Environmental factor intelligent response type organic carbon conversion regulation and control system

Abstract

The invention relates to the technical field of organic carbon conversion control, in particular to an environment factor intelligent response type organic carbon conversion regulation and control system, which comprises the following modules: an environment factor acquisition module for acquiring multi-dimensional environment factors of an environment where a reaction system is located and forming environment factor vectors; the process parameter detection module is used for acquiring the organic carbon concentration, the microbial activity, the dissolved oxygen content, the pH value and the conductivity of the solution on line to form a process state vector; according to the invention, environment factor vectors and process state vectors are collected and multi-modal fusion analysis is carried out, then regulation and control parameter vectors are generated based on system state vectors, and dynamic regulation and control are implemented by an execution module, so that the problems that most of the traditional organic carbon conversion processes adopt fixed control strategies, and the efficiency is high are solved. And because real-time adjustment is not carried out according to linkage change of an environment and a system state, carbon conversion efficiency fluctuation is large.

Description

Technical Field

[0001] This invention relates to the field of organic carbon conversion control technology, and in particular to an intelligent response-type organic carbon conversion regulation system for environmental factors. Background Technology

[0002] Against the backdrop of increasing global pressure for energy structure transformation and environmental governance, organic carbon conversion technology is widely used in wastewater treatment, soil improvement, and biomass energy utilization. Carbon conversion efficiency directly affects energy recovery efficiency and environmental emission reduction, while the performance of the reaction system is influenced by multidimensional environmental factors such as temperature, light, dissolved oxygen, pH, and gas composition, as well as process parameters such as internal microbial activity. Traditional organic carbon conversion processes mostly employ fixed control strategies, which, due to the failure to adjust in real-time according to the linkage changes between the environment and the system state, result in large fluctuations in carbon conversion efficiency. Summary of the Invention

[0003] To overcome the above shortcomings, this invention provides an intelligent environmental factor-responsive organic carbon conversion regulation system, which aims to improve the problem that traditional organic carbon conversion processes mostly adopt fixed control strategies, resulting in large fluctuations in carbon conversion efficiency due to the failure to adjust in real time according to the linkage changes between the environment and the system state.

[0004] This invention provides the following technical solution: an intelligent environmental factor-responsive organic carbon conversion regulation system, comprising the following modules: The environmental factor acquisition module is used to collect multidimensional environmental factors of the environment in which the reaction system is located and form an environmental factor vector. The process parameter detection module is used to collect data on solution organic carbon concentration, microbial activity, dissolved oxygen content, pH, and conductivity online to form a process state vector. The multimodal data fusion module is used to extract features, normalize and analyze trends of the environmental factor vector and process state vector, and to establish a system state vector to characterize the dynamic relationship between changes in environmental factors and changes in the state of the reaction system. The intelligent control and decision-making module is used to generate a control parameter vector based on the system state vector, including temperature, pH, dissolved oxygen, light and gas flow control commands, and to comprehensively optimize carbon conversion efficiency, environmental stability and energy consumption through a multi-objective optimization strategy. The execution module is used to adjust the temperature controller, light controller, fluid pump, gas regulator and pH adjustment device according to the control parameter vector to realize the dynamic control of the organic carbon conversion process; The feedback closed-loop module is used to collect the system status after execution and feed back the deviation signal to the intelligent control and decision module to realize closed-loop control.

[0005] By adopting the above technical solution, environmental factor vectors and process state vectors are collected and multimodal fusion analysis is performed. Then, based on the system state vector, a control parameter vector is generated and dynamically controlled by the execution module. This improves the problem that traditional organic carbon conversion processes mostly adopt fixed control strategies, which fail to adjust in real time according to the linkage changes between the environment and the system state, resulting in large fluctuations in carbon conversion efficiency.

[0006] Preferably, the environmental factor collection includes: A temperature sensor array is deployed to collect temperature distribution data at different locations within the system, and the data is read synchronously via a signal acquisition board. A humidity sensor collects humidity data from the air and solution surface, removes noise through a filter, and generates a continuous time series. A light sensor collects light intensity and spectral distribution, and uses spectral decomposition methods to extract key light band features. pH electrodes and redox potential sensors collect the acidity, alkalinity, and redox state of the solution, and use a digital conversion module to generate a calculable numerical signal. A CO2 concentration sensor collects the CO2 content in the gas phase and combines it with timestamps to generate a multidimensional environmental factor vector. The vector, after being standardized, is output to the multimodal data fusion module, providing basic input for reaction state analysis.

[0007] Preferably, the process parameter detection includes: The concentration of organic carbon in solution was measured using an online optical sensor, and the characteristics of carbon conversion rate and total organic carbon content were extracted. Microbial activity sensors monitor the microbial activity index within the system, and construct a reactivity index by combining dissolved oxygen, pH, and conductivity data. The collected data undergoes time-series synchronization processing, filtering, and denoising, and a process state vector is generated. The output process state vector is sent to the multimodal data fusion module for joint analysis with environmental factor vectors.

