Coal injection Roots blower control method based on improved cheongfish optimization algorithm

Abstract

The invention discloses a coal injection Roots blower control method based on an improved cheongfish optimization algorithm, and belongs to the technical field of PID control, and the method specifically comprises the steps: 1, building a Roots blower control model based on a PID controller; step 2, improving a cheongfish optimization algorithm; and step 3, optimizing and solving the parameters of the PID controller by using the improved cheongfish optimization algorithm. Experiments show that the improved algorithm is faster in optimization, the control precision of PID control is higher, and the robustness is stronger.

Description

Technical Field

[0001] This invention belongs to the field of PID control optimization technology, and in particular relates to a control method for a pulverized coal Roots blower based on an improved flagfish optimization algorithm. Background Technology

[0002] Precise temperature control is crucial during the calcination process in lime kilns. Too low a temperature leads to incomplete reactions, reducing yield; too high a temperature causes product deactivation, failing to meet required chemical properties, also resulting in reduced production. Therefore, the stability and rapid response of the Roots blower, a key piece of equipment for pulverized coal fuel transportation, are paramount, directly impacting the final output of the lime kiln.

[0003] Against this backdrop, the Roots blower control system was developed to meet the demand. This system employs advanced control algorithms to monitor the kiln status in real time and dynamically adjust the airflow of the Roots blower, achieving precise control of the kiln temperature. Utilizing PID control technology, the system can automatically optimize the airflow based on the real-time temperature and production status inside the kiln, thereby stabilizing the kiln temperature within the optimal range. This ensures the efficient operation of the lime kiln and guarantees high yield and excellent physicochemical properties of the final product, lime.

[0004] PID control technology (comprising proportional (P), integral (I), and derivative (D) components) is a core control method widely used in industrial automation. Its principle lies in the fact that the proportional component rapidly responds to system deviations, the integral component eliminates accumulated errors, and the derivative component predicts the trend of deviation changes; the three work together to achieve precise control. However, during the operation of a lime kiln, fluctuations in raw material composition, changes in ambient temperature, and other external disturbances place higher demands on the performance of the control system. Traditional PID control relies on fixed P, I, and D parameters, which are difficult to adapt flexibly to such complex and variable calcination conditions, often resulting in decreased control accuracy and insufficient response speed. Therefore, there is an urgent need to develop more intelligent and adaptable PID control methods to meet the stringent requirements of high response speed and high stability under different operating conditions.

[0005] The Sailfish Optimizer (SFO) is a novel metaheuristic algorithm inspired by the group hunting behavior of marine organisms. This algorithm simulates the cooperative predation of sardines by sailfish, dividing the population into two groups: sailfish (predators) and sardines (prey). During the development phase, the sailfish group refines its search around the current optimal solution, guiding the group towards high-potential areas through an alternating attack strategy. The sardine group, on the other hand, enhances the diversity of the search space through random escape behavior, preventing the algorithm from getting trapped in local optima. During position updates, sailfish adjust their movement direction based on the positions of elite individuals and injured sardines, while sardines dynamically update their positions based on an attack intensity parameter: when the attack intensity is high, sardines undergo large-scale random displacement to explore new areas; when the attack intensity is low, only some sardines make local adjustments. The algorithm adaptively balances global exploration and local development by capturing better-fit sardines to replace weaker sailfish and gradually reducing the number of prey. It excels in convergence speed, ability to escape local optima, and performance in high-dimensional optimization problems, making it particularly suitable for complex and constrained engineering problems. Summary of the Invention

[0006] The purpose of this invention is to propose a control method for a pulverized coal injection Roots blower in a lime kiln based on an improved sailfish optimization algorithm. This method enables the Roots blower control system to precisely regulate the temperature inside the kiln, and is particularly suitable for variable operating conditions such as raw material composition, ambient temperature, and external disturbances during calcination. This scheme solves the problems of premature convergence, high parameter sensitivity, and insufficient global search capability of the traditional sailfish optimization algorithm, significantly improving the system's response speed and control accuracy, and enhancing the stability and anti-interference capability of the calcination process.

