A method and system for automatic control of shearing of ship steel plates

Abstract

The present invention provides a ship steel plate shearing automation control method and system, which relates to the field of artificial intelligence technology. The method includes: generating corresponding mechanical arm motion trajectory and initial instructions for posture adjustment according to coordinate and posture information; controlling the mechanical arm to move to a specified position according to the initial instructions, and performing shearing operations according to preset shearing lines and shearing angles; real-time monitoring of the force, speed and position information during the shearing process, and comparing with the preset parameter range, analyzing the force, speed and position information during the shearing process, and identifying the deviation value during the shearing process; calculating the dynamic adjustment factor according to the size and direction of the deviation value; generating the final adjustment instruction according to the dynamic adjustment factor, and performing shearing operations according to the final adjustment instruction. The present invention can not only improve the shearing accuracy, but also improve the efficiency and fluency of the entire shearing process.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and in particular to an automatic control method and system for shearing of ship steel plates. Background Art

[0002] With the rapid development of the shipbuilding industry, the automation and accuracy of steel plate shearing, as an important part of the shipbuilding process, has received increasing attention. However, in traditional automated control systems, this step is usually simplified when processing shear line and shear angle data. After receiving this data, the system often directly performs coordinate conversion to generate the motion trajectory and posture adjustment instructions of the robot arm. However, this direct data processing method ignores several key issues.

[0003] For example, in actual operation, due to various reasons (such as human input errors, sensor errors, etc.), the cutting line and cutting angle data may have certain errors or irrationality. If the system does not effectively verify these data, then these erroneous data will directly lead to deviations in the motion trajectory and posture adjustment of the robot arm, thereby affecting the cutting accuracy. Summary of the invention

[0004] The technical problem to be solved by the present invention is to provide an automated control method and system for shearing of ship steel plates, which can not only improve the shearing accuracy, but also improve the efficiency and fluency of the entire shearing process.

[0005] In order to solve the above technical problems, the technical solution of the present invention is as follows:

[0006] In a first aspect, a method for automatic control of shearing of ship steel plates is provided, the method comprising:

[0007] Position the steel plate and determine the shear line and shear angle;

[0008] Convert the cutting line and cutting angle data into coordinate and posture information recognized by the robot arm;

[0009] According to the coordinate and posture information, the corresponding robot arm motion trajectory and posture adjustment initial instructions are generated;

[0010] According to the initial instructions, the robot arm is controlled to move to the specified position and perform cutting operations according to the preset cutting line and cutting angle;

[0011] Monitor the force, speed and position information during the shearing process in real time, compare them with the preset parameter range, analyze the force, speed and position information during the shearing process, and identify the deviation value during the shearing process;

[0012] Calculate the dynamic adjustment factor according to the size and direction of the deviation value;

[0013] According to the dynamic adjustment factor, a final adjustment instruction is generated, and the shearing operation is performed according to the final adjustment instruction.

[0014] Furthermore, according to the coordinate and posture information, the corresponding robot arm motion trajectory and posture adjustment initial instructions are generated, including:

[0015] Determine the target coordinates and posture that the robot needs to reach, and randomly initialize a group of particles in the search space. Each particle represents a motion trajectory and posture adjustment plan of the robot. Each particle contains position and velocity attributes, and the position represents the parameters of the motion trajectory.

[0016] Determine a fitness function for evaluating the quality of the trajectory and posture adjustment scheme represented by each particle;

[0017] According to the fitness function, the quality of each particle is evaluated, the position and velocity of each particle are updated, and the steps are repeated for multiple iterations until the preset number of iterations is reached to obtain the robot arm motion trajectory and initial instructions for posture adjustment.

[0018] Furthermore, the calculation formula of the fitness function is:

[0019]

[0020] Among them, α, β and γ are weight coefficients; x t and t are the horizontal and vertical coordinates of the target position respectively; x a and a are the horizontal and vertical coordinates of the actual position reached by the robot arm; d max is the maximum distance the robot can move; θ r is the difference between the actual posture of the robot and the target posture; θ max is the maximum attitude adjustment error; t t is the time required for the robot to complete the journey from the starting position to the target position according to the particle trajectory plan; t max is the preset maximum allowed time; x represents the particle; k2 is the current iteration number, and K1 is the total iteration number.

[0021] Furthermore, when updating the position and velocity of each particle, the velocity update formula is:

[0022]

[0023] Among them, v i (t+1) is the velocity of particle i at time t+1; w start is the initial inertia weight; is an exponential decay function, k is the decay factor, t is the current iteration number; Tmax is the maximum number of iterations; v i (t) is the velocity of particle i at time t; c1 and c2 are coefficients; r1 and r2 are random numbers generated in the range [0, 1]; pbest i is the corresponding position found by the particle during the search process; gbest is the corresponding position found by all particles during the search process; x i (t) is the position of particle i at time t;

[0024] The update formula of position is:

[0025] x i (t+1)=x i (t)+v i (t+1);

[0026] Among them, x i (t+1) is the position of particle i at time t+1.

[0027] Further, according to the initial instruction, the robot arm is controlled to move to a specified position, and a cutting operation is performed according to a preset cutting line and cutting angle, including:

[0028] Parse the initial instructions and extract specific coordinate parameters, cutting line trajectory data and cutting angle;

[0029] Determine the moving path according to the specific coordinate parameters and the current position of the robot arm;

[0030] Generate the motion trajectory of the robot arm according to the moving path and shear line trajectory data;

[0031] According to the shear angle and the direction of the shear line, the posture that needs to be adjusted by the end effector of the robot arm is calculated, and the angles of each joint of the robot arm are determined through the inverse kinematics calculation of the robot arm;

[0032] Send motion instructions to the robotic arm to make it move to the specified position according to the planned path and the motion trajectory of the robotic arm. When the robotic arm reaches the specified position and adjusts its posture, send a cutting instruction to make the end effector of the robotic arm perform the cutting operation according to the preset cutting line and cutting angle.

[0033] Furthermore, according to the specific coordinate parameters and the current position of the robot arm, the moving path is determined, including:

[0034] Define the starting point and target point, create an open list and a closed list, and add the starting point to the open list, where the starting point is the current robot position and the target point is the target position coordinate;

[0035] Define an evaluation function for each node, where a node is a position that the robot can move to;

[0036] In the open list, nodes are continuously selected and examined according to the evaluation function until the target node is found. When the target node is found, the search ends and the path from the starting point to the target point is constructed by backtracking to the previous node.

