Electrochemical purification optimization method for data analysis of calcium hardness removal rate of circulating water

Abstract

The present application relates to the technical field of circulating water purification intelligent analysis, and particularly relates to an electrochemical purification optimization method for data analysis of calcium hardness alkalinity removal rate of circulating water. The method comprises the following steps: performing multi-source state characteristic analysis of circulating water based on electrochemical initial regulation parameters and multi-source original observation data of circulating water, to generate multi-source state characteristic distribution data of circulating water; designing electrochemical inversion regulation parameter action space data through the multi-source state characteristic distribution data of circulating water; performing multi-working-condition purification behavior prediction characteristic analysis on the electrochemical inversion regulation parameter action space data, to generate multi-working-condition purification behavior prediction characteristic data; obtaining calcium hardness alkalinity removal target demand data of circulating water; and designing electrochemical purification intelligent regulation parameters of circulating water through the calcium hardness alkalinity removal target demand data of circulating water and the multi-working-condition purification behavior prediction characteristic data. The present application realizes efficient and accurate removal of calcium hardness alkalinity of circulating water through intelligent regulation of electrochemical purification.

Description

Technical Field

[0001] This invention relates to the field of intelligent analysis technology for circulating water purification, and in particular to an electrochemical purification optimization method for analyzing data on the removal rate of calcium hardness and alkalinity in circulating water. Background Technology

[0002] The operational efficiency of a circulating water system impacts the energy consumption, equipment lifespan, and operational safety of the entire production or usage system. During long-term circulation, substances such as calcium hardness and alkalinity accumulate in the water due to evaporation and concentration. If these substances are not removed promptly and effectively, they can lead to scaling on pipe walls and equipment corrosion, reducing heat exchange efficiency, increasing energy consumption, causing pipe blockages, equipment damage, and other safety hazards, severely affecting the stable operation of the circulating water system. However, existing electrochemical purification technologies for analyzing circulating water calcium hardness and alkalinity removal rates often use fixed electrochemical control parameters, failing to dynamically adjust based on the real-time characteristics of the circulating water. This results in unstable calcium hardness and alkalinity removal rates, an inability to clearly define the impact mechanisms of different pollutants on calcium hardness and alkalinity removal, and consequently, difficulty in optimizing electrochemical control parameters and predicting purification effects under different control parameters. Consequently, the design of control parameters lacks theoretical support, hindering precise control of calcium hardness and alkalinity removal rates and the maximization of purification efficiency. Summary of the Invention

[0003] Based on this, the present invention provides an electrochemical purification optimization method for analyzing the calcium hardness and alkalinity removal rate data of circulating water, in order to solve at least one of the above-mentioned technical problems.

[0004] To achieve the above objectives, an electrochemical purification optimization method for analyzing the calcium hardness and alkalinity removal rate data of circulating water includes the following steps: Step S1: Obtain the initial electrochemical control parameters of the circulating water system; collect the original observation data of the circulating water system from multiple sources using the circulating water multi-source sensing and acquisition equipment; perform multi-source state characteristic analysis of the circulating water based on the initial electrochemical control parameters and the original observation data of the circulating water multi-source, and generate multi-source state characteristic distribution data of the circulating water. Step S2: Perform electrochemical contribution characteristic analysis on the multi-source state characteristic distribution data of circulating water pollutants to generate electrochemical contribution characteristic data of pollutants; Step S3: Based on the electrochemical contribution characteristic data of pollutants, establish the action space of electrochemical inversion regulation parameters and generate action space data of electrochemical inversion regulation parameters; Step S4: Perform multi-condition purification behavior prediction feature analysis on the spatial data of the effect of electrochemical inversion control parameters to generate multi-condition purification behavior prediction feature data. Step S5: Obtain target demand data for calcium hardness and alkalinity removal in circulating water; design intelligent control parameters for electrochemical purification of circulating water based on the target demand data for calcium hardness and alkalinity removal in circulating water and the predictive feature data of purification behavior under multiple operating conditions.

[0005] Furthermore, step S1 includes the following steps: Step S11: Obtain the initial electrochemical control parameters of the circulating water system; Step S12: Use the circulating water multi-source sensing and acquisition equipment to perform multi-source collaborative sensing and acquisition of circulating water in the circulating water system, and generate raw observation data of circulating water multi-source; Step S13: Analyze the distribution of circulating water attributes based on the original observation data of multiple sources of circulating water to generate multi-source distribution data of circulating water; Step S14: Analyze the electrochemical behavior characteristics of circulating water based on the multi-source distribution data of circulating water according to the initial electrochemical control parameters, and generate electrochemical behavior characteristic data of circulating water. Step S15: Analyze the multi-source state characteristics of circulating water using multi-source distribution data and electrochemical behavior characteristic data of circulating water, and generate multi-source state characteristic distribution data of circulating water.

[0006] Furthermore, the circulating water multi-source sensing and acquisition device mentioned in step S12 includes a circulating water electrochemical sensor and a water quality multi-parameter monitoring device.

[0007] Furthermore, step S13 includes the following steps: Step S131: Perform multi-source attribute coding on the raw observation data of circulating water to generate multi-source attribute coded data of circulating water; Step S132: Analyze the distribution characteristics of sensing nodes based on the original multi-source observation data of circulating water to generate circulating water observation sensing distribution characteristic data; Step S133: Analyze the distribution of circulating water attributes by using circulating water observation and sensing distribution characteristic data to generate circulating water multi-source attribute coding data.

[0008] Furthermore, step S2 includes the following steps: Step S21: Based on the multi-source state characteristic distribution data of circulating water, perform multi-target pollutant feature identification processing to generate multi-target pollutant feature data; Step S22: Design the electrochemical reaction pathway diagram structure of multi-target pollutants based on the feature data of multi-target pollutants, and generate pollutant reaction pathway diagram structure data; Step S23: Perform coupling and interaction relationship feature analysis on the multi-target pollutant feature data to generate pollutant coupling and interaction relationship feature data; Step S24: Analyze the electrochemical reaction coupling relationship characteristics of pollutants using the pollutant reaction path diagram structure data, and generate pollutant electrochemical reaction coupling relationship characteristic data. Step S25: Based on the characteristic data of the electrochemical reaction coupling relationship of pollutants and the structural data of the reaction path diagram of pollutants, decouple the electrochemical reactions of pollutants to generate decoupled data of electrochemical reactions of pollutants. Step S26: Analyze the electrochemical contribution characteristics of pollutants using the electrochemical reaction coupling relationship characteristic data and the electrochemical reaction decoupling data of pollutants, and generate the electrochemical contribution characteristic data of pollutants.

[0009] Furthermore, the multi-target pollutant characteristic data in step S21 includes calcium hardness alkalinity pollutant characteristic data, turbidity factor characteristic data, and residual chlorine factor characteristic data.

[0010] Furthermore, step S22 includes the following steps: Step S221: Perform electrochemical reaction node feature analysis on the multi-target pollutant feature data to generate pollutant electrochemical reaction node feature data; Step S222: Perform time-intensity relationship analysis on the electrochemical reaction nodes of pollutants based on the multi-target pollutant characteristic data, and generate time-intensity relationship data of pollutant reaction nodes; Step S223: Design the directed weighted electrochemical reaction path diagram structure of pollutants based on the time-intensity relationship data of the pollutant reaction nodes, and generate pollutant reaction path diagram structure data.

[0011] Furthermore, step S3 includes the following steps: Step S31: Perform electrochemical characterization analysis on the electrochemical contribution characteristic data of pollutants to generate electrochemical characterization data; Step S32: Construct the electrochemical regulation parameter space based on the electrochemical interaction state characterization data to generate electrochemical regulation parameter space data; Step S33: Based on the electrochemical action state characterization data and the spatial data of electrochemical regulation parameters, perform the mapping relationship analysis between electrochemical action state and action to generate electrochemical action state-action mapping relationship data; Step S34: Perform response characteristic analysis on the electrochemical action state-action mapping relationship data to generate electrochemical action state-action response characteristic data; Step S35: Perform iterative inversion processing of electrochemical action-driven regulation parameters using electrochemical action state-action response characteristic data to generate electrochemical action-regulation parameter inversion data; Step S36: Based on the electrochemical action-regulation parameter inversion data, establish the action space of the electrochemical inversion regulation parameters and generate the action space data of the electrochemical inversion regulation parameters.

[0012] Furthermore, step S4 includes the following steps: Step S41: Based on the spatial data of the effect of the electrochemical inversion control parameters, perform simulation processing of the circulating water effect of the electrochemical inversion control parameters to generate simulation data of the circulating water effect of the inversion control parameters; Step S42: Perform electrochemical purification-driven stage constraint embedding processing on the simulation data of the inversion control parameter circulating water effect to generate constrained inversion control parameter circulating water effect simulation data; Step S43: Based on the spatial data of the effects of the electrochemical inversion control parameters, perform temporal perturbation scenario analysis of the inversion control parameters to generate temporal perturbation scenario data of the inversion control parameters; Step S44: Perform circulating water purification evolution processing of the inverted control parameters using the time-series disturbance scenario data of the inverted control parameters and the simulation data of the circulating water effect of the constrained inverted control parameters, and generate circulating water purification evolution data of the inverted control parameters. Step S45: Perform multi-condition purification behavior prediction feature analysis based on the inversion control parameters and circulating water purification evolution data to generate multi-condition purification behavior prediction feature data.

[0013] Furthermore, step S5 includes the following steps: Step S51: Obtain target data for calcium hardness and alkalinity removal in circulating water; Step S52: Perform multi-objective optimization analysis on the target requirement data for calcium hardness and alkalinity removal in circulating water to generate multi-objective optimization analysis data for electrochemical purification of circulating water; Step S53: Perform global search processing of circulating water electrochemical purification parameters based on the multi-objective optimization analysis data and multi-condition purification behavior prediction feature data of circulating water electrochemical purification, and generate global search data of circulating water electrochemical purification parameters. Step S54: Design intelligent control parameters for circulating water electrochemical purification based on global search data of circulating water electrochemical purification parameters.

[0014] The beneficial effects of this application are as follows: This invention achieves a comprehensive and accurate characterization of the circulating water state by systematically acquiring initial electrochemical control parameters, collecting multi-source raw observation data of circulating water, and combining the two to conduct multi-source state characteristic analysis. It employs a multi-source sensing acquisition device composed of circulating water electrochemical sensors and water quality multi-parameter monitoring equipment, overcoming the limitation of limited data dimensions of single sensing devices, and can comprehensively capture raw data related to water quality and electrochemistry of circulating water. Through sub-steps such as multi-source attribute encoding and sensing node distribution characteristic analysis, the raw data is deeply processed, effectively mining the multi-source distribution characteristics and electrochemical behavior characteristics of circulating water. The generated circulating water multi-source state characteristic distribution data provides comprehensive and reliable basic data support for subsequent pollutant analysis and control parameter optimization, avoiding subsequent analysis biases caused by incomplete data, and simultaneously realizing dynamic perception and characteristic quantification of the circulating water state. For the circulating water multi-source state characteristic distribution data, in-depth analysis of the electrochemical contribution characteristics of pollutants is conducted, effectively solving the problem of not being able to accurately distinguish the degree of influence of each pollutant on the electrochemical purification process. This study identifies key pollutants such as calcium hardness / alkalinity, turbidity, and residual chlorine through multi-target pollutant feature identification. Then, through electrochemical reaction pathway design, coupling interaction analysis, and decoupling processing, it clearly reveals the electrochemical reaction mechanisms, coupling relationships, and individual effects of each pollutant. The generated electrochemical contribution characteristic data of pollutants can accurately quantify the electrochemical contribution of different pollutants to the removal of calcium hardness / alkalinity in circulating water, improving the targeting and efficiency of calcium hardness / alkalinity removal. Based on the pollutant electrochemical contribution characteristic data, an electrochemical inversion control parameter action space is constructed, realizing the scientific inversion and spatial quantification of electrochemical control parameters. This provides a reasonable parameter range and theoretical support for subsequent multi-condition simulation and parameter optimization. This method, through sub-steps such as electrochemical state characterization, construction of the control parameter space, state-action mapping analysis, and iterative inversion, correlates the electrochemical contribution characteristics of pollutants with electrochemical control parameters. It accurately inverts the optimal control parameter range under different action states, generating electrochemical inversion control parameter action space data. This addresses the limitation of fixed control parameters failing to adapt to dynamic changes in water quality, clarifies the action boundaries and influence patterns of control parameters, and effectively improves the scientific rigor and rationality of electrochemical control parameter optimization. Furthermore, it conducts simulation and multi-condition purification behavior prediction feature analysis on the electrochemical inversion control parameter action space data, solving the technical problems of being unable to predict purification effects under different control parameters in advance and difficulty in adapting to complex operating conditions.Through sub-steps such as circulating water action simulation, stage constraint embedding, temporal disturbance scenario analysis, and purification evolution processing, this system can not only accurately simulate the effects of different electrochemical inversion control parameters on circulating water, but also fully consider the impact of complex operating conditions such as temporal disturbances on the purification effect. By embedding electrochemical purification stage constraints, it ensures the scientific rigor and practicality of the simulation. The generated multi-condition purification behavior prediction feature data can comprehensively present the circulating water purification behavior and calcium hardness / alkalinity removal effect under different control parameters and operating conditions. Guided by the target demand for calcium hardness / alkalinity removal in circulating water, and combined with multi-condition purification behavior prediction feature data, intelligent control parameters are designed to achieve targeted, intelligent, and precise electrochemical purification control. Through multi-objective optimization analysis and global search of control parameters, the target requirements for calcium hardness and alkalinity removal are deeply integrated with multi-condition prediction data. This allows for precise analysis of optimization directions under different target requirements. The optimal control parameters are selected through global search. The designed intelligent control parameters for circulating water electrochemical purification can accurately match the calcium hardness and alkalinity removal target, effectively solving the problems of disconnect between control parameters and removal requirements and insufficient control precision in existing technologies. At the same time, it realizes intelligent design of control parameters without excessive manual intervention. It can ensure that the calcium hardness and alkalinity removal rate reaches the expected target while taking into account purification efficiency and energy consumption control, significantly improving the operating performance and practicality of the circulating water electrochemical purification system.

