An end effector polishing control method based on chicken swarm optimization algorithm

Abstract

The application discloses an end effector polishing control method based on a chicken swarm optimization algorithm, a three-dimensional model of a workpiece to be polished is acquired through a visual camera, a standard sample is aligned in combination with an iterative closest point algorithm, grinding force and grinding amount are accurately calculated, and adaptive control of a complex curved surface and an edge mutation area is realized. The chicken swarm optimization algorithm is used for dynamic planning of a grinding track, and PID parameters are real-timely self-tuned, synchronous optimization of force and a path is realized, and the shortcomings of constant force control and path separation control in the prior art are effectively overcome. The application significantly improves machining quality and efficiency of the system on complex workpieces, enhances stability and response speed of the system in a high dynamic environment, and especially exhibits significant technical advantages under complex working conditions such as irregular surfaces and uneven hardness. The method reduces calculation delay, optimizes the synergistic effect of track and force control, and has the characteristics of precision, stability and high efficiency.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of intelligent control and optimization algorithm of polishing equipment, in particular to a polishing control method for an end effector based on a chicken swarm optimization algorithm. BACKGROUND

[0002] Polishing control technology is widely used in the surface treatment and finishing process of various workpieces such as metals and ceramics. The purpose is to control the grinding force and polishing path to make the workpiece surface achieve the predetermined smoothness and shape accuracy.

[0003] The existing polishing control system usually uses fixed force control or polishing through a pre-set force correction formula to process the workpiece surface in a constant force mode. However:

[0004] 1. Complex workpiece surfaces often have variable curved surfaces, uneven surfaces, edge mutations and other characteristics, making it difficult to achieve accurate grinding with fixed force control in these scenarios, which can easily cause over-polishing or under-polishing problems, seriously affecting the surface quality of the workpiece.

[0005] 2. In order to improve the accuracy of polishing control, six-axis force sensors are usually used in existing technologies to monitor the grinding force in real time, and the end effector is adjusted through control. The common adjustment method is to manually set the parameters of the PID controller, i.e. proportional gain (Kp), integral gain (Ki) and derivative gain (Kd). However, the manual adjustment of the PID parameters is not only time-consuming, but also difficult to quickly respond to real-time changes in the processing environment, often failing to find a globally optimal control solution under different working conditions, resulting in a decline in system control accuracy and efficiency.

[0006] 3. In order to further improve the intelligent level of polishing path planning, the existing technology gradually introduces model predictive control (MPC) and other algorithms to optimize the polishing trajectory. However, the MPC algorithm has a large amount of calculation and slow response speed, especially when dealing with complex curved surfaces or high dynamic environments, the system has obvious delay, which cannot meet the real-time requirements in the polishing process, resulting in low trajectory control accuracy and low processing efficiency.

[0007] In addition, most of the current polishing control technology treats force control and path planning as independent processes, which can easily cause the polishing head to stay in some areas for too long or the force control to be inaccurate, resulting in defects on the polished surface. In order to make up for this defect, the industry tries to integrate multiple control strategies, but the synchronous optimization of path and force control is still difficult to achieve, and the overall processing efficiency and accuracy are limited.

[0008] Therefore, how to achieve adaptive control of complex curved surfaces, real-time PID parameter optimization and synchronous optimization of path and force, and improve polishing accuracy and processing efficiency, has become a technical problem to be solved by the present application. SUMMARY

[0009] The technical problem solved by the present application is to provide an end effector polishing control method based on a chicken swarm optimization algorithm to solve the problems of low control accuracy, large response delay and disconnection between path and force control of the existing polishing control method in complex workpiece surface machining.

[0010] To solve the above technical problems, the technical solutions adopted by the present application are as follows:

[0011] An end effector polishing control method based on a chicken swarm optimization algorithm, comprising the following steps:

[0012] Step 1: Obtain the three-dimensional numerical model data of the workpiece to be polished, scan the surface shape of the workpiece to be polished by a vision camera, obtain its three-dimensional model, and align it with the three-dimensional model of the known standard sample, calculate the grinding amount and grinding force of each point of the workpiece, and realize adaptive control of complex curved surfaces and edge mutation areas;

[0013] Step 2: Use the chicken swarm optimization algorithm to plan the grinding track, convert the track planning problem into a constraint solving problem, set the kinematic constraints of the mechanical arm, the space obstacle avoidance constraints and the objective function of minimizing the total energy consumption, total time or track smoothness in the grinding process, optimize the control points of the polishing track or the path points of the mechanical arm joints, and realize dynamic synchronous optimization of force control and track planning;

[0014] Step 3: In the polishing process, use the chicken swarm optimization algorithm to perform real-time self-tuning of the PID parameters of the motor or cylinder, automatically optimize the proportional gain, integral gain and differential gain, monitor the changes of grinding force and grinding amount through a six-axis force sensor, dynamically optimize the control parameters in the preliminary adjustment and fine adjustment stages, and ensure the accuracy and stability of force and position control in high dynamic scenarios.

