A control optimization method for electronic infusion micro pump

Abstract

The invention provides an electronic infusion micro pump control optimization method, which belongs to the field of PID control optimization, and comprises the following specific steps: step one: converting the electronic infusion micro pump control problem into a mathematical model to be optimized; step two: establishing a PID control model of the electronic infusion micro pump control system; step three: establishing an improved galaxy cluster algorithm mathematical model, and verifying the performance of the improved galaxy cluster algorithm in optimizing the PID controller; the improved galaxy cluster algorithm comprises: D1, transforming the inertia weight w1 into an adaptive inertia weight; D2, introducing a Gaussian variation strategy; step four: optimizing the electronic infusion micro pump speed PID controller by using the improved galaxy cluster algorithm, and obtaining the optimal control parameters Kp, Ki, and Kd; step five: inputting the obtained optimal control parameters Kp, Ki, and Kd into the PID control model of the electronic infusion micro pump control system, and realizing the optimal robust control of the electronic infusion micro pump.

Description

Technical Field

[0001] The invention belongs to the field of PID control optimization, and in particular relates to an electronic infusion micro pump control optimization method. Background Art

[0002] The electronic infusion micropump is a precision medical device used to accurately deliver drugs, nutrients or other liquids to patients during clinical treatment. It accurately adjusts the infusion speed through a PID control system to ensure that the drugs or liquids are evenly and continuously delivered to the patient's body. The micropump has the characteristics of high precision, high reliability and easy operation. It is often used in treatments that require long-term continuous infusion, such as cancer chemotherapy, pain management, nutritional support, and treatment of chronic diseases. Compared with traditional gravity infusion methods, the electronic infusion micropump can more accurately control the infusion rate, reduce drug dosage errors, and reduce potential risks during the infusion process. Its portability and ease of use make it suitable for widespread use in hospitals, home care and mobile medical scenarios, effectively improving patients' treatment experience and quality of life.

[0003] PID controller is one of the most commonly used controllers in feedback control systems. It achieves precise control of the target output by adjusting the three core parameters of proportion, integration and differentiation. Due to its simple structure and good robustness, PID controller is widely used in industrial control and automation system fields. However, for complex systems with strong nonlinearity, finding the appropriate proportional coefficient (Kp), integral coefficient (Ki) and differential coefficient (Kd) often requires rich experience and repeated experiments. Although PID controller performs well in many cases, when faced with highly complex or nonlinear problems, relying solely on traditional parameter adjustment methods may not achieve the ideal control effect. For this reason, by introducing intelligent optimization algorithms to adjust the parameters of PID controller online, the optimal control parameter values ​​can be effectively found, thereby further improving its control performance and application range.

[0004] Galactic Swarm Optimization (GSO) is a new type of swarm intelligence optimization algorithm, which is inspired by the movement of galaxy clusters and gravitational interactions. GSO simulates the gravitational effects between galaxy clusters in the universe and the movement of stars inside galaxies, and achieves global optimization through information exchange and collaboration between multiple galaxy clusters. The algorithm divides the population into multiple galaxy clusters, each of which conducts independent search and guides the population to converge to the global optimal solution through gravitational interactions. GSO has good global search capabilities and is suitable for solving multi-modal complex function optimization problems. It can effectively balance exploration and development, thereby improving solution efficiency. However, like common intelligent optimization algorithms, the galaxy cluster optimization algorithm is prone to falling into local optimal solutions and has poor stability when facing complex optimization scenarios. Summary of the invention

[0005] The purpose of the present invention is to improve the global search capability of the algorithm in the early stage and the local development capability in the later stage during the optimization process by improving the galaxy cluster algorithm, reduce the possibility of the algorithm falling into the local optimum, thereby improving the optimization accuracy and response speed of the algorithm, optimize the electronic infusion micropump speed PID controller by improving the galaxy cluster algorithm, obtain the optimal control parameters Kp, Ki, Kd, ​​improve the accuracy and stability of the electronic infusion micropump control system, and reduce the adverse effects of dynamic errors on the control effect during the parameter setting process.

[0006] In order to achieve the above object, the present invention adopts the following technical solutions:

[0007] An electronic infusion micro pump control optimization method, the specific steps are:

[0008] Step 1: Convert the electronic infusion micropump control problem into a mathematical model to be optimized.

[0009] Step 2: Establish the PID control model of the electronic infusion micropump control system.

