Intelligent nitrogen oxide catalytic decomposition system

Abstract

The invention discloses an intelligent nitrogen oxide catalytic decomposition system which comprises a sensor module, a response type control system, a light reaction furnace and a cloud platform control system. The sensor module comprises a temperature sensor, a flue gas concentration sensor and an illumination sensor and is used for detecting the temperature, the flue gas concentration and the illumination in the current reaction furnace; and the response type control system comprises a heater, a methanol controller and a dimming lamp, and is used for regulating and controlling the temperature, the smoke concentration and the illumination intensity in the light reaction furnace. And the cloud platform control system receives the environment information, constructs a target function, performs optimization through an artificial firefly group optimization algorithm by taking the maximum reaction rate as a target, and adjusts the temperature, the flue gas concentration and the illumination intensity through the response type control system. Compared with traditional photocatalytic nitrogen oxide, the device is more intelligent, the reaction efficiency can be improved, the reaction can be more complete and thorough, the use of sacrificial agent methanol can be accurately controlled, and the cost can be reduced.

Description

Technical Field

[0001] The present invention relates to the field of environmental protection technology, and in particular to an intelligent nitrogen oxide catalytic decomposition system, in particular to process optimization and control of nitrogen oxide (NOx) treatment using photocatalytic technology. Background Art

[0002] Nitrogen oxides (NOx), as one of the main air pollutants, mainly come from industrial combustion, automobile exhaust and chemical production processes, posing a serious threat to environmental quality and human health. Photocatalytic technology, as a green and efficient means of air purification, uses photogenerated electron-hole pairs generated by semiconductor materials under light conditions to catalytically decompose or reduce nitrogen oxides into harmless nitrogen (N2) and water (H2O). Due to its advantages of low energy consumption and no secondary pollution, it has shown great potential in the field of industrial waste gas treatment.

[0003] However, the traditional photocatalytic nitrogen oxide treatment system has several limitations: first, the reaction efficiency is greatly affected by the fluctuation of environmental parameters (such as temperature, flue gas concentration, and light intensity), making it difficult to maintain continuous high efficiency; second, the reaction process lacks a real-time control mechanism, resulting in incomplete reaction and poor product selectivity; third, the amount of sacrificial agent (such as methanol) used is difficult to accurately control, which not only increases operating costs, but may also cause secondary pollution problems. Therefore, the development of a photocatalytic nitrogen oxide treatment system that can intelligently control reaction conditions, optimize the reaction process, and accurately control the amount of sacrificial agent has become a technical problem that needs to be solved urgently. Summary of the invention

[0004] Purpose of the invention: The purpose of the present invention is to provide an intelligent control system for industrial waste gas treatment. By integrating high-precision sensors, intelligent response control systems, cloud platform data analysis and intelligent algorithm decision-making, real-time monitoring and precise control of the photocatalytic reaction environment are realized, aiming to improve reaction efficiency and reaction completeness, and optimize the use of sacrificial agents, thereby providing a more efficient, economical and environmentally friendly solution for industrial waste gas treatment.

[0005] Technical solution: The present invention provides an intelligent nitrogen oxide catalytic decomposition system, characterized in that it includes a light reactor, a sensor module, a cloud platform control system, and a responsive control system;

[0006] The sensor module includes a temperature sensor, a smoke concentration sensor, and a light sensor, all of which are arranged in the photoreactor to detect environmental parameters such as temperature, smoke concentration, and light intensity in the photoreactor;

[0007] The responsive control system includes a heater, a methanol controller and a dimming lamp, which are used to adjust the temperature in the reaction furnace, the supply of methanol in the photoreaction furnace and the light intensity in the photoreaction furnace according to the instructions of the cloud platform control system;

[0008] The cloud platform control system is used to receive environmental parameters from the sensor module, construct a reaction rate objective function, and optimize the objective function by artificial firefly swarm optimization with the maximum reaction rate as the goal, so as to maximize the rate of photocatalytic nitrogen oxide reaction, and determine the optimal temperature, flue gas concentration, light intensity and methanol usage according to the optimization results. The cloud platform control system sends instructions to the responsive control system to adjust the environmental parameters in the reactor.

