Electrochemical reactor and method based on dynamic regulation of flow field and electric field

Abstract

The application discloses an electrochemical reactor and method based on dynamic regulation of flow field and electric field, relates to the field of electrochemical water treatment, and comprises a tool main body, electrolytic cell pipes and a regulation component. Two water inlet pipes and a water outlet pipe are symmetrically arranged inside the tool main body. The number of electrolytic cell pipes is several, and the electrolytic cell pipes are used for electrochemical reaction treatment through an electric field and flow field control system. At least one pair of anode and cathode is packaged inside each electrolytic cell pipe. The electrolytic cell pipes are uniformly arranged between the water inlet pipes and the water outlet pipe. The water inlet pipes and the water outlet pipe are both connected with the electrolytic cell pipes. The application realizes the dynamic optimization of electric field parameters and flow field parameters, ensures that no matter how the water inlet condition fluctuates, the system can automatically adjust each electrolytic cell pipe to the optimal working point, makes the system always run in a high-efficiency and stable state, and greatly improves the removal efficiency of pollutants, the current efficiency and the fault tolerance rate of the treatment process.

Description

Technical Field

[0001] This invention relates to the field of electrochemical water treatment technology, specifically to an electrochemical reactor and method based on dynamic control of flow field and electric field. Background Technology

[0002] With increasingly stringent environmental regulations, electrochemical technology, due to its environmental friendliness and the elimination of the need for chemical reagents, has shown great potential in treating recalcitrant organic matter and recovering heavy metals. However, in practical industrial applications, especially when treating wastewater with complex composition and large fluctuations in flow rate or concentration, the treatment efficiency and operational stability of reactors face severe challenges. Traditional electrochemical reactors typically employ fixed or simply segmented operating parameters, making it difficult to adapt to dynamically changing influent conditions. This leads to both overtreatment and undertreatment, resulting in energy waste, accelerated electrode wear, and substandard treatment effects.

[0003] Most existing technologies focus only on the independent adjustment of electric or flow fields, lacking a synergistic consideration of electric field, flow field, and water quality, thus failing to achieve overall optimization. Existing systems are usually based on fixed thresholds or simple feedback for control, unable to predict and proactively adjust for impending influent fluctuations or reaction processes, resulting in delayed control response, poor system stability, lack of systematic optimization and long-term planning, and lack of continuous planning for multiple future operating cycles. This easily leads to frequent and drastic parameter adjustments, which not only increase equipment wear and tear but also fail to achieve global optimization of long-term energy consumption, efficiency, and stability. Summary of the Invention

[0004] (a) Technical problems to be solved

[0005] In view of the above-mentioned shortcomings of the prior art, the present invention provides an electrochemical reactor and method based on dynamic control of flow field and electric field, which can effectively solve the problems of the prior art.

[0006] (II) Technical Solution

[0007] To achieve the above objectives, the present invention provides the following technical solution:

[0008] In a first aspect, this invention discloses an electrochemical reactor based on dynamic control of flow field and electric field, comprising a tooling body, an electrolytic cell tube, and a control component. The tooling body has two symmetrically arranged inlet pipes and an outlet pipe. The electrolytic cell tubes are numerous and used for electrochemical reaction processing via an electric field and flow field control system. Each electrolytic cell tube internally encapsulates at least one pair of anodes and cathodes, and the electrode surfaces can be loaded with a catalytic coating. The electrolytic cell tubes are uniformly arranged between the inlet pipes and the outlet pipes, and both the inlet and outlet pipes are connected to the electrolytic cell tubes. The control component is installed on the surface of the electrolytic cell tubes, and a sub-module is deployed below the control component, including:

[0009] The data acquisition unit is used to collect flow field, electric field, water quality and electrode state parameters in real time through sensors, providing a data foundation for subsequent model building and intelligent control;

[0010] The fluid simulation modeling module is used to construct a fluid simulation model that reflects the flow field distribution, velocity, and pressure drop within the system based on the flow rate and pressure data collected from the flow field parameters.

[0011] The electric field simulation modeling module is used to construct an electric field distribution simulation model that reflects the electric field intensity distribution and current density distribution within the system based on the current and voltage data and electrode physical parameters in the collected electric field parameters. When constructing the model, the electrodes are regarded as domains with specific boundary conditions. The model parameters, such as conductivity and double-layer capacitance, can be dynamically calibrated according to the electrode potential drift and impedance spectrum change data obtained by the acquisition unit to reflect the aging, contamination or passivation state of the electrodes.

[0012] The control and analysis module is used to pre-build a simulation identification model. In each control cycle, the model takes the current processing capacity attributes of each electrolyzer tube, the changes in the water quality data it processes, and the electrode status information as inputs. The model outputs the current density and voltage adjustment parameters, as well as the flow rate and pressure adjustment parameters for each electrolyzer tube in the next cycle. The electrodes in each electrolyzer tube adopt a parallel plate, mesh, or porous three-dimensional structure. The electrodes are connected to the power supply and acquisition unit circuit through independent pluggable interfaces. The processing capacity attributes include not only the electrolyzer tube structural parameters, but also the effective active area of ​​the electrode, coating type and thickness, and historical polarization curve characteristics of the electrode.