[0008] Preferably, the multimodal data fusion includes: Receive environmental factor vectors and process state vectors, and perform alignment and interpolation to eliminate sampling differences; Extract trend features, fluctuation features, and environment-response correlation features to construct a feature matrix; The feature matrix is ​​modeled using a state-space model to generate a system state vector, which is then output to the intelligent control and decision-making module.

[0009] Preferably, the multimodal data fusion further includes: Construct a state-space model between environmental factors and system state to describe the impact of environmental changes on carbon conversion; The model is used to predict the short-term system state, providing a basis for decision-making in the intelligent control and regulation module.

[0010] Preferably, the intelligent control decision includes: Receive the system state vector, combine it with the preset control target and historical operating data, and calculate the error vector that deviates from the target state; A multi-objective optimization strategy is used to generate a vector of control parameters, including temperature, pH, dissolved oxygen, light intensity, and gas flow control commands. Output the control parameter vector to the execution module and provide control strategy logs for subsequent closed-loop analysis.

[0011] Preferably, the intelligent control decision further includes: A multi-objective optimization function was established, with carbon conversion efficiency, system stability, and energy consumption as optimization objectives; Use constraints to ensure that the control parameters are within a safe range; The optimized control parameter vector is output to the execution module to achieve efficient dynamic control.

[0012] Preferably, the execution module includes: Receive the control parameter vector and control the temperature controller to adjust the system temperature; The lighting controller adjusts the light intensity and spectral combination. Control the fluid pump and gas regulator to achieve solution flow and gas introduction; A pH adjustment device is used to regulate acidity and alkalinity. The system status after execution is output to the feedback closed-loop module to realize closed-loop information collection.

[0013] Preferably, the feedback loop includes: The actual system state output by the acquisition and execution module is collected, and the deviation signal between the actual state and the target state is calculated. The deviation signal is transmitted to the intelligent control decision module, triggering the adaptive control parameter correction. It supports multiple rounds of iterative closed-loop operation, enabling the system to maintain a stable state under fluctuations in environmental factors.

[0014] Preferably, the feedback loop further includes: The intelligent control strategy parameters are adjusted based on the deviation signal, so that the control parameter vector is dynamically corrected according to the system state. It supports closed-loop iterative updates, enabling continuous optimization of the carbon conversion process and stable system operation under changes in environmental factors.

[0015] The present invention has the following beneficial effects: 1. In this invention, by collecting environmental factor vectors and process state vectors and performing multimodal fusion analysis, a control parameter vector is generated based on the system state vector and dynamically controlled by the execution module. This improves the problem that traditional organic carbon conversion processes mostly adopt fixed control strategies, which fail to adjust in real time according to the linkage changes of the environment and system state, resulting in large fluctuations in carbon conversion efficiency.

[0016] 2. In this invention, the external environment and system state are quantified in real time through the environmental factor acquisition module and the process parameter detection module, thereby providing a unified input for multimodal data fusion. This enables the system to fully grasp the reaction conditions, thus improving the problem that traditional organic carbon conversion processes mostly use local monitoring or single parameter acquisition, which cannot obtain complete environmental and reaction information, resulting in inaccurate system state analysis.

[0017] 3. In this invention, a system state vector is constructed by a multimodal data fusion module to characterize the dynamic relationship between environmental factors and the state of the reaction system, thereby providing a comprehensive basis for intelligent control decisions. This improves the problem that traditional organic carbon conversion processes mostly rely on independent parameter judgments, which fail to describe the coupled dynamic relationship between the environment and the system, resulting in control strategies deviating from actual operational requirements.

[0018] 4. In this invention, the system state after execution is collected by the feedback closed-loop module and the deviation signal is returned to the intelligent control decision module, thereby realizing closed-loop iterative control. This improves the problem that traditional organic carbon conversion processes mostly use single control commands, and due to the lack of adaptive correction mechanisms, the system is difficult to maintain long-term stable operation. Attached Figure Description

[0019] Figure 1 This is a module architecture diagram of the intelligent response-type organic carbon conversion regulation system for environmental factors proposed in this invention; Figure 2 This is a diagram showing the composition of the environmental factor acquisition module of the intelligent response organic carbon conversion regulation system proposed in this invention. Figure 3 This is a diagram showing the composition of the process parameter detection module of the intelligent response-type organic carbon conversion regulation system for environmental factors proposed in this invention; Figure 4 This is a flowchart of the multimodal data fusion processing of the intelligent response-type organic carbon conversion regulation system for environmental factors proposed in this invention. Figure 5 This is a flowchart of the intelligent control decision-making process of the intelligent response-type organic carbon conversion control system for environmental factors proposed in this invention. Detailed Implementation

