A positive pressure gas filtering ventilation control system and method for riot control and dispersal vehicles

Abstract

The present invention relates to the field of ventilation control technology, and specifically to a positive pressure gas filtering ventilation control system and method for riot control and dispersal vehicles. In the present invention, by combining the chemical characteristics and concentration of poisonous gas, a gradient boosting decision tree is adopted to dynamically adjust the working priority and distribution operation sequence of the filter layer, thereby realizing the selection and priority arrangement of targeted filtering and avoiding excessive consumption of filtering resources. By monitoring the adsorption saturation and working temperature of the filter layer and combining dynamic operation optimization decision-making, the filter device can monitor the operating status in real time during long-term operation, adjust the working sequence in time, and extend the effective life of the filter device. The fan speed and positive pressure maintainer setting are adjusted by a fuzzy control method, and the positive pressure and ventilation effect in the vehicle are optimized in real time. By simulating the ventilation path and adjusting the fan power output and the valve state, the flow efficiency and air quality distribution uniformity of the air in the vehicle are optimized, and the overall dynamic response capability and operational stability are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of ventilation control for dispersal vehicles, and in particular to a positive-pressure gas-filtering ventilation control system and method for a riot-control dispersal vehicle. Background Art

[0002] Spinosaurus riot control and dispersal vehicles are often used in the People's Armed Police Force, mainly in the performance of duties, handling emergencies, counter-terrorism operations and other tasks; generally speaking, Spinosaurus riot control and dispersal vehicles are mainly composed of three parts: riot control and strike, media transmission, and vehicle-mounted mobility. Among them, Spinosaurus riot control and dispersal vehicles are usually equipped with a gas filtration and ventilation system to ensure that the air breathed by people in the car meets safety standards in scenarios where toxic gas, smoke and other harmful gases invade, and to prevent external polluted gases from penetrating into the interior of the car, thereby improving the vehicle's protection capabilities and ensuring the life safety and continuity of action of people in the car; at present, the main function of the gas filtration and ventilation system is to achieve the exchange, purification and pressure regulation of air in a specific environment to ensure air quality and environmental safety. It has been widely used in industrial production, civil buildings, vehicle equipment and special scene protection, including core functions such as air filtration, flow regulation and pressure control.

[0003] However, existing riot control and dispersal vehicles are prone to identification bias when faced with scenarios where multiple toxic gases are mixed or the concentrations vary greatly. The configuration and operation of the filter device mostly use static settings or a single preset logic, and the operating status and adsorption performance of the filter layer are insufficiently monitored, resulting in the risk of filtration failure and leakage of air pollutants into the safe space. In addition, the existing technology mostly uses a fixed fan speed and pressure adjustment method, and cannot adjust the fan speed and positive pressure settings in real time according to changes in the environment inside and outside the vehicle, resulting in reduced ventilation efficiency and excessive energy consumption. At the same time, the optimization of the airflow distribution in the vehicle is insufficient, resulting in uneven air flow. The air quality in some areas cannot meet safety requirements, reducing the overall protection effect and operating efficiency.

[0004] Therefore, how to automatically control the ventilation of riot control dispersal vehicles is a technical problem that technicians need to solve. Summary of the Invention

[0005] The purpose of the present invention is to solve the shortcomings of the prior art and to propose a positive pressure gas filtering and ventilation control system and method for riot control and dispersal vehicles.

[0006] In order to achieve the above objectives, the first aspect of the present invention provides a positive pressure gas filtering and ventilation control system for a riot control and dispersal vehicle, comprising:

[0007] Gas type and concentration identification module: detects the toxic gas composition and concentration in the external environment based on chemical sensors and optical sensors, records the chemical properties of the gas, and generates gas characteristic data;

[0008] Dynamic configuration module for filter devices: Based on the gas characteristic data, a gradient boosting decision tree is used to select the appropriate filter layer according to the chemical characteristics of the toxic gas, adjust the working priority and working status of the activated carbon layer, HEPA layer and ionosphere, and assign the operation sequence to generate a filter configuration plan;

[0009] Optimize filtration operation module: Based on the filtration configuration plan, combined with the working priority and chemical characteristics of the filter layer, determine the timing of activating and deactivating the filter device, and adjust the working sequence of the filter device to match the actual needs, generating operation optimization decisions;

[0010] Filtration efficiency monitoring module: Based on the operation optimization decision, monitor the adsorption saturation and operating temperature of each filter layer, check the operating efficiency of each filter layer, and generate efficiency monitoring records;

[0011] Real-time ventilation effect adjustment module: Based on the performance monitoring records, the module uses fuzzy control methods to adjust the fan speed and the setting of the positive pressure maintainer in real time, analyzes the real-time data to maintain the positive pressure in the vehicle and optimize the ventilation effect, and generates ventilation parameter adjustments;

[0012] Ventilation path optimization module: Based on the ventilation parameter adjustment, simulate the airflow distribution in the vehicle, adjust the fan output power and air valve status according to the real-time ventilation effect and the space layout in the vehicle, and generate an optimized airflow path.

[0013] Preferably, the gas type and concentration identification module includes a chemical data acquisition submodule, an optical property analysis submodule and a gas property extraction submodule, wherein:

[0014] Chemical data acquisition submodule: Based on the detection of toxic gas components and concentrations in the external environment by chemical sensors, the module collects electrical signals from chemical sensors, extracts changes in electrical signal intensity, analyzes the chemical reaction characteristics of toxic gas components, extracts electrical signal characteristic values ​​related to toxic gas components, and generates chemical response characteristic data;

[0015] Optical characteristic analysis submodule: Based on the chemical response characteristic data, the optical sensor detects the absorption characteristics of light of a specific wavelength, collects changes in the absorption light intensity of the optical sensor, analyzes the wavelength absorption characteristics of the poison gas molecules to light, extracts the characteristic information of the poison gas molecules on the spectrum, and generates optical absorption characteristic data;

[0016] Gas characteristic extraction submodule: Based on the optical absorption characteristic data and combined with the chemical response characteristic data, the chemical properties and concentration information of the poisonous gas are extracted by matching the optical characteristics and chemical response characteristic values, and the gas characteristic data is output.

[0017] Preferably, the filtering device dynamic configuration module includes a filtering demand assessment submodule, a filtering layer priority adjustment submodule and a filtering configuration generation submodule, wherein:

[0018] Filtration demand assessment submodule: Based on the gas characteristic data, a gradient boosting decision tree is used to analyze the chemical properties of the toxic gas, calculate the reaction performance of the toxic gas components and the filter material, evaluate the adsorption capacity and load demand of the filter layer, extract the demand parameters of the filter material, and generate the filtration demand parameters;

[0019] Filter layer priority adjustment submodule: Based on the filtering requirement parameters, adjust the working mode of the filter layer, set the activation conditions of the activated carbon layer, HEPA layer and ionization layer, optimize the filtering priority order of each layer, establish the dynamic operation sequence configuration of the filter layer, and generate the filter layer priority configuration;

[0020] Filter configuration generation submodule: Based on the filter layer priority configuration, allocate the operating tasks of the filter device, set the working order of each layer in the filter device, set the operation logic and association rules during dynamic switching, generate the task operation table of the filter device, and output the filter configuration plan.

