A high-efficiency air purification system combining photocatalysis and biological reaction

Abstract

The application provides a kind of high efficiency air purification system of mixed photocatalysis and biological reaction, it is related to biological air purification technical field, system includes photocatalytic reaction module, biological reaction module, intelligent control module, sensor monitoring module, data analysis and optimization module, modular and self-maintenance module, adopts system combination photocatalytic reaction and biological reaction module, adopts multi-stage degradation and efficient decomposition processing mode, photocatalytic reaction module first degrades pollutants in air into intermediate products, then biological reaction module further degrades these intermediate products using microorganisms, finally realizes thorough purification, this multi-stage synergistic reaction not only significantly improves air purification efficiency, but also ensures complete removal of pollutants during the treatment process, reduces environmental risk, dynamically adjusts each index in the degradation process through multi-objective optimization algorithm, ensures that each stage achieves optimal effect, further improves the performance and stability of the whole system.

Description

Technical Field

[0001] This invention relates to the field of biological air purification technology, specifically a high-efficiency air purification system that combines photocatalysis and biological reaction. Background Technology

[0002] According to the cleanroom equipped with a non-thermal plasma air disinfection and purification device disclosed in Chinese Publication No. CN101922765B, the cleanroom includes an air purification unit, a reactor power supply, a fan, a cleanroom, a fresh air system, a controller, a return air trench, an air filter, a static pressure box, a return air duct, and a grid floor. The air purification unit is installed in the static pressure box at the top of the cleanroom, forming an airtight environment. The air purification unit is a plasma reactor, which contains several positive electrodes made of nickel-chromium metal wires or metal strips arranged in parallel at equal distances on the same plane. Both ends are fixed in corresponding grooves or protrusions on conductive rails that prevent micro-discharge. The switching tube in the reactor power supply is a single-ended flyback inverter. This invention provides a cleanroom with comprehensive air purification and disinfection effects, high efficiency, low energy consumption, low noise, simple structure, low maintenance costs, and long service life. It can be used in industrial cleanrooms or biological cleanrooms.

[0003] According to the photocatalytic air purifier control system disclosed in Chinese patent application CN116447711A, the intake volume of polluted air is adjusted by controlling the speed of the electric motor. After being drawn in, the polluted air first passes through the filter layer in the air purification unit to adsorb suspended particles, and then, under the irradiation of the photocatalyst by the ultraviolet lamp, it undergoes a chemical reaction with harmful gases to achieve purification. Finally, the clean air is discharged from the outlet. Specifically, the speed of the electric motor and the power control of the ultraviolet lamp are as follows: the air quality detection unit detects the air quality signal, which enters the graded pre-processing unit and is compared with the air quality signals corresponding to API Level 5 and Level 3 standards in sequence. The control signal is output to the circuit control unit with +5V, proportional factor value, and charging voltage. The microcontroller drives the electric motor / ultraviolet lamp to connect to the power supply for full speed / full power, variable speed / variable power control, and intermittent operation control. It can automatically adjust the intake and exhaust volume of the fan and the power of the ultraviolet lamp according to the control quality signal.

[0004] The aforementioned patent documents and prior art have the following technical problems when used:

[0005] Problem 1: Most existing air purification technologies rely on a single photocatalytic or biological reaction method. However, a single treatment mode is often difficult to completely degrade complex organic pollutants. Although traditional photocatalytic technology can effectively degrade some pollutants, it is often limited by the type and concentration of pollutants. Biological reactions require a long time and are weak in their ability to degrade intermediate products. Due to the limitations of these technologies, existing systems often suffer from low degradation efficiency and incomplete purification when faced with diverse pollutants.

[0006] Question 2: Most traditional air purification equipment is based on a fixed working mode and cannot automatically adjust its working parameters according to changes in actual pollutant concentration and environmental conditions. This makes the system often inefficient in different working environments. Even when the pollutant concentration is low, it still consumes a lot of energy, resulting in low energy efficiency and high operation and maintenance costs. It also has poor adaptability to environmental conditions and often cannot make flexible adjustments when the type, concentration and rate of change of pollutants are different, which makes the system unable to achieve the best treatment effect in certain specific environments.

[0007] Thirdly, existing air purification systems often suffer from complex structures and redundant components, making maintenance and upgrades difficult and incurring high operation and maintenance costs. Since the various reaction and control modules typically lack independence and modular design, extensive manual intervention is required when expanding or repairing the system, affecting its operability and maintenance efficiency. Summary of the Invention

[0008] Technical problems to be solved

[0009] To address the shortcomings of existing technologies, this invention provides a highly efficient air purification system that combines photocatalysis and biological reaction, solving the following problems:

[0010] 1. Addressing the problem that a single method of air pollution treatment leads to low pollutant degradation efficiency and difficulty in achieving complete purification;

[0011] 2. Addressing the issue of poor environmental adaptability and flexibility due to the lack of intelligent adjustment mechanisms;

[0012] 3. Addressing the issues of high system complexity and high operation and maintenance costs in the Jinghu system.

[0013] Technical solution

[0014] To achieve the above objectives, the present invention provides the following technical solution: a high-efficiency air purification system combining photocatalysis and biological reaction, the system comprising a photocatalytic reaction module, a biological reaction module, an intelligent control module, a sensor monitoring module, a data analysis and optimization module, and a modular and self-maintaining module, wherein:

[0015] The photocatalytic reaction module is used to perform photocatalytic degradation of pollutants in the air. It includes nanostructured photocatalytic materials such as TiO2 and ZnO and high-efficiency light source components. Through the action of light, organic pollutants are oxidized and decomposed into small molecules or harmless gases. The light source intensity and reaction time are adjusted by fuzzy logic control algorithm to adapt to changes in the concentration of pollutants in the air.

[0016] The bioreactor module is used to process intermediate products after photocatalytic degradation, achieving secondary degradation and thorough purification. It includes a microbial community (such as a specific bacterial community that degrades VOCs) and reactor components. It further degrades pollutants through biological metabolism, dynamically optimizes the selection of microbial communities through genetic algorithms, and adjusts metabolic pathways by combining reinforcement learning to improve bioreactor efficiency.

[0017] The intelligent control module is used to coordinate and schedule the various modules of the system, including an intelligent coordination mechanism and a real-time controller. It achieves synchronous operation of photocatalysis and biological reaction through a rule base and control strategy, and dynamically adjusts the working parameters of photocatalysis and biological reaction through a particle swarm optimization algorithm to ensure the maximization of synergistic effect.

[0018] The sensor monitoring module is used to monitor environmental parameters such as air quality, pollutant concentration, temperature and humidity in real time. It includes multimodal sensors and a monitoring network. It acquires multi-dimensional data through high-sensitivity sensing technology and analyzes changes in environmental parameters through multi-objective optimization algorithms to provide real-time control basis for the system.

[0019] The data analysis and optimization module is used to analyze system operating data and pollutant degradation efficiency, and provide intelligent optimization solutions. It includes a data acquisition device and an optimization model. It predicts failure risks and proposes maintenance suggestions through the support vector machine (SVM) algorithm, and learns historical data and environmental characteristics through the reinforcement learning algorithm to optimize system operation strategies and ensure long-term stable operation.