[0013] The simulation verification module is used to input current density and voltage adjustment parameters into the electric field simulation modeling module for simulation, simulate the changes in the adjusted electric field and current density distribution, and generate power supply adjustment feedback including the expected electrode reaction rate and side reaction risk; and input flow rate and pressure adjustment parameters into the fluid simulation modeling module for simulation, simulate the changes in the adjusted flow field distribution and mass transfer conditions, and generate fluid adjustment feedback including the expected hydraulic residence time and pollutant mass transfer efficiency.

[0014] The evaluation and execution module is used to comprehensively evaluate various adjustment parameters, generate the optimal multi-cycle execution trajectory, and drive the field equipment to execute.

[0015] Furthermore, the acquisition unit is equipped with sub-modules, including a fluid acquisition module, an electric field acquisition module, and a water quality acquisition module, wherein:

[0016] The fluid acquisition module is used to collect inlet and outlet flow rates in each electrolytic cell tube in real time, as well as pressure data inside the tube section or at the inlet and outlet.

[0017] The electric field acquisition module is used to collect the operating current, voltage, and cell voltage data between the electrodes of each electrolytic cell tube in real time.

[0018] The water quality acquisition module is used to acquire water quality data in real time and obtain electrode surface status information through water quality sensing components deployed inside or at the inlet and outlet of each electrolysis cell tube. The water quality sensing components include pH sensors, redox potential sensors, conductivity sensors and specific ion selective electrodes, which are used to comprehensively characterize the reaction process and the quality of the effluent.

[0019] Furthermore, the working logic of the fluid simulation modeling module is as follows:

[0020] The system receives in-time inlet and outlet flow and pressure data from each electrolytic cell tube in the acquisition unit, and performs filtering and validity verification.

[0021] Based on the actual physical layout, pipe size and connection relationship of the electrolytic cell tube array, the geometric domain of the simulation calculation is defined, and the collected real-time flow and pressure data are used as dynamic boundary condition inputs.

[0022] Computational fluid dynamics was used to simulate the steady-state or transient flow field distribution, velocity profile, and pressure field inside the electrolytic cell tube and connecting pipelines within the geometric domain.

[0023] From the simulation results, the average flow velocity, hydraulic residence time, wall shear force, and flow field uniformity index in each electrolytic cell tube were extracted.

[0024] The simulated parameters, such as outlet pressure, are compared with measured data, and the model parameters are fine-tuned using an inversion algorithm to ensure that the simulation model continuously approximates the actual flow field state.

[0025] Furthermore, the working logic of the electric field simulation modeling module is as follows:

[0026] It receives real-time data on the operating current, voltage, and cell voltage of each electrolytic cell tube from the acquisition unit, and integrates the geometric dimensions, arrangement, and material conductivity parameters of the electrodes in the electrolytic cell tube.

[0027] Based on the actual structure of the electrolytic cell tube, a simulation domain including electrodes and electrolyte solution is constructed. The collected voltage or current data is set as the electric field boundary condition, and the conductivity properties of the electrolyte solution are correlated with real-time water quality data.

[0028] By solving Maxwell's equations, the potential distribution, electric field intensity distribution, and current density distribution in the simulation domain are calculated.

[0029] The calculated local current density distribution is correlated with preset electrode reaction kinetic parameters to evaluate the electrochemical reaction rate, overpotential, and side reaction tendency in different regions of each electrode surface.

[0030] The simulation-predicted total current or voltage is compared with the measured values, and the electrode potential or impedance information obtained by the acquisition unit is used to iteratively correct the reaction kinetic parameters of the electrode interface, so as to improve the model's tracking accuracy of the electrode state evolution.

[0031] Furthermore, the construction process of the simulation recognition model in the regulation and analysis module is as follows:

[0032] Collect time-series datasets of each electrolyzer tube during historical operating cycles. The datasets include input features and target labels. The input features include: the initial self-processing capacity attribute vector of each electrolyzer tube in each cycle, the inlet and outlet water quality data vectors and their changes, the electrode state parameter vector, and the current, voltage, flow rate, and pressure parameters of the previous cycle. The target labels are the optimal current, voltage, flow rate, and pressure parameters actually used in the next cycle after optimization and verification.

[0033] A deep neural network was chosen as the model's infrastructure. This network includes a shared feature extraction layer for learning common high-order patterns in the input features. It is then divided into two parallel task-specific branch networks, which are used to regress and predict the current and voltage adjustment parameters and the flow and pressure adjustment parameters for the next cycle, respectively.

[0034] The constructed network model was trained under supervision using a time-series dataset. During training, a sliding time window method was used to divide the training set and the validation set to simulate time-series dependencies. The loss function was the weighted mean square error between the predicted values ​​of the two task branches and the true labels, and an L2 regularization term was added to prevent overfitting. The network weights were optimized using the backpropagation algorithm.

[0035] Furthermore, the evaluation execution module has sub-modules deployed below it, including an adjustment evaluation module, a trajectory planning module, and a dynamic execution module. The adjustment evaluation module interacts with the trajectory planning module and the dynamic execution module via a wireless network, wherein:

[0036] The adjustment evaluation module is used to evaluate the power adjustment feedback and fluid adjustment feedback of the simulation verification module in combination with several preset performance indicators, including energy consumption indicators. It calculates the adjustment cost of each adjustment and selects the feedback scheme with the lowest adjustment cost as the basis for execution.

[0037] The trajectory planning module integrates the adjustment feedback results of multiple continuous control cycles to generate a continuous adjustment trajectory that combines the power supply adjustment parameters and fluid adjustment parameters of each electrolytic cell tube within a specified number of future cycles. The model predictive control algorithm is used to minimize the total adjustment cost within multiple future cycles as the optimization objective. Under the condition of meeting the safety upper and lower limits of the process parameters of each electrolytic cell tube, the optimal continuous adjustment trajectory is solved in a rolling manner.

