Artificial Intelligence-Based Industrial Power Distribution Safety Early Warning Method and System

Abstract

The present invention discloses an industrial power distribution safety early warning method and system based on artificial intelligence. The method includes: data collection, industrial power distribution data processing, constructing an industrial power distribution safety detection model, and real-time early warning. The present invention belongs to the technical field of safety early warning. This solution introduces a comprehensive metric value, designs the upper and lower bounds of the noise data boundary, screens and removes noise data, divides the minority class boundary data, minority class safety data, and majority class boundary data based on the nearest neighbor, performs two syntheses of data based on the number of data to be synthesized and the selection probability, and verifies the synthesized data after the first synthesis; designs a random slope adjustment factor and a dynamic inversion adjustment factor to perform adaptive bidirectional mutation, designs an adaptive boundary, and combines a progressive adjustment factor and a convergence control coefficient for position update to find the optimal parameters, accurately and timely perform safety detection, and improve the reliability and accuracy of industrial power distribution safety early warning.

Description

Technical Field

[0001] The present invention belongs to the technical field of safety warning, and specifically refers to an industrial power distribution safety warning method and system based on artificial intelligence. Background Art

[0002] The industrial power distribution safety warning method uses advanced artificial intelligence technology to process and analyze various data in the industrial power distribution process in real time, detect the industrial power distribution safety status, issue safety warning signals, and remind relevant personnel to take measures in time, greatly improving the safety and reliability of industrial power distribution. However, in the existing industrial power distribution safety warning methods, there are problems such as poor quality of industrial power distribution data and susceptibility to noise data interference, as well as imbalance in the categories of industrial power distribution data, resulting in insufficient attention and identification ability for minority categories, and reducing the reliability and credibility of industrial power distribution safety warning; there are problems in the existing industrial power distribution safety warning methods that the industrial power distribution situation is complex and diverse, and the industrial power distribution data has complex non-linear relationships, making it difficult to conduct comprehensive and accurate safety detection, resulting in the inability to timely and accurately discover industrial power distribution safety hazards. Summary of the Invention

[0003] In view of the above situation, to overcome the defects of the prior art, the present invention provides an industrial power distribution safety warning method and system based on artificial intelligence. In the existing industrial power distribution safety warning methods, there are problems such as poor quality of industrial power distribution data and susceptibility to noise data interference, as well as imbalanced industrial power distribution data categories, resulting in insufficient attention and recognition ability for minority categories, and reducing the reliability and credibility of industrial power distribution safety warnings. This solution introduces a comprehensive metric value, designs the upper and lower bounds of the noise data boundary, screens and removes noise data, improves the quality and reliability of the data, and eliminates the adverse effects of noise on data analysis and warning; based on the nearest neighbor, divides the minority boundary data, minority safety data, and majority boundary data, classifies and defines different category data; synthesizes data twice based on the quantity to be synthesized and the selection probability, and verifies the synthesized data after the first synthesis to balance the data categories, enabling more comprehensive learning and processing of different categories of industrial power distribution data, and improving the reliability and credibility of industrial power distribution safety warnings; in view of the problems in the existing industrial power distribution safety warning methods that the industrial power distribution situation is complex and diverse, the industrial power distribution data has complex non-linear relationships, and it is difficult to conduct comprehensive and accurate safety detection, resulting in the inability to timely and accurately discover industrial power distribution safety hazards, this solution designs a random slope adjustment factor and a dynamic inversion adjustment factor to perform adaptive bidirectional mutation to adapt to the complex and diverse industrial power distribution situation; designs an adaptive boundary to adapt to the search requirements at different stages; and combines a progressive adjustment factor and a convergence control coefficient for position update to find the optimal parameters, complete the construction of the industrial power distribution safety detection model, ensure that the obtained parameters can meet the accuracy requirements for industrial power distribution safety detection, and conduct industrial power distribution safety detection accurately and timely, improving the effect and reliability of safety warnings.

[0004] The technical solution adopted by the present invention is as follows: The industrial power distribution safety warning method based on artificial intelligence provided by the present invention includes the following steps:

[0005] Step S1: Data collection;

[0006] Step S2: Industrial power distribution data processing;

[0007] Step S3: Construct an industrial power distribution safety detection model;

[0008] Step S4: Real-time warning.

[0009] Further, in step S1, the data collection is to collect historical industrial power distribution data; the historical industrial power distribution data includes power parameter data, equipment operation data, environmental data, and safety status; the power parameter data includes voltage, current, power, and frequency; the equipment operation data includes switch status, load status, maintenance records, and operation time data; the environmental data includes temperature, humidity, and air quality; the safety status includes normal, mild anomaly, moderate anomaly, and severe anomaly, and the safety status is used as the data label.