[0009] Furthermore, when the temperature sensor detects that the temperature in the photoreactor is lower than the optimal reaction temperature, the heater automatically starts to increase the temperature in the photoreactor; the dimming lamp adjusts the light intensity in the photoreactor according to the data of the light sensor. When the light intensity is insufficient, the dimming lamp automatically starts to increase the light intensity to ensure that the photocatalytic reaction can proceed fully; when the methanol controller detects that the methanol supply in the photoreactor is lower than the optimal methanol supply, the methanol controller automatically starts to replenish the methanol.

[0010] Furthermore, the objective function is as follows:

[0011]

[0012] Where R is the reaction rate, k is a positive proportional constant that depends on the properties of the photocatalyst, T is the temperature in the photoreactor, α is the index of the effect of temperature on the reaction rate, C is the concentration of nitrogen oxides in the flue gas, σ is the index of the effect of concentration on the reaction rate, I is the light intensity, η is the index of the effect of light intensity on the reaction rate, M is the amount of methanol used, δ is the index of the effect of methanol use on the reaction rate. Since methanol is a sacrificial agent, its effect is nonlinear, so M is used. δ To express; the amount of methanol used has a negative effect on the reaction rate because of its nature as a sacrificial agent.

[0013] Furthermore, the artificial firefly swarm optimization algorithm GSO is used to optimize the objective function and dynamically adjust the heater, methanol controller and dimming lamp in the responsive control system. The specific process is as follows:

[0014] Step 1: Initialization of Firefly;

[0015] Several fireflies are randomly placed in the feasible domain. In the population, each individual firefly is randomly distributed in the space defined by the objective function. The position information of each individual firefly corresponds to a reaction rate, and the position update of the individual firefly is affected by the fluorescein, movement probability and dynamic decision radius, which correspond to the effects of temperature, methanol usage and light intensity on the reaction rate respectively. In the initial stage, all fireflies have the same fluorescein value and dynamic decision radius, the dynamic decision domain is r0, the initialization step size is s, and the neighborhood threshold is n.t , the fluorescein update factor (timely extraction ratio) is γ, the dynamic decision domain update rate (neighborhood change rate) is β, and the firefly perception domain is r s , the number of iterations is M;

[0016] Step 2: Fluorescence renewal phase

[0017] The fluorescein value of each firefly individual is equal to the fluorescein value at the previous moment plus a certain extraction ratio of the current fitness value of the firefly, and then minus a certain ratio of the fluorescein value that evaporates over time, that is, the reaction rate is affected by the current temperature value, as shown in formula (1):

[0018] l i (t+1)=(1-ρ)l i (t)+γJ(x i (t+1)) (1)

[0019] Among them, l i (t) represents the fluorescein concentration of firefly i at the tth iteration, l i (t+1) represents the concentration of fluorescein of firefly i at the t+1th iteration, ρ is the volatility coefficient of fluorescein, γ is the fitness extraction ratio, and x i (t+1) represents the updated position of firefly i in the t+1th iteration; J(x i (t+1)) represents the fitness value of firefly i in the t+1th iteration, that is, the objective function value.

[0020] Step 3: Move probability calculation phase

[0021] Each firefly needs to decide the direction of movement according to the concentration of fluorescein of all neighboring fireflies within the decision radius. The catalyst of the reaction rate is affected by all environments and also depends on the temperature in the reaction environment. ij It represents the probability that firefly i moves to its neighbor firefly j at the tth iteration. The calculation formula is as follows:

[0022]