[0038] The dynamic execution module is used to send the continuous adjustment trajectory to the corresponding designated electrolytic cell tube, drive its power supply and fluid control system to perform the adjustment, and realize the coordinated dynamic optimization control of the flow field and electric field.

[0039] Furthermore, the formula for calculating the adjustment cost of each adjustment in the adjustment evaluation module is as follows:

[0040] ;

[0041] In the formula, This represents the overall adjustment cost; the smaller the value, the better the solution. This represents the adjusted system predicted energy consumption. This represents the preset minimum energy consumption threshold. This represents the preset maximum energy consumption threshold. This represents the adjusted predicted pollutant removal rate. This represents the preset target removal rate. This represents the adjusted predicted electrode wear rate. Represents the baseline loss rate. Represents the maximum permissible loss rate. This represents the adjustment range of the current or voltage parameter. This represents the adjustment range of the flow rate or pressure parameter. This represents the maximum permissible adjustment range of a current or voltage system. This represents the maximum allowable adjustment range of the fluid control system. , , , and These represent the corresponding weight coefficients.

[0042] Furthermore, the acquisition unit is interconnected with the fluid simulation modeling module and the electric field simulation modeling module via a wireless network, the control and analysis module is interconnected with the fluid simulation modeling module, the electric field simulation modeling module and the simulation verification module via a wireless network, and the simulation verification module is interconnected with the evaluation execution module via a wireless network.

[0043] Secondly, the present invention provides an electrochemical reaction method based on dynamic control of flow field and electric field, comprising the following steps:

[0044] Step 1: Real-time acquisition of fluid flow rate and pressure data, input current and voltage data, and water quality characterization data in each electrolytic cell tube arranged sequentially in the electrochemical reactor;

[0045] Step 2: Based on the collected flow and pressure data, construct and update in real time a dynamic fluid simulation model describing the fluid distribution state inside the reactor; based on the collected current and voltage data, construct and update in real time a dynamic electric field distribution simulation model describing the electric field distribution state inside the reactor.

[0046] Step 3: In each control cycle, the inherent processing capacity attributes of each electrolytic cell tube in the current cycle and the changing trend of the water quality data it processes are used as input. The simulation identification model is used for analysis and calculation, and the suggested parameters for adjusting the current and voltage of each electrolytic cell tube in the next cycle, as well as the suggested parameters for adjusting the water flow rate and pressure, are output respectively.

[0047] Step 4: Input the current and voltage adjustment suggestions into the dynamic electric field distribution simulation model for simulation adjustment to obtain power supply adjustment feedback; input the flow rate and pressure adjustment suggestions into the dynamic fluid simulation model for simulation adjustment to obtain fluid adjustment feedback; based on preset evaluation indicators including energy consumption indicators, evaluate the power supply adjustment feedback and fluid adjustment feedback respectively, and calculate their respective comprehensive adjustment costs;

[0048] Step 5: Compare the comprehensive adjustment costs corresponding to the power supply adjustment feedback and the fluid adjustment feedback, and select the adjustment scheme with the lowest adjustment cost as the final execution scheme for the current cycle;

[0049] Step 6: Integrate the final execution plan of multiple consecutive control cycles to form a continuous adjustment trajectory of each electrolytic cell tube in terms of power supply parameters and fluid parameters within a specified number of future cycles, and send the adjustment trajectory to the corresponding electrolytic cell tube actuator for real-time dynamic control.

[0050] Furthermore, the adjustment trajectory in step 6 is planned using a model predictive control algorithm, and the planning process includes:

[0051] The optimization objective is to minimize the overall system operating cost over a continuous period of time in the future. The operating cost is calculated by comprehensively considering the multiple evaluation indicators.

[0052] At the beginning of each control cycle, based on the latest system state and the dynamic simulation model, the optimal adjustment parameter sequence for multiple future control cycles is predicted and solved in a rolling manner.

[0053] In the entire sequence of adjustment parameters obtained by the solution, only the optimal adjustment parameter corresponding to the first control cycle is used as the actual execution instruction for the current cycle;

[0054] When entering the next regulation cycle, the solution process is repeated, and prediction and rolling optimization are performed again.

[0055] (III) Beneficial Effects

[0056] Compared with the known prior art, the technical solution provided by this invention has the following beneficial effects:

[0057] 1. By collecting real-time flow field, electric field, and water quality data and constructing a dynamic simulation model, the actual internal state of the reactor is accurately revealed. Through intelligent decision-making and model predictive control, the coordinated dynamic optimization of electric field parameters and flow field parameters is achieved. This ensures that no matter how the influent conditions fluctuate, the system can automatically adjust each electrolytic cell tube to the optimal operating point, so that the reactor always operates in a highly efficient and stable state, which greatly improves the removal efficiency of pollutants, current efficiency, and fault tolerance of the treatment process.

[0058] 2. By applying model predictive control algorithms to the planning of adjustment trajectories, the system optimizes future operating conditions. Before each adjustment, the system performs simulation verification and cost assessment in the model, avoiding ineffective or reverse adjustments that may result from experience or simple feedback. By selecting the scheme with the lowest global adjustment cost and performing multi-cycle planning, the system can achieve the processing target with minimal energy input and optimal fluid distribution. At the same time, by optimizing the electric field distribution, the system can effectively mitigate electrode passivation and wear, extend the life of core components, and thus reduce the total life cycle operating cost. Attached Figure Description

[0059] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the accompanying drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are merely some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without any creative effort.