[0020] The modular and self-maintaining module is used to realize the modular design and automatic maintenance of the system. It includes independent photocatalysis module, bioreaction module and control module. The modular design simplifies the expansion and upgrading of the system.

[0021] Preferably, the light source component of the photocatalytic reaction module adopts a high-intensity ultraviolet light source with adjustable function, which can intelligently adjust the light intensity under different pollutant concentrations. It uses high-surface-area nano-photocatalytic materials, and optimizes the photocatalytic performance of the materials through surface chemical modification and nanostructure design. Combined with fuzzy logic control algorithm, it dynamically adjusts the light source intensity and reaction time according to real-time sensor monitoring data, including pollutant concentration, temperature and humidity, to adapt to different air quality changes. The free radicals and gaseous oxides generated in the photocatalytic degradation reaction can interact with the microorganisms in the bio-reaction module to promote further degradation of pollutants.

[0022] Preferably, the bioreaction module employs intelligent regulation of the microbial community, optimizing the metabolic pathways and community structure of the microorganisms through genetic algorithms and reinforcement learning algorithms. Specific species in the microbial community can efficiently degrade organic pollutants and their degradation products, and possess strong environmental adaptability. The genetic algorithm optimizes the microbial genome by simulating natural selection, enabling it to adapt to different pollutant characteristics and improve the degradation rate. The reinforcement learning algorithm further enhances the bioreaction efficiency by dynamically adjusting the metabolic pathways of the microorganisms and learning changes in pollutant characteristics and environmental conditions.

[0023] Preferably, the rule base of the intelligent control module controls the working mode of each module in real time by intelligently analyzing pollutant type, concentration and environmental parameters (such as temperature and humidity). The particle swarm optimization algorithm optimizes the synergistic working time and intensity of photocatalysis and biological reaction based on sensor monitoring data to achieve the best degradation efficiency, provide adaptability to different working states, and automatically adjust the working ratio of each module when the pollutant concentration changes to ensure efficient system operation.

[0024] Preferably, the multimodal sensor network of the sensor monitoring module integrates gas sensors, temperature and humidity sensors, and particulate matter sensors, enabling real-time monitoring of the concentration of multiple pollutants in the air. The multi-objective optimization algorithm performs real-time analysis of multi-source sensor data, predicts air quality change trends, and provides adjustment suggestions to the intelligent control module. The high-sensitivity sensing technology ensures accurate capture of pollutant changes even under low-concentration pollutant conditions and timely response.

[0025] Preferably, the data acquisition unit of the data analysis and optimization module collects data from the sensors, reaction module, and control module in real time to ensure the timeliness and accuracy of the information. The SVM algorithm classifies the operating status of the equipment, predicts possible system failures, and proposes maintenance suggestions. The reinforcement learning algorithm automatically adjusts the system's operating strategy based on historical operating data and environmental characteristics to ensure long-term stable operation.

[0026] Preferably, the modular and self-maintaining modules enable each module of the system to be independent, allowing for dynamic switching or addition / removal of modules based on different pollutant concentrations. Through automatic detection and self-maintaining technologies, the system can achieve self-cleaning, automatic repair, and maintenance of modules, ensuring long-term efficient operation. Furthermore, each module adopts a standardized interface design, supporting rapid expansion and upgrades of the system. The self-maintaining mechanism includes automatic cleaning of photocatalytic materials, self-regulation of the microbial community, and periodic maintenance of reactor components. Combined with the SVM algorithm, the health status of the equipment is predicted and diagnosed, allowing for early detection and repair of potential faults.

[0027] Preferably, the photocatalytic reaction module and the biological reaction module together constitute a multi-stage degradation and efficient decomposition module for pollutants. This module maximizes degradation efficiency across multiple stages through the synergistic effect of photocatalysis and biological reaction. It employs a multi-objective optimization algorithm (MOGA) to process pollutants in stages, ensuring optimal results at each stage and achieving efficient synergy between reaction stages. The photocatalytic reaction module first performs preliminary degradation on the pollutants, converting them into intermediate products. The biological reaction module further decomposes these intermediate products using microorganisms, achieving thorough purification. The MOGA algorithm optimizes multiple objectives in the multi-stage degradation process, including degradation rate, energy consumption, and system stability, and performs real-time control.

[0028] Beneficial effects

[0029] This invention provides a highly efficient air purification system that combines photocatalysis and biological reaction. It offers the following advantages:

[0030] 1. This invention employs a system combining photocatalytic reaction and biological reaction modules, using a multi-stage degradation and efficient decomposition treatment mode. The photocatalytic reaction module first degrades air pollutants into intermediate products, and then the biological reaction module uses microorganisms to further degrade these intermediate products, ultimately achieving complete purification. This multi-stage synergistic reaction not only significantly improves air purification efficiency but also ensures the complete removal of pollutants during the treatment process, reducing environmental risks. By dynamically adjusting various indicators in the degradation process through a multi-objective optimization algorithm (MOGA), the optimal effect is ensured at each stage, further enhancing the performance and stability of the entire system.

[0031] 2. This invention integrates an intelligent control module and a sensor monitoring module. Through multimodal sensors, it monitors environmental parameters such as air quality, pollutant concentration, temperature, and humidity in real time. The intelligent control module uses a rule base and particle swarm optimization (PSO) algorithm to dynamically adjust the photocatalysis and bioreaction modules, ensuring that the system can automatically adjust the working status of each module according to real-time pollutant concentration and environmental changes. This adaptive adjustment mechanism not only improves degradation efficiency but also ensures long-term stable operation of the system under different working conditions, enhancing the system's intelligence and adaptability and reducing the need for manual intervention.

[0032] 3. This invention adopts a modular design, which makes each functional module independent and can be dynamically switched or added or removed according to different pollutant concentrations. At the same time, through automatic detection and self-maintenance technology, each module can perform self-cleaning, automatic repair and maintenance, reducing manual maintenance costs. Combined with the SVM algorithm, the health status of the equipment is predicted and diagnosed, and potential faults are detected and repaired in advance, which greatly improves the reliability and long-term operating efficiency of the system. In addition, the modular design also supports the rapid expansion and upgrading of the system, and has strong flexibility and scalability. Attached Figure Description

[0033] Figure 1 This is a system module architecture diagram of the present invention.

[0034] Figure 2 This is a data transmission flow diagram of the system modules of the present invention;

[0035] Figure 3 This is a diagram illustrating the system operation steps of the present invention;

[0036] Figure 4 This is the membership function curve for fuzzy logic control in this invention;

[0037] Figure 5 This is a diagram illustrating the optimization process of the genetic algorithm for optimizing bacterial community configuration in this invention.