[0007] To achieve the above objectives, the present invention adopts the following technical solution: A control method for a pulverized coal roots blower in a lime kiln based on an improved flagfish optimization algorithm is proposed. This method utilizes the improved flagfish optimization algorithm to quickly find optimal PID control parameters for the pulverized coal roots blower, thereby improving the reliability, stability, response speed, and control accuracy of the pulverized coal roots blower during operation. The specific steps are as follows.

[0008] S1: Establish a control model for a pulverized coal injection Roots blower based on a PID controller; S2: Improved sailfish optimization algorithm; S3: Optimize and adjust the parameters of the PID controller using the improved sailfish optimization algorithm, and iterate to obtain the optimal three control parameters Kp, Ki, and Kd; Furthermore, the pulverized coal Roots blower model of the PID controller in step S1 mainly includes the following functional modules: temperature difference calculation module, improved flagfish optimization algorithm module, pulverized coal control module, motor drive module, and temperature measurement module. The temperature difference calculation module is used to calculate the deviation between the target temperature and the actual temperature inside the kiln in real time, which serves as the input basis for the PID controller. The improved sailfish optimization algorithm module is used to intelligently optimize the proportional parameter (Kp), integral parameter (Ki), and derivative parameter (Kd) of the PID controller, and output the optimal control parameters to the motor drive module to improve the system regulation performance. The motor drive module controls the motor speed according to the optimized PID control parameters and drives the Roots blower to run; The pulverized coal control module dynamically calculates the air-coal ratio based on the current kiln temperature, the air intake volume and air pressure of the Roots blower, thereby achieving closed-loop control of the pulverized coal injection volume. The temperature measurement module is used to monitor the real-time temperature inside the kiln during the calcination process and input it as a feedback signal to the temperature difference calculation module, thereby forming a closed-loop control.

[0009] Furthermore, the improvements to the sailfish optimization algorithm mentioned in step S2 consist of four points, as detailed below: The first step involves updating the position of individual sailfish within a school using both pressure-based and gradual-based capture strategies. For each sailfish, the update consists of two scenarios, as shown in the following formula:

[0010] In the formula, This represents the optimal individual sailfish, indicating the currently optimal parameters. This indicates the step length that each sailfish moves. This represents the optimal individual sardine, which, together with the optimal individual marlin, guides the optimization direction. Indicates the first The current location of the sailfish. Indicates reference indicators for selecting different movement strategies for the sailfish; In the second process of updating the sardine school's location, a startled escape mechanism is introduced to update the sardines' positions. The updating process follows two strategies, with the relevant formulas as follows:

[0011] In the formula, Indicates the first The location of only sardines This indicates the location of the sailfish closest to the school of sardines. This indicates the first sardine randomly selected from the sardine swarm. Only sardines Position in direction This indicates the attack power of the sailfish. This represents a set of sardines randomly selected from a school of sardines. Indicates the first in the sardine school A sardine, Represents from set The set of directions randomly chosen by sardines in a container; The third aspect involves introducing a fin wave disturbance mechanism during the sailfish's movement to a new location. This mechanism represents the movement deviation of other sailfish caused by the water wave disturbance during the sailfish's movement. The formula followed in this process is as follows:

[0012] In the formula, Indicates the first The current location of the sailfish In addition to The water disturbance caused by the movement of other sailfish is weakened in the water during propagation. Size after level This indicates the water disturbance caused by the movement of other sailfish. The intensity of the impact of a single sailfish; The fourth point involves introducing a targeted pursuit enhancement mechanism during the sailfish's attack on the sardines from its newest position. This means that the sailfish will choose the direction from which it is most likely to attack the sardines to achieve the best hunting effect. The formula is as follows:

[0013] In the formula Indicates the first The fitness gradient of the sailfish decreases in each direction at its current position. Represents the small value in each direction. Represents the unit vector in each direction. This indicates that if the sailfish follows the currently indicated direction and returns to its new location, This represents the maximum value of the sailfish in each dimension, and... The minimum value of the sailfish in each dimension collectively limits the sailfish's attack position. The judgment indicates that if the fitness of the new location reached after launching an attack is better than the fitness of the old location before launching the attack, This indicates that if the sailfish has an aggressive tendency... If the conditions for an attack are met, the sailfish will launch an attack and move.