[0010] Step 3: Establishing a mathematical model of an improved galaxy cluster algorithm to verify the performance of the improved galaxy cluster algorithm in optimizing the PID controller; the improved galaxy cluster algorithm includes:

[0011] D1, by introducing the cosine function and the maximum value of the inertia weight, the inertia weight ω1 is transformed into an adaptive inertia weight, and the mathematical model for updating the position and velocity of stars in the sub-galaxy is improved;

[0012] D2. Use the Gaussian mutation strategy to improve the mathematical model for updating the positions and velocities of sub-galaxies within the super-population. By introducing functions that conform to the Gaussian distribution, the population is randomly perturbed to varying degrees. The details are as follows.

[0013] Step 1, simulate the exploration phase of the galaxy cluster algorithm, by introducing the cosine function and the maximum value of the inertia weight, the inertia weight ω1 is transformed into an adaptive inertia weight, and the mathematical model for updating the position and velocity of the stars in the sub-galaxy is improved. The specific improved mathematical model is:

[0014]

[0015] In the formula, is the velocity of the jth star in the i-th sub-galaxy, v (i) is the velocity of the ith sub-galaxy in the supergroup, is the optimal individual position of the jth star in the i-th sub-galaxy, is the position of the jth star in the ith sub-galaxy, g (i)is the global optimal solution for the sub-galaxy, ω1 is the inertia weight, c1 and c2 are acceleration constants, r1 and r2 are random numbers between -1 and 1, ω max is the maximum value of the inertia weight, which is 1, ω min is the minimum value of the inertia weight, which is 0.03, k is the current number of iterations, and L is the maximum number of iterations;

[0016] Step 2: In the development phase of the simulated galaxy cluster algorithm, the Gaussian mutation strategy is used to improve the mathematical model for updating the position and velocity of sub-galaxies in the super-cluster. By introducing a function that conforms to the Gaussian distribution, the population is randomly perturbed to varying degrees. The specific improved mathematical model is:

[0017]

[0018] In the formula, p (i) is the individual optimal position of the ith sub-galaxy in the super-group, y (i) is the position of the ith sub-galaxy in the super-swarm, g is the global optimal solution of the entire super-swarm, w2 is the inertia weight, c3 and c4 are acceleration constants, r3 and r4 are random numbers between -1 and 1, σ is the attenuation coefficient, which is 2, and the meanings of other parameters are the same as those in Step 1.

[0019] Step 4: Use the improved galaxy cluster algorithm to optimize the electronic infusion micropump speed PID controller and obtain the optimal control parameters Kp, Ki, and Kd.

[0020] Step 5: Input the obtained optimal control parameters Kp, Ki, and Kd into the PID control model of the electronic infusion micropump control system to obtain the optimal effect of PID control of the electronic infusion micropump control system.

[0021] Furthermore, in step 1, the mathematical model to be optimized is:

[0022]

[0023] e(t)=V(t)-Q(t) (2);

[0024] In the formula, Q(t) is the actual speed of the electronic infusion micro pump, V(t) is the expected speed of the electronic infusion micro pump, t is the current time, τ is the system time constant, indicating the speed of the electronic infusion micro pump response, K is the system gain, K p is the proportional gain, K i is the integral gain, K d is the differential gain, e(t) is the speed error, which represents the difference between the expected speed and the actual speed of the electronic infusion micro pump.

[0025] Furthermore, the mathematical model to be optimized combines the dynamic characteristics of the system with the PID controller. The PID controller adjusts the error through three links: proportional, integral, and differential, so that the actual speed Q(t) of the micro pump can accurately track the set expected speed V(t). The proportional term K p e(t) direct response error, integral term Eliminate steady-state error, differential term Predicting the error change trend, this comprehensive adjustment helps to improve the accuracy and stability of the electronic infusion micropump system.

[0026] Furthermore, in the step 2, a PID control model of the electronic infusion micropump control system is established, and the model includes an input module, an error calculation module, a speed PID controller module, an improved galaxy cluster algorithm module, a motor module, a speed detection module, and a micropump module; the expected speed value is input from the input module, and is input into the error calculation module together with the actual speed value detected by the speed detection module to obtain a speed error value by difference, the speed PID controller module receives the speed error value, and uses the PID parameters optimized by the improved galaxy cluster algorithm module to calculate and obtain a reference speed value, thereby controlling the motor to drive the micropump to rotate, thereby realizing the control of the speed of the electronic infusion micropump.

