Electrical stimulation biological water body in-situ remediation system and method based on data driving
Through the data-driven electrically stimulating biological water body in situ repair system, the key control parameters are dynamically adjusted, and the problems of environmental complexity and volatility in the pollution repair process of groundwater body in the existing technology are solved, and efficient and sustainable pollutant degradation is achieved. Effect.
Patent Information
- Application Number
- CN202411279059.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-12
- Publication Date
- 2024-11-22
- Estimated Expiration
- 2044-09-12
AI Technical Summary
The existing bioelectrochemical systems face the difficulty of complex hydrological and hydrochemical environments, diverse functional microorganisms, and environmental fluctuations in the process of regulating and optimizing groundwater pollution recovery, which leads to high cost, unsustainable and difficult to achieve a comprehensive response model.
The in-situ repair system of electrically stimulated biological water bodies is adopted based on data-driven. Through the in-situ repair device, data sampling system, data analysis system and equipment operation control system, key control parameters are dynamically adjusted, including temperature, water inlet flow and power supply voltage. Use mathematical analysis models and optimization algorithms to optimize process parameters to achieve automatic adjustment and optimization.
It realizes efficient degradation and purification of groundwater halogenated pollutants, ensures the efficient and sustainable operation of the bioelectric stimulating water body repair system, and adapts to dynamic changes in different environmental scenarios.
Smart Images

Figure CN118993313A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of water body restoration, and in particular to a data-driven, electrically stimulated biological water body in-situ restoration system and method. Background Art
[0002] In the process of water site pollution remediation, bioelectrochemical system / bioelectric stimulation system (BES) has become a competitive alternative due to its excellent degradation efficiency, environmental sustainability and low operating cost. Compared with the open circuit system, weak electrical stimulation can significantly enhance the metabolic activity of electroactive bacteria and significantly increase the degradation rate of pollutants, while almost no degradation ability is observed in the abiotic cathode.
[0003] Microbial electrode respiration technology offers huge sustainable benefits for groundwater remediation. However, the complexity of the hydrological and hydrochemical environment, the heterogeneity of pollution, and the diversity of functional microorganisms significantly increase the difficulty of regulating the BES system. Obtaining the optimal system design and operating characteristics usually requires exhaustive or orthogonal experiments in the laboratory, which is usually costly, labor-intensive, and unsustainable. In addition, it is very challenging to find similar scenarios with matching pollution characteristics, reaction conditions, and hydrogeological environments based on existing research and experience, which makes it very difficult to develop a comprehensive reaction model. It should also be noted that the environmental conditions of the contaminated site are dynamically changing. In order to cope with drastic environmental fluctuations, it is necessary to develop differentiated solutions for different scenarios, and the complex and uncontrollable operating environment determines that it is impossible to provide solutions for all foreseeable and unforeseeable scenarios. Even if a robust strategy system is constructed and more appropriate technical parameter indicators are adopted, the reactor cannot achieve the best degradation effect when the environment fluctuates slightly, because this set of optimal solutions is only the best solution for a single point of environmental conditions. Therefore, in order to obtain good dechlorination effects in terms of efficiency and economy, it is necessary to develop a control system for the dynamic optimization design of the reaction device and process parameters. Summary of the invention
[0004] In view of the defects of the prior art, the purpose of the present invention is to propose a data-driven electro-stimulation biological in-situ water body remediation system and remediation method. The remediation system can rely on data-driven to achieve dynamic adjustment of key control parameters of the in-situ water body remediation device, so as to efficiently degrade and purify halogenated pollutants in groundwater.