[0010] Further, in step S2, the processing of the industrial power distribution data specifically includes the following steps:

[0011] Step S21: Preprocessing, performing data cleaning, data conversion, and data normalization on the collected industrial power distribution data; data cleaning includes handling outliers, duplicate values, and missing values; data conversion is to convert the data into vector form; data normalization is to unify the data range based on the maximum-minimum normalization method;

[0012] Step S22: Removing noise data, constructing an industrial power distribution data set based on the preprocessed data, and dividing the industrial power distribution data set into a minority class data set and a majority class data set, calculating the average value of all industrial power distribution data in the minority class data set , and then calculating the Euclidean distance and kernel density estimation between each industrial power distribution data in the minority class data set and the average value The product of the Euclidean distance and the kernel density estimation is used as the comprehensive metric value of each industrial power distribution data. The comprehensive metric values are sorted in ascending order, and the comprehensive metric values at and are selected as the first reference metric c1 and the second reference metric c2. Based on the reference metrics, the upper bound ub and the lower bound lb of the noise data boundary are set. The industrial power distribution data in the minority class data set with a comprehensive metric value greater than the upper bound ub or less than the lower bound lb is regarded as noise data, and the noise data is deleted from the minority class data set. The formulas used are as follows:

[0013] ;

[0014] ;

[0015] In the formula, r is the control factor;

[0016] Step S23: Division. Calculate the k nearest neighbors of each industrial power distribution data in the minority-class dataset within the industrial power distribution dataset. If not all of the k nearest neighbors are data within the minority-class dataset, mark the industrial power distribution data in the corresponding minority-class dataset as minority-class boundary data; otherwise, mark the industrial power distribution data in the corresponding minority-class dataset as minority-class safe data. Then calculate the Euclidean distance between each industrial power distribution data in the minority-class dataset and its k nearest neighbors respectively, and mark the nearest neighbor with the smallest Euclidean distance d min and belonging to the majority-class dataset as majority-class boundary data, and use d min as the specific metric value of this majority-class boundary data. Construct the first reference dataset, the second reference dataset, and the detection dataset based on the minority-class boundary data, the minority-class safe data, and the majority-class boundary data respectively;

[0017] Step S24: First synthetic data, including the following steps:

[0018] Step S241: Calculate the first quantity to be synthesized. The formula used is as follows:

[0019] ;

[0020] In the formula, H1 is the first quantity to be synthesized, N min and N max are the quantities of industrial power distribution data in the minority-class dataset and the majority-class dataset respectively;

[0021] Step S242: Calculate the selection probability. The formula used is as follows:

[0022] ;

[0023] In the formula, x v is the v-th minority-class boundary data in the first reference dataset, g v is the selection probability of x v , v is the industrial power distribution data index, a1 and a2 are the first adjustment factor and the second adjustment factor respectively, d v is the Euclidean distance between x v and the average value , is the kernel density estimate of x v ;

[0024] Step S243: Synthetic data. Based on the selection probability, randomly extract data from the first reference dataset, and perform the first synthetic data based on the extracted data and the average value until the quantity of the synthetic data is equal to H1, and construct a synthetic dataset based on the synthetic data of the first time and the industrial power distribution dataset. The formula used is as follows:

[0025] ;

[0026] In the formula, is the wth data synthesized for the first time, rand(0,1) generates a random number between (0,1), x abs is the extracted data, w is the synthetic data index;

[0027] Step S244: Synthetic data verification, calculate the k nearest neighbors of each majority class boundary data in the detection data set in the synthetic data set, if the k nearest neighbors contain synthetic data , then calculate the majority class boundary data and synthetic data The Euclidean distance between ,like , then the synthetic data Delete from the synthetic data set to obtain a qualified data set, and obtain the number of data in the qualified data set A;

[0028] Step S25: synthesize data for the second time, calculate the number of synthesized data H2 = H1-A, and calculate the selection probability of each minority class safety data in the second reference data set. Based on the selection probability, randomly extract data from the second reference data set, and based on the extracted data and the average value The second synthetic data is performed until the amount of synthetic data is equal to H2, and the training data set and the test data set are constructed based on the second synthetic data and the qualified data set.

[0029] Further, in step S3, the construction of the industrial power distribution safety detection model is to construct a support vector machine, and perform optimal parameter search for the penalty parameters and kernel function parameters of the support vector machine based on a swarm intelligence algorithm, specifically including the following steps:

[0030] Step S31: Initialization, establish a parameter search space for the penalty parameter and the kernel function parameter, randomly initialize the individual position in the parameter search space, use the individual position as the representative of the model parameter, use Python to import the sklearn library to call the SVM function based on the model parameters, train the industrial power distribution safety detection model based on the training data set, and use the hinge loss function of the industrial power distribution safety detection model established based on the model parameters for the test data set as the fitness value of the corresponding individual position;

[0031] Step S32: Adaptive bidirectional mutation, including the following steps:

[0032] Step S321: designing a random slope adjustment factor and a dynamic reversal adjustment factor, the formula used is as follows:

[0033] ;

[0034] ;

[0035] Wherein, and are the random slope adjustment factor and the dynamic inversion adjustment factor during the t-th search respectively, is the dynamic inversion adjustment factor during the (t - 1)-th search, tan(·) is the tangent function, Q is the number of individuals, t is the search number index, and ε is a random number;

[0036] Step S322: Mutation, and the formula used is as follows:

[0037] ;

