A smart industrial water treatment information management and control system based on a lower computer

Abstract

The present invention discloses a smart industrial water treatment information management and control system based on a lower computer, which is used in the field of industrial wastewater treatment, including an intelligent edge execution module, a multi-communication module, an intelligent analysis module and a management and control module; the intelligent edge execution module is used to realize the coordination between the upper computer and the lower computer, and control the switch of the industrial water treatment equipment; the multi-communication module is used to intelligently select and adjust the communication path according to the data transmission requirements and network environment of the lower computer; the intelligent analysis module is used for data analysis and predictive modeling, and provides optimization strategies for the water treatment process; the management and control module is used to respond to environmental changes and industrial water treatment status in real time, and adjust the operating parameters and operation modes of the industrial water treatment equipment, and at the same time, fault prevention and maintenance plan formulation are carried out based on real-time data and long-term trends. The present invention can dynamically adjust the parameters of the genetic algorithm to achieve continuous optimization of the chemical agent addition strategy.

Description

Technical Field

[0001] The present invention relates to the field of industrial wastewater treatment, and in particular, to an intelligent industrial water treatment information management and control system based on a lower computer. Background Art

[0002] Industrial wastewater is wastewater generated during industrial production, containing industrial products, raw materials, intermediates and products, as well as sewage generated when cleaning industrial equipment and containers. It usually contains various harmful substances, such as heavy metals, organic matter, inorganic matter and other pollutants. If the substances are discharged directly without treatment, they will have serious impacts on the environment and human health. The sources of industrial wastewater are diverse, including but not limited to chemical, pharmaceutical, food processing, textile, mineral processing and metal processing industries.

[0003] With the acceleration of industrialization, the importance of industrial wastewater treatment has become increasingly prominent. Effective industrial wastewater treatment not only helps protect the environment, but also can recycle and reuse some resources, such as water resources and some valuable chemicals.

[0004] Traditional industrial water treatment systems often have delays in communication and command execution between the host and slave computers, and lack sufficient response speed and flexibility, which may lead to the inability to adjust equipment operation in an emergency, affecting the efficiency and safety of the entire water treatment process; under different network conditions, especially in complex or unstable network environments, data transmission may face interruptions and delays, affecting the effectiveness of real-time monitoring and control; previous systems may not be accurate enough in data analysis and prediction, and cannot effectively extract key information from large amounts of data, resulting in insufficient decision support, and traditional systems may have defects in identifying and handling abnormal situations, such as equipment failures or sudden changes in water quality, which will increase the risk of system operation and maintenance costs.

[0005] Currently, no effective solution has been proposed for the problems in the related technologies. Summary of the invention

[0006] In order to overcome the above problems, the present invention aims to propose an intelligent industrial water treatment information management and control system based on a lower computer, with the aim of solving the problems that previous systems may not be accurate enough in data analysis and prediction, and cannot effectively extract key information from large amounts of data, resulting in insufficient decision support. In addition, traditional systems may have defects in identifying and handling abnormal situations, such as equipment failures or sudden changes in water quality, which will increase the risk of system operation and maintenance costs.

[0007] To this end, the specific technical solution adopted by the present invention is as follows: A smart industrial water treatment information management and control system based on a lower computer, the system includes: an intelligent edge execution module, a multi-communication module, a smart analysis module and a management and control module; The intelligent edge execution module is connected to the cloud-based intelligent analysis module through the multi-communication module, and the cloud-based intelligent analysis module is connected to the control module; Intelligent edge execution module, used to realize the coordination between the host computer and the slave computer to control the switch of industrial water treatment equipment; Multiple communication modules are used to intelligently select and adjust communication paths according to the data transmission requirements and network environment of the lower computer; Smart analytics module for data analysis and predictive modeling, and providing optimization strategies for water treatment processes; The management and control module is used to respond to environmental changes and industrial water treatment status in real time, and adjust the operating parameters and operation modes of industrial water treatment equipment. At the same time, it formulates fault prevention and maintenance plans based on real-time data and long-term trends.

[0008] Optionally, the intelligent edge execution module includes the following when realizing the coordination between the upper computer and the lower computer to control the switch of the industrial water treatment equipment: Establish data exchange communication connection between the upper computer and the lower computer through the network; According to the control command of the host computer, operate the switch of the industrial water treatment equipment and send the control signal to the control interface of the equipment; Obtain data on water quality parameters and equipment status collected from various sensors and monitoring devices of industrial water treatment equipment.

