Industrial robot control method

Abstract

The invention relates to an industrial robot control method. The industrial robot control method comprises the following steps: S1, initializing a system: setting an initial position coordinate, an attitude angle and a speed of a robot; s2, state acquisition: high-precision position sensors and speed sensors are mounted on a base, arm joints and an end effector of the robot to cover all degrees of freedom of the robot, sensor data including a position Pt and a speed Vt are recorded regularly, and position coordinates and speed of each joint are recorded; and S3, deviation calculation: calculating the ideal position of the robot according to the theoretical model, and extracting the actual position of the robot from the position sensor data. According to the overall system provided by the embodiment of the invention, the improved particle swarm optimization algorithm is introduced, real-time online correction of the positioning deviation of the robot is realized, manual intervention is not needed in the process, the system automatically responds, and it is ensured that the robot can keep high-precision operation performance in various complex environments.

Description

Technical Field

[0001] The present application relates to the technical field of industrial robot control, and in particular to an industrial robot control method. Background Art

[0002] In industrial processing workshops, industrial robots face many challenges. First, the environmental conditions in the workshop are very complex, including high temperature, high humidity, dust, etc., which will affect the performance of the robot. Secondly, the robot's tasks are diverse and complex, and it needs to move between different workstations to perform welding, cutting, handling and other operations. In order to ensure the high-precision operation of the robot, the robot's motion trajectory needs to be accurately controlled, which is the core problem to be solved by this invention.

[0003] Static geometric parameter errors mainly come from the manufacturing process of the robot. In the manufacturing process of the robot, due to the limitation of processing accuracy, joint angle errors, connecting rod length errors, etc. are inevitable. Although these errors are small, they will gradually accumulate when the robot performs long-term or long-distance movements, resulting in positioning deviations. For example, a tiny connecting rod length error may cause the robot to have a large deviation when moving to a certain position. Dynamic non-geometric parameter errors are more complicated. These errors change with time and working conditions, including but not limited to: Changes in friction: The joints of the robot will generate friction during movement. The magnitude of friction is affected by factors such as temperature and lubrication conditions. Over time, the friction will change, thereby affecting the robot's motion characteristics. Motor wear: As the use time increases, the internal components of the motor may wear out, resulting in a decrease in motor performance, which in turn affects the robot's positioning accuracy. Temperature fluctuations: Temperature fluctuations in the workshop will affect the robot's mechanical structure. For example, thermal expansion will change the size of the robot, resulting in positioning deviations. Load changes: When the robot carries loads of different weights, its motion characteristics will also change, which will also affect the robot's positioning accuracy. In order to improve the positioning accuracy of industrial robots and improve workshop operation efficiency, we propose an industrial robot control method. Summary of the invention

[0004] The present application provides an industrial robot control method to solve the above-mentioned problems.

[0005] The present application provides an industrial robot control method, including the following method:

[0006] S1. Initialize the system: set the robot's initial position coordinates, attitude angle and speed;

[0007] S2, state acquisition: Install high-precision position sensors and velocity sensors on the robot's base, arm joints, and end effector to cover all degrees of freedom of the robot, and regularly record sensor data, including position Pt and velocity Vt, and record the position coordinates and velocity of each joint;

[0008] S3, deviation calculation: calculate the ideal position of the robot according to the theoretical model, extract the actual position of the robot from the position sensor data, and calculate the deviation between the ideal position and the actual position;

[0009] S4, Optimization solution: define the search space, including the geometric and non-geometric parameters that need to be corrected, and initialize the particle swarm, each particle represents a set of correction parameters X i , where i = 1, 2, ..., N, N is the number of particles, and the design fitness function F(X i ), is the sum of squares of the deviations, and the particle position X is updated using the improved particle swarm optimization algorithm i and speed V i ;

[0010] S5, correction application: select the particle with the lowest fitness value as the best particle gbest;

[0011] S6, Dynamic Adjustment: Continuously monitor sensor data and deviations, adjust correction parameters based on new sensor data and deviations, and restart the IPSON algorithm for correction if the deviation exceeds the preset threshold;

[0012] S7, check deviation: repeat the steps of state acquisition, deviation calculation, optimization solution, correction application and dynamic adjustment until the positioning accuracy meets the preset requirements or reaches the preset threshold.