[0005] The technical solution of the present invention is as follows:
[0006] A data-driven, electrically stimulated biological in-situ water body remediation system, comprising: an in-situ water body remediation device for in-situ water body remediation, a data sampling system for sampling data on the in-situ water body remediation device, a data analysis system for analyzing the sampled data obtained by the data sampling system, and an equipment operation control system for regulating the system through the analysis data obtained by the data analysis system; wherein the in-situ water body remediation device comprises a dual-chamber bioelectrochemical system reactor in which an anode chamber and a cathode chamber are connected via a proton exchange membrane, a constant temperature control device capable of sensing and regulating the temperature of the cathode chamber, a cathode chamber water inlet flow adjustment device capable of sensing and regulating the water inlet flow of the cathode chamber, a power supply and a power supply voltage regulator capable of regulating the power supply voltage, wherein the anode chamber is provided with a voltage regulator connected to the anode chamber via a proton exchange membrane; An anode electrode is connected to the positive pole of a power supply, and the cathode chamber is provided with a cathode electrode connected to the negative pole of the power supply; the anode chamber is also provided with an anode chamber water inlet and an anode chamber water outlet; the cathode chamber is also provided with a cathode chamber water inlet, a cathode chamber water outlet, a cathode chamber water inlet sampling port for sampling cathode chamber inlet water, a cathode chamber water outlet sampling port for sampling cathode chamber outlet water, and a cathode biofilm sampling port for sampling sludge mixture water samples near the cathode electrode; the data analysis system includes a model module and an output optimization module, wherein the model module contains a mathematical analysis model, the mathematical analysis model is trained according to the sampling data, and the output optimization module calculates the optimal process parameters of the water body in-situ remediation device according to the trained mathematical model.
[0007] In some specific embodiments, the samples from each sampling port are transmitted to the data sampling system by one or more of gravity flow, pressure flow generated by water inflow, and pressure flow generated by a water pump.
[0008] In some specific embodiments, the constant temperature control device includes a thermistor sensor and a power regulator.
[0009] In some specific embodiments, the cathode chamber water inlet flow rate adjustment device includes an ultrasonic flow sensor and a flow regulating valve.
[0010] In some specific embodiments, the data sampling system includes: a temperature sensing device arranged in the constant temperature control device, a flow sensing device arranged in the cathode chamber water inlet flow adjustment device, a water quality detection device capable of detecting water quality parameters of water samples at the cathode chamber water outlet sampling port and the cathode chamber water inlet sampling port, a biological detection device capable of detecting biological information in the water sample at the cathode biofilm sampling port, and a voltage detection device capable of measuring the power supply voltage value.
[0011] In some specific embodiments, the sampling data includes the cathode chamber temperature, the cathode chamber water inlet flow, the water quality parameters of the water sample at the cathode chamber outlet sampling port, the water quality parameters of the water sample at the cathode chamber inlet sampling port, the biological information in the water sample at the cathode biofilm sampling port, and the power supply voltage value.
[0012] In some specific embodiments, the water quality parameters include one or more of pH value, chemical oxygen demand (COD), biochemical oxygen demand (BOD), conductivity, total nitrogen, total phosphorus, ammonia nitrogen, nitrate content, phosphate content, residual chlorine, total chlorine, heavy metal (such as lead, cadmium, mercury, etc.) concentration, hardness and turbidity.
[0013] In some specific embodiments, the water quality detection equipment includes one or more of a pH detector, a spectrophotometer, a digestion reactor, a potassium permanganate titration instrument, a COD rapid tester, a respirometer, a rapid enzyme method or fluorescence quenching method instrument, a conductivity meter, an ion selective electrode method (ISE) or a colorimetric instrument, an X-ray fluorescence spectrometer (XRF), an EDTA titration instrument, a LaMotte 5-EP hardness tester, and a scattered light turbidity meter.
[0014] Among them, the pH detector can obtain the pH value; the spectrophotometer, digestion reactor or potassium permanganate titration instrument can obtain the chemical oxygen demand (COD); the respirometer, rapid enzyme method or fluorescence quenching method instrument can obtain the biochemical oxygen demand (BOD); the conductivity meter can obtain the conductivity; the ion selective electrode method (ISE) or colorimetric instrument can obtain the total nitrogen, total phosphorus, ammonia nitrogen, nitrate, phosphate, residual chlorine and total chlorine content; the X-ray fluorescence spectrometer (XRF) can obtain the concentration of heavy metals (such as lead, cadmium, mercury, etc.); the EDTA titration instrument or LaMotte 5-EP hardness tester can obtain the hardness; the scattered light turbidimeter can obtain the turbidity.
