Environmental protection equipment control system based on artificial intelligence algorithm

Abstract

The invention discloses an environmental protection equipment control system based on an artificial intelligence algorithm. The system comprises a data acquisition module, a data preprocessing module, an environmental protection equipment state identification module, an environmental protection equipment intelligent control module, a hyper-parameter optimization module and an environmental protection equipment control strategy execution module. The invention relates to the technical field of environmental protection equipment data processing, in particular to an environmental protection equipment control system based on an artificial intelligence algorithm. According to the scheme, a clustering algorithm is innovatively used for pre-classifying the state of environmental protection equipment, and related real-time data is selectively input as control model input; the intelligent level of the environmental protection equipment control system is improved; a common neighborhood adaptive density method and a clustering center dynamic identification mechanism are introduced, so that the reliability of state identification of the environmental protection equipment is improved; and through reversible chaotic mapping, a speed dynamic factor and dynamic iterative attenuation, the global optimal solution search capability is enhanced, an optimal parameter combination is obtained, and the accuracy of a model output result is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of environmental protection equipment data processing, and in particular to an environmental protection equipment control system based on an artificial intelligence algorithm. Background Art

[0002] The environmental protection equipment control system based on artificial intelligence algorithm can make up for the shortcomings of manual control and monitoring methods of traditional environmental protection equipment. Compared with traditional methods, the system is more intelligent and has the advantages of real-time response, intelligent adjustment and predictive maintenance. It not only improves the efficiency and accuracy of pollution treatment, but also reduces the consumption of manpower and material resources. Its application will promote the development of environmental protection equipment towards intelligence and automation, and provide more efficient and sustainable solutions for environmental protection and resource conservation; however, the traditional environmental protection equipment control system has problems such as inaccurate identification of environmental protection equipment status, low data processing efficiency and lack of flexibility in control strategies. The existing clustering methods suitable for environmental protection equipment status identification have problems such as inconsistent cluster center identification and inability to effectively capture local density changes, resulting in insufficient accuracy and reliability of environmental protection equipment status identification. There are improper parameter settings in traditional control models, and parameter optimization algorithms are prone to falling into local optimality, which leads to technical problems such as inaccurate final output results. Summary of the invention

[0003] In view of the above situation, in order to overcome the defects of the prior art, the present invention provides an environmental protection equipment control system based on artificial intelligence algorithm. In view of the problems of inaccurate identification of environmental protection equipment status, low data processing efficiency and lack of flexibility in control strategy in traditional environmental protection equipment control systems, this solution innovatively proposes measures to pre-classify the environmental protection equipment status by using cluster analysis, and selectively input relevant real-time data as input data of the control model according to the identification results, which can effectively avoid the processing of redundant data, improve the system response speed, and ensure that the environmental protection equipment is accurately adjusted according to specific environmental changes, thereby improving the intelligence level and adaptability of the environmental protection equipment control system; in view of the inconsistent identification of cluster centers and the inability to effectively capture local The problem of density change leads to insufficient accuracy and reliability in the identification of the state of environmental protection equipment. This scheme introduces a common neighborhood adaptive density method and a dynamic identification mechanism for cluster centers. By accurately selecting cluster centers and reflecting the similarity between data points, it can better reflect changes in environmental conditions and equipment operating conditions, improve the stability and consistency of clustering results, and thus improve the accuracy and reliability of the identification of the state of environmental protection equipment. In view of the technical problems of improper parameter settings in traditional control models and the easy trapping of parameter optimization algorithms in local optimality, which leads to inaccurate final output results, this scheme uses reversible chaotic mapping, speed dynamic factors and dynamic iterative attenuation to enhance the global optimal solution search and improve the robustness of the algorithm, thereby obtaining the optimal parameter values ​​and solving the problem of inaccurate output results of the control model.

[0004] The technical solution adopted by the present invention is as follows: an environmental protection equipment control system based on an artificial intelligence algorithm provided by the present invention includes a data acquisition module, a data preprocessing module, an environmental protection equipment state recognition module, an environmental protection equipment intelligent control module, a hyperparameter optimization module and an environmental protection equipment control strategy execution module;

[0005] The data acquisition module collects historical environmental protection equipment operation data and real-time environmental protection equipment operation data from the environmental protection equipment operation system to obtain the original data of environmental protection equipment control;

[0006] The data preprocessing module performs data cleaning, standardization processing and feature selection on the environmental protection equipment control raw data to obtain preliminary environmental protection equipment control data;

[0007] The environmental protection equipment state recognition module establishes an environmental protection equipment state recognition model by adopting a clustering algorithm of a common neighborhood adaptive density method and a cluster center dynamic recognition method, performs model training on the environmental protection equipment state recognition model, realizes real-time monitoring of the environmental protection equipment during operation, and obtains the environmental protection equipment recognition state during the current operation of the environmental protection equipment;

[0008] The environmental protection equipment intelligent control module generates a corresponding control strategy based on the output result of the environmental protection equipment state recognition module and the real-time environmental protection equipment operation data to obtain the equipment intelligent control result by establishing an equipment intelligent control model;

[0009] The hyperparameter optimization module obtains the optimal parameter combination of the equipment intelligent control model through a search algorithm;

[0010] The environmental protection equipment control strategy execution module accurately adjusts the operating status of the environmental protection equipment based on the output results of the environmental protection equipment status identification module and the environmental protection equipment intelligent control module, and sends reminders to equipment managers.

[0011] Furthermore, the data acquisition module specifically acquires the original data of environmental protection equipment control from the environmental protection equipment operation system by acquisition; the original data of environmental protection equipment control includes historical environmental protection equipment operation data and real-time environmental protection equipment operation data; the historical environmental protection equipment operation data and real-time environmental protection equipment operation data both include environmental quality data and equipment status data; the historical environmental protection equipment operation data also includes environmental protection equipment identification status and historical environmental protection equipment control strategy data; the environmental quality data includes air quality data, water quality data, and soil quality data; the air quality data includes fine particulate matter concentration, inhalable particulate matter concentration, The water quality data include water pH, dissolved oxygen concentration, chemical oxygen demand, ammonia nitrogen concentration, heavy metal content and turbidity; the soil quality data include soil moisture, soil pH, soil organic matter content and soil temperature; the equipment status data include equipment temperature, equipment vibration data, noise level, equipment current and equipment power; the environmental protection equipment identification status includes normal, air pollution, water pollution, soil pollution and abnormal equipment operation. The environmental protection equipment identification status is used as a data label. The data label is not considered during clustering and is only used when selecting cluster labels.