[0060] Figure 1 This is a schematic diagram of the overall three-dimensional structure of the present invention;

[0061] Figure 2 This is a schematic diagram of the control component in this invention;

[0062] Figure 3 This is a schematic diagram of the acquisition unit in this invention;

[0063] Figure 4 This is a schematic diagram of the framework of the evaluation execution module in this invention.

[0064] The labels in the diagram represent: 1. Tooling body; 2. Water inlet pipe; 3. Water outlet pipe; 4. Electrolytic cell pipe; 5. Control components;

[0065] 51. Acquisition Unit; Sub-modules under the acquisition unit include: 11. Fluid Acquisition Module; 12. Electric Field Acquisition Module; 13. Water Quality Acquisition Module;

[0066] 52. Fluid Simulation Modeling Module; 53. Electric Field Simulation Modeling Module; 54. Control Analysis Module; 55. Simulation Verification Module; 56. Evaluation and Execution Module; 61. Adjustment and Evaluation Module; 62. Trajectory Planning Module; 63. Dynamic Execution Module. Detailed Implementation

[0067] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below 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 creative effort are within the scope of protection of the present invention.

[0068] The present invention will be further described below with reference to embodiments.

[0069] The electrochemical reactor in this embodiment, based on dynamic control of the flow field and electric field, such as... Figures 1-4 As shown, the apparatus includes a tooling body 1, an electrolytic cell tube 4, and a control component 5. The tooling body 1 has two symmetrically arranged inlet pipes 2 and outlet pipes 3. Several electrolytic cell tubes 4 are used for electrochemical reaction treatment via an electric field and flow field control system. Each electrolytic cell tube 4 contains at least one pair of anodes and cathodes, and the electrode surfaces can be loaded with a catalytic coating. The electrolytic cell tubes 4 are evenly distributed between the inlet pipes 2 and the outlet pipes 3, and both the inlet pipes 2 and the outlet pipes 3 are connected to the electrolytic cell tubes 4. The control component 5 is installed on the surface of the electrolytic cell tubes 4, and sub-modules are deployed below the control component 5, including:

[0070] Acquisition unit 51 is used to collect flow field, electric field, water quality, and electrode state parameters in real time through sensors, providing a data foundation for subsequent model building and intelligent control. Acquisition unit 51 has sub-modules deployed below it, including a fluid acquisition module 11, an electric field acquisition module 12, and a water quality acquisition module 13, wherein:

[0071] The fluid acquisition module 11 is used to collect inlet and outlet flow rates in each electrolytic cell tube 4 in real time, as well as pressure data inside or at the inlet and outlet of the tube section.

[0072] The electric field acquisition module 12 is used to acquire the working current, voltage and cell voltage data between the electrodes of each electrolytic cell tube 4 in real time.

[0073] The water quality acquisition module 13 is used to acquire water quality data in real time and obtain electrode surface status information through water quality sensing components deployed inside or at the inlet and outlet of each electrolysis cell tube 4. The water quality sensing components include a pH sensor, a redox potential sensor, a conductivity sensor, and a specific ion selective electrode, which are used to comprehensively characterize the reaction process and the effluent water quality.

[0074] The fluid simulation modeling module 52 is used to construct a fluid simulation model reflecting the flow field distribution, velocity, and pressure drop within the system based on the collected flow field parameters, including flow rate and pressure data. The working logic of the fluid simulation modeling module 52 is as follows:

[0075] The system receives in real-time inlet and outlet flow and pressure data from each electrolytic cell tube 4 from the acquisition unit 51, and performs filtering and validity verification.

[0076] Based on the actual physical layout, pipe size and connection relationship of the electrolytic cell tube array, the geometric domain of the simulation calculation is defined, and the collected real-time flow and pressure data are used as dynamic boundary condition inputs.

[0077] Computational fluid dynamics was used to simulate the steady-state or transient flow field distribution, velocity profile, and pressure field inside the electrolytic cell tube 4 and its connecting pipes within the geometric domain.

[0078] From the simulation results, the average flow velocity, hydraulic residence time, wall shear force, and flow field uniformity index in each electrolytic cell tube 4 were extracted.

[0079] The simulated parameters, such as outlet pressure, are compared with measured data, and the model parameters are fine-tuned using an inversion algorithm to ensure that the simulation model continuously approximates the actual flow field state.

[0080] The electric field simulation modeling module 53 is used to construct an electric field distribution simulation model reflecting the electric field intensity distribution and current density distribution within the system based on the current and voltage data and electrode physical parameters collected in the electric field parameters. When constructing the model, the electrodes are considered as domains with specific boundary conditions. Their model parameters, such as conductivity and double-layer capacitance, can be dynamically calibrated based on the electrode potential drift and impedance spectrum change data acquired by the acquisition unit 51 to reflect the aging, contamination, or passivation state of the electrodes. The working logic of the electric field simulation modeling module 53 is as follows:

[0081] The system receives real-time data on the operating current, voltage, and cell voltage of each electrolytic cell tube 4 from the acquisition unit 51, and integrates the geometric dimensions, arrangement, and material conductivity parameters of the electrodes in the electrolytic cell tube 4.