[0015] Therefore, the electrochemical purification method for analyzing the calcium hardness and alkalinity removal rate of circulating water in this invention collects the characteristics of circulating water in different modes using a multi-source sensing device. Then, it dynamically adjusts the electrochemical control parameters based on the real-time state characteristics of the circulating water to ensure the calcium hardness and alkalinity removal rate remains stable. Precise analysis of the electrochemical contribution characteristics of pollutants clarifies the influence mechanism of different pollutants on calcium hardness and alkalinity removal, enabling targeted optimization of electrochemical control parameters. Simulation prediction of purification trends under different control parameters provides theoretical support for the design of control parameters, achieving precise control of the calcium hardness and alkalinity removal rate and maximizing purification efficiency. Attached Figure Description

[0016] Figure 1 This is a schematic diagram of the steps in an electrochemical purification optimization method for analyzing the calcium hardness and alkalinity removal rate of circulating water according to the present invention. Figure 2 for Figure 1 A detailed flowchart illustrating the implementation steps of step S4. The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0017] The technical method of the present invention will now be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without inventive effort are within the scope of protection of the present invention.

[0018] Furthermore, the accompanying drawings are merely illustrative of the invention and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and therefore repeated descriptions of them will be omitted. Some block diagrams shown in the drawings are functional entities and do not necessarily correspond to physically or logically independent entities. Functional entities may be implemented in software, or in one or more hardware modules or integrated circuits, or in different network and / or processor methods and / or microcontroller methods. The term "and / or" as used herein includes any and all combinations of one or more of the associated items listed.

[0019] To achieve the above objectives, please refer to Figures 1 to 2 This invention provides an electrochemical purification optimization method for analyzing the calcium hardness and alkalinity removal rate data of circulating water. In the embodiments of this invention, please refer to... Figure 1 The diagram shows a flowchart illustrating the steps of an electrochemical purification optimization method for analyzing the calcium hardness and alkalinity removal rate of circulating water according to the present invention. The electrochemical purification optimization method for analyzing the calcium hardness and alkalinity removal rate of circulating water includes the following steps: Step S1: Obtain the initial electrochemical control parameters of the circulating water system; collect the original observation data of the circulating water system from multiple sources using the circulating water multi-source sensing and acquisition equipment; perform multi-source state characteristic analysis of the circulating water based on the initial electrochemical control parameters and the original observation data of the circulating water multi-source, and generate multi-source state characteristic distribution data of the circulating water. In this embodiment of the invention, initial electrochemical control parameters are acquired, focusing on the core control dimensions affecting the electrochemical removal efficiency of calcium hardness and alkalinity in circulating water. The core types of initial control parameters are identified, covering key parameters such as voltage, current, electrode spacing, and electrolysis time during the electrolysis process. All initial control parameters are determined based on the normal operating conditions of the circulating water system and the basic requirements for calcium hardness and alkalinity removal. The value ranges of each parameter are clearly defined, forming a complete set of initial electrochemical control parameters, which serves as the benchmark for subsequent electrochemical behavior analysis. Subsequently, multi-source raw observation data of the circulating water are collected using a multi-source sensing and acquisition device. The acquisition process achieves multi-dimensional collaborative sensing, covering circulating water quality parameters and electrochemically related signals. The acquisition range covers key areas such as the inlet, outlet, and middle of the circulating pipeline of the circulating water system. The acquisition process is carried out continuously at fixed intervals to ensure that the acquired data can comprehensively capture the state changes of different areas and time periods of the circulating water system. After the acquisition is completed, a set of various raw observation data is formed, which can be used for subsequent analysis without additional preprocessing. Finally, based on the acquired initial electrochemical control parameters and original observation data of circulating water from multiple sources, a multi-source state characteristic analysis of circulating water was conducted. First, the attributes of the original observation data from multiple sources were sorted and classified to clarify the state dimensions of circulating water corresponding to each type of data. Then, combined with the initial electrochemical control parameters, the changes in the electrochemical behavior of circulating water under different initial control parameters were analyzed to explore the intrinsic relationship between circulating water quality parameters and electrochemical behavior. At the same time, the state distribution patterns of circulating water in different regions and time periods were extracted. The water quality characteristics, electrochemical behavior characteristics and distribution patterns were integrated to generate multi-source state characteristic distribution data of circulating water.

[0020] Step S2: Perform electrochemical contribution characteristic analysis on the multi-source state characteristic distribution data of circulating water pollutants to generate electrochemical contribution characteristic data of pollutants; In this embodiment of the invention, in-depth analysis of the multi-source state characteristic distribution data of circulating water is performed. Combined with the core requirement of calcium hardness and alkalinity removal in circulating water, key pollutants directly affecting the electrochemical purification effect and calcium hardness and alkalinity removal rate are identified. The core attributes and existing forms of various pollutants are clarified, and core pollutants related to calcium hardness and alkalinity are distinguished from other auxiliary influencing pollutants, forming a complete set of multi-target pollutants to ensure that subsequent analysis focuses on the core influencing factors. Subsequently, for the identified multi-target pollutants, electrochemical action pathway analysis is conducted to clarify the reaction process, core reaction nodes, and reaction types of various pollutants in the electrochemical purification process. The interaction relationships between different pollutants are analyzed, the role of various pollutants in the calcium hardness and alkalinity removal process is clarified, and the dominant and auxiliary pollutants are distinguished. Based on this, a quantitative analysis of the electrochemical contribution characteristics of pollutants was conducted. By analyzing the participation degree, reaction intensity, and timing of various pollutants in the electrochemical reaction, and combining the state change information in the multi-source state characteristic distribution data of circulating water, the electrochemical contribution of various pollutants to calcium hardness and alkalinity removal was quantified. The contribution priority and influence mechanism of different pollutants were clarified. At the same time, the synergistic effects and constraints among various pollutants were analyzed. By integrating the pollutant identification results, electrochemical action pathways, contribution quantification data, and interaction relationships, electrochemical contribution characteristic data of pollutants was generated. This data clearly defines the electrochemical contribution characteristics of various pollutants.

[0021] Step S3: Based on the electrochemical contribution characteristic data of pollutants, establish the action space of electrochemical inversion regulation parameters and generate action space data of electrochemical inversion regulation parameters; In this embodiment of the invention, electrochemical contribution characteristic data of pollutants are characterized and analyzed for electrochemical action state. The electrochemical contribution characteristics of pollutants are transformed into quantifiable electrochemical action state indicators, covering core dimensions such as electrochemical action intensity, efficiency, and stability. This clarifies the overall level of the current electrochemical action state and the existing optimization space, providing a state benchmark for the construction of the regulation parameter space. Subsequently, based on the characterized electrochemical action state data, the electrochemical regulation parameter space is constructed. Taking the core regulation parameters affecting the electrochemical action state and the contribution effect of pollutants as the core, and combining the contribution patterns of various factors in the pollutant electrochemical contribution characteristic data, the value range of each core regulation parameter is defined to ensure that the parameter range can cover all possible situations for achieving efficient removal of calcium hardness and alkalinity. A grid partitioning method is used to refine the value range of each regulation parameter, forming a large number of independent regulation parameter combinations. Electrochemical action state prediction is performed on each parameter combination, and effective parameter combinations that can maintain or improve the electrochemical action state and adapt to the contribution characteristics of pollutants are selected. Finally, the distribution patterns and interactions of each control parameter in the effective parameter combination were analyzed to clarify the correlation characteristics between each parameter. The effective parameter combination, the value range of each parameter, the distribution patterns and interactions were integrated to generate the spatial data of the effect of electrochemical inversion control parameters. This data clearly defines the range and combination of control parameters that are adapted to the electrochemical contribution characteristics of pollutants and can achieve efficient removal of calcium hard alkalinity.

[0022] Step S4: Perform multi-condition purification behavior prediction feature analysis on the spatial data of the effect of electrochemical inversion control parameters to generate multi-condition purification behavior prediction feature data. In this embodiment of the invention, based on the spatial data of the electrochemical inversion control parameters, a simulation of the effect of the electrochemical inversion control parameters on circulating water is conducted. Using the actual operating conditions of the circulating water system as a benchmark, a simulation duration and time interval consistent with actual operation are set. Each combination of control parameters within the spatial data is used as input to simulate the electrochemical purification process of different parameter combinations in the circulating water system. The dynamic changes in the calcium hardness / alkalinity, content of various pollutants, and electrochemical state of the circulating water are recorded in real time during the simulation, forming a complete simulation dataset. Subsequently, stage constraint embedding processing driven by electrochemical purification is performed. Combining the actual reaction stages of the electrochemical purification process, the process is divided into a start-up stage, a stabilization stage, and a termination stage. Clear constraints are set for each stage, and the simulation data is checked to ensure that it meets the constraints of each stage. Data that does not meet the constraints is corrected to ensure that the simulation data closely matches the actual electrochemical purification process and improve the accuracy of the simulation data. Based on this, a temporal disturbance scenario analysis of the inversion control parameters is conducted to simulate various disturbances that may occur in the control parameters during actual operation. Different disturbance levels are classified, and the temporal fluctuation patterns of the parameters under each disturbance scenario and their predictive impact on the purification effect are clarified. Subsequently, combining time-series perturbation scenario data and corrected simulation data, the evolution of circulating water purification was carried out. The purification evolution process under different parameter combinations under various perturbation scenarios was simulated, recording the impact of perturbations on the purification effect and the parameter adjustment logic. Finally, multi-condition purification behavior prediction feature analysis was conducted. Combining all simulation and evolution data, different operating condition types were classified, and the core features of circulating water purification behavior and calcium hardness / alkalinity removal effects under each operating condition were extracted. The optimal operating condition and corresponding parameter combination were selected, and the distribution pattern and characteristic correlation of the optimal operating condition were analyzed to generate multi-condition purification behavior prediction feature data.

[0023] Step S5: Obtain target demand data for calcium hardness and alkalinity removal in circulating water; design intelligent control parameters for electrochemical purification of circulating water based on the target demand data for calcium hardness and alkalinity removal in circulating water and the predictive feature data of purification behavior under multiple operating conditions.

[0024] In this embodiment of the invention, target requirement data for calcium hardness and alkalinity removal in circulating water are acquired. Focusing on the core objective of calcium hardness and alkalinity removal in circulating water, and considering the requirements for subsequent reuse and discharge, clear quantitative target indicators are set, covering core dimensions such as calcium hardness and alkalinity removal rate, removal speed, energy consumption control, and operational stability. Specific thresholds for each target indicator are defined, and the priority and weight allocation of each target are determined to ensure that the target requirement data clearly guides the subsequent parameter design direction, achieving a multi-objective balance between removal effect, energy consumption, and stability. Subsequently, combining the acquired target requirement data for calcium hardness and alkalinity removal in circulating water with the multi-condition purification behavior prediction feature data generated in step S4, multi-objective optimization analysis is conducted. The abstract target requirements are transformed into quantifiable and executable optimization indicators, clarifying the constraints and balance logic between each objective, establishing a multi-objective optimization analysis system, and determining the core optimization direction, providing a clear optimization basis for subsequent parameter searches. Based on this, a global search and processing of circulating water electrochemical purification parameters was conducted. Using the results of multi-objective optimization analysis as the search criterion, and all operating conditions and corresponding parameter combinations in the multi-condition purification behavior prediction feature data as the search scope, a global traversal search method was adopted to verify whether each operating condition and parameter combination met the target requirements and optimization requirements. The optimal parameter combination that could balance multiple objectives and had practical application feasibility was selected, and the comprehensive performance ranking of each optimal parameter combination was determined. Finally, based on the optimal parameter combination found through the global search, intelligent control parameters for circulating water electrochemical purification were designed. The parameter combination with the best comprehensive performance was prioritized as the core control parameter. Combining the disturbance scenarios and purification evolution laws in the multi-condition prediction feature data, corresponding disturbance adaptation rules were matched to the core control parameter, parameter adjustment trigger conditions were set, and the operating logic of intelligent control was clarified. This enabled the control parameters to automatically adjust according to the actual state of the circulating water and operating condition disturbances. Integrating the core control parameters, adaptation rules, trigger conditions, and operating logic, intelligent control parameters for circulating water electrochemical purification were generated, completing the entire electrochemical purification optimization process and ensuring efficient, energy-saving, and stable removal of calcium hardness and alkalinity from the circulating water.

