Power safety production method, system, equipment and medium combined with power organizations

Abstract

The present invention relates to the field of information technology, and discloses a power safety production method, system, device and medium combined with a power organization. The method includes obtaining real-time operation data of power equipment; performing anomaly detection on the real-time operation data through a hybrid multi-objective optimization algorithm to obtain abnormal operation data; the hybrid multi-objective optimization algorithm is a particle swarm algorithm combined with chaotic initialization, dynamic inertia weight and fuzzy logic; determining a response plan and a potential hazard level of the power equipment according to the abnormal operation data; based on the potential hazard level, matching target personnel from a power organization database through an artificial intelligence matching algorithm and executing the response plan to achieve the safe production of the power equipment, thereby greatly improving the safe production efficiency of the power equipment and reducing the social impact and economic losses caused by power accidents.

Description

Technical Field

[0001] The present invention relates to the field of information technology, and in particular, to a power safety production method, system, device and medium combined with a power organization. Background Art

[0002] In the process of power safety production, the abnormal detection of power equipment, the formulation of countermeasures, and the matching of implementers are becoming increasingly important.

[0003] Currently, most enterprises usually use sensors to monitor the working state of power equipment in real time, such as changes in parameters such as pressure, temperature, and humidity, to determine whether the equipment is in a normal working state. However, this method is inefficient; when formulating countermeasures and allocating implementers, it usually relies on the experience of technicians. However, the training cycle of technicians is long and the number is small, resulting in the decreasing efficiency of existing power safety production.

[0004] Therefore, how to solve the problem of low efficiency of existing power safety production has become a technical problem that needs to be urgently solved by technicians in this field. Summary of the Invention

[0005] The present invention provides a power safety production method, system, device and medium combined with a power organization to solve the problem of how to improve the efficiency of existing power safety production.

[0006] To solve the above technical problems, the first aspect of the present invention provides a power safety production method combined with a power organization, including:

[0007] Obtain the real-time operation data of power equipment;

[0008] Perform abnormal detection on the real-time operation data through a hybrid multi-objective optimization algorithm to obtain abnormal operation data; the hybrid multi-objective optimization algorithm is a particle swarm algorithm combined with chaotic initialization, dynamic inertia weight and fuzzy logic;

[0009] Determine the countermeasure plan and potential hazard level of the power equipment according to the abnormal operation data;

[0010] Based on the potential hazard level, match target personnel from the power organization database through an artificial intelligence matching algorithm and execute the countermeasure plan to achieve the safe production of the power equipment.

[0011] As a preferred solution, the performing abnormal detection on the real-time operation data through a hybrid multi-objective optimization algorithm to obtain abnormal operation data includes:

[0012] Generate the initial position of the particle swarm through chaotic mapping and initialize the velocity of each particle; each particle is a set of detection thresholds for the real-time operation data of the power equipment;

[0013] Construct a multi-objective function based on the false alarm rate, response speed, and computing resource consumption of the power equipment, and adjust the weight coefficients of each objective according to the preset service requirements through the fuzzy logic and its corresponding fuzzy rule base to obtain a multi-objective optimization function;

[0014] Take the multi-objective optimization function as the fitness function to calculate the fitness of each particle, and update the individual optimal position and global optimal position of the particle swarm based on the fitness calculation result, so as to adjust the speed and position of each particle through the particle swarm speed and position update formula introducing the dynamic inertia weight;

[0015] Iteratively execute the fitness calculation and the adjustment process of the particle speed and position according to the adjusted particle swarm, obtain several global optimal positions to construct a Pareto solution set, and screen the Pareto solution set through the non-dominated sorting method to obtain the optimal detection threshold;

[0016] Perform anomaly detection on the real-time operation data through the optimal detection threshold to obtain anomaly operation data.

[0017] As one of the preferred solutions, the dynamic inertia weight is expressed by the following formula:

[0018]

[0019]

[0020] In the formula, is the dynamic inertia weight; , are the minimum and maximum values of the dynamic inertia weight respectively; is the attenuation coefficient; t is the number of iterations; is the aggregation degree of the particle swarm; is the influence adjustment factor of the aggregation degree; is the total number of the particle swarm; is the position of the i-th particle; is the center of the particle swarm; is the Euclidean distance.

[0021] As one of the preferred solutions, the determining the countermeasure and hidden danger level of the power equipment according to the abnormal operation data includes:

[0022] Process the abnormal operation data through a risk assessment model to obtain a comprehensive risk score, and determine the countermeasure of the power equipment based on the comprehensive risk score; wherein, the risk assessment model is expressed by the following formula:

[0023]

[0024] In the formula, is the comprehensive risk score; is the importance factor of the nth power equipment; is the status correction factor of the nth power equipment; is the risk adjustment coefficient; M is the total number of power equipment.

[0025] As one of the preferred solutions, determining the response plan and potential hazard level of the power equipment according to the abnormal operation data further includes:

[0026] Determine the type of potential hazard of the power equipment according to the abnormal operation data, quantify the potential hazard level of the power equipment through a potential hazard assessment model, and calculate the severity of each type of potential hazard to obtain a potential hazard severity score; wherein, the potential hazard assessment model is expressed by the following formula:

[0027]

[0028] In the formula, is the potential hazard level; is the importance weight of the ath type of potential hazard; is the treatment weight of the ath type of potential hazard; A is the total number of types of potential hazards.

[0029] As one of the preferred solutions, based on the potential hazard level, matching target personnel from the power organization database through an artificial intelligence matching algorithm and implementing the response plan to achieve the safe production of the power equipment includes:

[0030] Obtain the real-time environmental data of the power equipment and the basic data of each person in the power organization database, and construct the potential hazard level, the real-time environmental data and each basic data as input features;

[0031] Process the input features through a deep learning network model constructed by a multi-layer perceptron to obtain the skill matching degree of each person, and use machine learning algorithms and reinforcement learning algorithms to optimize the skill matching degree of each person to obtain the optimized skill matching result of each person;

[0032] Based on the optimized skill matching result and the potential hazard severity score, construct a multi-objective matching function model, and use the particle swarm optimization algorithm to perform a global search on the multi-objective matching function model to obtain the target personnel and implement the response plan to achieve the safe production of the power equipment.