[0023] Where j∈N i (t), N i (t) = {j:||x j (t)-x i (t)||<r di (t); l i (t)<l j (t)} is the set of all neighboring fireflies of the i-th firefly individual in the t-th iteration, r di(t) represents the dynamic decision domain of firefly i in the tth iteration, ||x(t)|| represents the norm of x, l j (t) represents the concentration of fluorescein in the t-th iteration of firefly j, which corresponds to the influence of the firefly position movement information on the concentration of fluorescein, that is, the reaction rate is affected by the ambient temperature; x i (t), x j (t) represents the updated positions of firefly i and firefly j at the tth iteration respectively;

[0024] Step 4: Select the maximum movement probability and update the position: Firefly i moves a certain step length towards the firefly j with the largest fluorescence within its decision radius. Then the movement formula at the t+1 iteration is as follows:

[0025]

[0026] Among them, s is the step size, x i (t+1) is the updated position of firefly i at the t+1th iteration.

[0027] Step 5: Each firefly adopts an adaptive dynamic decision radius. The decision radius depends on the density of neighboring fireflies. The reaction rate is affected by the external environment light. In each iteration, the decision radius is changed according to the density of neighboring fireflies, that is, the dimming light is adjusted in real time according to the impact of the environment on the reaction rate, thereby changing the external environment light intensity. When the neighbor density is smaller, the decision radius is increased to find more neighbors. Conversely, when the neighbor density is smaller, the decision radius is reduced. The specific adjustment is made according to formula (4):

[0028] r di (t+1)=min{r s ,max{0,r di (t)+β(n t -|N i (t)|)}} (4)

[0029] Among them, β represents the domain change rate, n t represents the neighbor threshold, controlling the number of firefly neighbors, r s represents the firefly sensing range, r di (t) represents the dynamic decision range of firefly i at the tth iteration, and 0≤r di (t)≤r s ;

[0030] Step 6: Determine whether the maximum number of iterations or the required accuracy has been reached. If so, go to the next step; otherwise, go to step 4.

[0031] Step 7: Output the optimal individual value, that is, output the fastest global reaction rate.

[0032] Furthermore, the cloud platform control system includes a remote monitoring and early warning module for remote monitoring and early warning to ensure the safety and stability of the reaction process.

[0033] Beneficial effects:

[0034] 1. The present invention integrates advanced sensor technology, automated control systems, cloud computing platforms and intelligent algorithms, aiming to achieve efficient, accurate and intelligent management of industrial photocatalytic reaction processes in order to cope with increasingly stringent environmental protection requirements and industrial waste gas emission standards.

[0035] 2. The objective function designed in the present invention comprehensively considers multiple factors that have a significant impact on the photocatalytic reaction rate, such as temperature, flue gas concentration, light intensity and methanol usage, and reflects the interaction and influence between the various factors. It can accurately reflect the changing trend of the reaction rate when these factors change, so that the system can automatically adjust the environmental parameters according to actual needs, and achieve the optimal reaction effect through refined regulation.

[0036] 3. The artificial firefly swarm optimization algorithm (GSO) of the present invention is an ideal choice for optimizing the objective function in the present invention due to its strong global search capability, adaptive parameter adjustment, and easy implementation and expansion. The GSO algorithm simulates the natural behavior of fireflies and performs efficient global search in a larger search space, avoiding the risk of falling into a local optimal solution. At the same time, the individual fireflies in the algorithm can adaptively adjust their movement strategies and decision radius according to environmental information, making the search process more flexible and accurate. In addition, the GSO algorithm has a simple structure, is easy to implement, and can be improved and optimized according to actual needs, providing strong technical support for the intelligent control system of industrial photocatalytic nitrogen oxides. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 It is the structural block diagram of the system;

[0038] Figure 2 It is the flow chart of the system;

[0039] Figure 3 Schematic diagram of intelligent algorithm. DETAILED DESCRIPTION

[0040] The present invention will be further described below in conjunction with the accompanying drawings. The following embodiments are only used to more clearly illustrate the technical solution of the present invention, and cannot be used to limit the protection scope of the present invention.

[0041] The invention discloses an intelligent nitrogen oxide catalytic decomposition system, comprising a photoreactor, a sensor module, a cloud platform controller, and a responsive control system.