[0025] Furthermore, step S1 includes the following steps: Step S11: Obtain the initial electrochemical control parameters of the circulating water system; In this embodiment of the invention, to meet the electrochemical purification requirements for removing calcium hardness and alkalinity from circulating water, initial electrochemical control parameters of the circulating water system are obtained. These control parameters are set around the core factors affecting calcium hardness and alkalinity removal during the electrochemical purification process, specifically including four core parameters: electrolysis voltage, electrolysis current, electrode spacing, and electrolysis time. The electrolysis voltage is set to 3V-8V, the electrolysis current to 1A-5A, the electrode spacing to 5cm-15cm, and the electrolysis time to 30min-120min. These initial control parameters are determined based on the normal operating conditions of the circulating water system. Combining the basic requirements for calcium hardness and alkalinity removal, parameter ranges suitable for the initial water quality of most industrial circulating water are selected as the initial benchmark for subsequent electrochemical behavior characteristic analysis and parameter optimization, ensuring that the initial control parameters can support the accurate analysis of the multi-source state characteristics of circulating water.

[0026] Step S12: Use the circulating water multi-source sensing and acquisition equipment to perform multi-source collaborative sensing and acquisition of circulating water in the circulating water system, and generate raw observation data of circulating water multi-source; In this embodiment of the invention, a multi-source sensing and acquisition device for circulating water, consisting of a circulating water electrochemical sensor and a water quality multi-parameter monitoring device, is used to conduct multi-source collaborative sensing and acquisition of the circulating water system. The acquisition process is carried out synchronously without any sequential order. The circulating water electrochemical sensor focuses on acquiring electrochemical-related signals of the circulating water, including electrode potential, conductivity, and electrolysis reaction rate. The water quality multi-parameter monitoring device focuses on acquiring water quality parameters related to calcium hardness and alkalinity removal, including calcium hardness value, alkalinity value, turbidity, and residual chlorine content. The acquisition process is carried out continuously according to a fixed cycle, with the acquisition cycle set at 5 minutes / time. The acquisition range covers three key locations of the circulating water system: the inlet, outlet, and the middle of the circulating pipeline. This ensures that the acquired multi-source raw observation data of the circulating water can comprehensively reflect the water quality and electrochemical state of different areas of the circulating water system. After the acquisition is completed, multi-source raw observation data of the circulating water containing all the above parameters is directly generated.

[0027] Step S13: Analyze the distribution of circulating water attributes based on the original observation data of multiple sources of circulating water to generate multi-source distribution data of circulating water; In this embodiment of the invention, the raw observation data of circulating water from multiple sources are processed by multi-source attribute encoding. A binary encoding method is used, assigning a unique binary code to each of the seven parameters: calcium hardness, alkalinity, turbidity, residual chlorine content, electrode potential, conductivity, and electrolysis reaction rate. The code length is set to 8 bits. This encoding transforms different types of raw observation data into coded data in a unified format, generating multi-source attribute coded data for circulating water. Subsequently, based on the raw observation data of circulating water from multiple sources, the distribution characteristics of sensing nodes are analyzed. Taking three acquisition locations as core sensing nodes, the numerical differences of each parameter at each sensing node are calculated. A difference threshold of 10% was set to filter out parameters and corresponding sensing nodes whose numerical differences exceeded the threshold, generating circulating water observation and sensing distribution characteristic data. Finally, based on the circulating water observation and sensing distribution characteristic data, attribute distribution cluster analysis was performed on the circulating water multi-source attribute coding data. The K-means clustering algorithm was used, with a set number of three clusters, corresponding to the attribute distribution of the inlet, outlet, and middle of the circulating pipeline, respectively. Through cluster analysis, the attribute differences and overall distribution patterns of circulating water in different regions were clarified, generating circulating water multi-source distribution data. The data includes the parameter mean, distribution range, and difference characteristics of each cluster region.

[0028] Step S14: Analyze the electrochemical behavior characteristics of circulating water based on the multi-source distribution data of circulating water according to the initial electrochemical control parameters, and generate electrochemical behavior characteristic data of circulating water. In this embodiment of the invention, the electrochemical behavior characteristics of circulating water are analyzed based on the initial electrochemical control parameters of the multi-source distribution data. The analysis process uses electrolysis voltage, electrolysis current, electrode spacing, and electrolysis time as variables, respectively, to perform correlation analysis on conductivity, electrolysis reaction rate, calcium hardness value, and alkalinity value in the multi-source distribution data of circulating water. A correlation coefficient threshold of 0.8 is set for the correlation analysis, and circulating water attribute parameters with strong correlation to the initial electrochemical control parameters are screened out. Subsequently, based on the correlation analysis results, the electrochemical behavior indicators of circulating water under different initial electrochemical control parameters are calculated, including electrolysis reaction efficiency and ion migration rate. The electrolysis reaction efficiency is calculated by dividing the product of electrolysis current and electrolysis time by the electrode spacing, and the ion migration rate is calculated by the ratio of conductivity to electrolysis voltage. Simultaneously, the influence trends of different initial control parameter combinations on calcium hardness and alkalinity values ​​are analyzed, clarifying the decreasing patterns of calcium hardness and alkalinity values ​​when the electrolysis voltage and electrolysis current increase. The above analysis results are integrated to generate circulating water electrochemical behavior characteristic data, which includes electrochemical behavior indicator values, parameter correlations, and influence trends.

[0029] Step S15: Analyze the multi-source state characteristics of circulating water using multi-source distribution data and electrochemical behavior characteristic data of circulating water, and generate multi-source state characteristic distribution data of circulating water.

[0030] In this embodiment of the invention, multi-source distribution data and electrochemical behavior characteristic data of circulating water are used to analyze the multi-source state characteristics of circulating water. The mean values, distribution ranges, and differences of parameters in each region are extracted from the multi-source distribution data. Simultaneously, the electrochemical behavior index values, parameter correlations, and influence trends are extracted from the electrochemical behavior characteristic data. The two types of data are then fused using a weighted summation method. The weight of the multi-source distribution data is set to 0.4, and the weight of the electrochemical behavior characteristic data is set to 0.6, ensuring that the fused data reflects both the distribution of circulating water quality attributes and electrochemical behavior. Features were then extracted from the fused data, including calcium hardness distribution, alkalinity distribution, electrochemical reaction efficiency, and ion migration. Each feature was quantified: calcium hardness distribution was represented by the mean and minimum difference of calcium hardness in each region; alkalinity distribution was represented by the mean and variation of alkalinity in each region; electrochemical reaction efficiency was represented by the average electrolysis efficiency and fluctuation; and ion migration was represented by the average ion migration rate. All quantified features were integrated to generate multi-source state characteristic distribution data of circulating water, which comprehensively reflects the water quality and electrochemical behavior of circulating water.

[0031] Furthermore, the circulating water multi-source sensing and acquisition device mentioned in step S12 includes a circulating water electrochemical sensor and a water quality multi-parameter monitoring device.

[0032] Furthermore, step S13 includes the following steps: Step S131: Perform multi-source attribute coding on the raw observation data of circulating water to generate multi-source attribute coded data of circulating water; In this embodiment of the invention, multi-source raw observation data of circulating water are processed using multi-source attribute encoding. The multi-source raw observation data includes seven core parameters related to calcium hardness and alkalinity removal and electrochemical purification: calcium hardness value, alkalinity value, turbidity, residual chlorine content, electrode potential, conductivity, and electrolysis reaction rate. The encoding process uses a binary encoding method, with each parameter corresponding to a unique 8-bit binary code. The encoding rule is set so that the larger the parameter value, the larger the corresponding decimal value. The calcium hardness value corresponds to a code range of 00000001- 00111100, the corresponding coding ranges for alkalinity value are 01000000-01111111, turbidity is 10000000-10111100, residual chlorine content is 11000000-11011111, electrode potential is 11100000-11101111, conductivity is 11110000-11110111, and electrolysis reaction rate is 11111000-11111111. During the encoding process, the original values ​​of each parameter are first converted into decimal values ​​within the corresponding range, and then the decimal values ​​are converted into 8-bit binary codes. This encoding method transforms raw observation data of different types and magnitudes into coded data in a unified format, eliminating the magnitude differences between different parameters, ensuring the accuracy of subsequent attribute distribution analysis, and generating multi-source attribute coding data of circulating water containing the binary codes of all parameters. This provides a unified data foundation for subsequent analysis of the distribution characteristics of sensing nodes and clustering analysis of attribute distribution.

[0033] Step S132: Analyze the distribution characteristics of sensing nodes based on the original multi-source observation data of circulating water to generate circulating water observation sensing distribution characteristic data; In this embodiment of the invention, the distribution characteristics of sensing nodes are analyzed based on the multi-source raw observation data of circulating water. The sensing nodes are centered on the three collection locations set in step S12: the inlet, outlet, and middle of the circulating pipe of the circulating water system. Each sensing node corresponds to a complete set of multi-source raw observation data of circulating water. The analysis process first calculates the values ​​of seven core parameters at each sensing node, and then calculates the difference in the value of the same parameter between any two sensing nodes. The calculation method is to subtract the values ​​of the same parameter of the two nodes and take the absolute value. The threshold for the difference in the value is set to 10%. That is, when the ratio of the difference in the value of the same parameter between two nodes to the parameter value of the node with the larger value exceeds 10%, it is determined that there is a significant difference in the parameter between the two nodes. The numerical differences of each parameter between the inlet and outlet, between the inlet and the middle of the circulation pipe, and between the outlet and the middle of the circulation pipe are calculated separately. All parameters with a numerical difference exceeding 10% and their corresponding two sensing nodes are screened out. The types and number of parameters with significant differences at each sensing node are counted to clarify the distribution pattern of parameter differences between different sensing nodes. Circulating water observation sensing distribution characteristic data are generated. The data includes the parameter values ​​of each sensing node, the parameter differences between nodes, the parameters with significant differences, and the corresponding node information. This provides a basis for node differences in subsequent circulating water attribute distribution analysis, ensuring that the attribute distribution analysis can accurately reflect the attribute differences of circulating water in different areas.

[0034] Step S133: Analyze the distribution of circulating water attributes by using circulating water observation and sensing distribution characteristic data to generate circulating water multi-source attribute coding data.

[0035] In this embodiment of the invention, circulating water attribute distribution analysis is performed on the multi-source attribute coding data of circulating water through circulating water observation and sensing distribution characteristic data. Based on the difference information of sensing nodes in the circulating water observation and sensing distribution characteristic data, the K-means clustering algorithm is used to cluster the multi-source attribute coding data of circulating water. The number of clusters is set to 3, corresponding to the three sensing node regions of the inlet, outlet and middle of the circulating pipeline, respectively. During the clustering process, the decimal value corresponding to the binary code of each parameter is used as the clustering basis. The number of clustering iterations is set to 50, and the clustering error threshold is 0.05. When the number of iterations reaches 50 or the clustering error is less than 0.05, the clustering operation is stopped. After clustering, the mean decimal values ​​of the codes for the seven core parameters in each cluster region are calculated. The decimal mean is then converted into the corresponding original parameter values ​​to determine the distribution range of each parameter in each cluster region. The difference between the maximum and minimum values ​​of each parameter in each cluster region is calculated to clarify the fluctuation of parameters in each region. At the same time, the node difference information in the circulating water observation and sensing distribution characteristic data is combined to integrate the clustering results and node difference characteristics to generate multi-source distribution data of circulating water. The data includes sensing nodes corresponding to the three cluster regions, the mean, distribution range and fluctuation difference of the seven parameters in each region, clearly presenting the distribution patterns of water quality and electrochemical properties in different regions of the circulating water system.

[0036] Furthermore, step S2 includes the following steps: Step S21: Based on the multi-source state characteristic distribution data of circulating water, perform multi-target pollutant feature identification processing to generate multi-target pollutant feature data; In this embodiment of the invention, multi-target pollutant feature identification processing is performed based on the multi-source state characteristic distribution data of circulating water. The multi-source state characteristic distribution data of circulating water includes calcium hardness distribution features, alkalinity distribution features, electrochemical reaction efficiency features, ion migration features, and parameter distribution patterns in each region. The feature identification process adopts the feature threshold screening method, setting the feature identification threshold corresponding to each pollutant. The feature threshold corresponding to the calcium hardness and alkalinity pollutant is set as the average calcium hardness ≥150mg / L and the average alkalinity ≥120mg / L. The feature threshold corresponding to the turbidity factor is set as the average turbidity ≥5NTU. The feature threshold corresponding to the residual chlorine factor is set as the average residual chlorine content ≥0.3mg / L. During the identification process, all feature parameters meeting the aforementioned threshold requirements were extracted from the multi-source state characteristic distribution data of circulating water. The characteristics of calcium hardness and alkalinity pollutants were quantitatively characterized, recording the distribution range, fluctuation differences, and correlation with electrochemical reaction efficiency of calcium hardness and alkalinity. Turbidity was characterized, recording regional distribution differences and their impact on ion migration rates. Residual chlorine was characterized, recording the changing trends of residual chlorine content and its correlation with electrochemical reaction rates. Through the above identification and processing, the specific characteristics of the three core pollutants were clarified, generating multi-target pollutant feature data. This data only includes feature data of calcium hardness and alkalinity pollutants, turbidity, and residual chlorine.