[0021] Preferably, the calculation formula for the reaction performance of the toxic gas component and the filter material is:

[0022]

[0023] in: is the gradient value of the left branch filter material, is the gradient value of the right branch filter material, is the second-order gradient value of the left branch filter material, is the second-order gradient value of the right branch filter material, is the regularization parameter, T is the chemical reaction time between the poison gas and the filter material, is the chemical reaction time between the left branch poison gas and the filter material, is the chemical reaction time of the right branch poison gas and the filter material, P is the affinity coefficient between the poison gas molecules and the filter material molecules, M is the surface molecular density of the filter material, is the surface molecular density of the left branch filter material, is the surface molecular density of the right branch filter material, is the weight coefficient of chemical reaction time, is the weight of the affinity coefficient, is the weight of the molecular density.

[0024] Preferably, the optimized filtering operation module includes a filtering timing control submodule, a work sequence adjustment submodule and an operation decision generation submodule, wherein:

[0025] Filter timing control submodule: Based on the filtering configuration scheme, by detecting the current state of the filter layer in the filter device and combining it with the ambient toxic gas concentration, extracting environmental parameters and filter layer operation data, calculating the filtering conditions required for device startup, extracting the filter layer switching time, and generating a filtering timing determination result;

[0026] Working sequence adjustment submodule: Based on the filtration timing determination result, combined with the chemical characteristics of each filter layer, by analyzing the working conditions of the filter layer and the internal parameters of the device, setting the priority switching rules of the filter layer, optimizing the operating order of the filter layer, determining the working mode of each layer, and generating the filtration operation sequence;

[0027] Operation decision generation submodule: Based on the filtering operation sequence, by extracting the dynamic switching rules and operation logic of the filtering layer, setting the overall task allocation of the filtering device and the startup conditions of each layer, generating the device operation plan and synchronizing it to all filtering modules, and outputting the operation optimization decision.

[0028] Preferably, the filtration efficiency monitoring module includes an adsorption saturation monitoring submodule, an operating temperature monitoring submodule and an operation efficiency evaluation submodule, wherein:

[0029] Adsorption saturation monitoring submodule: Based on the above-mentioned operation optimization decision, the adsorption performance of the filter layer is collected using real-time data. By extracting the working records and chemical adsorption amount of the adsorption layer, the saturation change of the adsorption layer is analyzed, and the remaining adsorption capacity is calculated in combination with the toxic gas concentration to generate the adsorption status monitoring results;

[0030] Working temperature monitoring submodule: Based on the adsorption state monitoring results, by real-time monitoring of the filter layer temperature changes, extracting the heat data recorded by the temperature sensor, analyzing the impact of temperature changes on filtration performance, determining temperature parameters in combination with the saturation state, and generating working temperature parameter records;

[0031] Operation efficiency evaluation submodule: Based on the operating temperature parameter records, analyze the overall operation data of the filter device under different temperatures and adsorption states, calculate the filter device operation indicators by extracting efficiency parameters and residual filtration capacity, and output efficiency monitoring records.

[0032] Preferably, the ventilation effect real-time adjustment module includes a fan speed adjustment submodule, a positive pressure setting adjustment submodule and a ventilation parameter analysis submodule, wherein:

[0033] The fan speed adjustment submodule extracts the airflow data inside and outside the vehicle and the fan operating status data based on the efficiency monitoring records, reads the current fan speed in real time, compares the current air pressure inside the vehicle with the external air pressure, analyzes the impact of the air pressure difference on ventilation demand, calculates the fan speed adjustment amount based on the real-time toxic gas concentration, determines the adjusted fan operating parameters, and generates the fan speed adjustment result.

[0034] Positive pressure setting adjustment submodule: Based on the fan speed adjustment result, a fuzzy control method is used to extract the positive pressure maintainer operating data. By calculating the positive pressure difference inside the vehicle and the change in the external ambient pressure, the positive pressure maintainer output parameters are analyzed in combination with the fan speed adjustment amount. The operating mode and control logic of the positive pressure maintainer are adjusted to generate the positive pressure setting parameters.

[0035] Ventilation parameter analysis submodule: Based on the positive pressure setting parameters, it extracts real-time ventilation effect related data and the change status of the airflow in the vehicle. By calculating the combined effect of positive pressure and fan speed on the air flow in the vehicle, it extracts the air exchange rate and airflow distribution data in the vehicle, and outputs the ventilation parameter adjustment.

[0036] Preferably, the extraction of the positive pressure maintainer operating data requires collecting the maintainer's output pressure value, target pressure setting value, real-time output power, pressure adjustment range, and valve opening and closing state. The output pressure is collected in real time by a pressure sensor, and the target pressure and adjustment range are extracted in combination with the set value. The current power output is recorded, and the valve opening and closing angle and operation state are recorded at the same time. All data are synchronously extracted by the real-time control system of the positive pressure maintainer.

[0037] The extraction of real-time ventilation effect related data needs to include pollutant concentration, temperature, humidity, air pressure, air flow speed and direction. The pollutant concentration is obtained through the air quality sensor, the temperature and humidity distribution is obtained through the temperature and humidity sensor, the air pressure difference inside and outside the vehicle is recorded through the air pressure sensor, and the flow speed and direction data of different areas in the vehicle are obtained through the air flow sensor. The air flow distribution characteristics in the vehicle are comprehensively analyzed in combination with the operating status of the fan and the air valve.

[0038] Preferably, the ventilation path optimization module includes an airflow distribution simulation submodule, a fan power adjustment submodule and a valve state optimization submodule, wherein:

[0039] Airflow distribution simulation submodule: Based on the ventilation parameter adjustment, it extracts the interior space layout data and the physical position relationship of the fan and air valve, reads the real-time ventilation status data and combines it with the temperature and humidity distribution in the vehicle to analyze the air flow trajectory in each area of ​​the vehicle, identify areas where air flow is blocked, optimize the airflow path, and generate the airflow distribution path;

[0040] Fan power adjustment submodule: extracts fan power output data based on the airflow distribution path, adjusts the fan power output level and operation mode by comparing the airflow distribution uniformity and air exchange rate in each area, optimizes the fan operating parameters to improve the airflow distribution, and generates the fan output power parameters;

[0041] Valve state optimization submodule: Based on the fan output power parameters, extract the real-time opening and closing state data of the valve, analyze the linkage relationship between the valve opening and closing and the fan output, optimize the airflow channel by adjusting the valve opening angle and dynamic switching strategy, establish a ventilation path optimization plan, and output the airflow optimization path.

[0042] A second aspect of the present invention provides a positive pressure gas filtering and ventilation control method for a riot control and dispersal vehicle, which is applied to the positive pressure gas filtering and ventilation control system for the riot control and dispersal vehicle described above, and comprises the following steps:

[0043] Step 1: Based on the output data of chemical and optical sensors, extract the chemical reaction signals and optical absorption signals of the toxic gas, analyze their characteristic values, and combine the chemical reaction time, conductivity, and light absorption spectrum to classify the toxic gas type and quantify the concentration to generate gas characteristic data;

[0044] Step 2: Based on the gas characteristic data, combined with the chemical composition and concentration of the toxic gas, the reaction performance of the toxic gas and the filter material is analyzed. The activated carbon layer's adsorption adaptability to organic toxic gases, the HEPA layer's efficiency in filtering particulate matter, and the ionosphere's ability to remove chemical reaction toxic gases are analyzed. The priority and operation timing rules of each layer of filter units are dynamically adjusted through a gradient boosting decision tree. Filtering tasks are assigned and the required units are activated to generate a filtration configuration plan.