[0009] Optionally, the multiple communication module includes: Analyze the data transmission requirements of the lower computer; Assess the current network environment; Select the best communication path based on the data transmission requirements and network environment assessment results; Dynamically adjust the communication path according to the actual data transmission process and network environment conditions.

[0010] Optionally, the smart analytics module includes data analysis and predictive modeling capabilities to provide optimization strategies for the water treatment process: Acquire water quality parameter data and process the water quality parameter data; The principal component analysis method was used to analyze the characteristics of the extracted water quality parameter data; According to the characteristics of water quality parameter data, the long short-term memory network model is used to predict the parameters in the water treatment process; Detecting anomalies in water treatment processes using isolation forest models; Genetic algorithms are used to determine the optimal chemical dosage and treatment time, and the prediction results of the long-short-term memory network model are combined to provide adjustment suggestions and formulate optimization strategies.

[0011] Optionally, the principal component analysis method is used to analyze the characteristics of the extracted water quality parameter data including: The water quality parameter data are centralized and standardized to ensure that the variables of the water quality parameter data are on the same scale; The processed water quality parameter data are used to calculate the covariance matrix between variables, and the covariance matrix is ​​subjected to eigendecomposition to obtain eigenvalues ​​and eigenvectors; Select components that meet the preset requirements according to the size of the characteristic value; Use the eigenvectors to create a transformation matrix, and use the transformation matrix to map the components that meet the preset requirements into the principal component space; Components meeting preset requirements are parsed in the principal component space, and the components meeting preset requirements are applied according to the eigenvectors.

[0012] Optionally, the processed water quality parameter data is used to calculate the covariance matrix between the variables, and the covariance matrix is ​​subjected to eigendecomposition to obtain eigenvalues ​​and eigenvectors including: Obtain the dissolved oxygen content and organic matter content in each pair of variables in the data set of water quality parameter data, and calculate the covariance between the dissolved oxygen content and organic matter content; The covariance values ​​of all pairs of variables are constructed into a square matrix to form a covariance matrix; Perform eigendecomposition on the covariance matrix and extract eigenvalues ​​and eigenvectors; Get the degree of data change for each eigenvalue and eigenvector.

[0013] Alternatively, the covariance formula between pairs of variables is: ; In the formula, Representation variables and The covariance between Represents the dissolved oxygen content of the data set in the water quality parameter data; Indicates the organic matter content of the data set in the water quality parameter data; represents the total number of observations; Indicates dissolved oxygen content The value in the kth observation; Indicates organic matter content The value in the kth observation; and Represents the average value of different variables.

[0014] Optionally, according to the characteristics of water quality parameter data, the long short-term memory network model is used to predict the parameters in the water treatment process, including: Construct the architecture of the LSTM network model, which includes the input layer, the hidden layer of the LSTM network, and the output layer; The characteristics of water quality parameter data are divided into training set and test set, and the training set is used to train the long short-term memory network model; Use the test set to evaluate the model prediction performance; The trained model is used to predict future parameters in the water treatment process and output the predicted values ​​of water quality parameters in the future.

[0015] Optionally, using the Isolation Forest Model to detect anomalies in the water treatment process includes: S1. Initialize the isolation forest model. For each isolated tree, randomly select a subset of the data set. S2, randomly select features in the subset and randomly select the split point between the maximum and minimum values ​​of the feature; S3, divide the data into two subsets according to the split point, and repeat the steps of S2 until the data is completely isolated or the preset tree depth is reached; S4. For each detected data, calculate the average path length of each detected data isolated in all isolated trees; S5. Setting a threshold value according to the calculated isolation score; S6, data points with scores below this threshold are marked as outliers; S7. Analyze the detected abnormal points and identify equipment failure problems.

[0016] Optionally, a genetic algorithm is used to determine the optimal chemical dosage and treatment time, combined with the prediction results of the long short-term memory network model to provide adjustment suggestions and develop optimization strategies including: Determine the method of expressing the amount of chemical agent added and the treatment time; Create a fitness function that quantifies the effect of parameter combinations; Set selection, crossover, and mutation strategies, and execute cycles of selection, crossover, mutation, and fitness evaluation; Monitor the optimization progress of the genetic algorithm and the search for the optimal solution, and integrate the prediction results of the long short-term memory network model; Integrate the prediction results of future water quality parameters by the long short-term memory network model into the decision-making process of the genetic algorithm; The parameters of the genetic algorithm were adjusted according to the prediction results of the long short-term memory network model, and an optimization strategy for chemical dosage and treatment time was formulated.