[0033] As one of the preferred solutions, using machine learning algorithms and reinforcement learning algorithms to optimize the skill matching degree of each person to obtain the optimized skill matching result of each person includes:

[0034] Process the severity score of the potential hazard through the Isolation Forest algorithm to obtain an optimized score, and adjust the skill matching degree of each person according to the optimized score to obtain the comprehensive matching degree of each person;

[0035] Use the potential hazard level and the comprehensive matching degree of each person as status information, define the action of determining a candidate person from the power organization database, assign an agent to each person, and construct a reward function for the time, completion degree, and resource waste amount required for the agent to execute the countermeasure plan,

[0036] With the goal of maximizing the cumulative reward, optimize the skill matching degree of each person through the Deep Q Network to obtain the optimized result of the skill matching of each person.

[0037] The second aspect of the present invention provides a power safety production system combined with a power organization, including:

[0038] A data acquisition module for acquiring real-time operation data of power equipment;

[0039] An anomaly detection module for detecting anomalies in the real-time operation data through a hybrid multi-objective optimization algorithm to obtain anomaly operation data; the hybrid multi-objective optimization algorithm is a particle swarm algorithm combined with chaotic initialization, dynamic inertia weight, and fuzzy logic;

[0040] A level determination module for determining the countermeasure plan and potential hazard level of the power equipment according to the anomaly operation data;

[0041] A personnel matching module for matching target personnel from the power organization database based on the potential hazard level and executing the countermeasure plan to achieve the safe production of the power equipment.

[0042] The third aspect of the present invention provides an electronic device, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, it implements the power safety production method combined with a power organization as described above.

[0043] The fourth aspect of the present invention provides a computer-readable storage medium, which includes a stored computer program. When the device where the computer-readable storage medium is located executes the computer program, it implements the power safety production method combined with a power organization as described above.

[0044] Compared with the prior art, the beneficial effects of the embodiments of the present invention are at least one of the following:

[0045] (1) Through the application of real-time data acquisition and hybrid multi-objective optimization algorithms, continuous and efficient monitoring of the operating status of power equipment can be achieved, abnormal situations can be detected and processed in a timely manner, thereby improving the monitoring efficiency and accuracy;

[0046] (2) According to the response plans and potential hazard levels determined based on abnormal operation data, targeted treatment measures can be formulated to avoid waste of resources and ineffective investment. At the same time, through artificial intelligence matching algorithms, precise matching of personnel can be achieved to ensure the effective implementation of response plans;

[0047] (3) By comprehensively applying advanced technologies and management means, potential safety hazards of power equipment can be detected and processed in a timely manner, accidents can be effectively prevented, thereby enhancing the safety production guarantee ability of power enterprises. Combining the power organization database with the safety production of power equipment not only improves the management level of power equipment but also promotes the innovation and development of power organization work. Brief Description of the Drawings

[0048] To more clearly illustrate the technical solutions of the present invention, the drawings required for implementation will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0049] Figure 1 is a flowchart of a power safety production method combining a power organization provided by an embodiment of the present invention;

[0050] Figure 2 is a structural diagram of a power safety production system combining a power organization provided by an embodiment of the present invention;

[0051] Figure 3 is a structural diagram of an electronic device provided by an embodiment of the present invention. Detailed Embodiments

[0052] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings and embodiments. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. The purpose of providing these embodiments is to make the public content of the present invention more thorough and comprehensive. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present invention.

[0053] In the description of this application, the terms "first", "second", "third", etc. are only used for descriptive purposes and cannot be construed as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, features defined with "first", "second", "third", etc. may explicitly or implicitly include one or more of such features. In the description of this application, unless otherwise stated, the meaning of "a plurality" is two or more.

[0054] In the description of this application, it should be noted that unless otherwise clearly specified and defined, the terms "installed", "connected", "coupled" should be understood in a broad sense. For example, it may be a fixed connection, a detachable connection, or an integral connection; it may be a mechanical connection or an electrical connection; it may be directly connected or indirectly connected through an intermediate medium, and it may be the communication inside two components. The terms "vertical", "horizontal", "left", "right", "up", "down" and similar expressions used herein are only for the purpose of illustration and do not indicate or imply that the indicated system or component must have a specific orientation, be constructed and operated in a specific orientation, and thus cannot be construed as a limitation on the present invention. The term "and / or" used herein includes any and all combinations of one or more of the related listed items. For those of ordinary skill in the art, the specific meanings of the above terms in this application can be understood according to specific circumstances.

[0055] In the description of this application, it should be noted that unless otherwise defined, all technical and scientific terms used in this invention have the same meaning as commonly understood by those skilled in the technical field to which this belongs. The terms used in the specification of this invention are only for the purpose of describing specific embodiments and are not intended to limit this invention. For those of ordinary skill in the art, the specific meanings of the above terms in this application can be understood according to specific circumstances.

[0056] In one embodiment, as Figure 1 shown, the first aspect of the present invention provides a method for safe production of electric power combined with electric power organization, including:

[0057] S1. Obtain the real-time operation data of the electric power equipment;

[0058] S2. Perform anomaly detection on the real-time operation data through a hybrid multi-objective optimization algorithm to obtain anomaly operation data; the hybrid multi-objective optimization algorithm is a particle swarm algorithm combined with chaotic initialization, dynamic inertia weight and fuzzy logic;

[0059] S3. Determine the countermeasure and potential hazard level of the electric power equipment according to the anomaly operation data;

[0060] S4. Based on the hidden danger level, match target personnel from the power organization database through an artificial intelligence matching algorithm and execute the corresponding solution to achieve the safe production of the power equipment.

[0061] Specifically, through advanced sensor technology and data acquisition system, the present invention can obtain the operation data of power equipment in real time. These data include but are not limited to key parameters such as current, voltage, temperature, vibration, etc. The power equipment includes transformers, generators, motors, switchgear, power supplies, etc. Then, the hidden danger level and the corresponding solution correspond to the number of power equipment. That is to say, each power equipment has its corresponding hidden danger level and corresponding solution.