[0027] Furthermore, in the step three, the exploration phase of the galaxy cluster algorithm is simulated, and the inertia weight ω1 is transformed into an adaptive inertia weight by introducing the cosine function and the maximum value of the inertia weight, thereby improving the mathematical model for updating the position and velocity of stars in the sub-galaxy; the change of the adaptive inertia weight makes the motion state of the population more diversified, which helps to explore different paths in the search space. This diversity can avoid premature convergence of the population and help the algorithm find potential optimal solutions in a larger range.

[0028] Furthermore, in the step three, the galaxy cluster algorithm development phase is simulated, and the mathematical model for updating the positions and velocities of sub-galaxies within the super-cluster is improved using a Gaussian mutation strategy, and the population is randomly perturbed to varying degrees by introducing functions that conform to the Gaussian distribution; in the later development phase of algorithm optimization, Gaussian mutation can make subtle adjustments to the solution, allowing the algorithm to approach the optimal solution more quickly, and through small mutations, the algorithm can perform effective and fine searches in the local solution space and quickly converge to a high-quality solution.

[0029] Furthermore, in step 4, the specific steps of using the improved galaxy cluster algorithm to optimize the electronic infusion micro pump speed PID controller to obtain the optimal control parameters Kp, Ki, and Kd are:

[0030] S1. The mathematical model to be optimized is used as the objective function of the improved galaxy cluster algorithm;

[0031] S2, simulate the working conditions of the electronic infusion micro pump control system and design the transfer function to describe the dynamic characteristics of the system;

[0032] S3, given the input of the electronic infusion micro pump control system, the input being the expected speed value of the micro pump in the control system;

[0033] S4, encoding the parameters Kp, Ki, and Kd of the electronic infusion micro pump speed PID controller into a solution of the improved galaxy cluster algorithm search space;

[0034] S5. Initialize the parameters of the improved galaxy cluster algorithm, including population size M, problem dimension D, maximum number of iterations L, upper limit ub and lower limit lb of the search space;

[0035] S6. Calculate the individual fitness value of the current iteration population according to the fitness function, record the minimum fitness value, and compare it with the optimal fitness value of the population in the previous iteration, retaining the optimal fitness value. The fitness function is:

[0036]

[0037] In the formula, J is the fitness value, y i is the actual output value at the current moment, y ref is the expected output value at the current moment, t is the current time, and T is the total running time of the system;

[0038] S7, simulate the optimization process of the galaxy cluster algorithm exploration and development stage, that is, update the Kp, Ki, Kd parameters of the electronic infusion micro pump speed PID controller;

[0039] S8. If the updated positions and velocities of the star and sub-galaxy are better than those in the last iteration, the current optimal solution is retained;

[0040] S9. Determine whether the current number of iterations reaches the maximum number of iterations L. If so, exit the loop, output the global optimal solution, and assign it to the electronic infusion micro pump speed PID controller as the three parameters Kp, Ki, and Kd. Otherwise, return to execute S3.

[0041] Furthermore, in S2, the working condition of the electronic infusion micro pump control system is simulated, and a transfer function is designed to describe the dynamic characteristics of the system; the transfer function formula is:

[0042]

[0043] Where s represents the complex frequency domain variable in Laplace transform.

[0044] Furthermore, in S4, the parameters Kp, Ki, and Kd of the electronic infusion micropump speed PID controller are encoded as a solution of the improved galaxy cluster algorithm search space, and the encoding vector is:

[0045] x = [x1, x2, x3];

[0046] Where x is the encoding vector, x1, x2, and x3 are the proportional parameter, integral parameter, and differential parameter of the electronic infusion micropump speed PID controller, respectively.

[0047] Furthermore, in said S7, the optimization process of the exploration and development phase of the galaxy cluster algorithm is simulated, and the specific steps are as follows: S71, simulating the exploration phase of the galaxy cluster algorithm, by introducing the cosine function and the maximum value of the inertia weight, the inertia weight ω1 is transformed into an adaptive inertia weight, the position and velocity update mathematical model of the stars in the sub-galaxy is improved, and formulas (3)-(5) are executed;

[0048] S72. During the development phase of the simulated galaxy cluster algorithm, the Gaussian mutation strategy is used to improve the mathematical model for updating the positions and velocities of sub-galaxies within the super-cluster. By introducing a function that conforms to the Gaussian distribution, the population is randomly perturbed to varying degrees, and formulas (6)-(8) are executed.