[0015] In some specific embodiments, the biological information includes one or more of the refractive index of water samples containing microorganisms under light of different wavelengths and / or directions, the abundance and uniformity of biological macromolecules (such as proteins, peptides, carbohydrates and lipids), community genome, colony morphological characteristics and quantity.
[0016] In some specific embodiments, the biological detection equipment includes one or more of a stained or non-stained flow cytometer, a MALDI-TOF (Matrix-Assisted Laser Desorption / Ionization Time-of-Flight Mass Spectrometry) mass spectrometer, a high-throughput sequencing instrument, and a plate culture instrument.
[0017] Among them, stained or non-stained flow cytometers can obtain the refractive index under light of different wavelengths and / or different directions; MALDI-TOF mass spectrometers can obtain the flight time of biological macromolecules (such as proteins, peptides, carbohydrates and lipids); high-throughput sequencing instruments can obtain community genomes; and plate culture instruments can separate microorganisms and obtain colony morphological characteristics and quantities.
[0018] Preferably, the biological detection equipment is a flow cytometer and / or a MALDI-TOF mass spectrometer.
[0019] In some specific embodiments, the voltage detection device is one or more of a potentiometer, a voltmeter, a digital multimeter, an oscilloscope, a bridge, a differential amplifier, a precision voltage sensor, an intelligent voltage monitoring system, a power analyzer, a current probe, a voltage divider, and an application-specific integrated circuit (ASIC) with integrated measurement and monitoring functions.
[0020] The voltage detection device measures the power supply voltage. In some specific embodiments, a reference electrode can be set in the cathode chamber, and the power supply voltage can be measured and adjusted by measuring and adjusting the reference electrode voltage instead of measuring and adjusting the power supply voltage.
[0021] The data sampling system and the data analysis system, and the data analysis system and the equipment operation control system, are connected via wired and / or wireless (such as via radio frequency communication, 5G communication, Wi-Fi communication, etc.) signals.
[0022] In some specific embodiments, the mathematical analysis model takes the cathode chamber temperature, the cathode chamber water inlet flow rate, the water quality parameters of the water sample at the cathode chamber water inlet sampling port, the biological information in the water sample at the cathode biofilm sampling port, and the power supply voltage value as input, and takes the water quality parameters of the water sample at the cathode chamber water outlet sampling port as output.
[0023] In some specific embodiments, the output optimization module is based on the trained mathematical analysis model, and obtains the input process parameters, i.e., the optimized process parameters, under the optimal output conditions of the trained mathematical analysis model through an optimization algorithm. The optimized process parameters include the cathode chamber water inlet flow rate, the power supply voltage value, and the cathode chamber temperature.
[0024] In some specific embodiments, the mathematical analysis model includes a linear regression model, a ridge regression model, a random forest model, an extreme learning machine model, a support vector machine model, a decision tree model, a logistic regression model, a Bayesian model, a K-nearest neighbor model, a principal component analysis model, a gradient boosting machine model, a neural network model, a long short-term memory model, a self-organizing map model, a Gaussian process regression model, a Markov chain Monte Carlo model, an XGBoost model, a LightGBM model, a CatBoost model, a Bayesian network model, an entropy weight method model, a partial least squares regression model, an integrated learning model, a factor analysis model, a principal component regression model, a weighted least squares model, an elastic network regression model, a quantile regression model, a time series analysis model, an adaptive enhanced neural network model, a multilayer perceptron model, a mixed Gaussian model, a t-SNE model, a U-Net model, a generative adversarial network model, a variational autoencoder model, a sparse representation model, an independent component analysis model, a causal inference model, a graph neural network model, and a Laplace regularization model. One or more of the model.