[0012] Furthermore, the data preprocessing module specifically performs data cleaning, standardization and feature selection on the original data of environmental protection equipment control to obtain preliminary data of environmental protection equipment control; the data cleaning is to process missing values, abnormal values ​​and duplicate values; the standardization is to standardize the data based on the maximum and minimum normalization method; the feature selection is to use the correlation analysis method to calculate the correlation between each feature and the environmental protection equipment status identification and environmental protection equipment control, and screen out the most valuable features for environmental protection equipment status identification and environmental protection equipment control.

[0013] Furthermore, the environmental protection equipment state recognition module specifically establishes an environmental protection equipment state recognition model, performs model training on the environmental protection equipment state recognition model, realizes real-time monitoring of the environmental protection equipment during operation, and obtains real-time monitoring results of the environmental protection equipment state; and includes the following steps:

[0014] Establish an environmental protection equipment status recognition model, specifically select cluster centers and generate more accurate clustering results through common neighborhood adaptive density method and cluster center dynamic recognition method; including the following steps:

[0015] The similarity between the sample data points is calculated, specifically, to measure the distance between the sample data points. The sample data points are the data values ​​of various operating parameters in the historical environmental protection equipment operation data and the real-time environmental protection equipment operation. The formula used is expressed as follows:

[0016] ;

[0017] In the formula, Represents the similarity between sample data points. and Represents sample data points and sample data points Environmental quality data, and Represents sample data points and sample data points Device status data, and Respectively represent the weights of environmental quality data and equipment status data, Indicates the similarity of device status data in sample data points, calculated by cosine similarity;

[0018] The local density of the sample data points is calculated, specifically, the local density of the sample data points is calculated by the common neighborhood adaptive density method. The formula used is expressed as follows:

[0019] ;

[0020] In the formula, Represents sample data points The local density value, Represents sample data points The nearest neighbor set of Represents sample data points The nearest neighbor set of Represents sample data points Neighbor sample data points, Represents sample data points and sample data points The sample data points in the common nearest neighbor set of Represents the distance between the sample data point and its kth nearest neighbor, calculated by Euclidean distance;

[0021] Calculate the relative distance; the formula used is expressed as follows:

[0022] ;

[0023] In the formula, Represents sample data points The local density value, Represents sample data points The distance to the nearest point with higher density, j means that the condition is met The sample data point index of Represents sample data points and sample data points The number of common nearest neighbors between Represents sample data points It has the highest local density among all sample data points, and M represents the number of sample data points;

[0024] Calculate the decision value, specifically first and Normalize to the interval [0,1] to ensure that they are in the same range, and then calculate the decision value of each sample data point to determine the cluster center. The decision value is obtained by multiplying the local density and the relative distance. The formula used is expressed as follows:

[0025] ;

[0026] In the formula, represents the decision value, represents the local density of sample data points, Represents the distance between a sample data point and the nearest point with higher density;

[0027] Dynamic identification of cluster centers, specifically, by setting the probability threshold of the decision value to select the candidate cluster centers, first calculate the cumulative probability of the decision value, if the cumulative probability of the decision value meets the set probability threshold, then the sample data point is selected as the candidate cluster center, then all candidate cluster centers are compared in pairs, if the similarity between two candidate cluster centers is greater than 0.9, the candidate cluster center with lower local density is determined as a subordinate point, remove these subordinate points, and the remaining candidate cluster centers are the final cluster centers; the formula used is expressed as follows:

[0028] ;

[0029] In the formula, Represents the cumulative probability function, that is, the decision value falls within the interval The probability within represents the lower threshold of the decision value, represents the upper threshold of the decision value;

[0030] Cluster assignment, specifically, for each subordinate point, find the point with the closest distance and higher local density, and assign the point to the corresponding cluster center;

[0031] Environmental protection equipment state recognition model training, specifically using the environmental quality data, equipment state data and environmental protection equipment recognition state data in the historical environmental protection equipment operation data as input data to train the environmental protection equipment state recognition model, and analyzing the clustering results to determine the environmental protection equipment recognition state corresponding to each cluster, and obtaining the trained environmental protection equipment state recognition model;

[0032] The real-time monitoring of the environmental protection equipment status specifically uses the environmental quality data and equipment status data in the real-time environmental protection equipment operation data as input data of the trained environmental protection equipment status recognition model to obtain the environmental protection equipment recognition status during the current operation of the environmental protection equipment.

[0033] Furthermore, the environmental protection equipment intelligent control module specifically obtains the environmental protection equipment intelligent control strategy by establishing an equipment intelligent control model, training the equipment intelligent control model and generating an equipment intelligent control strategy; specifically includes the following steps:

[0034] Establishing the equipment intelligent control model includes the following steps:

[0035] The LSTM bidirectional unit output calculation is specifically to calculate the forward and reverse hidden states based on the input data at the current moment, the hidden state and cell state at the previous moment, and the hidden state and cell state at the next moment, and combine these two hidden states to obtain the final hidden state of the LSTM bidirectional unit; the formula used is as follows:

[0036] ;

[0037] ;

[0038] ;

[0039] In the formula, represents the unit operation function, h represents the hidden state of the combined forward and backward LSTM units, Indicates the hidden state in the positive direction at the current moment, Indicates the hidden state in the positive direction at the previous moment, Indicates the reverse hidden state at the current moment. Indicates the hidden state in the reverse direction at the next moment, Represents the input data at the current moment, Indicates the state of the cell in the positive direction at the previous moment, Indicates the state of the cell unit in the reverse direction at the next moment;

[0040] The model output value is obtained using the following formula:

[0041] ;

[0042] In the formula, represents the output value of the model, represents the weight matrix corresponding to the output, represents the activation function, B y Represents the bias parameter of the output layer;

[0043] Equipment intelligent control model training, specifically, using the historical environmental protection equipment operation data in the preliminary environmental protection equipment control data to train the equipment intelligent control model training to obtain a trained equipment intelligent control model training;

[0044] The equipment intelligent control strategy is generated by dynamically selecting corresponding data in the real-time environmental protection equipment operation data as input data of the trained equipment intelligent control model according to the output result of the environmental protection equipment state recognition module to obtain the environmental protection equipment intelligent control strategy.