[0042] The sensor module includes a temperature sensor, a flue gas concentration sensor, and a light sensor, which are used to detect the environmental parameters of temperature, flue gas concentration, and light intensity in the photoreactor; among them, the temperature sensor is used to monitor the temperature in the photoreactor in real time. Temperature is one of the key factors affecting the rate and efficiency of photocatalytic reactions. By accurately measuring the temperature in the furnace, it can be ensured that the reaction is carried out within the optimal temperature range, thereby improving the conversion efficiency of photocatalytic nitrogen oxides. The flue gas concentration sensor is used to detect the concentration of nitrogen oxides and other harmful gases in the reactor. By monitoring the flue gas concentration, the reaction conditions can be adjusted in time to ensure that nitrogen oxides are effectively converted while avoiding the accumulation of other harmful gases. The light sensor is used to measure the light intensity in the reactor. Light is a necessary condition for photocatalytic reactions, and changes in light intensity will directly affect the reaction rate. The light sensor can ensure that the light intensity in the reactor is always kept within the optimal range, thereby optimizing the photocatalytic effect.

[0043] The responsive control system includes a heater, a methanol controller, and a dimming lamp. According to the instructions of the cloud platform control system, the temperature in the reactor is adjusted. When the temperature sensor detects that the temperature in the furnace is lower than the optimal reaction temperature, the heater will automatically start to increase the temperature in the furnace to ensure that the reaction is carried out under suitable temperature conditions. The main function of the methanol controller is to accurately adjust the supply of methanol in the reactor. Methanol is usually used as a sacrificial agent in this photocatalytic reaction to promote the photocatalytic conversion process of nitrogen oxides. According to the instructions of the cloud platform, the use of sacrificial agent methanol can be accurately controlled to reduce production costs, improve reaction efficiency, optimize the reaction process, and ensure the safety and stability of the reaction process. The dimming lamp adjusts the light intensity in the reactor according to the data of the light sensor. When the light intensity is insufficient, the dimming lamp will automatically start to increase the light intensity in the furnace to ensure that the photocatalytic reaction can be fully carried out.

[0044] The cloud platform control system is the core of the entire intelligent control system. The cloud platform control system receives data from the sensor module and analyzes and processes the data through intelligent algorithms. According to the analysis results, the cloud platform control system will issue instructions to the responsive control system to adjust the environmental parameters in the reactor. In addition, the cloud platform control system can also realize remote monitoring and early warning functions to ensure the safety and stability of the reaction process. The cloud platform control system also includes a remote monitoring and early warning module for remote monitoring and early warning to ensure the safety and stability of the reaction process.

[0045] The present invention constructs an objective function with the optimal reaction rate as the goal, and optimizes the objective function through artificial firefly swarm optimization to maximize the rate of photocatalytic nitrogen oxide reaction. The optimal temperature, flue gas concentration, light intensity and methanol usage are determined according to the optimization results, and each device in the responsive control system is flexibly adjusted to achieve optimal regulation of the photocatalytic nitrogen oxide reaction to maximize the rate of the photocatalytic nitrogen oxide reaction.

[0046] Considering that the reaction rate (R) is affected by temperature (T), flue gas concentration (C), light intensity (I) and methanol usage (M), the following objective function is constructed:

[0047]

[0048] Where R is the reaction rate, k is a positive proportional constant that depends on the properties of the photocatalyst, T is the temperature in the photoreactor, α is the index of the effect of temperature on the reaction rate, C is the concentration of nitrogen oxides in the flue gas, σ is the index of the effect of concentration on the reaction rate, I is the light intensity, η is the index of the effect of light intensity on the reaction rate, M is the amount of methanol used, δ is the index of the effect of methanol use on the reaction rate. Since methanol is a sacrificial agent, its effect is nonlinear, so M is used. δ To express; the amount of methanol used has a negative effect on the reaction rate because of its nature as a sacrificial agent.