[0025] In some specific embodiments, the optimization algorithm is selected from one or more of an exhaustive method, a greedy algorithm, a dynamic programming algorithm, a divide and conquer algorithm, a backtracking algorithm, a branch and bound algorithm, a simulated annealing algorithm, a taboo search algorithm, an ant colony algorithm, a particle swarm algorithm, an artificial bee colony algorithm, a genetic algorithm, a Monte Carlo method, a gradient descent algorithm, a forgetting learning algorithm, a neural network algorithm, a genetic programming algorithm, a reinforced genetic algorithm, a Bayesian optimization algorithm, a Lagrange relaxation algorithm, a convex optimization algorithm, a Newton method, a quasi-Newton method, an interior point method, a Lagrange multiplier method, an alternating direction multiplier method, a graph algorithm, a permutation algorithm, a probabilistic graphical model, a fuzzy logic algorithm, a neuro-fuzzy system, a quantum algorithm, a linear programming algorithm, a nonlinear programming algorithm, a multi-objective optimization algorithm, a Markov decision process, a game theory algorithm, and a differential evolution algorithm.
[0026] In some specific embodiments, the device operation control system is an embedded control system, including one or more of a PLC (programmable logic controller), a PAC (programmable automation controller), a Linux system board, a microcontroller, and a single-chip microcomputer.
[0027] The present invention ensures and promotes the efficient and sustainable operation of the bioelectric stimulation water body in-situ remediation system by automatically adjusting the operating parameters of the water body in-situ remediation device. BRIEF DESCRIPTION OF THE DRAWINGS
[0028] Figure 1 This is a schematic diagram of the structure of the water body in-situ remediation system in Example 1;
[0029] Figure 2 A schematic flow chart of a repair method of the water body in-situ repair system in Example 1;
[0030] Figure 3 This is a schematic diagram of the structure of the water body in-situ remediation system in Example 9;
[0031] Figure 4 A schematic flow chart of a repair method of the water body in-situ repair system in Example 9;
[0032] in:
[0033] X1-anode chamber, X2-cathode chamber, 1-anode chamber water outlet, 2-anode electrode, 3-anode chamber water inlet, 4-constant temperature device, 4a-thermistor sensor, 4b-constant temperature device power regulator, 5-power supply voltage regulator, 6-power supply, 7-porous fender, 8-cathode biofilm sampling port, 9-cathode chamber water outlet sampling port, 10-cathode electrode, 11-cathode chamber water inlet sampling port, 12-cathode chamber water outlet, 13-cathode chamber water inlet flow adjustment device, 13a-ultrasonic flow sensor, 13b-flow regulating valve, 14-cathode chamber water inlet, 15-exchange membrane, 16a-reference electrode, 16b-reference electrode voltage regulator. DETAILED DESCRIPTION
[0034] The present invention is described in detail below in conjunction with the embodiments and drawings, but it should be understood that the embodiments and drawings are only used to exemplify the present invention and do not constitute any limitation on the protection scope of the present invention. All reasonable changes and combinations within the scope of the inventive concept of the present invention fall within the protection scope of the present invention.
[0035] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "illustrative embodiments", "examples", "specific examples", or "some examples" means that the specific features, structures, materials, or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.