[0014] Furthermore, in step S22, the value of ISFO_jump is determined by the following formula:

[0015] This is a standardized factor derived to conform to the characteristics of the Levy distribution. The distribution index of Levy, In order to comply with the relevant The set of vectors that are normally distributed. It is a set of vectors that conform to a standard normal distribution.

[0016] Furthermore, in step S24, The value is calculated using the following formula:

[0017] In the formula, This indicates the sailfish's aggressive nature. Indicates the current iteration round. The formula represents the total number of iterations. As the number of iterations increases, the attack desire of the sailfish increases, and the local exploitation capability of the algorithm is enhanced.

[0018] Furthermore, the control method for the pulverized coal Roots blower based on the improved flagfish optimization algorithm described in step S3 includes the following specific steps: S31: Randomly initialize the swordfish and sardine populations, ensuring that all individuals are randomly distributed within a possible parameter range. The formula is as follows:

[0019] and These indicate the positions of the sailfish and sardines, respectively. , This represents the minimum and maximum values ​​in each direction. Represents a random value randomly distributed within [0, 1]; S32: Select a suitable fitness function and calculate the fitness, the formula is as follows:

[0020] In the formula, Representing the Individuals Position in the direction; S33: Select the one with the lowest fitness. and As a guide for optimization, the formula is as follows:

[0021] This represents the optimal individual sailfish. This represents the best individual sardine. and These represent the fitness sets of sailfish and sardines, respectively. S34: Move the sailfish and sardines. The sailfish movement strategy is as described in S21, and the sardine movement strategy is as described in S22. S35: The sailfish launches an attack, and the sailfish attack strategy is as described in step S24; S36: Replace the predatory sardines with swordfish, as shown in the formula below:

[0022] This represents the fitness level of the sardines that are about to be preyed upon. The fitness level represents the sailfish about to launch an attack. and These represent using the location of the preyed sardine to update the location of the sailfish that preyed on it. This indicates the removal of preyed sardines; S37: Determine whether the iteration termination condition has been met. If the maximum number of iterations has been reached or no better solution has been updated for a long time, then end the iteration; otherwise, continue the calculation from S32.

[0023] In summary, due to the adoption of the above technical solution, the beneficial effects of the present invention are as follows: Compared with existing technologies, the pulverized coal Roots blower control method based on the improved sailfish optimization algorithm provided by this invention, on the basis of the traditional sailfish optimization algorithm, utilizes two different strategies, pressure encirclement and gradual encirclement, to enable the algorithm to dynamically balance between global search and local exploitation; it adopts a fin wave perturbation mechanism to enhance the algorithm's ability to escape local optima; and it uses a directional pursuit enhancement mechanism to accelerate the convergence speed of the algorithm. The comprehensive application of these strategies enables the algorithm to find the global optimum more efficiently, which not only accelerates the optimization efficiency of the global optimum but also improves the system's adjustment accuracy and response speed, significantly enhancing the system's stability and reliability in complex environments. It provides a more sensitive and reliable control strategy for pulverized coal Roots blower systems, significantly improving the system's robustness and adaptability.