[0017] Compared with the prior art, this application has the following beneficial effects: 1. The present invention establishes a stable communication connection through the network to realize data exchange between the host computer and the industrial water treatment equipment (slave computer). According to the instructions of the host computer, the intelligent edge execution module operates the switch of the industrial water treatment equipment, including starting or stopping the equipment, adjusting the working parameters, etc., which improves the response speed and flexibility, and collects the operating data of the industrial water treatment equipment, including the water quality parameters and equipment status obtained by various sensors and monitoring equipment, which is very important for monitoring the efficiency and safety of the entire water treatment process.

[0018] 2. The present invention intelligently selects the best communication path according to the data transmission requirements of the lower computer and the current network environment, such as selecting the network with the fastest speed and the lowest latency. During the data transmission process, the communication path can be dynamically adjusted according to changes in the network environment, such as automatically switching from a congested network to a more stable network, to ensure the continuity and reliability of data transmission. By optimizing the communication path, efficient and stable data transmission can be maintained under different network conditions, which is crucial for data processing and decision-making in industrial automation systems.

[0019] 3. The present invention can effectively extract key features from a large number of water quality parameters through principal component analysis, simplify the data processing process, and retain the most important information, providing a solid foundation for subsequent predictions and decisions. By using the long short-term memory network model, the module can accurately predict key parameters in the water treatment process, such as pH value, temperature, etc. The LSTM model is particularly suitable for processing time series data, and can capture long-term dependencies in the data to improve the accuracy of predictions. The use of the isolation forest model can quickly identify abnormal conditions in the water treatment process, such as equipment failures or parameter mutations, which is crucial for timely intervention and maintenance of system stability. By combining the prediction results of the genetic algorithm and the LSTM model, the optimal chemical dosage and treatment time can be determined, which helps to maximize cost-effectiveness while ensuring that the water quality meets the predetermined standards. According to the prediction results of the LSTM model, the parameters of the genetic algorithm can be dynamically adjusted to achieve continuous optimization of the chemical addition strategy and adapt to changes in water quality and environmental conditions. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] The above characteristics, features and advantages of the present invention and their implementation methods and methods will become more clearly understood in conjunction with the following description of the embodiments, which are described in detail in conjunction with the accompanying drawings. Herein, a schematic diagram is shown: Figure 1It is a principle block diagram of a smart industrial water treatment information management and control system based on a lower computer according to an embodiment of the present invention.

[0021] In the figure: 1. Intelligent edge execution module; 2. Multi-communication module; 3. Intelligent analysis module; 4. Management and control module. DETAILED DESCRIPTION

[0022] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0023] According to an embodiment of the present invention, a smart industrial water treatment information management and control system based on a lower computer is provided.

[0024] The present invention is further described with reference to the accompanying drawings and specific embodiments. Figure 1 As shown, according to the smart industrial water treatment information management and control system based on the lower computer according to an embodiment of the present invention, the system includes: an intelligent edge execution module 1, a multi-communication module 2, a smart analysis module 3 and a management and control module 4; The intelligent edge execution module 1 is connected to the cloud intelligent analysis module 3 through the multi-communication module 2, and the cloud intelligent analysis module 3 is connected to the control module 4; The intelligent edge execution module 1 is used to realize the collaboration between the upper computer and the lower computer to control the switch of the industrial water treatment equipment.

[0025] Preferably, the intelligent edge execution module 1 includes the following steps when realizing the collaboration between the host computer and the slave computer to control the switch of the industrial water treatment equipment: Establish data exchange communication connection between the upper computer and the lower computer through the network; According to the control command of the host computer, operate the switch of the industrial water treatment equipment and send the control signal to the control interface of the equipment; Obtain data on water quality parameters and equipment status collected from various sensors and monitoring devices of industrial water treatment equipment.