[0036] Example 1
[0037] See attached Figure 1 The data-driven electrical stimulation biological water body in-situ remediation system of the present invention comprises: a water body in-situ remediation device, a data sampling system, a data analysis system and an equipment operation control system;
[0038] The water body in-situ remediation device includes an H-type double-chamber BES reactor, which includes an anode chamber X1 provided with an anode electrode 2, a cathode chamber X2 provided with a cathode electrode 10, a power supply 6 and a power supply voltage regulator 5 capable of regulating the voltage of the power supply 6, wherein the anode chamber X1 and the cathode chamber X2 are connected via a proton exchange membrane 15; the anode electrode 2 is connected to the positive electrode of the power supply 6, and the cathode electrode 10 is connected to the negative electrode of the power supply 6; a constant temperature control device capable of regulating the temperature of the cathode chamber X2 is also provided at the bottom of the cathode chamber X2; the anode chamber X1 and the cathode chamber X2 are connected to each other via a proton exchange membrane 15; the anode electrode 2 is connected to the positive electrode of the power supply 6, and the cathode electrode 10 is connected to the negative electrode of the power supply 6; a constant temperature control device capable of regulating the temperature of the cathode chamber X2 is provided at the bottom of the cathode chamber X2; 2 are all provided with water inlets and outlets, namely, the anode chamber water outlet 1, the anode chamber water inlet 3, the cathode chamber water outlet 12 and the cathode chamber water inlet 14; wherein, the cathode chamber water inlet 14 is provided with a cathode chamber water inlet flow rate adjustment device for regulating the water inlet flow rate of the cathode chamber X2 and a cathode chamber water inlet sampling port 11 for sampling the cathode chamber water inlet; the cathode chamber water outlet 12 is provided with a cathode chamber water outlet sampling port 9 for sampling the cathode chamber water outlet; a cathode biofilm sampling port 8 is provided near the cathode electrode 10 to sample the sludge mixture water sample near the cathode electrode 10.
[0039] Its application method is as follows: in order to start the in-situ water body remediation device, first add sludge to the cathode chamber X2, inject water into the anode chamber water inlet 3 of the anode chamber X1 until the anode electrode 2 is submerged, inject water into the cathode chamber water inlet 14 of the cathode chamber X2, and discharge water from the cathode chamber water outlet 12, control the water inlet flow rate of the cathode chamber X1 through the cathode chamber water inlet flow adjustment device so that the cathode chamber X2 maintains a certain hydraulic retention time, and then turn on the power supply 6 to allow the functional bacteria in the sludge added to the cathode chamber X2 to receive electrons from the cathode electrode 10, thereby stimulating the bacteria to accelerate the removal of water pollutants. In this process, turn on the constant temperature control device to maintain a certain temperature in the cathode chamber X2.
[0040] Example 2
[0041] In the data-driven electro-stimulation biological water body in-situ remediation system shown in Example 1, the constant temperature control device includes a thermistor sensor 4a and a power regulator 4b.
[0042] Example 3
[0043] In the data-driven electro-stimulation biological water body in-situ remediation system shown in Example 1, the cathode chamber water inlet flow adjustment device includes an ultrasonic flow sensor 13a and a flow regulating valve 13b.
[0044] Example 4
[0045] Preferably, a porous fender 7 is provided on the upper portion of the cathode electrode 2 to slow down the loss of the cathode biofilm on the cathode electrode 2 caused by water scouring.
[0046] Example 5
[0047] In the data-driven electro-stimulation biological water body in-situ remediation system shown in Example 1, the data sampling system includes: an outlet sampling device that can measure the COD value of the water sample at the cathode chamber outlet sampling port 9 and the cathode chamber inlet sampling port 11, such as a COD photometric rapid measuring instrument; a sampling device that can measure the numerical distribution information of the forward and side scattered light of the water sample at the cathode biofilm sampling port 8 at different wavelengths, such as a flow cytometer; a device that can measure the power supply voltage value, such as a potentiometer.