[0037] Furthermore, according to the size and direction of the deviation value, a dynamic adjustment factor is calculated, including:

[0038] According to the deviation value, Calculate dynamic adjustment factors;

[0039] Wherein, Δ(k3) is the dynamic adjustment factor at sampling time k3; Kp is the proportional gain coefficient; Ki is the integral gain coefficient; represents the cumulative sum of the deviation values ​​from sampling time 0 to sampling time k3; Kd is the differential gain coefficient; e(k3)-e(k3-1) represents the change in the deviation value between two adjacent sampling times; e(k3) is the deviation value at sampling time k3, which represents the difference between the shear position, speed or force monitored in real time and the preset value; a1, b and c are constants.

[0040] In a second aspect, an automatic control system for shearing of ship steel plates is used in the method described, comprising:

[0041] The acquisition module is used to locate the steel plate and determine the cutting line and cutting angle; convert the cutting line and cutting angle data into coordinates and posture information recognized by the robot; generate the corresponding robot arm motion trajectory and posture adjustment initial instructions according to the coordinates and posture information; according to the initial instructions, control the robot arm to move to the specified position and perform the cutting operation according to the preset cutting line and cutting angle;

[0042] The processing module is used to monitor the force, speed and position information during the shearing process in real time, and compare them with the preset parameter range, analyze the force, speed and position information during the shearing process, and identify the deviation value during the shearing process; calculate the dynamic adjustment factor according to the size and direction of the deviation value; generate the final adjustment instruction according to the dynamic adjustment factor, and perform the shearing operation according to the final adjustment instruction.

[0043] According to a third aspect, a computing device includes:

[0044] one or more processors;

[0045] The storage device is used to store one or more programs. When the one or more programs are executed by the one or more processors, the one or more processors implement the method described.

[0046] In a fourth aspect, a computer-readable storage medium stores a program, and when the program is executed by a processor, the method described is implemented.

[0047] The above solution of the present invention includes at least the following beneficial effects:

[0048] This method can significantly improve the shearing accuracy of steel plates by accurately positioning the steel plate and determining the shearing line and shearing angle, combined with real-time monitoring and dynamic adjustment. This improvement in accuracy helps reduce material waste and improve product quality. The automated control system can quickly process data and generate accurate robot arm motion trajectories and posture adjustment instructions, thereby reducing the time for manual intervention and decision-making, and greatly improving production efficiency. By real-time monitoring of the force, speed and position information during the shearing process and comparing them with the preset parameter range, the system can promptly detect and handle abnormal situations, effectively prevent the occurrence of production accidents, and improve the safety of the production process. Based on the real-time monitored data, the system can calculate the dynamic adjustment factor and generate the final adjustment instruction accordingly. This dynamic adjustment mechanism makes the shearing operation more flexible and can better adapt to changes in different steel plate materials and shearing requirements. The automated control system reduces the need for manual operation, thereby reducing labor costs. At the same time, due to the improvement of shearing accuracy and the reduction of material waste, material costs are further reduced. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] Figure 1 It is a flow chart of an automated control method for shearing of ship steel plates provided by an embodiment of the present invention.

[0050] Figure 2 It is a schematic diagram of an automatic control system for shearing of ship steel plates provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0051] The exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in a form and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided in order to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0052] like Figure 1 As shown, an embodiment of the present invention provides an automatic control method for shearing of ship steel plates, the method comprising the following steps:

[0053] Step 11, positioning the steel plate and determining the shear line and shear angle;

[0054] Step 12, converting the cutting line and cutting angle data into coordinate and posture information recognized by the robot arm;

[0055] Step 13, generating the corresponding robot arm motion trajectory and initial posture adjustment instructions according to the coordinate and posture information;

[0056] Step 14, according to the initial instruction, control the robot arm to move to the specified position, and perform the cutting operation according to the preset cutting line and cutting angle;

[0057] Step 15, real-time monitoring of the force, speed and position information during the shearing process, and comparing with the preset parameter range, analyzing the force, speed and position information during the shearing process, and identifying the deviation value during the shearing process;

[0058] Step 16, calculating a dynamic adjustment factor according to the size and direction of the deviation value;

[0059] Step 17: Generate a final adjustment instruction according to the dynamic adjustment factor, and perform a shearing operation according to the final adjustment instruction.

[0060] In an embodiment of the present invention, the method can significantly improve the shearing accuracy of the steel plate by accurately positioning the steel plate and determining the shearing line and shearing angle, combined with real-time monitoring and dynamic adjustment. This improvement in accuracy helps to reduce material waste and improve product quality. The automated control system can quickly process data and generate accurate robot arm motion trajectories and posture adjustment instructions, thereby reducing the time for manual intervention and decision-making, and greatly improving production efficiency. By real-time monitoring of the force, speed and position information during the shearing process and comparing them with the preset parameter range, the system can promptly detect and handle abnormal situations, effectively prevent the occurrence of production accidents, and improve the safety of the production process. Based on the data monitored in real time, the system can calculate the dynamic adjustment factor and generate the final adjustment instruction accordingly. This dynamic adjustment mechanism makes the shearing operation more flexible and can better adapt to changes in different steel plate materials and shearing requirements. The automated control system reduces the need for manual operation, thereby reducing labor costs. At the same time, due to the improvement of shearing accuracy and the reduction of material waste, material costs are further reduced.

[0061] In another preferred embodiment of the present invention, the above step 11 may include:

[0062] Step 111, select an appropriate high-definition camera or laser scanner and ensure that its installation position can fully cover the workbench so as to capture a complete image of the steel plate; label the steel plate or pre-draw lines as specific marks or features, which will be used to assist positioning, and ensure that the lighting conditions in the working area are good to reduce the impact of shadows and reflections on the scanning results. Turn on the high-definition camera or laser scanner to fully scan the steel plate. During the scanning process, the equipment will capture the edges and feature points of the steel plate, including the labels or pre-drawn lines attached to the steel plate, and the camera or scanner will transmit this information to the computer in the form of digital images.

[0063] Step 112, after receiving the image, the computer uses image processing and computer vision algorithms to analyze the image, and identifies the edge and feature points of the steel plate through edge detection and feature extraction technology; uses specific marks or features (such as labels attached to the steel plate or pre-drawn lines) for auxiliary positioning to ensure that the exact position and posture of the steel plate on the workbench are accurately identified to obtain the edge detection result; based on the edge detection result, uses the Hough transform algorithm to extract the outer contour of the steel plate, and fits the extracted contour through a fitting algorithm (such as the least squares method) to obtain an approximate geometric shape, such as a rectangle or an ellipse, representing the position and size of the steel plate; based on the fitted steel plate geometric shape, calculates the specific position coordinates of the steel plate on the workbench (such as the center point coordinates, the coordinates of the four corners, etc.); determines the posture of the steel plate, including the rotation angle and inclination, by analyzing the distribution of feature points and the position of the auxiliary positioning marks.