[0082] Based on the actual structure of the electrolytic cell tube 4, a simulation domain containing electrodes and electrolyte solution is constructed. The collected voltage or current data is set as the electric field boundary condition, and the conductivity properties of the electrolyte solution are correlated with the real-time water quality data.

[0083] By solving Maxwell's equations, the potential distribution, electric field intensity distribution, and current density distribution in the simulation domain are calculated.

[0084] The calculated local current density distribution is correlated with preset electrode reaction kinetic parameters to evaluate the electrochemical reaction rate, overpotential, and side reaction tendency in different regions of each electrode surface.

[0085] The simulated total current or voltage is compared with the measured value, and the electrode potential or impedance information obtained by the acquisition unit 51 is used to iteratively correct the reaction kinetic parameters of the electrode interface, so as to improve the model's tracking accuracy of the electrode state evolution.

[0086] The control and analysis module 54 is used to pre-build a simulation identification model. In each control cycle, the model takes the current processing capacity attributes of each electrolytic cell tube 4, the changes in the water quality data it processes, and the electrode status information as inputs. The model outputs the current density and voltage adjustment parameters, as well as the flow rate and pressure adjustment parameters for each electrolytic cell tube 4 in the next cycle. The electrodes in each electrolytic cell tube 4 adopt a parallel plate, mesh, or porous three-dimensional structure. The electrodes are connected to the power supply and acquisition unit 51 circuit through independent pluggable interfaces. The processing capacity attributes include not only the structural parameters of the electrolytic cell tube 4, but also the effective active area of ​​the electrode, the coating type and thickness, and the characteristics of the electrode's historical polarization curve.

[0087] The simulation verification module 55 is used to input the current density and voltage adjustment parameters into the electric field simulation modeling module 53 for simulation, simulate the changes in the adjusted electric field and current density distribution, and generate power supply adjustment feedback including the expected electrode reaction rate and side reaction risk; and input the flow rate and pressure adjustment parameters into the fluid simulation modeling module 52 for simulation, simulate the changes in the adjusted flow field distribution and mass transfer conditions, and generate fluid adjustment feedback including the expected hydraulic residence time and pollutant mass transfer efficiency.

[0088] The evaluation and execution module 56 is used to comprehensively evaluate various adjustment parameters, generate the optimal multi-cycle execution trajectory, and drive the field equipment to execute. Sub-modules are deployed under the evaluation and execution module 56, including an adjustment evaluation module 61, a trajectory planning module 62, and a dynamic execution module 63. The adjustment evaluation module 61 interacts with the trajectory planning module 62 and the dynamic execution module 63 via a wireless network.

[0089] The adjustment evaluation module 61 is used to evaluate the power supply adjustment feedback and fluid adjustment feedback of the simulation verification module 55, combined with several preset performance indicators, including energy consumption indicators. It calculates the adjustment cost of each adjustment and selects the feedback scheme with the lowest adjustment cost as the execution basis. The calculation formula for the adjustment cost of each adjustment in the adjustment evaluation module 61 is as follows:

[0090] ;

[0091] In the formula, This represents the overall adjustment cost; the smaller the value, the better the solution. This represents the adjusted system predicted energy consumption. This represents the preset minimum energy consumption threshold. This represents the preset maximum energy consumption threshold. This represents the adjusted predicted pollutant removal rate. This represents the preset target removal rate. This represents the adjusted predicted electrode wear rate. Represents the baseline loss rate. Represents the maximum permissible loss rate. This represents the adjustment range of the current or voltage parameter. This represents the adjustment range of the flow rate or pressure parameter. This represents the maximum permissible adjustment range of a current or voltage system. This represents the maximum allowable adjustment range of the fluid control system. , , , and These represent the corresponding weight coefficients;

[0092] The adjustment ranges for energy consumption, removal rate, electrode loss, and various factors such as current, voltage, flow rate, and pressure are linearly normalized using preset safe operating ranges or target values, transforming them into dimensionless values ​​between 0 and 1, thereby eliminating the incomparability of different physical dimensions. Subsequently, based on real-time operating conditions and optimization objectives, the system dynamically assigns corresponding weight coefficients to each factor, multiplies the normalized scores of each factor by their weights, and sums them to obtain a comprehensive adjustment cost score. The smaller this score, the better the overall performance of the adjustment scheme after comprehensively balancing energy efficiency, treatment effect, equipment lifespan, and control stability. This provides a clear basis for the decision-making module to select the adjustment scheme with the lowest cost and highest overall benefits.

[0093] The trajectory planning module 62 is used to integrate the adjustment feedback results of multiple continuous control cycles and generate a continuous adjustment trajectory that combines the power supply adjustment parameters and fluid adjustment parameters of each electrolytic cell tube 4 within a specified number of future cycles. The model predictive control algorithm is used to minimize the total adjustment cost within multiple future cycles as the optimization objective. Under the condition of meeting the safety upper and lower limit constraints of the process parameters of each electrolytic cell tube 4, the optimal continuous adjustment trajectory is solved in a rolling manner.

[0094] The dynamic execution module 63 is used to send the continuous adjustment trajectory to the corresponding designated electrolytic cell tube 4, drive its power supply and fluid control system to perform the adjustment, and realize the coordinated dynamic optimization control of the flow field and electric field.

[0095] The acquisition unit 51 is interconnected with the fluid simulation modeling module 52 and the electric field simulation modeling module 53 via a wireless network. The control and analysis module 54 is interconnected with the fluid simulation modeling module 52, the electric field simulation modeling module 53 and the simulation verification module 55 via a wireless network. The simulation verification module 55 is interconnected with the evaluation and execution module 56 via a wireless network.

