Production line intelligent clamp control method and system

Abstract

The invention relates to the field of production line intelligent clamp control, and discloses a production line intelligent clamp control method and system, and the method comprises the steps: collecting the 3D point cloud data of a workpiece, calculating the geometric features and shape errors of the workpiece through a point cloud processing algorithm, predicting and optimizing the clamping force, and optimizing the clamp task switching through combining PID control and a Q learning algorithm; compared with the prior art that the traditional fixture control method mostly depends on manual adjustment of the position and the clamping force of the fixture, the requirements of high precision and rapid adaptation are difficult to meet when the requirements of complex workpiece shapes and diversified operation are met, and particularly, the requirements of high precision and rapid adaptation are not met under the conditions that the shapes of workpieces are irregular and the surfaces have large errors. In order to solve the technical problem that the production efficiency is low due to the fact that a traditional method cannot efficiently adjust a clamp, clamping points are accurately selected through visual detection, workpiece form changes are automatically adapted, and the production efficiency of a production line and the workpiece clamping precision are remarkably improved.

Description

Technical Field

[0001] This invention belongs to the field of intelligent fixture control for production lines, and particularly relates to an intelligent fixture control method and system for production lines. Background Technology

[0002] Currently, intelligent fixture control methods for production lines have certain shortcomings. For example, traditional fixture control systems mostly rely on manual settings and adjustments, and cannot flexibly adjust in real time according to the actual shape, size, weight, and other factors of the workpiece. Existing technologies mainly use manual or preset clamping forces and clamping points, resulting in low clamping accuracy and an inability to effectively handle situations with complex workpiece shapes and large shape errors. Especially in environments with frequent task switching and diverse workpiece types on the production line, existing technologies cannot fully meet the demands for high precision and high efficiency. Therefore, there is an urgent need for an intelligent fixture control method that can automatically adapt to the geometric shape and shape errors of the workpiece. Even with different workpiece shapes and large surface errors, it should still be able to accurately predict clamping forces and adjust fixture positions through visual inspection, 3D point cloud processing, and machine learning models. This would improve the automation level, work efficiency, and fixture adaptability of the production line, ensure stable workpiece clamping during the production process, and reduce human error. Summary of the Invention

[0003] To address the aforementioned technical shortcomings, the purpose of this invention is to propose an intelligent fixture control method for production lines. This method aims to solve the problem that traditional fixture control methods in the prior art mostly rely on manually adjusting the position and clamping force of the fixture. This makes it difficult to meet the requirements of high precision and rapid adaptation when facing complex workpiece shapes and diverse operational needs. In particular, under conditions where the workpiece shape is irregular and the surface has large errors, traditional methods cannot efficiently adjust the fixture, resulting in low production efficiency.

[0004] To solve the above-mentioned technical problems, the present invention adopts the following technical solution: The present invention provides a method for controlling intelligent fixtures in production lines. The intelligent fixture control method for the production line includes: Step S10: Use a laser scanner to acquire the first set of 3D point cloud data of the workpiece operated by the intelligent fixture on the production line, and use the point cloud processing algorithm to calculate the geometric feature value of the workpiece, the position information of the workpiece and the shape error value of the workpiece. Step S20: Based on the workpiece shape error value, remove uneven areas to obtain the second set of 3D point cloud data. Based on the visual intelligence algorithm, perform plane fitting on the second set of 3D point cloud data to obtain candidate clamping points, and select the candidate clamping point with the lowest workpiece shape error value to obtain the optimized clamping point. Step S30: Based on the optimized clamping point, combined with the workpiece geometric feature value, workpiece position information, workpiece shape error value, and historical clamping force data, a clamping force prediction model is constructed to predict the optimized clamping force; Step S40: Monitor the workpiece offset during the clamping process in real time using visual inspection method, and adjust the fixture position in combination with PID control algorithm; Step S50: After the current clamping task is completed, the Q-learning method is used to switch clamping tasks and optimize the initial adjustment parameters of the clamp for the next clamping task.

[0005] Preferably, in step S10, the formula for calculating the workpiece shape error value is:

[0006] in, For point The workpiece shape error value at that location, For the first set of 3D point cloud data, the first point on the workpiece surface The height of each point For point The average height of points on the workpiece surface within a local area of ​​a preset size. For point The number of points within a local area of ​​a preset size. For point The magnitude of the normal vector at that point.

[0007] Preferably, in step S20, the step of obtaining candidate clamping points by performing plane fitting on the second set of 3D point cloud data based on the visual intelligence algorithm specifically includes: the visual intelligence algorithm specifically adopts the random sampling consensus algorithm, and the fitting plane adopts the formula... ,in, For three-dimensional coordinate variables, To fit the normal vector components of the plane, To fit the distance from the plane to the point, .

[0008] Preferably, in step S10, the geometric features of the workpiece are calculated using the first 3D point cloud data of the workpiece combined with the minimum bounding rectangle method, and the calculation formula is as follows: ,in, The length of the workpiece, This represents the maximum value in the X-axis direction. This is the minimum value in the X-axis direction; The width of the workpiece. This represents the maximum value in the Y-axis direction. This is the minimum value in the Y-axis direction; The height of the workpiece. This represents the maximum value in the Z-axis direction. It is the minimum value in the Z-axis direction.