[0037] Step S22: Design the electrochemical reaction pathway diagram structure of multi-target pollutants based on the feature data of multi-target pollutants, and generate pollutant reaction pathway diagram structure data; In this embodiment of the invention, an electrochemical reaction path diagram structure for multiple target pollutants is designed based on the feature data of multiple target pollutants. The electrochemical reaction node features of the multiple target pollutants are analyzed, and electrochemical reaction nodes corresponding to three types of pollutants are extracted. Specifically, the calcium hardness / alkalinity pollutant corresponds to two core reaction nodes: a calcium ion electrolytic precipitation node and a bicarbonate ion electrolytic decomposition node; the turbidity factor corresponds to one core reaction node: a suspended matter electrolytic coagulation node; and the residual chlorine factor corresponds to one core reaction node: a chloride ion electrolytic oxidation node. Each reaction node corresponds to a unique node identifier, which uses a 4-digit decimal code: 0001 for the calcium ion electrolytic precipitation node, 0002 for the bicarbonate ion electrolytic decomposition node, 0003 for the suspended matter electrolytic coagulation node, and 0004 for the chloride ion electrolytic oxidation node. Simultaneously, the reaction intensity of each reaction node is calculated by multiplying the characteristic value of the corresponding pollutant by the electrochemical reaction efficiency. Subsequently, based on the characteristic data of multiple pollutants, the time-intensity relationship of each pollutant's electrochemical reaction node was analyzed. The reaction time interval was set to 10 min, and the reaction intensity of each reaction node within each time interval was recorded to clarify the reaction start-up sequence and intensity change law of each node. Among them, the calcium ion electrolytic precipitation node and the bicarbonate ion electrolytic decomposition node started simultaneously, the suspended matter electrolytic coagulation node started 5 min after the above two nodes started, and the chloride ion electrolytic oxidation node started 3 min after the suspended matter electrolytic coagulation node started. Finally, based on the time-intensity relationship data of pollutant reaction nodes, a directed weighted electrochemical reaction path diagram structure was designed. Directed line segments connect each reaction node in the path diagram, with the line segment direction corresponding to the reaction direction and the line segment weight corresponding to the reaction correlation strength between two nodes. The correlation strength was set to 0.1-1.0. The correlation strength between the calcium ion electrolytic precipitation node and the bicarbonate ion electrolytic decomposition node was set to 0.9, the correlation strength between the suspended solids electrolytic coagulation node and the calcium ion electrolytic precipitation node was set to 0.7, and the correlation strength between the chloride ion electrolytic oxidation node and the bicarbonate ion electrolytic decomposition node was set to 0.5. This generated pollutant reaction path diagram structure data containing node identifiers, reaction time sequence, intensity data, and directed weighted paths.

[0038] Step S23: Perform coupling and interaction relationship feature analysis on the multi-target pollutant feature data to generate pollutant coupling and interaction relationship feature data; In this embodiment of the invention, the coupling and interaction relationship characteristics of pollutants are analyzed based on the characteristic data of multi-target pollutants. The correlation analysis method is adopted, and the characteristic values ​​of calcium hardness alkalinity pollutant, turbidity factor, and residual chlorine factor are used as the analysis objects. The coupling correlation degree between any two types of pollutants is calculated. The coupling correlation degree is calculated using the Pearson correlation formula. The correlation degree threshold is set to 0.6. A correlation degree ≥ 0.6 is considered strong coupling, 0.3 ≤ correlation degree < 0.6 is considered moderate coupling, and correlation degree < 0.3 is considered weak coupling. In the specific analysis, the characteristic values ​​of calcium hardness and alkalinity from the calcium hardness-alkalinity pollutant, the characteristic value of turbidity from the turbidity pollutant, and the characteristic value of residual chlorine content from the residual chlorine pollutant were first extracted. The coupling correlation between the calcium hardness-alkalinity pollutant and the turbidity pollutant, the calcium hardness-alkalinity pollutant and the residual chlorine pollutant, and the turbidity pollutant and the residual chlorine pollutant were calculated. The calculated coupling correlation between the calcium hardness-alkalinity pollutant and the turbidity pollutant was 0.82, indicating strong coupling, meaning that increased turbidity leads to a decrease in calcium hardness-alkalinity removal efficiency. The calculated coupling correlation between the calcium hardness-alkalinity pollutant and the residual chlorine pollutant was 0.65, also indicating strong coupling, meaning that an increase in residual chlorine content within a reasonable range promotes calcium hardness-alkalinity removal. The calculated coupling correlation between the turbidity pollutant and the residual chlorine pollutant was 0.43, indicating moderate coupling, meaning that there is some mutual influence, but the degree of influence is limited. Simultaneously, the direction and degree of influence of each coupling relationship were recorded, clarifying the core influence mechanism of strong coupling relationships, and generating characteristic data of pollutant coupling interaction relationships. This data includes the coupling correlation values, coupling strength levels, influence directions, and influence mechanisms among various pollutants.

[0039] Step S24: Analyze the electrochemical reaction coupling relationship characteristics of pollutants using the pollutant reaction path diagram structure data, and generate pollutant electrochemical reaction coupling relationship characteristic data. In this embodiment of the invention, the electrochemical reaction coupling relationship characteristics of pollutants are analyzed using pollutant reaction path diagram structure data based on pollutant coupling interaction relationship feature data. Using the coupling correlation degree and coupling strength level in the pollutant coupling interaction relationship feature data as the core basis, reaction nodes and directed weighted paths in the pollutant reaction path diagram structure data are matched accordingly. First, the coupling strength of each directed weighted path in the path diagram is labeled, and the coupling correlation degree value is converted into path coupling strength. Strong coupling corresponds to a coupling strength of 0.7-1.0, moderate coupling corresponds to a coupling strength of 0.4-0.6, and weak coupling corresponds to a coupling strength of 0.1-0. 3. After labeling, analyze the coupling influence range of each reaction node, that is, the number and intensity of the coupling influence of each node on other nodes. Among them, the calcium ion electrolysis precipitation node is coupled with the reaction nodes corresponding to the turbidity factor and residual chlorine factor, with coupling strengths of 0.82 and 0.65, respectively; the bicarbonate ion electrolysis decomposition node is coupled with the reaction node corresponding to the residual chlorine factor, with a coupling strength of 0.65; the suspended matter electrolysis coagulation node is coupled with the reaction node corresponding to the calcium hardness alkalinity factor, with a coupling strength of 0.82; the chloride ion electrolysis oxidation node is coupled with the reaction nodes corresponding to the calcium hardness alkalinity factor and turbidity factor, with coupling strengths of 0.65 and 0.43, respectively. Subsequently, the reaction synergy efficiency of each coupling path was calculated. The synergy efficiency was calculated by multiplying the path coupling strength by the reaction strength of the corresponding node. The synergy efficiency threshold was set to 0.5, and coupling paths with a synergy efficiency ≥ 0.5 were screened to clarify the promoting effect of these paths on calcium hardness and alkalinity removal. Characteristic data of the electrochemical reaction coupling relationship of pollutants were generated. The data included path coupling strength labeling, coupling influence range of each node, synergy efficiency of coupling paths, and information on highly efficient synergy paths, clearly presenting the coupling characteristics of each pollutant in the electrochemical reaction process.

[0040] Step S25: Based on the characteristic data of the electrochemical reaction coupling relationship of pollutants and the structural data of the reaction path diagram of pollutants, decouple the electrochemical reactions of pollutants to generate decoupled data of electrochemical reactions of pollutants. In this embodiment of the invention, the electrochemical reactions of pollutants are decoupled based on the characteristic data of the electrochemical reaction coupling relationship of pollutants and the structural data of the pollutant reaction path diagram. A layered stripping method is adopted, and the coupling is stripped sequentially from high to low according to the coupling strength level. Strong coupling relationships are stripped first, followed by medium coupling relationships. Weak coupling relationships, due to their low influence, are not stripped separately and are directly classified as basic interference items. In specific operation, the strong coupling paths in the characteristic data of the electrochemical reaction coupling relationship of pollutants are extracted first, namely the coupling paths corresponding to calcium hardness alkalinity factor and turbidity factor, and calcium hardness alkalinity factor and residual chlorine factor. For the strong coupling path between calcium hardness alkalinity factor and turbidity factor, the reaction parameters of calcium hardness alkalinity pollutant are fixed, the influence of turbidity factor on calcium hardness alkalinity electrochemical reaction is stripped, and the reaction nodes, paths and reaction intensities corresponding to calcium hardness alkalinity factor after stripping are recorded. The reaction parameters of turbidity factor are fixed, the influence of calcium hardness alkalinity factor on turbidity electrochemical reaction is stripped, and the reaction nodes, paths and reaction intensities corresponding to turbidity factor after stripping are recorded. For the strong coupling pathway between calcium hardness alkalinity and residual chlorine, the same method was used to fix the reaction parameters of one type of factor, isolate the influence of the other type of factor, and record the reaction characteristics of the two types of factors after isolation. Subsequently, the coupling pathways corresponding to the moderate coupling relationship, namely turbidity and residual chlorine, were isolated. Using the same method of fixing parameters and isolating influences, the reaction nodes, pathways, and reaction intensities of the two types of factors after isolation were recorded. After isolation, the electrochemical reaction data of all isolated individual pollutants were integrated to clarify the reaction pathways, node characteristics, and reaction intensities of each pollutant acting independently, eliminating coupling interference between different pollutants and generating decoupled electrochemical reaction data of pollutants. This data includes the independent electrochemical reaction pathways, reaction nodes, reaction intensities, and pathway characteristics of the three types of pollutants, laying the foundation for subsequent accurate analysis of the electrochemical contributions of each pollutant.

[0041] Step S26: Analyze the electrochemical contribution characteristics of pollutants using the electrochemical reaction coupling relationship characteristic data and the electrochemical reaction decoupling data of pollutants, and generate the electrochemical contribution characteristic data of pollutants.

[0042] In this embodiment of the invention, the electrochemical contribution characteristics of pollutants are analyzed using the electrochemical reaction coupling relationship characteristic data and the electrochemical reaction decoupling data of pollutants. A contribution quantification calculation method is adopted, with calcium hardness and alkalinity removal efficiency as the core evaluation index. The contribution of a single pollutant acting independently and the synergistic contribution of multiple pollutants acting in combination are calculated separately. The contribution calculation adopts a normalized calculation method, setting the maximum value of calcium hardness and alkalinity removal efficiency to 1. The contribution of each pollutant is the ratio of its corresponding removal efficiency to the maximum value. Specifically, the calcium hardness and alkalinity removal efficiency of the three types of pollutants acting independently is first extracted from the electrochemical reaction decoupling data. The removal efficiency of calcium hardness and alkalinity pollutant acting independently is 0.78, the removal efficiency of turbidity factor acting independently is 0.12, and the removal efficiency of residual chlorine factor acting independently is 0.10. The independent contribution of the three is calculated as 0.78, 0.12, and 0.10, respectively. Subsequently, the synergistic efficiency of each coupling path in the characteristic data of electrochemical reaction coupling relationships of pollutants was extracted, and the synergistic contribution of multiple pollutant coupling effects was calculated. The synergistic contribution of calcium hardness alkalinity factor coupled with turbidity factor was 0.08, the synergistic contribution of calcium hardness alkalinity factor coupled with residual chlorine factor was 0.15, and the synergistic contribution of turbidity factor coupled with residual chlorine factor was 0.03, with a total contribution of 1.0. Simultaneously, the influencing factors of each pollutant contribution were analyzed, clarifying that the contribution of calcium hardness alkalinity pollutant is mainly affected by its own reaction intensity, the contribution of turbidity factor is mainly affected by coupling effects, and the contribution of residual chlorine factor is mainly affected by reaction sequence. Integrating all contribution data, influencing factors, and synergistic characteristics, electrochemical contribution characteristic data of pollutants was generated. This data includes the independent contribution, synergistic contribution, influencing factors, and synergistic law of the three types of pollutants, accurately quantifying the electrochemical contribution of each pollutant to calcium hardness alkalinity removal, providing a core basis for establishing the action space of subsequent electrochemical inversion control parameters.

[0043] Furthermore, the multi-target pollutant characteristic data in step S21 includes calcium hardness alkalinity pollutant characteristic data, turbidity factor characteristic data, and residual chlorine factor characteristic data.

