Laboratory temperature and humidity intelligent monitoring and adjusting method based on artificial intelligence

Abstract

The invention belongs to the technical field of laboratory environment control, and particularly relates to a laboratory temperature and humidity intelligent monitoring and adjusting method based on artificial intelligence. The method comprises the following steps: firstly, establishing laboratory temperature and humidity PID control, and designing a temperature and humidity PID controller; then, an objective function is constructed, indexes such as overshoot and rise time are integrated and normalized, and temperature and humidity adjusting performance is optimized by adjusting a weight coefficient; secondly, optimizing proportion, integral and differential coefficients of a PID controller through the steps of parameter setting, population initialization and the like by applying an improved starfish optimization algorithm SFOA; and finally performing simulation to obtain a response curve. Compared with a traditional PID control technology, the temperature and humidity can be adjusted more efficiently and accurately, and the stability of an experimental environment and the reliability of an experimental result are effectively improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of laboratory environment control, and in particular relates to an artificial intelligence-based intelligent monitoring and adjustment method for laboratory temperature and humidity. Background Art

[0002] In a laboratory environment, temperature and humidity are key factors that affect the accuracy of experimental results and the stability of experimental equipment. Existing laboratory temperature and humidity control methods mostly use simple PID control technology. However, traditional PID control has many limitations. On the one hand, its parameters are usually set based on experience, which is difficult to adapt to the complex and changeable laboratory environment, resulting in low temperature and humidity adjustment accuracy, large overshoot, and long adjustment time. Traditional PID control cannot quickly and accurately adjust the temperature back to the set value. On the other hand, traditional PID control lacks adaptability and cannot adjust the control strategy in real time according to environmental changes. Summary of the invention

[0003] In view of the technical problems existing in the above-mentioned background technology, the present invention proposes an intelligent monitoring and adjustment method for laboratory temperature and humidity based on artificial intelligence.

[0004] In order to achieve the above object, the technical solution adopted by the present invention comprises the following steps:

[0005] S1. First, establish a laboratory temperature and humidity PID control system and design two PID controllers for temperature and humidity respectively;

[0006] S2. Construct the objective function to achieve the ideal temperature and humidity adjustment state and minimize the error and adjustment time: J = ω 1 Overshoot+ω 2 ·RiseTime+ω 3 Steady-StateError+ω 4 ·SettingTime, where J is the overall performance index, i.e., the objective function value. The smaller the value, the better the performance. 1 ,ω 2 ,ω 3 ,ω 4 is the weight coefficient, which is used to balance the importance of each performance indicator. Overshoot is the overshoot, RiseTime is the rise time, Steady-StateError is the steady-state error, and SettingTime is the adjustment time.

[0007] S3. Use the improved starfish optimization algorithm SFOA to optimize the proportional coefficient K of the PID controller p , integral coefficient K i and the differential coefficient K d ;

[0008] S4, finally based on the optimized K p , K i and K d The response curve is obtained by simulation.

[0009] Preferably, in step S2, for each indicator in the objective function:

[0010] Among them, Overshoot is the maximum deviation percentage of the output exceeding the target value in the dynamic response of the system: where y max ,y target are the maximum value and target value of the output respectively;

[0011] RiseTime is the rise time, which is the time required for the response to reach 10%-90% of the steady-state value: RiseTime = t 90％ -t 10％ ;

[0012] Among them, Steady-StateError is the steady-state error, which is the deviation between the output value and the target value after stabilization: Steady-StateError = y steady -y target , where y steady Indicates the output value in steady state;

[0013] Among them, SettingTime is the adjustment time, which is the time required for the output to stabilize within the 2% error range of the target value;

[0014] Finally, the different performance indicators of the objective function are normalized.

[0015] Preferably, the specific implementation steps of improving the starfish optimization algorithm in step S3 are:

[0016] S31, first set the parameters and set the maximum number of iterations T max , population size N, variable range is [X min ,X max ];

[0017] S32, initialize the population, each individual is: X i =X min +(X max -X min )·rand();

[0018] S33, calculate the initial fitness and set the inverse of the objective function is the initial fitness, and evaluates the fitness value F(X i), record the initial global optimal solution and its fitness value;

[0019] S34, improve the behavior mechanism to carry out centralization, random diffusion and regeneration behavior;

[0020] S35, updating the position of the starfish, each individual updates the position based on the behavior mechanism, and performs boundary processing if the new position exceeds the range;

[0021] S36, evaluating the fitness value of each new position, and if the fitness value of the new solution is greater than the current global optimal solution, updating the global optimal solution and its fitness value;

[0022] S37, when the maximum number of iterations T is reached max After the iteration ends, the individual position is assigned to K p , K i and K d .