[0013] Preferably, the initialization system sets the robot's initial position coordinates (x0, y0, z0) = (0, 0, 0), attitude angle (θ x ,θ y ,θ z )=(0,0,0) and speed V0=0.

[0014] Preferably, the state acquisition includes position data, location data and speed data;

[0015] The position data is specifically regularly recorded sensor data Dt, including position Pt and speed Vt;

[0016] The position data record specifically records the position coordinates of each joint;

[0017] The speed data specifically records the speed of each joint.

[0018] Preferably, the deviation calculation includes theoretical model calculation, actual position acquisition and deviation calculation;

[0019] The theoretical model calculation is specifically to calculate the ideal position P according to the theoretical model. theo (t);

[0020] The actual position acquisition is specifically to extract the actual position P from the sensor data real (t);

[0021] The deviation calculation is specifically to calculate the deviation ΔP(t)=P theo (t)-P real (t);

[0022] Deviation formula:

[0023]

[0024] Where: x theo (t) represents the x-axis coordinate of the ideal position of the robot, x real (t) represents the x-axis coordinate of the robot's actual position, y theo (t) represents the y-axis coordinate of the ideal position of the robot, real (t) represents the y-axis coordinate of the robot’s actual position, z theo (t) represents the z-axis coordinate of the ideal position of the robot, z real (t) represents the z-axis coordinate of the robot’s actual position.

[0025] Preferably, the optimization solution includes defining a search space, geometric parameters, non-geometric parameters, initializing a particle swarm, initializing particles, designing a fitness function, updating a fitness function, updating particle positions and velocities, selecting the best particle, and an iterative termination condition;

[0026] Defining the search space specifically includes defining a search space including geometric and non-geometric parameters that need to be corrected;

[0027] The geometric parameters are specifically the joint angle error δθ and the connecting rod length error δl;

[0028] The non-geometric parameters are specifically the friction coefficient μ and the gravity influence coefficient kg;

[0029] Specifically, each particle of the initialized particle group represents a set of correction parameters Xi, where i=1, 2, ..., N, and N is the number of particles;

[0030] The particle initialization is specifically to randomly generate N=50 particles, each particle contains the correction parameter X i =(δθ, δl, μ, kg);

[0031] The fitness function design is specifically defined as the fitness function F(X i ) is the sum of squares of the deviation ΔP;

[0032] The fitness function is specifically:

[0033] The particle position and velocity update is specifically to use the improved particle swarm optimization algorithm to update the particle position X i and speed V i ;

[0034] Speed ​​update formula:

[0035] V i (t+1)=ω·V i (t)+c1·r1·(pbest i -X i (t))+c2·r2·(gbest i -X i (t))

[0036] Among them: w = 0.7298 is the inertia weight, c1 = c2 = 1.4962 is the acceleration constant, r1 and r2 are random numbers, gbest i represents the best particle, pbest i represents the best position passed by the i-th particle;

[0037] Position update formula:

[0038] X i (t+1)=X i (t)+V i (t+1)

[0039] The optimal particle selection is specifically to select the particle with the lowest fitness value as the optimal particle, that is,

[0040] gbest i =min(F(X i ))

[0041] The iteration termination condition is specifically to stop the iteration when the preset number of iterations T=1000 is reached or the fitness value is lower than the threshold ε=0.001.

[0042] Preferably, the correction application is specifically to apply the correction parameter corresponding to the optimal particle gbest to the control system of the robot, and update the theoretical model according to the correction parameter to reduce the deviation ΔP. The update formula is:

[0043] P theo (t+1)=P theo (t)+ΔP(t)·gbest.

[0044] Preferably, the dynamic adjustment is specifically to continuously monitor the sensor data and deviation, adjust the correction parameter according to the new sensor data and deviation, and restart to perform correction if the deviation is greater than a threshold.