[0038] Wherein, and are the original position and the mutated position of the q-th individual during the t-th search respectively, is the fitness value of the position of the q-th individual during the t-th search, is the average fitness value of all individual positions during the t-th search, and q is the individual index;

[0039] Step S33: Design the adaptive boundary, and the formula used is as follows:

[0040] ;

[0041] ;

[0042] Wherein, and are the lower bound and the upper bound of the parameter search space during the t-th search respectively, max{·} and min{·} are the maximum value function and the minimum value function respectively, t max is the maximum number of searches, is the best individual position after mutation during the t-th search, and are the initial values of the lower bound and the upper bound of the parameter search space respectively;

[0043] Step S34: Position update. Before the update, a random number in the range (0, 1) is randomly generated for each individual. Based on the adaptive boundary and the random number, and combined with the progressive adjustment factor and the convergence control coefficient to perform the update of the individual position, and the formula used is as follows:

[0044] ;

[0045] Wherein, is the position of the q-th individual during the (t + 1)-th search, is the random number of the q-th individual during the t-th search, and are respectively the progressive adjustment factor and the convergence control coefficient during the t-th search, and are respectively the position correction factor and the attenuation exponent;

[0046] Step S35: Determine the optimal parameters, preset the fitness threshold, update the fitness value of the individual position. When the fitness value of the optimal individual position is less than the fitness threshold, the parameters corresponding to the optimal individual position are the optimal parameters. Based on the optimal parameters, call the SVM function to construct an industrial power distribution safety detection model; otherwise, if the maximum search number is reached, go to step S31 to re-initialize; otherwise, increment the search number by 1 and return to step S32 to continue the search.

[0047] Furthermore, in step S4, the real-time warning is to collect real-time industrial power distribution data, which includes power parameter data, equipment operation data, and environmental data. After preprocessing, it is input into the industrial power distribution safety detection model constructed based on the optimal parameters for processing. Based on the output data label, obtain the real-time safety status of the industrial power distribution and issue a safety warning signal.

[0048] The industrial power distribution safety warning system based on artificial intelligence provided by the present invention includes a data acquisition module, an industrial power distribution data processing module, a module for constructing an industrial power distribution safety detection model, and a real-time warning module;

[0049] The data acquisition module collects historical industrial power distribution data and sends the data to the industrial power distribution data processing module;

[0050] The industrial power distribution data processing module introduces a comprehensive metric value, designs the upper and lower bounds of the noise data boundary, screens and removes noise data, divides the minority class boundary data, minority class safety data, and majority class boundary data based on the nearest neighbor, performs two syntheses of data based on the number of data to be synthesized and the selection probability, and conducts verification of the synthesized data after the first synthesis, and sends the data to the module for constructing an industrial power distribution safety detection model;

[0051] The module for constructing an industrial power distribution safety detection model designs a random slope adjustment factor and a dynamic inversion adjustment factor, performs adaptive bidirectional mutation, designs an adaptive boundary, and updates the position by combining the progressive adjustment factor and the convergence control coefficient to find the optimal parameters, complete the construction of the industrial power distribution safety detection model, and send the data to the real-time warning module;

[0052] The real-time warning module inputs the real-time industrial power distribution data into the industrial power distribution safety detection model constructed based on the optimal parameters for processing, obtains the real-time safety status of the industrial power distribution, and issues a safety warning signal.

[0053] The beneficial effects achieved by the present invention using the above solution are as follows:

[0054] (1) Aiming at the problems in the existing industrial power distribution safety warning methods, such as poor quality of industrial power distribution data, susceptibility to noise data interference, and imbalance in the categories of industrial power distribution data, which lead to insufficient attention and recognition ability for minority categories, and reduce the reliability and credibility of industrial power distribution safety warnings. This solution introduces a comprehensive metric value, designs the upper and lower bounds of the noise data boundary, screens and removes noise data, comprehensively evaluates the characteristics and quality of industrial power distribution data, clarifies the scope of noise data, clears interfering data, improves the quality and reliability of industrial power distribution data, and eliminates the adverse effects of noise on industrial power distribution data analysis and warning; based on the nearest neighbor, divides the boundary data of the minority class, the safety data of the minority class, and the boundary data of the majority class, classifies and defines different category data; performs two syntheses of data based on the required synthesis quantity and selection probability, and verifies the synthesized data after the first synthesis, increases the quantity of minority class data, balances the data categories, ensures the quality and effectiveness of the synthesized data, can more comprehensively learn and process different categories of industrial power distribution data, and improves the reliability and credibility of industrial power distribution safety warnings.