[0023] Preferably, the specific implementation of the centralization behavior in the improved behavior mechanism in step S34 is as follows: first, the population center position C is calculated: Perform a local search around the center position C and improve the update formula: in, is the dynamic step size, which decreases with the number of iterations, γ is the local disturbance intensity, and R is the random vector; finally, the center position weight is dynamically adjusted according to the fitness distribution of the current population: where λ i For individual X i The weight of .

[0024] As a preference, the specific implementation of the random diffusion behavior in the improved behavior mechanism in step S34 is to solve the global optimal solution X best Introduce random diffusion nearby to enhance the global search ability of the population: in The diffusion strength decreases with the number of iterations.

[0025] Preferably, the specific implementation of the regeneration behavior in the improved behavior mechanism in step S34 is to randomly generate new individuals in the variable range area according to the diversity requirements of the population:

[0026] Preferably, the position in step S35 is updated as follows: Among them, ω c ,ω d ,ω r It is to adjust the contribution ratio of the behavioral mechanism according to different stages.

[0027] Preferably, the boundary processing operation in step S35 is to execute when the updated position of the individual exceeds the maximum boundary. Execute when the individual's updated position exceeds the minimum boundary

[0028] Compared with the prior art, the advantages and positive effects of the present invention are that, in view of the shortcomings of traditional PID control, it constructs a laboratory temperature and humidity PID control system to lay the foundation for precise control. The constructed objective function integrates multiple indicators such as overshoot, combined with adjustable weight coefficients and normalization processing. The improved starfish optimization algorithm SFOA improves the search ability through innovative centralization, random diffusion and regeneration behavior, and adaptively optimizes the PID controller parameters. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0030] Figure 1 It is the laboratory temperature response curve; Figure 2 This is the laboratory humidity response curve. DETAILED DESCRIPTION

[0031] In order to more clearly understand the above-mentioned purpose, features and advantages of the present invention, the present invention is further described below in conjunction with the accompanying drawings and embodiments. It should be noted that the embodiments of the present application and the features in the embodiments can be combined with each other without conflict.

[0032] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways than those described herein. Therefore, the present invention is not limited to the specific embodiments of the following disclosure.

[0033] Embodiment, in modern laboratories, accurate temperature and humidity control plays a decisive role in the accuracy of experimental results and the stability of experimental equipment. Traditional PID control technology is difficult to meet the needs of high-precision temperature and humidity control when facing the complex and changeable environment of the laboratory. The present invention is to solve this problem and provide an artificial intelligence-based laboratory temperature and humidity intelligent monitoring and adjustment method to achieve efficient and accurate control of laboratory temperature and humidity.

[0034] First, two PID controllers for temperature and humidity are designed respectively. As the basis for temperature and humidity regulation, these two controllers receive real-time temperature and humidity data collected by sensors, calculate according to the preset target temperature and humidity values, and output corresponding control signals to adjust the operating status of the equipment, thus preliminarily achieving temperature and humidity regulation.

[0035] Next, we construct an objective function, J = ω 1 Overshoot+ω 2 ·RiseTime+ω 3 Steady-StateError+ω 4 ·SettingTime, where J is the overall performance index, i.e., the objective function value. The smaller the value, the better the performance. 1 ,ω 2 ,ω 3 ,ω 4 is the weight coefficient used to balance the importance of each performance indicator, Overshoot is the overshoot, RiseTime is the rise time, Steady-StateError is the steady-state error, and SettingTime is the adjustment time; where Overshoot is the overshoot, which is the maximum deviation percentage of the output exceeding the target value in the dynamic response of the system: where y max ,y target are the maximum value and target value of the output respectively; RiseTime is the rise time, which is the time required for the response to reach 10%-90% of the steady-state value: RiseTime = t 90％ -t 10％ ; Where Steady-StateError is the steady-state error, which is the deviation between the output value and the target value after stabilization: Steady-StateError = y steady -y target , where y steady Represents the output value in steady state; among them, SettingTime is the adjustment time, which is the time required for the output to stabilize within the 2% error range of the target value; finally, the different performance indicators of the objective function are normalized. This objective function comprehensively considers multiple key indicators, including overshoot, rise time, steady-state error and adjustment time, and comprehensively reflects the temperature and humidity regulation performance. A small steady-state error can ensure the stability of the experimental environment and is conducive to the accuracy of the experimental data. Secondly, the setting of the weight coefficient is very flexible. Users can adjust the weight according to the emphasis of different experiments on temperature and humidity control to make the control more practical. Finally, the different performance indicators are normalized to unify the dimensions and scales of each indicator, making the optimization process more scientific and accurate, and avoiding optimization deviations caused by dimensional differences between indicators.