[0064] Step 113, according to production requirements or design drawings, the lines that need to be cut are marked on the positioned steel plate image, and a graphical user interface (GUI) or dedicated CAD software is used to allow the operator to manually input or adjust the position and angle of the cutting line. Automatic recognition technology (such as edge detection algorithm) can also be used to assist in determining the cutting line. In particular, when cutting is required according to the edge or specific features of the steel plate, the cutting angle can be set by entering a specific angle value or using the rotation tool on the graphical interface.

[0065] For example, a shipbuilding company introduced a high-definition camera system installed above the workbench in the steel plate processing workshop to ensure full coverage of the workbench and capture the complete image of the steel plate. In order to improve positioning accuracy, the staff attached obvious labels to the steel plates to be cut and pre-drew lines on the edges of the steel plates as auxiliary marks for positioning.

[0066] Before starting the scan, the staff ensured that the lighting conditions in the workshop were good to avoid the influence of shadows and reflections on the scanning results. Then, the high-definition camera was turned on to conduct a comprehensive scan of the steel plate. During the scanning process, the camera successfully captured the edges and feature points of the steel plate, as well as the labels and pre-drawn lines attached to the steel plate. This information was transmitted to the computer in real time in the form of digital images.

[0067] After receiving the image, the computer immediately uses image processing and computer vision algorithms to conduct an in-depth analysis of the image. Through edge detection and feature extraction technology, the system successfully identifies the edges and feature points of the steel plate. At the same time, using the labels attached to the steel plate and pre-drawn lines as auxiliary positioning marks, it ensures that the exact position and posture of the steel plate on the workbench are accurately identified.

[0068] After obtaining the edge detection results, the system further uses the Hough transform algorithm to extract the outer contour of the steel plate, and fits the contour through a fitting algorithm (such as the least squares method) to obtain an approximate rectangular geometric shape that represents the position and size of the steel plate. Based on this fitting result, the system accurately calculates the specific position coordinates of the steel plate on the workbench (such as the center point coordinates, the coordinates of the four corners, etc.). At the same time, by analyzing the distribution of feature points and the position of auxiliary positioning marks, the system also determines the posture of the steel plate, including the rotation angle and inclination.

[0069] After accurately positioning the steel plate, the staff marked the lines that need to be cut on the positioned steel plate image according to production requirements or design drawings. An intuitive graphical user interface (GUI) is used to allow the operator to manually enter or adjust the position and angle of the cutting line. To further improve efficiency, the system also provides automatic recognition technology (such as edge detection algorithms) to assist in determining the cutting line, especially when it is necessary to cut according to the edge of the steel plate or specific features. The cutting angle is set by entering a specific angle value or using the rotation tool on the graphical interface.

[0070] In another preferred embodiment of the present invention, the above step 12 may include:

[0071] Step 121, first calibrate the camera to determine the intrinsic and extrinsic parameters of the camera. This includes the parameters of the camera itself, such as focal length, distortion coefficient, and external parameters such as the position and posture of the camera relative to the manipulator. Once the camera calibration is completed, you can prepare for the coordinate transformation. For example, create a transformation matrix to map the coordinates in the image space to the coordinates of the manipulator workspace.

[0072] Step 122, using the calibrated camera parameters and transformation matrix, convert the calibrated shear line coordinates in the image space into the coordinates of the robot workspace. This process needs to ensure that the points in the image correspond to the points in the robot coordinate system one by one. Specifically, the coordinate conversion can be performed by the following steps:

[0073] Extract the coordinates of the cutting line in the image; use the camera intrinsics and extrinsics, as well as the transformation matrix, to transform these image coordinates into 3D coordinates in the robot coordinate system; verify that the transformed coordinates are accurate and ensure that they do reflect the actual position of the cutting line in the robot workspace.

[0074] Step 123, based on the converted shear line coordinates and shear angle, calculate the posture of the end effector of the robot arm (such as scissors or cutting tools). This includes determining the rotation angle, inclination and other parameters of the actuator to ensure that it can align the steel plate in the correct direction and angle for shearing. The specific steps of calculating the posture include:

[0075] Determine the target posture that the end effector of the robot arm needs to achieve based on the direction of the shear line and the shear angle. Use the inverse kinematics algorithm to calculate the robot arm joint angle required to achieve this posture. Verify that the calculated posture and joint angle are accurate to ensure that the robot arm can correctly shear the steel plate according to these parameters.

[0076] Step 124, finally, the converted coordinates and calculated posture information are formatted into instructions that can be understood and executed by the robot control system. These instructions need to include parameters such as target position, speed and acceleration, as well as the posture information of the shearing tool. Specifically, it can be:

[0077] The converted coordinate and posture information is encoded into a format that can be recognized by the robot control system; the necessary speed and acceleration parameters are added to ensure that the robot can move to the target position at the appropriate speed and acceleration. The generated instructions are verified to be correct and then sent to the robot control system for execution. Through the above steps, the shear line coordinates and shear angles in the image space can be converted into instructions that can be recognized and executed by the robot, thereby completing the precise shearing task of the steel plate.

[0078] For example, the high-definition camera was first calibrated using a professional camera calibration tool to determine the camera's internal parameters (such as focal length, distortion coefficient, etc.) and external parameters (the position and posture of the camera relative to the robotic arm). After completing the calibration, the technician created a transformation matrix for subsequent coordinate transformation.

[0079] After marking the cutting line on the steel plate image, the technicians used the calibrated camera parameters and transformation matrix to convert these image coordinates into the coordinates of the robot's workspace. For example, the coordinates of a specific cutting line in the image are (x1, y1) to (x2, y2). After conversion, the three-dimensional coordinate range of this line in the robot's coordinate system is (X1, Y1, Z1) to (X2, Y2, Z2). After the conversion is completed, the technicians verified the accuracy of the converted coordinates by comparing them with the actual steel plate position.

[0080] Based on the converted shear line coordinates and the preset shear angle (e.g. 45 degrees), the technicians determined the target posture of the end effector of the robot arm (a pair of automated scissors). By using the inverse kinematics algorithm, the joint angles required to achieve this posture were calculated.