[0020] The technical solutions in 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 embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0021] Example 1: In the first embodiment of the present invention, the present invention provides an intelligent environmental factor-responsive organic carbon conversion regulation system, such as... Figures 1-5 As shown, it includes the following steps: The environmental factor acquisition module is used to collect multidimensional environmental factors of the environment in which the reaction system is located and form an environmental factor vector. Furthermore, environmental factor collection includes: A temperature sensor array is deployed to collect temperature distribution data at different locations within the system, and the data is read synchronously via a signal acquisition board. A humidity sensor collects humidity data from the air and solution surface, removes noise through a filter, and generates a continuous time series. A light sensor collects light intensity and spectral distribution, and uses spectral decomposition methods to extract key light band features. pH electrodes and redox potential sensors collect the acidity, alkalinity, and redox state of the solution, and use a digital conversion module to generate a calculable numerical signal. A CO2 concentration sensor collects the CO2 content in the gas phase and combines it with timestamps to generate a multidimensional environmental factor vector. After standardization, the vector is output to the multimodal data fusion module, providing basic input for reaction state analysis.

[0022] Specifically, the environmental factor acquisition module is used to obtain multidimensional environmental factor information of the environment in which the reaction system is located, and convert it into an environmental factor vector that the system can calculate, providing the original data foundation for subsequent multimodal data fusion and intelligent control. Environmental factor acquisition includes the acquisition of parameters such as temperature, humidity, light intensity, acid-base and redox states, and gaseous CO2 concentration.

[0023] Temperature acquisition is achieved through an array of deployed temperature sensors to monitor the temperature at different locations within the reaction system. Measurements are performed, and the acquired signals are synchronously read by the signal acquisition board to form a temperature vector. ;in, Indicates the first Temperature values ​​collected by a temperature sensor, This represents the number of temperature sensors. The temperature vector provides input for the system's thermal state during subsequent state analysis.

[0024] Humidity data was collected using humidity sensors on the air and solution surface to measure humidity values. And form a humidity vector: ;in Indicates the first Values ​​collected by a humidity sensor This represents the number of humidity sensors. The acquired signals are filtered to remove noise, generating a continuous time series for real-time humidity analysis of the environment.

[0025] Light acquisition uses a light sensor to obtain light intensity and spectral distribution, and records the spectral power density. This forms the illumination vector: ;in Indicates the first A light sensor at wavelength The light intensity value, This represents the number of light sensors. Spectral data is analyzed using spectral decomposition to extract key band features, which are then used to characterize the impact of illumination conditions on carbon transformation.

[0026] Acid-base and redox states are collected using a pH electrode and a redox potential sensor to measure the pH value of the solution. and redox potential This forms acid-base and redox vectors: ; in This represents the number of acid-base and redox sensors. Sensor signals are converted into calculable values ​​via a digital conversion module. This vector characterizes the internal chemical state of the solution, providing a basis for intelligent control decisions.

[0027] Gas phase CO2 concentration is collected using a CO2 concentration sensor, which records the CO2 content at different locations. This forms a CO2 vector: ;in This represents the number of CO2 sensors. Data collection is linked to timestamps to ensure the continuity of environmental factors over time.

[0028] All collected vectors were standardized to form a unified environmental factor vector. : ; in For environmental factor vectors, This represents the normalization function for each collected vector, ensuring that parameters from different dimensions can be used for fusion calculations on the same numerical scale. The processed environmental factor vectors are output to the multimodal data fusion module, providing input for the joint analysis of the environmental and reaction system states.

[0029] The environmental factor acquisition module achieves a complete characterization of the environmental conditions of the reaction system through the above steps, ensuring that multidimensional parameters can be used for system state analysis and intelligent control decisions, while guaranteeing data continuity, computability, and traceability, providing a reliable foundation for the dynamic control of organic carbon conversion.

[0030] The process parameter detection module is used to collect data on solution organic carbon concentration, microbial activity, dissolved oxygen content, pH, and conductivity online to form a process state vector. Furthermore, process parameter detection includes: The concentration of organic carbon in solution was measured using an online optical sensor, and the characteristics of carbon conversion rate and total organic carbon content were extracted. Microbial activity sensors monitor the microbial activity index within the system, and construct a reactivity index by combining dissolved oxygen, pH, and conductivity data. The collected data undergoes time-series synchronization processing, filtering, and denoising, and a process state vector is generated. The output process state vector is sent to the multimodal data fusion module for joint analysis with environmental factor vectors.

[0031] Specifically, the process parameter detection module is used to monitor the key process states within the reaction system online and generate process state vectors that can be used for intelligent control, thereby characterizing the dynamic behavior of the system and analyzing its reactivity. The parameters collected by the module include solution organic carbon concentration, microbial activity, dissolved oxygen content, pH, and conductivity.

[0032] The concentration of organic carbon in the solution is collected using an online optical sensor to measure the total amount of organic carbon in the solution. Real-time measurement is performed on the carbon conversion rate. It can be calculated from the rate of change of organic carbon concentration over continuous time: ;in Indicates time The total organic carbon concentration of the solution, expressed in milligrams per liter. This represents the carbon conversion rate, expressed in milligrams per liter per hour. The input to this step is the solution sample signal, and the output is a continuous time series vector of carbon concentration and carbon conversion rate. .