[0026] It needs to be explained that, first, the intelligent edge execution module establishes a stable communication connection through the network (such as WiFi, Bluetooth or wired network), so that the upper computer (usually a central control system or monitoring system) can exchange data with the lower computer (that is, the industrial water treatment equipment itself), and the communication connection allows real-time data transmission and command issuance; according to the control command issued by the upper computer, the intelligent edge execution module will operate the switch of the industrial water treatment equipment, which includes starting or stopping the equipment, adjusting the working parameters, etc., which is usually achieved by sending control signals to the control interface of the equipment, which can be digital or analog signals; the intelligent edge execution module is also responsible for collecting the operating data of the industrial water treatment equipment, including water quality parameters (such as pH value, turbidity, harmful substance content, etc.) obtained from various sensors and monitoring equipment and the operating status of the equipment (such as flow, pressure, temperature, etc.), which is crucial for monitoring the efficiency and safety of the entire water treatment process.

[0027] The multi-communication module 2 is used to intelligently select and adjust the communication path according to the data transmission requirements and network environment of the lower computer.

[0028] Preferably, the multi-communication module 2 includes: Analyze the data transmission requirements of the lower computer; Assess the current network environment; Select the best communication path based on the data transmission requirements and network environment assessment results; Dynamically adjust the communication path according to the actual data transmission process and network environment conditions.

[0029] It should be explained that by analyzing the data transmission requirements of the lower computer and evaluating the current network environment, the communication path is intelligently selected and adjusted to ensure that data transmission is both efficient and reliable. Specifically, the data type and transmission requirements sent by the lower computer are first identified, and then the performance of the available network, such as bandwidth, latency and stability, is evaluated. Based on the above information, the best communication path is selected, such as selecting the network with the fastest speed and lowest latency. The multi-communication module 2 can dynamically adjust the communication path during data transmission to adapt to changes in the network environment, such as automatically switching from a congested network to a more stable network, making the multi-communication module 2 a key factor in ensuring data transmission efficiency and stability in industrial automation systems.

[0030] Smart Analysis Module 3 is used for data analysis and predictive modeling, and provides optimization strategies for the water treatment process.

[0031] Preferably, the intelligent analysis module 3 includes the following functions in data analysis and predictive modeling to provide an optimization strategy for the water treatment process: Acquire water quality parameter data and process the water quality parameter data; The principal component analysis method was used to analyze the characteristics of the extracted water quality parameter data; According to the characteristics of water quality parameter data, the long short-term memory network model is used to predict the parameters in the water treatment process; Detecting anomalies in water treatment processes using isolation forest models; Genetic algorithms are used to determine the optimal chemical dosage and treatment time, and the prediction results of the long-short-term memory network model are combined to provide adjustment suggestions and formulate optimization strategies.

[0032] In addition, it should be noted that the smart analysis module 3 collects water quality-related data such as pH, temperature, turbidity, etc. from various sensors and monitoring equipment. Then, the data is preprocessed, including cleaning, standardization and normalization, to facilitate in-depth analysis. Through principal component analysis, the module can extract the most important features from a large number of water quality parameters, which helps to simplify the data and highlight the most critical information, laying the foundation for subsequent prediction and analysis. The long short-term memory network is an efficient time series analysis tool that can predict key parameters in the water treatment process based on historical data. This is very useful for identifying potential problems in advance and adjusting the treatment process. The isolation forest model is an effective anomaly detection algorithm that can quickly identify data points that do not conform to the normal pattern during the water treatment process, thereby helping to promptly discover and deal with potential problems. The smart analysis module uses genetic algorithms to determine the optimal dosage and treatment time of chemical agents, and combines the prediction results of the long short-term memory network (LSTM) model for fine-tuning to ensure that the chemical treatment process is both efficient and cost-effective.

[0033] Preferably, the characteristics of the water quality parameter data extracted by principal component analysis include: The water quality parameter data are centralized and standardized to ensure that the variables of the water quality parameter data are on the same scale; The processed water quality parameter data are used to calculate the covariance matrix between variables, and the covariance matrix is ​​subjected to eigendecomposition to obtain eigenvalues ​​and eigenvectors; Select components that meet the preset requirements according to the size of the characteristic value; Use the eigenvectors to create a transformation matrix, and use the transformation matrix to map the components that meet the preset requirements into the principal component space; Components meeting preset requirements are parsed in the principal component space, and the components meeting preset requirements are applied according to the eigenvectors.