[0044] Furthermore, step S22 includes the following steps: Step S221: Perform electrochemical reaction node feature analysis on the multi-target pollutant feature data to generate pollutant electrochemical reaction node feature data; In this embodiment of the invention, the electrochemical reaction node characteristics of the multi-target pollutant characteristic data are analyzed. The multi-target pollutant characteristic data includes calcium hardness alkalinity pollutant characteristic data, turbidity pollutant characteristic data, and residual chlorine pollutant characteristic data. The calcium hardness alkalinity pollutant characteristic data includes the distribution range, fluctuation difference, and correlation characteristics with electrochemical reaction efficiency of calcium hardness and alkalinity. The turbidity pollutant characteristic data includes the regional distribution differences of turbidity and its influence on ion migration rate. The residual chlorine pollutant characteristic data includes the changing trend of residual chlorine content and its correlation with electrochemical reaction rate. The analysis process is guided by the core reaction of calcium hardness and alkalinity removal in electrochemical purification. Combining the characteristics of various pollutants, the electrochemical reaction nodes corresponding to each type of pollutant are extracted. Calcium hardness and alkalinity pollutants correspond to two core reaction nodes: the calcium ion electrolytic precipitation node and the bicarbonate ion electrolytic decomposition node. The calcium ion electrolytic precipitation node corresponds to the electrolytic conversion process of the calcium hardness factor, and the bicarbonate ion electrolytic decomposition node corresponds to the electrolytic decomposition process of the alkalinity factor. Turbidity factors correspond to one core reaction node: the suspended matter electrolytic coagulation node, which corresponds to the electrolytic coagulation removal process of suspended matter in the turbidity factor. Residual chlorine factors correspond to one core reaction node: the chloride ion electrolytic oxidation node, which corresponds to the electrolytic oxidation conversion process of chloride ions in the residual chlorine factor. Each reaction node corresponds to a unique node identifier, using a 4-digit decimal code: calcium ion electrolytic precipitation node is coded as 0001, bicarbonate ion electrolytic decomposition node as 0002, suspended matter electrolytic coagulation node as 0003, and chloride ion electrolytic oxidation node as 0004. Simultaneously, the reaction intensity of each reaction node is calculated. The reaction intensity is obtained by multiplying the characteristic value of the corresponding pollutant by the electrochemical reaction efficiency, thus clarifying the reaction intensity benchmark of each node and generating characteristic data of the electrochemical reaction nodes of pollutants. The data includes the identifier of each reaction node, the corresponding pollutant, the reaction type and the reaction intensity, clearly defining the core characteristics of each node and providing accurate node data support for subsequent steps.

[0045] Step S222: Perform time-intensity relationship analysis on the electrochemical reaction nodes of pollutants based on the multi-target pollutant characteristic data, and generate time-intensity relationship data of pollutant reaction nodes; In this embodiment of the invention, the time-intensity relationship of electrochemical reaction nodes of pollutants is analyzed based on multi-target pollutant characteristic data. Based on the changing trends of various pollutants and the correlation characteristics of electrochemical reaction efficiency in the multi-target pollutant characteristic data, and combined with the four reaction nodes extracted in step S221, the reaction time interval is set to 10 min. The total time duration of the time series analysis is consistent with the electrolysis time in the initial electrochemical control parameters, i.e., 120 min, and is divided into 12 time intervals. Within each time interval, the reaction intensity of the four reaction nodes is recorded synchronously, and the intensity change of each node within each time interval is calculated. The change is calculated as the difference between the reaction intensity of the current time interval and the reaction intensity of the previous time interval, thus clarifying the rise and fall pattern of the reaction intensity of each node. Simultaneously, the start-up sequence of each reaction node was determined. Combining the electrochemical reaction logic of calcium hardness removal, the calcium ion electrolytic precipitation node and the bicarbonate ion electrolytic decomposition node were started synchronously, with the start time being the beginning of electrochemical purification. After both started, the reaction intensity gradually increased with time intervals, reaching a peak at the 6th time interval (60 min), and then remained stable. The suspended matter electrolytic coagulation node started 5 min after the above two nodes, that is, started in the middle of the 1st time interval (10 min). The reaction intensity gradually increased with time intervals, reaching a peak at the 7th time interval (70 min), and then slowly decreased. The chloride ion electrolytic oxidation node started 3 min after the suspended matter electrolytic coagulation node, that is, started at the end of the 1st time interval (10 min). The reaction intensity continued to increase with time intervals, reaching a peak at the 12th time interval (120 min). Within each time interval, the activation status, reaction intensity, and intensity change of each node are recorded. The intensity characteristics of each node in different time stages are statistically analyzed to clarify the correlation between time and intensity. Time-intensity relationship data of pollutant reaction nodes are generated. The data includes time intervals, activation status of each node, reaction intensity and intensity change of each node in the corresponding time interval, clearly presenting the time-series operation rules and intensity change characteristics of each reaction node, providing a basis for node connection and time sequence association in path diagram structure design.

[0046] Step S223: Design the directed weighted electrochemical reaction path diagram structure of pollutants based on the time-intensity relationship data of the pollutant reaction nodes, and generate pollutant reaction path diagram structure data.

[0047] In this embodiment of the invention, a directed weighted electrochemical reaction path diagram structure of pollutants is designed based on the time-intensity relationship data of pollutant reaction nodes. The node information, time sequence rules and intensity data in the time-intensity relationship data of pollutant reaction nodes are used as the core basis. First, the core nodes of the path diagram are determined and arranged in sequence according to the node identifiers, and the position of each node and the corresponding reaction type are clarified. Subsequently, directed line segments were designed between the nodes. The direction of these directed line segments corresponds to the direction of the electrochemical reaction. Combining the start-up timing and reaction logic in the time-intensity relationship data, the calcium ion electrolytic precipitation node and the bicarbonate ion electrolytic decomposition node are interconnected to form a bidirectional directed line segment, corresponding to their synchronous start-up and mutually promoting reaction relationship. A unidirectional directed line segment is formed between the suspension electrolytic coagulation node and the calcium ion electrolytic precipitation node, with the direction pointing from the suspension electrolytic coagulation node to the calcium ion electrolytic precipitation node, corresponding to the reaction logic that suspension electrolytic coagulation provides favorable conditions for calcium ion electrolytic precipitation. A unidirectional directed line segment is also formed between the chloride ion electrolytic oxidation node and the bicarbonate ion electrolytic decomposition node, with the direction pointing from the chloride ion electrolytic oxidation node to the bicarbonate ion electrolytic decomposition node, corresponding to the reaction logic that chloride ion electrolytic oxidation products promote bicarbonate ion decomposition. Subsequently, a weight was assigned to each directed line segment. The weight corresponds to the reaction correlation strength between two nodes. The correlation strength is calculated based on the average of the products of the reaction strengths of the two nodes at each time interval, with the correlation strength range set from 0.1 to 1.0. Specifically, the correlation strength between the calcium ion electrolytic precipitation node and the bicarbonate ion electrolytic decomposition node is 0.9, the correlation strength between the suspended matter electrolytic coagulation node and the calcium ion electrolytic precipitation node is 0.7, and the correlation strength between the chloride ion electrolytic oxidation node and the bicarbonate ion electrolytic decomposition node is 0.5. The path diagram structure simultaneously labels the identifier of each node, the reaction type, and the reaction strength at each time interval, as well as the weight and reaction direction of each directed line segment. By integrating node information, directed line segments, weights, and time-series intensity data, a pollutant reaction path diagram structure data is generated. This data fully presents the correlation relationships, electrochemical reaction directions, correlation strengths, and time-series changes of the four types of reaction nodes, clearly reflecting the reaction paths of the three types of pollutants in the electrochemical purification process.

[0048] Furthermore, step S3 includes the following steps: Step S31: Perform electrochemical characterization analysis on the electrochemical contribution characteristic data of pollutants to generate electrochemical characterization data; In this embodiment of the invention, the electrochemical contribution characteristic data of pollutants are characterized by electrochemical action state analysis. The electrochemical contribution characteristic data of pollutants includes the independent contribution, synergistic contribution, influencing factors of contribution, and synergistic effect law of calcium hard alkalinity pollutant, turbidity pollutant, and residual chlorine pollutant. Among them, the independent contribution of calcium hard alkalinity pollutant is 0.78 and the synergistic contribution is 0.23, the independent contribution of turbidity pollutant is 0.12 and the synergistic contribution is 0.11, and the independent contribution of residual chlorine pollutant is 0.10 and the synergistic contribution is 0.18. The characterization and analysis process focuses on the removal of calcium hardness and alkalinity as the core objective. Electrochemical action state characterization indicators are set, including three core indicators: electrochemical action intensity, action efficiency, and action stability. Electrochemical action intensity is calculated by the total contribution of the three types of pollutants, which is the sum of independent and synergistic contributions, with a total contribution of 1.0. Electrochemical action efficiency is calculated by the ratio of the contribution of calcium hardness and alkalinity pollutants to the electrochemical action intensity, i.e., 0.78 ÷ 1.0 = 0.78. Electrochemical action stability is calculated by the fluctuation difference of the contribution of each pollutant, which is the difference between the maximum and minimum contribution of each pollutant. The fluctuation difference for calcium hardness and alkalinity pollutants is 0.12, for turbidity is 0.03, and for residual chlorine is 0.02. Overall stability is calculated by the average of these three fluctuation differences, i.e., 0.057. Simultaneously, the classification criteria for each characterization index were clearly defined. Electrochemical interaction intensity was divided into three levels: strong, medium, and weak. A total contribution of 0.8-1.0 was strong, 0.5-0.79 was medium, and 0.1-0.49 was weak. Interaction efficiency was 0.7-1.0 high, 0.4-0.69 medium, and 0.1-0.39 low. Interaction stability fluctuations were ≤0.06 for stable, 0.07-0.1 for relatively stable, and >0.1 for unstable. Based on the calculation results, the current electrochemical interaction intensity is strong, the interaction efficiency is high, and the interaction stability is stable. Integrating all characterization indices, calculation results, and level classifications, electrochemical interaction state characterization data was generated. This data includes specific values ​​and levels for electrochemical interaction intensity, efficiency, and stability, clearly presenting the interaction state during the electrochemical purification process.

[0049] Step S32: Construct the electrochemical regulation parameter space based on the electrochemical interaction state characterization data to generate electrochemical regulation parameter space data; In this embodiment of the invention, an electrochemical control parameter space is constructed based on electrochemical interaction state characterization data. The electrochemical interaction state characterization data shows that the current electrochemical interaction intensity is strong, the interaction efficiency is high, and the interaction stability is stable. The construction process is based on the initial electrochemical control parameters set in step S11, and clarifies the value range of four core control parameters: electrolysis voltage, electrolysis current, electrode spacing, and electrolysis time. The electrolysis voltage value range is optimized to 4V-7V based on the initial parameter of 3V-8V and combined with the interaction efficiency. The electrolysis current is optimized to 2A-4A based on the initial parameter of 1A-5A. The electrode spacing is optimized to 8cm-12cm based on the initial parameter of 5cm-15cm. The electrolysis time remains unchanged from the initial parameter of 30min-120min. The parameter space was constructed using a grid-based approach, uniformly dividing the value ranges of the four control parameters. Electrolysis voltage was divided into 7 grid nodes for every 0.5V; electrolysis current into 11 grid nodes for every 0.2A; electrode spacing into 9 grid nodes for every 0.5cm; and electrolysis time into 10 grid nodes for every 10min. Each grid node corresponds to a unique combination of control parameters. The predicted electrochemical state for each parameter combination was calculated using a correlation formula between the parameter combination and the electrochemical state characterization index: Predicted action intensity = Electrolysis voltage × 0.15 + Electrolysis current × 0.2 + Electrode spacing × 0.05 + Electrolysis time × 0.01; Predicted action efficiency = Predicted action intensity × 0.78; Predicted action stability = 1 - (Electrolysis voltage fluctuation + Electrolysis current fluctuation + Electrode spacing fluctuation + Electrolysis time fluctuation) × 0.25. Parameter combinations with predicted action intensity ≥ 0.8, predicted action efficiency ≥ 0.7, and predicted action stability ≥ 0.94 were selected, resulting in 386 effective parameter combinations. By integrating all effective parameter combinations, parameter value ranges, grid node information, and predicted state values, spatial data of electrochemical regulation parameters were generated. The data clearly defines the range and combination of regulation parameters that are suitable for the current electrochemical action state and can achieve efficient removal of calcium hard alkalinity.

[0050] Step S33: Based on the electrochemical action state characterization data and the spatial data of electrochemical regulation parameters, perform the mapping relationship analysis between electrochemical action state and action to generate electrochemical action state-action mapping relationship data; In this embodiment of the invention, the mapping relationship between electrochemical action states and actions is analyzed based on electrochemical action state characterization data and electrochemical regulation parameter spatial data. Action intensity, action efficiency, and action stability from the electrochemical action state characterization data are used as state variables, and the adjustment amounts of the four core regulation parameters from the electrochemical regulation parameter spatial data are used as action variables. The state variables are divided into three intervals: action intensity is divided into strong (0.8-1.0), medium (0.5-0.79), and weak (0.1-0.49); action efficiency is divided into three intervals: high efficiency (0.7-1.0), medium efficiency (0.4-0.69), and low efficiency (0.1-0.39); and action stability is divided into three intervals: stable (≤0.06), relatively stable (0.07-0.1), and unstable (>0.1). A total of 27 different electrochemical action states are formed by these combinations. The action variables were set as the adjustment ranges of four control parameters: electrolysis voltage adjustment ranges of ±0.5V and ±1.0V, electrolysis current adjustment ranges of ±0.2A and ±0.4A, electrode spacing adjustment ranges of ±0.5cm and ±1.0cm, and electrolysis time adjustment ranges of ±10min and ±20min. Each adjustment range corresponds to one action. The influence of different parameter adjustments on the action state under each action state was analyzed, and the action influence coefficient was calculated. The influence coefficient was calculated by the difference between the action state index after adjustment and the index before adjustment. A positive influence coefficient indicates that the action improves the action state, and a negative coefficient indicates that the action worsens the action state. For example, when the operating state is "high intensity, high efficiency, and stable stability," the influence coefficient of adjusting the electrolysis voltage by +0.5V is 0.03, and the influence coefficient of adjusting it by -0.5V is -0.02; the influence coefficient of adjusting the electrolysis current by +0.2A is 0.02, and the influence coefficient of adjusting it by -0.2A is -0.01; the influence coefficient of adjusting the electrode spacing by -0.5cm is 0.01, and the influence coefficient of adjusting it by +0.5cm is -0.01; the influence coefficient of adjusting the electrolysis time by +10min is 0.01, and the influence coefficient of adjusting it by -10min is -0.02. Actions with positive influence coefficients and absolute values ​​≥0.01 in each state are selected, establishing a correspondence between states and actions. The optimal parameter adjustment action for each state is identified, generating electrochemical operating state-action mapping data. This data includes 27 operating states, the optimal adjustment action for each state, and the action influence coefficient, clearly presenting the parameter adjustment logic under different operating states.