[0045] Furthermore, the hyperparameter optimization module specifically obtains the optimal parameter combination of the equipment intelligent control model through a search algorithm; and includes the following steps:

[0046] Initialization parameters, specifically by constructing the initial parameters of the algorithm; the initial parameters of the algorithm include the population size N, the population dimension D and the maximum number of iterations ;

[0047] Initializing the population, specifically, initializing the population by generating chaotic sequence values ​​through a reversible chaotic mapping, includes the following steps:

[0048] Generate N chaotic sequence values ​​and initialize the random value z0; the formula used is as follows:

[0049] ;

[0050] In the formula, represents the i-th chaotic sequence value of the d-th dimension, represents the i+1th chaotic sequence value in the dth dimension, Represents adjustment parameters, which are used to adjust the mapping behavior;

[0051] The chaotic sequence value conversion search individual is expressed as follows:

[0052] ;

[0053] In the formula, represents the initialization position of the dth dimension of the i-th individual, lb d andub d Respectively represent the search lower and upper limits of dimension d;

[0054] Calculate the fitness value, specifically the individual fitness value F in the population i ; The performance of the equipment intelligent control model based on the individual position is used as the individual fitness value;

[0055] To calculate the individual speed dynamic factor, the formula used is as follows:

[0056] ;

[0057] In the formula, It represents the dynamic factor of the speed of the i-th individual at the t+1th iteration, represents the dynamic factor of the motion speed of the i-th individual in the t-th iteration, represents the Cauchy probability distribution;

[0058] Search for individual motion attribute updates, specifically updating motion frequency and motion speed; the formula used is as follows:

[0059] ;

[0060] ;

[0061] In the formula, represents the movement frequency of the i-th individual, represents the minimum frequency of individual movement, represents the maximum frequency of individual movement, represents a random number uniformly distributed in the range [0,1]. represents the movement speed of the i-th individual in the t+1-th iteration, represents the movement speed of the i-th individual in the t-th iteration, represents the d-th dimension position of the i-th individual in the t-th iteration, Indicates the position of the individual with the best fitness value among all current individuals;

[0062] In the individual local search phase, the formula used is as follows:

[0063] ;

[0064] In the formula, represents the d-th dimension position of the i-th individual in the t+1-th iteration, represents the search intensity of the i-th individual in the t-th iteration, and represents a random number uniformly distributed in the range [0,1]. represents the exploration ability of the i-th individual in the t-th iteration;

[0065] Update individual exploration control parameters, specifically if and , then accept As the global optimal position, and update the individual exploration control parameters, the updating of the individual exploration control parameters is specifically to update the individual search intensity and update the individual exploration ability through dynamic iterative attenuation; the formula used is as follows:

[0066] ;

[0067] ;

[0068] In the formula, represents the fitness function, represents a random number uniformly distributed in the range [0,1]. represents the search intensity of the i-th individual in the t+1-th iteration, represents the exploration capability of the i-th individual in the t+1th iteration, t represents the current number of iterations, It represents the exploration capability enhancement coefficient, which is a constant;

[0069] Get the optimal individual position of the current iteration, specifically sort all individuals by fitness value, sort the individuals from best to worst according to fitness value, and get the individual position with the highest current fitness value as the optimal individual position of the current iteration;

[0070] Search determination, specifically, by constructing a search termination condition, searching and determining the optimal individual position, and obtaining the optimal individual position data setting;

[0071] The search termination conditions include threshold termination and iteration termination;

[0072] The threshold termination is specifically to set the fitness threshold, when the individual fitness value F i When it is above the fitness threshold, the hyperparameter search is completed;

[0073] The iteration termination specifically refers to terminating the iteration and obtaining the optimal individual position when the maximum number of iterations is reached;

[0074] The optimal individual position includes equipment intelligent control model parameters.

[0075] Furthermore, the environmental protection equipment control strategy execution module specifically adjusts the operating status of the environmental protection equipment based on the output results of the environmental protection equipment status identification module and the environmental protection equipment intelligent control module; if the output result of the environmental protection equipment status identification module is an abnormal state, the environmental protection equipment automatically adjusts the operating status of the environmental protection equipment according to the output result of the environmental protection equipment intelligent control module, responds to environmental problems and equipment problems identified by the environmental protection equipment, and triggers a safety response mechanism, generates a safety alarm and notifies equipment management personnel to ensure stable operation of the equipment and environmental safety.

[0076] The beneficial effects achieved by the present invention using the above scheme are as follows:

[0077] (1) In response to the problems of inaccurate equipment status identification, low data processing efficiency and lack of flexibility in control strategies in traditional environmental protection equipment control systems, this solution innovatively proposes measures to pre-classify the equipment status by using cluster analysis, and selectively input relevant real-time data as input data for the control model based on the identification results. This can effectively avoid the processing of redundant data, improve the system response speed, and ensure that the environmental protection equipment can be accurately adjusted according to specific environmental changes, thereby improving the intelligence level and adaptability of the environmental protection equipment control system.

[0078] (2) In view of the problems of inconsistent cluster center identification and inability to effectively capture local density changes in existing clustering methods suitable for environmental protection equipment status identification, which leads to insufficient accuracy and reliability of environmental protection equipment status identification, this scheme introduces a common neighborhood adaptive density method and a cluster center dynamic identification mechanism. By accurately selecting cluster centers and reflecting the similarities between data points, it can better reflect changes in environmental conditions and equipment operating conditions, improve the stability and consistency of clustering results, and thus improve the accuracy and reliability of environmental protection equipment status identification.