[0034] Preferably, the processed water quality parameter data is used to calculate the covariance matrix between the variables, and the covariance matrix is ​​subjected to eigendecomposition to obtain eigenvalues ​​and eigenvectors including: Obtain the dissolved oxygen content and organic matter content in each pair of variables in the data set of water quality parameter data, and calculate the covariance between the dissolved oxygen content and organic matter content; The covariance values ​​of all pairs of variables are constructed into a square matrix to form a covariance matrix; Perform eigendecomposition on the covariance matrix and extract eigenvalues ​​and eigenvectors; Get the degree of data change for each eigenvalue and eigenvector.

[0035] In addition, it should be noted that each eigenvalue and eigenvector can be obtained according to the degree of change of the data. The greater the degree of change, the more obvious the change trend in the water quality parameter data, thereby realizing water quality monitoring and management.

[0036] Preferably, the covariance formula between the variable pairs is: ; In the formula, Representation variables and The covariance between Represents the dissolved oxygen content of the data set in the water quality parameter data; Indicates the organic matter content of the data set in the water quality parameter data; represents the total number of observations; Indicates dissolved oxygen content The value in the kth observation; Indicates organic matter content The value in the kth observation; and Represents the average value of different variables.

[0037] In addition, it should be noted that the water quality parameter data are first centered and standardized to ensure that different variables are compared on the same scale. This is achieved by subtracting the mean of each variable and dividing it by its standard deviation, ensuring that the data has consistent importance in all directions. Next, the processed data is used to calculate the covariance matrix between the variables. The covariance matrix reveals the correlation between the variables, in which each element is the covariance value between the corresponding variable pairs. Then, the covariance matrix is ​​eigendecomposed to extract eigenvalues ​​and eigenvectors. The eigenvalues ​​represent the variance of each principal component, while the eigenvectors define the direction of the components. The main direction of change in the data is determined by selecting the eigenvector corresponding to the largest eigenvalue, and then the eigenvector is used to construct a transformation. Matrix, maps the original data to the principal component space, so that the component that best represents the variability of the data can be analyzed. In the principal component space, the principal component that meets the preset requirements can be selected according to the size of the eigenvalue; finally, the water quality parameter data is parsed and applied according to the selected principal component and its eigenvector for in-depth analysis and prediction, which helps to compress data, reduce dimensions, and retain the most critical information, providing accurate data support and optimization strategies for the water treatment process. The principal component analysis method has become an indispensable tool in water quality monitoring and treatment, and provides a solid data foundation for ensuring water quality and optimizing the treatment process; dissolved oxygen content and organic matter content are important variables in water quality parameter data, which are important factors in detecting sewage treatment, and are also the basis for obtaining water quality parameter data.

[0038] Preferably, according to the characteristics of water quality parameter data, using the long short-term memory network model to predict the parameters in the water treatment process includes: Construct the architecture of the LSTM network model, which includes the input layer, the hidden layer of the LSTM network, and the output layer; The characteristics of water quality parameter data are divided into training set and test set, and the training set is used to train the long short-term memory network model; Use the test set to evaluate the model prediction performance; The trained model is used to predict future parameters in the water treatment process and output the predicted values ​​of water quality parameters in the future.

[0039] Preferably, using the isolation forest model to detect abnormal conditions in the water treatment process includes: S1. Initialize the isolation forest model. For each isolated tree, randomly select a subset of the data set. S2, randomly select features in the subset and randomly select the split point between the maximum and minimum values ​​of the feature; S3, divide the data into two subsets according to the split point, and repeat the steps of S2 until the data is completely isolated or the preset tree depth is reached; S4. For each detected data, calculate the average path length of each detected data isolated in all isolated trees; S5. Setting a threshold value according to the calculated isolation score; S6, data points with scores below this threshold are marked as outliers; S7. Analyze the detected abnormal points and identify equipment failure problems.

[0040] In addition, it should be noted that, first, a network structure including an input layer, several hidden layers (composed of LSTM units) and an output layer is defined. The network architecture is designed to capture long-term dependencies in time series data, and the collected water quality parameter data is divided into a training set and a test set. The training set is used to train the LSTM model. In this process, the LSTM model learns how to predict key parameters in the water treatment process based on historical data. The test set is used to evaluate the prediction performance of the model to ensure that the model can also make accurate predictions on unknown data. The trained LSTM model is used to predict future parameters in the water treatment process, and the predicted values ​​of water quality parameters within a period of time are output to adjust the treatment strategy in advance and avoid potential problems.