[0015] As a further scheme of the present application, the acquisition of the three-dimensional numerical model data comprises scanning the three-dimensional data of the workpiece to be polished by a vision camera, generating grinding deviation values of each region, and constructing a color mapping diagram to display the regions to be polished for adaptive adjustment of the grinding force.

[0016] As a further scheme of the present application, the chicken swarm optimization algorithm is used for trajectory planning, and the trajectory planning and grinding force control are optimized synchronously, and the optimal path planned can adapt to irregular surfaces, complex curved surfaces and workpieces with variable shapes to avoid inaccuracy and low efficiency caused by disconnection between path and force control.

[0017] As a further scheme of the present application, the target function of the real-time self-tuning of the PID parameters comprises integral square error, integral time weighted square error or other control indicators related to system performance, and the PID parameter combination is optimized to achieve precise force control.

[0018] As a further scheme of the present application, the integrated optimization of trajectory planning and force control is performed by the chicken swarm optimization algorithm for multiple iterations to optimize the polishing trajectory control point and PID parameter combination and achieve a shared optimization strategy of path and force control.

[0019] As a further scheme of the present application, the alignment of the three-dimensional model data comprises using the iterative closest point (ICP) algorithm to align the three-dimensional scanning data of the workpiece to be polished with the three-dimensional model reference points of the standard sample to accurately calculate the grinding deviation value of each point.

[0020] As a further scheme of the present application, the determination of the grinding force takes into account the hardness of the material, the grinding depth, the grinding tool characteristics and the grinding speed, and the grinding force of each point is determined comprehensively through theoretical formulas and empirical parameters.

[0021] As a further scheme of the present application, the polishing trajectory planning comprises setting the joint angle, speed and acceleration limits of the mechanical arm to avoid collision with the workpiece or other equipment during polishing.

[0022] As a further scheme of the present application, when the chicken swarm optimization algorithm is used to optimize the grinding trajectory, the individuals are divided into three categories of roosters, hens and chicks according to the fitness value, and the polishing trajectory control point is optimized through multiple iterations until the termination condition is met.

[0023] As a further scheme of the present application, the PID control process uses the feedback data of the six-axis force sensor to calculate the error, outputs a control signal to the motor or air cylinder to adjust the output force and position in real time during polishing; and the PID parameter self-tuning is evaluated in terms of fitness after each adjustment, and the control system performance is gradually optimized by minimizing the fitness to keep the system in the best state in a complex and dynamic polishing environment.

[0024] Compared with the prior art, the present application has the following advantages:

[0025] 1. Self-adaptive gain control of complex surfaces: The present application obtains the three-dimensional model of the workpiece through a vision camera, and accurately aligns it by combining the iterative closest point (ICP) algorithm to calculate the grinding force and grinding amount of each point, thereby achieving self-adaptive control of complex surfaces and edge mutation areas. Compared with the traditional constant force polishing method, the present application can dynamically adjust the grinding force, thereby effectively avoiding over-repair or insufficient repair, significantly improving the machining quality and consistency of complex workpiece surfaces, and overcoming the control failure problem of the prior art in dealing with complex working conditions.

[0026] 2. Real-time customization of PID parameter self-tuning for high efficiency application: The present application uses chicken swarm optimization algorithm to perform real-time self-tuning of PID parameters for motors or cylinders, automatically optimizes control parameters, and enables dynamic optimization of the system in the preliminary adjustment and fine adjustment stages. This method overcomes the hysteresis and inaccuracy of traditional manual adjustment of PID parameters, especially in high reflectivity or uneven hardness workpiece processing, significantly improves the response speed and control accuracy of the system, avoids vibration and scratching caused by parameter mismatch, and enables the control system to maintain optimal performance in complex dynamic environments.