[0079] (3) In order to solve the technical problems of improper parameter settings in traditional control models and the parameter optimization algorithm being prone to falling into local optimality, which leads to inaccurate final output results, this scheme uses reversible chaotic mapping, speed dynamic factors and dynamic iterative attenuation to enhance the global optimal solution search and improve the robustness of the algorithm, thereby obtaining the optimal parameter values ​​and solving the problem of inaccurate final control model output results. BRIEF DESCRIPTION OF THE DRAWINGS

[0080] Figure 1 A module schematic diagram of an environmental protection equipment control system based on an artificial intelligence algorithm provided by the present invention;

[0081] Figure 2 This is a flow chart of the environmental protection equipment status identification module;

[0082] Figure 3This is a flow chart of the intelligent control module of environmental protection equipment;

[0083] Figure 4 This is a flowchart of the hyperparameter optimization module;

[0084] Figure 5 A schematic diagram of the process of establishing an environmental protection equipment status recognition model in an environmental protection equipment status recognition module;

[0085] The accompanying drawings are used to provide further understanding of the present invention and constitute a part of the specification. They are used to explain the present invention together with the embodiments of the present invention and do not constitute a limitation of the present invention. DETAILED DESCRIPTION

[0086] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments; based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0087] In the description of the present invention, it is necessary to understand that terms such as “upper”, “lower”, “front”, “back”, “left”, “right”, “top”, “bottom”, “inside” and “outside” indicating directions or positional relationships are based on the directions or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the referred system or element must have a specific direction, be constructed and operated in a specific direction, and therefore cannot be understood as a limitation on the present invention.

[0088] Example 1, see Figure 1 , an environmental protection equipment control system based on artificial intelligence algorithm provided by the present invention includes a data acquisition module, a data preprocessing module, an environmental protection equipment state recognition module, an environmental protection equipment intelligent control module, a hyperparameter optimization module and an environmental protection equipment control strategy execution module;

[0089] The data acquisition module collects historical environmental protection equipment operation data and real-time environmental protection equipment operation data from the environmental protection equipment operation system, obtains the original data of environmental protection equipment control, and sends the data to the data preprocessing module;

[0090] The data preprocessing module receives the data sent by the data acquisition module, performs data cleaning, standardization processing and feature selection on the environmental protection equipment control raw data, obtains preliminary environmental protection equipment control data, and sends the data to the environmental protection equipment state recognition module and the environmental protection equipment intelligent control module;

[0091] The environmental protection equipment state recognition module receives the data sent by the data preprocessing module, establishes an environmental protection equipment state recognition model by adopting a clustering algorithm of a common neighborhood adaptive density method and a cluster center dynamic recognition method, performs model training on the environmental protection equipment state recognition model, realizes real-time monitoring of the environmental protection equipment during operation, obtains the environmental protection equipment recognition state during the current operation of the environmental protection equipment, and sends the data to the environmental protection equipment intelligent control module and the environmental protection equipment control strategy execution module;

[0092] The environmental protection equipment intelligent control module receives data sent by the data preprocessing module, the environmental protection equipment state identification module and the hyperparameter optimization module, establishes an equipment intelligent control model, generates a corresponding control strategy according to the output result of the environmental protection equipment state identification module and the real-time environmental protection equipment operation data, obtains the equipment intelligent control result, and sends the data to the environmental protection equipment control strategy execution module;

[0093] The hyperparameter optimization module obtains the optimal parameter combination of the equipment intelligent control model through a search algorithm and sends the data to the environmental protection equipment intelligent control module;

[0094] The environmental protection equipment control strategy execution module receives data sent by the environmental protection equipment status identification module and the environmental protection equipment intelligent control module, accurately adjusts the operating status of the environmental protection equipment based on the output results of the environmental protection equipment status identification module and the environmental protection equipment intelligent control module, and sends reminders to equipment managers.

[0095] Example 2, see Figure 1 This embodiment is based on the above embodiment, and the data acquisition module specifically acquires the original data of environmental protection equipment control from the environmental protection equipment operation system by acquisition; the original data of environmental protection equipment control includes historical environmental protection equipment operation data and real-time environmental protection equipment operation data; the historical environmental protection equipment operation data and real-time environmental protection equipment operation data both include environmental quality data and equipment status data; the historical environmental protection equipment operation data also includes environmental protection equipment identification status and historical environmental protection equipment control strategy data; the environmental quality data includes air quality data, water quality data, and soil quality data; the air quality data includes fine particulate matter concentration, inhalable particulate matter concentration, carbon dioxide concentration, nitrogen oxide concentration, sulfur dioxide concentration and ozone concentration; the water quality data include water pH, dissolved oxygen concentration, chemical oxygen demand, ammonia nitrogen concentration, heavy metal content and turbidity; the soil quality data include soil moisture, soil pH, soil organic matter content and soil temperature; the equipment status data include equipment temperature, equipment vibration data, noise level, equipment current and equipment power; the environmental protection equipment identification status includes normal, air pollution, water pollution, soil pollution and abnormal equipment operation. The environmental protection equipment identification status is used as a data label. The data label is not considered during clustering and is only used when selecting cluster labels.

[0096] Example 3, see Figure 1 This embodiment is based on the above embodiment. The data preprocessing module specifically performs data cleaning, standardization processing and feature selection on the original data of environmental protection equipment control to obtain preliminary data of environmental protection equipment control; the data cleaning is to process missing values, abnormal values ​​and repeated values; the standardization processing is to standardize the data based on the maximum and minimum normalization method; the feature selection is to use the correlation analysis method to calculate the correlation between each feature and the environmental protection equipment status identification and environmental protection equipment control, and screen out the most valuable features for environmental protection equipment status identification and environmental protection equipment control.