[0024] In contrast, while traditional PID control methods and basic sailfish optimization algorithms possess certain fundamental performance characteristics, they still suffer from drawbacks in practical applications, such as slow convergence speed, susceptibility to local optima, and limited optimization accuracy, especially under complex environmental conditions. The pulverized coal injection Roots blower control method proposed in this invention, based on an improved sailfish optimization algorithm, effectively overcomes these shortcomings by introducing a dynamic adjustment mechanism and optimization strategy, significantly improving control performance and adaptability. Attached Figure Description

[0025] Figure 1 This is a flowchart of a pulverized coal injection Roots blower control method based on an improved flagfish optimization algorithm.

[0026] Figure 2 This is a model diagram of the PID controller for the pulverized coal Roots blower control system.

[0027] Figure 3 This is a block diagram of a pulverized coal injection Roots blower system.

[0028] Figure 4 A comparison chart showing the optimization of the proportional gain Kp of the PID in the improved sailfish optimization algorithm and the basic sailfish optimization algorithm.

[0029] Figure 5 A comparison chart showing the optimization of the integral gain Ki of PID using the improved sailfish optimization algorithm and the basic sailfish optimization algorithm.

[0030] Figure 6 A comparison chart showing the optimization of the differential gain Kd of PID using the improved sailfish optimization algorithm and the basic sailfish optimization algorithm.

[0031] Figure 7 A comparison chart showing the changes in fitness values ​​during the optimization process of the improved sailfish optimization algorithm and the basic sailfish optimization algorithm.

[0032] Figure 8 A comparison of the control effects of the improved sailfish optimization algorithm and the basic sailfish optimization algorithm for PID control. Detailed Implementation

[0033] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. It should be noted that the following embodiments are only some embodiments of the present invention, not all of them, and are only used to more clearly illustrate the technical solutions of the present invention. However, the implementation of the present invention is not limited thereto. Therefore, based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0034] Please refer to Figures 1 to 8 The present invention provides a technical solution: A control method for the pulverized coal injection Roots blower in a lime kiln based on an improved sailfish optimization algorithm is proposed. This method enables the Roots blower control system to precisely regulate the kiln temperature, making it particularly suitable for variable operating conditions such as raw material composition, ambient temperature, and external disturbances during calcination. This scheme solves the problems of premature convergence, high parameter sensitivity, and insufficient global search capability of the traditional sailfish optimization algorithm, significantly improving the system's response speed and control accuracy, and enhancing the stability and anti-interference ability of the calcination process. The specific steps are as follows: S1: As shown in Figure 3, establish a control model for the pulverized coal injection Roots blower based on a PID controller; S2: Improved sailfish optimization algorithm; S3: Optimize and adjust the parameters of the PID controller using the improved sailfish optimization algorithm, and iterate to obtain the optimal three control parameters Kp, Ki, and Kd; Optionally, the method further includes: S4: Simulate the PID controller-based pulverized coal injection Roots blower control model, apply the optimized control parameters to the PID controller-based pulverized coal injection Roots blower control model, verify the response effect of the obtained control parameters in the control process of the Roots blower, and ensure the effectiveness of the control parameter improvement.

[0035] The pulverized coal Roots blower model of the PID controller in step S1 mainly includes the following functional modules: temperature difference calculation module, improved flagfish optimization algorithm module, motor drive module, pulverized coal control module, and temperature measurement module. The temperature difference calculation module is used to calculate the deviation between the target temperature and the actual temperature inside the kiln in real time, which serves as the input basis for the PID controller. The improved sailfish optimization algorithm module is used to intelligently optimize the proportional parameter (Kp), integral parameter (Ki), and derivative parameter (Kd) of the PID controller, and output the optimal control parameters to the motor drive module to improve the system regulation performance. The motor drive module controls the motor speed according to the optimized PID control parameters and drives the Roots blower to run; The pulverized coal control module dynamically calculates the air-coal ratio based on the current kiln temperature, the air intake volume and air pressure of the Roots blower, thereby achieving closed-loop control of the pulverized coal injection volume. The temperature measurement module is used to monitor the real-time temperature inside the kiln during the calcination process and input it as a feedback signal to the temperature difference calculation module, thereby forming a closed-loop control.