[0048] Example 6
[0049] See attached Figure 2 In the data-driven electrostimulation biological water body in-situ remediation system shown in Example 1, the data analysis system includes a model module and an output optimization module, wherein the model module contains a mathematical analysis model; the data analysis system is connected to the data sampling system through a 4G DTU wireless data transmission device, and can store and run a feedforward artificial neural network model and a genetic algorithm;
[0050] The feedforward artificial neural network model uses the COD of the water sample at the cathode chamber water inlet sampling port 11 obtained by the data sampling system, the numerical distribution information of the forward and side scattered light of the water sample at the cathode biofilm sampling port 8 at different wavelengths, the power supply voltage, the cathode chamber temperature obtained by the constant temperature control device, and the cathode chamber water inlet flow rate obtained by the cathode chamber water inlet flow rate adjustment device as input, and uses the COD of the water sample at the cathode chamber water outlet sampling port 9 as output;
[0051] The optimization process of the output optimization module includes: taking the COD of the water sample at the cathode chamber outlet sampling port to reach the lower limit of the Class II surface water quality requirements specified in the surface water environmental quality standard (GB3838-2022) as the target output value, calculating the input parameters that can obtain the target output through a genetic algorithm, and the input parameters to be adjusted include the COD of the water sample at the cathode chamber inlet sampling port 11, and the numerical distribution information of the forward and side scattered light of the water sample at the cathode biofilm sampling port 8 at different wavelengths using the measured values;
[0052] Among them, the genetic algorithm obtains different output values by adjusting the input parameters based on the mathematical analysis model. When the calculation threshold requirements are met, such as the difference between the COD of the water sample at the cathode chamber outlet sampling port and the target output value is less than 0.5, the optimization process is exited to obtain the optimal input parameters, namely the optimal power supply voltage, cathode chamber temperature and cathode chamber water inlet flow, which are transmitted to the equipment operation control system through the 4GDTU wireless data transmission device;
[0053] Among them, the neural network used in the feedforward artificial neural network model has 1 hidden layer and 5 hidden layer neurons.
[0054] Example 7
[0055] The equipment operation control system adjusts and updates the system's power supply voltage, cathode chamber temperature, and cathode chamber water inlet flow rate through the power supply voltage regulator 5, the constant temperature power regulator 4b, and the cathode chamber water inlet flow rate regulating valve 13b according to the stored operation parameters and the optimized process parameters from the data analysis system, and can specifically adopt devices such as single-chip microcomputers. More specifically, when the stored operation parameters are inconsistent with the data from the data analysis system, the power supply voltage, cathode chamber temperature, and cathode chamber water inlet flow rate regulating valve 13b are adjusted to be consistent with the data from the data analysis system through the power supply voltage regulator 5, the constant temperature power regulator 4b, and the cathode chamber water inlet flow rate regulating valve 13b, and the original stored operation parameters are updated through the operation parameters at this time.
[0056] During the operation of the in-situ water body remediation device, the calculations of the above data sampling system and data analysis system and the parameter adjustments of the equipment operation control system are repeated, thereby realizing the automated operation of the bioelectric stimulation in-situ water body remediation system without human intervention and maintaining the efficient performance of the system remediation.
[0057] Example 8
[0058] In a specific operation mode, when the proton exchange rate in the water body in-situ remediation device is limited, such as when the proton exchange membrane 15 is blocked, H + It may accumulate in the anode chamber X1, which is reflected by the continuous increase in pH value. At this time, water can be discharged from the anode chamber water inlet 3 and then injected again, or water can continue to be injected into the anode chamber X1 from the anode chamber water inlet 3 and discharged from the anode chamber water outlet 1 to replace the water in the anode chamber X1.
[0059] Example 9
[0060] In another specific operation mode, refer to the attached Figure 3 The water body in-situ remediation device is provided with a reference electrode 16a and a reference electrode voltage regulator 16b, wherein the reference electrode 16a is a saturated calomel electrode. The remediation performed by the water body in-situ remediation system containing the reference electrode is as shown in the attached Figure 4 As shown, compared with the attached Figure 2 The repair process of the repair system shown does not need to collect the voltage data of the power supply 6, but collects the voltage data of the reference electrode 16a, and adjusts the voltage of the reference electrode 16a through the reference electrode voltage regulator 16b in the equipment operation control system.
[0061] Finally, it should be noted that the above is only used to illustrate the technical solution of the present invention rather than to limit it. Although the embodiments have described the present invention in detail, those skilled in the art should understand that the technical solution of the present invention (such as pump type, charging form, sequence of steps, etc.) can be modified or replaced by equivalents without departing from the spirit and scope of the technical solution of the present invention.