[0049] The amount of methanol used may have a negative impact on the reaction rate due to its nature as a sacrificial agent. The goal is to find the best values ​​of T, C, I, and M to maximize R. The cloud platform control system will collect real-time data from the sensor module and use the artificial glowworm swarm optimization (GSO) algorithm to dynamically adjust the heater, methanol controller, and dimming lamp in the responsive control system to optimize the above objective function. The specific steps of the artificial glowworm swarm optimization algorithm are:

[0050] Step 1, Firefly deployment (initialization)

[0051] A number of fireflies are randomly placed in the feasible domain. In the population, each individual firefly is randomly distributed in the space defined by the objective function. The position information of each individual firefly corresponds to a reaction rate, and the position update of the individual firefly is affected by the fluorescein, movement probability and dynamic decision radius, which correspond to the effects of temperature, methanol amount and light intensity on the reaction rate. In the initial stage, all fireflies have the same fluorescein value and dynamic decision radius, the dynamic decision domain is r0, the initialization step size is s, and the neighborhood threshold is n t , fluorescein update factor (timely extraction ratio) γ, dynamic decision domain update rate (neighborhood change rate) β, firefly perception domain is rs , the number of iterations is M.

[0052] Step 2: Fluorescence renewal phase

[0053] The fluorescein value of each firefly individual is equal to the fluorescein value at the previous moment plus a certain extraction ratio of the current fitness value of the firefly, and then minus a certain ratio of the fluorescein value that evaporates over time, that is, the reaction rate is affected by the current temperature value, as shown in formula (1):

[0054] l i (t+1)=(1-ρ)l i (t)+γJ(x i (t+1)) (1)

[0055] Among them, l i (t) represents the fluorescein concentration of firefly i at the tth iteration, l i (t+1) represents the concentration of fluorescein of firefly i at the t+1th iteration, ρ is the volatility coefficient of fluorescein, γ is the fitness extraction ratio, and x i (t+1) represents the updated position of firefly i in the t+1th iteration; J(x i (t+1)) represents the fitness value of firefly i in the t+1th iteration, that is, the objective function value.

[0056] Step 3: Movement probability calculation phase

[0057] Each firefly needs to decide its movement direction according to the concentration of fluorescein of all neighboring fireflies within its decision radius. The catalyst of reaction rate is affected by all environments and also depends on the temperature in the reaction environment. ij It represents the probability that the i-th firefly moves to the j-th neighbor firefly at time t (iteration number), and the calculation formula is as follows:

[0058]

[0059] Where j∈N i (t), N i (t) = {j:||x j (t)-x i (t)||<r di (t); l i (t)<l j (t)} is the set of all neighboring fireflies of the i-th firefly individual in the t-th iteration, r di (t) represents the dynamic decision domain of firefly i in the tth iteration, ||x(t)|| represents the norm of x, l j(t) represents the concentration of fluorescein in the t-th iteration of firefly j, which corresponds to the influence of the firefly position movement information on the concentration of fluorescein, that is, the reaction rate is affected by the ambient temperature; x i (t), x j (t) represent the updated positions of firefly i and firefly j at the tth iteration respectively.

[0060] Step 4: Select the maximum movement probability and update the position: The i-th firefly moves a certain step length towards the firefly j with the largest fluorescence within its decision radius. Then the movement formula at time t+1 is as follows:

[0061]

[0062] Among them, s is the step size, x i (t+1) is the updated position of firefly i at the t+1th iteration.