[0038] Figure 6 This is a schematic diagram illustrating the change of pollutant concentration over time during the operation of the system of the present invention;

[0039] Figure 7 This is a schematic diagram illustrating the dynamic and collaborative degradation of pollutants by the system of the present invention;

[0040] Figure 8 This is a spatial thermodynamic distribution diagram of the photocatalytic efficiency of the present invention;

[0041] Figure 9 This is a schematic diagram illustrating the dynamic distribution characteristics of the airflow according to the present invention. Detailed Implementation

[0042] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some 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. Specific Implementation Example 1:

[0044] like Figures 1 to 9As shown, a high-efficiency air purification system combining photocatalysis and biological reaction is disclosed. The system includes a photocatalytic reaction module, a biological reaction module, an intelligent control module, a sensor monitoring module, a data analysis and optimization module, and a modular and self-maintaining module, wherein:

[0045] Photocatalytic reaction module: Used for photocatalytic degradation of air pollutants, including nanostructured photocatalytic materials such as TiO2 and ZnO and high-efficiency light source components. Through light irradiation, organic pollutants are oxidized and decomposed into small molecules or harmless gases. Fuzzy logic control algorithm is used to adjust the light source intensity and reaction time to adapt to changes in air pollutant concentration. The light source component of the photocatalytic reaction module adopts a high-intensity ultraviolet light source with adjustable function, which can intelligently adjust the light intensity under different pollutant concentrations. High surface area nano-photocatalytic materials are used, and the photocatalytic performance of the materials is optimized through surface chemical modification and nanostructure design. Combined with fuzzy logic control algorithm, the light source intensity and reaction time are dynamically adjusted according to real-time sensor monitoring data, including pollutant concentration, temperature and humidity, to adapt to different air quality changes. The free radicals and gaseous oxides generated in the photocatalytic degradation reaction can interact with microorganisms in the bioreactor module to promote further degradation of pollutants.

[0046] The bioreactor module is used to process intermediate products after photocatalytic degradation, achieving secondary degradation and thorough purification. It includes a microbial community (such as specific bacteria that degrade VOCs) and reactor components. Through biological metabolism, pollutants are further degraded. The selection of microbial communities is dynamically optimized through genetic algorithms, and metabolic pathways are adjusted by reinforcement learning to improve bioreactor efficiency. The bioreactor module adopts intelligent regulation of microbial communities, optimizing the metabolic pathways and community structure of microorganisms through genetic and reinforcement learning algorithms. Specific species in the microbial community can efficiently degrade organic pollutants and their degradation products and have strong environmental adaptability. The genetic algorithm optimizes the genome of microorganisms by simulating natural selection, making them adapt to different pollutant characteristics and improving the degradation rate. The reinforcement learning algorithm further improves bioreactor efficiency by dynamically adjusting the metabolic pathways of microorganisms and learning changes in pollutant characteristics and environmental conditions.

[0047] Intelligent control module: Used to coordinate and schedule the various modules of the system, including intelligent coordination mechanism and real-time controller. It realizes the synchronous operation of photocatalysis and biological reaction through rule base and control strategy. The working parameters of photocatalysis and biological reaction are dynamically adjusted through particle swarm optimization algorithm to ensure the maximization of synergistic effect. The rule base of the intelligent control module controls the working mode of each module in real time by intelligently analyzing pollutant type, concentration and environmental parameters (such as temperature and humidity). The particle swarm optimization algorithm optimizes the synergistic working time and intensity of photocatalysis and biological reaction according to sensor monitoring data to achieve the best degradation efficiency. It provides adaptability to different working states and automatically adjusts the working ratio of each module when the pollutant concentration changes to ensure the efficient operation of the system.

[0048] Sensor monitoring module: Used for real-time monitoring of environmental parameters such as air quality, pollutant concentration, temperature, and humidity. It includes multimodal sensors and a monitoring network, acquiring multi-dimensional data through high-sensitivity sensing technology and analyzing environmental parameter changes through multi-objective optimization algorithms. This provides a basis for real-time system control. The multimodal sensor network of the sensor monitoring module integrates gas sensors, temperature and humidity sensors, and particulate matter sensors, enabling real-time monitoring of the concentration of various pollutants in the air. The multi-objective optimization algorithm performs real-time analysis of multi-source sensor data, predicts air quality change trends, and provides adjustment suggestions to the intelligent control module. High-sensitivity sensing technology ensures accurate capture of pollutant changes even under low-concentration conditions and timely responses. The system integrates the intelligent control module and the sensor monitoring module. Through multimodal sensors, it monitors environmental parameters such as air quality, pollutant concentration, temperature, and humidity in real time. The intelligent control module uses a rule base and particle swarm optimization (PSO) algorithm to dynamically adjust the photocatalysis and bioreaction modules, ensuring that the system can automatically adjust the working status of each module according to real-time pollutant concentration and environmental changes. This adaptive adjustment mechanism not only improves degradation efficiency but also ensures long-term stable operation of the system under different working conditions, enhancing the system's intelligence and adaptability and reducing the need for manual intervention.

[0049] The data analysis and optimization module analyzes system operating data and pollutant degradation efficiency, providing intelligent optimization solutions. It includes a data acquisition unit and an optimization model. The module uses a Support Vector Machine (SVM) algorithm to predict failure risks and propose maintenance suggestions, and a reinforcement learning algorithm to learn from historical data and environmental characteristics, optimizing system operation strategies to ensure long-term stable operation. The data acquisition unit collects data in real time from sensors, the reaction module, and the control module, ensuring the timeliness and accuracy of information. The SVM algorithm classifies equipment operating states, predicts potential system failures, and proposes maintenance suggestions. The reinforcement learning algorithm automatically adjusts the system's operating strategy based on historical operating data and environmental characteristics, ensuring long-term stable operation.

[0050] Modular and self-maintaining modules: These modules enable modular design and automatic maintenance of the system. They include independent photocatalytic, bioreaction, and control modules. Modular design simplifies system expansion and upgrades, while the self-maintaining modules ensure the independence of each module. Modules can be dynamically switched or added / removed based on different pollutant concentrations. Through automatic detection and self-maintenance technologies, the system can achieve self-cleaning, automatic repair, and maintenance of modules, ensuring long-term, efficient operation. Each module uses a standardized interface design, supporting rapid system expansion and upgrades. The self-maintenance mechanisms include automatic cleaning of photocatalytic materials, self-regulation of the microbial community, and periodic maintenance of reactor components. Periodic maintenance, combined with SVM algorithm to predict and diagnose the health status of equipment, can detect and repair potential faults in advance. The modular design makes each functional module independent and can be dynamically switched or added or removed according to different pollutant concentrations. At the same time, through automatic detection and self-maintenance technology, each module can perform self-cleaning, automatic repair and maintenance, reducing manual maintenance costs. The combination of SVM algorithm to predict and diagnose the health status of equipment and detect and repair potential faults in advance greatly improves the reliability and long-term operating efficiency of the system. In addition, the modular design also supports the rapid expansion and upgrade of the system, which has strong flexibility and scalability.