[0045] Step 3: Based on the filter configuration scheme, the current operating load, task priority, and toxic gas characteristics of the filter unit are dynamically analyzed. By judging the saturation and chemical adaptability of the filter unit, the filter unit is started or shut down according to the task priority. The operating time of low-load units is extended, and the operating time of high-load units is reduced. The working sequence is optimized and dynamic switching is completed to generate operation optimization decisions;

[0046] Step 4: Based on the above-mentioned operation optimization decision, the adsorption saturation, current operating temperature and filtration time of each filter unit are collected, the remaining capacity of the adsorption layer is determined according to the chemical reaction rate, the filtration saturation and operating efficiency of the HEPA layer for particulate matter are recorded, the thermal impact of the high-temperature filter layer is dynamically adjusted, the current performance status of all layers is recorded, and an efficiency monitoring record is generated;

[0047] Step 5: Based on the performance monitoring records, the fan speed is dynamically adjusted to stabilize the positive pressure state by analyzing the pressure difference between the inside and outside of the vehicle, the fan output speed, and the current power of the positive pressure maintainer. The power level of the positive pressure maintainer is adjusted according to the fuzzy control method and the positive pressure output range to optimize the ventilation effect and synchronously adjust the fan and positive pressure device to generate ventilation parameter adjustments;

[0048] Step 6: Based on the ventilation parameter adjustment, the linkage relationship between the fan output power and the airflow distribution is analyzed, the adaptive adjustment plan of the airflow path is calculated through the air pressure distribution at different positions in the vehicle, the opening and closing angle of the air valve and the fan output power are dynamically adjusted, the distribution area of ​​the airflow in the vehicle is corrected in real time, and the optimized airflow path is generated.

[0049] Compared with the prior art, the advantages and positive effects of the present invention are:

[0050] 1. This invention combines the chemical properties and concentration of toxic gases and uses a gradient boosting decision tree to dynamically adjust the working priorities of the filtration layers and allocate the operation sequence, achieving targeted filtration selection and priority arrangement, and avoiding excessive consumption of filtration resources.

[0051] 2. In this invention, by monitoring the adsorption saturation and operating temperature of the filter layer and combining it with dynamic operation optimization decisions, the filter device can monitor its operating status in real time during long-term operation, adjust the operating sequence in a timely manner, and extend the effective life of the filter device.

[0052] 3. This invention uses fuzzy control to adjust fan speed and positive pressure maintainer settings, optimizing interior positive pressure and ventilation in real time. By simulating the ventilation path and adjusting fan power output and valve status, it optimizes interior air flow efficiency and air quality distribution uniformity, enhancing overall dynamic response and operational stability. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] Figure 1 It is a system flow chart of the present invention.

[0054] Figure 2 Schematic diagram of the system framework of the present invention.

[0055] Figure 3 Schematic diagram of the method steps of the present invention. DETAILED DESCRIPTION

[0056] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0057] See also Figure 1 The present invention provides a technical solution: a positive pressure gas filtering and ventilation control system for a riot control and dispersal vehicle, comprising:

[0058] Gas type and concentration identification module: detects the toxic gas composition and concentration in the external environment based on chemical sensors and optical sensors, records the chemical properties of the gas, and generates gas characteristic data;

[0059] Dynamic configuration module for filter devices: Based on gas characteristic data, a gradient boosting decision tree is used to select the appropriate filter layer according to the chemical characteristics of the toxic gas, adjust the working priority and working status of the activated carbon layer, HEPA layer, and ionosphere, and assign the operation sequence to generate a filter configuration plan;

[0060] Optimize filtration operations: Based on the filtration configuration plan, combined with the working priority and chemical characteristics of the filter layer, it determines the timing of activating and deactivating the filter device, and adjusts the working sequence of the filter device to match the actual needs, generating operation optimization decisions;

[0061] Filtration efficiency monitoring module: Based on the operation optimization decision, it monitors the adsorption saturation and operating temperature of each filter layer, checks the operating efficiency of each filter layer, and generates efficiency monitoring records;

[0062] Real-time ventilation effect adjustment module: Based on performance monitoring records, fuzzy control methods are used to adjust fan speed and positive pressure maintainer settings in real time. Real-time data is analyzed to maintain positive pressure in the vehicle and optimize ventilation effects, generating ventilation parameter adjustments.

[0063] Ventilation Path Optimization Module: Based on ventilation parameter adjustments, it simulates the airflow distribution inside the vehicle, adjusts the fan output power and air valve status according to the real-time ventilation effect and the interior space layout, and generates an optimized airflow path.

[0064] See also Figure 2 The gas type and concentration identification module includes a chemical data acquisition submodule, an optical characteristics analysis submodule, and a gas characteristics extraction submodule, among which:

[0065] Chemical data acquisition submodule: Based on the detection of toxic gas components and concentrations in the external environment by chemical sensors, the module collects electrical signals from chemical sensors, extracts changes in electrical signal intensity, analyzes the chemical reaction characteristics of toxic gas components, extracts electrical signal characteristic values ​​related to toxic gas components, and generates chemical response characteristic data;

[0066] Optical property analysis submodule: Based on the chemical response characteristic data, the optical sensor detects the absorption characteristics of light of a specific wavelength, collects the changes in the absorption light intensity of the optical sensor, analyzes the wavelength absorption characteristics of the poison gas molecules to light, extracts the characteristic information of the poison gas molecules on the spectrum, and generates optical absorption characteristic data;

[0067] Gas characteristic extraction submodule: Based on the optical absorption characteristic data and combined with the chemical response characteristic data, the chemical properties and concentration information of the poisonous gas are extracted by matching the optical characteristics and chemical response characteristic values, and the gas characteristic data is output;

[0068] Chemical data acquisition submodule: Based on chemical sensors, the composition and concentration of toxic gases are detected. The constant current potentiometry method is used to perform electrochemical detection of toxic gas components by setting a constant current value of 1 microampere. The electrical signals of the redox reaction between the toxic gas components and the sensor electrode materials are collected. The collected electrical signals are converted to the frequency domain using a signal decoding algorithm, specifically a Fourier transform algorithm. The number of transformation points is set to 1024, and the spectral amplitude changes of the electrical signal intensity are collected. The converted data is windowed, each window is set to 256 points, and a sliding window processing is performed with an overlay of 50% of the window size. The characteristic spectrum peaks associated with the toxic gas components and their corresponding frequencies are extracted to generate chemical response characteristic data.

[0069] Optical property analysis submodule: Based on the chemical response characteristic data, an ultraviolet-visible spectrophotometer is used to detect the absorption characteristics of light of a specific wavelength. The detection wavelength range is set to 200 nanometers to 800 nanometers, and the scanning step length is 2 nanometers. The absorption light intensity generated by the optical sensor is collected. A spectral decomposition algorithm, specifically a least squares curve fitting algorithm, is used to analyze the light absorption curve by setting the fitting order to 4. The absorption peak of the specific wavelength light and its corresponding wavelength are extracted. The change data of the light absorption intensity are normalized by setting the normalization range to 0 to 1 and the absorption spectrum peak characteristic data are extracted to generate optical absorption characteristic data.