[0055] (2) Aiming at the problems in the existing industrial power distribution safety warning methods, such as the complex and diverse industrial power distribution situations, the data having complex non-linear relationships, and it being difficult to conduct comprehensive and accurate safety detections, resulting in the inability to timely and accurately discover industrial power distribution safety hazards. This solution uses a support vector machine for detection, uses the individual position as a representative of the model parameters, designs a random slope adjustment factor and a dynamic inversion adjustment factor, performs adaptive bidirectional mutation, can more flexibly explore different parameter regions to adapt to complex and diverse industrial power distribution situations; designs an adaptive boundary to adapt to the search requirements at different stages, and avoids the search range being too broad or too narrow; and combines a progressive adjustment factor and a convergence control coefficient for position update to find the optimal parameters, completes the construction of the industrial power distribution safety detection model, can move more effectively in the search space, ensures that the obtained parameters can meet the accuracy requirements for industrial power distribution safety detection, and conducts industrial power distribution safety detection accurately and timely, improving the effect and reliability of safety warnings. Brief Description of the Drawings

[0056] Figure 1 It is a schematic flowchart of the industrial power distribution safety warning method based on artificial intelligence provided by the present invention;

[0057] Figure 2 It is a schematic diagram of the industrial power distribution safety warning system based on artificial intelligence provided by the present invention;

[0058] Figure 3 It is a schematic flowchart of step S2;

[0059] Figure 4 It is a schematic flow diagram of step S3.

[0060] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. They are used together with the embodiments of the present invention to explain the present invention, but do not constitute a limitation to the present invention. Specific embodiments

[0061] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0062] In the description of the present invention, it should be understood that the terms "upper", "lower", "front", "rear", "left", "right", "top", "bottom", "inner", "outer", etc. indicating the orientation or position relationship are based on the orientation or position relationship shown in the accompanying drawings. It is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and thus should not be construed as a limitation to the present invention.

[0063] Embodiment 1, referring to Figure 1 , the industrial power distribution safety warning method based on artificial intelligence provided by the present invention includes the following steps:

[0064] Step S1: Data collection, collecting historical industrial power distribution data;

[0065] Step S2: Industrial power distribution data processing, introducing a comprehensive metric value, designing the upper and lower bounds of the noise data boundary, screening and removing noise data, partitioning the minority class boundary data, minority class safety data, and majority class boundary data based on the nearest neighbor, performing two syntheses of data based on the quantity to be synthesized and the selection probability, and verifying the synthesized data after the first synthesis;

[0066] Step S3: Constructing an industrial power distribution safety detection model, designing a random slope adjustment factor and a dynamic inversion adjustment factor, performing adaptive bidirectional mutation, designing an adaptive boundary, and updating the position by combining a progressive adjustment factor and a convergence control coefficient to find the optimal parameters and complete the construction of the industrial power distribution safety detection model;

[0067] Step S4: Real-time warning, inputting the real-time industrial power distribution data into the industrial power distribution safety detection model constructed based on the optimal parameters for processing, obtaining the real-time safety status of the industrial power distribution, and sending out a safety warning signal.

[0068] Example 2. Refer to Figure 1 In this example, based on the above example, in step S1, the historical industrial power distribution data includes power parameter data, equipment operation data, environmental data, and safety status; the power parameter data includes voltage, current, power, and frequency; the equipment operation data includes switch status, load status, maintenance records, and operation time data; the environmental data includes temperature, humidity, and air quality; the safety status includes normal, slightly abnormal, moderately abnormal, and severely abnormal, and the safety status is used as the data label.

[0069] Example 3. Refer to Figure 1 and Figure 3 In this example, based on the above example, in step S2, the processing of industrial power distribution data specifically includes the following steps:

[0070] Step S21: Preprocessing, performing data cleaning, data conversion, and data normalization on the collected industrial power distribution data; data cleaning includes processing outliers, duplicate values, and missing values; data conversion is to convert the data into vector form; data normalization is to unify the data range based on the maximum-minimum normalization method;

[0071] Step S22: Removing noise data, constructing an industrial power distribution data set based on the preprocessed data, and dividing the industrial power distribution data set into a minority class data set and a majority class data set, calculating the average value of all industrial power distribution data in the minority class data set and then calculating the Euclidean distance and kernel density estimation between each industrial power distribution data in the minority class data set and the average value , taking the product of the Euclidean distance and the kernel density estimation as the comprehensive metric value of each industrial power distribution data, sorting the comprehensive metric values in ascending order, and selecting and as the first reference metric c1 and the second reference metric c2, setting the upper bound ub and the lower bound lb of the noise data boundary based on the reference metrics, and taking the industrial power distribution data in the minority class data set whose comprehensive metric value is greater than the upper bound ub or less than the lower bound lb as noise data, and deleting the noise data from the minority class data set. The formulas used are as follows:

[0072] ;

[0073] ;

[0074] where r is a control factor in the range of (1, 3), x i and x j are the i-th and j-th industrial power distribution data in the minority class data set, is x iKernel density estimation, where i and j are industrial power distribution data indices, K(·) is the kernel function, h is the bandwidth, and N min is the number of industrial power distribution data in the minority class dataset;

[0075] Step S23: Division. Calculate the k nearest neighbors of each industrial power distribution data in the minority class dataset within the industrial power distribution dataset. If not all of the k nearest neighbors are data within the minority class dataset, mark the corresponding industrial power distribution data in the minority class dataset as minority class boundary data; otherwise, mark the corresponding industrial power distribution data in the minority class dataset as minority class safe data. Then calculate the Euclidean distance between each industrial power distribution data in the minority class dataset and its k nearest neighbors respectively, and mark the nearest neighbor with the smallest Euclidean distance d min and belonging to the majority class dataset as majority class boundary data, and mark d min as the specific metric value of this majority class boundary data. Construct a first reference dataset, a second reference dataset, and a detection dataset based on the minority class boundary data, the minority class safe data, and the majority class boundary data respectively;