[0051] The photocatalytic reaction module and the biological reaction module together constitute a multi-stage degradation and efficient decomposition module for pollutants. This module maximizes degradation efficiency across multiple stages through the synergistic effect of photocatalysis and biological reaction. It employs a multi-objective optimization algorithm (MOGA) to treat pollutants in stages, ensuring optimal results at each stage and achieving efficient synergy between reaction stages. The photocatalytic reaction module first performs preliminary degradation of pollutants, converting them into intermediate products. The biological reaction module further decomposes these intermediate products using microorganisms, achieving complete purification. The MOGA algorithm optimizes the multi-stage degradation process. The system targets multiple objectives, including degradation rate, energy consumption, and system stability, and adjusts them in real time. It combines photocatalytic and biological reaction modules, employing a multi-stage degradation and efficient decomposition treatment mode. The photocatalytic reaction module first degrades air pollutants into intermediate products, and then the biological reaction module uses microorganisms to further degrade these intermediate products, ultimately achieving complete purification. This multi-stage synergistic reaction not only significantly improves air purification efficiency but also ensures the complete removal of pollutants during the treatment process, reducing environmental risks. Through a multi-objective optimization algorithm (MOGA), various indicators in the degradation process are dynamically adjusted to ensure that each stage achieves optimal results, further enhancing the performance and stability of the entire system. Specific Implementation Example 2:

[0053] like Figures 1 to 9As shown, based on the content of the above specific embodiments, the following content is further disclosed:

[0054] Based on the system structure, the runtime steps of each module in the entire system are as follows:

[0055] SP1: Sensor Monitoring and Data Acquisition

[0056] The multi-modal sensors in the sensor monitoring module collect air quality parameters in real time, including multi-dimensional data such as pollutant concentration, temperature, humidity, and particulate matter. The collected data is transmitted to the data analysis and optimization module for preliminary processing. The data analysis and optimization module analyzes the air quality change trend in real time through a multi-objective optimization algorithm, providing a basis for the operation and control of subsequent modules.

[0057] SP2: Intelligent Control Module Scheduling Mode

[0058] The intelligent control module obtains air quality analysis results from the data analysis and optimization module, determines the types and concentration characteristics of pollutants by combining the rule base, and uses the particle swarm optimization algorithm (PSO) to dynamically adjust the working parameters of the photocatalytic reaction module and the biological reaction module, including light source intensity, reaction time, biological metabolic rate, etc. According to changes in environmental conditions, it intelligently coordinates the operating ratio of each module to ensure that the synergistic effect of photocatalysis and biological reaction is maximized.

[0059] Sp3: Photocatalytic reaction module treats primary pollutants.

[0060] The photocatalytic reaction module uses nanostructured photocatalytic materials (such as TiO2 and ZnO) under the action of a high-efficiency ultraviolet light source to oxidize and decompose organic pollutants in the air into intermediate products or harmless gases. The fuzzy logic control algorithm dynamically adjusts the light source intensity and reaction time according to sensor feedback to adapt to changes in air quality. The air after primary treatment is transmitted to the bio-reaction module for secondary purification.

[0061] Sp4: Intermediate product of deep degradation of bioreaction module

[0062] The bioreactor module uses specific microbial communities (such as bacteria that degrade VOCs) to perform secondary degradation on intermediate products after photocatalytic reaction, achieving thorough purification. The genetic algorithm optimizes the population structure of microorganisms to adapt to different pollutant characteristics, and the reinforcement learning algorithm adjusts the metabolic pathways of microorganisms in real time to dynamically optimize biodegradation efficiency according to environmental changes.

[0063] Sp5: Multi-stage degradation and synergistic treatment of pollutants

[0064] The photocatalytic reaction module and the biological reaction module work together to form a multi-stage degradation and efficient decomposition module for pollutants. The multi-objective optimization algorithm (MOGA) dynamically optimizes the reaction efficiency at each degradation stage, including degradation rate, energy consumption and system stability, to ensure the gradual and complete decomposition of pollutants.

[0065] SP6: System Operation Status Monitoring and Optimization

[0066] The data analysis and optimization module analyzes system operation data in real time, including pollutant degradation efficiency, module operating parameters, equipment status, etc. The support vector machine (SVM) algorithm predicts possible system failures, generates maintenance suggestions and feeds them back to the modular and self-maintenance module. The reinforcement learning algorithm optimizes the system operation strategy based on historical operation data to improve long-term stability and adaptability.

[0067] SP7: Modular Operation and Self-Maintenance Mechanism Activation

[0068] The modular and self-maintenance module dynamically switches the working ratio of the photocatalysis and bioreaction modules according to the operating status, or adds or removes modules to cope with changes in pollutant concentration. The system activates automatic cleaning, repair and maintenance functions, including automatic cleaning of photocatalytic materials, self-regulation of microbial communities and periodic maintenance of reactor components. The system can be rapidly expanded and upgraded through standardized interfaces to ensure long-term efficient operation.

[0069] SP8: System Intelligent Feedback and Closed-Loop Optimization

[0070] The system compares the operating results with the sensor monitoring data to evaluate the air purification effect. Based on the feedback, it adjusts the parameters of the photocatalytic reaction module and the biological reaction module in real time to form a closed-loop optimization mechanism, ensuring that the pollutant treatment efficiency is always at the best level, while saving energy and reducing operating costs.

[0071] The entire system achieves efficient air purification under different environmental conditions through intelligent sensing and monitoring, dynamic adjustment, and modular design. The synergistic effect of photocatalysis and bioreaction modules ensures multi-stage degradation and thorough purification of pollutants, while optimizing energy efficiency and system stability. The intelligent control module and self-maintenance mechanism continuously optimize operating parameters and maintenance strategies based on real-time data, realizing the system's adaptive adjustment and long-term efficient operation. The combination of these steps not only improves the air purification effect but also effectively reduces energy consumption and operation and maintenance costs, ensuring the system's flexibility and scalability. Specific Implementation Example 3:

[0073] like Figures 1 to 9 As shown, based on the content of the above specific embodiments, the following content is further disclosed:

[0074] The algorithmic content of each module in the entire system further includes the following:

[0075] The following are the relevant mathematical formulas, explanations, implementation steps, operating logic, and beneficial effects of the algorithms involved in each module:

[0076] Photocatalytic reaction module - fuzzy logic control algorithm:

[0077] Fuzzy logic control systems are based on fuzzy rule bases. Their core computational process involves steps such as fuzzification, fuzzy inference, and defuzzification. Taking adjusting light source intensity as an example, let the pollutant concentration be the input variable x (unit: mg / m³). 3 The light source intensity is the output variable y (unit: W), and the fuzzy rule is in the form of:

[0078] If xisA1thenyisB1

[0079] If xisA2thenyisB2 ...

[0081] Among them, A i It is a fuzzy subset description of pollutant concentration (such as "low concentration", "medium concentration", "high concentration", etc.), B i It is a fuzzy subset description of the corresponding light source intensity (such as "low intensity", "medium intensity", "high intensity", etc.), x represents the real-time monitored concentration of pollutants in the air, which is the input of the algorithm and determines the direction of subsequent adjustment of the light source intensity, y represents the light source intensity to be adjusted, which is the output of the algorithm and directly affects the photocatalytic reaction efficiency;

[0082] The fuzzification process transforms the actual pollutant concentration values ​​into membership degrees to each fuzzy subset using a membership function. For example, for a Gaussian membership function:

[0083]

[0084] in, It is a fuzzy subset A i The central value, It is its standard deviation, which indicates that the current pollutant concentration x belongs to the fuzzy subset A. i To what extent, This indicates that the current pollutant concentration x belongs to the fuzzy subset A. i membership degree Determine the center location of the fuzzy subset, i.e., the typical pollutant concentration value. Controlling the "width" of the membership function reflects the sensitivity to fuzzy division of concentration values;

[0085] Fuzzy inference is based on fuzzy rules. Commonly used inference methods include Mamdani inference. By calculating the activation intensity of each rule (i.e., the product or minimum of the membership degrees of the premises), a fuzzy set of the output variable is obtained.