[0081] Finally, the technicians encode the converted coordinates and calculated posture information into an instruction format that can be recognized by the robot control system. These instructions include the target position, speed and acceleration parameters, as well as the posture information of the shearing tool. For example, a typical instruction may be as follows: "Move to the position (X1, Y1, Z1), move at a speed of V1 and an acceleration of A1, adjust the scissors posture to R1 after arriving, and then perform the shearing operation"; after verifying that the instructions are correct, the technicians send these instructions to the robot control system for execution. Through the above steps, the conversion of the shear line coordinates and shear angles in the image space into precise control instructions for the robot arm was successfully realized, which not only greatly improved the production efficiency of steel plate shearing, but also significantly improved the precision and quality of shearing.

[0082] In a preferred embodiment of the present invention, the above step 13, generating the corresponding robot arm motion trajectory and initial posture adjustment instructions according to the coordinate and posture information, may include:

[0083] Step 131, determine the target coordinates and posture that the robot needs to reach, and randomly initialize a group of particles in the search space, each particle represents a motion trajectory and posture adjustment scheme of the robot, each particle contains position and speed attributes, and the position represents the parameters of the motion trajectory;

[0084] Step 132, determining a fitness function for evaluating the quality of the trajectory and posture adjustment scheme represented by each particle;

[0085] Step 133, evaluate the quality of each particle according to the fitness function, update the position and speed of each particle, repeat the steps, and perform multiple iterations until a preset number of iterations is reached to obtain the robot arm motion trajectory and initial posture adjustment instructions.

[0086] In an embodiment of the present invention, the particle swarm optimization algorithm can find the optimal solution in the entire search space, not just the local optimum, which means that the algorithm can find the trajectory that enables the robot to reach the target coordinates and posture in the most efficient and stable way. Compared with traditional optimization methods, the particle swarm optimization algorithm usually has a faster convergence speed; through multiple iterations and information sharing between particles, the algorithm can quickly approach the optimal solution, thereby shortening the planning time of the robot's motion trajectory and posture adjustment. The particle swarm optimization algorithm does not require a specific form of the problem and can handle complex nonlinear and non-convex optimization problems; this enables the algorithm to cope with various complex robot motion trajectories and posture adjustment requirements. Since the particle swarm optimization algorithm is a population-based search method, it has a low dependence on the initial solution and is not easy to fall into the local optimum. This enhances the robustness of the algorithm in the face of different initial conditions and constraints.

[0087] For example, determine the target coordinates and posture that the robot needs to reach. Then, 50 particles are randomly initialized in the search space, each particle represents a possible robot motion trajectory and posture adjustment scheme. The position attribute of each particle represents the parameters of the motion trajectory, such as path points, speed curves, etc., while the speed attribute is used to adjust these parameters during the search process.

[0088] In order to evaluate the quality of the trajectory and posture adjustment scheme represented by each particle, a fitness function is defined. This function takes into account multiple factors, including the smoothness of the trajectory, execution time, energy consumption, and accuracy of posture adjustment. Through this function, the performance of different particles can be quantitatively compared.

[0089] Next, we started to use the particle swarm optimization algorithm to search for the optimal solution. In each iteration, the quality of each particle was evaluated according to the fitness function, and the position and velocity of each particle were updated accordingly. Through continuous iteration and optimization, the particle swarm gradually converged to the vicinity of the optimal solution. After 100 iterations, the algorithm found a motion trajectory and posture adjustment scheme with excellent performance. This scheme not only ensured that the robot arm could reach the target position quickly and accurately, but also achieved a smooth trajectory and precise posture adjustment.

[0090] In a preferred embodiment of the present invention, the calculation formula of the fitness function is:

[0091]

[0092] Among them, α, β and γ are weight coefficients; x t and t are the horizontal and vertical coordinates of the target position respectively; x a and a are the horizontal and vertical coordinates of the actual position reached by the robot arm; d maxis the maximum distance the robot can move; θ r is the difference between the actual posture of the robot and the target posture; θ max is the maximum attitude adjustment error; t t is the time required for the robot to complete the journey from the starting position to the target position according to the particle trajectory plan; t max is the preset maximum allowed time; x represents the particle; k2 is the current iteration number, and K1 is the total iteration number.

[0093] In the embodiment of the present invention, the fitness function can simultaneously consider the accuracy of the robot arm's arrival position, the accuracy of posture adjustment, and the time efficiency of task completion. This multi-objective optimization method helps to find a motion trajectory and posture adjustment solution with the best overall performance. By adjusting the weight coefficients α, β, and γ, the priorities between different goals can be flexibly set. For example, if the position accuracy is more important, the value of α can be appropriately increased; if the time efficiency is more important, the value of γ can be increased. The term takes into account the iterative process, so that different emphases can be placed at different stages of optimization. As the number of iterations increases, this term will gradually decrease, thus affecting the weight of other terms in fitness evaluation. By introducing d max ,θ max and t max The fitness function takes into account the limitations of the robot's motion and posture adjustment capabilities, thereby ensuring that the generated trajectory and posture adjustment scheme are feasible in practice. This function design helps to find a balance between accuracy and efficiency. For example, accuracy is improved by reducing position errors and posture differences, while the time required to complete the task is reduced by optimizing the motion trajectory.

[0094] In a preferred embodiment of the present invention, when updating the position and velocity of each particle, the velocity update formula is:

[0095]

[0096] Among them, v i (t+1) is the velocity of particle i at time t+1; w start is the initial inertia weight; is an exponential decay function, k is the decay factor, t is the current iteration number; T max is the maximum number of iterations; v i (t) is the velocity of particle i at time t; c1 and c2 are coefficients; r1 and r2 are random numbers generated in the range [0, 1]; pbest i is the corresponding position found by the particle during the search process; gbest is the corresponding position found by all particles during the search process; x i(t) is the position of particle i at time t.

[0097] The update formula of position is:

[0098] x i (t+1)=x i (t)+v i (t+1);

[0099] Among them, x i (t+1) is the position of particle i at time t+1.

[0100] In the embodiment of the present invention, by adjusting the inertia weight w start The coefficients c1 and c2 control the balance between the algorithm's global search (exploring new areas) and local search (deeper search in known promising areas). An exponential decay function is used to adjust the inertia weight so that in the early stages of the search process, particles are able to explore the search space more freely, while in the later stages, as the inertia weight decreases, particles are more inclined to conduct refined searches in local areas. By introducing random numbers r1 and r2, the randomness of the search process is increased, which helps the algorithm escape from the local optimal solution and increases the chance of finding the global optimal solution.