[0045] Preferably, the specific parameters of the inspection deviation are set as follows:

[0046] Inertia weight w = 0.7298, acceleration constant C1 = C2 = 1.4962, number of particles N = 50, number of iterations T = 1000, fitness threshold ε = 0.001, deviation threshold ΔP thres =0.01.

[0047] The above technical solution provided by the embodiment of the present application has the following advantages compared with the prior art:

[0048] The overall system provided in the embodiment of the present application realizes real-time online correction of the robot positioning deviation by introducing an improved particle swarm optimization algorithm (IPSON). This process does not require human intervention, and the system responds automatically, ensuring that the robot can maintain high-precision operating performance in various complex environments.

[0049] On the technical level, the present invention effectively reduces positioning deviations caused by external factors such as mechanical wear, temperature changes, and load changes by monitoring the robot's motion state in real time and dynamically adjusting control parameters. This adaptive correction mechanism not only improves the robot's operating accuracy, but also enhances the robustness of the system, enabling it to quickly adapt to environmental changes and maintain stable operation. In addition, the intelligence of the system is also reflected in its ability to self-optimize based on real-time feedback, continuously learn, and improve the efficiency and accuracy of the correction algorithm.

[0050] In terms of commercial value, the implementation of this invention significantly reduces the operating costs of industrial robots. By reducing dependence on professional technicians and simplifying the calibration process, enterprises can save a lot of manpower and time costs. At the same time, due to the improvement of robot positioning accuracy, material waste and defective rate in the production process are reduced, further improving production efficiency and product quality, and bringing higher economic benefits to the enterprise. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0052] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0053] Figure 1 It is a system flow chart of the present invention. DETAILED DESCRIPTION

[0054] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0055] Various embodiments of the present application may exist in the form of a range. It should be understood that the description in the form of a range is only for convenience and simplicity and should not be understood as a hard limit to the scope of the present application; therefore, it should be considered that the range description has specifically disclosed all possible sub-ranges and single values ​​within the range. For example, it should be considered that the range description from 1 to 6 has specifically disclosed sub-ranges, such as from 1 to 3, from 1 to 4, from 1 to 5, from 2 to 4, from 2 to 6, from 3 to 6, etc., as well as single numbers within the range, such as 1, 2, 3, 4, 5 and 6, which are applicable regardless of the range. In addition, whenever a numerical range is indicated in the present application, it is meant to include any quoted numbers (fractions or integers) within the indicated range. Unless otherwise specified, various raw materials, reagents, instruments and equipment used in the present application, etc., can be purchased from the market or can be prepared by existing equipment.

[0056] In the present application, in the absence of any contrary description, the directional words used, such as "upper" and "lower", are specifically the directions of the drawings in the accompanying drawings. In addition, in the present application, the terms "include", "comprise", etc. refer to "including but not limited to". In the present application, relational terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. In the present application, "and / or" describes the association relationship of the associated objects, indicating that three relationships may exist, for example, A and / or B, which can represent: A exists alone, A and B exist at the same time, and B exists alone. Wherein A, B can be singular or plural. In the present application, "at least one" refers to one or more, and "plural" refers to two or more. "At least one", "at least one of the following" or similar expressions refer to any combination of these items, including any combination of singular items or plural items. For example, "at least one of a, b, or c" or "at least one of a, b and c" can both mean: a, b, c, ab, i.e. a and b, ac, bc or abc, where a, b, c can be single or plural, respectively.