[0070] Gas characteristic extraction submodule: Based on the optical absorption characteristic data and combined with the chemical response characteristic data, a correlation analysis algorithm is used, specifically the Pearson correlation coefficient calculation method. By calculating the correlation coefficient between the chemical response characteristic spectrum and the optical absorption characteristic data, the correlation threshold is set to 0.85, and the highly matching characteristics of the toxic gas molecules in chemical and optical characteristics are extracted. The concentration value of the toxic gas molecules is calculated based on the matching characteristic data through a linear regression algorithm. The loss function of the linear regression is set to the least squares error function and the number of iterations is optimized to 1000 times through the gradient descent method, and the gas characteristic data is finally output.

[0071] See also Figure 2 The dynamic configuration module of the filtering device includes a filtering demand evaluation submodule, a filtering layer priority adjustment submodule and a filtering configuration generation submodule, wherein:

[0072] Filtration demand assessment submodule: Based on gas characteristic data, a gradient boosting decision tree is used to analyze the chemical properties of toxic gases, calculate the reaction performance of toxic gas components and filter materials, evaluate the adsorption capacity and load requirements of the filter layer, extract the demand parameters of the filter materials, and generate filtration demand parameters;

[0073] Filter layer priority adjustment submodule: Based on the filtration requirement parameters, adjust the working mode of the filter layer, set the activation conditions of the activated carbon layer, HEPA layer and ionization layer, optimize the filtration priority order of each layer, establish the dynamic operation sequence configuration of the filter layer, and generate the filter layer priority configuration;

[0074] Filter configuration generation submodule: Based on the filter layer priority configuration, it allocates the operation tasks of the filter device, sets the working order of each layer in the filter device, sets the operation logic and association rules during dynamic switching, generates the task operation table of the filter device, and outputs the filter configuration plan;

[0075] Filtration demand assessment submodule: Based on gas characteristic data, a gradient boosting decision tree is used to analyze the chemical properties of the toxic gas. The maximum depth is set to 10, the learning rate of each tree is set to 0.1, and the subsample ratio is set to 0.8. The reaction performance of the toxic gas components and the filter material is calculated. By defining the adsorption parameters of the filter material, including the adsorption constant set to 0.005 mol / L and the reaction time constant set to 10 seconds, the adsorption capacity of the filter material is evaluated. The adsorption load of the filter layer is calculated. The material adsorption demand analysis is performed by defining the material adsorption upper limit of the load threshold as 500 mg / g, extracting the filter material demand parameters, and generating the filtration demand parameters.

[0076] Filter layer priority adjustment submodule: Based on the filtration requirement parameters, a dynamic priority adjustment algorithm is used to optimize the working mode of the filter layer. The activation condition for the activated carbon layer is set to an input toxic gas concentration greater than 50 mg per cubic meter. The activation condition for the HEPA layer is set to an input particle diameter less than 2.5 microns and a concentration greater than 35 micrograms per cubic meter. The activation condition for the ionosphere is set to an input toxic gas type containing components with charged ionization characteristics. The priority adjustment function is used to define the filter layer priority order: the activated carbon layer priority value is 1, the HEPA layer priority value is 2, and the ionosphere priority value is 3. The operation order of the filter layers is dynamically adjusted according to the toxic gas characteristics, and a dynamic operation order configuration of the filter layers is established to generate the filter layer priority configuration.

[0077] Filter configuration generation submodule: Based on the filter layer priority configuration, the task allocation algorithm is used to allocate the filter device operation tasks, and the task allocation parameters of each layer of the filter device are defined, including the task processing time is set to no more than 10 minutes each time the running time is set to the dynamic switching condition is set to the task execution time reaching the set value or the adsorption layer load exceeds the set threshold, the working order of each layer in the filter device is set to switch in order from low to high priority, the operation logic and association rules of dynamic switching are set, including the switching condition between tasks is set to automatically trigger the activation of the lower layer when the current layer cannot meet the task requirements, and the switching rules of each layer are defined by functions, including task suspension rules and switching activation rules, to generate a task operation table for the filter device and output the filter configuration plan.

[0078] The calculation formula for the reaction performance of toxic gas components and filter materials is:

[0079]

[0080] in: is the gradient value of the left branch filter material, is the gradient value of the right branch filter material, is the second-order gradient value of the left branch filter material, is the second-order gradient value of the right branch filter material, is the regularization parameter, T is the chemical reaction time between the poison gas and the filter material, is the chemical reaction time between the left branch poison gas and the filter material, is the chemical reaction time of the right branch poison gas and the filter material, P is the affinity coefficient between the poison gas molecules and the filter material molecules, M is the surface molecular density of the filter material, is the surface molecular density of the left branch filter material, is the surface molecular density of the right branch filter material, is the weight coefficient of chemical reaction time, is the weight of the affinity coefficient, is the weight of molecular density;

[0081] Execution process: First, the gradient values ​​of the left and right branch filter materials are calculated using the gradient boosting decision tree method. and The gradient value indicates the effect of the toxic gas characteristics on the filter material in the two branches. Then calculate the second-order gradient value. and , which represents the curvature of the performance change of the poison gas on the filter material. The chemical reaction time T between the poison gas and the filter material is determined by experiment, and the chemical reaction time of the left branch and the right branch is further obtained. and Then, the affinity coefficient P between the poison gas molecules and the filter material molecules is calculated by molecular dynamics method. Then, the surface molecular density M of the filter material is calculated by material surface analysis experiment, including the molecular density of the left and right branches. and , the molecular density is determined by the number of molecules per unit area, and finally the weight coefficient of the chemical reaction time is determined by fitting the data through multiple experiments , the weight of affinity coefficient and the weight of molecular density , the weight coefficients are 、 、 , substitute all parameters into the formula, calculate the reaction performance gain value between the toxic gas components and the filter material, and use it as the key parameter to evaluate the adsorption capacity and load demand of the filter layer, and finally generate the filtration demand parameters of the system.

[0082] See also Figure 2 The optimized filtering operation module includes a filtering timing control submodule, a work sequence adjustment submodule, and an operation decision generation submodule, wherein:

[0083] Filter timing control submodule: Based on the filter configuration scheme, by detecting the current status of the filter layer in the filter device and combining it with the ambient toxic gas concentration, extracting environmental parameters and filter layer operation data, calculating the filtering conditions required for device startup, extracting the filter layer switching time, and generating a filter timing determination result;

[0084] Working sequence adjustment submodule: Based on the filtration timing judgment results, combined with the chemical characteristics of each filter layer, by analyzing the working conditions of the filter layer and the internal parameters of the device, it sets the priority switching rules of the filter layer, optimizes the operating order of the filter layer, determines the working mode of each layer, and generates the filtration operation sequence;

[0085] Operation decision generation submodule: Based on the filter operation sequence, by extracting the dynamic switching rules and operation logic of the filter layer, setting the overall task allocation of the filter device and the start conditions of each layer, generating the device operation plan and synchronizing it to all filter modules, and outputting the operation optimization decision;

[0086] Filtration timing control submodule: Based on the filtration configuration scheme, a state monitoring algorithm is used to detect the current state of the filter layer in the filtration device. The state monitoring parameters are defined, including the filter layer load value set to 500 mg / g and the filter layer adsorption efficiency threshold set to 80%. In combination with the ambient toxic gas concentration, the toxic gas concentration data is collected through the environmental monitoring instrument and the sliding window averaging algorithm is used to smooth the toxic gas concentration data. The window size is set to 10 seconds for real-time concentration mean calculation. The filter layer operation data is used to determine the filtering conditions through the logistic regression model in the state monitoring algorithm. The filter start threshold is set to activate the filter device when the state judgment value is greater than 0.8. The filter layer switching time is extracted, and the switching timing is determined by calculating the toxic gas concentration change rate and setting the change rate threshold to 5 mg per second to generate the filtration timing judgment result.