[0033] Microbial activity monitoring is achieved through online microbial activity sensors to obtain the microbial activity index within the system. This index can be correlated with dissolved oxygen. pH and conductivity Joint calculation of reaction activity index : ;in The system represents the time. The comprehensive reactivity index, function This method characterizes the coupling relationship between microbial activity and environmental parameters, and is used to characterize the active state of the system. The input is the real-time signal measured by each sensor, and the output is a continuous time-series vector of reactivity indicators. .

[0034] All collected data underwent time-series synchronization processing, and high-frequency noise and abrupt data were processed using filtering and denoising algorithms to form a unified process state matrix. ; in This is a process state vector matrix, where rows represent different parameters and columns represent time series points. This matrix is ​​standardized to form the process state vector. Used for joint analysis with environmental factor vectors: The processed process state vector is output to the multimodal data fusion module as input for joint state analysis, enabling coupled characterization of environmental factors and system state. The process parameter detection module ensures continuous, calculable, and traceable data acquisition of key indicators within the reaction system, providing fundamental data for the intelligent control module and supporting closed-loop control and carbon conversion optimization.

[0035] The multimodal data fusion module is used to extract features, normalize and analyze trends of environmental factor vectors and process state vectors, and to establish system state vectors to characterize the dynamic relationship between changes in environmental factors and changes in the state of the reaction system. Furthermore, multimodal data fusion includes: Receive environmental factor vectors and process state vectors, and perform alignment and interpolation to eliminate sampling differences; Extract trend features, fluctuation features, and environment-response correlation features to construct a feature matrix; The feature matrix is ​​modeled using a state-space model to generate a system state vector, which is then output to the intelligent control and decision-making module.

[0036] Multimodal data fusion further includes: Construct a state-space model between environmental factors and system state to describe the impact of environmental changes on carbon conversion; The model is used to predict the short-term system state, providing a basis for decision-making in the intelligent control and regulation module.

[0037] Specifically, the multimodal data fusion module unifies the processing of environmental factor vectors and process state vectors, extracts key features, and establishes system state vectors. This enables a dynamic representation of the relationship between environmental factor changes and the state of the reaction system, providing calculable decision inputs for intelligent regulation. The module comprises four parts: data alignment, feature extraction, state modeling, and system state vector generation.

[0038] Environmental factor vector With process state vector As input data, alignment and interpolation are first performed. Since different sensor sampling frequencies and time delays may cause data sequences to be out of sync, the module uses linear interpolation or spline interpolation methods to unify the time series and generate aligned data vectors. and The formula is as follows: ; ; in For a moment Aligned environmental factor vectors For a moment Aligned process state vector and These are adjacent time points to ensure that the input data is consistent in the time dimension.

[0039] Feature extraction, including trend features, is performed on the aligned data vectors. Fluctuation characteristics and environment-response correlation characteristics Trend characteristics were calculated using moving averages and linear fitting; volatility characteristics were obtained using standard deviation and analysis of variance; and correlation characteristics were calculated using Pearson correlation coefficients or covariance matrices. ;in Indicates the first The environmental factor and the first The correlation between process state parameters and ... It is composed of a combination of trend characteristics, volatility characteristics, and correlation characteristics: ; Feature matrix This module is used to describe the multidimensional dynamic relationship between the environment and the system state. It further establishes a state-space model, mapping the feature matrix to a system state vector. : ;in This is the internal state vector of the system. The input vector is the aligned environmental factor vector. The output vector, i.e., the system state vector. ,matrix Represents the system state transition matrix. Indicates the input control matrix. This represents the state-to-output mapping matrix. This represents the direct mapping matrix from input to output. This model can predict the short-term system state, providing a basis for intelligent control and decision-making modules.

[0040] The data input process involves environmental factor vectors and process state vectors being fed into the module via an interface. After alignment and interpolation, a unified time series is generated. Feature extraction is then performed to construct a feature matrix, and finally, the system state vector is output through a state-space model. The module output is sent to the intelligent control and decision-making module to generate closed-loop control parameters and regulate carbon conversion.

[0041] The multimodal data fusion module achieves a comprehensive characterization of the environment and state of the reaction system through the above processing, enabling the system to continuously quantify the impact of environmental factors on the carbon conversion process, realize high-precision state prediction, provide a reliable data foundation for intelligent control, and at the same time ensure the computability, continuity and traceability of data processing.

[0042] The intelligent control and decision-making module is used to generate control parameter vectors based on the system state vector, including temperature, pH, dissolved oxygen, light and gas flow control commands, and to comprehensively optimize carbon conversion efficiency, environmental stability and energy consumption through a multi-objective optimization strategy. Furthermore, intelligent control decision-making includes: Receive the system state vector, combine it with the preset control target and historical operating data, and calculate the error vector that deviates from the target state; A multi-objective optimization strategy is used to generate a vector of control parameters, including temperature, pH, dissolved oxygen, light intensity, and gas flow control commands. Output the control parameter vector to the execution module and provide control strategy logs for subsequent closed-loop analysis.