[0049] In summary, due to the adoption of the above technical solution, the beneficial effects of the present invention are:

[0050] This paper proposes an electronic infusion micropump control optimization method, which improves the accuracy and performance of the algorithm by introducing the cosine function and the maximum value of the inertia weight, transforming the inertia weight ω1 into an adaptive inertia weight, and introducing the Gaussian mutation strategy to improve the galaxy cluster algorithm in the algorithm development stage; the improved galaxy cluster algorithm is used to optimize the electronic infusion micropump speed PID controller to obtain the optimal control parameters Kp, Ki, and Kd. The obtained optimal control parameters Kp, Ki, and Kd are input into the PID control model of the electronic infusion micropump control system to achieve optimal robust control of the electronic infusion micropump. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] Figure 1 A step-by-step diagram of the electronic infusion micropump control optimization method.

[0052] Figure 2 This is the PID control model diagram of the electronic infusion micro pump control system.

[0053] Figure 3 A curve chart comparing the fitness values ​​of the basic galaxy cluster algorithm and the improved galaxy cluster algorithm.

[0054] Figure 4 Diagram of the process of searching for optimal parameter value Kp for basic galaxy cluster algorithm and improved galaxy cluster algorithm.

[0055] Figure 5 Diagram of the process of searching for optimal parameter value Ki for the basic galaxy cluster algorithm and the improved galaxy cluster algorithm.

[0056] Figure 6 Diagram of the process of searching for optimal parameter value Kd for the basic galaxy cluster algorithm and the improved galaxy cluster algorithm.

[0057] Figure 7 Comparison chart of PID control optimization effects between basic galaxy cluster algorithm and improved galaxy cluster algorithm. DETAILED DESCRIPTION

[0058] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them; based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0059] See also Figure 1-Figure 7 , the present invention provides a technical solution:

[0060] A method for optimizing the control of an electronic infusion micropump, such as Figure 1 As shown, the specific steps are:

[0061] Step 1: Convert the electronic infusion micro pump control problem into a mathematical model to be optimized. The mathematical model to be optimized is:

[0062]

[0063] e(t)=V(t)-Q(t) (2);

[0064] In the formula, Q(t) is the actual speed of the electronic infusion micro pump, V(t) is the expected speed of the electronic infusion micro pump, t is the current time, τ is the system time constant, indicating the speed of the electronic infusion micro pump response, K is the system gain, K p is the proportional gain, K i is the integral gain, K d is the differential gain, e(t) is the speed error, which represents the difference between the expected speed and the actual speed of the electronic infusion micro pump.

[0065] Step 2: Establish the PID control model of the electronic infusion micro pump control system, such as Figure 2As shown, the model includes an input module, an error calculation module, a speed PID controller module, an improved galaxy cluster algorithm module, a motor module, a speed detection module, and a micro pump module; the expected speed value is input from the input module, and is input together with the actual speed value detected by the speed detection module into the error calculation module for subtraction to obtain a speed error value; the speed PID controller module receives the speed error value, and uses the PID parameters optimized by the improved galaxy cluster algorithm module to calculate and obtain a reference speed value, thereby controlling the motor to drive the micro pump to rotate, thereby realizing the speed control of the electronic infusion micro pump.

[0066] Step 3: Establishing a mathematical model of an improved galaxy cluster algorithm to verify the performance of the improved galaxy cluster algorithm in optimizing the PID controller; the improved galaxy cluster algorithm includes:

[0067] D1. By introducing the cosine function and the maximum value of the inertia weight, the inertia weight ωω1 is transformed into an adaptive inertia weight, and the mathematical model for updating the position and velocity of stars in the sub-galaxy is improved;

[0068] D2. Use the Gaussian mutation strategy to improve the mathematical model for updating the positions and velocities of sub-galaxies within the super-population. By introducing functions that conform to the Gaussian distribution, the population is randomly perturbed to varying degrees. The details are as follows.