[0062] There are multiple challenges in the abnormal detection of power equipment: the sensor data of the equipment is diverse and dynamically changing, and it is necessary to adjust and optimize the strategy in real time to maintain the detection accuracy and response speed. In this environment, the traditional particle swarm optimization algorithm may fail due to the local optimum problem, while the genetic algorithm has a strong global search ability but a relatively slow convergence speed. To overcome the shortcomings of both and process various complex and dynamic monitoring data in power equipment, the present invention proposes an innovative solution based on a hybrid multi-objective optimization algorithm. This solution combines adaptive chaotic initialization, dynamic inertia weight, and fuzzy logic decision-making, which can effectively handle various complex scenarios in the operation of power equipment, enhance the efficiency and stability of the algorithm, and at the same time handle the conflicts and trade-offs between multiple objectives, and then detect the abnormalities in the real-time operation data of power equipment; among them, chaotic initialization: the traditional particle swarm initialization method may cause the particle swarm to fall into the local optimum, and the chaotic initialization generated by the introduction of the chaotic mapping increases the randomness and diversity of the initialized particles and improves the search breadth; dynamic inertia weight: by adaptively adjusting the dynamic inertia weight, it can flexibly switch between global search and local search. Especially during the monitoring of power equipment, data such as temperature, current, and voltage fluctuate greatly, and a flexible search strategy is required to quickly capture abnormal changes; fuzzy logic decision-making: by introducing fuzzy logic and its corresponding fuzzy rule base, the conflicts between multiple objectives are dynamically adjusted, so as to improve the adaptive ability of the solution and ensure that the power equipment control system can flexibly respond to different working scenarios (such as abnormal detection in high-load and high-temperature environments). The present invention utilizes the powerful search ability and optimization performance of the hybrid multi-objective optimization algorithm to accurately and quickly locate equipment failures or potential problems to improve the efficiency of power safety production.

[0063] Then, based on the detected abnormal operation data, combined with the historical data and expert knowledge of the power equipment, determine the corresponding solution and the hidden danger level; among them, the hidden danger level is usually divided into different levels such as urgent, important, general, etc., and can also be represented by numerical values for subsequent corresponding measures.

[0064] Finally, based on the determined potential hazard levels, an artificial intelligence matching algorithm is used to screen out personnel from the power organization database who match the target tasks and execute the response plan, making full use of the personnel information in the power organization database, including professional skills, work experience, emergency handling capabilities, etc., to ensure that the most suitable personnel are assigned to the places where they are most needed. The present invention combines the power organization database with the safe production of power equipment, not only improving the management level of power equipment, but also promoting the innovation and development of the work of power organizations.

[0065] In one embodiment, step S2 includes:

[0066] Generate the initial positions of the particle swarm through chaotic mapping and initialize the velocity of each particle; each of the particles is a set of detection thresholds for the real-time operation data of the power equipment;

[0067] Construct a multi-objective function based on the false alarm rate, response speed, and computing resource consumption of the power equipment, and adjust the weight coefficients of each objective according to the preset business requirements through the fuzzy logic and its corresponding fuzzy rule base to obtain a multi-objective optimization function;

[0068] Take the multi-objective optimization function as the fitness function to calculate the fitness of each particle, and update the individual optimal position and global optimal position of the particle swarm based on the fitness calculation results, so as to adjust the velocity and position of each particle through the particle swarm velocity and position update formula introducing the dynamic inertia weight;

[0069] Iteratively execute the fitness calculation and the adjustment process of the particle velocity and position according to the adjusted particle swarm to obtain several global optimal positions to construct a Pareto solution set, and screen the Pareto solution set through the non-dominated sorting method to obtain the optimal detection threshold;

[0070] Perform anomaly detection on the real-time operation data through the optimal detection threshold to obtain anomaly operation data.

[0071] Specifically, the present invention uses the chaotic initialization method to initialize the particle swarm. That is, in order to increase the diversity of the particle swarm and avoid the initial local optimal solution, the Logistic mapping is used to generate the initial positions of the particles, which is represented by the following formula:

[0072]

[0073] In the formula, is the control parameter of the Logistic mapping; $x_0$ is the initial position of the particle, and the value of each position is within the interval (0, 1). For the monitoring of power equipment, the sensor data (such as temperature, vibration, load) fluctuates greatly. The chaotic initialization method can ensure the wide distribution of particles during initialization and avoid the search space being too concentrated.

[0074] The velocity of each particle can be randomly generated or initialized according to a certain strategy, usually set to a random value or zero; among them, each particle represents a set of detection thresholds for the real-time operation data of power equipment to judge whether the data is abnormal. For example, for a transformer, its real-time operation data includes vibration data and temperature data, then the particle corresponding to the transformer consists of the transformer vibration detection threshold and the transformer temperature detection threshold; similarly, the particle swarm formed by the particles corresponding to the real-time operation data of all power equipment can be obtained.

[0075] When constructing the multi-objective optimization function, consider the false alarm rate, response speed and computing resource consumption of power equipment. This function is expressed by the following formula:

[0076]

[0077] In the formula, , , are the weight coefficients of the false alarm rate, response delay and computing resource consumption respectively. These weight coefficients are dynamically adjusted by fuzzy logic, based on the real-time operation data of power equipment (such as equipment load, temperature change, vibration, etc.) and the preset business requirements to balance different objectives. Among them, the adjustment mechanism of the weight coefficient includes: the false alarm rate refers to the ratio of the power equipment control system misjudging a normally operating equipment as abnormal. When the equipment load is low or the equipment state is relatively stable, the power equipment control system tends to reduce the weight of the false alarm rate to avoid excessive intervention; while when the equipment load is heavy (such as high temperature, overloaded operation, etc.), it is necessary to increase the weight of the false alarm rate to reduce the impact of false alarms on the power equipment control system; the response delay refers to the time from the occurrence of equipment failure to the response of the power equipment control system. In the monitoring of power equipment, the shorter the response delay, the more beneficial it is to reduce the losses caused by equipment failures. Therefore, when the equipment shows abnormal signs (such as too high temperature, overload, etc.), it is necessary to optimize the response delay first; the monitoring of power equipment needs to process a large amount of sensor data and real-time calculations, which may cause a large burden on the resources of the power equipment control system. Especially when the equipment is operating stably, the power equipment control system should try to reduce the occupation of computing resources to avoid waste.