[0076] Step S24: First synthetic data, including the following steps:

[0077] Step S241: Calculate the first quantity to be synthesized, using the following formula:

[0078] ;

[0079] In the formula, H1 is the first quantity to be synthesized, N min and N max are the numbers of industrial power distribution data in the minority class dataset and the majority class dataset respectively;

[0080] Step S242: Calculate the selection probability, using the following formula:

[0081] ;

[0082] In the formula, x v is the v-th minority class boundary data in the first reference dataset, g v is the selection probability of x v , v is the industrial power distribution data index, a1 and a2 are the first adjustment factor and the second adjustment factor respectively, d v is the Euclidean distance between x v and the average value , is the kernel density estimation of x v ;

[0083] Step S243: Synthesize data. Randomly extract data from the first reference dataset based on the selection probability, and perform the first synthesis of data based on the extracted data and the average value until the number of synthesized data is equal to H1. Then, construct a synthetic dataset based on the first synthesized data and the industrial power distribution dataset. The formula used is as follows: ; and construct a synthetic dataset based on the first synthesized data and the industrial power distribution dataset. The formula used is as follows:

[0084] ;

[0085] In the formula, is the w-th data synthesized for the first time, rand(0, 1) is a random number generated between (0, 1), x abs is the extracted data, and w is the synthetic data index;

[0086] Step S244: Validate the synthesized data. Calculate the k nearest neighbors of each majority class boundary data in the detection dataset in the synthetic dataset. If the k nearest neighbors include the synthesized data , then calculate the Euclidean distance between the majority class boundary data and the synthesized data . If , then delete the synthesized data from the synthetic dataset to obtain a qualified dataset, and obtain the number A of data in the qualified dataset.

[0087] Step S25: Second synthesis of data. Calculate the number H2 to be synthesized for the second time as H2 = H1 - A, and calculate the selection probability of each minority class safety data in the second reference dataset. Randomly extract data from the second reference dataset based on the selection probability, and perform the second synthesis of data based on the extracted data and the average value until the number of synthesized data is equal to H2. Then, construct a training dataset and a test dataset based on the second synthesized data and the qualified dataset. until the number of synthesized data is equal to H2, and construct a training dataset and a test dataset based on the second synthesized data and the qualified dataset.

[0088] By performing the above operations, aiming at the problems existing in the existing industrial power distribution safety warning methods, such as poor quality of industrial power distribution data and susceptibility to noise data interference, as well as unbalanced industrial power distribution data categories, resulting in insufficient attention and recognition ability for minority categories, and reducing the reliability and credibility of industrial power distribution safety warning, this solution introduces a comprehensive metric value, designs the upper and lower bounds of the noise data boundary, screens and removes noise data, comprehensively evaluates the characteristics and quality of industrial power distribution data, clarifies the range of noise data, cleans up interfering data, improves the quality and reliability of industrial power distribution data, and eliminates the adverse effects of noise on industrial power distribution data analysis and warning; divides the minority class boundary data, minority class safety data, and majority class boundary data based on the nearest neighbor, classifies and defines different category data; synthesizes data twice based on the quantity to be synthesized and the selection probability, and conducts verification of the synthesized data after the first synthesis, increases the quantity of minority class data, balances the data categories, ensures the quality and effectiveness of the synthesized data, can learn and process different categories of industrial power distribution data more comprehensively, and improves the reliability and credibility of industrial power distribution safety warning.

[0089] Example 4, refer to Figure 1 and Figure 4 , based on the above example, in step S3, the industrial power distribution safety detection model is constructed as a support vector machine, and the penalty parameter and kernel function parameter of the support vector machine are searched for the optimal parameters based on the swarm intelligence algorithm, which specifically includes the following steps:

[0090] Step S31: Initialization, establish a parameter search space for the penalty parameter and kernel function parameter, randomly initialize the individual positions within the parameter search space, use the individual positions as representatives of the model parameters, import the sklearn library using python to call the SVM function based on the model parameters, train the industrial power distribution safety detection model based on the training dataset, and use the hinge loss function of the industrial power distribution safety detection model established based on the model parameters for the test dataset as the fitness value corresponding to the individual position;

[0091] Step S32: Adaptive bidirectional mutation, including the following steps:

[0092] Step S321: Design a random slope adjustment factor and a dynamic inversion adjustment factor, and the used formulas are as follows:

[0093] ;

[0094] ;

[0095] In the formula, and are the random slope adjustment factor and the dynamic inversion adjustment factor at the t-th search respectively, is the dynamic inversion adjustment factor during the (t - 1)-th search, tan(·) is the tangent function, Q is the number of individuals, t is the search number index, and ε is a random number within the range of [0, 1];