[0041] In addition, the initialization isolation forest model randomly selects a part of the data from the entire data set as a subset, and uses it to construct multiple isolated trees. Each tree is an independently analyzed unit, and they together form a "forest". In each subset, a feature is randomly selected, and a split point is randomly determined within the possible value range of the feature (between the maximum and minimum values). Then the data is divided into two subsets based on this split point. This process is repeated until each data point is "isolated" or the tree reaches a preset depth. Next, for each data point, its average path length in all isolated trees is calculated. The average path length reflects the difficulty of the data point being isolated. The shorter the path, the easier it is for the data point to be isolated, which usually means that it is more likely to be an anomaly. By setting a threshold, data points with low isolation scores (i.e., short average path length) are marked as anomalies. The data points may represent abnormal conditions in the water treatment process, such as equipment failure, parameter mutation, etc. Finally, the data points marked as abnormal are analyzed in detail to determine the specific cause of the problem and possible solutions.

[0042] Preferably, a genetic algorithm is used to determine the optimal chemical dosage and treatment time, and adjustment suggestions are provided in combination with the prediction results of the long short-term memory network model, and an optimization strategy is formulated including: Determine the method of expressing the amount of chemical agent added and the treatment time; Create a fitness function that quantifies the effect of parameter combinations; Set selection, crossover, and mutation strategies, and execute cycles of selection, crossover, mutation, and fitness evaluation; Monitor the optimization progress of the genetic algorithm and the search for the optimal solution, and integrate the prediction results of the long short-term memory network model; Integrate the prediction results of future water quality parameters by the long short-term memory network model into the decision-making process of the genetic algorithm; The parameters of the genetic algorithm were adjusted according to the prediction results of the long short-term memory network model, and an optimization strategy for chemical dosage and treatment time was formulated.

[0043] It should be explained that, first of all, it is necessary to define the representation of the dosage of chemical agents and the treatment time. Usually, the parameters will be encoded as a set of numerical values ​​to facilitate the processing of genetic algorithms. Then, a fitness function is designed to evaluate the effects of different combinations of chemical dosages and treatment times. This function is based on the quality of the water treatment effect, such as the stability of water quality parameters, treatment costs and environmental impacts, to quantify the performance of each parameter combination. In the genetic algorithm, new parameter combinations are generated through operations such as selection, crossover and mutation. The selection operation selects excellent solutions based on the fitness function, and crossover and mutation are used to generate new possible solutions, increasing the diversity of the search space. The above steps are executed cyclically. In each iteration, the algorithm is guided to search for the optimal solution through fitness evaluation. At the same time, the optimization progress of the algorithm is monitored to ensure that the algorithm evolves towards a more effective solution. The prediction results of the long short-term memory network model on future water quality parameters are integrated into the decision-making process of the genetic algorithm to ensure that the optimization strategy is not only based on historical and current data, but also takes into account future trends. According to the prediction results of the LSTM model, the parameters in the genetic algorithm, such as the mutation rate or crossover rate, are adjusted in time to adapt to the changing water quality conditions. Finally, the results of the genetic algorithm and the LSTM model are combined to develop an optimization strategy for the amount of chemical agent added and the treatment time that is both economical and efficient.

[0044] The management and control module 4 is used to respond to environmental changes and industrial water treatment status in real time, and adjust the operating parameters and operation modes of industrial water treatment equipment, while formulating fault prevention and maintenance plans based on real-time data and long-term trends.

[0045] It needs to be explained that the management and control module 4 plays a vital role in the industrial water treatment system. It monitors environmental changes and water treatment status in real time, automatically adjusts equipment operating parameters and operation modes, and ensures the efficiency and stability of the water treatment process. The module continuously collects water quality parameters such as temperature, pH value, chemical concentration, etc. through sensors to understand the status of the water treatment process in real time. Once any abnormality or change is detected, such as a sudden rise in water temperature or a change in chemical concentration, the system will respond immediately and adjust the filter's operating frequency or chemical dosage to adapt to the current water quality conditions. In addition, the module also uses long-term data analysis to predict potential failures and formulate maintenance plans to effectively prevent failures. The real-time monitoring and adaptive adjustment mechanism not only improves water treatment efficiency, but also reduces operating costs and potential risks, ensuring the long-term stable operation of the system.