[0078] The present invention takes the tolerance of false alarm rate, the requirement for response speed, the limitation of computing resource consumption, etc. as service requirement indicators, takes the current false alarm rate, the current response speed, the current computing resource consumption, etc. as state indicators, and through fuzzy processing of these two types of indicators, converts them into fuzzy variables, with the weight coefficients of each target as output scalars; defines fuzzy sets and membership functions for each input and output variable. For example, for the tolerance of false alarm rate, the fuzzy sets can be defined as "low", "medium", "high"; for the requirement for response speed, the fuzzy sets can be defined as "slow", "medium", "fast"; for the limitation of computing resource consumption, the fuzzy sets can be defined as "loose", "medium", "strict"; the fuzzy sets of the output variable (weight coefficient) can be defined as "small", "medium", "large"; the membership function is used to map specific input values to the membership degrees of the fuzzy sets, such as triangular functions, trapezoidal functions, and Gaussian functions, etc.; then by introducing fuzzy logic rules, the power equipment control system can dynamically adjust the weights of each target according to real-time data (such as equipment load, temperature change, etc.). The rules are a set of "IF-THEN" rules designed based on expert experience and service requirements. For example, IF the temperature is on the high side AND the load is high THEN increase the weight of response delay and reduce the weight of computing resource consumption; IF the equipment is operating normally AND the vibration is normal THEN increase the weight of false alarm rate and reduce the weights of response delay and computing resource consumption, etc.; finally, according to the current values of the input variables and the fuzzy rule base, the Mamdani method and the Sugeno method are used to calculate the fuzzy values of the output variables and defuzzify them to obtain the weight coefficients of each target. Through this dynamic adjustment mechanism, the present invention can adaptively balance these three optimization targets to ensure the accuracy and efficiency of power equipment monitoring.

[0079] The present invention uses a multi-objective optimization function as the fitness function to calculate the fitness value of each particle, then updates the individual best position (pbest) and the global best position (gbest) of the particle swarm according to the fitness calculation result, and introduces a dynamic inertia weight to adjust the velocity and position update formulas of the particle swarm; wherein, the dynamic inertia weight is represented by the following formula:

[0080]

[0081]

[0082] In the formula, is the dynamic inertia weight; and are respectively the minimum and maximum values of the dynamic inertia weight; is the attenuation coefficient; t is the number of iterations; is the aggregation degree of the particle swarm; is the influence adjustment factor of the aggregation degree; is the total number of particle swarms; is the position of the i-th particle; is the center of the particle swarm; is the Euclidean distance.

[0083] Since the inertial weight may lead to overly extensive search and getting trapped in local optima when controlling the search behavior of particles, the present invention adopts a dynamic inertial weight to balance global and local searches, so as to improve the convergence speed and accuracy of the algorithm; among them, the velocity and position update formulas introducing the dynamic inertial weight are as follows:

[0084]

[0085] In the formula, v i is the velocity of the i-th particle; c1 and c2 are learning factors respectively; r1 and r2 are random numbers respectively.

[0086] Subsequently, according to the adjusted particle swarm, the fitness calculation and the process of adjusting the velocity and position of the particles are iteratively executed; during the iteration process, the global optimal position is continuously updated until the stopping condition is satisfied (such as reaching the maximum number of iterations or the fitness change is less than the threshold); through multiple iterations, several global optimal positions are obtained and constructed into a Pareto solution set. Each solution in the Pareto solution set is a non-dominated solution of the multi-objective optimization problem, that is, it is superior to other solutions in a certain objective and not inferior to other solutions in other objectives; the non-dominated sorting method is used to screen the Pareto solution set to obtain the optimal detection threshold, so as to retain the solutions on the Pareto front and ensure the diversity and optimality of the solution set; finally, the optimal detection threshold is used to perform anomaly detection on the real-time operation data, so as to screen out the abnormal operation data.

[0087] Taking the anomaly monitoring of a transformer as an example, assuming the monitoring objectives are: false alarm rate ≤ 5%, response delay ≤ 2 seconds, CPU occupancy rate ≤ 30%. In the monitoring of the transformer, by applying the hybrid multi-objective optimization algorithm, it dynamically adjusts the weights of each optimization objective according to the actual operating state of the power equipment (such as equipment vibration, temperature change, etc.). Finally, due to the frequent occurrence of transformer vibration anomalies, the weight of vibration is increased from 0.6 to 0.7, and the sensitivity of the detection threshold is reduced from 1.5 to 1.2, so as to reduce false alarms for less serious anomalies and ensure timely response to potential faults.

[0088] The present invention initializes the particle swarm through chaotic mapping, combines multi-objective optimization and fuzzy logic to dynamically adjust the weights, and uses the particle swarm algorithm for iterative optimization to finally obtain the optimal detection threshold. This not only effectively improves the accuracy, real-time performance, and resource efficiency of power equipment anomaly detection, but also optimizes the utilization of computing resources, with high practical value. At the same time, combined with the actual requirements of power equipment monitoring, the power equipment control system can adaptively adjust the weights of optimization objectives in real time to ensure good comprehensive performance under different operating states.

[0089] In one embodiment, step S3 includes:

[0090] Processing the abnormal operation data through a risk assessment model to obtain a comprehensive risk score, and determining a response plan for the power equipment based on the comprehensive risk score; where the risk assessment model is represented by the following formula:

[0091]

[0092] In the formula, is the comprehensive risk score; is the importance factor of the nth power equipment, evaluated according to the criticality of the equipment and its influence on the power equipment control system; is the state correction factor of the nth power equipment, adjusting the risk coefficient of the power equipment based on real-time monitoring data; is the risk adjustment coefficient, usually considering factors such as the historical failure records of the power equipment and the service life of the equipment; M is the total number of power equipment.

[0093] Specifically, after detecting an anomaly, the present invention generates a handling suggestion based on the comprehensive risk score calculated by the risk assessment model, such as immediately shutting down for inspection, replacing damaged components, adjusting the operation process (correcting violations or non-compliant behaviors), etc., to ensure equipment safety. Suppose a power production device (such as a transformer) is undergoing risk assessment, and the system monitors the following factors: the importance factor of the transformer is set to 5 according to its key role in the power system; the failure risk degree of the transformer is set to 0.8 based on real-time monitoring data (both the equipment temperature and vibration indicators exceed the normal range). Then, through formula calculation, the comprehensive risk score of the transformer is: 5 * 0.8 = 4. This result indicates that the risk score of the transformer is relatively high, suggesting that immediate measures need to be taken for inspection and repair. Among them, each response plan corresponds to a comprehensive risk score range. When the calculated comprehensive risk score falls within a certain range, the response plan belonging to that range is executed accordingly. The specific range division can be determined based on historical data and will not be elaborated as the key point here. Additionally, once an anomaly warning is triggered, the power equipment control system will automatically generate a hidden danger report and push it to relevant management personnel in real time through the linkage platform. Among them, the warning report will include detailed information such as the type, severity, occurrence time, and location of the hidden danger. The system will automatically match appropriate personnel for handling based on the severity and type of the warning information.