[0027] 3. Deep integration optimization of path and force control: The present application deeply integrates grinding trajectory planning and force control, and performs multiple iterations of optimization through chicken swarm optimization algorithm, enabling synchronous adjustment of path and force control in dynamic environments, breaking through the precision decline and low efficiency bottleneck caused by path and force separation control in existing technologies. This shared optimization strategy effectively reduces unnecessary pauses and repetitive actions, improves polishing efficiency and surface quality, and is particularly suitable for processing of irregular shapes, complex curved surfaces, and variable element workpieces.

[0028] 4. Efficient and accurate real-time optimization capability: The chicken swarm optimization algorithm is used for synchronous optimization of trajectory and parameters, which not only reduces the computational complexity, but also significantly saves processing time. Compared with traditional model predictive control (MPC), the calculation amount and delay of trajectory planning are greatly reduced, improving real-time performance and overall efficiency. The system can monitor and adjust the grinding force and grinding amount of each point in real time during the grinding process, ensuring the efficiency and accuracy of the grinding process, and greatly improving the surface quality of the workpiece polishing.

[0029] 5. Enhanced system stability and adaptability: The present application ensures the stability of the system in complex working conditions by adjusting the force and trajectory planning in real time. Combined with the chicken swarm optimization algorithm for cooperative optimization of PID parameters and grinding trajectory, the control system has stronger adaptability and can cope with diversified workpiece requirements, thereby greatly expanding the application range and flexibility of the system and improving the market competitiveness of the product.

[0030] Additional aspects and advantages of the present application will be partially given in the following description, partially will become apparent from the following description, or will be learned by practice of the present application. BRIEF DESCRIPTION OF DRAWINGS

[0031] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings in the following description only constitute some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained without creative labor.

[0032] Figure 1 is a flow chart of the control method in the embodiments of the present application.

[0033] Figure 2 is a technical roadmap of the CSO planning polishing trajectory in the embodiments of the present application.

[0034] Figure 3 is a technical roadmap of the CSO setting PID parameters in the embodiments of the present application. DETAILED DESCRIPTION

[0035] The technical solutions in the embodiments of the present application will be described clearly and completely below. Obviously, the described embodiments only constitute some embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0036] Please refer to Figure 1 In the embodiments of the present application, a polishing control method for an end effector based on a chicken swarm optimization algorithm comprises the following steps:

[0037] Step 1: Obtain the three-dimensional model data of the workpiece to be polished, scan the surface shape of the workpiece to be polished through a visual camera, obtain its three-dimensional model, and align it with the three-dimensional model of a known standard sample, calculate the grinding amount and grinding force of each point of the workpiece, so as to realize adaptive control of complex curved surfaces and edge mutation areas;

[0038] Step 2: Use the chicken swarm optimization algorithm to plan the grinding trajectory, convert the trajectory planning problem into a constraint solving problem, set the kinematic constraints of the mechanical arm, the space obstacle avoidance constraints, and the objective function of minimizing the total energy consumption, total time or trajectory smoothness in the grinding process, optimize the control points of the polishing trajectory or the path points of the joints of the mechanical arm, and realize dynamic synchronous optimization of force control and trajectory planning;

[0039] Step 3: In the polishing process, use the chicken swarm optimization algorithm to perform real-time self-setting of the PID parameters of the motor or the cylinder, automatically optimize the proportional gain, integral gain and differential gain, monitor the changes of the grinding force and grinding amount through a six-dimensional force sensor, dynamically optimize the control parameters in the preliminary adjustment and fine adjustment stages, and ensure the accuracy and stability of force and position control in high dynamic scenarios.

[0040] As a further scheme of the present application, the acquisition of the three-dimensional model data comprises acquiring three-dimensional data of the workpiece to be polished by visual camera scanning, generating grinding deviation values of each region, and constructing a color mapping diagram to display the regions to be polished for adaptive adjustment of the grinding force.

[0041] As a further scheme of the present application, when the chicken swarm optimization algorithm is used for trajectory planning, the trajectory planning and grinding force control are synchronously optimized, and the optimal path planned can adapt to irregular surfaces, complex curved surfaces and workpieces with variable shapes to avoid inaccuracy and low efficiency caused by separation of path and force control.