[0097] Example 4, see Figure 1 , Figure 2 and Figure 5 This embodiment is based on the above embodiment. The environmental protection equipment state recognition module specifically establishes an environmental protection equipment state recognition model, trains the environmental protection equipment state recognition model, realizes real-time monitoring of the environmental protection equipment during operation, and obtains the real-time monitoring result of the environmental protection equipment state; it includes the following steps:

[0098] Establish an environmental protection equipment status recognition model, specifically select cluster centers and generate more accurate clustering results through common neighborhood adaptive density method and cluster center dynamic recognition method; including the following steps:

[0099] The similarity between the sample data points is calculated, specifically, to measure the distance between the sample data points. The sample data points are the data values ​​of various operating parameters in the historical environmental protection equipment operation data and the real-time environmental protection equipment operation. The formula used is expressed as follows:

[0100] ;

[0101] In the formula, Represents the similarity between sample data points. and Represents sample data points and sample data points Environmental quality data, and Represents sample data points and sample data points Device status data, and Respectively represent the weights of environmental quality data and equipment status data, Indicates the similarity of device status data in sample data points, calculated by cosine similarity;

[0102] The local density of the sample data points is calculated, specifically, the local density of the sample data points is calculated by the common neighborhood adaptive density method. The formula used is expressed as follows:

[0103] ;

[0104] In the formula, Represents sample data points The local density value, Represents sample data points The nearest neighbor set of Represents sample data points The nearest neighbor set of Represents sample data points Neighbor sample data points, Represents sample data points and sample data points The sample data points in the common nearest neighbor set of Represents the distance between the sample data point and its kth nearest neighbor, calculated by Euclidean distance;

[0105] Calculate the relative distance; the formula used is expressed as follows:

[0106] ;

[0107] In the formula, Represents sample data points The local density value, Represents sample data points The distance to the nearest point with higher density, j means that the condition is met The sample data point index of Represents sample data points and sample data points The number of common nearest neighbors between Represents sample data points It has the highest local density among all sample data points, and M represents the number of sample data points;

[0108] Calculate the decision value, specifically first and Normalize to the interval [0,1] to ensure that they are in the same range, and then calculate the decision value of each sample data point to determine the cluster center. The decision value is obtained by multiplying the local density and the relative distance. The formula used is expressed as follows:

[0109] ;

[0110] In the formula, represents the decision value, represents the local density of sample data points, Represents the distance between a sample data point and the nearest point with higher density;

[0111] Dynamic identification of cluster centers, specifically, by setting the probability threshold of the decision value to select the candidate cluster centers, first calculate the cumulative probability of the decision value, if the cumulative probability of the decision value meets the set probability threshold, then the sample data point is selected as the candidate cluster center, then all candidate cluster centers are compared in pairs, if the similarity between two candidate cluster centers is greater than 0.9, the candidate cluster center with lower local density is determined as a subordinate point, remove these subordinate points, and the remaining candidate cluster centers are the final cluster centers; the formula used is expressed as follows:

[0112] ;

[0113] In the formula, Represents the cumulative probability function, that is, the decision value falls within the interval The probability within represents the lower threshold of the decision value, represents the upper threshold of the decision value;

[0114] Cluster assignment, specifically, for each subordinate point, find the point with the closest distance and higher local density, and assign the point to the corresponding cluster center;

[0115] Environmental protection equipment state recognition model training, specifically using the environmental quality data, equipment state data and environmental protection equipment recognition state data in the historical environmental protection equipment operation data as input data to train the environmental protection equipment state recognition model, and analyzing the clustering results to determine the environmental protection equipment recognition state corresponding to each cluster, and obtaining the trained environmental protection equipment state recognition model;

[0116] The real-time monitoring of the environmental protection equipment status specifically uses the environmental quality data and equipment status data in the real-time environmental protection equipment operation data as input data of the trained environmental protection equipment status recognition model to obtain the environmental protection equipment recognition status during the current operation of the environmental protection equipment.

[0117] By performing the above operations, in order to address the problems of inconsistency in cluster center identification and inability to effectively capture local density changes in existing clustering methods suitable for environmental protection equipment status identification, resulting in insufficient accuracy and reliability in environmental protection equipment status identification, this scheme introduces a common neighborhood adaptive density method and a dynamic identification mechanism for cluster centers. By accurately selecting cluster centers and reflecting the similarities between data points, it can better reflect changes in environmental conditions and equipment operating conditions, improve the stability and consistency of clustering results, and thus improve the accuracy and reliability of environmental protection equipment status identification.

[0118] Example 5, see Figure 1 and Figure 3 This embodiment is based on the above embodiment. The environmental protection equipment intelligent control module specifically obtains the environmental protection equipment intelligent control strategy by establishing an equipment intelligent control model, training the equipment intelligent control model and generating an equipment intelligent control strategy. Specifically, it includes the following steps:

[0119] Establishing the equipment intelligent control model includes the following steps:

[0120] The LSTM bidirectional unit output calculation is specifically to calculate the forward and reverse hidden states based on the input data at the current moment, the hidden state and cell state at the previous moment, and the hidden state and cell state at the next moment, and combine these two hidden states to obtain the final hidden state of the LSTM bidirectional unit; the formula used is as follows:

[0121] ;

[0122] ;

[0123] ;

[0124] In the formula, represents the unit operation function, h represents the hidden state of the combined forward and backward LSTM units, Indicates the hidden state in the positive direction at the current moment, Indicates the hidden state in the positive direction at the previous moment, Indicates the reverse hidden state at the current moment. Indicates the hidden state in the reverse direction at the next moment, Represents the input data at the current moment, Indicates the state of the cell in the positive direction at the previous moment, Indicates the state of the cell unit in the reverse direction at the next moment;

[0125] The model output value is obtained using the following formula:

[0126] ;

[0127] In the formula, represents the output value of the model, represents the weight matrix corresponding to the output, represents the activation function, B y Represents the bias parameter of the output layer;

[0128] Equipment intelligent control model training, specifically, using the historical environmental protection equipment operation data in the preliminary environmental protection equipment control data to train the equipment intelligent control model training to obtain a trained equipment intelligent control model training;

[0129] The equipment intelligent control strategy is generated by dynamically selecting corresponding data in the real-time environmental protection equipment operation data as input data of the trained equipment intelligent control model according to the output result of the environmental protection equipment status identification module to obtain the generated environmental protection equipment intelligent control strategy. The dynamic selection of corresponding data in the real-time environmental protection equipment operation data is specifically to select air quality data in the real-time environmental protection equipment operation data when the output result of the environmental protection equipment status identification module is air pollution.

[0130] By performing the above operations, this solution innovatively proposes measures to pre-classify the status of environmental protection equipment by using cluster analysis to address the problems of inaccurate identification of environmental protection equipment status, low data processing efficiency and lack of flexibility in control strategies in traditional environmental protection equipment control systems. It also selectively inputs relevant real-time data as input data for the control model based on the identification results, which can effectively avoid the processing of redundant data, improve the system response speed, and ensure that the environmental protection equipment is accurately adjusted according to specific environmental changes, thereby improving the intelligence level and adaptability of the environmental protection equipment control system.