Claims
1. A data-driven electrostimulation biological water body in-situ remediation system, characterized in that: It includes: An in-situ water body remediation device for in-situ water body remediation, a data sampling system for sampling data for the in-situ water body remediation device, a data analysis system for analyzing the sampling data obtained by the data sampling system, and an equipment operation control system for regulating the in-situ water body remediation device through the analysis data obtained by the data analysis system; wherein the in-situ water body remediation device includes a dual-chamber bioelectrochemical system reactor in which an anode chamber and a cathode chamber are connected via a proton exchange membrane, a constant temperature control device capable of sensing and regulating the temperature of the cathode chamber, a cathode chamber water inlet flow adjustment device capable of sensing and regulating the water inlet flow of the cathode chamber, a power supply and a power supply voltage regulator capable of regulating the voltage of the power supply, wherein the anode chamber is provided with an anode electrode connected to the positive pole of the power supply, and the cathode chamber is provided with a The cathode electrode is connected to the negative pole of the power supply; the anode chamber is also provided with an anode chamber water inlet and an anode chamber water outlet; the cathode chamber is also provided with a cathode chamber water inlet, a cathode chamber water outlet, a cathode chamber water inlet sampling port arranged near the cathode chamber water inlet for sampling the water inlet of the cathode chamber, a cathode chamber water outlet sampling port arranged near the cathode chamber water outlet for sampling the water outlet of the cathode chamber, and a cathode biofilm sampling port for sampling a water sample containing a sludge mixture near the cathode electrode; the data analysis system includes a model module and an output optimization module, wherein the model module contains a mathematical analysis model, the mathematical analysis model is trained according to the sampling data, and the output optimization module calculates the optimal process parameters of the water body in-situ remediation device according to the trained mathematical analysis model.
2. The water body in-situ remediation system according to claim 1, characterized in that: in, The dual-chamber bioelectrochemical system reactor is a dual-chamber reactor; the constant temperature control device includes a thermistor sensor and a power regulator; the cathode chamber water inlet flow adjustment device includes an ultrasonic flow sensor and a flow regulating valve.
3. The water body in-situ remediation system according to claim 1, characterized in that: in, The data sampling system includes: a temperature sensing device arranged in the constant temperature control device, a flow sensing device arranged in the cathode chamber water inlet flow adjustment device, a water quality detection device capable of detecting water quality parameters of water samples at the cathode chamber water outlet sampling port and the cathode chamber water inlet sampling port, a biological detection device capable of detecting biological information in water samples at the cathode biofilm sampling port, and a voltage detection device capable of measuring the power supply voltage value; the equipment operation control system includes one or more of PLC, PAC, Linux system board, microcontroller, and single-chip microcomputer.
4. The water body in-situ remediation system according to claim 3, characterized in that: The temperature sensing device is a thermistor sensor, the flow sensing device is an ultrasonic flow sensor, the water quality detection equipment is a rapid chemical oxygen demand determination instrument, and the biological detection equipment is a flow cytometer and / or a MALDI-TOF mass spectrometer.
5. The water body in-situ remediation system according to claim 1, characterized in that: It also includes: a reference electrode and a reference electrode voltage regulator arranged in the cathode chamber.