[0051] Step S34: Perform response characteristic analysis on the electrochemical action state-action mapping relationship data to generate electrochemical action state-action response characteristic data; In this embodiment of the invention, response characteristic analysis of the electrochemical state-action mapping relationship data is performed. Based on the state, action, and influence coefficient in the electrochemical state-action mapping relationship data, response characteristic analysis indicators are set, including three core indicators: response time, response amplitude, and response decay rate. Response time refers to the time required for the electrochemical state to stabilize after parameter adjustment. Response amplitude refers to the difference between the adjusted state indicator and the original state indicator (i.e., the absolute value of the influence coefficient). Response decay rate refers to the ratio of the difference between the stabilized state indicator and the adjusted instantaneous indicator to the response amplitude. A response time threshold of 5 min, a response amplitude threshold of 0.01, and a response decay rate threshold of 0.05 are set. That is, a response is considered valid when the response time is ≤5 min, the response amplitude is ≥0.01, and the response decay rate is ≤0.05. For each state-action combination, three response characteristic indices are calculated as follows: Response time = Adjusted state stabilization time - Adjustment time; Response amplitude = |Adjusted state index - Unadjusted state index|; Response decay rate = (Adjusted instantaneous index - Stabilized index) ÷ Response amplitude. For example, when the action state is "high intensity, high efficiency, and stable stability", and the action is electrolysis voltage +0.5V, the response time is 3min, the response amplitude is 0.03, and the response decay rate is 0.03; when the action is electrolysis current +0.2A, the response time is 4min, the response amplitude is 0.02, and the response decay rate is 0.04; when the action is electrode spacing -0.5cm, the response time is 5min, the response amplitude is 0.01, and the response decay rate is 0.05; and when the action is electrolysis time +10min, the response time is 4min, the response amplitude is 0.01, and the response decay rate is 0.04. The response characteristic indices of all state-action combinations met the effective response criteria. Subsequently, the correlation between response characteristics and action adjustment amplitude was analyzed, clarifying that a larger adjustment amplitude results in a larger response amplitude, longer response time, and higher response decay rate. Simultaneously, the response differences for different parameter actions were analyzed: electrolytic voltage adjustment resulted in the largest response amplitude, electrode spacing adjustment had the longest response time, and electrolytic current adjustment had the lowest response decay rate. By integrating the response characteristic indices, response patterns, and parameter action differences of all state-action combinations, electrochemical action state-action response characteristic data was generated. This data includes the response time, response amplitude, response decay rate, response patterns, and parameter action differences for each state-action combination.

[0052] Step S35: Perform iterative inversion processing of electrochemical action-driven regulation parameters using electrochemical action state-action response characteristic data to generate electrochemical action-regulation parameter inversion data; In this embodiment of the invention, electrochemical action state-action response characteristic data is used to perform iterative inversion processing of electrochemical action-driven control parameters. The inversion processing is based on the electrochemical action state-action response characteristic data, with the target state being the electrochemical action state (high intensity, high efficiency, and stable stability) corresponding to calcium hardness alkalinity removal. The initial parameter combination for iterative inversion is set as the initial control parameters of step S11 (electrolysis voltage 5V, electrolysis current 3A, electrode spacing 10cm, electrolysis time 60min). The number of iterations is set to 50, and the iteration error threshold is 0.01. That is, iteration stops when the number of iterations reaches 50 or the difference in action state indices corresponding to parameter combinations between two adjacent iterations is less than 0.01. During each iteration, the electrochemical action state index corresponding to the current parameter combination is first calculated. Then, combined with the electrochemical action state-action response characteristic data, the parameter adjustment action that can improve the action state and achieve the best response effect is selected. The adjustment range is determined based on the response amplitude and attenuation rate, with priority given to actions with large response amplitude and low attenuation rate. In the first iteration, the current parameter combination corresponds to an action strength of 0.85, an efficiency of 0.68, and a stability of 0.95, which does not reach the target efficiency (≥0.7). Therefore, an action of increasing the electrolysis voltage by 0.5V is selected. After adjustment, the parameters are 5.5V, 3A, 10cm, and 60min, corresponding to an action strength of 0.88, an efficiency of 0.70, and a stability of 0.94, with an iteration error of 0.02. In the second iteration, an action of increasing the electrolysis current by 0.2A is selected. After adjustment, the parameters are 5.5V, 3.2A, 10cm, and 60min, resulting in an action strength of 0.90, an efficiency of 0.71, and a stability of 0.94, with an iteration error of 0.01, reaching the error threshold, and the iteration stops. If the number of iterations does not reach the threshold and the error does not meet the requirements, the above process continues until the stopping condition is met. After iteration, the optimal parameter combination is recorded, along with the parameter adjustment actions, adjustment magnitudes, corresponding action state indicators, and iteration errors for each iteration. This clarifies the process and rules of the iterative inversion and generates electrochemical action-regulation parameter inversion data. The data includes the optimal regulation parameter combination, the number of iterations, parameter adjustments for each iteration, and state change information. The optimal parameter combination obtained from the inversion is an electrolysis voltage of 5.5V, an electrolysis current of 3.2A, an electrode spacing of 10cm, and an electrolysis time of 60min, which can stably maintain the target electrochemical action state.

[0053] Step S36: Based on the electrochemical action-regulation parameter inversion data, establish the action space of the electrochemical inversion regulation parameters and generate the action space data of the electrochemical inversion regulation parameters.

[0054] In this embodiment of the invention, the action space of electrochemical inversion control parameters is established based on electrochemical action-control parameter inversion data. The establishment process is centered on the optimal parameter combination (electrolysis voltage 5.5V, electrolysis current 3.2A, electrode spacing 10cm, electrolysis time 60min) in the electrochemical action-control parameter inversion data. Combined with the electrochemical control parameter space data generated in step S32, the parameter fluctuation range is set as follows: the electrolysis voltage fluctuation range is ±0.5V, i.e., 5.0V-6.0V; the electrolysis current fluctuation range is ±0.3A, i.e., 2.9A-3.5A; the electrode spacing fluctuation range is ±0.5cm, i.e., 9.5cm-10.5cm; and the electrolysis time fluctuation range is ±10min, i.e., 50min-70min. Within this fluctuation range, a grid-based approach was adopted, with an electrolysis voltage node every 0.1V, an electrolysis current node every 0.1A, an electrode spacing node every 0.1cm, and an electrolysis time node every 5min, resulting in a total of 11×7×11×5=4235 parameter combinations. The electrochemical performance of each parameter combination was verified by calculating the corresponding performance intensity, efficiency, and stability. Parameter combinations meeting the target performance (intensity ≥ 0.8, efficiency ≥ 0.7, stability ≥ 0.94) were selected, resulting in 896 effective parameter combinations. Subsequently, the distribution patterns of each parameter in the effective parameter combination were analyzed, and the mean, maximum, minimum, and fluctuation differences of each parameter were calculated. The optimal range for electrolysis voltage was determined to be 5.2V-5.8V, the optimal range for electrolysis current was 3.0A-3.4A, the optimal range for electrode spacing was 9.7cm-10.3cm, and the optimal range for electrolysis time was 55min-65min. Simultaneously, the interaction relationships between these parameters were analyzed. Electrolysis voltage and electrolysis current were positively correlated, electrode spacing and interaction intensity were negatively correlated, and electrolysis time and efficiency were positively correlated. These correlations were derived through correlation calculations of the parameter values. By integrating the effective parameter combination, the optimal range of each parameter, the distribution patterns, and the interaction relationships, spatial data of the electrochemical inversion control parameters were generated. The data clearly presents the range, combination, and interaction patterns of the electrochemical control parameters that can stably achieve efficient removal of calcium hardness alkalinity.

[0055] Furthermore, as an embodiment of the present invention, reference is made to... Figure 2 As shown, Figure 1 A detailed flowchart illustrating the implementation steps of step S4 is provided in this embodiment. Step S4 includes: Step S41: Based on the spatial data of the effect of the electrochemical inversion control parameters, perform simulation processing of the circulating water effect of the electrochemical inversion control parameters to generate simulation data of the circulating water effect of the inversion control parameters; In this embodiment of the invention, the effect of electrochemical inversion control parameters on circulating water is simulated based on the spatial data of the electrochemical inversion control parameters. This spatial data includes 896 effective parameter combinations, the optimal range of each parameter, and their interaction patterns. The optimal ranges are: electrolysis voltage 5.2V-5.8V, electrolysis current 3.0A-3.4A, electrode spacing 9.7cm-10.3cm, and electrolysis time 55min-65min. The simulation process is based on the actual operating conditions of the circulating water system. The simulation duration is set to be consistent with the electrolysis time, i.e., 55min-65min, with a simulation time interval of 5min. At each time interval, the numerical changes in calcium hardness, alkalinity, turbidity, and residual chlorine content of the circulating water, as well as the dynamic changes in the intensity, efficiency, and stability of the electrochemical interaction, are recorded simultaneously. During the simulation, each set of inversion control parameters was used as input. Based on the principle of electrochemical purification reaction, the removal amount of calcium hard alkalinity within different time intervals was calculated. The calculation method was the difference between the initial calcium hard alkalinity value and the calcium hard alkalinity value at the current time interval. Simultaneously, changes in turbidity and residual chlorine content, as well as real-time values ​​of electrochemical performance indicators, were calculated. For each parameter combination, a full-duration simulation was completed, recording all data at all time intervals to clarify the rate and amount of calcium hard alkalinity removal under different parameter combinations, as well as the dynamic changes in the electrochemical performance state. The simulation data of all parameter combinations were integrated and categorized by parameter combination, clarifying the changes in circulating water quality and electrochemical performance corresponding to each parameter set. This generated simulation data of the circulating water performance of the inversion control parameters. The data included all effective parameter combinations, circulating water quality parameters at each time interval, and electrochemical performance indicators, clearly presenting the effects of different inversion control parameters on the circulating water, providing accurate simulation data support for subsequent steps.

[0056] Step S42: Perform electrochemical purification-driven stage constraint embedding processing on the simulation data of the inversion control parameter circulating water effect to generate constrained inversion control parameter circulating water effect simulation data; In this embodiment of the invention, the simulation data of the circulating water action of the inversion control parameters are subjected to stage-constrained embedding processing driven by electrochemical purification. The electrochemical purification process is divided into three stages according to the reaction progress: the start-up stage, the stabilization stage, and the termination stage. Each stage is given specific constraints. The constraints for the start-up stage (0-10 min) are: electrochemical action intensity ≥ 0.8 and calcium hardness removal rate ≥ 0.5 mg / (L·min); the constraints for the stabilization stage (10-55 min) are: electrochemical action efficiency ≥ 0.7, action stability ≤ 0.06, and calcium hardness removal rate maintained at 0.3-0.5 mg / (L·min); the constraints for the termination stage (55-65 min) are: electrochemical action intensity ≥ 0.8 and calcium hardness removal amount ≥ 80%. During the constraint embedding process, the simulation data of each parameter combination in the circulating water effect simulation data of the inverted control parameters are checked one by one at each stage to determine whether the constraint conditions of the corresponding stage are met. Data that do not meet the constraint conditions are corrected by adjusting the electrochemical effect index and calcium hardness / alkalinity removal-related data in the simulation data based on the constraint threshold of the corresponding stage, ensuring that the corrected data meets the constraint requirements of each stage. For example, if the electrochemical effect intensity of a parameter combination in the start-up stage (5 min) is 0.78, which does not meet the constraint of ≥0.8, it is corrected to 0.81, and the calcium hardness / alkalinity removal rate is adjusted to 0.52 mg / (L·min) to ensure matching with the constraint conditions; if the effect stability of a parameter combination in the steady stage is 0.07, which does not meet the constraint of ≤0.06, it is corrected to 0.06, and the calcium hardness / alkalinity removal rate is adjusted to 0.4 mg / (L·min). After the correction is completed, the data of each stage are checked again to ensure that the simulation data of all parameter combinations meet the constraints of the corresponding stage. All the corrected simulation data are integrated and sorted by parameter combination and reaction stage to generate the simulation data of the effect of the constraint inversion control parameters on the circulating water. The data includes the corrected parameter combination, the circulating water quality data of each stage, and the electrochemical effect index.