[0131] Example 6, see Figure 1 and Figure 4 This embodiment is based on the above embodiment, and the hyperparameter optimization module specifically obtains the optimal parameter combination of the equipment intelligent control model through a search algorithm; it includes the following steps:

[0132] Initialization parameters, specifically by constructing the initial parameters of the algorithm; the initial parameters of the algorithm include the population size N, the population dimension D and the maximum number of iterations ;

[0133] Initializing the population, specifically, initializing the population by generating chaotic sequence values ​​through a reversible chaotic mapping, includes the following steps:

[0134] Generate N chaotic sequence values ​​and initialize the random value z0; the formula used is as follows:

[0135] ;

[0136] In the formula, represents the i-th chaotic sequence value of the d-th dimension, represents the i+1th chaotic sequence value in the dth dimension, Represents adjustment parameters, which are used to adjust the mapping behavior;

[0137] The chaotic sequence value conversion search individual is expressed as follows:

[0138] ;

[0139] In the formula, represents the initialization position of the dth dimension of the i-th individual, lb d andub d Respectively represent the search lower and upper limits of dimension d;

[0140] Calculate the fitness value, specifically the individual fitness value F in the population i ; The performance of the equipment intelligent control model based on the individual position is used as the individual fitness value;

[0141] To calculate the individual speed dynamic factor, the formula used is as follows:

[0142] ;

[0143] In the formula, It represents the dynamic factor of the speed of the i-th individual at the t+1th iteration, represents the dynamic factor of the motion speed of the i-th individual in the t-th iteration, represents the Cauchy probability distribution;

[0144] Search for individual motion attribute updates, specifically updating motion frequency and motion speed; the formula used is as follows:

[0145] ;

[0146] ;

[0147] In the formula, represents the movement frequency of the i-th individual, represents the minimum frequency of individual movement, represents the maximum frequency of individual movement, represents a random number uniformly distributed in the range [0,1]. represents the movement speed of the i-th individual in the t+1-th iteration, represents the movement speed of the i-th individual in the t-th iteration, represents the d-th dimension position of the i-th individual in the t-th iteration, Indicates the position of the individual with the best fitness value among all current individuals;

[0148] In the individual local search phase, the formula used is as follows:

[0149] ;

[0150] In the formula, represents the d-th dimension position of the i-th individual in the t+1-th iteration, represents the search intensity of the i-th individual in the t-th iteration, and represents a random number uniformly distributed in the range [0,1]. represents the exploration ability of the i-th individual in the t-th iteration;

[0151] Update individual exploration control parameters, specifically if and , then accept As the global optimal position, and update the individual exploration control parameters, the updating of the individual exploration control parameters is specifically to update the individual search intensity and update the individual exploration ability through dynamic iterative attenuation; the formula used is as follows:

[0152] ;

[0153] ;

[0154] In the formula, represents the fitness function, represents a random number uniformly distributed in the range [0,1]. represents the search intensity of the i-th individual in the t+1-th iteration, represents the exploration capability of the i-th individual in the t+1th iteration, t represents the current number of iterations, It represents the exploration capability enhancement coefficient, which is a constant;

[0155] Get the optimal individual position of the current iteration, specifically sort all individuals by fitness value, sort the individuals from best to worst according to fitness value, and get the individual position with the highest current fitness value as the optimal individual position of the current iteration;

[0156] Search determination, specifically, by constructing a search termination condition, searching and determining the optimal individual position, and obtaining the optimal individual position data setting;

[0157] The search termination conditions include threshold termination and iteration termination;

[0158] The threshold termination is specifically to set the fitness threshold, when the individual fitness value F i When it is above the fitness threshold, the hyperparameter search is completed;

[0159] The iteration termination specifically refers to terminating the iteration and obtaining the optimal individual position when the maximum number of iterations is reached;

[0160] The optimal individual position includes equipment intelligent control model parameters.

[0161] By performing the above operations, in order to solve the technical problems of improper parameter settings in traditional control models and the parameter optimization algorithm being prone to falling into local optimality, which leads to inaccurate final output results, this solution uses reversible chaotic mapping, speed dynamic factors and dynamic iterative attenuation to enhance the global optimal solution search and improve the robustness of the algorithm, thereby obtaining the optimal parameter values ​​and solving the problem of inaccurate output results of the final control model.

[0162] Embodiment 7, see Figure 1 This embodiment is based on the above embodiment, and the execution of the environmental protection equipment control strategy is specifically to accurately adjust the operating state of the environmental protection equipment based on the output results of the environmental protection equipment state identification module and the environmental protection equipment intelligent control module; if the output result of the environmental protection equipment state identification module is an abnormal state, the environmental protection equipment automatically adjusts the operating state of the environmental protection equipment according to the output result of the environmental protection equipment intelligent control module, responds to the environmental problems and equipment problems identified by the environmental protection equipment, and triggers the safety response mechanism, generates a safety alarm and notifies the equipment management personnel to ensure the stable operation of the equipment and environmental safety.

[0163] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0164] While the embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that many changes, modifications, substitutions and variations can be made to the embodiments without departing from the principles and spirit of the invention.

[0165] The present invention and its embodiments are described above, and such description is not restrictive. The drawings show only one embodiment of the present invention, and the actual structure is not limited thereto. In short, if ordinary technicians in the field are inspired by it, without departing from the purpose of the invention, they can design a structure and embodiment similar to the technical solution without creativity, which should belong to the protection scope of the present invention.