[0096] Step S322: Mutation. If the fitness of an individual's position is lower than the average fitness value, a positive mutation is performed using a random slope adjustment factor; if the fitness of an individual's position is greater than or equal to the average fitness value, a negative mutation is performed using the dynamic inversion adjustment factor. The formula used is as follows:

[0097] ;

[0098] In the formula, and are the original position and the mutated position of the q-th individual during the t-th search respectively, is the fitness value of the q-th individual's position during the t-th search, is the average fitness value of all individuals' positions during the t-th search, and q is the individual index;

[0099] Step S33: Design an adaptive boundary. The formula used is as follows:

[0100] ;

[0101] ;

[0102] In the formula, and are the lower bound and the upper bound of the parameter search space during the t-th search respectively, max{·} and min{·} are the maximum value function and the minimum value function respectively, t max is the maximum number of searches, is the best individual position after mutation during the t-th search. The best individual position is the position of the individual with the smallest fitness value, and are the initial values of the lower bound and the upper bound of the parameter search space respectively;

[0103] Step S34: Position update. Before the update, a random number in the range of (0, 1) is randomly generated for each individual. Based on the adaptive boundary and the random number, and combined with the progressive adjustment factor and the convergence control coefficient the position of the individual is updated. The formula used is as follows:

[0104] ;

[0105] In the formula, is the position of the q-th individual during the (t + 1)-th search, is the random number of the q-th individual during the t-th search, and are the progressive adjustment factor and the convergence control coefficient during the t-th search respectively, and are the position correction factor and the attenuation exponent within the range of (0, 1) respectively;

[0106] Step S35: Determine the optimal parameters, preset the fitness threshold, update the fitness value of the individual position. When the fitness value of the optimal individual position is less than the fitness threshold, the parameters corresponding to the optimal individual position are the optimal parameters. Based on the optimal parameters, call the SVM function to construct an industrial power distribution safety detection model; otherwise, if the maximum search times are reached, go to Step S31 to re-initialize; otherwise, increment the search times by 1 and return to Step S32 to continue the search.

[0107] By performing the above operations, aiming at the problem that the existing industrial power distribution safety warning methods have complex and diverse industrial power distribution situations, the data has complex non-linear relationships, it is difficult to conduct comprehensive and accurate safety detections, resulting in the inability to timely and accurately discover industrial power distribution safety hazards, this solution uses a support vector machine for detection, uses the individual position as a representative of the model parameters, designs a random slope adjustment factor and a dynamic inversion adjustment factor, conducts adaptive bidirectional mutation, can explore different parameter regions more flexibly to adapt to complex and diverse industrial power distribution situations; designs an adaptive boundary to adapt to the search requirements at different stages, and avoids the search range being too broad or too narrow; and combines the progressive adjustment factor and the convergence control coefficient for position update to find the optimal parameters, complete the construction of the industrial power distribution safety detection model, can move more effectively in the search space, ensure that the obtained parameters can meet the accuracy requirements for industrial power distribution safety detection, conduct industrial power distribution safety detection accurately and timely, and improve the effect and reliability of safety warning.

[0108] Example Five, refer to Figure 1 , this example is based on the above example. In Step S4, real-time warning is to collect real-time industrial power distribution data, and the real-time industrial power distribution data includes power parameter data, equipment operation data and environmental data. After preprocessing, it is input into the industrial power distribution safety detection model constructed based on the optimal parameters for processing. Based on the output data label, obtain the real-time safety status of industrial power distribution and issue a safety warning signal.

[0109] Example Six, refer to Figure 2 , this example is based on the above example. The industrial power distribution safety warning system based on artificial intelligence provided by the present invention includes a data acquisition module, an industrial power distribution data processing module, a module for constructing an industrial power distribution safety detection model, and a real-time warning module;

[0110] The data acquisition module collects historical industrial power distribution data and sends the data to the industrial power distribution data processing module;

[0111] The industrial power distribution data processing module introduces a comprehensive metric value, designs the upper and lower bounds of the noise data boundary, filters and removes noise data, divides the minority class boundary data, minority class safe data, and majority class boundary data based on the nearest neighbor, performs two syntheses of data based on the required synthesis quantity and selection probability, verifies the synthesized data after the first synthesis, and sends the data to the module for constructing an industrial power distribution safety detection model;

[0112] The module for constructing an industrial power distribution safety detection model designs a random slope adjustment factor and a dynamic inversion adjustment factor, performs adaptive bidirectional mutation, designs an adaptive boundary, and updates the position by combining a progressive adjustment factor and a convergence control coefficient to find the optimal parameters, completes the construction of the industrial power distribution safety detection model, and sends the data to the real-time warning module;

[0113] The real-time warning module inputs the real-time industrial power distribution data into the industrial power distribution safety detection model constructed based on the optimal parameters for processing, obtains the real-time safety status of the industrial power distribution, and issues a safety warning signal.

[0114] It should be noted that in this article, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements not only includes those elements, but also includes other elements not expressly listed, or elements inherent to such process, method, article or device.

[0115] Although the embodiments of the present invention have been shown and described, those of ordinary skill in the art can understand that various changes, modifications, substitutions and variations can be made to these embodiments without departing from the principles and spirit of the present invention.