[0057] Step S43: Based on the spatial data of the effects of the electrochemical inversion control parameters, perform temporal perturbation scenario analysis of the inversion control parameters to generate temporal perturbation scenario data of the inversion control parameters; In this embodiment of the invention, the temporal perturbation scenario analysis of the electrochemical inversion control parameter is performed based on the spatial data of the electrochemical inversion control parameter. The core parameters in the spatial data of the electrochemical inversion control parameter are electrolysis voltage, electrolysis current, electrode spacing, and electrolysis time. Among them, the electrode spacing fluctuates little in actual operation, so no perturbation is set. Only the electrolysis voltage, electrolysis current, and electrolysis time are subject to temporal perturbation settings. The perturbation scenarios are divided into three categories: slight perturbation, moderate perturbation, and severe perturbation. Each perturbation scenario corresponds to different perturbation amplitudes and timing patterns. In the slight perturbation scenario, the perturbation amplitude of the electrolytic voltage is ±0.1V, the perturbation amplitude of the electrolytic current is ±0.1A, the perturbation amplitude of the electrolytic time is ±3min, the perturbation interval is 15min, and each perturbation lasts for 5min before returning to the initial parameters. In the moderate perturbation scenario, the perturbation amplitude of the electrolytic voltage is ±0.2V, the perturbation amplitude of the electrolytic current is ±0.2A, the perturbation amplitude of the electrolytic time is ±5min, the perturbation interval is 10min, and each perturbation lasts for 8min before returning to the initial parameters. In the severe perturbation scenario, the perturbation amplitude of the electrolytic voltage is ±0.3V, the perturbation amplitude of the electrolytic current is ±0.3A, the perturbation amplitude of the electrolytic time is ±8min, the perturbation interval is 8min, and each perturbation lasts for 10min before returning to the initial parameters. During the analysis, the optimal parameter combination (electrolysis voltage 5.5V, electrolysis current 3.2A, electrode spacing 10cm, and electrolysis time 60min) from the spatial data of electrochemical inversion regulation parameters was used as a benchmark. The temporal fluctuation process of the parameters was simulated under three types of perturbation scenarios. The perturbation time, duration, amplitude, and corresponding parameter values ​​were recorded to clarify the temporal variation patterns of the parameters under different perturbation scenarios. Simultaneously, based on the electrochemical action principle, the influence trend of parameter fluctuations on the calcium hardness alkalinity removal effect under each perturbation scenario was predicted. For example, the calcium hardness alkalinity removal rate fluctuation was ≤0.05mg / (L·min) under slight perturbation, ≤0.1mg / (L·min) under moderate perturbation, and ≤0.15mg / (L·min) under severe perturbation. By integrating the time-series fluctuation data, disturbance patterns, and predicted impact trends of parameters from three types of disturbance scenarios, inversion control parameter time-series disturbance scenario data is generated. The data includes the three types of disturbance scenarios, the time-series fluctuation information of parameters in each scenario, disturbance patterns, and predicted impact trends, providing comprehensive disturbance scenario support for subsequent circulating water purification evolution treatment.

[0058] Step S44: Perform circulating water purification evolution processing of the inverted control parameters using the time-series disturbance scenario data of the inverted control parameters and the simulation data of the circulating water effect of the constrained inverted control parameters, and generate circulating water purification evolution data of the inverted control parameters. In this embodiment of the invention, the circulating water purification evolution of the inverted control parameters is processed using time-series perturbation scenario data of the inverted control parameters and simulation data of the circulating water effect of the constrained inverted control parameters. The purification evolution process is based on the simulation data of the circulating water effect of the constrained inverted control parameters, combined with three types of perturbation scenarios in the time-series perturbation scenario data of the inverted control parameters. Purification evolution simulation is performed for each combination of inverted control parameters, with the simulation duration consistent with the electrolysis time, i.e., 60 min, and the simulation time interval being 5 min. During the evolution simulation, the time-series fluctuation data of the parameters corresponding to the perturbation scenario is embedded into the constrained simulation data, and the control parameter values ​​at each time interval are adjusted in real time. The changes in the calcium hardness alkalinity, turbidity, and residual chlorine content of the circulating water after each parameter perturbation, as well as the changes in the intensity, efficiency, and stability of the electrochemical effect, are calculated to clarify the degree of influence of parameter perturbation on the purification effect. For example, in a slightly disturbed scenario, when the electrolysis voltage experiences a +0.1V disturbance at 15 minutes, the change in the calcium hardness removal rate at that moment and over the following 5 minutes is calculated. The rate increases from 0.4 mg / (L·min) to 0.43 mg / (L·min), the electrochemical efficiency increases from 0.71 to 0.73, and the stability remains unchanged at 0.06. In a moderately disturbed scenario, when the electrolysis current experiences a -0.2A disturbance at 10 minutes, the calcium hardness removal rate decreases from 0.4 mg / (L·min) to 0.32 mg / (L·min), and the electrochemical efficiency decreases from 0.71 to 0.68. At this point, the parameter callback mechanism is activated to restore the electrolysis current to its initial value, ensuring that the subsequent purification effect meets the constraints. For three types of disturbance scenarios, purification evolution simulations were performed for all parameter combinations. Parameter values, circulating water quality data, and electrochemical performance indicators were recorded at each time interval. The evolutionary patterns of purification effects under different disturbance scenarios and parameter combinations were analyzed, clarifying the scope of parameter disturbance influence and the callback logic. All evolution simulation data were integrated, categorized by disturbance scenario and parameter combination, to generate inversion control parameter circulating water purification evolution data. This data includes purification evolution process data for each of the three disturbance scenarios and parameter combinations, disturbance influence patterns, and parameter callback logic, clearly presenting the dynamic evolution process of circulating water purification under different disturbance scenarios.

[0059] Step S45: Perform multi-condition purification behavior prediction feature analysis based on the inversion control parameters and circulating water purification evolution data to generate multi-condition purification behavior prediction feature data.

[0060] In this embodiment of the invention, multi-condition purification behavior prediction feature analysis is performed based on the circulating water purification evolution data of the inverted control parameters. Using the circulating water purification evolution data of the inverted control parameters as a basis, the conditions are divided into 896 × 3 = 2688 conditions, combining parameter combinations and disturbance scenarios. Each condition corresponds to a set of parameter combinations and a disturbance scenario. The analysis process sets prediction feature indicators, including four core indicators: calcium hardness and alkalinity removal amount, peak removal rate, removal stability, and electrochemical action adaptability. Calcium hardness and alkalinity removal amount is the total amount of calcium hardness and alkalinity removed at the end of the simulation; peak removal rate is the maximum value of the calcium hardness and alkalinity removal rate during the purification evolution process; removal stability is the fluctuation difference in the removal rate; and electrochemical action adaptability is the percentage of time during which the electrochemical action indicators meet the constraints. The specific values ​​of four predicted characteristic indicators were calculated for each operating condition. The calculation method was as follows: Removal amount = Initial calcium hardness alkalinity value - Calcium hardness alkalinity value at the end of the simulation; Peak removal rate = Maximum removal rate at each time interval; Removal stability = Peak removal rate - Minimum removal rate; Electrochemical adaptability = Duration of meeting constraints ÷ Total simulation duration. Predictive characteristic thresholds were set: calcium hardness alkalinity removal amount ≥ 80%, peak removal rate ≥ 0.5 mg / (L·min), removal stability ≤ 0.1 mg / (L·min), and electrochemical adaptability ≥ 90%. Optimal operating conditions that met all threshold requirements were screened, resulting in 128 optimal operating conditions. Subsequently, the optimal operating conditions and the characteristics of disturbance scenarios were analyzed to clarify the distribution pattern of the optimal parameter combinations and the adjustment logic of the optimal parameters under different disturbance scenarios. For example, under slight disturbance scenarios, the optimal electrolysis voltage is concentrated between 5.3V and 5.7V; under moderate disturbance scenarios, the optimal electrolysis current is concentrated between 3.1A and 3.3A; and under severe disturbance scenarios, the optimal electrolysis time is concentrated between 58min and 62min. Simultaneously, the correlation between predicted characteristic indicators was analyzed: the removal amount of calcium hardness alkalinity is positively correlated with the peak removal rate and negatively correlated with removal stability; electrochemical adaptability is positively correlated with the removal amount. By integrating the predicted characteristic indicators, optimal operating condition information, parameter distribution patterns, and characteristic correlations of all operating conditions, multi-condition purification behavior prediction characteristic data was generated.

[0061] Furthermore, step S5 includes the following steps: Step S51: Obtain target data for calcium hardness and alkalinity removal in circulating water; In this embodiment of the invention, the core of obtaining target demand data for calcium hardness and alkalinity removal in circulating water is to clarify the specific targets for calcium hardness and alkalinity removal in circulating water. This provides core guidance for subsequent multi-objective optimization analysis and intelligent control parameter design, ensuring that the designed control parameters can accurately match the actual removal needs and align with the core objective of electrochemical purification optimization through circulating water calcium hardness and alkalinity removal rate data analysis. The obtained target demand data revolves around the core of calcium hardness and alkalinity removal and, combined with the actual application scenarios of electrochemical purification, sets clear quantitative indicators, specifically including four core indicators: calcium hardness and alkalinity removal rate target, removal rate target, energy consumption control target, and operational stability target. The priority of each target is also clearly defined: the calcium hardness and alkalinity removal rate target has the highest priority, followed by the energy consumption control target, while the removal rate target and operational stability target have equal priority. The priority weights are set as follows: removal rate 40%, energy consumption 30%, removal rate 15%, and stability 15%. By integrating all the above quantitative indicators, priorities, and weights, target requirement data for the removal of calcium hardness and alkalinity in circulating water is generated. The data includes the specific thresholds, priority rankings, and weight allocations for the four core objectives, providing a clear basis for subsequent multi-objective optimization analysis and ensuring that the subsequent optimization direction always revolves around the efficient, energy-saving, and stable removal of calcium hardness and alkalinity.

[0062] Step S52: Perform multi-objective optimization analysis on the target requirement data for calcium hardness and alkalinity removal in circulating water to generate multi-objective optimization analysis data for electrochemical purification of circulating water; In this embodiment of the invention, a multi-objective optimization analysis of circulating water electrochemical purification is performed on the target requirement data for calcium hardness and alkalinity removal in circulating water. Based on the four core objectives, priorities, and weights in the target requirement data for calcium hardness and alkalinity removal in circulating water, and combined with the predicted feature indicators in the multi-condition purification behavior prediction feature data generated in step S45, a multi-objective optimization analysis model is established. The model uses calcium hardness and alkalinity removal rate, removal speed, energy consumption, and stability as optimization variables, the threshold of each objective as a constraint condition, and priority weights as a guide to calculate the balance coefficient between each optimization variable. The balance coefficient is calculated by the sum of the products of the weight of each objective and the corresponding predicted feature indicator. The balance coefficient is set to a range of 0-1. The closer the balance coefficient is to 1, the better the parameter combination can take into account multiple objectives. In the specific analysis, the targets for calcium hardness and alkalinity removal (≥85%), removal rate (≥0.4 mg / (L·min)), energy consumption (≤1.2 kWh / m³), and stability (≤0.06) are first converted into model constraints. Then, priority weights are substituted into the model to calculate the degree of satisfaction of each target under different operating conditions. The degree of satisfaction is calculated by the ratio of the actual value to the target threshold. A satisfaction degree ≥1 for removal rate, removal rate, and stability is considered satisfactory, while a satisfaction degree ≤1 for energy consumption is considered satisfactory. Simultaneously, the constraints between the targets are analyzed, clarifying that an increase in removal rate leads to an increase in energy consumption, and an increase in removal rate leads to a decrease in stability. The weight ratio of each target is adjusted by a balance coefficient to ensure that the analysis results achieve a balance among multiple targets. For example, when the removal rate meets the target but energy consumption exceeds the target, the weight of removal rate is reduced by 0.05, the weight of energy consumption is increased by 0.05, and the balance coefficient is recalculated. After analysis, the core direction of multi-objective optimization is to minimize energy consumption and improve stability while ensuring that the removal rate meets the target. The optimization direction, the constraints of each objective, the calculation results of the balance coefficient, and the objective constraint relationship are integrated to generate multi-objective optimization analysis data for circulating water electrochemical purification. The data includes optimization model parameters, constraints of each objective, balance coefficient, objective constraint relationship, and optimization direction, providing accurate analytical basis for subsequent global parameter search.