Claims

1. An environmental protection equipment control system based on artificial intelligence algorithm, characterized by: It includes data acquisition module, data preprocessing module, environmental protection equipment status identification module, environmental protection equipment intelligent control module, hyperparameter optimization module and environmental protection equipment control strategy execution module; The data acquisition module collects historical environmental protection equipment operation data and real-time environmental protection equipment operation data from the environmental protection equipment operation system to obtain the environmental protection equipment control original data; The data preprocessing module performs data cleaning, standardization and feature selection on the environmental protection equipment control raw data to obtain preliminary environmental protection equipment control data; The environmental protection equipment status recognition module establishes an environmental protection equipment status recognition model by adopting a clustering algorithm based on a common neighborhood adaptive density method and a cluster center dynamic recognition method, performs model training on the environmental protection equipment status recognition model, and realizes real-time monitoring of the environmental protection equipment during operation to obtain the environmental protection equipment recognition status during the current operation of the environmental protection equipment; The environmental protection equipment intelligent control module establishes an equipment intelligent control model and dynamically selects corresponding data from the real-time environmental protection equipment operation data as input data for the trained equipment intelligent control model based on the output result of the environmental protection equipment status recognition module to obtain equipment intelligent control results; The hyperparameter optimization module improves the search algorithm for obtaining the optimal parameters of the control model through reversible chaotic mapping, speed dynamic factor and dynamic iterative attenuation, and finally obtains the optimal parameter combination of the equipment intelligent control model; The environmental protection equipment control strategy execution module accurately adjusts the operating status of the environmental protection equipment based on the output results of the environmental protection equipment status identification module and the environmental protection equipment intelligent control module, and sends reminders to equipment management personnel.

2. The environmental protection equipment control system based on artificial intelligence algorithm according to claim 1 is characterized in that: The environmental protection equipment status recognition module specifically establishes an environmental protection equipment status recognition model, trains the environmental protection equipment status recognition model, and realizes real-time monitoring of the environmental protection equipment during operation to obtain real-time monitoring results of the environmental protection equipment status; and includes the following steps: Establish an environmental protection equipment status recognition model, specifically select cluster centers and generate accurate clustering results through the common neighborhood adaptive density method and cluster center dynamic identification method; including the following steps: Calculate the similarity between sample data points, specifically to measure the distance between sample data points. The sample data points are the data values ​​of various operating parameters in the historical environmental protection equipment operation data and the real-time environmental protection equipment operation. The formula used is expressed as follows: ； Where, Represents the similarity between sample data points, and Represents sample data points and sample data points Environmental quality data, and Represents sample data points and sample data points Device status data, and Represent the weights of environmental quality data and equipment status data respectively, Indicates the similarity of device status data in sample data points, calculated by cosine similarity; Calculate the local density of the sample data points. Specifically, the local density of the sample data points is calculated using the common neighborhood adaptive density method. The formula used is as follows: ； Where, Represents sample data points Local density value, Represents sample data points The nearest neighbor set of Represents sample data points The nearest neighbor set of Represents sample data points Neighbor sample data points, Represents sample data points and sample data points The sample data points in the common nearest neighbor set of Represents the distance between the sample data point and its kth nearest neighbor, calculated using the Euclidean distance; Calculate the relative distance; the formula used is as follows: ； Where, Represents sample data points Local density value, Represents sample data points The distance to the nearest point with higher density, j means that the condition is met The index of the sample data point, Represents sample data points and sample data points The number of common nearest neighbors between Represents sample data points It has the highest local density among all sample data points, and M represents the number of sample data points; Calculate the decision value, specifically first and Normalize to the interval [0,1] to ensure that they are in the same range, and then calculate the decision value of each sample data point to determine the cluster center. The decision value is obtained by multiplying the local density and the relative distance. The formula used is as follows: ； Where, represents the decision value, represents the local density of sample data points, Represents the distance between a sample data point and the nearest point with higher density; Dynamic identification of cluster centers is specifically to select candidate cluster centers by setting a probability threshold of the decision value. First, the cumulative probability of the decision value is calculated. If the cumulative probability of the decision value meets the set probability threshold, the sample data point is selected as the candidate cluster center. Then, all candidate cluster centers are compared in pairs. If the similarity between two candidate cluster centers is greater than 0.9, the candidate cluster center with lower local density is determined as a subordinate point. After removing these subordinate points, the remaining candidate cluster centers are the final cluster centers. The formula used is expressed as follows: ； Where, Represents the cumulative probability function, that is, the decision value falls within the interval The probability within represents the lower threshold of the decision value, Indicates the upper threshold of the decision value; Cluster assignment, specifically, for each subordinate point, find the point with the closest distance and higher local density, and assign the point to the corresponding cluster center; Training an environmental protection equipment status recognition model, specifically using the environmental quality data, equipment status data, and environmental protection equipment recognition status data in the historical environmental protection equipment operation data as input data to train the environmental protection equipment status recognition model, and analyzing the clustering results to determine the environmental protection equipment recognition status corresponding to each cluster, thereby obtaining a trained environmental protection equipment status recognition model; Real-time monitoring of environmental protection equipment status specifically involves using the environmental quality data and equipment status data in the real-time environmental protection equipment operation data as input data of the trained environmental protection equipment status recognition model to obtain the environmental protection equipment recognition status during the current operation of the environmental protection equipment.

3. The environmental protection equipment control system based on artificial intelligence algorithm according to claim 1 is characterized in that: The environmental protection equipment intelligent control module specifically obtains the environmental protection equipment intelligent control strategy by establishing an equipment intelligent control model, training the equipment intelligent control model and generating an equipment intelligent control strategy; The specific steps include: Establishing an intelligent control model for equipment includes the following steps: The output calculation of the LSTM bidirectional unit is specifically based on the input data at the current moment, the hidden state and cell state at the previous moment, and the hidden state and cell state at the next moment. The forward and reverse hidden states are calculated respectively, and these two hidden states are combined to obtain the final hidden state of the LSTM bidirectional unit. The formula used is as follows: ； ； ； Where, Represents the unit operation function, h represents the hidden state of the combined forward and backward LSTM units, Indicates the current hidden state in the forward direction. Indicates the hidden state in the forward direction at the previous moment, Indicates the reverse hidden state at the current moment, Indicates the reverse hidden state at the next moment, Represents the input data at the current moment, Indicates the state of the cell in the forward direction at the previous moment, Indicates the state of the cell in the reverse direction at the next moment; The model output value is obtained using the following formula: ； Where, represents the output value of the model, represents the weight matrix corresponding to the output, represents the activation function, B y Represents the bias parameter of the output layer; Equipment intelligent control model training, specifically using the historical environmental protection equipment operation data in the environmental protection equipment control preliminary data to train the equipment intelligent control model training to obtain a trained equipment intelligent control model training; The equipment intelligent control strategy is generated by dynamically selecting corresponding data from the real-time environmental protection equipment operation data as input data of the trained equipment intelligent control model based on the output results of the environmental protection equipment status recognition module to obtain the environmental protection equipment intelligent control strategy.