[0069] Step 1, simulate the exploration phase of the galaxy cluster algorithm, by introducing the cosine function and the maximum value of the inertia weight, the inertia weight ω1 is transformed into an adaptive inertia weight, and the mathematical model for updating the position and velocity of the stars in the sub-galaxy is improved. The specific improved mathematical model is:

[0070]

[0071] In the formula, is the velocity of the jth star in the i-th sub-galaxy, v (i) is the velocity of the ith sub-galaxy in the supergroup, is the individual optimal position of the jth star in the i-th sub-galaxy, is the position of the jth star in the ith sub-galaxy, g (i) is the global optimal solution for the sub-galaxy, ω1 is the inertia weight, c1 and c2 are acceleration constants, r1 and r2 are random numbers between -1 and 1, ω max is the maximum value of the inertia weight, which is 1, ω min is the minimum value of the inertia weight, which is 0.03, k is the current number of iterations, and L is the maximum number of iterations;

[0072] Step 2: In the development phase of the simulated galaxy cluster algorithm, the Gaussian mutation strategy is used to improve the mathematical model for updating the position and velocity of sub-galaxies in the super-cluster. By introducing a function that conforms to the Gaussian distribution, the population is randomly perturbed to varying degrees. The specific improved mathematical model is:

[0073]

[0074] In the formula, p (i) is the individual optimal position of the ith sub-galaxy in the super-group, y (i) is the position of the ith sub-galaxy in the super-swarm, g is the global optimal solution of the entire super-swarm, w2 is the inertia weight, c3 and c4 are acceleration constants, r3 and r4 are random numbers between -1 and 1, σ is the attenuation coefficient, which is 2, and the meanings of other parameters are the same as those in Step 1.

[0075] Step 4: Use the improved galaxy cluster algorithm to optimize the electronic infusion micro pump speed PID controller. The specific steps to obtain the optimal control parameters Kp, Ki, and Kd are as follows:

[0076] S1. The mathematical model to be optimized is used as the objective function of the improved galaxy cluster algorithm;

[0077] S2, simulate the working conditions of the electronic infusion micro pump control system and design the transfer function to describe the dynamic characteristics of the system;

[0078] S3, given the input of the electronic infusion micro pump control system, the input being the expected speed value of the micro pump in the control system;

[0079] S4, encoding the parameters Kp, Ki, and Kd of the electronic infusion micro pump speed PID controller into a solution of the improved galaxy cluster algorithm search space;

[0080] S5. Initialize the parameters of the improved galaxy cluster algorithm, including population size M, problem dimension D, maximum number of iterations L, upper limit ub and lower limit lb of the search space;

[0081] S6. Calculate the individual fitness value of the current iteration population according to the fitness function, record the minimum fitness value, and compare it with the optimal fitness value of the population in the previous iteration, retaining the optimal fitness value. The fitness function is:

[0082]

[0083] In the formula, J is the fitness value, y i is the actual output value at the current moment, y r , ef is the expected output value at the current moment, t is the current time, and T is the total running time of the system;

[0084] S7, simulate the optimization process of the galaxy cluster algorithm exploration and development stage, that is, update the Kp, Ki, Kd parameters of the electronic infusion micro pump speed PID controller;

[0085] S8. If the updated positions and velocities of the star and sub-galaxy are better than those in the last iteration, the current optimal solution is retained;

[0086] S9. Determine whether the current number of iterations reaches the maximum number of iterations L. If so, exit the loop, output the global optimal solution, and assign it to the electronic infusion micro pump speed PID controller as the three parameters Kp, Ki, and Kd. Otherwise, return to execute S3.

[0087] Furthermore, in S2, the working condition of the electronic infusion micro pump control system is simulated, and a transfer function is designed to describe the dynamic characteristics of the system; the transfer function formula is:

[0088]

[0089] Where s represents the complex frequency domain variable in Laplace transform.

[0090] Furthermore, in S4, the parameters Kp, Ki, and Kd of the electronic infusion micropump speed PID controller are encoded as a solution of the improved galaxy cluster algorithm search space, and the encoding vector is:

[0091] x = [x1, x2, x3];

[0092] Where x is the encoding vector, x1, x2, and x3 are the proportional parameter, integral parameter, and differential parameter of the electronic infusion micropump speed PID controller, respectively.

[0093] Furthermore, in S7, the optimization process of the galaxy cluster algorithm exploration and development phase is simulated, and the specific steps are:

[0094] S71, simulate the exploration phase of the galaxy cluster algorithm, by introducing the cosine function and the maximum value of the inertia weight, transform the inertia weight ω1 into an adaptive inertia weight, improve the position and velocity update mathematical model of the stars in the sub-galaxy, and execute formulas (3)-(5);

[0095] S72. During the development phase of the simulated galaxy cluster algorithm, the Gaussian mutation strategy is used to improve the mathematical model for updating the positions and velocities of sub-galaxies within the super-cluster. By introducing a function that conforms to the Gaussian distribution, the population is randomly perturbed to varying degrees, and formulas (6)-(8) are executed.