[0042] As a further scheme of the present application, the target function of the real-time self-tuning of the PID parameters comprises integral square error, integral time weighted square error or other control indicators related to system performance, and the combination of PID parameters is optimized to realize accurate force control.

[0043] As a further scheme of the present application, the integrated optimization of the trajectory planning and force control is performed by the chicken swarm optimization algorithm for multiple iterations to optimize the combination of polishing trajectory control points and PID parameters and realize a shared optimization strategy of path and force control.

[0044] As a further scheme of the present application, the alignment of the three-dimensional model data comprises using an iterative closest point (ICP) algorithm to make the three-dimensional scanning data of the workpiece to be polished coincide with the three-dimensional model reference points of a standard sample to accurately calculate grinding deviation values of each point.

[0045] As a further scheme of the present application, the determination of the grinding force comprehensively considers the hardness of the material, the grinding depth, the characteristics of the grinding tool and the grinding speed, and the grinding force of each point is determined by a theoretical formula and empirical parameters.

[0046] As a further scheme of the present application, the polishing trajectory planning comprises setting joint angle, speed and acceleration limits of the mechanical arm to avoid collision with the workpiece or other equipment during polishing.

[0047] As a further scheme of the present application, when the chicken swarm optimization algorithm is used for optimization of the grinding trajectory, individuals are divided into three categories of roosters, hens and chicks according to fitness values, the polishing trajectory control points are optimized through multiple iterations until the termination condition is met.

[0048] As a further scheme of the present application, the PID control process uses feedback data of a six-dimensional force sensor for error calculation, outputs a control signal to a motor or a pneumatic cylinder to real-time adjust the output force and position during polishing, and the PID parameter self-tuning performs fitness evaluation after each adjustment, gradually optimizes the performance of the control system by minimizing the fitness, and keeps the system in the best state in a complex and dynamic polishing environment.

[0049] Embodiment 1:

[0050] The embodiment provides an end effector polishing control method based on a chicken swarm optimization algorithm, which is applied to a high-precision polishing process of a complex curved workpiece, and is particularly suitable for surface finishing of metal or ceramic workpieces with irregular surfaces, edge mutations and uneven hardness.

[0051] In actual application, first, a three-dimensional data of a workpiece to be polished is acquired through a visual camera. Taking an aero-engine blade as an example, the surface of the blade has a complex curved surface structure and a variable edge shape, and the traditional constant force polishing control cannot meet the high-precision surface quality requirement. The blade is scanned by the visual camera to acquire three-dimensional model data, and the three-dimensional model data is aligned with the three-dimensional model of a known standard sample, and the iterative closest point (ICP) algorithm is used to accurately match the reference points of the two. By comparing the surface deviation of the workpiece to be polished and the standard sample, a color mapping diagram showing the grinding requirements of each region is generated, so that the grinding amount and the corresponding grinding force of each point are calculated, and the basic data for polishing is formed.

[0052] After obtaining the basic data of the grinding force and the grinding amount, the chicken swarm optimization algorithm is used to plan the grinding trajectory of the end effector. Specifically, the trajectory planning problem is converted into a constraint solving problem, and the kinematic constraints (such as joint angle, speed and acceleration limits) and space obstacle avoidance constraints (to avoid collision with the workpiece or equipment) of the robot arm are set. By setting the objective function, such as minimizing the total energy consumption, polishing time or trajectory smoothness in the grinding process, the chicken swarm optimization algorithm optimizes the polishing path into a set of control points and path points. In the optimization process, the chicken swarm algorithm divides the population into three types of individuals, namely roosters, hens and chicks, and iteratively optimizes the control points according to the fitness values of the individuals to realize dynamic adjustment of the trajectory and planning of the optimal running path. The core of this step is to optimize the path planning and force control simultaneously to avoid the inaccuracy and low efficiency caused by the separation of path planning and force control.