[0101] In a preferred embodiment of the present invention, the above step 14, according to the initial instruction, controls the robot arm to move to the specified position and performs the shearing operation according to the preset shearing line and shearing angle, may include:

[0102] Step 141, parse the initial instruction, extract the specific coordinate parameters, cutting line trajectory data and cutting angle. The initial instruction contains the coordinate parameters of the target position, which may be two-dimensional (x, y) or three-dimensional (x, y, z). The cutting line trajectory data describes the path that the cutting tool should follow. These data are a series of point coordinates. During the parsing process, these trajectory data will be extracted and converted into path instructions that the robot can execute. The cutting angle refers to the angle that the cutting tool should maintain when performing the cutting operation; the system will extract this angle value from the instruction and ensure that it is expressed in units that the robot control system can understand (such as degrees or radians);

[0103] Step 142, determining the moving path according to the specific coordinate parameters and the current position of the robot arm;

[0104] Step 143, generating a motion trajectory of the robot arm according to the moving path and the shear line trajectory data, specifically comprising: integrating the moving path determined in step 142 with the shear line trajectory data, the moving path being the path of the robot arm from the current position to the shearing starting point, and the shear line trajectory data describing the specific path during the shearing process, ensuring that the two paths are continuous in space and logic to avoid jumps or breaks; using a path planning algorithm (such as an interpolation method) to smooth the integrated path to ensure that the robot arm can move smoothly and continuously;

[0105] Step 144, calculating the posture that needs to be adjusted for the end effector of the robotic arm according to the shearing angle and the direction of the shearing line, and determining the angles of each joint of the robotic arm through inverse kinematics calculation of the robotic arm;

[0106] Step 145, sending a motion instruction to the robot arm so that it moves to the specified position according to the planned path and the motion trajectory of the robot arm. When the robot arm reaches the specified position and adjusts its posture, sending a shearing instruction so that the end effector of the robot arm performs a shearing operation according to a preset shearing line and shearing angle, specifically includes:

[0107] The motion trajectory and joint angle calculated in step 143 and step 144 are converted into an instruction format that can be understood by the robot control system, and these instructions are sent to the robot through the control system, so that it starts to move according to the planned path and posture; during the movement of the robot, its position and posture are monitored in real time through sensors and feedback systems. If deviations or errors are found, the instructions are adjusted in time to correct the movement of the robot; when the robot reaches the starting point of shearing and adjusts its posture, its precise position and posture are confirmed by sensors. If fine-tuning is required, additional instructions are sent for precise adjustment; once it is confirmed that the robot is accurately in place, a shearing instruction is sent to the control system. The shearing instruction should include parameters such as shearing speed and shearing depth to ensure the accuracy and efficiency of the shearing operation.

[0108] In an embodiment of the present invention, by parsing the initial instruction and extracting key parameters (such as coordinates, shear line trajectory, shear angle), this process ensures that the robot arm can accurately move to the specified position and operate according to the predetermined shear line and angle. The movement path is determined according to the specific coordinate parameters and the current position of the robot arm, which optimizes the movement efficiency of the robot arm and reduces unnecessary movement and time waste. The movement trajectory of the robot arm is generated by combining the movement path and the shear line trajectory data, which not only ensures the accuracy of shearing, but also makes the movement of the robot arm smoother and more efficient. The posture of the end effector of the robot arm is determined by calculating the shear angle and the direction of the shear line, and the angle of each joint is determined by inverse kinematics calculation. This method ensures the precise execution of the shearing operation while reducing the collision or error that may occur during the movement of the robot arm. The entire process is highly automated, from instruction parsing to the final shearing operation, reducing the need for manual intervention, and improving production efficiency and consistency of operation. The modular design of this method makes it easy to adapt to different robot arm systems and shearing tasks, improving its flexibility and scalability in practical applications.

[0109] In a preferred embodiment of the present invention, the above step 142, determining the moving path according to the specific coordinate parameters and the current position of the robot arm, may include:

[0110] Step 1421, define the starting point and the target point, create an open list and a closed list, and add the starting point to the open list, where the starting point is the current robot arm position and the target point is the target position coordinate;

[0111] Step 1422, defining an evaluation function for each node, where a node is a position to which the robot arm can move;

[0112] Step 1423, in the open list, nodes are continuously selected and examined according to the evaluation function until the target node is found. When the target node is found, the search ends, and a path from the starting point to the target point is constructed by backtracking to the previous node.

[0113] In an embodiment of the present invention, by defining an evaluation function, the algorithm can intelligently select the node that is most likely to lead to the target for investigation, thereby reducing unnecessary searches and improving the efficiency of path planning. The evaluation function usually takes into account the actual cost from the starting point to the current node and the estimated cost from the current node to the target point, so that the optimal path can be gradually approached during the search process, and finally an optimal or approximately optimal path from the starting point to the target point can be found. This method is applicable to different environments and scenarios. As long as a suitable evaluation function and the movement cost between nodes can be defined, an effective path can be found in various complex spaces. The path planning method can be used in combination with other optimization techniques or algorithms. For example, the weights in the evaluation function can be dynamically adjusted to adapt to different optimization goals, or combined with machine learning methods to improve the intelligence and adaptability of path planning. When defining nodes and movement costs, obstacles and collision avoidance can be considered to ensure that the planned path is safe and feasible.

[0114] When applied specifically, the following steps are included:

[0115] Step 1421, define the starting point and the target point, where the starting point is the current position of the robot, and the target point is the final position coordinates that the robot needs to reach. The determination of these two points is based on the specific task requirements and the working environment of the robot. Create an open list and a closed list, where the open list is used to store the nodes to be investigated, and the closed list is used to store the nodes that have been investigated. Add the starting point to the open list, which is the starting point of the search, and subsequent searches will expand outward from this point.

[0116] Step 1422, define an evaluation function for each node (the various positions that the robot can move to), which is used to measure the quality of the node and determines the order in which the nodes are selected and examined during the search process. For example, the evaluation function can be the actual cost from the starting point to the current node (such as moving distance, time, etc.) plus the estimated cost from the current node to the target point (such as straight-line distance). This design is intended to guide the search in a direction that is more likely to lead to the target point and has a lower cost.

[0117] Step 1423, in the open list, continuously select the best nodes for inspection according to the value of the evaluation function. The principle of selection is to select the node with the smallest evaluation function value; inspect the selected node to determine whether it is the target node. If it is, the search ends; if it is not the target node, remove it from the open list and add it to the closed list, then add its adjacent movable nodes to the open list, and calculate the evaluation function values ​​of these adjacent nodes. When the target node is found, construct a path from the starting point to the target point by backtracking the previous node. Starting from the target node, trace back to its previous node in sequence until you return to the starting point, thus forming a complete moving path.