[0063] Step S53: Perform global search processing of circulating water electrochemical purification parameters based on the multi-objective optimization analysis data and multi-condition purification behavior prediction feature data of circulating water electrochemical purification, and generate global search data of circulating water electrochemical purification parameters. In this embodiment of the invention, a global search process for circulating water electrochemical purification parameters is performed based on multi-objective optimization analysis data and multi-condition purification behavior prediction feature data. The global search process uses the optimization direction, constraints, and balance coefficients in the multi-objective optimization analysis data as search criteria, and the 2688 conditions and corresponding parameter combinations in the multi-condition purification behavior prediction feature data as the search scope. A global traversal search method is used to check the parameter combinations and prediction feature indicators corresponding to each condition one by one to determine whether all objective constraints and balance coefficient requirements are met. During the search process, a balance coefficient threshold of 0.9 is set, and conditions and corresponding parameter combinations with a balance coefficient ≥ 0.9 and all objectives met are selected. Simultaneously, the optimal range of parameters in the electrochemical inversion control parameter action space data generated in step S36 is combined to further select conditions where the parameter combinations are within the optimal range, ensuring that the searched parameter combinations not only meet the multi-objective requirements but also have practical application feasibility. During the specific search, the following conditions were first selected: calcium hardness alkalinity removal rate ≥85%, removal rate ≥0.4mg / (L·min), energy consumption ≤1.2kWh / m³, and stability ≤0.06, resulting in 64 conditions. Then, the balance coefficient of these 64 conditions was calculated, and conditions with a balance coefficient ≥0.9 were selected, resulting in 32 conditions. Finally, the parameter combinations of these 32 conditions were checked to ensure that the electrolysis voltage was within the optimal range of 5.2V-5.8V, the electrolysis current was within the optimal range of 3.0A-3.4A, the electrode spacing was within the optimal range of 9.7cm-10.3cm, and the electrolysis time was within the optimal range of 55min-65min, retaining 28 conditions and their corresponding parameter combinations. Simultaneously, a comprehensive score was calculated for each parameter combination, with the comprehensive score equal to the balance coefficient multiplied by 100. This determined the ranking of the comprehensive performance of each parameter combination. The parameter combination with the highest comprehensive score was 5.5V electrolysis voltage, 3.2A electrolysis current, 10.0cm electrode spacing, and 60min electrolysis time, with a comprehensive score of 96. All 28 selected parameter combinations, their comprehensive scores, corresponding predicted characteristic indicators, and balance coefficients were integrated to generate global search data for circulating water electrochemical purification parameters. This data includes the 28 optimal parameter combinations, the comprehensive scores for each combination, and their corresponding operating characteristics.

[0064] Step S54: Design intelligent control parameters for circulating water electrochemical purification based on global search data of circulating water electrochemical purification parameters.

[0065] In this embodiment of the invention, based on 28 optimal parameter combinations and comprehensive scores from the global search data, the top 5 parameter combinations with the highest comprehensive scores are selected as core control parameters. These are: electrolysis voltage 5.5V, electrolysis current 3.2A, electrode spacing 10.0cm, electrolysis time 60min (comprehensive score 96); electrolysis voltage 5.6V, electrolysis current 3.3A, electrode spacing 9.9cm, electrolysis time 62min (comprehensive score 95); electrolysis voltage 5.4V, electrolysis current 3.1A, electrode spacing 10.1cm, electrolysis time 58min (comprehensive score 94); electrolysis voltage 5.7V, electrolysis current 3.2A, electrode spacing 9.8cm, electrolysis time 61min (comprehensive score 93); and electrolysis voltage 5.3V, electrolysis current 3.3A, electrode spacing 10.2cm, electrolysis time 59min (comprehensive score 92). Subsequently, combining the temporal disturbance scenarios in step S43 and the purification evolution patterns in step S44, corresponding disturbance adaptation rules are matched for each core control parameter. In the case of minor disturbances, the parameter combination with the highest comprehensive score is used, requiring no adjustment. In the case of moderate disturbances, when the electrolysis current fluctuates by ±0.2A, the parameter combination with an electrolysis current of 3.3A is automatically switched to maintain the removal effect. In the case of severe disturbances, when the electrolysis voltage fluctuates by ±0.3V, the parameter combination with an electrolysis voltage of 5.7V or 5.3V is automatically switched, and the electrolysis time is adjusted to 61min or 59min to ensure stability. Simultaneously, parameter adjustment trigger conditions are set: when the calcium hardness alkalinity removal rate is below 85%, energy consumption is above 1.2kWh / m³, stability is above 0.06, or the removal rate is below 0.4mg / (L·min), parameter switching is automatically triggered, switching to the corresponding adapted core control parameter. Furthermore, the operational logic of the intelligent control parameters is clearly defined. Real-time data collection of circulating water quality and electrochemical state is performed, comparing these data with target threshold requirements to automatically determine whether parameter adjustments are needed, achieving dynamic intelligent adaptation of the control parameters. The system integrates core control parameters, disturbance adaptation rules, parameter adjustment trigger conditions, and operational logic to generate intelligent control parameters for circulating water electrochemical purification. These parameters include five sets of core control parameters, corresponding disturbance adaptation rules, trigger conditions, and operational logic. This allows for automatic adaptation to different temporal disturbance scenarios, precisely meeting multiple target requirements for calcium hardness and alkalinity removal, achieving efficient, energy-saving, and stable removal of calcium hardness and alkalinity from circulating water, and completing the entire electrochemical purification optimization process.

[0066] Therefore, the embodiments should be considered as exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description. Thus, all variations falling within the meaning and scope of the equivalents of the application are intended to be included within the invention.

[0067] The above description is merely a specific embodiment of the present invention, enabling those skilled in the art to understand or implement the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the invention. Therefore, the present invention is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features of the invention herein.

Claims

1. An electrochemical purification optimization method for analyzing calcium hardness and alkalinity removal rate data in circulating water, characterized in that, Includes the following steps: Step S1: Obtain the initial electrochemical control parameters of the circulating water system; collect the original observation data of the circulating water system from multiple sources using the circulating water multi-source sensing and acquisition equipment; Based on the initial electrochemical control parameters and the original observation data of multiple sources of circulating water, the state characteristics of multiple sources of circulating water are analyzed, and the distribution data of the state characteristics of multiple sources of circulating water are generated. Step S2: Perform electrochemical contribution characteristic analysis on the multi-source state characteristic distribution data of circulating water pollutants to generate electrochemical contribution characteristic data of pollutants; Step S3: Based on the electrochemical contribution characteristic data of pollutants, establish the action space of electrochemical inversion regulation parameters and generate action space data of electrochemical inversion regulation parameters; Step S4: Perform multi-condition purification behavior prediction feature analysis on the spatial data of the effect of electrochemical inversion control parameters to generate multi-condition purification behavior prediction feature data. Step S5: Obtain target data for calcium hardness and alkalinity removal in circulating water; Intelligent control parameters for electrochemical purification of circulating water were designed based on the target demand data for calcium hardness and alkalinity removal in circulating water and the predictive characteristic data of purification behavior under multiple operating conditions.

2. The electrochemical purification optimization method for analyzing the calcium hardness and alkalinity removal rate data of circulating water according to claim 1, characterized in that, Step S1 includes the following steps: Step S11: Obtain the initial electrochemical control parameters of the circulating water system; Step S12: Use the circulating water multi-source sensing and acquisition equipment to perform multi-source collaborative sensing and acquisition of circulating water in the circulating water system, and generate raw observation data of circulating water multi-source; Step S13: Analyze the distribution of circulating water attributes based on the original observation data of multiple sources of circulating water to generate multi-source distribution data of circulating water; Step S14: Analyze the electrochemical behavior characteristics of circulating water based on the multi-source distribution data of circulating water according to the initial electrochemical control parameters, and generate electrochemical behavior characteristic data of circulating water. Step S15: Analyze the multi-source state characteristics of circulating water using multi-source distribution data and electrochemical behavior characteristic data of circulating water, and generate multi-source state characteristic distribution data of circulating water.

3. The electrochemical purification optimization method for analyzing the calcium hardness and alkalinity removal rate data of circulating water according to claim 2, characterized in that, The circulating water multi-source sensing and acquisition equipment mentioned in step S12 includes a circulating water electrochemical sensor and a water quality multi-parameter monitoring device.

4. The electrochemical purification optimization method for analyzing the calcium hardness and alkalinity removal rate data of circulating water according to claim 2, characterized in that, Step S13 includes the following steps: Step S131: Perform multi-source attribute coding on the raw observation data of circulating water to generate multi-source attribute coded data of circulating water; Step S132: Analyze the distribution characteristics of sensing nodes based on the original multi-source observation data of circulating water to generate circulating water observation sensing distribution characteristic data; Step S133: Analyze the distribution of circulating water attributes by using circulating water observation and sensing distribution characteristic data to generate circulating water multi-source attribute coding data.

5. The electrochemical purification optimization method for analyzing the calcium hardness and alkalinity removal rate data of circulating water according to claim 1, characterized in that, Step S2 includes the following steps: Step S21: Based on the multi-source state characteristic distribution data of circulating water, perform multi-target pollutant feature identification processing to generate multi-target pollutant feature data; Step S22: Design the electrochemical reaction pathway diagram structure of multi-target pollutants based on the feature data of multi-target pollutants, and generate pollutant reaction pathway diagram structure data; Step S23: Perform coupling and interaction relationship feature analysis on the multi-target pollutant feature data to generate pollutant coupling and interaction relationship feature data; Step S24: Analyze the electrochemical reaction coupling relationship characteristics of pollutants using the pollutant reaction path diagram structure data, and generate pollutant electrochemical reaction coupling relationship characteristic data. Step S25: Based on the characteristic data of the electrochemical reaction coupling relationship of pollutants and the structural data of the reaction path diagram of pollutants, decouple the electrochemical reactions of pollutants to generate decoupled data of electrochemical reactions of pollutants. Step S26: Analyze the electrochemical contribution characteristics of pollutants using the electrochemical reaction coupling relationship characteristic data and the electrochemical reaction decoupling data of pollutants, and generate the electrochemical contribution characteristic data of pollutants.

6. The electrochemical purification optimization method for analyzing the calcium hardness and alkalinity removal rate data of circulating water according to claim 5, characterized in that, The multi-target pollutant characteristic data in step S21 includes calcium hardness alkalinity pollutant characteristic data, turbidity factor characteristic data, and residual chlorine factor characteristic data.

7. The electrochemical purification optimization method for analyzing the calcium hardness and alkalinity removal rate data of circulating water according to claim 5, characterized in that, Step S22 includes the following steps: Step S221: Perform electrochemical reaction node feature analysis on the multi-target pollutant feature data to generate pollutant electrochemical reaction node feature data; Step S222: Perform time-intensity relationship analysis on the electrochemical reaction nodes of pollutants based on the multi-target pollutant characteristic data, and generate time-intensity relationship data of pollutant reaction nodes; Step S223: Design the directed weighted electrochemical reaction path diagram structure of pollutants based on the time-intensity relationship data of the pollutant reaction nodes, and generate pollutant reaction path diagram structure data.

8. The electrochemical purification optimization method for analyzing the calcium hardness and alkalinity removal rate data of circulating water according to claim 1, characterized in that, Step S3 includes the following steps: Step S31: Perform electrochemical characterization analysis on the electrochemical contribution characteristic data of pollutants to generate electrochemical characterization data; Step S32: Construct the electrochemical regulation parameter space based on the electrochemical interaction state characterization data to generate electrochemical regulation parameter space data; Step S33: Based on the electrochemical action state characterization data and the spatial data of electrochemical regulation parameters, perform the mapping relationship analysis between electrochemical action state and action to generate electrochemical action state-action mapping relationship data; Step S34: Perform response characteristic analysis on the electrochemical action state-action mapping relationship data to generate electrochemical action state-action response characteristic data; Step S35: Perform iterative inversion processing of electrochemical action-driven regulation parameters using electrochemical action state-action response characteristic data to generate electrochemical action-regulation parameter inversion data; Step S36: Based on the electrochemical action-regulation parameter inversion data, establish the action space of the electrochemical inversion regulation parameters and generate the action space data of the electrochemical inversion regulation parameters.

9. The electrochemical purification optimization method for analyzing the calcium hardness and alkalinity removal rate data of circulating water according to claim 1, characterized in that, Step S4 includes the following steps: Step S41: Based on the spatial data of the effect of the electrochemical inversion control parameters, perform simulation processing of the circulating water effect of the electrochemical inversion control parameters to generate simulation data of the circulating water effect of the inversion control parameters; Step S42: Perform electrochemical purification-driven stage constraint embedding processing on the simulation data of the inversion control parameter circulating water effect to generate constrained inversion control parameter circulating water effect simulation data; Step S43: Based on the spatial data of the effects of the electrochemical inversion control parameters, perform temporal perturbation scenario analysis of the inversion control parameters to generate temporal perturbation scenario data of the inversion control parameters; Step S44: Perform circulating water purification evolution processing of the inverted control parameters using the time-series disturbance scenario data of the inverted control parameters and the simulation data of the circulating water effect of the constrained inverted control parameters, and generate circulating water purification evolution data of the inverted control parameters. Step S45: Perform multi-condition purification behavior prediction feature analysis based on the inversion control parameters and circulating water purification evolution data to generate multi-condition purification behavior prediction feature data.

10. The electrochemical purification optimization method for analyzing the calcium hardness and alkalinity removal rate data of circulating water according to claim 1, characterized in that, Step S5 includes the following steps: Step S51: Obtain target data for calcium hardness and alkalinity removal in circulating water; Step S52: Perform multi-objective optimization analysis on the target requirement data for calcium hardness and alkalinity removal in circulating water to generate multi-objective optimization analysis data for electrochemical purification of circulating water; Step S53: Perform global search processing of circulating water electrochemical purification parameters based on the multi-objective optimization analysis data and multi-condition purification behavior prediction feature data of circulating water electrochemical purification, and generate global search data of circulating water electrochemical purification parameters. Step S54: Design intelligent control parameters for circulating water electrochemical purification based on global search data of circulating water electrochemical purification parameters.

Images