[0087] Working sequence adjustment submodule: Based on the results of filtration timing judgment and combined with the chemical characteristics of each filter layer, a priority sorting algorithm is used to sort the working conditions of the filter layer through a dynamic weighted model. The weight parameters are set, including the filter layer adsorption capacity weight of 0.5, the filter layer working temperature adaptability weight of 0.3, and the filter layer life weight of 0.2. The internal parameters of the device, including the current operating load and temperature data, are collected in real time and used as model input. The priority switching rules of the filter layer are determined through iterative weighted calculations. The operating sequence of the filter layer is optimized through the dynamic adjustment module. The filter layer operating sequence is generated based on the adjusted operating sequence. The working mode of each layer is determined and the filtration operating sequence is generated.

[0088] Operation decision generation submodule: Based on the filtering operation sequence, the task allocation algorithm is used to analyze the dynamic switching rules and operation logic of the filter layer. The overall task allocation of the filtration device is performed by defining the task priority weight, setting the activated carbon layer weight to 0.6, the HEPA layer weight to 0.3, and the ionosphere weight to 0.1 to perform dynamic task allocation. The starting conditions of each layer are determined by the logic judgment module. The setting starting conditions include the toxic gas concentration exceeding the set threshold or the filter layer priority triggering. The operation tasks are allocated and the device operation plan is generated through the dynamic task scheduling module. The operation plan is broadcast to all filtering modules through the synchronization module, and the operation optimization decision is output.

[0089] See also Figure 2 The filtration efficiency monitoring module includes an adsorption saturation monitoring submodule, an operating temperature monitoring submodule, and an operation efficiency evaluation submodule, among which:

[0090] Adsorption saturation monitoring submodule: Based on operation optimization decisions, it uses real-time data to collect the adsorption performance of the filter layer. By extracting the working records and chemical adsorption amount of the adsorption layer, it analyzes the saturation changes of the adsorption layer, calculates the remaining adsorption capacity based on the toxic gas concentration, and generates adsorption status monitoring results;

[0091] Working temperature monitoring submodule: Based on the adsorption state monitoring results, by real-time monitoring of the filter layer temperature changes, extracting the heat data recorded by the temperature sensor, analyzing the impact of temperature changes on filtration performance, determining temperature parameters in combination with the saturation state, and generating working temperature parameter records;

[0092] Operation efficiency evaluation submodule: Based on the operating temperature parameter records, it analyzes the overall operation data of the filter device under different temperatures and adsorption states, calculates the filter device operation indicators by extracting efficiency parameters and residual filtration capacity, and outputs efficiency monitoring records;

[0093] Adsorption saturation monitoring submodule: Based on the operation optimization decision, a real-time data acquisition algorithm is used to monitor the adsorption performance of the filter layer, and data is extracted from the working records of the adsorption layer. The extracted parameters include the working time record in seconds and the adsorption amount in milligrams. The linear regression model is used to analyze the saturation change trend of the chemical adsorption amount. The loss function of the model is set to the least squares error function, and the number of iterations is set to 1000 times. The saturation of the adsorption layer is curve fitted. The current adsorption state is calculated based on the fitting results. Combined with the toxic gas concentration data, the residual adsorption capacity calculation formula is set to be the residual adsorption capacity equal to the total adsorption capacity minus the current adsorption amount, and the adsorption state monitoring results are generated;

[0094] Working temperature monitoring submodule: Based on the adsorption state monitoring results, a temperature change analysis algorithm is used to monitor the temperature changes of the filter layer. The temperature change record is collected through real-time temperature sensor data. Parameters are extracted, including real-time data of heat units in joules and temperature units in degrees Celsius. The heat data is analyzed for changes in filtration performance using a formula based on the laws of thermodynamics. The temperature change rate calculation formula is set as the temperature change rate equal to the temperature difference divided by the time difference. The temperature parameters are determined by a cross-analysis model of saturation and temperature changes in combination with the adsorption state, and the working temperature parameter records are generated;

[0095] Operation efficiency evaluation submodule: Based on the working temperature parameter records, the operation efficiency analysis algorithm is used to analyze the overall operation data of the filter device under different temperatures and adsorption states. By extracting the filtration efficiency parameters including the amount of toxic gas processed per minute in milligrams per minute and the remaining filtration capacity in milligrams, the K-means clustering algorithm is used to group the extracted data for analysis of the operation status. The cluster centers are set to 3 groups, corresponding to high-efficiency operation, low-efficiency operation and critical operation states respectively. The operation indicators of the filter device are calculated based on the clustering results, and the performance monitoring records are output.

[0096] See also Figure 2 The ventilation effect real-time adjustment module includes a fan speed adjustment submodule, a positive pressure setting adjustment submodule and a ventilation parameter analysis submodule, among which:

[0097] Fan speed adjustment submodule: Based on performance monitoring records, it extracts airflow data inside and outside the vehicle and fan operating status data, reads the current fan speed in real time, compares the current air pressure inside the vehicle with the external air pressure, analyzes the impact of the air pressure difference on ventilation demand, calculates the fan speed adjustment amount based on the real-time toxic gas concentration, determines the adjusted fan operating parameters, and generates the fan speed adjustment result;

[0098] Positive pressure setting adjustment submodule: Based on the fan speed adjustment results, a fuzzy control method is used to extract the positive pressure maintainer operating data. By calculating the positive pressure difference inside the vehicle and the change in the external ambient pressure, the positive pressure maintainer output parameters are analyzed in combination with the fan speed adjustment amount. The operating mode and control logic of the positive pressure maintainer are adjusted to generate the positive pressure setting parameters.

[0099] Ventilation parameter analysis submodule: Based on the positive pressure setting parameters, it extracts real-time ventilation effect data and the changing state of airflow inside the vehicle. By calculating the combined effect of positive pressure and fan speed on the air flow inside the vehicle, it extracts the air exchange rate and airflow distribution data inside the vehicle and outputs ventilation parameter adjustments.

[0100] Fan speed adjustment submodule: Based on efficiency monitoring records, a real-time data acquisition algorithm is used to extract airflow data inside and outside the vehicle and fan operating status data. The PID control algorithm is used to compare the real-time in-vehicle air pressure and external air pressure by reading the current fan speed. The parameters of the PID control algorithm are set to a proportional coefficient of 0.5, an integral coefficient of 0.1, and a differential coefficient of 0.05. The ventilation demand is analyzed based on the pressure difference data. The fan operating speed adjustment amount is calculated by an interpolation algorithm based on the toxic gas concentration data. The interpolation step size is set to 0.1. The adjusted fan speed data is combined with the PID control parameters to update the speed, determine the adjusted fan operating parameters, and generate the fan speed adjustment result.