[0057] like Figure 1 As shown: This embodiment of the application provides an industrial robot control method, including the following method:

[0058] S1. Initialize the system: set the robot's initial position coordinates, attitude angle and speed;

[0059] S2, state acquisition: Install high-precision position sensors and velocity sensors on the robot's base, arm joints, and end effector to cover all degrees of freedom of the robot, and regularly record sensor data, including position Pt and velocity Vt, and record the position coordinates and velocity of each joint;

[0060] S3, deviation calculation: calculate the ideal position of the robot according to the theoretical model, extract the actual position of the robot from the position sensor data, and calculate the deviation between the ideal position and the actual position;

[0061] S4, Optimization solution: define the search space, including the geometric and non-geometric parameters that need to be corrected, and initialize the particle swarm, each particle represents a set of correction parameters X i , where i = 1, 2, ..., N, N is the number of particles, and the design fitness function F(X i ), is the sum of squares of the deviations, and the particle position X is updated using the improved particle swarm optimization algorithm i and speed V i ;

[0062] S5, correction application: select the particle with the lowest fitness value as the best particle gbest;

[0063] S6, Dynamic Adjustment: Continuously monitor sensor data and deviations, adjust correction parameters based on new sensor data and deviations, and restart the IPSON algorithm for correction if the deviation exceeds the preset threshold;

[0064] S7, check deviation: repeat the steps of state acquisition, deviation calculation, optimization solution, correction application and dynamic adjustment until the positioning accuracy meets the preset requirements or reaches the preset threshold.

[0065] Preferably, the initialization system sets the robot's initial position coordinates (x0, y0, z0) = (0, 0, 0), attitude angle (θ x ,θ y ,θ z )=(0,0,0) and speed V0=0.

[0066] The state acquisition includes position data, location data and speed data;

[0067] The position data is specifically regularly recorded sensor data Dt, including position Pt and speed Vt;

[0068] The position data record specifically records the position coordinates of each joint;

[0069] The speed data specifically records the speed of each joint.

[0070] The deviation calculation includes theoretical model calculation, actual position acquisition and deviation calculation;

[0071] The theoretical model calculation is specifically to calculate the ideal position P according to the theoretical model. theo (t);

[0072] The actual position acquisition is specifically to extract the actual position P from the sensor data real (t);

[0073] The deviation calculation is specifically to calculate the deviation ΔP(t)=P theo (t)-P real (t);

[0074] Deviation formula:

[0075]

[0076] Where: x theo (t) represents the x-axis coordinate of the ideal position of the robot, x real (t) represents the x-axis coordinate of the robot's actual position, y theo(t) represents the y-axis coordinate of the ideal position of the robot, real (t) represents the y-axis coordinate of the robot’s actual position, z theo (t) represents the z-axis coordinate of the ideal position of the robot, z real (t) represents the z-axis coordinate of the robot’s actual position.

[0077] The optimization solution includes defining search space, geometric parameters, non-geometric parameters, initializing particle swarm, particle initialization, fitness function design, fitness function, particle position and velocity update, optimal particle selection and iteration termination condition;

[0078] Defining the search space specifically includes defining a search space including geometric and non-geometric parameters that need to be corrected;

[0079] The geometric parameters are specifically the joint angle error δθ and the connecting rod length error δl;

[0080] The non-geometric parameters are specifically the friction coefficient μ and the gravity influence coefficient kg;

[0081] Specifically, each particle of the initialized particle group represents a set of correction parameters Xi, where i=1, 2, ..., N, and N is the number of particles;

[0082] The particle initialization is specifically to randomly generate N=50 particles, each particle contains the correction parameter X i =(δθ, δl, μ, kg);

[0083] The fitness function design is specifically defined as the fitness function F(X i ) is the sum of squares of the deviation ΔP;

[0084] The fitness function is specifically:

[0085] The particle position and velocity update is specifically to use the improved particle swarm optimization algorithm to update the particle position X i and speed V i ;

[0086] Speed ​​update formula:

[0087] V i (t+1)=ω·V i (t)+c1·r1·(pbest i -X i (t))+c2·r2·(gbest i -X i (t))

[0088] Among them: w = 0.7298 is the inertia weight, c1 = c2 = 1.4962 is the acceleration constant, r1 and r2 are random numbers, gbest i represents the best particle, pbest i represents the best position passed by the i-th particle;

[0089] Position update formula:

[0090] X i (t+1)=X i (t)+V i (t+1)

[0091] The optimal particle selection is specifically to select the particle with the lowest fitness value as the optimal particle, that is,

[0092] gbest i =min(F(X i ))

[0093] The iteration termination condition is specifically to stop the iteration when the preset number of iterations T=1000 is reached or the fitness value is lower than the threshold ε=0.001.