[0094] The risk assessment model of the present invention comprehensively considers the severity and occurrence probability of hidden dangers, provides a scientific comprehensive risk score, helps decision-makers fully understand the equipment risks, and formulates reasonable response plans based on the risk level and hidden danger type to ensure the effectiveness and pertinence of response measures.

[0095] In one embodiment, step S3 further includes:

[0096] Determine the type of hidden danger of the power equipment according to the abnormal operation data, quantify the hidden danger level of the power equipment through the hidden danger assessment model, and calculate the severity of each type of hidden danger to obtain the hidden danger severity score. Among them, the hidden danger assessment model is represented by the following formula:

[0097]

[0098] In the formula, is the hidden danger level; is the importance weight of the a-th type of hidden danger; is the handling weight of the a-th type of hidden danger; A is the total number of hidden danger types.

[0099] Specifically, according to the characteristics of abnormal operation data, the present invention classifies potential hazard types into several categories, such as electrical hazards: such as short circuits, leakage, overload, etc.; mechanical hazards: such as equipment wear, abnormal vibration, etc.; environmental hazards: such as excessive temperature, high humidity, etc.; control hazards: such as signal loss, control failure, etc.; or potential hazard types can be determined based on countermeasures (such as equipment failures, operation errors, safety violations, etc.). Subsequently, through the potential hazard assessment model, the potential hazard level of the power equipment can be quantified, and a severity score (S) is assigned to each potential hazard according to the impact degree of the potential hazard. The calculation formula is as follows:

[0100]

[0101] In the formula, are preset weights, which respectively reflect the importance of the power equipment, the fault range, and the impact of production interruption. The weights and their respective adjustment objects can be determined according to historical fault data.

[0102] Through the analysis of abnormal operation data and the classification of potential hazard types, the present invention can accurately identify potential hazards of power equipment. The potential hazard assessment model can quantify the potential hazard level and provide a clear scoring standard, which is convenient for decision-makers to understand and manage.

[0103] In one embodiment, step S4 includes:

[0104] Obtain the real-time environmental data of the power equipment and the basic data of each person in the power organization database, and construct the potential hazard level, the real-time environmental data, and each basic data as input features;

[0105] Process the input features through a deep learning network model constructed by a multi-layer perceptron to obtain the skill matching degree of each person, and optimize the skill matching degree of each person by using machine learning algorithms and reinforcement learning algorithms to obtain the optimized skill matching results of each person;

[0106] Based on the optimized skill matching results and the potential hazard severity score, construct a multi-objective matching function model, and use the particle swarm optimization algorithm to perform a global search on the multi-objective matching function model to obtain the target personnel and execute the countermeasures to achieve the safe production of the power equipment.

[0107] Specifically, for the matching of tasks and handlers, the present invention designs a multi-layer nested artificial intelligence matching framework, which uses a deep learning network (multi-layer perceptron, MLP) for scoring, combines an anomaly detection algorithm based on isolation forest, and a reinforcement learning (RL) algorithm to optimize the allocation strategy, and matches the response plan tasks with each person in the power organization database to improve the adaptive ability of the matching model. Among them, the power organization database stores the skill tags, affiliated teams, historical tasks, qualification levels, task feedback indices, responsibility fulfillment indices, etc. of each person.

[0108] First, retrieve the skill tags of each person from the power organization database, which are the basic data, such as repair capabilities: mechanical repair, electrical maintenance, structural fault repair, electrical expertise: circuit design analysis, sensor debugging, etc., hidden danger analysis experience: hidden danger early warning analysis, historical handling records, etc.; combine the hidden danger level: the emergency response level required by the task (such as high risk, medium risk, low risk) and the qualification level implied in the response plan: the requirements for professional certificates and work experience of the task, and the context features: the current team structure (such as the skill composition of other members in the team) and the real-time environmental data of the power equipment: such as temperature, humidity, air pressure, vibration, etc., and construct them as input features. This input feature On the basis of the basic features, more dimensions are introduced to increase the learning ability of the model.

[0109] Subsequently, the input features are processed by a deep learning network model constructed by a multi-layer perceptron to predict the skill matching degree of the handlers ; among them, the deep learning network model includes an input layer (receiving the feature vector ), a hidden layer (using the ReLU activation function: where is the weight and bias of the i-th layer) and an output layer (outputting the matching score ), and the model is trained by combining historical data (including hidden danger level, environmental data, personnel basic data, and actual matching results). The loss function is defined as the mean square error between the predicted value and the true score. The weight parameters are updated through the backpropagation algorithm, and the skill matching degrees of each person are predicted by the trained deep learning network model. Then, a machine learning algorithm is used to preliminarily optimize the skill matching degree to improve the accuracy of the matching degree through feature selection and hyperparameter tuning, and a reinforcement learning algorithm is used to further optimize the skill matching degree. The goal of reinforcement learning is to maximize the matching effect. By continuously interacting with the environment (simulating the matching scenario) and adjusting the matching strategy, the optimized results of the skill matching degrees of each person are obtained.

[0110] Finally, a multi-objective optimization algorithm is introduced in the matching and optimization process to make the system more flexible and efficient. The present invention comprehensively considers factors such as skill matching, task priority, and team workload, and defines a multi-objective matching function model :

[0111]

[0112] In the formula, 、 、 、 are the weight coefficients of their corresponding objectives respectively, which can be determined according to business requirements and historical data; is the score of historical task completion; is the current workload of the personnel.

[0113] The particle swarm optimization algorithm is used to perform a global search on the multi-objective matching function model to find the best allocation plan. When the improvement amplitude of the objective function is lower than the threshold or the number of iterations reaches the set value, the algorithm is stopped, and the target personnel corresponding to each response plan are obtained and the response plan is executed to achieve the safe production of power equipment.