4. The environmental protection equipment control system based on artificial intelligence algorithm according to claim 1 is characterized in that: The hyperparameter optimization module specifically obtains the optimal parameter combination of the equipment intelligent control model through a search algorithm; The following steps are involved: Initialization parameters, specifically by constructing the initial parameters of the algorithm; the initial parameters of the algorithm include the population size N, the population dimension D and the maximum number of iterations ; Initializing the population, specifically by generating chaotic sequence values ​​through a reversible chaotic map, includes the following steps: Generate N chaotic sequence values ​​and initialize the random value z0; the formula used is as follows: ； Where, represents the i-th chaotic sequence value of the d-th dimension, represents the i+1th chaotic sequence value in the dth dimension, Represents adjustment parameters, used to adjust mapping behavior; The chaotic sequence value conversion search individual is expressed as follows: ； Where, Indicates the initialization position of the dth dimension of the i-th individual, lb d and ub d Respectively represent the search lower and upper limits of dimension d; Calculate the fitness value, specifically calculate the individual fitness value F in the population i ; The performance of the equipment intelligent control model based on the individual position is used as the individual fitness value; To calculate the individual speed dynamic factor, the formula used is as follows: ； Where, It represents the dynamic factor of the speed of the i-th individual at the t+1th iteration, represents the dynamic factor of the motion speed of the i-th individual in the t-th iteration, represents the Cauchy probability distribution; Search for individual motion attribute updates, specifically updating motion frequency and motion speed; the formula used is as follows: ； ； Where, represents the movement frequency of the i-th individual, represents the minimum frequency of individual movement, represents the maximum frequency of individual movement, represents a random number uniformly distributed in the range [0,1]. represents the speed of the i-th individual in the t+1-th iteration, represents the speed of the i-th individual in the t-th iteration, represents the d-th dimension position of the i-th individual in the t-th iteration, Indicates the position of the individual with the best fitness value among all current individuals; In the individual local search phase, the formula used is as follows: ； Where, represents the d-th dimension position of the i-th individual in the t+1-th iteration, represents the search intensity of the i-th individual in the t-th iteration, and represents a random number uniformly distributed in the range [0,1]. represents the exploration ability of individual i in iteration t; Update individual exploration control parameters, specifically if and , then accept As the global optimal position, and update the individual exploration control parameters, the updated individual exploration control parameters are specifically updated by dynamic iterative attenuation of the individual search intensity and the individual exploration ability; the formula used is as follows: ； ； Where, represents the fitness function, represents a random number uniformly distributed in the range [0,1]. Indicates the search intensity of the i-th individual in the t+1th iteration, t represents the current number of iterations, represents the exploration ability of the i-th individual in the t+1-th iteration, It represents the exploration ability enhancement coefficient, which is a constant; Get the optimal individual position of the current iteration. Specifically, sort all individuals by fitness value, sort the individuals from best to worst, and get the individual position with the highest current fitness value as the optimal individual position of the current iteration. Search determination, specifically, by constructing a search termination condition, performing search determination on the optimal individual position, and obtaining the optimal individual position data setting; The search termination conditions include threshold termination and iteration termination; The threshold termination is specifically to set the fitness threshold, when the individual fitness value F i When it is above the fitness threshold, the hyperparameter search is completed; The iteration termination specifically refers to terminating the iteration and obtaining the optimal individual position when the maximum number of iterations is reached; The optimal individual position includes equipment intelligent control model parameters.

5. The environmental protection equipment control system based on artificial intelligence algorithm according to claim 1 is characterized in that: The environmental protection equipment control strategy execution module specifically adjusts the operating status of the environmental protection equipment based on the output results of the environmental protection equipment status identification module and the environmental protection equipment intelligent control module; if the output result of the environmental protection equipment status identification module is an abnormal state, the environmental protection equipment automatically adjusts the operating status of the environmental protection equipment according to the output result of the environmental protection equipment intelligent control module, responds to the environmental problems and equipment problems identified by the environmental protection equipment, and triggers the safety response mechanism, generates a safety alarm and notifies the equipment management personnel to ensure the stable operation of the equipment and environmental safety.

6. The environmental protection equipment control system based on artificial intelligence algorithm according to claim 1, characterized in that: The data acquisition module specifically acquires the original data of environmental protection equipment control from the environmental protection equipment operation system by acquisition; the original data of environmental protection equipment control includes historical environmental protection equipment operation data and real-time environmental protection equipment operation data; the historical environmental protection equipment operation data and real-time environmental protection equipment operation data both include environmental quality data and equipment status data; the historical environmental protection equipment operation data also includes environmental protection equipment identification status and historical environmental protection equipment control strategy data; the environmental quality data includes air quality data, water quality data, soil quality data; the air quality data includes fine particulate matter concentration, inhalable particulate matter concentration, carbon dioxide concentration, nitrogen oxide concentration, sulfur dioxide concentration and ozone concentration; the water quality data includes water pH, dissolved oxygen concentration, chemical oxygen demand, ammonia nitrogen concentration, heavy metal content and turbidity; the soil quality data includes soil moisture, soil pH, soil organic matter content and soil temperature; the equipment status data includes equipment temperature, equipment vibration data, noise level, equipment current and equipment power; the environmental protection equipment identification status includes normal, air pollution, water pollution, soil pollution and equipment operation abnormality. The environmental protection equipment identification status is used as a data label. The data label is not considered during clustering and is only used when selecting cluster labels.

7. The environmental protection equipment control system based on artificial intelligence algorithm according to claim 1 is characterized in that: The data preprocessing module specifically performs data cleaning, standardization and feature selection on the original data of environmental protection equipment control to obtain preliminary data of environmental protection equipment control; the data cleaning is to process missing values, outliers and duplicate values; the standardization is to standardize the data based on the maximum and minimum normalization method; the feature selection is to use the correlation analysis method to calculate the correlation between each feature and environmental protection equipment status identification and environmental protection equipment control, and screen out the most valuable features for environmental protection equipment status identification and environmental protection equipment control.

Images