[0036] Then the present invention improves the starfish optimization algorithm SFOA. In terms of search mechanism, SFOA improves the centralized behavior, introduces dynamic step size and local disturbance intensity, and dynamically adjusts according to the number of iterations, thereby enhancing the local search capability and finding a better solution faster. Secondly, its random diffusion behavior improves the global search performance and reduces the risk of falling into local optimality through a unique formula combined with the characteristic that the diffusion intensity decreases with the number of iterations. Furthermore, the added regeneration behavior can randomly generate new individuals within the variable range, effectively maintaining population diversity and avoiding premature convergence of the algorithm. Finally, for the calculation of individual update positions and boundary processing, SFOA considers the contribution ratio of the behavior mechanisms at different stages to ensure that the update process is more scientific and reasonable. The improved starfish optimization algorithm SFOA is used to optimize the proportional coefficient K of the PID controller p , integral coefficient K i and the differential coefficient K d , first set the parameters and set the maximum number of iterations T max , population size N, variable range is [X min ,X max ]; initialize the population, each individual is: X i =X min +(X max -X min )·rand(); calculate the initial fitness and set the inverse of the objective function is the initial fitness, and evaluates the fitness value F(X i ), record the initial global optimal solution and its fitness value; improve the behavior mechanism, perform centralization, random diffusion and regeneration behaviors; the specific implementation of the centralization behavior is: first calculate the population center position C: Perform a local search around the center position C and improve the update formula: in, is the dynamic step size, which decreases with the number of iterations, γ is the local disturbance intensity, and R is the random vector; finally, the center position weight is dynamically adjusted according to the fitness distribution of the current population: where λ i For individual X i The specific implementation of random diffusion behavior is in the global optimal solution X best Introduce random diffusion nearby to enhance the global search ability of the population: in The diffusion intensity decreases with the number of iterations. The specific implementation of the regeneration behavior is to randomly generate new individuals in the variable range area in response to the diversity requirements of the population: Then update the position of the starfish, and each individual updates its position based on the behavior mechanism Among them, ω c ,ω d ,ωr It is to adjust the contribution ratio of the behavioral mechanism according to different stages. d >ω c >ω r Strengthen global exploration, late ω c >ω d >ω r Emphasize local development and optimal solution refinement. If the new position exceeds the range, boundary processing is performed. When the position of the individual update exceeds the maximum boundary, it is executed. Execute when the individual's updated position exceeds the minimum boundary Then evaluate the fitness value of each new position. If the fitness value of the new solution is greater than the current global optimal solution, update the global optimal solution and its fitness value. Finally, when the maximum number of iterations T is reached, max After the iteration ends, the individual position is assigned to K p , K i and K d .

[0037] Finally, simulation is performed based on the above optimization results to obtain the response curves of laboratory temperature and humidity, as shown in Figure 1 and Figure 2 By analyzing the response curve, the effect of temperature and humidity adjustment can be intuitively evaluated, achieving high-precision, fast-response, highly adaptive and reliable temperature and humidity control, providing strong support for the stability of the laboratory environment and the accuracy of the experimental results.

[0038] The above description is only a preferred embodiment of the present invention and does not limit the present invention in other forms. 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 still falls within the protection scope of the technical solution of the present invention.