[0053] During the polishing process, the system uses the chicken swarm optimization algorithm to adjust the PID control parameters of the motor or the cylinder in real time, including the proportional gain (Kp), the integral gain (Ki) and the differential gain (Kd), to realize accurate control of the grinding force and the grinding amount. The self-tuning of the PID parameters sets the performance index of the control system as the objective function, such as the integral square error or the integral time weighted square error, and automatically searches for the optimal parameter combination through the chicken swarm optimization algorithm. In the complex processing process of the blade surface, the system can continuously adjust the polishing force and the trajectory according to the real-time feedback data of the six-axis force sensor, so that the end effector can maintain the best force and position control under different working conditions; specifically, in the polishing process, the system can adjust the PID parameters of the motor or the cylinder in real time according to the real-time feedback data of the six-axis force sensor, so that the end effector can maintain the best force and position control under different working conditions. Figure 3In the formula, Kp is proportional gain, which is proportional to the current error. Increasing the proportional gain can speed up the system response, but too large a proportional gain can lead to oscillation; Ki is integral gain, which is proportional to the cumulative value of the error. The integral gain can eliminate the steady-state error of the system, but too large an integral gain can lead to system overshoot or oscillation; Kd is derivative gain, which is proportional to the rate of change of error. The derivative gain responds to rapid changes in system response and can improve system stability, but too large a derivative gain can also introduce noise sensitivity.

[0054] For example, in the polishing of the edge mutation area of the blade, the traditional control method is prone to over-polishing or insufficient polishing due to inaccurate force control, resulting in irregular blade edges, vibration or surface scratches and other defects. The embodiment adjusts the PID parameters in real time to keep the grinding force stable in the edge area, avoiding the adverse consequences of traditional methods. Through real-time force control and trajectory planning synchronous optimization, the accuracy and uniformity of the polishing process are ensured, significantly improving the machining quality of the workpiece and avoiding the low efficiency problem caused by the disconnection of path planning and force control.

[0055] In summary, the embodiment realizes efficient polishing under complex curved surfaces and variable working conditions through the cooperative work of visual cameras, chicken swarm optimization algorithm, real-time PID control and other technical means. This method significantly improves the accuracy, efficiency and stability of the polishing process, especially in complex surfaces and high dynamic environments, showing technical advantages that traditional control methods cannot match. Through the above steps, the invention solves the problems of low control accuracy, large response delay, separation of path and force control in existing polishing control technology, and provides an innovative solution for high-precision workpiece surface treatment.

[0056] Embodiment 2:

[0057] This embodiment demonstrates the application of a polishing control method based on chicken swarm optimization algorithm for end effector polishing in automobile engine cylinder block polishing. The polishing of automobile engine cylinder block requires high precision and high efficiency, especially for the complex surface of the inner wall of the cylinder and the convex structure. Traditional constant force polishing method is difficult to achieve precise machining of each part, resulting in uneven grinding, surface defects or damage and other problems. This embodiment realizes efficient polishing of the complex surface of the cylinder through innovative adaptive control and optimization algorithm.

[0058] In actual operation, first, a visual camera is used to scan a three-dimensional model of the engine cylinder block, three-dimensional model data of the inner wall and complex surface thereof are acquired, and alignment is performed with an ideal model of a standard sample, an iterative closest point (ICP) algorithm is used to accurately calculate a deviation value of a region to be polished. A color mapping chart is generated based on the deviation value, and polishing requirements of each part, including the inner wall of the cylinder, the convex part and the groove region, are displayed. This process can accurately identify the polishing amount of each point and calculate the corresponding polishing force to meet the polishing requirements of different parts of the cylinder block.

[0059] Then, the chicken swarm optimization algorithm is used to plan the optimal operation trajectory of the mechanical arm and the end effector. By setting multiple constraint conditions such as kinematics and space obstacle avoidance, and combining the goals to be minimized in the polishing process (such as total energy consumption, polishing time and trajectory smoothness), the chicken swarm optimization algorithm automatically optimizes the trajectory control points. During the optimization process, the chicken swarm is divided into three types of individuals: roosters, hens and chicks. Each type of individual adjusts the trajectory according to the fitness value to ensure the synchronous optimization of trajectory planning and polishing force control. This deep integration of trajectory and force control avoids the low efficiency and uneven polishing caused by the separation of path and force control in traditional polishing methods.

[0060] In the actual polishing process, the system uses the chicken swarm optimization algorithm to perform real-time self-tuning of the PID parameters of the motor and cylinder. Taking the polishing of the inner wall of the cylinder block as an example, the traditional control method is difficult to maintain a constant polishing force due to uneven hardness or complex inner wall shape, and is prone to over-polishing or insufficient polishing. By monitoring the feedback data of the six-axis force sensor in real time, the chicken swarm optimization algorithm automatically adjusts the proportional gain (Kp), integral gain (Ki) and derivative gain (Kd) to ensure accurate control of the polishing force and the position of the end effector. The adaptive PID parameter adjustment continuously optimizes the control performance during the initial polishing stage, the transition stage and the fine polishing process, so that the system always maintains the best state in different polishing environments.