[0096] Step 5: Input the obtained optimal control parameters Kp, Ki, and Kd into the PID control model of the electronic infusion micropump control system to obtain the optimal effect of PID control of the electronic infusion micropump control system.

[0097] In order to verify the innovation of the electronic infusion micropump control optimization method proposed in the present invention, the present invention conducts simulation experiments through Matlab and Simulink to compare the PID control optimization of the improved galaxy cluster algorithm and the basic galaxy cluster algorithm. First, the mathematical model of the galaxy cluster algorithm is improved by Matlab, and the PID control model of the electronic infusion micropump control system is established by Simulink; the parameters of the improved galaxy cluster algorithm are initialized, where the population size M=50, the problem dimension D=3, the maximum number of iterations L=30, the upper limit ub=1 of the search space, and the lower limit lb=0; the Matlab program is run to obtain a fitness value comparison curve of the basic galaxy cluster algorithm and the improved galaxy cluster algorithm, as shown in FIG. Figure 3 As shown in the figure, the improved galaxy cluster algorithm reaches the optimal fitness value of 6.64 at about the 9th iteration. Compared with the basic galaxy cluster algorithm, it has better optimization accuracy and convergence speed, which can better improve the control performance of the electronic infusion micropump control system, thereby achieving better medical effects.

[0098] Furthermore, if Figure 4-6 As shown, the improved galaxy cluster algorithm and the basic galaxy cluster algorithm are used to adjust the parameters of the speed PID controller of the electronic infusion micropump control system model. The optimal PID control parameters obtained by the improved algorithm are Kp=0.165, Ki=0.148, Kd=0.115, and the optimal PID control parameters obtained by the basic algorithm are Kp=0.171, Ki=0.151, Kd=0.124; the optimal control parameters are input into the electronic infusion micropump speed PID controller, and the optimal effect of the electronic infusion micropump control system PID control is obtained; Figure 7 The comparison chart of the optimization effect of PID control by basic galaxy cluster algorithm and improved galaxy cluster algorithm is shown in the figure. The expected value is set to 3 units. Figure 7 It can be seen that the improved galaxy cluster algorithm optimizes the PID control response curve with lower overshoot and faster response speed. Compared with the basic galaxy cluster algorithm, the parameters of PID control are better and the effect of electronic infusion micropump control is better. The fast response speed and lower overshoot can reduce the impact of dynamic errors and make the speed of the electronic infusion micropump quickly reach a stable state, so as to accurately adjust the infusion speed, ensure that the drugs are evenly and continuously delivered to the patient, and improve the medical effect.

Claims

1. A method for optimizing the control of an electronic infusion micropump, characterized in that: The specific steps are: Step 1: Convert the electronic infusion micro pump control problem into a mathematical model to be optimized. The mathematical model to be optimized is: （1）； （2）； In the formula, is the actual speed of the electronic infusion micro pump, is the expected speed of the electronic infusion micro pump, t is the current time, is the system time constant, indicating the speed of response of the electronic infusion micro pump, K is the system gain, is the proportional gain, is the integral gain, is the differential gain, is the speed error, which represents the difference between the expected speed and the actual speed of the electronic infusion micro pump; Step 2: Establish the PID control model of the electronic infusion micro pump control system; Step 3: Establishing a mathematical model of an improved galaxy cluster algorithm to verify the performance of the improved galaxy cluster algorithm in optimizing the PID controller; the improved galaxy cluster algorithm includes: D1. By introducing the cosine function and the maximum value of the inertia weight, the inertia weight Transformed into adaptive inertia weight, the mathematical model for updating the position and velocity of stars in the sub-galaxy is improved. The specific improved mathematical model is: （3）； （4）； （5）； In the formula, is the velocity of the jth star in the ith sub-galaxy, is the velocity of the ith sub-galaxy in the supergroup, is the optimal individual position of the jth star in the i-th sub-galaxy, is the position of the jth star in the ith sub-galaxy, is the global optimal solution for the sub-galaxy, is the inertia weight, and is the acceleration constant, and is a random number between -1 and 1. is the maximum value of the inertia weight, which is 1. is the minimum value of the inertia weight, which is 0.03, k is the current number of iterations, and L is the maximum number of iterations; D2. Use the Gaussian mutation strategy to improve the mathematical model for updating the position and velocity of sub-galaxies in the super-group. By introducing a function that conforms to the Gaussian distribution, the population is randomly disturbed to varying degrees. The specific improved mathematical model is: （6）； （7）； （8）； In the formula, is the individual optimal position of the ith sub-galaxy in the supergroup, is the position of the ith sub-galaxy in the supergroup, is the global optimal solution for the entire super group, is the inertia weight, and is the acceleration constant, and is a random number between -1 and 1. is the attenuation coefficient, the value is 2, and the meanings of other parameters are the same as those in step D1; Step 4: Use the improved galaxy cluster algorithm to optimize the electronic infusion micro pump speed PID controller to obtain the optimal control parameters Kp, Ki, and Kd; Step 5: Input the obtained optimal control parameters Kp, Ki, and Kd into the PID control model of the electronic infusion micropump control system to obtain the optimal effect of PID control of the electronic infusion micropump control system.