[0096] Compared with existing technologies, it breaks through the limitations of traditional static or single-variable control, and can dynamically and collaboratively optimize multiple parameters such as flow rate, pressure, current, and voltage. While ensuring the treatment effect, it reduces the overall energy consumption of the system and improves the adaptability to different water quality fluctuations and the overall operational stability.

[0097] At other levels, this embodiment provides an electrochemical reaction method based on dynamic control of flow and electric fields, including the following steps:

[0098] Step 1: Real-time acquisition of fluid flow rate and pressure data, input current and voltage data, and water quality characterization data in each electrolytic cell tube 4 arranged in sequence in the electrochemical reactor;

[0099] Step 2: Based on the collected flow and pressure data, construct and update in real time a dynamic fluid simulation model describing the fluid distribution state inside the reactor; based on the collected current and voltage data, construct and update in real time a dynamic electric field distribution simulation model describing the electric field distribution state inside the reactor.

[0100] Step 3: In each control cycle, the inherent processing capacity attributes of each electrolytic cell tube 4 in the current cycle and the changing trend of the water quality data it processes are used as input. The simulation identification model is used for analysis and calculation, and the suggested parameters for adjusting the current and voltage of each electrolytic cell tube 4 in the next cycle, as well as the suggested parameters for adjusting the water flow rate and pressure, are output respectively.

[0101] Step 4: Input the suggested parameters for current and voltage adjustment into the dynamic electric field distribution simulation model for simulation adjustment to obtain power supply adjustment feedback; input the suggested parameters for flow and pressure adjustment into the dynamic fluid simulation model for simulation adjustment to obtain fluid adjustment feedback; based on preset evaluation indicators including energy consumption indicators, evaluate the power supply adjustment feedback and fluid adjustment feedback respectively, and calculate their respective comprehensive adjustment costs.

[0102] Step 5: Compare the comprehensive adjustment costs corresponding to the power supply adjustment feedback and the fluid adjustment feedback, and select the adjustment scheme with the lowest adjustment cost as the final execution scheme for the current cycle;

[0103] Step 6: Integrate the final execution plan for multiple consecutive control cycles to form a continuous adjustment trajectory for each electrolytic cell tube 4 in terms of power supply and fluid parameters within a specified number of future cycles. This adjustment trajectory is then sent to the corresponding electrolytic cell tube 4 actuator for real-time dynamic control. The adjustment trajectory is planned using a model predictive control algorithm. The planning process includes:

[0104] The optimization objective is to minimize the overall system operating cost over a continuous period of time in the future. The operating cost is calculated by comprehensively considering multiple evaluation indicators.

[0105] At the beginning of each control cycle, based on the latest system state and dynamic simulation model, the optimal adjustment parameter sequence for multiple future control cycles is predicted and solved in a rolling manner.

[0106] In the entire sequence of adjustment parameters obtained by the solution, only the optimal adjustment parameter corresponding to the first control cycle is used as the actual execution instruction for the current cycle;

[0107] When entering the next control cycle, the solution process is repeated. That is, based on the latest collected system state data, prediction and rolling optimization are performed again, so as to incorporate the changes and uncertainties of the system state into the continuous decision-making and achieve dynamic optimal control.

[0108] This embodiment provides a process for constructing a simulated recognition model, specifically as follows:

[0109] Collect time-series datasets of each electrolyzer tube 4 during historical operating cycles. The datasets include input features and target labels. Input features include: the initial self-processing capacity attribute vector of each electrolyzer tube 4 in each cycle, the inlet and outlet water quality data vectors and their changes, the electrode state parameter vector, and the current, voltage, flow rate, and pressure parameters of the previous cycle. The target labels are the optimal current, voltage, flow rate, and pressure parameters actually used in the next cycle after optimization and verification.

[0110] A deep neural network was chosen as the model's infrastructure. This network includes a shared feature extraction layer for learning common high-order patterns in the input features. It is then divided into two parallel task-specific branch networks, which are used to regress and predict the current and voltage adjustment parameters and the flow and pressure adjustment parameters for the next cycle, respectively.

[0111] The constructed network model was trained under supervision using a time-series dataset. During training, a sliding time window method was used to divide the training set and the validation set to simulate time-series dependencies. The loss function was the weighted mean square error between the predicted values ​​of the two task branches and the true labels, and an L2 regularization term was added to prevent overfitting. The network weights were optimized using the backpropagation algorithm.

[0112] After completing the initial supervised training, the model is placed in a simulation environment composed of the fluid simulation modeling module 52 and the electric field simulation modeling module 53. It is used as an agent for reinforcement learning fine-tuning. The state of the agent is the current state of the simulation environment, and the action is the adjustment parameter suggestion output by the model. The reward function is constructed based on multiple performance indicators in the adjustment evaluation module 61. Through the policy gradient method, the model learns to explore and generate control strategies that can obtain higher long-term cumulative rewards in the simulation environment, thereby overcoming the limitations of historical data and achieving better global dynamic optimization capabilities.

[0113] The trained and fine-tuned model is deployed to the regulation and analysis module 54. During system operation, the model periodically uses new actual operating data and corresponding optimization decision results to perform incremental learning, thereby realizing online adaptive updates of the model to track long-term changes such as system characteristic drift and electrode aging.