[0094] The correction application specifically applies the correction parameters corresponding to the optimal particle gbest to the control system of the robot, and updates the theoretical model according to the correction parameters to reduce the deviation ΔP. The update formula is:

[0095] P theo (t+1)=P theo (t)+ΔP(t)·gbest.

[0096] The dynamic adjustment specifically includes continuously monitoring the sensor data and deviation, adjusting the correction parameters according to the new sensor data and deviation, and restarting to perform correction if the deviation is greater than a threshold.

[0097] The specific parameter settings of the inspection deviation are:

[0098] Inertia weight w = 0.7298, acceleration constant C1 = C2 = 1.4962, number of particles N = 50, number of iterations T = 1000, fitness threshold ε = 0.001, deviation threshold ΔP thres =0.01.

[0099] Example:

[0100] For example, we need to locate the robot to a specific location:

[0101] (x target ,y target , z target ) = (1.0, 1.0, 0.5)

[0102] There is a deviation between the ideal position calculated according to the theoretical model and the actual position. By improving the particle swarm optimization algorithm (IPSON), we can adjust the control parameters of the robot in real time to reduce the positioning deviation. The specific steps are as follows:

[0103] Initialize the system: Set the robot's initial position to ((0,0,0) and initialize time t=0.

[0104] The sensor data, including position and speed, is recorded once per second. Assume that at the 5th second, the ideal position calculated according to the theoretical model is ((0.95, 0.98, 0.48), while the actual position read by the sensor is (0.92, 0.94, 0.46), then the deviation is

[0105] Optimization solution: Use the IPSON algorithm to solve the optimal correction parameters. Assume that after 100 iterations, a set of correction parameters is found:

[0106] gbest=(δθ=-0.005, δl=0.003, μ=0.001, kg=0.002)

[0107] Set the fitness function F(gbest) = 0.0005, apply gbest to the robot's control system, update the theoretical model, and continue to monitor the deviation. If the deviation exceeds the threshold ΔP thres =0.01, then restart the IPSON algorithm.

[0108] The above is only a specific implementation of the present application, so that those skilled in the art can understand or implement the present application. It will be apparent to those skilled in the art that various modifications to these embodiments are possible, and the general principles defined in the present application can be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to these embodiments shown in the present application, but will conform to the widest scope consistent with the principles and novel features applied for by the present application.

Claims

1. A method for controlling an industrial robot, characterized in that: The following methods are included: S1. Initialize the system: set the robot's initial position coordinates, attitude angle and speed; S2, state acquisition: Install high-precision position sensors and velocity sensors on the robot's base, arm joints, and end effector to cover all degrees of freedom of the robot, and regularly record sensor data, including position Pt and velocity Vt, and record the position coordinates and velocity of each joint; S3, deviation calculation: calculate the ideal position of the robot according to the theoretical model, extract the actual position of the robot from the position sensor data, and calculate the deviation between the ideal position and the actual position; S4, Optimization solution: define the search space, including the geometric and non-geometric parameters that need to be corrected, and initialize the particle swarm, each particle represents a set of correction parameters X i , where i = 1, 2, ..., N, N is the number of particles, and the design fitness function F(X i ), is the sum of squares of the deviations, and the particle position X is updated using the improved particle swarm optimization algorithm i and speed V i ; S5, correction application: select the particle with the lowest fitness value as the best particle gbest; S6, Dynamic Adjustment: Continuously monitor sensor data and deviations, adjust correction parameters based on new sensor data and deviations, and restart the IPSON algorithm for correction if the deviation exceeds the preset threshold; S7, check deviation: repeat the steps of state acquisition, deviation calculation, optimization solution, correction application and dynamic adjustment until the positioning accuracy meets the preset requirements or reaches the preset threshold.