[0063] Step 5: Each firefly uses an adaptive dynamic decision radius. The decision radius depends on the density of neighboring fireflies. The reaction rate is affected by the external environment light. In each iteration, the decision radius is changed according to the density of neighboring fireflies, that is, the dimming light is adjusted in real time according to the impact of the environment on the reaction rate, thereby changing the external environment light intensity. When the neighbor density is smaller, it increases the decision radius to find more neighbors. Conversely, when the neighbor density is smaller, the decision radius is reduced; that is, when the external environment brightness is smaller, the external light intensity is increased; when the external environment brightness is larger, the external environment light intensity is reduced. Specifically, the adjustment is made according to formula (4):

[0064] r di (t+1)=min{r s ,max{0,r di (t)+β(n t -|N i (t)|)}} (4)

[0065] Among them, β represents the domain change rate, n t represents the neighbor threshold, controlling the number of firefly neighbors, r s represents the firefly sensing range, r di (t) represents the dynamic decision range of firefly i at the tth iteration, and 0≤r di (t)≤r s .

[0066] Step 6: Check whether the maximum number of iterations or the required accuracy has been reached. If so, go to the next step; otherwise, go to step 4.

[0067] Step 7: Output the optimal individual value, that is, output the fastest global reaction rate.

[0068] The above embodiments are only for illustrating the technical concept and features of the present invention, and their purpose is to enable people familiar with the technology to understand the content of the present invention and implement it accordingly, and they cannot be used to limit the protection scope of the present invention. Any equivalent transformation or modification made according to the spirit of the present invention should be included in the protection scope of the present invention.

Claims

1. An intelligent nitrogen oxide catalytic decomposition system, characterized in that: Including light reactor, sensor module, cloud platform control system, responsive control system; The sensor module includes a temperature sensor, a smoke concentration sensor, and a light sensor, all of which are arranged in the photoreactor to detect environmental parameters such as temperature, smoke concentration, and light intensity in the photoreactor; The responsive control system includes a heater, a methanol controller and a dimming lamp, which are used to adjust the temperature in the reaction furnace, the supply of methanol in the photoreaction furnace and the light intensity in the photoreaction furnace according to the instructions of the cloud platform control system; The cloud platform control system is used to receive environmental parameters from the sensor module, construct a reaction rate objective function, and optimize the objective function by artificial firefly swarm optimization with the maximum reaction rate as the goal, so as to maximize the rate of photocatalytic nitrogen oxide reaction, and determine the optimal temperature, flue gas concentration, light intensity and methanol usage according to the optimization results. The cloud platform control system sends instructions to the responsive control system to adjust the environmental parameters in the reactor.

2. The intelligent nitrogen oxide catalytic decomposition system according to claim 1, characterized in that: When the temperature sensor detects that the temperature inside the photoreactor is lower than the optimal reaction temperature, the heater automatically starts to increase the temperature inside the photoreactor; the dimming lamp adjusts the light intensity in the photoreactor according to the data of the light sensor. When the light intensity is insufficient, the dimming lamp automatically starts to increase the light intensity to ensure that the photocatalytic reaction can proceed fully; when the methanol controller detects that the methanol supply in the photoreactor is lower than the optimal methanol supply, the methanol controller automatically starts to replenish the methanol.

3. The intelligent nitrogen oxide catalytic decomposition system according to claim 1, characterized in that: The objective function is as follows: Where R is the reaction rate, k is a positive proportional constant that depends on the properties of the photocatalyst, T is the temperature in the photoreactor, α is the index of the effect of temperature on the reaction rate, C is the concentration of nitrogen oxides in the flue gas, σ is the index of the effect of concentration on the reaction rate, I is the light intensity, η is the index of the effect of light intensity on the reaction rate, M is the amount of methanol used, δ is the index of the effect of methanol use on the reaction rate. Since methanol is a sacrificial agent, its effect is nonlinear, so M is used. δ To express; the amount of methanol used has a negative effect on the reaction rate because of its nature as a sacrificial agent.