Claims

1. An artificial intelligence-based intelligent monitoring and adjustment method for laboratory temperature and humidity, characterized in that: The following steps are involved: S1. First, establish the laboratory temperature and humidity PID control and design two PID controllers for temperature and humidity respectively; S2. Construct an objective function to achieve an ideal temperature and humidity adjustment state and minimize the error and adjustment time: J = ω1·Overshoot+ω2·RiseTime+ω3·Steady-StateError+ω4·SettingTime, where J is the overall performance index, i.e., the objective function value. The smaller the value, the better the performance. ω1, ω2, ω3, and ω4 are weight coefficients used to balance the importance of each performance index. Overshoot is the overshoot, RiseTime is the rise time, Steady-StateError is the steady-state error, and SettingTime is the adjustment time. S3. Use the improved starfish optimization algorithm SFOA to optimize the proportional coefficient K of the PID controller p , integral coefficient K i and the differential coefficient K d ; S4, finally based on the optimized K p , K i and K d The response curve is obtained by simulation.

2. According to claim 1, a method for intelligent monitoring and adjustment of laboratory temperature and humidity based on artificial intelligence is characterized in that: In step S2, for each indicator in the objective function: Among them, Overshoot is the maximum deviation percentage of the output exceeding the target value in the dynamic response of the system: where y max ,y target are the maximum value and target value of the output respectively; RiseTime is the rise time, which is the time required for the response to reach 10%-90% of the steady-state value: RiseTime = t 90％ -t 10％ ; Among them, Steady-StateError is the steady-state error, which is the deviation between the output value and the target value after stabilization: Steady-StateError=|y steady -y target |, where y steady Represents the output value in steady state; Among them, SettingTime is the adjustment time, which is the time required for the output to stabilize within the 2% error range of the target value; Finally, the different performance indicators of the objective function are normalized.

3. According to the method of intelligent monitoring and adjustment of laboratory temperature and humidity based on artificial intelligence in claim 1, it is characterized in that: The specific implementation steps of improving the starfish optimization algorithm in step S3 are: S31, first set the parameters and set the maximum number of iterations T max , population size N, variable range is [X min ,X max ]; S32, initialize the population, each individual is: X i =X min +(X max -X min )·rand(); S33, calculate the initial fitness and set the inverse of the objective function is the initial fitness, and evaluates the fitness value F(X i ), record the initial global optimal solution and its fitness value; S34, improve the behavior mechanism to carry out centralization, random diffusion and regeneration behavior; S35, updating the position of the starfish, each individual updates the position based on the behavior mechanism, and performs boundary processing if the new position exceeds the range; S36, evaluating the fitness value of each new position, and if the fitness value of the new solution is greater than the current global optimal solution, updating the global optimal solution and its fitness value; S37, when the maximum number of iterations T is reached max After the iteration ends, the individual position is assigned to K p , K i and K d .

4. The method for intelligent monitoring and regulating temperature and humidity in a laboratory based on artificial intelligence according to claim 3 is characterized in that: The specific implementation of the centralization behavior in the improved behavior mechanism in step S34 is as follows: first, the population center position C is calculated: Perform a local search around the center position C and improve the update formula: in, is the dynamic step size, which decreases with the number of iterations, γ is the local disturbance intensity, and R is the random vector; finally, the center position weight is dynamically adjusted according to the fitness distribution of the current population: where λ i For individual X i The weight of .

5. The method for intelligent monitoring and regulating laboratory temperature and humidity based on artificial intelligence according to claim 3 is characterized in that: The specific implementation of the random diffusion behavior in the improved behavior mechanism in step S34 is to solve the global optimal solution X best Introduce random diffusion nearby to enhance the global search ability of the population: in The diffusion strength decreases with the number of iterations.

6. The method for intelligent monitoring and regulating laboratory temperature and humidity based on artificial intelligence according to claim 3 is characterized in that: The specific implementation of the regeneration behavior in the improved behavior mechanism in step S34 is to randomly generate new individuals in the variable range area in response to the diversity requirements of the population:

7. The method for intelligent monitoring and regulating laboratory temperature and humidity based on artificial intelligence according to claim 3 is characterized in that: The position in step S35 is updated as follows: Among them, ω c ,ω d ,ω r It is to adjust the contribution ratio of the behavioral mechanism according to different stages.

8. The method for intelligent monitoring and regulating laboratory temperature and humidity based on artificial intelligence according to claim 3 is characterized in that: The boundary processing operation in step S35 is to execute when the updated position of the individual exceeds the maximum boundary. Execute when the individual's updated position exceeds the minimum boundary

Images