[0043] Intelligent regulation and control decision-making further includes: A multi-objective optimization function was established, with carbon conversion efficiency, system stability, and energy consumption as optimization objectives; Use constraints to ensure that the control parameters are within a safe range; The optimized control parameter vector is output to the execution module to achieve efficient dynamic control.

[0044] Specifically, the intelligent control and decision-making module is used to generate control parameter vectors based on the system state vector, realize dynamic control of temperature, pH, dissolved oxygen, light and gas flow, and comprehensively optimize carbon conversion efficiency, environmental stability and energy consumption through multi-objective optimization strategy, provide control commands to the execution module and ensure the safe operation of the system.

[0045] System state vector As input to the module, combined with the preset control target vector and historical operating data Calculate the error vector deviating from the target. : ;in Indicates the current system status. This indicates the set values ​​of each target parameter. This represents the error of each state parameter deviating from the target, used for subsequent adjustment and optimization. The module quantifies the degree to which the current state of the system deviates from the target through the error vector, providing input for multi-objective optimization.

[0046] Multi-objective optimization strategies are used to generate control parameter vectors. Including temperature pH Dissolved oxygen ,illumination and gas flow rate Control commands: .

[0047] Optimization function Defined as carbon conversion efficiency System stability and energy consumption Comprehensive indicators: ; in These are the weighting coefficients for each optimization objective, reflecting the relative priority of the control strategy among carbon conversion efficiency, system stability, and energy consumption. System stability Energy consumption is calculated based on the fluctuation amplitude and error rate of temperature, pH, dissolved oxygen, and light intensity. This is generated by the cumulative power consumption of each control action. Constraints ensure that all control parameters remain within safe operating ranges. ; The optimal control parameter vector is calculated through gradient descent or heuristic algorithms. : ; The output process is as follows: System state vector The input module generates an error vector through error calculation. The multi-objective optimization function calculates the error vector and historical data to generate the control parameter vector. Finally, it outputs control commands to the execution module and records the control strategy log for closed-loop analysis and subsequent control strategy optimization.

[0048] The intelligent control and decision-making module achieves efficient dynamic control of the carbon conversion system using the methods described above. It transforms real-time feedback from environmental factors and process states into optimized control parameters, ensuring the system operates with high carbon conversion efficiency and stability while keeping energy consumption within a reasonable range. The module's output data can be used to continuously optimize multi-objective weights and constraints, enabling iterative upgrades of the system's control strategy.

[0049] The execution module is used to adjust the temperature controller, light controller, fluid pump, gas regulator and pH adjustment device according to the control parameter vector to achieve dynamic control of the organic carbon conversion process; Furthermore, the execution module includes: Receive the control parameter vector and control the temperature controller to adjust the system temperature; The lighting controller adjusts the light intensity and spectral combination. Control the fluid pump and gas regulator to achieve solution flow and gas introduction; A pH adjustment device is used to regulate acidity and alkalinity. The system status after execution is output to the feedback closed-loop module to realize closed-loop information collection.

[0050] Specifically, the execution module regulates the temperature controller, light controller, fluid pump, gas regulator, and pH adjustment device according to the control parameter vector, thereby updating the physical and chemical states of the organic carbon conversion system according to the control logic. The input of the execution module is the control parameter vector, and the output is the system state data after the control action, which is then sent back to the feedback closed-loop module.

[0051] The execution module receives the control parameter vector from the intelligent control decision module: ; in Indicates the temperature setpoint; This indicates the illumination control quantity, including the light intensity and spectral combination number; This indicates the solution flow rate setpoint; This indicates the gas inlet rate setpoint; This represents the pH adjustment setpoint. The execution module parses the parameters of each element in the vector, mapping each setpoint to the corresponding control command sequence of the actuator, forming an internal control command matrix: ;in This is a mapping function from parameters to hardware instructions, used to generate specific drive signals. Parameter explanation: For control instruction matrix; It is a mapping function based on the device calibration table.

[0052] Thermostat based on Adjust the power output of the heating or cooling unit. The thermostat uses a power regulation equation internally: ;in The power output of the temperature controller; This refers to the temperature control response coefficient. The current system temperature is provided by the feedback closed-loop module. Actions are executed to bring the system temperature closer to the target temperature, thereby creating a stable environment for the carbon conversion reaction.

[0053] Light controller according to Adjust the light source drive current by setting the light intensity and spectral combination. The drive current calculation formula is: ;in: This is the driving current for the light source; This is the light source current-to-light intensity conversion coefficient. The spectral combinations correspond to the selection table of the internal light source matrix through preset numbers, forming the irradiation conditions required for the photogenerated reaction.