[0086] Finally, deblurring converts the blurred output into precise values. Common methods include the centroid method.

[0087]

[0088] Among them, y i It is a fuzzy subset B i The corresponding typical values ​​(e.g., 10W for "low strength", 30W for "medium strength", etc.) Output the membership degree of the fuzzy subset;

[0089] As pollutant concentrations change, the system continuously re-evaluates the input membership degree through fuzzy logic algorithms, thereby dynamically adjusting the light source intensity. For example, when pollutant concentrations increase, the membership degree shifts to the "high concentration" subset. After inference and defuzzification, the light source intensity increases to accelerate the photocatalytic reaction rate, ensuring effective treatment of air with different levels of pollution. It can handle complex and nonlinear input-output relationships without requiring precise mathematical models. It can flexibly respond to fluctuations in pollutant concentrations under different environments, improving the adaptability of the photocatalytic reaction module to varying air quality. The redundancy and fuzziness of the fuzzy rules enable the system to operate stably even when there are certain errors in sensor data or environmental interference, ensuring the rationality of light source intensity adjustment and maintaining the purification effect.

[0090] Biological reaction module - genetic algorithm:

[0091] In the scenario of optimizing the microbial community structure, let the genome of the microbial community be represented by binary encoding (each bit represents the presence or absence of a certain gene feature), let the population size be N, the gene length be L, and the gene representation of individual i be g. i =[g i1 g i2 , ..., g iL Fitness function F(g) i This measures the effectiveness of an individual in degrading pollutants, for example, by the rate of degradation of the target pollutant per unit time.

[0092]

[0093] Where m0 is the initial pollutant mass, m t It is the mass of the remaining pollutants after time t.

[0094] The main operations of genetic algorithms include selection, crossover, and mutation:

[0095] Selection: Fitness-based roulette wheel selection, where the probability P of individual i being selected is... i for:

[0096]

[0097] Crossover: Randomly select two individuals g a and g b A crossover operation is performed at a random position k (1≤k<L) to generate two offspring individuals:

[0098]

[0099] Mutation: with a certain probability p m To perform mutation operations on each individual gene, that is, g ij Invert (if g) ij = 0 becomes 1, and vice versa;

[0100] Starting with a random initial microbial community structure, the genetic algorithm continuously selects individuals with high fitness for reproduction, gene recombination, and mutation. This allows the microbial community to gradually optimize its ability to degrade pollutants during genetic evolution, adapting to the characteristics of different pollutants. Each generation of the population evolves towards higher degradation efficiency. It can search in a complex microbial community structure combination space, avoiding getting trapped in local optima, and find the optimal microbial community configuration adapted to different pollutants. This improves the bioreaction module's ability to degrade multiple pollutants. As pollutant characteristics change (such as fluctuations in composition and concentration), the genetic algorithm continuously optimizes the microbial community. There is no need for precise pre-setting of the microbial community structure, enabling the bioreaction module to dynamically adapt to the environment and maintain high-efficiency purification in the long term.

[0101] Biological Response Module - Reinforcement Learning Algorithm:

[0102] In the scenario of adjusting microbial metabolic pathways, taking the Q-learning algorithm as an example, let S be the set of environmental states of the microorganism (including pollutant types, concentrations, environmental temperature and humidity, etc.), and A be the set of actions the microorganism can take (such as choosing different metabolic pathways, regulating the activity of metabolic enzymes, etc.). Define the Q-value function Q(s, a) as the expected cumulative reward for taking action a∈A in state s∈S, and continuously update iteratively:

[0103]

[0104] Where α is the learning rate (0 < α < 1), which determines the degree to which newly acquired experience updates the old Q value; γ is the discount factor (0 < γ < 1), used to weigh the importance of future rewards against current rewards; r is the immediate reward obtained after performing action a, which is usually related to the degradation effect of microorganisms on pollutants under this action, such as an increase in the amount of degradation; s' is the new environmental state transitioned to after performing action a.

[0105] Implementation steps:

[0106] Initialization: For all s∈S and a∈A, initialize Q(s, a) to a random or empirically preset value;

[0107] Environmental perception: Microorganisms perceive the current environmental state in real time, including information such as pollutant concentration, temperature and humidity obtained from the sensor monitoring module;

[0108] Action selection: Based on the current Q(s, a) value, select action a from A using a certain strategy (such as a greedy strategy, i.e., randomly select an action with probability ∈ to explore new strategies, or select the action with the largest current Q value with probability 1-∈ to utilize existing experience);

[0109] Action execution: The microorganism performs the selected action a, changes its metabolic pathway, and carries out a biological reaction. At the same time, the environmental state changes to s' and it receives an immediate reward r.

[0110] Q-value update: According to the formula Q(s, a) ← Q(s, a) + α[r + γmax] a' Update the value of Q(s, a) by [Q(s, a)] - Q(s, a);

[0111] Iteration: Repeat the steps of environmental awareness, action selection, action execution, and Q-value update to continuously learn and optimize the metabolic strategy.

[0112] Microorganisms continuously explore different metabolic actions in response to environmental changes, adjusting their strategies based on immediate rewards and expectations of future rewards (represented by Q-values). As the learning process progresses, they gradually focus on metabolic pathways that yield the best degradation results under different environments, achieving dynamic optimization. They can respond in real time to environmental changes (such as sudden changes in pollutant concentrations or fluctuations in temperature and humidity), autonomously learning and adjusting their metabolic pathways to ensure that the bioreaction module maintains high degradation efficiency under various operating conditions. Through continuous learning, microorganisms "remember" past successful and unsuccessful strategies, gradually forming optimal response patterns for different environmental conditions, reducing reliance on human intervention and lowering operational complexity.

[0113] Intelligent Control Module - Particle Swarm Optimization Algorithm:

[0114] Let the operating parameters of the photocatalytic reaction module and the bioreaction module constitute the particle position vector X. i =[x i1 x i2 , ..., x in ], where n is the number of parameters (such as photocatalytic light source intensity, reaction time, biological reaction metabolic rate, etc.), and the particle velocity vector is V. i =[v i1 v i2 , ..., vin , and each particle also has its individual best position P i (the best parameter combination found by itself during the historical search process), the global best position G (the best parameter combination found by the entire particle swarm). The particle position and velocity update formulas are as follows:

[0115] v ij (t + 1) = w·v ij (t) + c1·r1·(p ij -x ij (t)) + c2·r2·(g j -x ij (t))

[0116] x ij (t + 1) = x ij (t) + v ij (t + 1)

[0117] Among them, t represents the iteration number, w is the inertia weight (0 < w < 1), which balances the global exploration and local exploitation capabilities of the particle; c1 and c2 are learning factors (usually C1, c2 > 0), which respectively adjust the step sizes for the particle to approach its own best and the global best; r1 and r2 are random numbers uniformly distributed in the interval [0, 1].