[0036] Step S2 includes: S21: During the update of the sailfish school location, pressure trapping and gradual trapping strategies are used for location updates; for each sailfish, the update consists of two cases, as shown in the following formula:

[0037] In the formula, This represents the optimal individual sailfish, indicating the currently optimal parameters. This indicates the step length that each sailfish moves. This represents the optimal individual sardine, which, together with the optimal individual marlin, guides the optimization direction. Indicates the first The current location of the sailfish. In this embodiment, the reference index for selecting different movement strategies for the sailfish is... A random function with a uniform distribution in [0, 1] is chosen to achieve the purpose of randomly selecting a movement strategy; S22: During the update of the sardine school's position, a startled escape mechanism is introduced to update the sardines' positions. The update process for the sardines follows two strategies, and the relevant formulas are as follows:

[0038] In the formula, Indicates the first The location of only sardines This indicates the location of the sailfish closest to the school of sardines. This indicates the first sardine randomly selected from the sardine swarm. Only sardines Position in direction This indicates the attack power of the sailfish. This represents a set of sardines randomly selected from a school of sardines. Indicates the first in the sardine school A sardine, Represents from set The set of randomly chosen directions of the sardines; in this embodiment, For the three parameters Kp, Ki, and Kd of the PID controller, r is chosen as a random function uniformly distributed in [0, 1] to achieve the purpose of randomly selecting the movement strategy. The value is determined by the following formula:

[0039] This is a standardized factor derived to conform to the characteristics of the Levy distribution. The distribution index of Levy, in this embodiment, The value is 1.5. In order to comply with the relevant The set of vectors that are normally distributed. It is a set of vectors that conform to a standard normal distribution.

[0040] S23: During the process of the sailfish moving to a newer position, a fin wave disturbance mechanism is introduced. This mechanism represents the movement deviation of other sailfish caused by the water wave disturbance during the sailfish's movement. The formula followed in this process is as follows:

[0041] in, Indicates the first The current location of the sailfish In addition to Other sailfish, besides those swimming, cause water disturbances that iterate in the water during propagation. Size after level This indicates the water disturbance caused by the movement of other sailfish. In this embodiment, the influence intensity of a single sailfish is... The value is 0.1; S24: During the process of the sailfish reaching its latest position and attacking the sardines, a targeted pursuit enhancement mechanism is introduced. This means that during the attack, the sailfish will choose the direction from which it is easiest to attack the sardines to achieve the best hunting effect. The formula is as follows:

[0042] In the formula Indicates the first The fitness gradient of the sailfish decreases in each direction at its current position. Represents the small value in each direction. Represents the unit vector in each direction. This indicates that if the sailfish follows the currently indicated direction and returns to its new location, This represents the maximum value of the sailfish in each dimension, and... The minimum value of the sailfish in each dimension collectively limits the sailfish's attack position. The judgment indicates that if the fitness of the new location reached after launching an attack is better than the fitness of the old location before launching the attack, This indicates that if the sailfish has an aggressive tendency... If the conditions for an attack are met, the sailfish will launch an attack and move.

[0043] Furthermore, as mentioned in step S23 It is calculated using the following formula:

[0044] The chaos parameter represents the magnitude of the disturbance, which is selected as 4 in this embodiment. The final disturbance result is the vector after the above formula has been iterated 4 times.

[0045] Furthermore, in step S24, The value is calculated using the following formula:

[0046] In the formula, This indicates the sailfish's aggressive nature. Indicates the current iteration round. Indicates the total number of iterations. Furthermore, such as Figure 1 The improved sailfish optimization algorithm is used to optimize and adjust the parameters of the PID controller in step S3, as shown in the figure. The specific steps include: S31: Randomly initialize the swordfish and sardine populations, ensuring that all individuals are randomly distributed within a possible parameter range. The formula is as follows:

[0047] In the above formula and These indicate the positions of the sailfish and sardines, respectively. , This represents the minimum and maximum values ​​in each direction. In this embodiment, due to the limitations on the values ​​of the PID parameters, and The values ​​are 0 and 10, and the selection criteria conform to the range of PID parameters. Represents a random value randomly distributed within [0, 1]; S32: Select a suitable fitness function and calculate the fitness, the formula is as follows:

[0048] In the formula, Representing the Individuals In this embodiment, the position relative to the direction is... These are three-dimensional variables representing the parameters of the PID controller. S33: Select the one with the lowest fitness. and As a guide for optimization, the formula is as follows:

[0049] This represents the optimal individual sailfish. This represents the best individual sardine. and These represent the fitness sets of sailfish and sardines, respectively. S34: Move the sailfish and sardines. The sailfish movement strategy is as described in S21, and the sardine movement strategy is as described in step S22. S35: The sailfish launches an attack, as described in step S24 of the sailfish attack strategy; S36: Replace the predatory sardines with swordfish, as shown in the formula below:

[0050] This represents the fitness level of the sardines that are about to be preyed upon. This indicates the fitness level of the sardines removed from the diet. and These represent using the location of the preyed sardine to update the location of the sailfish that preyed on it. This indicates the removal of preyed sardines; S37: Determine whether the iteration termination condition has been met. If the maximum number of iterations has been reached or no better solution has been updated for a long time, then end the iteration; otherwise, continue the calculation from S32.

[0051] Furthermore, as shown in Figure 2, in step S4, MATLAB and Simulink are used to simulate the pulverized coal injection Roots blower control model based on a PID controller. The structure is as follows: a temperature difference calculation module, an improved flagfish optimization algorithm module, a pulverized coal control module, a motor drive module, and a temperature measurement module. The temperature difference calculation module is used to obtain the deviation between the set temperature and the actual detected temperature; this error signal is input to the PID controller module. The proportional parameter (Kp), integral parameter (Ki), and derivative parameter (Kd) in the PID controller are intelligently optimized by the improved flagfish optimization algorithm. The motor drive module controls the Roots blower according to the optimized PID control parameters, adjusting the blower's output air volume and air pressure in real time, and, in conjunction with the pulverized coal control module, regulates the air-coal ratio, ultimately affecting the kiln temperature. The system feeds back the temperature to the temperature difference calculation module through the actual temperature output module, forming a closed-loop regulation.

[0052] Through analysis Figure 4 , Figure 5 and Figure 6 The improved sailfish optimization algorithm and the basic sailfish optimization algorithm shown in the figure demonstrate the performance of the improved sailfish PID control algorithm in optimizing the parameters of the sailfish PID controller. It is easy to see that the improved sailfish optimization algorithm can stabilize near the optimal Kp, Ki, and Kd values ​​in fewer iterations than the basic sailfish optimization algorithm, achieving the optimal control effect of the model. This indicates that the improved sailfish version of the algorithm is faster in optimization and convergence speed, while improving the stability of the system. This makes the improved sailfish optimization algorithm more effective in complex application environments, able to quickly adapt to different conditions and optimize the parameters of the PID controller, significantly improving control accuracy and response performance.

[0053] Fitness values ​​are often used to evaluate the quality of solutions in a population. Generally, the smaller the fitness value of a solution, the higher its quality. Therefore, by analyzing... Figure 7As can be seen from the fitness data of the improved sailfish optimization algorithm and the basic sailfish optimization algorithm, the improved sailfish optimization algorithm has a smaller fitness value and reaches a stable state faster. This indicates that the improved sailfish optimization algorithm can achieve a better convergence state in fewer iterations, thus providing faster and more stable optimization performance. Therefore, compared with the basic version, the improved sailfish optimization algorithm shows a significant advantage in performance.