[0046] In summary, with the help of the above-mentioned technical scheme of the present invention, the present invention establishes a stable communication connection through the network to realize data exchange between the upper computer and the industrial water treatment equipment (lower computer). According to the instructions of the upper computer, the intelligent edge execution module operates the switch of the industrial water treatment equipment, including starting or stopping the equipment, adjusting the working parameters, etc., thereby improving the response speed and flexibility, and collecting the operating data of the industrial water treatment equipment, including water quality parameters and equipment status obtained by various sensors and monitoring equipment, which is crucial for monitoring the efficiency and safety of the entire water treatment process; the present invention intelligently selects the best communication path according to the data transmission requirements of the lower computer and the current network environment, such as selecting the network with the fastest speed and the lowest latency. During the data transmission process, the communication path can be dynamically adjusted according to changes in the network environment, such as automatically switching from a congested network to a more stable network, to ensure the continuity and reliability of data transmission. By optimizing the communication path, efficient and stable data transmission can be maintained under different network conditions, which is very important for data processing in industrial automation systems. The present invention can effectively extract key features from a large number of water quality parameters through principal component analysis, simplify the data processing process, retain the most important information, and provide a solid foundation for subsequent prediction and decision-making. By using the long short-term memory network model, the module can accurately predict key parameters in the water treatment process, such as pH value, temperature, etc. The LSTM model is particularly suitable for processing time series data, and can capture long-term dependencies in the data to improve the accuracy of prediction. The use of the isolation forest model can quickly identify abnormal conditions in the water treatment process, such as equipment failure or parameter mutation, which is crucial for timely intervention and maintenance of system stability. By combining the prediction results of the genetic algorithm and the LSTM model, the optimal chemical dosage and treatment time can be determined, which helps to maximize cost-effectiveness and ensure that the water quality meets the predetermined standards. According to the prediction results of the LSTM model, the parameters of the genetic algorithm can be dynamically adjusted to achieve continuous optimization of the chemical addition strategy and adapt to changes in water quality and environmental conditions.

[0047] Although the present invention has been disclosed as above with preferred embodiments, the embodiments are merely examples for the convenience of description and are not intended to limit the present invention. Those skilled in the art may make several changes and modifications without departing from the spirit and scope of the present invention. The scope of protection claimed by the present invention shall be based on the claims.

Claims

1. A smart industrial water treatment information management and control system based on a lower computer, characterized in that: The system includes: intelligent edge execution module, multi-communication module, intelligent analysis module and control module; The intelligent edge execution module is connected to the cloud-based intelligent analysis module through the multi-communication module, and the cloud-based intelligent analysis module is connected to the control module; Intelligent edge execution module, used to realize the coordination between the host computer and the slave computer to control the switch of industrial water treatment equipment; Multiple communication modules are used to intelligently select and adjust communication paths according to the data transmission requirements and network environment of the lower computer; Smart analytics module for data analysis and predictive modeling, and providing optimization strategies for water treatment processes; The management and control module is used to respond to environmental changes and industrial water treatment status in real time, and adjust the operating parameters and operation modes of industrial water treatment equipment. At the same time, it formulates fault prevention and maintenance plans based on real-time data and long-term trends.

2. According to claim 1, a smart industrial water treatment information management and control system based on a lower computer is characterized in that: The intelligent edge execution module includes the following steps when realizing the coordination between the host computer and the slave computer to control the switch of the industrial water treatment equipment: Establish data exchange communication connection between the upper computer and the lower computer through the network; According to the control command of the host computer, operate the switch of the industrial water treatment equipment and send the control signal to the control interface of the equipment; Obtain data on water quality parameters and equipment status collected from various sensors and monitoring devices of industrial water treatment equipment.

3. According to claim 1, a smart industrial water treatment information management and control system based on a lower computer is characterized in that: The multi-communication module intelligently selects and adjusts the communication path according to the data transmission requirements and network environment of the lower computer, including: Analyze the data transmission requirements of the lower computer; Assess the current network environment; Select the best communication path based on the data transmission requirements and network environment assessment results; Dynamically adjust the communication path according to the actual data transmission process and network environment conditions.

4. According to claim 1, a smart industrial water treatment information management and control system based on a lower computer is characterized in that: The smart analysis module includes data analysis and predictive modeling functions to provide optimization strategies for the water treatment process: Acquire water quality parameter data and process the water quality parameter data; The principal component analysis method was used to analyze the characteristics of the extracted water quality parameter data; According to the characteristics of water quality parameter data, the long short-term memory network model is used to predict the parameters in the water treatment process; Detecting anomalies in water treatment processes using isolation forest models; Genetic algorithms are used to determine the optimal chemical dosage and treatment time, and the prediction results of the long-short-term memory network model are combined to provide adjustment suggestions and formulate optimization strategies.