[0118] Assume that the robot arm works in a two-dimensional plane, the starting point coordinates are (0, 0), and the target point coordinates are (10, 10). In step 1421, the starting point is clearly (0, 0) and the target point is (10, 10), an open list and a closed list are created, and the starting point (0, 0) is added to the open list. In step 1422, the evaluation function is defined as F(n) = G(n) + H(n), where G(n) is the Euclidean distance from the starting point to the current node, and H(n) is the Euclidean distance from the current node to the target point.

[0119] In step 1423, first select the node with the smallest evaluation function value from the open list, such as node (1, 1), remove it from the open list and add it to the closed list. Then examine its adjacent nodes, such as (0, 1), (1, 0), (2, 1), (1, 2), etc., add these nodes to the open list and calculate the evaluation function value. Repeat this process until the target node (10, 10) is found. Finally, construct a path by backtracking, for example, a possible path is (0, 0) → (1, 1) → (2, 2) → ... → (10, 10).

[0120] The above step 144 may include:

[0121] Extract the shear angle (denoted as θ) and the direction vector of the shear line (denoted as d) from the previous step; ensure that the shear line direction vector d is a unit vector, if not, normalize it by dividing by its magnitude.

[0122] Based on the shear angle θ and the shear line direction d, a posture matrix (or rotation matrix) R can be constructed, which describes the rotation of the end effector from the default posture to the target posture. If the shear line is on a two-dimensional plane, the rotation matrix is ​​a 2×2 matrix; if it is in three-dimensional space, it is a 3×3 matrix; the rotation matrix R is used to transform the default posture of the end effector to obtain its proper posture. This transformation involves rotating the coordinate system of the end effector so that it is consistent with the direction of the shear line and the shear plane is perpendicular to the shear line.

[0123] Among them, in the two-dimensional plane, if the shear angle is θ, the shear line direction vector is and Then the formula of the rotation matrix R is:

[0124] In three-dimensional space, if the shear angle is θ, the shear line direction vector is and Then the rotation matrix R can be calculated by the Rodriguez rotation formula, which is:

[0125] R=I+sinθK+(1-cosθ)K 2 ; Where I is the identity matrix, K is the shear line direction vector The antisymmetric matrix formed is:

[0126]

[0127] The calculated position and posture of the end effector (including position coordinates and rotation matrix R) are used as input data for inverse kinematics calculation; the inverse kinematics equation of the robot is established according to the DH parameters (Denavit-Hartenberg parameters) of the robot; the Newton-Raphson method is used to solve the inverse kinematics equation; an initial guess value is set (which can be the current joint angle of the robot), and then iteratively solved until the joint angle that meets the position and posture requirements of the end effector is found. The solved joint angle is output as the result, and these joint angles are sent to the control system of the robot to move the robot to the specified position and posture for shearing operation; the specific calculation process is as follows:

[0128] The inverse kinematics equation of the robot arm can be established according to its DH parameters (Denavit-Hartenberg parameters) in the following way:

[0129] Assume that the robot has n joints and the joint variables are θ1, θ2, …, θ n , the position coordinates of the end effector are (x, y, z) and the rotation matrix is ​​R.

[0130] For each joint, the transformation matrix A can be obtained according to the DH parameters i , then the transformation matrix T of the end of the robot arm relative to the base is: T = A1A2…A n ; expand it into position and attitude form:

[0131] Among them, (p x ,p y ,p z ) is the position coordinate of the end effector; (n x ,ny ,n z ), (o x ,o y ,o z ),(a x ,a y ,a z ) is the attitude direction vector of the end effector.

[0132] Given the desired position and posture of the end effector, the following equation is established:

[0133]

[0134] This is the inverse kinematics equation for the robotic arm.

[0135] Next is the specific process of solving the inverse kinematics equations using the Newton-Raphson method:

[0136] Assume that the initial guess of the joint angle is Define function F(θ)=[f1(θ),f2(θ),f3(θ),g1(θ),g2(θ),g3(θ),h1(θ),h2(θ),h3(θ),k1(θ),k2(θ),k3(θ)] T , where, θ=[θ1,θ2,…,θ n ] T .

[0137] Then the iteration formula of the Newton-Raphson method is: θ k+1 =θ k -J(θ k ) -1 F(θ k ), where J(θ) is the Jacobian matrix of F(θ). In each iteration, F(θ k ) and J(θ k ), then update the joint angle θ k+1 .

[0138] Repeat this process until F(θ k ) is small enough, that is, it meets the requirements of the end effector position and posture. At this time, θ k This is the desired joint angle.

[0139] For example, assuming a simple 2-joint robotic arm, its inverse kinematics equation is: Then the function F(θ) is:

[0140] F(θ)=x-(l1cosθ1+l2cos(θ1+θ2))y-(l1sinθ1+l2sin1+θ2));

[0141] The Jacobian matrix J(θ) is:

[0142]

[0143] Given an initial guess Perform iterative calculations until a joint angle that meets the requirements is found.

[0144] In a preferred embodiment of the present invention, the above step 15 may include:

[0145] Step 151, during the shearing operation performed by the robotic arm, corresponding sensors are installed to obtain force, speed and position information in real time. For force monitoring, force sensors can be installed on the end effector or shearing tool of the robotic arm. These force sensors can measure the magnitude of the force applied during the shearing process. Speed ​​monitoring can be achieved by installing encoders or speed measuring devices at the joints of the robotic arm. They can measure the rotation speed of the joints and then calculate the moving speed of the end effector of the robotic arm. The acquisition of position information can rely on position sensors, such as laser rangefinders, GPS positioning devices, or machine vision-based position detection systems to accurately determine the position of the end effector of the robotic arm in space.

[0146] Step 152, after obtaining these real-time information, compare them with the preset parameter range. The preset parameter range is a standard range set in advance according to the requirements of the shearing operation and the performance of the robot arm. For example, the preset force range may be 100-200 Newtons, the speed range may be 0.5-1 m / s, and the position accuracy requirement may be within ±1 mm. Then, the actual force, speed and position information collected are analyzed. The deviation between the actual value and the preset range is calculated. For example, if the actual force is 80 Newtons and the preset range is 100-200 Newtons, the deviation value of the force is -20 Newtons, indicating that the force is too small. If the actual speed is 0.3 m / s, the preset speed range is 0.5-1 m / s, and the speed deviation value is -0.2 m / s, which means that the speed is lower than the preset standard. The calculation of the position deviation is similar, and the deviation value is determined by comparing the actual position with the preset ideal position. Through such real-time monitoring and comparative analysis, abnormal conditions in the shearing process can be discovered in time so that corresponding adjustment measures can be taken to ensure the accuracy and stability of the shearing operation.