[0118] Implementation steps:

[0119] Initialization: Randomly initialize the positions X i and velocities V i of a group of particles within the parameter value range, and set the initial individual best P i of each particle to be equal to X i . By evaluating the system performance indicators corresponding to the initial particle positions (such as pollutant degradation efficiency, energy consumption, etc.), find the global best position G;

[0120] Iterative update:

[0121] For each particle i, calculate and update the velocity Y i (t + 1) according to the formula. The velocity update consists of three parts: The first term w·v ij (t) is based on the current velocity of the particle, maintaining the motion inertia; the second term c1·r1·(p ij -x ij (t)) makes the particle approach its own historical best position, reflecting the learning of its own experience; the third term c2·r2·(g j -x ij (t)) drives the particle to move towards the global best position, leveraging the collective wisdom;

[0122] According to the updated velocity, through x ij (t + 1) = xij (t)+v ij (t+1) Calculate the new particle position to obtain a new set of working parameters for the photocatalysis and bioreaction module;

[0123] Evaluate the system's performance metrics at the new position. If the performance of a particle at its new position is better than that at its individual optimal position P, then... i Then update P i =X i (t+1), if the performance of the new position is better than that of the globally optimal position G, update G = X. i (t+1);

[0124] Termination condition judgment: Repeat the iterative update steps until the preset number of iterations is reached, or the performance index corresponding to the global optimal position changes less than the set threshold for multiple consecutive times. At this time, the algorithm is considered to have converged, and the working parameters corresponding to the global optimal position G are output as the optimal configuration.

[0125] The particle swarm initially "flies" randomly in the parameter space. By continuously comparing itself, its companions, and historical experience, it dynamically adjusts its flight direction and speed, gradually converging in the high-performance parameter region. For example, when a particle discovers that moving closer to its historical best parameters can improve the system's degradation efficiency, it will increase its tendency to move in that direction. If a particle in the swarm finds a better global solution, other particles will also be attracted to it, iterating and optimizing repeatedly. Compared to the traditional exhaustive method, it does not need to traverse all possible parameter combinations. Through inter-particle collaboration and self-learning, it quickly locates near-optimal photocatalytic and biological reaction operating parameters, greatly reducing computational load and time costs, and improving system debugging and optimization efficiency. As environmental parameters (such as pollutant concentration, temperature, and humidity) change, the particle swarm can restart the optimization process to find the best parameters adapted to the new operating conditions, ensuring that the system always maintains efficient and collaborative operation and effectively copes with complex and ever-changing air purification needs.

[0126] Sensor Monitoring Module - Multi-Objective Optimization Algorithm:

[0127] Suppose the objective to be optimized is the accuracy f1 of air quality prediction (which can be measured by the mean square error between the predicted and actual values).

[0128]

[0129] Where m is the number of samples, y i This is the actual air quality value. It includes multiple objectives such as predicted value, sensor energy consumption f2 (energy consumption per unit time), and real-time monitoring data performance f3 (data delay time);

[0130] Define the comprehensive objective function F(X):

[0131] F(X) = w1·f1(X) + w2·f2(X) + w3·f3(X)

[0132] Where X is the decision variable, including factors such as sensor sampling frequency and data transmission strategy that affect each objective; w1, w2, and w3 are the weights corresponding to the objectives, and w1 + w2 + w3 = 1. The weights reflect the relative importance of each objective in the optimization process and are set by the user according to actual needs.

[0133] Implementation steps:

[0134] Initialization: Given the initial decision variable X0, including setting the initial sampling frequency, data transmission method, etc., and calculating the values of each objective function f1(X0), f2(X0), f3(X0) according to the initial settings, and then obtaining the value of the comprehensive objective function F(X0);

[0135] Neighborhood search: By changing the value of the decision X, such as fine-tuning the sampling frequency, switching the transmission protocol, etc., generate a set of neighborhood solutions X i (i = 1, 2,..., k), and calculate their corresponding comprehensive objective function values F(X i );

[0136] Comparison and selection: Compare the comprehensive objective function values of the neighborhood solutions with the current solution F(X0). If there exists a neighborhood solution X j such that F(X j ) < F(X0), then update the current solution X0 = X j ; Otherwise, keep the current solution unchanged;

[0137] Iteration: Repeat the neighborhood search, comparison and selection steps until the termination condition is met, such as reaching the preset number of iterations, the comprehensive objective function value converges to a certain accuracy, or the values of each objective function reach the satisfactory interval set by the user.

[0138] Starting from the initial monitoring configuration, continuously explore possible improvement solutions in the surrounding area. Each time, evaluate the pros and cons of the new solution based on the comprehensive objective function, and gradually optimize in the direction of accurate air quality prediction, low sensor energy consumption, and good data real-time performance. For example, if it is found that appropriately reducing the sampling frequency (within the acceptable prediction error) can significantly reduce energy consumption, update the configuration; if the new transmission protocol can balance the improvement of real-time performance and energy consumption control, also switch in time, dynamically adapt to the requirements, overcome the limitations of single-objective optimization, take into account the multi-faceted needs of air quality monitoring, avoid neglecting one thing while attending to another, achieve the coordinated improvement of accurate monitoring, energy-saving and efficient, and timely response, lay a solid foundation for the stable operation of the entire air purification system. Through weight adjustment, it fits the key requirements of different application scenarios and different stages. Whether it is high-precision monitoring in scientific research, energy-saving operation in business, or rapid response in an emergency, it can accurately optimize the sensor monitoring strategy and maximize the system benefits.

[0139] Data Analysis and Optimization Module - Support Vector Machine (SVM) Algorithm:

[0140] Let the training sample set be:

[0141] {(x1,y1),(x2,y2),…,(x m y m )}

[0142] Where, x i It is a sample feature vector (containing various operational data collected by sensors, such as pollutant degradation efficiency, module operating parameters, equipment temperature, etc.); y i ∈{-1, 1} is the class label of the sample (-1 indicates failure, 1 indicates normal);

[0143] The goal of SVM is to find a hyperplane ω·x+b=0 such that the two classes of samples lie on opposite sides of the hyperplane with the maximum margin. This is achieved by solving the following optimization problem:

[0144]

[0145] subjecttoy i (ω·x i +b)≥1, fora / / i=1, 2,…,m

[0146] Introducing the Lagrange multiplier α i (i = 1, 2, ..., m), the original problem is transformed into the dual problem:

[0147]

[0148] Solving the dual problem yields α i The hyperplane parameters can then be obtained. Then choose another support vector (satisfying y) i (ω·x i Given a sample x + b) = 1, calculate b to determine the hyperplane position. For a new sample x new By judging f(x) new )=ω·x new The +b sign is used to predict its category;

[0149] ||ω|| 2 It represents the regularization term in the objective function, which controls the complexity of the hyperplane, prevents overfitting, ensures the generalization ability of the model, and balances the fit of training data with the handling of unknown samples.

[0150] x i ·x j It represents the inner product operation between samples, reflects the similarity of samples, plays a core role in the construction of dual problems, optimizes the hyperplane based on sample correlation, and uncovers the fault discrimination rules hidden in the data;

[0151] f(x new ) represents the new sample prediction function. Based on the hyperplane parameters obtained from training, it quickly classifies newly collected running data, provides real-time early warning of potential system faults, and ensures operational reliability.