[0054] from Figure 8 The results show that when the PID parameters obtained by S37 are input into the pulverized coal Roots blower control model based on the PID controller, the improved flagfish optimization algorithm exhibits significantly lower overshoot in the PID control system. Furthermore, the improved algorithm can track responses more quickly and shortens the iteration time required to reach a steady state. This indicates that in complex environments, the improved flagfish optimization algorithm can achieve steady-state control more efficiently, demonstrating superior response speed and control performance, while also possessing stronger robustness. These characteristics make the algorithm perform exceptionally well in the application of pulverized coal Roots blower control systems, effectively improving the system's efficiency, stability, and overall performance.

Claims

1. A control method for a pulverized coal injection Roots blower based on an improved sailfish optimization algorithm, characterized in that, By improving the flagfish optimization algorithm, the three parameters of the PID controller for the Roots blower used to convey pulverized coal, namely Kp, Ki, and Kd, are optimized to improve parameter optimization and response speed, and to ensure the accuracy and robustness of PID control. The specific steps are as follows: S1: Establish a control model for a pulverized coal injection Roots blower based on a PID controller; S2: Improved sailfish optimization algorithm; S3: Optimize and adjust the parameters of the PID controller using the improved sailfish optimization algorithm, and iterate to obtain the optimal three control parameters Kp, Ki, and Kd.

2. The control method for a pulverized coal injection Roots blower based on the improved sailfish optimization algorithm as described in claim 1, characterized in that, The pulverized coal Roots blower model of the PID controller in step S1 mainly includes the following functional modules: temperature difference calculation module, improved flagfish optimization algorithm module, pulverized coal control module, motor drive module, and temperature measurement module; The temperature difference calculation module is used to calculate the deviation between the target temperature and the actual temperature inside the kiln in real time, which serves as the input basis for the PID controller. The improved sailfish optimization algorithm module is used to intelligently optimize the proportional parameter Kp, integral parameter Ki, and derivative parameter Kd of the PID controller, and output the optimal control parameters to the motor drive module to improve the system regulation performance. The motor drive module controls the motor speed according to the optimized PID control parameters and drives the Roots blower to run; The pulverized coal control module dynamically calculates the air-coal ratio based on the current kiln temperature, the air intake volume and air pressure of the Roots blower, thereby achieving closed-loop control of the pulverized coal injection volume. The temperature measurement module is used to monitor the real-time temperature inside the kiln during the calcination process and input it as a feedback signal to the temperature difference calculation module, thereby forming a closed-loop control.

3. The control method for a pulverized coal injection Roots blower based on the improved sailfish optimization algorithm as described in claim 1, characterized in that, Step S2 includes: S21: During the update of the sailfish school location, pressure trapping and gradual trapping strategies are used for location updates; for each sailfish, the update consists of two cases, as shown in the following formula: In the formula, This represents the optimal individual sailfish, indicating the currently optimal parameters. This indicates the step length that each sailfish moves. This represents the optimal individual sardine, which, together with the optimal individual marlin, guides the optimization direction. Indicates the first The current location of the sailfish. Indicates reference indicators for selecting different movement strategies for the sailfish; S22: During the update of sardine school positions, a startled escape mechanism is introduced to update the sardine positions. The update process for sardine positions follows two strategies, and the relevant formulas are as follows: In the formula, Indicates the first The location of the sardines. This indicates the location of the sailfish closest to the school of sardines. This represents the first sardine randomly selected from the sardine swarm. Only sardines Position in direction This indicates the attack power of the sailfish. This represents a set of sardines randomly selected from a school of sardines. Indicates the first in the sardine school A sardine, Represents from set The set of directions randomly chosen by sardines in the water. The random step size vector that follows Levy's flight path.