[0061] For example, in the polishing of the convex part of the cylinder block, the traditional constant force control is prone to over-polishing or damage to the convex part due to the small size and irregular shape of the convex part. This embodiment adjusts the PID parameters in real time, so that the polishing force can be quickly adjusted according to real-time feedback, avoiding defects caused by inaccurate control during the polishing process. At the same time, the synchronous optimization of trajectory and force ensures the uniform movement and stable output of the polishing tool on the complex surface, achieving high efficiency and accuracy in the polishing process.

[0062] This embodiment greatly improves the quality and efficiency of polishing by adaptive control of complex cylinder surfaces and dynamic optimization of chicken swarm optimization algorithm, avoiding the problems of low control accuracy, slow response and path and force disconnection in traditional polishing methods. This method is particularly suitable for complex surfaces and variable processing scenarios, providing an innovative and efficient solution for precision manufacturing and surface treatment of high-quality workpieces.

[0063] Embodiment 3:

[0064] This embodiment demonstrates the application of a chicken swarm optimization (CSO) based end effector polishing control method in high-precision polishing of complex curved surfaces, particularly suitable for polishing of mold surfaces with small features, edge mutations and sharp curvature changes. This method solves the problems of low precision and low efficiency in traditional methods for complex curved surface processing through visual scanning, chicken swarm optimization algorithm and real-time adaptive control. The specific implementation steps are as follows:

[0065] Step 1: 3D model data acquisition and grinding amount calculation: First, use a high-precision visual camera to scan the mold to be polished, and obtain its 3D model data. For the small features, edge mutation areas and complex curvature of the mold surface, use the Iterative Closest Point (ICP) algorithm to align the scanning data with the 3D model of the standard sample. By comparing the surface deviation of the mold to be polished with the standard sample, the system generates the grinding amount and grinding force requirement of each point, forming the polishing basic data. At the same time, a color mapping chart is generated to show the grinding deviation of each area, so as to intuitively present the size and position of the polishing force that needs to be adjusted.

[0066] Step 2: Grinding trajectory planning and optimization: After obtaining the grinding basic data, use the chicken swarm optimization algorithm to optimize the polishing trajectory of the end effector. Specifically, the trajectory planning problem is converted into a constraint solving problem, and constraints including kinematics constraints of the robot arm (such as joint angle, speed and acceleration limits), space obstacle avoidance constraints and objective functions (such as minimizing total energy consumption, total time or trajectory smoothness in the grinding process) are set. The chicken swarm optimization algorithm optimizes the trajectory control points through multiple iterations, divides the population into three categories of roosters, hens and chicks, and dynamically adjusts the control points based on the fitness value to ensure synchronous optimization of path and force control.

[0067] The optimized trajectory can accurately adapt to the irregular surface and complex curvature of the mold, avoiding the problems of inaccuracy and low efficiency caused by the separation of path and force control. For example, in the polishing of edge mutation areas, the system can automatically adjust the path to reduce the problem of insufficient or excessive polishing caused by path deviation, significantly improving the polishing quality.

[0068] Step 3: Real-time self-tuning of PID parameters and optimization of force control: During the polishing process, the chicken swarm optimization algorithm is used to perform real-time self-tuning of the PID parameters of the motor or air cylinder. For example, in the case of complex changes in the mold surface, traditional control methods often fail to control accurately in areas with sudden changes in curvature and uneven hardness, resulting in uneven grinding and surface scratches. The present application monitors the real-time changes in grinding force and grinding amount through a six-axis force sensor and automatically optimizes the PID control parameters (proportional gain Kp, integral gain Ki, and derivative gain Kd) to ensure accurate control in each polishing stage (such as preliminary adjustment and fine adjustment).

[0069] The self-tuning of PID parameters takes system performance indicators such as integral squared error and integral time weighted squared error as the objective function, and the chicken swarm optimization algorithm finds the optimal parameter combination through multiple iterations. Specifically, when the system detects force and position control deviations during the polishing process, the chicken swarm algorithm quickly adjusts the control parameters based on real-time feedback, allowing the end effector to automatically optimize the grinding force based on different regional characteristics. For example, during the polishing of concave or convex parts of the mold, the system can quickly adjust the output force to avoid excessive grinding or insufficient grinding caused by inaccurate force control in traditional methods.