[0116] The above describes the present invention and its implementation manners, and this description is not restrictive. What is shown in the drawings is only one of the implementation manners of the present invention, and the actual structure is not limited thereto. Generally speaking, if those of ordinary skill in the art are inspired by it and design similar structural manners and embodiments without creative efforts without departing from the purpose of the present invention, they shall fall within the protection scope of the present invention.

Claims

1. An industrial power distribution safety early warning method based on artificial intelligence, characterized by: The method comprises the following steps: Step S1: data collection, collecting historical industrial power distribution data; Step S2: industrial power distribution data processing; Step S3: construct an industrial power distribution safety detection model; Step S4: real-time warning, inputting the real-time industrial power distribution data into the industrial power distribution safety detection model constructed based on the optimal parameters for processing, obtaining the real-time safety status of the industrial power distribution, and issuing a safety warning signal; Step S2 includes step S22: removing noise data, constructing an industrial power distribution data set based on the preprocessed data, and dividing the industrial power distribution data set into a minority class data set and a majority class data set, and calculating the average value of all industrial power distribution data in the minority class data set. , and then calculate the average value of each industrial power distribution data in the minority class data set The Euclidean distance and kernel density estimation between them are used, and the product of the Euclidean distance and the kernel density estimation is used as the comprehensive metric value of each industrial power distribution data. The comprehensive metric values ​​are sorted in ascending order and selected. and The comprehensive metric value at the position is used as the first reference metric c1 and the second reference metric c2. The upper bound ub and the lower bound 1b of the noise data boundary are set based on the reference metric. The industrial power distribution data with a comprehensive metric value greater than the upper bound ub or less than the lower bound lb in the minority class data set is used as noise data, and the noise data is deleted from the minority class data set. The formula used is as follows: ； ； Where r is the control factor; In step S3, the construction of the industrial power distribution safety detection model is to construct a support vector machine, and perform optimal parameter search for the penalty parameters and kernel function parameters of the support vector machine based on a swarm intelligence algorithm, specifically including the following steps: Step S31: Initialization, establish a parameter search space for the penalty parameter and the kernel function parameter, randomly initialize the individual position in the parameter search space, use the individual position as the representative of the model parameter, use Python to import the sklearn library to call the SVM function based on the model parameters, train the industrial power distribution safety detection model based on the training data set, and use the hinge loss function of the industrial power distribution safety detection model established based on the model parameters for the test data set as the fitness value of the corresponding individual position; Step S32: Adaptive bidirectional mutation; Step S33: Design an adaptive boundary, the formula used is as follows: ； ； In the formula, and are the lower and upper bounds of the parameter search space for the t-th search, max{·} and min{·} are the maximum and minimum functions, respectively. max is the maximum number of searches, is the best individual position after mutation in the t-th search, and are the lower and upper bound initial values ​​of the parameter search space, respectively, and t is the search count index; Step S34: Position update. Before the update, a random number (0, 1) is randomly generated for each individual, based on the adaptive boundary and random number, combined with the gradual adjustment factor and convergence control coefficient To update the individual position, the formula used is as follows: ； In the formula, is the position of the qth individual in the t+1th search, is the random number of the qth individual in the tth search, and are the asymptotic adjustment factor and convergence control coefficient during the t-th search, and are the position correction factor and the attenuation exponent, respectively. is the position of the qth individual after mutation in the tth search; Step S35: Determine the optimal parameters, pre-set the fitness threshold, update the fitness value of the individual position, when the fitness value of the best individual position is less than the fitness threshold, the parameters corresponding to the best individual position are the optimal parameters, and the SVM function is called based on the optimal parameters to build an industrial power distribution safety detection model; otherwise, if the maximum number of searches is reached, go to step S31 to reinitialize; otherwise, add 1 to the number of searches and return to step S32 to continue searching.

2. The industrial power distribution safety early warning method based on artificial intelligence according to claim 1 is characterized in that: In step S32, the adaptive bidirectional mutation specifically includes the following steps: Step S321: designing a random slope adjustment factor and a dynamic reversal adjustment factor, the formula used is as follows: ； ； In the formula, and are the random slope adjustment factor and dynamic reversal adjustment factor during the t-th search, is the dynamic inversion adjustment factor at the t-1th search, tan(·) is the tangent function, Q is the number of individuals, t is the search index, and ε is a random number; Step S322: mutation, the formula used is as follows: ； In the formula, and are the original position and the position after mutation of the qth individual in the tth search, is the fitness value of the position of the qth individual in the tth search, is the average fitness value of all individual positions during the t-th search, and q is the individual index.