[0152] Based on historical data, the system learns the differences between normal and faulty operating modes and constructs a distinguishing hyperplane. During operation, new data is continuously compared with the hyperplane. Once a new sample falls on the fault side, anomalies are immediately detected. For example, data combinations such as a continuous abnormal rise in equipment temperature or a sharp drop in pollutant degradation efficiency trigger SVM judgment, preventing the system fault from worsening in advance. In the complex and high-dimensional system operation data space, fault boundaries are accurately delineated, effectively distinguishing between normal and faulty states, keenly observing potential faults, reducing the risk of false alarms and false alarms, and ensuring the stable and long-term operation of the purification system. It does not rely excessively on specific sample details. After regularization constraints, it can adapt to changes in operating conditions within a certain range. It can still accurately predict data that appears but has similar characteristics to historical faults, reducing the trouble of frequent remodeling.

[0153] This series of algorithms works together to comprehensively improve the performance of the high-efficiency air purification system that combines photocatalysis and biological reaction. From precise monitoring and intelligent control to fault prediction and maintenance, it ensures that the system can stably and efficiently purify the air in complex environments and continuously meet people's demand for high-quality air. Specific Implementation Example 4:

[0155] like Figures 1 to 9 As shown, based on the content of the above specific embodiments, the following content is further disclosed:

[0156] To evaluate the air purification efficiency, energy efficiency, system stability, and self-maintenance capability of the system under different environmental conditions, a series of experiments were conducted based on the system architecture. The following is a detailed experimental design, which aims to reflect the innovation and advantages of the system through experiments.

[0157] I. Experimental Objective

[0158] 1. Compare the purification efficiency of this system with traditional air purification technologies (HEPA filters and activated carbon adsorption devices) at the same pollutant concentration;

[0159] 2. Evaluate the system's response capability and intelligent adjustment capability under changes in pollutant concentration;

[0160] 3. Compare the energy efficiency, system stability, and maintenance costs of the two systems;

[0161] II. Experimental Equipment and Materials

[0162] 1. Experimental setup:

[0163] This system includes a photocatalytic reaction module (TiO2, ZnO nanomaterials), a bio-reaction module (VOCs-degrading bacteria), an intelligent control module (particle swarm optimization and reinforcement learning), and a sensor monitoring module (gas, temperature, humidity, and particulate matter sensors).

[0164] Control system: Traditional HEPA filter + activated carbon adsorption device;

[0165] 2. Pollutant sources: VOCs (such as formaldehyde, benzene, xylene), PM2.5;

[0166] 3. Controlled Environment: Enclosed indoor environment (approximately 50m³ in volume) 3 );

[0167] 4. Sensors and data analysis equipment: Real-time monitoring of air pollutant concentrations, recording of system operation data, and analysis by data acquisition devices and optimization models.

[0168] III. Experimental Procedure

[0169] Sp1: Pollutant Input and Environmental Settings

[0170] In the experimental environment, VOCs (such as formaldehyde, benzene, and xylene) and PM2.5 of known concentrations were injected, with the concentration range set at 50-500 ppb for VOCs and 100-500 μg / m³. 3 PM2.5 was measured, the ambient temperature was set to 22℃ and the humidity to 50%, and the experiment was conducted under standard indoor conditions. The comparative experimental system, including this system and the control system, was started.

[0171] SP2: Purification system operation:

[0172] The system is activated, including a photocatalytic reaction module and a bio-reaction module. Based on the data monitored by the sensors, the intelligent control module will adjust the photocatalytic reaction time and the light source intensity, and dynamically adjust the microbial metabolic pathway in the bio-reaction module according to the concentrations of VOCs and PM2.5. The control system (HEPA filter and activated carbon adsorption device) is activated to simulate traditional air purification operation and record the degradation of pollutants during the purification process.

[0173] Sp3: Pollutant Concentration Monitoring and Data Recording

[0174] Every 30 minutes, the system monitors pollutant concentrations via sensors, records VOCs (formaldehyde, benzene, xylene) and PM2.5 concentration data in real time, compares the purification efficiency, reaction time, energy consumption, and other data of the two systems, and uses the data analysis and optimization module to evaluate the changes in purification efficiency of this system under different pollutant concentrations, as well as energy consumption, system stability, and maintenance requirements.

[0175] SP4: Experimental Duration and System Stability Testing:

[0176] The two systems were run continuously for 48 hours to observe the changing trends of pollutant concentrations and the stability of the two systems during long-term operation. The self-maintenance capabilities of the systems during long-term operation were recorded, including the self-cleaning of photocatalytic reaction materials, the self-regulation of microbial communities, and the self-maintenance of reactor components.

[0177] IV. Experimental Data Recording and Analysis

[0178] 1. Comparison of purification efficiency:

[0179]

[0180] Table 1

[0181] Note: The data represents the purification effect of the system after photocatalysis and biological reaction for each pollutant experiment. The calculation method is: purification rate = (initial concentration - purified concentration) / initial concentration × 100%.

[0182] 2. Energy efficiency analysis:

[0183] System type Pollutant purification (g / h) Energy consumption (W) Purification energy efficiency (g / W·h) This system 0.35g / h 50W 7.0 g / W·h Control system 0.20g / h 40W 5.0 g / W·h

[0184] Table 2

[0185] Note: Data is calculated based on the amount of pollutant degradation per unit time and the total energy consumption of the system;

[0186] 3. System stability and self-maintenance

[0187] After 48 hours of operation, the photocatalytic reaction module of this system remains highly efficient, and the microbial community is able to self-regulate to adapt to different characteristics of pollutants. During continuous use, there is no significant performance degradation of the photocatalytic material and the microbial community, and the system maintains a purification efficiency of over 90%.

[0188] Control system: After 24 hours of operation, the HEPA filter and activated carbon adsorption device showed a significant decrease in effectiveness, requiring manual cleaning or replacement, resulting in a reduction in purification efficiency to about 60%.

[0189] 4. System self-cleaning and self-maintenance

[0190] In this system: the photocatalytic material uses an automatic cleaning mechanism that triggers a cleaning cycle every 12 hours to ensure continuous reaction efficiency; the microbial community of the bioreactor module is dynamically adjusted through genetic and reinforcement learning algorithms to adaptively optimize when pollutant concentrations change.

[0191] Comparison system: Traditional systems do not have a self-cleaning function and require regular manual maintenance.

[0192] V. Experimental Conclusions

[0193] 1. Purification efficiency: This system is superior to traditional air purification systems in terms of degradation efficiency of formaldehyde, benzene, xylene and PM2.5. Especially in environments with high concentrations of pollutants, it can achieve a degradation rate of over 85%, while the degradation efficiency of traditional systems is 60%-75%.

[0194] 2. Energy efficiency: The energy efficiency of this system is significantly higher than that of the control system. Under the same energy consumption, this system can degrade more pollutants, showing a better energy efficiency ratio (7.0 g / W·h vs 5.0 g / W·h).