[0147] In a preferred embodiment of the present invention, the above step 16, calculating the dynamic adjustment factor according to the size and direction of the deviation value, may include:

[0148] Step 161, according to the deviation value, by Calculate dynamic adjustment factors;

[0149] Wherein, Δ(k3) is the dynamic adjustment factor at sampling time k3; Kp is the proportional gain coefficient; Ki is the integral gain coefficient; represents the cumulative sum of the deviation values ​​from sampling time 0 to sampling time k3; Kd is the differential gain coefficient; e(k3)-e(k3-1) represents the change in the deviation value between two adjacent sampling times; e(k3) is the deviation value at sampling time k3, which represents the difference between the shear position, speed or force monitored in real time and the preset value; a1, b and c are constants.

[0150] In an embodiment of the present invention, by comprehensively considering the current deviation, deviation change and cumulative deviation, the dynamic adjustment factor can more accurately reflect the real-time state of the system, thereby adjusting the control output and improving the control accuracy. The calculation of the dynamic adjustment factor includes three parts: proportional, integral and differential, which correspond to the current state, historical cumulative state and change trend of the system respectively. By reasonably adjusting the three gain coefficients Kp, Ki and Kd, as well as constants a, b and c, the system can be made more stable and overshoot and oscillation can be reduced. Since the dynamic adjustment factor is calculated based on the real-time deviation and its change trend, the system can automatically adapt to different working conditions and external environmental changes, and has a certain degree of adaptive ability. By introducing the differential term Kd×(e(k3)-e(k3-1)), the system can respond to changes in deviation more quickly and improve the dynamic performance of the system. Integral term The cumulative sum of deviations from the initial moment to the current moment is taken into account, which helps to eliminate the static error of the system and improve the accuracy of long-term operation.

[0151] In another preferred embodiment of the present invention, the above step 17 may include:

[0152] Step 171, calculate the dynamic adjustment factor Δ(k3) according to the formula described in step 16. This factor combines the current deviation, the change in deviation and the cumulative deviation, and provides an important basis for the generation of adjustment instructions. Next, based on the calculated dynamic adjustment factor Δ(k3), combined with the control logic, the final adjustment instruction is generated. This instruction will be used to guide the shearing operation to ensure the accuracy of the shearing position. The adjustment instruction involves multiple parameters, such as shearing speed, shearing force, shearing position, etc., depending on the characteristics and requirements of the controlled system. According to the generated adjustment instruction, the control system will drive the shearing equipment (such as shearing machine, cutter, etc.) to perform corresponding operations. For example, if the dynamic adjustment factor indicates that the shearing speed needs to be increased, the control system will increase the operating speed of the shearing machine; if the shearing force needs to be reduced, the control system will adjust the force control device accordingly. Among them, the control logic can specifically include the following contents:

[0153] If the dynamic adjustment factor is positive, it indicates that certain parameters (such as shear speed, force, etc.) need to be increased; if the dynamic adjustment factor is negative, it indicates that certain parameters need to be reduced; based on the size of the dynamic adjustment factor, the system determines the specific adjustment amount. For example, if the dynamic adjustment factor is large, the adjustment amount may also be correspondingly large. The system will combine preset rules (such as maximum speed limit, acceleration limit, etc.) to ensure that the generated adjustment instructions are within a safe range. These rules may also include preventing mechanical overload, maintaining smooth operation, etc. Based on the above analysis and calculations, the system ultimately generates one or more specific adjustment instructions, including specific operations such as "increase the shear speed by 10%", "move the shear position 0.5mm to the left", etc.

[0154] For example, assume that in a shearing operation, the preset shearing speed is 2 m / s, the shearing force is 150 N, and the ideal shearing position is (50, 50) mm.

[0155] In real-time monitoring, the current deviations are as follows:

[0156] The current shear speed is 1.5 m / s, and the speed deviation is -0.5 m / s; the shear force is 120 Newtons, and the force deviation is -30 Newtons; the current shear position is (48, 52) mm, and the position deviation is -2 mm in the x direction and 2 mm in the y direction.

[0157] The variation of the deviation is:

[0158] The speed deviation decreased at a rate of -0.1 m / s over the past period of time, the force deviation decreased at a rate of -5 N / s, the position deviation changed at a rate of -0.5 mm / s in the x direction and 0.3 mm / s in the y direction. In terms of cumulative deviations, the cumulative speed deviation is -2 m / s, the cumulative force deviation is -60 N, the cumulative position deviation is -8 mm in the x direction, and 6 mm in the y direction. Combining these deviations, deviation changes and cumulative deviations, the dynamic adjustment factor is calculated to be -0.3.

[0159] According to the control logic, some parameters need to be reduced because the dynamic adjustment factor is negative.

[0160] In terms of specific adjustment amounts, considering the size of the dynamic adjustment factor, the system determines to reduce the shear speed by 5%, reduce the shear force by 10 Newtons, move the shear position 1 mm to the right in the x direction, and move 1 mm downward in the y direction. The final generated adjustment instructions are:

[0161] "Reduce shear speed by 5%", "Reduce shear force by 10 Newtons", "Move shear position 1 mm to the right", "Move shear position 1 mm downward". After receiving these instructions, the control system adjusts the operating parameters of the shearing equipment accordingly to improve the accuracy of the shearing position.

[0162] like Figure 2 As shown, an embodiment of the present invention further provides a ship steel plate shearing automatic control system 20, comprising:

[0163] The acquisition module 21 is used to locate the steel plate and determine the cutting line and cutting angle; convert the cutting line and cutting angle data into coordinates and posture information recognized by the robot; generate the corresponding robot arm motion trajectory and posture adjustment initial instructions according to the coordinates and posture information; according to the initial instructions, control the robot arm to move to the specified position and perform the cutting operation according to the preset cutting line and cutting angle;

[0164] The processing module 22 is used to monitor the force, speed and position information during the shearing process in real time, and compare them with the preset parameter range, analyze the force, speed and position information during the shearing process, and identify the deviation value during the shearing process; calculate the dynamic adjustment factor according to the size and direction of the deviation value; generate the final adjustment instruction according to the dynamic adjustment factor, and perform the shearing operation according to the final adjustment instruction.