3. The industrial power distribution safety early warning method based on artificial intelligence according to claim 1 is characterized in that: In step S2, the industrial power distribution data processing specifically includes the following steps: Step S21: preprocessing, data cleaning, data conversion and data normalization processing are performed on the collected industrial power distribution data; data cleaning includes processing abnormal values, duplicate values ​​and missing values; data conversion is to convert the data into vector form; data normalization is to unify the data range based on the maximum and minimum normalization method; Step S22: removing noise data; Step S23: partition, calculate the k nearest neighbors of each industrial power distribution data in the minority class data set in the industrial power distribution data set; if the k nearest neighbors are not all data in the minority class data set, then mark the corresponding industrial power distribution data in the minority class data set as minority class boundary data; otherwise, mark the corresponding industrial power distribution data in the minority class data set as minority class safety data; then calculate the Euclidean distance between each industrial power distribution data in the minority class data set and its k nearest neighbors, and the one with the smallest Euclidean distance d min The nearest neighbor belonging to the majority class data set is marked as the majority class boundary data, and d min as a specific measurement value of the majority class boundary data; constructing a first reference data set, a second reference data set and a detection data set based on the minority class boundary data, the minority class safety data and the majority class boundary data respectively; Step S24: synthesizing data for the first time; Step S25: synthesize data for the second time, calculate the number of synthesized data H2 = H1-A, and calculate the selection probability of each minority class safety data in the second reference data set. Based on the selection probability, randomly extract data from the second reference data set, and based on the extracted data and the average value Perform the second synthesis of data until the amount of synthesized data is equal to H2, and build the training data set and the test data set based on the second synthesis data and the qualified data set; where H1 is the amount of data to be synthesized for the first time, and A is the amount of data in the qualified data set.

4. The artificial intelligence-based industrial power distribution safety early warning method according to claim 3 is characterized in that: In step S24, the first synthesis of data specifically includes the following steps: Step S241: Calculate the first required synthesis quantity, the formula used is as follows: ； In the formula, H1 is the number of synthesized items required for the first time, N min and N max are the number of industrial power distribution data in the minority class dataset and the majority class dataset, respectively; Step S242: Calculate the selection probability, using the following formula: ； In the formula, x v is the vth minority class boundary data in the first reference dataset, g v is x v The selection probability of , v is the industrial power distribution data index, a1 and a2 are the first adjustment factor and the second adjustment factor, respectively, d v is x v With the average The Euclidean distance between is x v Kernel density estimation of ; Step S243: Synthesize data by randomly extracting data from the first reference data set based on the selection probability, and then The first synthetic data is performed until the number of synthetic data is equal to H1, and a synthetic data set is constructed based on the first synthetic data and the industrial power distribution data set. The formula used is as follows: ； In the formula, is the synthetic data, representing the wth data of the first synthesis; rand(0,1) generates a random number between (0,1), x abs is the extracted data, w is the synthetic data index; Step S244: Synthetic data verification, calculate the k nearest neighbors of each majority class boundary data in the detection data set in the synthetic data set, if the k nearest neighbors contain synthetic data , then calculate the majority class boundary data and synthetic data The Euclidean distance between ,like , then the synthetic data Delete from the synthetic data set to obtain a qualified data set, and obtain the number of data A in the qualified data set.

5. The industrial power distribution safety early warning method based on artificial intelligence according to claim 1 is characterized in that: In step S1, the data collection is to collect historical industrial power distribution data; the historical industrial power distribution data includes power parameter data, equipment operation data, environmental data and safety status; the power parameter data includes voltage, current, power and frequency; the equipment operation data includes switch status, load status, maintenance records and operating time data; the environmental data includes temperature, humidity and air quality; the safety status includes normal, slight abnormality, moderate abnormality and severe abnormality, and the safety status is used as a data label.

6. The industrial power distribution safety early warning method based on artificial intelligence according to claim 1 is characterized in that: In step S4, the real-time warning is to collect real-time industrial power distribution data, which includes power parameter data, equipment operation data and environmental data. After pre-processing, the data is input into the industrial power distribution safety detection model constructed based on the optimal parameters for processing. Based on the output data label, the real-time safety status of the industrial power distribution is obtained, and a safety warning signal is issued.

7. An artificial intelligence-based industrial power distribution safety early warning system, used to implement the artificial intelligence-based industrial power distribution safety early warning method as described in any one of claims 1 to 6, characterized in that: It includes data acquisition module, industrial power distribution data processing module, industrial power distribution safety detection model building module and real-time warning module; The data acquisition module collects historical industrial power distribution data and sends the data to the industrial power distribution data processing module; The industrial power distribution data processing module introduces a comprehensive metric value, designs the upper and lower bounds of the noise data boundary, screens and removes noise data, divides minority class boundary data, minority class safety data and majority class boundary data based on the nearest neighbor, synthesizes data twice based on the required number of synthesized and the selection probability, verifies the synthesized data after the first synthesis, and sends the data to the module for building an industrial power distribution safety detection model; The module for constructing the industrial power distribution safety detection model designs a random slope adjustment factor and a dynamic reversal adjustment factor, performs adaptive bidirectional mutation, designs an adaptive boundary, and combines the progressive adjustment factor and the convergence control coefficient to perform position update, find the optimal parameters, complete the construction of the industrial power distribution safety detection model, and send the data to the real-time warning module; The real-time warning module inputs real-time industrial power distribution data into an industrial power distribution safety detection model constructed based on optimal parameters for processing, obtains the real-time safety status of industrial power distribution, and issues a safety warning signal.

Images