4. The control method for a pulverized coal injection Roots blower based on the improved sailfish optimization algorithm as described in claim 3, characterized in that, Step S2 also includes: S23: During the process of the sailfish moving to a newer position, a fin wave disturbance mechanism is introduced. This mechanism represents the movement deviation of other sailfish caused by the water wave disturbance during the sailfish's movement. The formula followed in this process is as follows: in, Indicates the first The current location of the sailfish In addition to The water disturbance caused by the movement of other sailfish is weakened in the water during propagation. Size after level This indicates the water disturbance caused by the movement of other sailfish. The intensity of the impact of a single sailfish; S24: During the process of the sailfish reaching its latest position and attacking the sardines, a targeted pursuit enhancement mechanism is introduced. This means that during the attack, the sailfish will choose the direction from which it is easiest to attack the sardines to achieve the best hunting effect. The formula is as follows: In the formula Indicates the first The fitness gradient of the sailfish decreases in each direction at its current position. Represents the small value in each direction. Represents the unit vector in each direction. This indicates that if the sailfish follows the currently indicated direction and returns to its new location, This represents the maximum value of the sailfish in each dimension, and... The minimum value of the sailfish in each dimension collectively limits the sailfish's attack position. The judgment indicates that if the fitness of the new location reached after launching an attack is better than the fitness of the old location before launching the attack, This indicates that if the sailfish has an aggressive tendency... If the conditions for an attack are met, the sailfish will launch an attack and move.

5. The control method for a pulverized coal injection Roots blower based on the improved sailfish optimization algorithm as described in claim 4, characterized in that, In S3, the improved sailfish optimization algorithm is used to optimize and adjust the parameters of the PID controller. The specific steps include: S31: Randomly initialize the swordfish and sardine populations, ensuring that all individuals are randomly distributed within a possible parameter range. The formula is as follows: and These indicate the positions of the sailfish and sardines, respectively. , This represents the minimum and maximum values ​​in each direction. Represents a random value randomly distributed within [0, 1], used to randomly initialize two groups of fish; S32: Select a suitable fitness function and calculate the fitness, the formula is as follows: In the formula, Representing the Individuals The position in the direction.

6. The control method for a pulverized coal injection Roots blower based on the improved sailfish optimization algorithm as described in claim 5, characterized in that, In S3, the improved sailfish optimization algorithm is used to optimize and adjust the parameters of the PID controller. The specific steps also include: S33: Select the one with the lowest fitness. and As a guide for optimization, the formula is as follows: This represents the optimal individual sailfish. Representing the best sardine individual, and These represent the fitness sets of sailfish and sardines, respectively. S34: Sailfish and sardines move, the sailfish movement strategy is as described in S21, and the sardine movement strategy is as described in S22; S35: The sailfish launches an attack, and the sailfish attack strategy is as described in S24; S36: Replace the predatory sardines with swordfish, as shown in the formula below: This represents the fitness level of the sardines that are about to be preyed upon. The fitness level represents the sailfish about to launch an attack. and These represent using the location of the preyed sardine to update the location of the sailfish that preyed on it. This indicates the removal of preyed sardines; S37: Determine whether the iteration termination condition has been met. If the maximum number of iterations has been reached or no better solution has been updated for a long time, then end the iteration; otherwise, continue the calculation from S32.

7. The control method for a pulverized coal injection Roots blower based on an improved sailfish optimization algorithm as described in claim 4, characterized in that, In step S22, The value is determined by the following formula: This is a standardized factor derived to conform to the characteristics of the Levy distribution. The distribution index of Levy, In order to comply with the relevant The set of vectors that are normally distributed. It is a set of vectors that conform to a standard normal distribution.

8. The control method for a pulverized coal injection Roots blower based on an improved sailfish optimization algorithm as described in claim 4, characterized in that, In step S23, The value is calculated using the following formula: The chaos parameter represents the magnitude of the disturbance, and the final disturbance result is the vector obtained after iterating the above formula four times.

9. The control method for a pulverized coal injection Roots blower based on an improved sailfish optimization algorithm as described in claim 4, characterized in that, In step S24, The value is calculated using the following formula: In the formula, This indicates the sailfish's aggressive nature. Indicates the current iteration round. The formula represents the total number of iterations. As the number of iterations increases, the attack desire of the sailfish increases, and the local exploitation capability of the algorithm is enhanced.

Images