6. A method for in-situ restoration of a water body based on the in-situ restoration system of any one of claims 1 to 5, comprising: The data acquisition system is used to collect sampling data of the water body in-situ restoration device when performing water body restoration, and the sampling data includes cathode chamber temperature, cathode chamber water inlet flow, water quality parameters of water samples at the cathode chamber water outlet sampling port, water quality parameters of water samples at the cathode chamber water inlet sampling port, biological information in water samples at the cathode biofilm sampling port, and power supply voltage or reference electrode voltage value; The mathematical analysis model is trained according to the sampling data by the data analysis system; the mathematical analysis model takes the cathode chamber temperature, the cathode chamber water inlet flow, the water quality parameters of the water sample at the cathode chamber water inlet sampling port, the biological information in the water sample at the cathode biofilm sampling port and the power supply voltage or reference electrode voltage value as input, and takes the water quality parameters of the water sample at the cathode chamber water outlet sampling port as output; Based on the trained mathematical analysis model, the output optimization module of the data analysis system adopts an optimization algorithm to obtain input process parameters that can achieve the optimal output conditions of the trained mathematical analysis model, namely, optimized process parameters, wherein the optimized process parameters include cathode chamber water inlet flow, power supply voltage or reference electrode voltage value and cathode chamber temperature; The obtained optimized process parameters are transmitted to the equipment operation control system as control targets, and the equipment operation control system adjusts the operation parameters of the water body in-situ remediation device to achieve the control targets.
7. The in-situ water body remediation method according to claim 6, characterized in that: in, The mathematical analysis model is selected from a linear regression model, a ridge regression model, a random forest model, an extreme learning machine model, a support vector machine model, a decision tree model, a logistic regression model, a Bayesian model, a K-nearest neighbor model, a principal component analysis model, a gradient boosting machine model, a neural network model, a long short-term memory model, a self-organizing map model, a Gaussian process regression model, a Markov chain Monte Carlo model, an XGBoost model, a LightGBM model, a CatBoost model, a Bayesian network model, an entropy weight method model, a partial least squares regression model, an integrated learning model, a factor analysis model, a principal component regression model, a weighted least squares model, an elastic network regression model, a quantile regression model, a time series analysis model, an adaptive enhanced neural network model, a multilayer perceptron model, a mixed Gaussian model, a t-SNE model, a U-Net model, a generative adversarial network model, and a variational autoencoder model. , sparse representation model, independent component analysis model, causal inference model, graph neural network model, Laplace regularization model or more; the optimization algorithm is selected from exhaustive method, greedy algorithm, dynamic programming algorithm, divide and conquer algorithm, backtracking algorithm, branch and bound algorithm, simulated annealing algorithm, taboo search algorithm, ant colony algorithm, particle swarm algorithm, artificial bee colony algorithm, genetic algorithm, Monte Carlo method, gradient descent algorithm, forgetting learning algorithm, neural network algorithm, genetic programming algorithm, reinforced genetic algorithm, Bayesian optimization algorithm, Lagrange relaxation algorithm, convex optimization algorithm, Newton method, quasi-Newton method, interior point method, Lagrange multiplier method, alternating direction multiplier method, graph algorithm, permutation algorithm, probabilistic graph model, fuzzy logic algorithm, neuro-fuzzy system, quantum algorithm, linear programming algorithm, nonlinear programming algorithm, multi-objective optimization algorithm, Markov decision process, game theory algorithm, differential evolution algorithm or one or more.
8. The in-situ water body remediation method according to claim 6, characterized in that: The water quality parameters include one or more of pH value, chemical oxygen demand, biochemical oxygen demand, electrical conductivity, total nitrogen, total phosphorus, ammonia nitrogen, nitrate content, phosphate content, residual chlorine, total chlorine, heavy metal concentration, hardness and turbidity; the biological information includes one or more of the refractive index of water samples containing microorganisms under light of different wavelengths and / or directions, the abundance and / or uniformity of biological macromolecules, community genome, and colony morphological characteristics and quantity.
Citation Information
Patent Citations
Microbial fuel cell capable of repairing nitrate polluted underground water in situ
CN104064794A
Dyeing wastewater treatment device and method for treating wastewater by using device
CN105948221A
River and lake water quality-hydrodynamics online intelligent monitoring system and method
CN115508528A
Intelligent control method for dry bulk cargo wharf sewage treatment equipment
CN118410312A
Simultaneous phosphorus and nitrogen removal double-chamber microbiological fuel cell
CN203871429U