[0114] Suppose the task queue contains 3 high-risk tasks, and the power organization database contains 5 people. Their respective skill scores, workloads, and historical completion scores are as follows:

[0115] Task characteristics: Task 1: Hidden danger level 9, abnormal score 0.8; Task 2: Hidden danger level 7, abnormal score 0.6; Task 3: Hidden danger level 6, abnormal score 0.4;

[0116] Personnel characteristics: , ;

[0117] After calculation by the algorithm described in the present invention, the final matching result of tasks and personnel is: Task 1 is assigned to Person 4; Task 2 is assigned to Person 1; Task 3 is assigned to Person 2.

[0118] Through the deep learning network model and optimization algorithm, the present invention can accurately match the skills of personnel with the requirements for handling potential hazards, improving the handling efficiency; comprehensively considering the skill matching degree and the severity score of potential hazards to construct a multi-objective matching function model to ensure the comprehensiveness and scientificity of the matching scheme; the adopted particle swarm optimization algorithm can search for the optimal matching scheme globally, avoiding falling into local optimal solutions; the adopted reinforcement learning algorithm can dynamically adjust the matching strategy according to the actual matching effect, improving the adaptability and robustness of the system; through accurate matching and rapid response, it can effectively reduce the risk of potential hazards and ensure the safe production of power equipment; the automated matching and optimization process reduces manual intervention, improving the efficiency and accuracy of handling potential hazards; this solution realizes the accurate matching and efficient response to potential hazards in power equipment through data acquisition, feature construction, deep learning model, multi-objective matching function and particle swarm optimization algorithm, and has scientificity, practicability and high efficiency, and can effectively improve the level of safe production of power equipment.

[0119] In one embodiment, the skill matching degree of each person is optimized by using machine learning algorithms and reinforcement learning algorithms to obtain the optimized skill matching results of each person, including:

[0120] The severity score of the potential hazard is processed by the isolation forest algorithm to obtain an optimized score, and the skill matching degree of each person is adjusted according to the optimized score to obtain the comprehensive matching degree of each person;

[0121] Taking the potential hazard level and the comprehensive matching degree of each person as state information, defining determining a candidate person from the power organization database as an action, allocating an agent to each person, and constructing a reward function with the time, completion degree and resource waste amount required for the agent to execute the coping scheme,

[0122] With the goal of maximizing the cumulative reward, the skill matching degree of each person is optimized through a deep Q network to obtain the optimized skill matching results of each person.

[0123] Specifically, the present invention uses the isolation forest algorithm to perform anomaly-assisted detection on the task potential hazard score to ensure that high-risk tasks are preferentially matched. By constructing a random tree structure, the optimized score of each data point is calculated (optimized score = path length / sample depth). The higher the score, the more likely the task is a potential hazard hot spot. Taking the severity score of the potential hazard as the input, the optimized score of each score is calculated using the isolation forest algorithm, and the severity score of the potential hazard is adjusted according to the optimized score to calculate the comprehensive matching degree ; where is an adjustment coefficient.

[0124] Next, reinforcement learning is used to dynamically optimize the matching results to improve the allocation efficiency in complex task scenarios. The hidden danger level and the time limit corresponding to the countermeasure plan are used as task features, the comprehensive matching degree and workload of each person are used as the personnel status, and the task features and personnel status are used as the state (State, S); the optimal processing personnel are selected from the power organization database based on the skill matching degree of each person , which means allocating the i-th person to the task as an action (Action, ), for example, Person A is selected in Plan 1, Person B is selected in Plan 2, Plan 3: Person C is selected, etc., and an agent is assigned to each person. Each agent is responsible for selecting and executing the countermeasure plan. For example, Agent A: responsible for the matching and task execution of Person A, Agent B: responsible for the matching and task execution of Person B, Agent C: responsible for the matching and task execution of Person C, etc.; and calculate the reward value according to the effect of the allocation result. The reward function is as follows:

[0125]

[0126] Finally, the deep Q-learning algorithm is used to optimize the skill matching degree of each person with the goal of maximizing the cumulative reward, and the optimized results of the skill matching of each person are obtained. The optimization process is represented by the following formula:

[0127]

[0128] In the formula, is the discount factor.

[0129] When using the deep Q-network to optimize the strategy of each agent, its input is the state information, and the output is the Q value of each action (i.e., the expected cumulative reward). By continuously interacting with the environment, the Q value is updated and the strategy is gradually optimized; the training process of the deep Q-network includes: initializing the network parameters of the DQN and the experience replay buffer; for each agent: select an action according to the current state (using the ε-greedy strategy); execute the action, observe the reward and the next state; store the experience (state, action, reward, next state) in the experience replay buffer; randomly sample a batch of experiences from the experience replay buffer and update the network parameters of the DQN; repeat the above process until the DQN converges. Finally, the skill matching degree of each person is optimized through the DQN, and the optimized results of the skill matching of each person are obtained.

[0130] The present invention optimizes the severity score of potential hazards through the Isolation Forest algorithm, reduces the scoring deviation, and improves the reliability of the scoring; adjusts the skill matching degree according to the optimized potential hazard score to ensure that high-risk potential hazards are handled by high-skilled personnel; through the design of the agent and the reward function, it can comprehensively consider the task completion degree, time, and resource waste amount, and optimize the matching strategy; uses the Deep Q Network to optimize the matching strategy, which can dynamically adjust the strategy to adapt to different potential hazard handling scenarios; through deep learning and reinforcement learning algorithms, it can accurately match the personnel skills with the potential hazard handling requirements, improve the handling efficiency; and through optimizing the matching strategy, it can reduce resource waste and improve resource utilization rate.

[0131] In the embodiment of the present application, based on the problem of how to improve the existing power safety production efficiency, a power safety production method combined with a power organization is designed. It uses a hybrid multi-objective optimization algorithm formed by combining the particle swarm algorithm with chaotic initialization, dynamic inertia weight, and fuzzy logic to perform anomaly detection on the real-time operation data of each power device, improving the detection accuracy and response speed, optimizing the utilization of computing resources, and ensuring that the power devices can maintain good comprehensive performance under different operating states; at the same time, a multi-layer nested artificial intelligence matching framework is designed, which uses deep learning network scoring, combines the anomaly detection algorithm based on the Isolation Forest, and optimizes the allocation strategy through reinforcement learning, and matches the response plan tasks with each person in the power organization database to enhance the adaptive ability of the matching model, greatly improving the power safety production efficiency and reducing the social impact and economic losses caused by power accidents.