5. According to claim 4, a smart industrial water treatment information management and control system based on a lower computer is characterized in that: The characteristics of the water quality parameter data extracted by principal component analysis include: Centralizing and standardizing water quality parameter data to ensure that variables of the water quality parameter data are on the same scale, wherein the variables include dissolved oxygen content and organic matter content; The processed water quality parameter data are used to calculate the covariance matrix between variables, and the covariance matrix is ​​subjected to eigendecomposition to obtain eigenvalues ​​and eigenvectors; Select components that meet the preset requirements according to the size of the characteristic value; Use the eigenvectors to create a transformation matrix, and use the transformation matrix to map the components that meet the preset requirements into the principal component space; Components meeting preset requirements are parsed in the principal component space, and the components meeting preset requirements are applied according to the eigenvectors.

6. According to claim 5, a smart industrial water treatment information management and control system based on a lower computer is characterized in that: The covariance matrix between variables is calculated by using the processed water quality parameter data, and the covariance matrix is ​​subjected to eigendecomposition to obtain eigenvalues ​​and eigenvectors, including: Obtain the dissolved oxygen content and organic matter content in each pair of variables in the data set of water quality parameter data, and calculate the covariance between the dissolved oxygen content and organic matter content; The covariance values ​​of all pairs of variables are constructed into a square matrix to form a covariance matrix; Perform eigendecomposition on the covariance matrix and extract eigenvalues ​​and eigenvectors; Get the degree of data change for each eigenvalue and eigenvector.

7. According to claim 6, a smart industrial water treatment information management and control system based on a lower computer is characterized in that: The covariance formula between the variable pairs is: ； In the formula, Representation variables and The covariance between Represents the dissolved oxygen content of the data set in the water quality parameter data; Indicates the organic matter content of the data set in the water quality parameter data; represents the total number of observations; Indicates dissolved oxygen content The value in the kth observation; Indicates organic matter content The value in the kth observation; and Represents the average value of different variables.

8. The intelligent industrial water treatment information management and control system based on a lower computer according to claim 7 is characterized in that: The method of predicting the parameters in the water treatment process using the long short-term memory network model according to the characteristics of the water quality parameter data includes: Constructing an architecture of a long short-term memory network model, the architecture comprising an input layer, a hidden layer of a long short-term memory network, and an output layer; The characteristics of water quality parameter data are divided into training set and test set, and the training set is used to train the long short-term memory network model; Use the test set to evaluate the model prediction performance; The trained model is used to predict future parameters in the water treatment process and output the predicted values ​​of water quality parameters in the future.

9. The intelligent industrial water treatment information management and control system based on a lower computer according to claim 8 is characterized in that: The use of the isolation forest model to detect abnormal conditions in the water treatment process includes: S1. Initialize the isolation forest model. For each isolated tree, randomly select a subset of the data set. S2, randomly select features in the subset and randomly select the split point between the maximum and minimum values ​​of the feature; S3, divide the data into two subsets according to the split point, and repeat the steps of S2 until the data is completely isolated or the preset tree depth is reached; S4. For each detected data, calculate the average path length of each detected data isolated in all isolated trees; S5. Setting a threshold value according to the calculated isolation score; S6, data points with scores below this threshold are marked as outliers; S7. Analyze the detected abnormal points and identify equipment failure problems.

10. The intelligent industrial water treatment information management and control system based on a lower computer according to claim 9 is characterized in that: The genetic algorithm is used to determine the optimal chemical dosage and treatment time, and the prediction results of the long short-term memory network model are combined to provide adjustment suggestions and formulate optimization strategies including: Determine the method of expressing the amount of chemical agent added and the treatment time; Create a fitness function that quantifies the effect of parameter combinations; Set selection, crossover, and mutation strategies, and execute cycles of selection, crossover, mutation, and fitness evaluation; Monitor the optimization progress of the genetic algorithm and the search for the optimal solution, and integrate the prediction results of the long short-term memory network model; Integrate the prediction results of future water quality parameters by the long short-term memory network model into the decision-making process of the genetic algorithm; The parameters of the genetic algorithm were adjusted according to the prediction results of the long short-term memory network model, and an optimization strategy for chemical dosage and treatment time was formulated.

Images