[0114] In summary, in this invention, the water source to be treated enters the electrolytic cell tube 4 through the water inlet pipe 2, the working strategy of the electrolytic cell tube 4 is set by the control component 5, and the treated water source is discharged through the water outlet pipe 3.

[0115] This invention constructs a high-fidelity simulation model of dynamically updated flow field and electric field, enabling operators to understand the real reaction environment inside each electrolytic cell tube 4. By introducing a control component 5, and taking the properties of the electrolytic cell tube 4 and the dynamic changes in water quality as input, a personalized control scheme is generated. This breaks through the traditional single-point control mode. The control suggestions are not directly executed, but need to be verified in the digital space first. After comprehensively evaluating multiple indicators such as energy consumption and efficiency, the optimal solution is selected, which greatly avoids the blindness and risk of actual adjustment.

[0116] The system not only performs single-step optimal adjustments, but also integrates multi-cycle schemes to form a continuous adjustment trajectory. Combined with model predictive control, it achieves optimal dynamic planning and rolling optimization of the process, giving the entire system strong anti-interference capabilities and adaptability to water quality fluctuations. While ensuring treatment effects, it minimizes overall operating costs, providing a systematic solution for the intelligent operation of electrochemical reactor systems.

[0117] The above embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions will not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. An electrochemical reactor based on dynamic regulation of flow field and electric field, characterized in that, The system includes a tooling body, electrolytic cell tubes, and control components. The tooling body has two symmetrically arranged inlet and outlet pipes. Several electrolytic cell tubes are used for electrochemical reaction treatment via an electric field and flow field control system. Each electrolytic cell tube contains at least one pair of anodes and cathodes. The electrolytic cell tubes are evenly distributed between the inlet and outlet pipes, and both the inlet and outlet pipes are connected to the electrolytic cell tubes. The control components are mounted on the surface of the electrolytic cell tubes, and sub-modules are deployed below the control components, including: The data acquisition unit is used to acquire flow field, electric field, water quality and electrode state parameters in real time through sensors; The fluid simulation modeling module is used to construct a fluid simulation model based on the flow rate and pressure data in the collected flow field parameters; The electric field simulation modeling module is used to construct an electric field distribution simulation model based on the current and voltage data and electrode property parameters collected in the electric field parameters. The regulation and analysis module is used to pre-build a simulation identification model. It takes the current processing capacity attributes of each electrolytic cell tube, the changes in the water quality data it processes, and the electrode status information as inputs. The model outputs the current density and voltage adjustment parameters, as well as the flow rate and pressure adjustment parameters for each electrolytic cell tube in the next cycle. The simulation verification module is used to input current density and voltage adjustment parameters into the electric field simulation modeling module to generate power supply adjustment feedback; and to input flow rate and pressure adjustment parameters into the fluid simulation modeling module to generate fluid adjustment feedback. The evaluation and execution module is used to comprehensively evaluate various adjustment parameters, generate the optimal multi-cycle execution trajectory, and drive the field equipment to execute.

2. The electrochemical reactor based on dynamic control of flow field and electric field according to claim 1, characterized in that, The acquisition unit has sub-modules deployed below it, including a fluid acquisition module, an electric field acquisition module, and a water quality acquisition module, wherein: The fluid acquisition module is used to collect inlet and outlet flow rates in each electrolytic cell tube in real time, as well as pressure data inside the tube section or at the inlet and outlet. The electric field acquisition module is used to collect the operating current, voltage, and cell voltage data between the electrodes of each electrolytic cell tube in real time. The water quality acquisition module is used to acquire water quality data in real time and obtain electrode surface status information through water quality sensing components deployed inside or at the inlet and outlet of each electrolytic cell tube.

3. The electrochemical reactor based on dynamic control of flow field and electric field according to claim 1, characterized in that, The working logic of the fluid simulation modeling module is as follows: The system receives in-time inlet and outlet flow and pressure data from each electrolytic cell tube in the acquisition unit, and performs filtering and validity verification. Based on the actual physical layout, pipe size and connection relationship of the electrolytic cell tube array, the geometric domain of the simulation calculation is defined, and the collected real-time flow and pressure data are used as dynamic boundary condition inputs. Within the geometric domain, the steady-state or transient flow field distribution, velocity profile, and pressure field inside the electrolytic cell tube and connecting pipelines are simulated. From the simulation results, the average flow velocity, hydraulic residence time, wall shear force, and flow field uniformity index in each electrolytic cell tube were extracted.

4. The electrochemical reactor based on dynamic control of flow field and electric field according to claim 1, characterized in that, The working logic of the electric field simulation modeling module is as follows: It receives real-time data on the operating current, voltage, and cell voltage of each electrolytic cell tube from the acquisition unit, and integrates the geometric dimensions, arrangement, and material conductivity parameters of the electrodes in the electrolytic cell tube. Based on the actual structure of the electrolytic cell tube, a simulation domain including electrodes and electrolyte solution is constructed. The collected voltage or current data is set as the electric field boundary condition, and the conductivity properties of the electrolyte solution are correlated with real-time water quality data. By solving Maxwell's equations, the potential distribution, electric field intensity distribution, and current density distribution in the simulation domain are calculated. The calculated local current density distribution is correlated with preset electrode reaction kinetic parameters to evaluate the electrochemical reaction rate, overpotential, and side reaction tendency in different regions of each electrode surface.