[0054] fluid pump according to The flow rate is set, and the flow control formula is executed internally within the execution module. ;in This represents the output flow rate of the fluid pump. This action is used to maintain the stability of the material transport rate and reactant concentration distribution.

[0055] Gas regulator according to The gas inlet rate is controlled, and the execution module generates valve opening commands based on the set rate. ;in This refers to the opening degree of the gas valve; This is a gas flow rate versus valve opening characteristic function. This action is used to regulate the gas supply in the system, thereby affecting the supply of carbon source or electron acceptor.

[0056] pH adjustment device according to The injection volume of acid or alkali is adjusted according to the following relationship: ;in The injection rate of acid and base; The acid-base injection conversion coefficient; The current system pH value is provided by the feedback closed-loop module. This operation is used to maintain the system's acidity or alkalinity, keeping the microenvironment within a range that sustains the carbon conversion reaction.

[0057] After completing the adjustment, the execution module collects the following system states as output data vectors: ; in The real-time temperature after execution; The lighting parameters after execution; This refers to the actual flow rate; This represents the actual gas flow rate. The pH value after execution is [value]. The collected system state vector serves as the input to the feedback closed-loop module for subsequent closed-loop iterations.

[0058] The feedback closed-loop module is used to collect the system status after execution and feed the deviation signal back to the intelligent control decision module to realize closed-loop control. Furthermore, the feedback loop includes: The actual system state output by the acquisition and execution module is collected, and the deviation signal between the actual state and the target state is calculated. The deviation signal is transmitted to the intelligent control decision module, triggering the adaptive control parameter correction. It supports multiple rounds of iterative closed-loop operation, enabling the system to maintain a stable state under fluctuations in environmental factors.

[0059] The feedback loop further includes: The intelligent control strategy parameters are adjusted based on the deviation signal, so that the control parameter vector is dynamically corrected according to the system state. It supports closed-loop iterative updates, enabling continuous optimization of the carbon conversion process and stable system operation under changes in environmental factors.

[0060] Specifically, the feedback closed-loop module is used to collect actual system state data after the execution module completes its adjustment, construct a deviation signal, and transmit this deviation signal to the intelligent control decision module, thereby forming a closed-loop control link. The input of this module is the system state vector output by the execution module, and the output is the deviation signal and related state records.

[0061] The feedback closed-loop module receives the system state vector generated by the execution module: ; in The system temperature after execution; The illumination parameters after execution include a state expression containing the combination number of light intensity and spectrum. This represents the actual solution flow rate; This represents the actual gas flow rate; The pH value after execution. The feedback closed-loop module internally stores the target state vector: The deviation signal is calculated based on the element-level difference: ;in This is the deviation signal vector; each element corresponds to the deviation between the actual state and the target state.

[0062] After the deviation signal is generated, the feedback closed-loop module will vector The parameter update interface, transmitted to the intelligent control decision module, is used to trigger the adaptive correction process of the control parameter vector. The transmitted data structure is as follows: ; The set contains the system state, target state, and deviation signals to provide a complete closed-loop data foundation.

[0063] The feedback closed-loop module records the deviation data from multiple rounds and generates an iteration sequence: ; in For closed-loop iteration rounds; For the first The system state after each round of execution. The module records the deviation sequence of multiple rounds for trend judgment by the intelligent control decision module, enabling the control to continuously converge under environmental factor fluctuations.

[0064] After the intelligent control decision module receives the deviation signal, if it needs to update the control strategy parameters, the feedback closed-loop module provides the deviation change rate as an auxiliary quantity. The deviation change rate is calculated as follows: ; in This represents the change in deviation; it indicates the dynamic trend of the system's state. The rate of change in deviation is used to assist the intelligent control decision-making module in evaluating the correction amount of the control parameter vector, enabling the control strategy to automatically adjust according to the trend of state change. The data packet output by the feedback closed-loop module is in the following format: Used to provide the complete chain of state changes required for closed-loop iteration.

[0065] Supported by the deviation signals and deviation change sequences provided by the feedback closed-loop module, the intelligent control decision module adjusts the control parameter vector to maintain the system in a controllable state under conditions of changes in external environmental factors or internal load. The feedback closed-loop module, through continuous state acquisition, deviation calculation, and iteration, enables the entire control system to form a dynamic closed-loop link, creating stable operating conditions.

[0066] Example 2: The system is applied to the dynamic control of organic carbon conversion processes in indoor photobioreactor systems. The reaction system typically contains a microbial community capable of metabolic activity under light conditions, placed within a photobioreactor equipped with temperature regulation, gas introduction, light regulation, agitation, and pH control. During organic carbon conversion, environmental factors such as ambient temperature, light intensity and spectral composition, solution pH, dissolved oxygen content, and gaseous carbon dioxide concentration change over time, while internal process parameters such as microbial activity, organic carbon concentration, and conductivity also fluctuate continuously. To achieve a stable carbon conversion process, real-time adjustments are needed to the temperature controller, light controller, fluid pump, gas regulator, and pH adjustment device based on the combined changes in environmental factors and process states, ensuring the reaction system maintains a specified state even under external disturbances.