2. The electronic infusion micro pump control optimization method according to claim 1, characterized in that: In the step 2, a PID control model of the electronic infusion micro pump control system is established, wherein the model includes an input module, an error calculation module, a speed PID controller module, an improved galaxy cluster algorithm module, a motor module, a speed detection module, and a micro pump module; The expected speed value is input from the input module and input into the error calculation module together with the actual speed value detected by the speed detection module to obtain the speed error value. The speed PID controller module receives the speed error value and uses the PID parameters optimized by the improved galaxy cluster algorithm module to calculate the reference speed value, and then controls the motor to drive the micro pump to rotate, thereby realizing the speed control of the electronic infusion micro pump.

3. The electronic infusion micro pump control optimization method according to claim 2, characterized in that: In step 4, the specific steps of optimizing the electronic infusion micro pump speed PID controller using the improved galaxy cluster algorithm to obtain the optimal control parameters Kp, Ki, and Kd are as follows: S1. The mathematical model to be optimized is used as the objective function of the improved galaxy cluster algorithm; S2, simulate the working conditions of the electronic infusion micro pump control system and design the transfer function to describe the dynamic characteristics of the system; S3, given the input of the electronic infusion micro pump control system, the input being the expected speed value of the micro pump in the control system; S4, encoding the parameters Kp, Ki, and Kd of the electronic infusion micro pump speed PID controller into a solution of the improved galaxy cluster algorithm search space; S5. Initialize the parameters of the improved galaxy cluster algorithm, including population size M, problem dimension D, maximum number of iterations L, upper limit ub and lower limit lb of the search space; S6. Calculate the individual fitness value of the current iteration population according to the fitness function, record the minimum fitness value, and compare it with the optimal fitness value of the population in the previous iteration, retaining the optimal fitness value. The fitness function is: （9）； In the formula, J is the fitness value, is the actual output value at the current moment, is the expected output value at the current moment, t is the current time, and T is the total running time of the system; S7, simulate the optimization process of the galaxy cluster algorithm exploration and development stage, that is, update the Kp, Ki, Kd parameters of the electronic infusion micro pump speed PID controller; S8. If the updated positions and velocities of the star and sub-galaxy are better than those in the last iteration, the current optimal solution is retained; S9. Determine whether the current number of iterations reaches the maximum number of iterations L. If so, exit the loop, output the global optimal solution, and assign it to the electronic infusion micro pump speed PID controller as the three parameters Kp, Ki, and Kd. Otherwise, return to execute S3.

4. The electronic infusion micro pump control optimization method according to claim 3, characterized in that: Simulate the optimization process of the galaxy cluster algorithm exploration and development phase. The specific steps are: S71, simulate the exploration phase of the galaxy cluster algorithm, by introducing the cosine function and the maximum value of the inertia weight, the inertia weight Transformed into adaptive inertia weight, the mathematical model of the position and velocity of stars in the sub-galaxy is improved and updated, and formulas (3)-(5) are executed; S72. During the development phase of the simulated galaxy cluster algorithm, the Gaussian mutation strategy is used to improve the mathematical model for updating the positions and velocities of sub-galaxies within the super-cluster. By introducing a function that conforms to the Gaussian distribution, the population is randomly perturbed to varying degrees, and formulas (6)-(8) are executed.

Images