[0165] It should be noted that the system is a system corresponding to the above method, and all implementation methods in the above method embodiment are applicable to this embodiment and can achieve the same technical effect.

[0166] The embodiment of the present invention further provides a computing device, comprising: a processor, a memory storing a computer program, wherein when the computer program is executed by the processor, the method described above is executed. All implementations in the above method embodiment are applicable to this embodiment and can achieve the same technical effect.

[0167] The embodiment of the present invention also provides a computer-readable storage medium storing instructions, which, when executed on a computer, enable the computer to execute the method described above. All implementations in the above method embodiment are applicable to this embodiment and can achieve the same technical effect.

[0168] The above is a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A ship steel plate shearing automation control method, characterized in that: The method comprises: Position the steel plate and determine the shear line and shear angle; Convert the cutting line and cutting angle data into coordinate and posture information recognized by the robot arm; According to the coordinate and posture information, the corresponding robot arm motion trajectory and posture adjustment initial instructions are generated; According to the initial instructions, the robot arm is controlled to move to the specified position and perform cutting operations according to the preset cutting line and cutting angle; Monitor the force, speed and position information during the shearing process in real time, compare them with the preset parameter range, analyze the force, speed and position information during the shearing process, and identify the deviation value during the shearing process; Calculate the dynamic adjustment factor according to the size and direction of the deviation value; According to the dynamic adjustment factor, the final adjustment instruction is generated, and the shearing operation is performed according to the final adjustment instruction; according to the coordinate and posture information, the corresponding robot arm motion trajectory and posture adjustment initial instruction are generated, including: Determine the target coordinates and posture that the robot needs to reach, and randomly initialize a group of particles in the search space. Each particle represents a motion trajectory and posture adjustment plan of the robot. Each particle contains position and velocity attributes, and the position represents the parameters of the motion trajectory. Determine a fitness function for evaluating the quality of the trajectory and posture adjustment scheme represented by each particle; According to the fitness function, the quality of each particle is evaluated, the position and speed of each particle are updated, and the steps are repeated for multiple iterations until the preset number of iterations is reached to obtain the robot arm motion trajectory and initial instructions for posture adjustment; the calculation formula of the fitness function is: Among them, α, β and γ are weight coefficients; x t and t are the horizontal and vertical coordinates of the target position respectively; x a and a are the horizontal and vertical coordinates of the actual position reached by the robot arm; d max is the maximum distance the robot can move; θ r is the difference between the actual posture of the robot and the target posture; θ max is the maximum attitude adjustment error; t t is the time required for the robot to complete the journey from the starting position to the target position according to the particle trajectory plan; t max is the preset maximum allowed time; x represents the particle; k2 is the current number of iterations, and K1 is the total number of iterations; when updating the position and velocity of each particle, the velocity update formula is: Among them, v i (t+1) is the velocity of particle i at time t+1; w start is the initial inertia weight; is an exponential decay function, k is the decay factor, t is the current iteration number; T max is the maximum number of iterations; v i (t) is the velocity of particle i at time t; c1 and c2 are coefficients; r1 and r2 are random numbers generated in the range [0, 1]; pbest i is the corresponding position found by the particle during the search process; gbest is the corresponding position found by all particles during the search process; x i (t) is the position of particle i at time t; The update formula of position is: x i (t+1)=x i (t)+v i (t+1); Among them, x i (t+1) is the position of particle i at time t+1; according to the initial instruction, the robot arm is controlled to move to the specified position and perform the shearing operation according to the preset shearing line and shearing angle, including: Parse the initial instructions and extract specific coordinate parameters, cutting line trajectory data and cutting angle; Determine the moving path according to the specific coordinate parameters and the current position of the robot arm; Generate the motion trajectory of the robot arm according to the moving path and shear line trajectory data; According to the shear angle and the direction of the shear line, the posture that needs to be adjusted by the end effector of the robot arm is calculated, and the angles of each joint of the robot arm are determined through the inverse kinematics calculation of the robot arm; Send motion instructions to the robot arm to make it move to the specified position according to the planned path and the motion trajectory of the robot arm. When the robot arm reaches the specified position and adjusts its posture, send a cutting instruction to make the end effector of the robot arm perform the cutting operation according to the preset cutting line and cutting angle; determine the moving path according to the specific coordinate parameters and the current position of the robot arm, including: Define the starting point and target point, create an open list and a closed list, and add the starting point to the open list, where the starting point is the current robot position and the target point is the target position coordinate; Define an evaluation function for each node, where nodes are the positions the robot can move to; In the open list, nodes are continuously selected and examined according to the evaluation function until the target node is found. When the target node is found, the search ends, and the path from the starting point to the target point is constructed by backtracking the previous node; according to the size and direction of the deviation value, the dynamic adjustment factor is calculated, including: According to the deviation value, Calculate dynamic adjustment factors; Wherein, Δ(k3) is the dynamic adjustment factor at sampling time k3; Kp is the proportional gain coefficient; Ki is the integral gain coefficient; represents the cumulative sum of the deviation values ​​from sampling time 0 to sampling time k3; Kd is the differential gain coefficient; e(k3)-e(k3-1) represents the change in the deviation value between two adjacent sampling times; e(k3) is the deviation value at sampling time k3, which represents the difference between the shear position, speed or force monitored in real time and the preset value; a1, b and c are constants.

2. An automatic control system for shearing of ship steel plates, characterized in that: Applied in the method as claimed in claim 1, comprising: The acquisition module is used to locate the steel plate and determine the cutting line and cutting angle; convert the cutting line and cutting angle data into coordinates and posture information recognized by the robot; generate the corresponding robot arm motion trajectory and posture adjustment initial instructions according to the coordinates and posture information; according to the initial instructions, control the robot arm to move to the specified position and perform the cutting operation according to the preset cutting line and cutting angle; The processing module is used to monitor the force, speed and position information during the shearing process in real time, and compare them with the preset parameter range, analyze the force, speed and position information during the shearing process, and identify the deviation value during the shearing process; calculate the dynamic adjustment factor according to the size and direction of the deviation value; generate the final adjustment instruction according to the dynamic adjustment factor, and perform the shearing operation according to the final adjustment instruction.

3. A computing device, characterized in that: include: one or more processors; A storage device, used for storing one or more programs, when the one or more programs are executed by the one or more processors, the one or more processors implement the method as claimed in claim 1.

4. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a program, which implements the method according to claim 1 when executed by a processor.

Images