[0067] In application scenarios, the reaction system is influenced by multiple environmental factors and internal process parameters. The sampling benchmarks and rates of change differ among various data points, making it difficult to construct a unified input vector for analysis. This results in a lack of a systematic expression describing the dynamic coupling relationship between environmental conditions and the system's reaction state. Simultaneously, process parameters such as organic carbon concentration, microbial activity, and dissolved oxygen fluctuate over time. Without effective joint characterization, it is difficult to accurately describe the true state of the system. Furthermore, without a quantitative expression of the system state, there are constrained relationships between control quantities such as temperature, light intensity, pH, and gas flow rate, making it difficult to jointly solve for multi-objective control parameters. In addition, the actual output of the actuator is affected by equipment inertia and disturbances. Without a closed-loop correction mechanism based on deviation signals, the control commands cannot converge to the target state, easily leading to system response lag or deviation. To solve these problems, this invention provides an intelligent response-type organic carbon conversion control system based on environmental factors, the structure of which is as follows: Figure 1 As shown. The specific implementation process of this system is as follows: The environmental factor acquisition module is used to obtain information such as temperature, humidity, light intensity, acid-base state, and gas composition of the external environment of the reaction system, and converts the collected data into a calculable environmental factor vector according to a unified time base. Temperature sensors are deployed at different locations in the reaction system to collect local temperatures, which are then read by the signal acquisition board to form temperature data with spatial distribution characteristics. Humidity sensors measure air and liquid surface humidity, and the sampling error is removed by a filtering stage to form a continuous sequence. Light sensors measure light intensity and spectral distribution, and representative light components are extracted by decomposing the spectral signal. pH electrode and redox potential sensors convert acidity / alkalinity and redox potential into numerical signals. Carbon dioxide sensors collect gaseous carbon dioxide content and record time points. The various sensor signals are time-aligned and scaled to form an environmental factor vector, which serves as the input for the subsequent multimodal fusion stage.

[0068] The process parameter detection module reflects the internal state of the reaction system. An online optical sensor measures the concentration of organic carbon in the solution and extracts characteristic quantities related to carbon conversion. A microbial activity sensor outputs an activity index, quantifying the metabolic state within the system. Dissolved oxygen, pH, and conductivity sensors measure oxygen content, pH, and conductivity, respectively, providing supplementary information on the system's reaction conditions. All signals are processed synchronously and noise is removed to construct a process state vector.

[0069] The multimodal data fusion module takes into account environmental factor vectors from the environmental factor acquisition module and process state vectors from the process parameter detection module. First, the two types of vectors are aligned along the time axis, and sampling interval differences are handled through interpolation. Then, trend information, fluctuation information, and the relationship between the reaction state and environmental changes are extracted from the data to construct a unified feature matrix. Based on the feature matrix, a state representation model describing the coupling relationship between the environment and the reaction system is established, outputting the system state vector.

[0070] The intelligent control and decision-making module receives the system state vector and compares it with the control target, generating an error signal based on the difference. This error signal is used to construct a control parameter vector, which includes control quantities such as temperature, pH, dissolved oxygen, light intensity, and gas flow rate. Based on a multi-objective optimization strategy, the system solves for parameters among objectives such as carbon conversion efficiency, stability, and energy consumption, obtaining control commands that satisfy the constraints. These control commands are recorded as a control strategy log for closed-loop correction and subsequent iterations.

[0071] The execution module receives the control parameter vector and controls the specific execution device. The temperature controller adjusts the reaction system temperature according to the temperature command. The light controller adjusts the light intensity and spectral composition according to the light command. The fluid pump drives the solution flow according to the flow command, and the gas regulator adjusts the gas input according to the gas supply command. The acid-base adjustment device adds a regulator to the reaction system according to the acidity / alkalinity command to bring the acidity / alkalinity value to the target range. The execution module feeds back the system state after execution to the closed-loop module.

[0072] The feedback closed-loop module collects the actual state of the system after execution and compares it with the target state to obtain a deviation signal. This deviation signal is then sent to the intelligent control and decision-making module, which corrects the control parameter vector. The closed-loop module supports multiple iterations; the continuous input of the deviation signal updates the control strategy during the execution phase, ensuring stable system operation even under fluctuating environmental factors.