4. The intelligent nitrogen oxide catalytic decomposition system according to claim 3, characterized in that: The artificial firefly swarm optimization algorithm GSO is used to optimize the objective function and dynamically adjust the heater, methanol controller and dimming lamp in the responsive control system. The specific process is as follows: Step 1: Initialization of Firefly; Several fireflies are randomly placed in the feasible domain. In the population, each individual firefly is randomly distributed in the space defined by the objective function. The position information of each individual firefly corresponds to a reaction rate, and the position update of the individual firefly is affected by the fluorescein, movement probability and dynamic decision radius, which correspond to the effects of temperature, methanol usage and light intensity on the reaction rate respectively. In the initial stage, all fireflies have the same fluorescein value and dynamic decision radius, the dynamic decision domain is r0, the initialization step size is s, and the neighborhood threshold is n. t , the fluorescein update factor is γ, the dynamic decision domain update rate is β, and the firefly perception domain is r s , the number of iterations is M; Step 2: Fluorescent Renewal Phase The fluorescein value of each firefly individual is equal to the fluorescein value at the previous moment plus a certain extraction ratio of the current fitness value of the firefly, and then minus a certain ratio of the fluorescein value that evaporates over time, that is, the reaction rate is affected by the current temperature value, as shown in formula (1): l i (t+1)=(1-ρ)l i (t)+γJ(x i (t+1)) (1) Among them, l i (t) represents the fluorescein concentration of firefly i at the tth iteration, l i (t+1) represents the concentration of fluorescein of firefly i at the t+1th iteration, ρ is the volatility coefficient of fluorescein, γ is the fitness extraction ratio, and x i (t+1) represents the updated position of firefly i in the t+1th iteration; J(x i (t+1)) represents the fitness value of firefly i in the t+1th iteration, that is, the objective function value. Step 3: Move probability calculation phase Each firefly needs to decide the direction of movement according to the concentration of fluorescein of all neighboring fireflies within the decision radius. The catalyst of the reaction rate is affected by all environments and also depends on the temperature in the reaction environment. ij It represents the probability that firefly i moves to its neighbor firefly j at the tth iteration. The calculation formula is as follows: Where j∈N i (t), N i (t) = {j:||x j (t)-x i (t)||<r di (t); l i (t)<l j (t)} is the set of all neighboring fireflies of the i-th firefly individual in the t-th iteration, r di (t) represents the dynamic decision domain of firefly i in the tth iteration, ||x(t)|| represents the norm of x, l j (t) represents the concentration of fluorescein in the t-th iteration of firefly j, which corresponds to the influence of the firefly position movement information on the concentration of fluorescein, that is, the reaction rate is affected by the ambient temperature; x i (t), x j (t) represents the updated positions of firefly i and firefly j at the tth iteration respectively; Step 4: Select the maximum movement probability and update the position: Firefly i moves a certain step length towards the firefly j with the largest fluorescence within its decision radius. Then the movement formula at the t+1 iteration is as follows: Among them, s is the step size, x i (t+1) is the updated position of firefly i at the t+1th iteration. Step 5: Each firefly adopts an adaptive dynamic decision radius. The decision radius depends on the density of neighboring fireflies. The reaction rate is affected by the external environment light. In each iteration, the decision radius is changed according to the density of neighboring fireflies, that is, the dimming light is adjusted in real time according to the impact of the environment on the reaction rate, thereby changing the external environment light intensity. When the neighbor density is smaller, the decision radius is increased to find more neighbors. Conversely, when the neighbor density is smaller, the decision radius is reduced. The specific adjustment is made according to formula (4): r di (t+1)=min{r s ,max{0,r di (t)+β(n t -|N i (t)|)}} (4) Among them, β represents the domain change rate, n t represents the neighbor threshold, controlling the number of firefly neighbors, r s represents the firefly sensing range, r di (t) represents the dynamic decision range of firefly i at the tth iteration, and 0≤r di (t)≤r s ; Step 6: Determine whether the maximum number of iterations or the required accuracy has been reached. If so, go to the next step; otherwise, go to step 4. Step 7: Output the optimal individual value, that is, output the fastest global reaction rate.

5. The intelligent nitrogen oxide catalytic decomposition system according to claim 1, characterized in that: The cloud platform control system also includes a remote monitoring and early warning module for remote monitoring and early warning to ensure the safety and stability of the reaction process.

Images