5. The electrochemical reactor based on dynamic control of flow field and electric field according to claim 1, characterized in that, The construction process of the simulation identification model in the regulation and analysis module is as follows: Collect time-series datasets of each electrolytic cell tube during historical operating cycles. The datasets include input features and target labels. A deep neural network was chosen as the model's infrastructure, which includes a shared feature extraction layer followed by two parallel task-specific branch networks. The constructed network model was trained under supervision using a time-series dataset, and the loss function was the weighted mean square error between the predicted values ​​of the two task branches and the true labels.

6. The electrochemical reactor based on dynamic control of flow field and electric field according to claim 1, characterized in that, The evaluation execution module has sub-modules deployed below it, including an adjustment evaluation module, a trajectory planning module, and a dynamic execution module. The adjustment evaluation module interacts with the trajectory planning module and the dynamic execution module via a wireless network. The adjustment evaluation module is used to evaluate the power adjustment feedback and fluid adjustment feedback of the simulation verification module in combination with several preset performance indicators, including energy consumption indicators. It calculates the adjustment cost of each adjustment and selects the feedback scheme with the lowest adjustment cost as the basis for execution. The trajectory planning module is used to integrate the adjustment feedback results of multiple continuous control cycles and generate a continuous adjustment trajectory that combines the power supply adjustment parameters and fluid adjustment parameters of each electrolytic cell tube within a specified number of future cycles. The dynamic execution module is used to send the continuous adjustment trajectory to the corresponding designated electrolytic cell tube, driving its power supply and fluid control system to perform the adjustment.

7. The electrochemical reactor based on dynamic control of flow field and electric field according to claim 6, characterized in that, The formula for calculating the adjustment cost of each adjustment in the adjustment evaluation module is as follows: ； In the formula, Represents the overall adjustment cost, This represents the adjusted system predicted energy consumption. This represents the preset minimum energy consumption threshold. This represents the preset maximum energy consumption threshold. This represents the adjusted predicted pollutant removal rate. This represents the preset target removal rate. This represents the adjusted predicted electrode wear rate. Represents the baseline loss rate. Represents the maximum permissible loss rate. This represents the adjustment range of the current or voltage parameter. This represents the adjustment range of the flow rate or pressure parameter. This represents the maximum permissible adjustment range of a current or voltage system. This represents the maximum allowable adjustment range of the fluid control system. , , , and These represent the corresponding weight coefficients.

8. The electrochemical reactor based on dynamic control of flow field and electric field according to claim 1, characterized in that, The acquisition unit is interconnected with the fluid simulation modeling module and the electric field simulation modeling module via a wireless network. The control and analysis module is interconnected with the fluid simulation modeling module, the electric field simulation modeling module, and the simulation verification module via a wireless network. The simulation verification module is interconnected with the evaluation and execution module via a wireless network.

9. An electrochemical reaction method based on dynamic control of flow field and electric field, wherein the method is an implementation method of an electrochemical reactor based on dynamic control of flow field and electric field according to any one of claims 1-8, characterized in that, Includes the following steps: Step 1: Real-time acquisition of fluid flow rate and pressure data, input current and voltage data, and water quality characterization data in each electrolytic cell tube arranged sequentially in the electrochemical reactor; Step 2: Based on the collected flow and pressure data, construct and update in real time a dynamic fluid simulation model describing the fluid distribution state inside the reactor; based on the collected current and voltage data, construct and update in real time a dynamic electric field distribution simulation model describing the electric field distribution state inside the reactor. Step 3: In each control cycle, the inherent processing capacity attributes of each electrolytic cell tube in the current cycle and the changing trend of the water quality data it processes are used as input. The simulation identification model is used for analysis and calculation, and the suggested parameters for adjusting the current and voltage of each electrolytic cell tube in the next cycle, as well as the suggested parameters for adjusting the water flow rate and pressure, are output respectively. Step 4: Input the current and voltage adjustment suggestions into the dynamic electric field distribution simulation model for simulation adjustment to obtain power supply adjustment feedback; input the flow rate and pressure adjustment suggestions into the dynamic fluid simulation model for simulation adjustment to obtain fluid adjustment feedback; based on preset evaluation indicators including energy consumption indicators, evaluate the power supply adjustment feedback and fluid adjustment feedback respectively, and calculate their respective comprehensive adjustment costs; Step 5: Compare the comprehensive adjustment costs corresponding to the power supply adjustment feedback and the fluid adjustment feedback, and select the adjustment scheme with the lowest adjustment cost as the final execution scheme for the current cycle; Step 6: Integrate the final execution plan of multiple consecutive control cycles to form a continuous adjustment trajectory of each electrolytic cell tube in terms of power supply parameters and fluid parameters within a specified number of future cycles, and send the adjustment trajectory to the corresponding electrolytic cell tube actuator for real-time dynamic control.

10. The electrochemical reaction method based on dynamic control of flow field and electric field according to claim 9, characterized in that, The adjustment trajectory in step 6 is planned using a model predictive control algorithm. The planning process includes: The optimization objective is to minimize the overall system operating cost over a continuous period of time in the future. The operating cost is calculated by comprehensively considering the multiple evaluation indicators. At the beginning of each control cycle, based on the latest system state and the dynamic simulation model, the optimal adjustment parameter sequence for multiple future control cycles is predicted and solved in a rolling manner. In the entire sequence of adjustment parameters obtained by the solution, only the optimal adjustment parameter corresponding to the first control cycle is used as the actual execution instruction for the current cycle; When entering the next regulation cycle, the solution process is repeated, and prediction and rolling optimization are performed again.

Images