communication interface, a display screen, and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is implemented by technologies such as a network, NFC (Near Field Communication), or others. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen. The input device of the computer device can be a touch layer covering the display screen, or a button, trackball, or touchpad provided on the housing of the computer device, or an external keyboard, touchpad, or mouse, etc.

[0036] Those skilled in the art can understand that the various modules in the device can be adaptively split or combined. Such splitting or combination of specific modules will not cause the technical solution to deviate from the principle of the present invention. Therefore, the technical solutions after splitting or combination will fall within the protection scope of the present invention.

Claims

1. A circuit breaker safety management method based on operating environment data, characterized in that the steps Including: S1. Sample and monitor n electrical consumption modules YD in the circuit, where YD = [YD1, YD2, YD3, …, YD n , and the i-th electrical consumption module YD i . The operating parameters IW that trigger the circuit breaker to cut off power include m categories, IW = [IW1, IW2, IW3, …, IW m . Set the function weight of the j-th category of operating parameter IW j to be λ j . The power-off value at which the circuit breaker triggers the power-off for the j-th category of operating parameter IW j is W j-max ; S2. Obtain the operating parameters IW i of the power consumption module YD j and the parameter value P j of it, and calculate the monitoring score i of the power consumption module YD ; where P j ’ is the value of the operating parameter IW j after normalization of the parameter value P j of it. Set the power consumption module YD i Monitor the score threshold IQ0; When IQ i ≥ IQ0, the power consumption module YD i is added to the power consumption risk list L; S3. Obtain the circuit risk score for the T1 monitoring time ; Among them, ξ is the initially set circuit risk coefficient, and the circuit risk coefficient at the T1 monitoring time is obtained. , where F min is the minimum value of the circuit risk scores in the historical data, and F max is the maximum value of the circuit risk scores in the historical data; Set the circuit risk score threshold F0; When F1≥F0, go to step S4; S4, Obtain k power consumption modules included in the power consumption risk list L, sort the power consumption risk list L in descending order according to the circuit risk score, and turn off the power consumption module ranked first; Obtain the circuit risk score again at the second monitoring time T2 after closing the first power-consuming module ; where e is the natural constant, ; When F2≥F1, it is judged that the circuit may have a continuously increasing risk, and an early warning is sent to the safety management personnel; When F0<F2<F1, continue to obtain the circuit risk score and the circuit risk coefficient at the monitoring time T3, and turn off the power consumption modules in sequence according to the order of the power consumption risk list, and loop this step until the circuit risk score does not exceed F1; When F2≤F0, the turned-off power consumption module is used as a safety risk module, and a warning prompt for the safety risk module is sent to the safety management personnel.

2. The circuit breaker safety management method based on operating environment data according to claim 1, wherein, In step S2, the operating parameter IW j The parameter value P j The normalized value , where represents rounding up.

3. The circuit breaker safety management method based on operating environment data according to claim 1, characterized in that, The operating parameters for triggering the circuit breaker to cut off power include current, voltage, power, and temperature.

4. The circuit breaker safety management method based on operating environment data according to claim 1, wherein The power-off value refers to the threshold value when the circuit breaker monitors that the operating parameter value of the power consumption module reaches the trigger for power-off, and the threshold value is set according to the historical data in the circuit.

5. The circuit breaker safety management method based on operating environment data according to claim 4, characterized in that, Put the obtained operating parameter characteristics into the trained SVM model for analysis to judge whether the currently set threshold is appropriate. The SVM algorithm is as follows; Objective function: ; where W and b are plane coefficients, representing the classification label of the sample, =[-1,1], then they are training samples; W is a plane coefficient, and when extended to an n-dimensional space, it is an n-dimensional vector such as: W = [W1, W2,..., Wn], is the transpose of W, and ||W|| is the norm of the hyperplane; Since the SVM objective function assumes linearly separable data, but in reality there will be noisy data, slack variables and penalty parameters are added to increase the model's tolerance through the slack variables: ; Among them, is the penalty coefficient, is the slack variable, which is represented by the distance from the misclassified point to the plane where the support vector of the corresponding class is located. The of the correctly classified sample points, and the penalty term is determined by all the outlier points; this optimization problem is transformed into a dual problem by using the Lagrange multiplier method and the KKT conditions, and the SMO method is used for solution; among them is the Lagrange multiplier; the dual problem form obtained by mapping this model to a high-dimensional space is: ， ； The kernel function selected in this paper is the Gaussian function: ; Through analysis by the SVM classifier, it is obtained whether the current threshold meets the requirements. -1 means yes, and 1 means no.

6. The circuit breaker safety management method based on operating environment data according to claim 1, characterized in that, In step S4, an initial time interval between adjacent monitoring times is set as ΔT0, and according to the power consumption module YD that has been turned off i the weight is ω i ; the times of the first monitoring time T1 and the second monitoring time T2 are .

Images