[0070] It will be obvious to a person skilled in the art that the application is not limited to the details of the above exemplary embodiments, but can be implemented in other specific forms without departing from the spirit or essential characteristics of the application. Therefore, the embodiments should be considered exemplary and non-limiting, and the scope of the application is defined by the appended claims rather than the above description, and all changes falling within the meaning and scope of the equivalent elements of the claims are intended to be included in the application.

Claims

1. A method for polishing control of an end effector based on chicken swarm optimization algorithm, characterized in that, The method comprises the following steps: Step 1: Obtain the three-dimensional model data of the workpiece to be polished, scan the surface shape of the workpiece to be polished by a visual camera, obtain its three-dimensional model, and align it with the three-dimensional model of the known standard sample, calculate the grinding amount and grinding force of each point of the workpiece, and realize adaptive control of complex curved surfaces and edge mutation areas; The determination of the grinding force comprehensively considers the hardness of the material, the grinding depth, the grinding tool characteristics and the grinding speed, and determines the grinding force of each point by theoretical formula and empirical parameters; Step 2: The chicken swarm optimization algorithm is used to plan the grinding track, the track planning problem is converted into a constraint solving problem, the kinematic constraints of the mechanical arm, the space obstacle avoidance constraints and the target function of minimizing the total energy consumption, the total time or the smoothness of the track in the grinding process are set, the control points of the polishing track or the path points of the joints of the mechanical arm are optimized, and the dynamic synchronous optimization of force control and track planning is realized; The dynamic synchronous optimization of force control and track planning is realized by multiple iterations of the chicken swarm optimization algorithm to optimize the combination of polishing track control points and PID parameters and realize the shared optimization strategy of path and force control; When the chicken swarm optimization algorithm is used to optimize the grinding track, the individuals are divided into three categories according to the fitness value, i.e. rooster, hen and chick, the polishing track control points are optimized through multiple iterations, and the termination condition is met until the termination condition is met; Step 3: In the polishing process, the PID parameters of the motor or air cylinder are real-time self-tuned using the chicken swarm optimization algorithm, the proportional gain, integral gain and differential gain are automatically optimized, the change of the grinding force and the grinding amount is monitored by the six-dimensional force sensor, the control parameters are dynamically optimized in the preliminary adjustment and fine adjustment stages, and the accuracy and stability of the force and position control in the high dynamic scene are ensured; The PID control process uses the feedback data of the six-dimensional force sensor to calculate the error, outputs the control signal of the motor or air cylinder to real-time adjust the output force and position in the polishing process; The PID parameter self-tuning is evaluated by fitness after each adjustment, and the control system performance is gradually optimized by minimizing the fitness, so that the system maintains the best state in the complex and dynamic polishing environment.

2. The end effector polishing control method based on chicken swarm optimization algorithm according to claim 1, characterized in that, The acquisition of the three-dimensional model data includes scanning the three-dimensional data of the workpiece to be polished by a visual camera, generating grinding deviation values of each region, and constructing a color mapping diagram to display the regions to be polished for adaptive adjustment of the grinding force.

3. The end effector polishing control method based on chicken swarm optimization algorithm according to claim 1, characterized in that, When the chicken swarm optimization algorithm is used for track planning, the optimal path can adapt to irregular surfaces, complex curved surfaces and workpieces with variable shapes to avoid inaccuracy and low efficiency caused by the separation of path and force control.

4. The end effector polishing control method based on chicken swarm optimization algorithm according to claim 1, characterized in that, The target function of the real-time self-tuning of the PID parameters includes integral square error, integral time weighted square error or other control indicators related to system performance, and the PID parameter combination is optimized to realize accurate force control.

5. The end effector polishing control method based on chicken swarm optimization algorithm according to claim 1, characterized in that, The alignment of the three-dimensional model data includes using the iterative closest point (ICP) algorithm to make the three-dimensional scanning data of the workpiece to be polished coincide with the three-dimensional model reference points of the standard sample to accurately calculate the grinding deviation values of each point.

6. The end effector polishing control method based on chicken swarm optimization algorithm according to claim 1, characterized in that, The grinding track planning includes setting joint angle, speed and acceleration limits of the mechanical arm to avoid collision with the workpiece or other equipment during grinding.

Images