[0073] Finally, it should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments or make equivalent substitutions for some of the technical features. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. An intelligent environmental factor-responsive organic carbon conversion regulation system, characterized in that, Includes the following modules: The environmental factor acquisition module is used to collect multidimensional environmental factors of the environment in which the reaction system is located and form an environmental factor vector. The process parameter detection module is used to collect data on solution organic carbon concentration, microbial activity, dissolved oxygen content, pH, and conductivity online to form a process state vector. The multimodal data fusion module is used to extract features, normalize and analyze trends of the environmental factor vector and process state vector, and to establish a system state vector to characterize the dynamic relationship between changes in environmental factors and changes in the state of the reaction system. The intelligent control and decision-making module is used to generate a control parameter vector based on the system state vector, including temperature, pH, dissolved oxygen, light and gas flow control commands, and to comprehensively optimize carbon conversion efficiency, environmental stability and energy consumption through a multi-objective optimization strategy. The execution module is used to adjust the temperature controller, light controller, fluid pump, gas regulator and pH adjustment device according to the control parameter vector to realize the dynamic control of the organic carbon conversion process; The feedback closed-loop module is used to collect the system status after execution and feed back the deviation signal to the intelligent control and decision module to realize closed-loop control.

2. The intelligent environmental factor-responsive organic carbon conversion regulation system according to claim 1, characterized in that, The environmental factor collection includes: A temperature sensor array is deployed to collect temperature distribution data at different locations within the system, and the data is read synchronously via a signal acquisition board. A humidity sensor collects humidity data from the air and solution surface, removes noise through a filter, and generates a continuous time series. A light sensor collects light intensity and spectral distribution, and uses spectral decomposition methods to extract key light band features. pH electrodes and redox potential sensors collect the acidity, alkalinity, and redox state of the solution, and use a digital conversion module to generate a calculable numerical signal. A CO2 concentration sensor collects the CO2 content in the gas phase and combines it with timestamps to generate a multidimensional environmental factor vector. The vector, after being standardized, is output to the multimodal data fusion module, providing basic input for reaction state analysis.

3. The intelligent environmental factor-responsive organic carbon conversion regulation system according to claim 1, characterized in that, The process parameter detection includes: The concentration of organic carbon in solution was measured using an online optical sensor, and the characteristics of carbon conversion rate and total organic carbon content were extracted. Microbial activity sensors monitor the microbial activity index within the system, and construct a reactivity index by combining dissolved oxygen, pH, and conductivity data. The collected data undergoes time-series synchronization processing, filtering, and denoising, and a process state vector is generated. The output process state vector is sent to the multimodal data fusion module for joint analysis with environmental factor vectors.

4. The intelligent environmental factor-responsive organic carbon conversion regulation system according to claim 1, characterized in that, The multimodal data fusion includes: Receive environmental factor vectors and process state vectors, and perform alignment and interpolation to eliminate sampling differences; Extract trend features, fluctuation features, and environment-response correlation features to construct a feature matrix; The feature matrix is ​​modeled using a state-space model to generate a system state vector, which is then output to the intelligent control and decision-making module.

5. The intelligent environmental factor-responsive organic carbon conversion regulation system according to claim 1, characterized in that, The multimodal data fusion further includes: Construct a state-space model between environmental factors and system state to describe the impact of environmental changes on carbon conversion; The model is used to predict the short-term system state, providing a basis for decision-making in the intelligent control and regulation module.

6. The intelligent environmental factor-responsive organic carbon conversion regulation system according to claim 1, characterized in that, The intelligent control decision-making includes: Receive the system state vector, combine it with the preset control target and historical operating data, and calculate the error vector that deviates from the target state; A multi-objective optimization strategy is used to generate a vector of control parameters, including temperature, pH, dissolved oxygen, light intensity, and gas flow control commands. Output the control parameter vector to the execution module and provide control strategy logs for subsequent closed-loop analysis.

7. The intelligent environmental factor-responsive organic carbon conversion regulation system according to claim 1, characterized in that, The intelligent control decision-making further includes: A multi-objective optimization function was established, with carbon conversion efficiency, system stability, and energy consumption as optimization objectives; Use constraints to ensure that the control parameters are within a safe range; The optimized control parameter vector is output to the execution module to achieve efficient dynamic control.

8. The intelligent environmental factor-responsive organic carbon conversion regulation system according to claim 1, characterized in that, The execution module includes: Receive the control parameter vector and control the temperature controller to adjust the system temperature; The lighting controller adjusts the light intensity and spectral combination. Control the fluid pump and gas regulator to achieve solution flow and gas introduction; A pH adjustment device is used to regulate acidity and alkalinity. The system status after execution is output to the feedback closed-loop module to realize closed-loop information collection.

9. The intelligent environmental factor-responsive organic carbon conversion regulation system according to claim 1, characterized in that, The feedback loop includes: The actual system state output by the acquisition and execution module is collected, and the deviation signal between the actual state and the target state is calculated. The deviation signal is transmitted to the intelligent control decision module, triggering the adaptive control parameter correction. It supports multiple rounds of iterative closed-loop operation, enabling the system to maintain a stable state under fluctuations in environmental factors.

10. The intelligent environmental factor-responsive organic carbon conversion regulation system according to claim 1, characterized in that, The feedback loop further includes: The intelligent control strategy parameters are adjusted based on the deviation signal, so that the control parameter vector is dynamically corrected according to the system state. It supports closed-loop iterative updates, enabling continuous optimization of the carbon conversion process and stable system operation under changes in environmental factors.

Images