[0101] Positive pressure setting adjustment submodule: Based on the fan speed adjustment result, a fuzzy control algorithm is used to extract the positive pressure maintainer operation data. By calculating the positive pressure difference in the vehicle, the pressure difference formula is used to set the positive pressure calculation model to pressure difference equal to the vehicle pressure minus the external pressure. The external environmental pressure changes are monitored in real time. The fuzzy control rules are used to set the fuzzy set to three output levels of low, medium and high based on the fan speed adjustment amount. The output parameters of the positive pressure maintainer are rule-based reasoning. The adjusted output value is generated through fuzzy rules and the setting range is 0 to 100. The positive pressure maintainer operation mode and control logic are adjusted to generate the positive pressure setting parameters.

[0102] Ventilation parameter analysis submodule: Based on the positive pressure setting parameters, a joint analysis algorithm is used to extract real-time ventilation effect related data and the airflow change state in the vehicle. The positive pressure parameters and fan speed data are jointly analyzed through a multivariate linear regression model. The linear regression model parameters are set to include independent variables such as positive pressure and fan speed, and the dependent variable is the air exchange rate in the vehicle. The air flow state in the vehicle is extracted through a wind speed sensor to extract air flow distribution data. The data collection frequency is set to 10 times per second. The air exchange rate and airflow distribution data in the vehicle are extracted through the joint regression results, and the ventilation parameter adjustment is output.

[0103] Extracting the operating data of the positive pressure maintainer requires collecting the maintainer's output pressure value, target pressure setting value, real-time output power, pressure adjustment range, and valve opening and closing status. The output pressure is collected in real time through the pressure sensor, and the target pressure and adjustment range are extracted in combination with the set value. The current power output is also recorded, and the valve opening and closing angle and operation status are also recorded. All data is synchronously extracted through the real-time control system of the positive pressure maintainer.

[0104] Extracting real-time ventilation effect-related data requires pollutant concentration, temperature, humidity, air pressure, air flow speed and direction. The pollutant concentration is obtained through air quality sensors, the temperature and humidity distribution is obtained through temperature and humidity sensors, the air pressure difference inside and outside the vehicle is recorded through air pressure sensors, and the flow speed and direction data in different areas of the vehicle are obtained through air flow sensors. The air flow distribution characteristics in the vehicle are comprehensively analyzed in combination with the operating status of the fan and air valve.

[0105] See also Figure 2 The ventilation path optimization module includes an airflow distribution simulation submodule, a fan power adjustment submodule, and a valve state optimization submodule, among which:

[0106] Airflow distribution simulation submodule: Based on ventilation parameter adjustments, it extracts interior space layout data and the physical position relationship of fans and air valves. It reads real-time ventilation status data and combines it with the interior temperature and humidity distribution to analyze the air flow trajectory in each area of ​​the vehicle. It identifies areas where air flow is blocked, optimizes the airflow path, and generates an airflow distribution path.

[0107] Fan power adjustment submodule: Based on the airflow distribution path, it extracts fan power output data. By comparing the airflow distribution uniformity and air exchange rate in each area, it adjusts the fan power output level and operation mode, optimizes the fan operating parameters to improve the airflow distribution, and generates the fan output power parameters.

[0108] Valve state optimization submodule: Based on the fan output power parameters, it extracts the real-time valve opening and closing status data, analyzes the linkage relationship between valve opening and closing and fan output, optimizes the airflow channel by adjusting the valve opening angle and dynamic switching strategy, establishes a ventilation path optimization plan, and outputs the optimized airflow path;

[0109] Airflow distribution simulation submodule: Based on ventilation parameter adjustment, a numerical fluid dynamics simulation algorithm is used to simulate and analyze the interior space layout data and the physical position relationship between the fan and the air valve. Parameters extracted from the interior space layout data include geometric information with length, width and height dimensions in meters and the cross-sectional area of ​​the ventilation channel in square meters. Real-time ventilation status data is read and combined with the interior temperature and humidity distribution data, an interpolation algorithm is used to smooth the temperature and humidity gradients. The interpolation step size is set to 0.01 meters for spatial temperature and humidity distribution grid processing. The air flow trajectory in each area of ​​the vehicle is calculated using a fluid dynamics calculation model with a flow rate of meters per second and a turbulence intensity of 10%. The air flow obstruction area is identified by setting the obstruction judgment condition to mark the area with a flow rate below 0.1 meters per second as the obstructed area and performing path adjustment to generate the airflow distribution path.

[0110] Fan power adjustment submodule: Based on the airflow distribution path, a linear regression algorithm is used to analyze the fan power output data. By extracting the fan output power data in watts and comparing it with the airflow distribution uniformity in percentage and the air exchange rate in air changes per hour in each area, the fan power adjustment amount is set as the dependent variable of the regression model, and the independent variables are airflow uniformity and exchange rate. The number of model iterations is set to 1000 times. The fan power output level is adjusted based on the fitting calculation results. The adjusted fan operation mode, including variable frequency operation and constant operation mode, is used to set the operating parameters and generate the fan output power parameters.

[0111] Valve state optimization submodule: Based on the fan output power parameters, a genetic algorithm is used to optimize the real-time opening and closing state data of the valve. By extracting the valve opening and closing state data, including the records of the opening angle in degrees and the dynamic switching time in seconds, the linkage relationship between the valve opening and closing and the fan output is analyzed. The genetic algorithm sets the population size to 50, the crossover probability to 0.8, and the mutation probability to 0.1 to optimize the valve opening angle and dynamic switching strategy. The ventilation path is adjusted for the optimized valve state through the control logic module, the optimized ventilation path is established, and the airflow optimization path is generated.

[0112] A positive pressure gas filtering and ventilation control method for a riot control and dispersal vehicle is applied to the positive pressure gas filtering and ventilation control system of the riot control and dispersal vehicle, and includes the following steps:

[0113] Step 1: Based on the output data of chemical and optical sensors, extract the chemical reaction signals and optical absorption signals of the toxic gas, analyze their characteristic values, and combine the chemical reaction time, conductivity, and light absorption spectrum to classify the toxic gas type and quantify the concentration to generate gas characteristic data;

[0114] Step 2: Based on the gas characteristic data, combined with the chemical composition and concentration of the toxic gas, the reaction performance of the toxic gas and the filter material is analyzed. The activated carbon layer's adsorption adaptability to organic toxic gases, the HEPA layer's efficiency in filtering particulate matter, and the ionosphere's ability to remove chemical reaction toxic gases are analyzed. Through a gradient boosting decision tree, the priority and operation timing rules of each layer's filter unit are dynamically adjusted, filtration tasks are assigned, and the required units are activated to generate a filtration configuration plan.

[0115] Step 3: Based on the filter configuration plan, the current operating load, task priority, and toxic gas characteristics of the filter unit are dynamically analyzed. By judging the saturation and chemical adaptability of the filter unit, the filter unit is started or shut down according to the task priority. The operating time of low-load units is extended, and the operating time of high-load units is reduced. The working sequence is optimized and dynamic switching is completed to generate operation optimization decisions;

[0116] Step 4: Based on operational optimization decisions, collect the adsorption saturation, current operating temperature, and filtration time of each filter unit, determine the remaining capacity of the adsorption layer based on the chemical reaction rate, record the filtration saturation and operating efficiency of the HEPA layer for particulate matter, dynamically adjust the thermal impact of the high-temperature filter layer, record the current performance status of all layers, and generate performance monitoring records;

[0117] Step 5: Based on performance monitoring records, the fan speed is dynamically adjusted to stabilize the positive pressure state by analyzing the pressure difference between the inside and outside of the vehicle, the fan output speed, and the current power of the positive pressure maintainer. The power level of the positive pressure maintainer is adjusted using fuzzy control methods combined with the positive pressure output range to optimize ventilation effect and synchronously adjust the fan and positive pressure device to generate ventilation parameter adjustments.