[0132] It should be noted that although the steps in the above flowchart are displayed in sequence according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless there is a clear description in this article, the execution of these steps has no strict order limit, and these steps can be executed in other orders.

[0133] In another embodiment, as Figure 2 shown, the second aspect of the present invention provides a power safety production system combined with a power organization, including:

[0134] A data acquisition module 10, configured to acquire the real-time operation data of the power device;

[0135] An anomaly detection module 20, configured to perform anomaly detection on the real-time operation data through the hybrid multi-objective optimization algorithm to obtain abnormal operation data; the hybrid multi-objective optimization algorithm is a particle swarm algorithm combined with chaotic initialization, dynamic inertia weight, and fuzzy logic;

[0136] A level determination module 30, configured to determine the response plan and potential hazard level of the power device according to the abnormal operation data;

[0137] A personnel matching module 40, configured to match target personnel from a power organization database through an artificial intelligence matching algorithm based on the hidden danger level and execute the coping plan, so as to achieve the safe production of the power equipment.

[0138] It should be noted that each module in the above power safety production system combined with a power organization can be implemented in whole or in part by software, hardware, and their combination. The above modules can be embedded in or independent of the processor in the computer device in the form of hardware, or stored in the memory in the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules. For the specific limitations of a power safety production system combined with a power organization, refer to the limitations of a power safety production method combined with a power organization in the above text. The two have the same functions and effects, and will not be elaborated here.

[0139] The third aspect of the present invention provides an electronic device, which includes:

[0140] A processor, a memory, and a bus;

[0141] The bus is used to connect the processor and the memory;

[0142] The memory is used to store operation instructions;

[0143] The processor is configured to execute the operations corresponding to a power safety production method combined with a power organization as shown in the first aspect of the present application by calling the operation instructions.

[0144] In an optional embodiment, an electronic device is provided, as Figure 3 shown, Figure 3 The electronic device 5000 shown includes a processor 5001 and a memory 5003. Among them, the processor 5001 and the memory 5003 are connected, such as connected through a bus 5002. Optionally, the electronic device 5000 may further include a transceiver 5004. It should be noted that in practical applications, the transceiver 5004 is not limited to one, and the structure of the electronic device 5000 does not constitute a limitation to the embodiments of the present application.

[0145] The processor 5001 may be a CPU, a general-purpose processor, a DSP, an ASIC, an FPGA, or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It can implement or execute various exemplary logic blocks, modules, and circuits described in combination with the disclosed content of the present application. The processor 5001 may also be a combination that realizes computing functions, such as a combination including one or more microprocessors, a combination of a DSP and a microprocessor, etc.

[0146] The bus 5002 may include a path for transmitting information between the above components. The bus 5002 can be a PCI bus or an EISA bus, etc. The bus 5002 can be divided into an address bus, a data bus, a control bus, etc. For the sake of convenience of representation, Figure 3 only a thick line is used to represent it in Figure 3 , but it does not mean that there is only one bus or one type of bus.

[0147] The memory 5003 can be a ROM or other types of static storage devices that can store static information and instructions, a RAM or other types of dynamic storage devices that can store information and instructions, or it can also be an EEPROM, a CD-ROM or other optical disc storage, optical disc storage (including compact discs, laser discs, optical discs, digital versatile discs, Blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto.

[0148] The memory 5003 is used to store the application program code for implementing the solution of this application, and is controlled by the processor 5001 to execute. The processor 5001 is used to execute the application program code stored in the memory 5003 to implement the content shown in any of the foregoing method embodiments.

[0149] Among them, the electronic device includes but is not limited to: mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (tablet computers), PMPs (portable multimedia players), vehicle terminals (such as vehicle navigation terminals), etc. and fixed terminals such as digital TVs, desktop computers, etc.

[0150] The fourth aspect of the present invention provides a computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, it implements a power safety production method combined with a power organization as shown in the first aspect of this application.

[0151] Another embodiment of this application provides a computer-readable storage medium, on which a computer program is stored, and when it runs on a computer, it enables the computer to execute the corresponding content in the foregoing method embodiments.

[0152] In addition, an embodiment of the present invention also proposes a computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, it implements the steps of the above method.

[0153] In summary, the present invention relates to the field of information technology, and discloses a power safety production method, system, device and medium combined with a power organization. The method includes obtaining real-time operation data of power equipment; performing anomaly detection on the real-time operation data through a hybrid multi-objective optimization algorithm to obtain abnormal operation data; the hybrid multi-objective optimization algorithm is a particle swarm algorithm combined with chaotic initialization, dynamic inertia weight and fuzzy logic; determining a response plan and a potential hazard level of the power equipment according to the abnormal operation data; based on the potential hazard level, matching target personnel from a power organization database through an artificial intelligence matching algorithm and executing the response plan to achieve the safe production of the power equipment, greatly improving the safe production efficiency of the power equipment and reducing the social impact and economic losses caused by power accidents.

[0154] Each embodiment in this specification is described in a progressive manner. For parts that are the same or similar in each embodiment, reference can be made to each other. Each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can refer to the partial description of the method embodiment. It should be noted that the technical features of the above embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope described in this specification.

[0155] The above embodiments only represent several preferred implementation manners of the present application. The description is relatively specific and detailed, but it should not be construed as a limitation on the scope of the invention patent. It should be pointed out that for those of ordinary skill in the art in this technical field, without departing from the technical principle of the present invention, several improvements and replacements can still be made, and these improvements and replacements should also be regarded as the protection scope of the present application. Therefore, the protection scope of the patent of the present application should be subject to the protection scope of the claims.