2. The industrial robot control method according to claim 1, characterized in that: The initialization system sets the robot's initial position coordinates (x0, y0, z0) = (0, 0, 0), attitude angle (θ x ,θ y ,θ z )=(0,0,0) and speed V0=0.

3. The industrial robot control method according to claim 1, characterized in that: The state acquisition includes position data, location data and speed data; The position data is specifically regularly recorded sensor data Dt, including position Pt and speed Vt; The position data record specifically records the position coordinates of each joint; The speed data specifically records the speed of each joint.

4. The industrial robot control method according to claim 1, characterized in that: The deviation calculation includes theoretical model calculation, actual position acquisition and deviation calculation; The theoretical model calculation is specifically to calculate the ideal position P according to the theoretical model. theo (t); The actual position acquisition is specifically to extract the actual position P from the sensor data real (t); The deviation calculation is specifically to calculate the deviation ΔP(t)=P theo (t)-P real (t); Deviation formula: Where: x theo (t) represents the x-axis coordinate of the ideal position of the robot, x real (t) represents the x-axis coordinate of the robot's actual position, y theo (t) represents the y-axis coordinate of the ideal position of the robot, real (t) represents the y-axis coordinate of the robot’s actual position, z theo (t) represents the z-axis coordinate of the ideal position of the robot, z real (t) represents the z-axis coordinate of the robot’s actual position.

5. The industrial robot control method according to claim 1, characterized in that: The optimization solution includes defining search space, geometric parameters, non-geometric parameters, initializing particle swarm, particle initialization, fitness function design, fitness function, particle position and velocity update, optimal particle selection and iteration termination condition; Defining the search space specifically includes defining a search space including geometric and non-geometric parameters that need to be corrected; The geometric parameters are specifically the joint angle error δθ and the connecting rod length error δl; The non-geometric parameters are specifically the friction coefficient μ and the gravity influence coefficient kg; Specifically, each particle of the initialized particle group represents a set of correction parameters Xi, where i=1, 2, ..., N, and N is the number of particles; The particle initialization is specifically to randomly generate N=50 particles, each particle contains the correction parameter X i =(δθ, δl, μ, kg); The fitness function design is specifically defined as the fitness function F(X i ) is the sum of squares of the deviation ΔP; The fitness function is specifically: The particle position and velocity update is specifically to use the improved particle swarm optimization algorithm to update the particle position X i and speed V i ; Speed ​​update formula: V i (t+1)=ω·V i (t)+c1·r1·(pbest i -X i (t))+c2·r2·(gbest i -Xx(t)) Among them: w = 0.7298 is the inertia weight, c1 = c2 = 1.4962 is the acceleration constant, r1 and r2 are random numbers, gbest i represents the best particle, pbest i represents the best position passed by the i-th particle; Position update formula: X i (t+1)=X i (t)+V i (t+1) The optimal particle selection is specifically to select the particle with the lowest fitness value as the optimal particle, that is, gbest i =min(F(X i )) The iteration termination condition is specifically to stop the iteration when the preset number of iterations T=1000 is reached or the fitness value is lower than the threshold ε=0.

001.

6. The industrial robot control method according to claim 1, characterized in that: The correction application specifically applies the correction parameters corresponding to the optimal particle gbest to the control system of the robot, and updates the theoretical model according to the correction parameters to reduce the deviation ΔP. The update formula is: P theo (t+1)=P theo (t)+ΔP(t)·gbest 7. The industrial robot control method according to claim 1, characterized in that: The dynamic adjustment is specifically to continuously monitor the sensor data D t+1 and deviation ΔP, adjust the correction parameters according to the new sensor data and deviation, if the deviation ΔP is greater than the threshold ΔP thres =0.01, restart to make corrections.

8. The industrial robot control method according to claim 1, characterized in that: The specific parameter settings of the inspection deviation are: Inertia weight w = 0.7298, acceleration constant C1 = C2 = 1.4962, number of particles N = 50, number of iterations T = 1000, fitness threshold ε = 0.001, deviation threshold ΔP thres =0.01.

Images