[0118] Step 6: Based on the ventilation parameter adjustment, analyze the linkage between the fan output power and the airflow distribution, calculate the adaptive adjustment plan of the airflow path through the air pressure distribution at different locations in the vehicle, dynamically adjust the opening and closing angle of the air valve and the fan output power, perform real-time correction on the airflow distribution area in the vehicle, and generate an optimized airflow path.

[0119] The above are merely preferred embodiments of the present invention and do not limit the present invention in any other form. Any technician familiar with the profession may use the technical content disclosed above to change or modify it into an equivalent embodiment with equivalent changes and apply it to other fields. However, any simple modification, equivalent change and modification made to the above embodiment based on the technical essence of the present invention without departing from the content of the technical solution of the present invention shall still fall within the scope of protection of the technical solution of the present invention.

Claims

1. A positive pressure gas filtering and ventilation control system for a riot control and dispersal vehicle, characterized in that: The system comprises: Gas type and concentration identification module: used to detect the composition and concentration of toxic gases in the external environment based on chemical sensors and optical sensors, record the chemical properties of the gases, and generate gas characteristic data; The dynamic configuration module for the filter device is used to select the appropriate filter layer based on the chemical characteristics of the toxic gas using a gradient boosting decision tree based on the gas characteristic data, adjust the working priority and working status of the activated carbon layer, HEPA layer and ionosphere, and assign an operation sequence to generate a filter configuration plan; the dynamic configuration module for the filter device includes a filter demand assessment submodule, a filter layer priority adjustment submodule and a filter configuration generation submodule, wherein: Filtration demand assessment submodule: Based on the gas characteristic data, a gradient boosting decision tree is used to analyze the chemical properties of the toxic gas, calculate the reaction performance of the toxic gas components and the filter material, evaluate the adsorption capacity and load demand of the filter layer, extract the demand parameters of the filter material, and generate the filtration demand parameters; Filter layer priority adjustment submodule: Based on the filtering requirement parameters, adjust the working mode of the filter layer, set the activation conditions of the activated carbon layer, HEPA layer and ionization layer, optimize the filtering priority order of each layer, establish the dynamic operation sequence configuration of the filter layer, and generate the filter layer priority configuration; Filter configuration generation submodule: Based on the filter layer priority configuration, it allocates the operation tasks of the filter device, sets the working order of each layer in the filter device, sets the operation logic and association rules during dynamic switching, generates the task operation table of the filter device, and outputs the filter configuration plan; Optimizing filtration operation module: used to determine the timing of activating and deactivating the filter device based on the filtration configuration scheme, combined with the working priority and chemical characteristics of the filter layer, and adjust the working sequence of the filter device to match the actual needs, thereby generating an operation optimization decision; Filter efficiency monitoring module: used to monitor the adsorption saturation and operating temperature of each filter layer based on the operation optimization decision, check the operating efficiency of each filter layer, and generate efficiency monitoring records; A real-time ventilation effect adjustment module is used to adjust the fan speed and the setting of the positive pressure maintainer in real time based on the performance monitoring records using a fuzzy control method, analyze the real-time data to maintain the positive pressure in the vehicle and optimize the ventilation effect, and generate ventilation parameter adjustments; Ventilation path optimization module: used to simulate the airflow distribution in the vehicle based on the ventilation parameter adjustment, adjust the fan output power and air valve status according to the real-time ventilation effect and the space layout in the vehicle, and generate an optimized airflow path.

2. The positive pressure gas filtering and ventilation control system for a riot control and dispersal vehicle according to claim 1 is characterized in that: The gas type and concentration identification module includes a chemical data acquisition submodule, an optical property analysis submodule, and a gas property extraction submodule, wherein: Chemical data acquisition submodule: Based on the detection of toxic gas components and concentrations in the external environment by chemical sensors, the module collects electrical signals from chemical sensors, extracts changes in electrical signal intensity, analyzes the chemical reaction characteristics of toxic gas components, extracts electrical signal characteristic values ​​related to toxic gas components, and generates chemical response characteristic data; Optical characteristic analysis submodule: Based on the chemical response characteristic data, the optical sensor detects the absorption characteristics of light of a specific wavelength, collects changes in the absorption light intensity of the optical sensor, analyzes the wavelength absorption characteristics of the poison gas molecules to light, extracts the characteristic information of the poison gas molecules on the spectrum, and generates optical absorption characteristic data; Gas characteristic extraction submodule: Based on the optical absorption characteristic data and combined with the chemical response characteristic data, the chemical properties and concentration information of the poisonous gas are extracted by matching the optical characteristics and chemical response characteristic values, and the gas characteristic data is output.

3. The positive pressure gas filtering and ventilation control system for a riot control and dispersal vehicle according to claim 1 is characterized in that: The calculation formula for the reaction performance of the toxic gas component and the filter material is: ； Where: Gain is the gain value of the reaction performance between the toxic gas component and the filter material, is the gradient value of the left branch filter material, is the gradient value of the right branch filter material, is the second-order gradient value of the left branch filter material, is the second-order gradient value of the right branch filter material, is the regularization parameter, is the chemical reaction time between the poison gas and the filter material, is the chemical reaction time between the left branch poison gas and the filter material, is the chemical reaction time between the right branch poison gas and the filter material, is the affinity coefficient between the poison gas molecules and the filter material molecules, is the surface molecular density of the filter material, is the surface molecular density of the left branch filter material, is the surface molecular density of the right branch filter material, is the weight coefficient of chemical reaction time, is the weight of the affinity coefficient, is the weight of the molecular density.

4. The positive pressure gas filtering and ventilation control system for a riot control and dispersal vehicle according to claim 1 is characterized in that: The optimized filtering operation module includes a filtering timing control submodule, a work sequence adjustment submodule, and an operation decision generation submodule, wherein: Filter timing control submodule: Based on the filtering configuration scheme, by detecting the current state of the filter layer in the filter device and combining it with the ambient toxic gas concentration, extracting environmental parameters and filter layer operation data, calculating the filtering conditions required for device startup, extracting the filter layer switching time, and generating a filtering timing determination result; Working sequence adjustment submodule: Based on the filtration timing determination result, combined with the chemical characteristics of each filter layer, by analyzing the working conditions of the filter layer and the internal parameters of the device, setting the priority switching rules of the filter layer, optimizing the operating order of the filter layer, determining the working mode of each layer, and generating the filtration operation sequence; Operation decision generation submodule: Based on the filtering operation sequence, by extracting the dynamic switching rules and operation logic of the filtering layer, setting the overall task allocation of the filtering device and the startup conditions of each layer, generating the device operation plan and synchronizing it to all filtering modules, and outputting the operation optimization decision.