[0195] 3. System stability and self-maintenance capability: This system has self-cleaning and self-adjusting capabilities, and can maintain high purification efficiency during long-term operation, while traditional systems require frequent manual intervention and cleaning;

[0196] 4. Intelligent adjustment: This system dynamically adjusts its operating parameters through an intelligent control module, responding quickly to changes in pollutant concentration and maintaining optimal system operation. This is a level of precision that other systems cannot achieve under changing environments.

[0197] The experimental data above demonstrates the significant advantages of this system in terms of air purification efficiency, energy efficiency, stability, and maintainability.

[0198] It should be noted that, in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising a reference structure" does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes the element.

[0199] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. A high-efficiency air purification system that combines photocatalysis and biological reaction, characterized in that: The system includes a photocatalytic reaction module, a bioreaction module, an intelligent control module, a sensor monitoring module, a data analysis and optimization module, and a modular and self-maintaining module, wherein: The photocatalytic reaction module is used to perform photocatalytic degradation of pollutants in the air. It includes nanostructured photocatalytic materials and high-efficiency light source components. Through the action of light, organic pollutants are oxidized and decomposed into small molecules or harmless gases. The light source intensity and reaction time are adjusted by fuzzy logic control algorithm to adapt to changes in the concentration of pollutants in the air. The bioreactor module is used to process intermediate products after photocatalytic degradation, achieving secondary degradation and thorough purification. It includes a microbial community and reactor components. It further degrades pollutants through biological metabolism, dynamically optimizes the selection of microbial communities through genetic algorithms, and adjusts metabolic pathways by combining reinforcement learning to improve bioreactor efficiency. The intelligent control module is used to coordinate and schedule the various modules of the system, including an intelligent coordination mechanism and a real-time controller. It achieves synchronous operation of photocatalysis and biological reaction through a rule base and control strategy, and dynamically adjusts the working parameters of photocatalysis and biological reaction through a particle swarm optimization algorithm to ensure the maximization of synergistic effect. The sensor monitoring module is used to monitor air quality, pollutant concentration, temperature and humidity environmental parameters in real time. It includes multimodal sensors and a monitoring network. It acquires multi-dimensional data through high-sensitivity sensing technology and analyzes changes in environmental parameters through multi-objective optimization algorithms to provide real-time control basis for the system. The data analysis and optimization module is used to analyze system operating data and pollutant degradation efficiency, and provide intelligent optimization solutions. It includes a data acquisition device and an optimization model. It predicts failure risks and proposes maintenance suggestions through the support vector machine (SVM) algorithm, and learns historical data and environmental characteristics through the reinforcement learning algorithm to optimize system operation strategies and ensure long-term stable operation. The modular and self-maintaining module is used to realize the modular design and automatic maintenance of the system. It includes independent photocatalysis module, bioreaction module and control module. The modular design simplifies the expansion and upgrading of the system.

2. The high-efficiency air purification system combining photocatalysis and biological reaction according to claim 1, characterized in that: The light source component of the photocatalytic reaction module adopts a high-intensity ultraviolet light source with adjustable function, which can intelligently adjust the light intensity under different pollutant concentrations. It uses high-surface-area nano-photocatalytic materials, and optimizes the photocatalytic performance of the materials through surface chemical modification and nanostructure design. Combined with fuzzy logic control algorithm, it dynamically adjusts the light source intensity and reaction time based on real-time sensor monitoring data, including pollutant concentration, temperature and humidity, to adapt to different air quality changes. The free radicals and gaseous oxides generated in the photocatalytic degradation reaction can interact with the microorganisms in the bio-reaction module to promote the further degradation of pollutants.

3. The high-efficiency air purification system combining photocatalysis and biological reaction according to claim 1, characterized in that: The bioreaction module employs intelligent regulation of the microbial community, optimizing the metabolic pathways and community structure of the microorganisms through genetic and reinforcement learning algorithms. Specific species within the microbial community can efficiently degrade organic pollutants and their degradation products, and possess strong environmental adaptability. The genetic algorithm optimizes the microbial genome by simulating natural selection, enabling it to adapt to different pollutant characteristics and improve the degradation rate. The reinforcement learning algorithm further enhances the bioreaction efficiency by dynamically adjusting the microbial metabolic pathways and learning changes in pollutant characteristics and environmental conditions.

4. The high-efficiency air purification system combining photocatalysis and biological reaction according to claim 1, characterized in that: The rule base of the intelligent control module controls the working mode of each module in real time by intelligently analyzing pollutant type, concentration and environmental parameters. The particle swarm optimization algorithm optimizes the synergistic working time and intensity of photocatalysis and biological reaction based on sensor monitoring data to achieve the best degradation efficiency, provides adaptability to different working states, and automatically adjusts the working ratio of each module when the pollutant concentration changes to ensure efficient system operation.

5. The high-efficiency air purification system combining photocatalysis and biological reaction according to claim 1, characterized in that: The multimodal sensor network of the sensor monitoring module integrates gas sensors, temperature and humidity sensors, and particulate matter sensors, enabling real-time monitoring of the concentration of various pollutants in the air. A multi-objective optimization algorithm performs real-time analysis of multi-source sensor data, predicts air quality change trends, and provides adjustment suggestions to the intelligent control module. High-sensitivity sensing technology ensures accurate capture of pollutant changes even under low-concentration pollutant conditions and timely responses.

6. The high-efficiency air purification system combining photocatalysis and biological reaction according to claim 1, characterized in that: The data acquisition unit of the data analysis and optimization module collects data from sensors, reaction modules, and control modules in real time to ensure the timeliness and accuracy of information. The SVM algorithm classifies the operating status of the equipment, predicts possible system failures, and proposes maintenance suggestions. The reinforcement learning algorithm automatically adjusts the system's operating strategy based on historical operating data and environmental characteristics to ensure long-term stable operation.

7. The high-efficiency air purification system combining photocatalysis and biological reaction according to claim 1, characterized in that: The modular and self-maintenance modules enable each module of the system to operate independently. Modules can be dynamically switched or added / removed based on different pollutant concentrations. Through automatic detection and self-maintenance technologies, the system can achieve self-cleaning, automatic repair, and maintenance of modules, ensuring long-term efficient operation. Furthermore, each module adopts a standardized interface design, supporting rapid system expansion and upgrades. The self-maintenance mechanism includes automatic cleaning of photocatalytic materials, self-regulation of the microbial community, and periodic maintenance of reactor components. Combined with SVM algorithms, the health status of the equipment is predicted and diagnosed, allowing for early detection and repair of potential faults.

8. The high-efficiency air purification system combining photocatalysis and biological reaction according to claim 1, characterized in that: The photocatalytic reaction module and the biological reaction module together constitute a multi-stage degradation and efficient decomposition module for pollutants. This module maximizes degradation efficiency across multiple stages through the synergistic effect of photocatalysis and biological reaction. It employs a multi-objective optimization algorithm (MOGA) to process pollutants in stages, ensuring optimal results at each stage and achieving efficient synergy between reaction stages. The photocatalytic reaction module first performs preliminary degradation of pollutants, converting them into intermediate products. The biological reaction module further decomposes these intermediate products using microorganisms, achieving thorough purification. The MOGA algorithm optimizes multiple objectives in the multi-stage degradation process, including degradation rate, energy consumption, and system stability, and performs real-time control.

Images