Claims

1. A method for safe production of electric power combined with an electric power organization, characterized in that, Including: Obtain the real-time operation data of the power equipment; Perform anomaly detection on the real-time operation data through a hybrid multi-objective optimization algorithm to obtain anomaly operation data; The hybrid multi-objective optimization algorithm is a particle swarm algorithm combined with chaotic initialization, dynamic inertia weight, and fuzzy logic; Determine the countermeasure plan and potential hazard level of the power equipment according to the anomaly operation data; Based on the potential hazard level, match target personnel from the power organization database through an artificial intelligence matching algorithm and execute the countermeasure plan to achieve the safe production of the power equipment; The performing anomaly detection on the real-time operation data through a hybrid multi-objective optimization algorithm to obtain anomaly operation data includes: Generate the initial positions of the particle swarm through chaotic mapping and initialize the velocity of each particle; each particle is a set of detection thresholds for the real-time operation data of the power equipment; Construct a multi-objective function based on the false alarm rate, response speed, and computing resource consumption of the power equipment, and adjust the weight coefficients of each objective according to preset service requirements through the fuzzy logic and its corresponding fuzzy rule base to obtain a multi-objective optimization function; Use the multi-objective optimization function as a fitness function to calculate the fitness of each particle, and update the individual optimal position and global optimal position of the particle swarm based on the fitness calculation result to adjust the velocity and position of each particle through the particle swarm velocity and position update formula introducing the dynamic inertia weight; Iteratively execute the fitness calculation and the adjustment process of the particle velocity and position according to the adjusted particle swarm to obtain several global optimal positions to construct a Pareto solution set, and screen the Pareto solution set through the non-dominated sorting method to obtain the optimal detection threshold; Perform anomaly detection on the real-time operation data through the optimal detection threshold to obtain anomaly operation data.

2. A power safety production method combined with a power organization according to claim 1, characterized in that, The dynamic inertia weight is represented by the following formula: In the formula, is the dynamic inertia weight; , are the minimum and maximum values of the dynamic inertia weight respectively; is the attenuation coefficient; t is the number of iterations; is the aggregation degree of the particle swarm; is the influence adjustment factor of the aggregation degree; is the total number of the particle swarm; is the position of the i-th particle; is the center of the particle swarm; is the Euclidean distance.

3. A method for safe power production combining power organizations according to claim 1, characterized in that, The determining the countermeasure plan and potential hazard level of the power equipment according to the anomaly operation data includes: Process the anomaly operation data through a risk assessment model to obtain a comprehensive risk score, and determine the countermeasure plan of the power equipment based on the comprehensive risk score; where, the risk assessment model is represented by the following formula: In the formula, is the comprehensive risk score; is the importance factor of the nth power equipment; is the status correction factor of the nth power equipment; is the risk adjustment coefficient; M is the total number of power equipment.

4. A method for safe power production combined with a power organization according to claim 1, characterized in that, The determining the countermeasure plan and potential hazard level of the power equipment according to the anomaly operation data further includes: Determine the potential hazard type of the power equipment according to the anomaly operation data, quantify the potential hazard level of the power equipment through a potential hazard assessment model, and calculate the severity of each potential hazard type to obtain a potential hazard severity score; where, the potential hazard assessment model is represented by the following formula: Wherein, is the potential hazard level; is the importance weight of the a-th potential hazard type; is the handling weight of the a-th potential hazard type; A is the total number of potential hazard types.

5. A power safety production method combined with a power organization according to claim 4, characterized in that, The matching target personnel from the power organization database through an artificial intelligence matching algorithm and executing the countermeasure plan based on the potential hazard level to achieve the safe production of the power equipment includes: Obtain the real-time environmental data of the power equipment and the basic data of each person in the power organization database, and construct the potential hazard level, the real-time environmental data, and each basic data as input features; Process the input features through a deep learning network model constructed by a multi-layer perceptron to obtain the skill matching degrees of each person, and optimize the skill matching degrees of each person using machine learning algorithms and reinforcement learning algorithms to obtain the optimized skill matching results of each person; Based on the optimized skill matching results and the hidden danger severity scores, construct a multi-objective matching function model, and use the particle swarm optimization algorithm to perform a global search on the multi-objective matching function model to obtain the target personnel and execute the corresponding solution to achieve the safe production of the power equipment.

6. A method for safe power production combining power organizations according to claim 5, characterized in that, The step of using machine learning algorithms and reinforcement learning algorithms to optimize the skill matching degrees of each person to obtain the optimized skill matching results of each person includes: Process the hidden danger severity scores through the isolation forest algorithm to obtain optimized scores, and adjust the skill matching degrees of each person according to the optimized scores to obtain the comprehensive matching degrees of each person; Use the hidden danger levels and the comprehensive matching degrees of each person as state information, define the action of determining a candidate person from the power organization database, assign an agent to each person, and construct a reward function based on the time, completion degree, and resource waste amount required for the agent to execute the corresponding solution; With the goal of maximizing the cumulative reward, optimize the skill matching degrees of each person through a deep Q network to obtain the optimized skill matching results of each person.

7. A power production safety system combined with a power organization, characterized in that, It includes: A data acquisition module for acquiring the real-time operation data of the power equipment; An anomaly detection module for performing anomaly detection on the real-time operation data through a hybrid multi-objective optimization algorithm to obtain anomaly operation data; the hybrid multi-objective optimization algorithm is a particle swarm algorithm combined with chaotic initialization, dynamic inertia weight, and fuzzy logic; A level determination module for determining the corresponding solution and hidden danger level of the power equipment according to the anomaly operation data; A personnel matching module for matching target personnel from the power organization database based on the hidden danger level through an artificial intelligence matching algorithm and executing the corresponding solution to achieve the safe production of the power equipment; The step of performing anomaly detection on the real-time operation data through a hybrid multi-objective optimization algorithm to obtain anomaly operation data includes: Generate the initial positions of the particle swarm through chaotic mapping and initialize the velocity of each particle; each particle is a set of detection thresholds for the real-time operation data of the power equipment; Construct a multi-objective function based on the false alarm rate, response speed, and computing resource consumption of the power equipment, and adjust the weight coefficients of each objective according to the preset business requirements through the fuzzy logic and its corresponding fuzzy rule base to obtain a multi-objective optimization function; Use the multi-objective optimization function as the fitness function to calculate the fitness of each particle, and update the individual optimal position and global optimal position of the particle swarm based on the fitness calculation results to adjust the velocity and position of each particle through the particle swarm velocity and position update formula introducing the dynamic inertia weight; According to the adjusted particle swarm, the fitness calculation and the processes of adjusting the velocity and position of the particles are iteratively executed to obtain several global optimal positions to construct a Pareto solution set, and the Pareto solution set is screened by the non-dominated sorting method to obtain the optimal detection threshold; The abnormal operation data is obtained by performing abnormal detection on the real-time operation data through the optimal detection threshold.

8. An electronic device, characterized in that, It includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, it implements the power safety production method combined with a power organization as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored computer program. When the device where the computer-readable storage medium is located executes the computer program, it implements the power safety production method combined with a power organization as described in any one of claims 1 to 6.

Images