5. The positive pressure gas filtering and ventilation control system for a riot control and dispersal vehicle according to claim 1 is characterized in that: The filtration efficiency monitoring module includes an adsorption saturation monitoring submodule, an operating temperature monitoring submodule, and an operation efficiency evaluation submodule, wherein: Adsorption saturation monitoring submodule: Based on the above-mentioned operation optimization decision, the adsorption performance of the filter layer is collected using real-time data. By extracting the working records and chemical adsorption amount of the adsorption layer, the saturation change of the adsorption layer is analyzed, and the remaining adsorption capacity is calculated in combination with the toxic gas concentration to generate the adsorption status monitoring results; Working temperature monitoring submodule: Based on the adsorption state monitoring results, by real-time monitoring of the filter layer temperature changes, extracting the heat data recorded by the temperature sensor, analyzing the impact of temperature changes on filtration performance, determining temperature parameters in combination with the saturation state, and generating working temperature parameter records; Operation efficiency evaluation submodule: Based on the operating temperature parameter records, analyze the overall operation data of the filter device under different temperatures and adsorption states, calculate the filter device operation indicators by extracting efficiency parameters and residual filtration capacity, and output efficiency monitoring records.

6. The positive pressure gas filtering and ventilation control system for a riot control and dispersal vehicle according to claim 1 is characterized in that: The ventilation effect real-time adjustment module includes a fan speed adjustment submodule, a positive pressure setting adjustment submodule and a ventilation parameter analysis submodule, wherein: The fan speed adjustment submodule extracts the airflow data inside and outside the vehicle and the fan operating status data based on the efficiency monitoring records, reads the current fan speed in real time, compares the current air pressure inside the vehicle with the external air pressure, analyzes the impact of the air pressure difference on ventilation demand, calculates the fan speed adjustment amount based on the real-time toxic gas concentration, determines the adjusted fan operating parameters, and generates the fan speed adjustment result. Positive pressure setting adjustment submodule: Based on the fan speed adjustment result, a fuzzy control method is used to extract the positive pressure maintainer operating data. By calculating the positive pressure difference inside the vehicle and the change in the external ambient pressure, the positive pressure maintainer output parameters are analyzed in combination with the fan speed adjustment amount. The operating mode and control logic of the positive pressure maintainer are adjusted to generate the positive pressure setting parameters. Ventilation parameter analysis submodule: Based on the positive pressure setting parameters, it extracts real-time ventilation effect related data and the change status of the airflow in the vehicle. By calculating the combined effect of positive pressure and fan speed on the air flow in the vehicle, it extracts the air exchange rate and airflow distribution data in the vehicle, and outputs the ventilation parameter adjustment.

7. The positive pressure gas filtering and ventilation control system for a riot control and dispersal vehicle according to claim 6 is characterized in that: The extraction of the positive pressure maintainer operating data requires collecting the maintainer's output pressure value, target pressure setting value, real-time output power, pressure adjustment range, and valve opening and closing status. The output pressure is collected in real time by a pressure sensor, and the target pressure and adjustment range are extracted in combination with the set value. The current power output is recorded, and the valve opening and closing angle and operation status are recorded at the same time. All data are synchronously extracted by the real-time control system of the positive pressure maintainer. The extraction of real-time ventilation effect related data needs to include pollutant concentration, temperature, humidity, air pressure, air flow speed and direction. The pollutant concentration is obtained through the air quality sensor, the temperature and humidity distribution is obtained through the temperature and humidity sensor, the air pressure difference inside and outside the vehicle is recorded through the air pressure sensor, and the flow speed and direction data of different areas in the vehicle are obtained through the air flow sensor. The air flow distribution characteristics in the vehicle are comprehensively analyzed in combination with the operating status of the fan and the air valve.

8. The positive pressure gas filtering and ventilation control system for a riot control and dispersal vehicle according to claim 1 is characterized in that: The ventilation path optimization module includes an airflow distribution simulation submodule, a fan power adjustment submodule, and a valve state optimization submodule, wherein: Airflow distribution simulation submodule: Based on the ventilation parameter adjustment, it extracts the interior space layout data and the physical position relationship of the fan and air valve, reads the real-time ventilation status data and combines it with the temperature and humidity distribution in the vehicle to analyze the air flow trajectory in each area of ​​the vehicle, identify areas where air flow is blocked, optimize the airflow path, and generate the airflow distribution path; Fan power adjustment submodule: extracts fan power output data based on the airflow distribution path, adjusts the fan power output level and operation mode by comparing the airflow distribution uniformity and air exchange rate in each area, optimizes the fan operating parameters to improve the airflow distribution, and generates the fan output power parameters; Valve state optimization submodule: Based on the fan output power parameters, extract the real-time opening and closing state data of the valve, analyze the linkage relationship between the valve opening and closing and the fan output, optimize the airflow channel by adjusting the valve opening angle and dynamic switching strategy, establish a ventilation path optimization plan, and output the airflow optimization path.

9. A positive pressure gas filtration and ventilation control method for a riot control and dispersal vehicle, applied to the positive pressure gas filtration and ventilation control system for a riot control and dispersal vehicle according to any one of claims 1 to 8, characterized in that: The method comprises the following steps: Step 1: Based on the output data of chemical and optical sensors, extract the chemical reaction signals and optical absorption signals of the toxic gas, analyze their characteristic values, and combine the chemical reaction time, conductivity, and light absorption spectrum to classify the toxic gas type and quantify the concentration to generate gas characteristic data; Step 2: Based on the gas characteristic data, combined with the chemical composition and concentration of the toxic gas, the reaction performance of the toxic gas and the filter material is analyzed. The activated carbon layer's adsorption adaptability to organic toxic gases, the HEPA layer's efficiency in filtering particulate matter, and the ionosphere's ability to remove chemical reaction toxic gases are analyzed. The priority and operation timing rules of each layer of filter units are dynamically adjusted through a gradient boosting decision tree. Filtering tasks are assigned and the required units are activated to generate a filtration configuration plan. Step 3: Based on the filter configuration scheme, the current operating load, task priority, and toxic gas characteristics of the filter unit are dynamically analyzed. By judging the saturation and chemical adaptability of the filter unit, the filter unit is started or shut down according to the task priority. The operating time of low-load units is extended, and the operating time of high-load units is reduced. The working sequence is optimized and dynamic switching is completed to generate operation optimization decisions; Step 4: Based on the above-mentioned operation optimization decision, the adsorption saturation, current operating temperature and filtration time of each filter unit are collected, the remaining capacity of the adsorption layer is determined according to the chemical reaction rate, the filtration saturation and operating efficiency of the HEPA layer for particulate matter are recorded, the thermal impact of the high-temperature filter layer is dynamically adjusted, the current performance status of all layers is recorded, and an efficiency monitoring record is generated; Step 5: Based on the performance monitoring records, the fan speed is dynamically adjusted to stabilize the positive pressure state by analyzing the pressure difference between the inside and outside of the vehicle, the fan output speed, and the current power of the positive pressure maintainer. The power level of the positive pressure maintainer is adjusted according to the fuzzy control method and the positive pressure output range to optimize the ventilation effect and synchronously adjust the fan and positive pressure device to generate ventilation parameter adjustments; Step 6: Based on the ventilation parameter adjustment, the linkage relationship between the fan output power and the airflow distribution is analyzed, the adaptive adjustment plan of the airflow path is calculated through the air pressure distribution at different positions in the vehicle, the opening and closing angle of the air valve and the fan output power are dynamically adjusted, the distribution area of ​​the airflow in the vehicle is corrected in real time, and the optimized airflow path is generated.

Images