[0009] Preferably, in step S30, the clamping force prediction model is constructed using the random forest algorithm, employing the formula: curvature, history ,in, To optimize the clamping force, To optimize the clamping point, This refers to the preset number of decision trees in the random forest algorithm used. () is the first The output of the decision tree is: curvature is the workpiece shape error value, and history is the historical clamping force data.

[0010] Preferably, step S40, which involves real-time monitoring of the workpiece's offset during the clamping process using visual inspection, includes: The second set of 3D point cloud data was processed using Python's OpenCV library. Use the PyTorch deep learning object detection model YOLO to identify the positional offset of the workpiece; The offset is calculated based on the predicted and actual locations.

[0011] Preferably, in step S50, the Q-learning method uses the formula:

[0012] in, For state The updated Q value corresponding to the next action A is executed. A represents the state variables of the current workpiece's optimized clamping force, optimized clamping point, and workpiece geometric feature values; A represents the adjustment actions that the fixture needs to perform. For state The Q value of the next action A is used to represent the optimality measure of task switching; To determine the degree of influence of the newly learned Q-value on the old value, For the reward function, As a discount factor, For the next state The maximum Q value.

[0013] The present invention also provides an intelligent fixture control system for production lines, comprising: The data acquisition module is used to acquire the first set of 3D point cloud data of the workpiece operated by the intelligent fixture on the production line using a laser scanner, and to calculate the workpiece geometric feature value, workpiece position information and workpiece shape error value using a point cloud processing algorithm. The clamping point selection module is used to determine and eliminate uneven areas based on the workpiece shape error value to obtain a second set of 3D point cloud data. Based on the visual intelligence algorithm, the second set of 3D point cloud data is fitted to a plane to obtain candidate clamping points, and the candidate clamping point with the lowest workpiece shape error value is selected to obtain the optimized clamping point. The clamping force prediction module is used to build a clamping force prediction model based on the optimized clamping point, workpiece geometric feature value, workpiece position information, workpiece shape error value, and historical clamping force data, and predict the optimized clamping force. The clamping process offset monitoring and adjustment module is used to monitor the workpiece offset in real time during the clamping process through visual inspection and adjust the clamp position in combination with PID control algorithm; The task switching optimization module is used to monitor the workpiece's offset during the clamping process in real time using visual inspection and to adjust the fixture position using a PID control algorithm.

[0014] The present invention also provides a computer program product, including a production line intelligent fixture control program, which, when executed by a processor, implements the production line intelligent fixture control method.

[0015] The beneficial effects of this invention are as follows: Compared with the prior art, traditional clamp control methods mostly rely on manually adjusting the position and clamping force of the clamp. When faced with complex workpiece shapes and diverse operational needs, it is difficult to meet the requirements of high precision and rapid adaptation. Especially under the condition of irregular workpiece shape and large surface error, traditional methods cannot efficiently adjust the clamp, resulting in low production efficiency. Since this application uses high-precision visual inspection technology, the system can acquire the geometric features and shape error of the workpiece in real time, accurately calculate the most suitable clamping point, avoid the instability of manually selecting the clamping point in the traditional method, and ensure precise control of the clamping force. This application can automatically adjust the clamping point and clamping force even when the workpiece shape varies and the surface error is large. This automatic adaptability enables the production line to handle a wider variety of workpiece types, significantly improving the flexibility and adaptability of the production line; Because of the precise selection of clamping force and clamping point in this application, the problem of frequent fixture adjustments required in traditional methods is avoided. The production line can achieve faster and more stable workpiece clamping, thereby significantly reducing downtime and manual intervention in the production process and improving production efficiency.

[0016] In summary, this invention, through visual inspection technology and automated fixture control, not only improves the accuracy of fixture adjustment, but also solves the problems of poor adaptability and low efficiency of traditional methods when dealing with complex workpieces, significantly improving the production efficiency of the production line and the workpiece clamping accuracy. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 This is a flowchart illustrating the first embodiment of an intelligent fixture control method for a production line according to the present invention.

[0019] Figure 2 This is a schematic diagram of an equipment for a production line intelligent fixture control method according to the present invention. Detailed Implementation

[0020] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0021] Example 1: As Figure 1 The diagram shown is a flowchart of the first embodiment of the intelligent fixture control method for production lines of the present invention, which presents the first embodiment of the intelligent fixture control method for production lines of the present invention.

[0022] In the first embodiment, the intelligent fixture control method for the production line includes: Step S10: Use a laser scanner to acquire the first set of 3D point cloud data of the workpiece operated by the intelligent fixture on the production line, and use the point cloud processing algorithm to calculate the geometric feature value of the workpiece, the position information of the workpiece and the shape error value of the workpiece. It should be noted that in step S10, the formula for calculating the workpiece shape error value is as follows:

[0023] in, For point The workpiece shape error value at that location, For the first set of 3D point cloud data, the first point on the workpiece surface The height of each point For point The average height of points on the workpiece surface within a local area of ​​a preset size. For point The number of points within a local area of ​​a preset size. For point The magnitude of the normal vector at the specified location. In step S10, the geometric features of the workpiece are calculated using the first 3D point cloud data of the workpiece combined with the minimum bounding rectangle method. The calculation formula is as follows: ,in, The length of the workpiece, This represents the maximum value of the workpiece in the X-axis direction. This represents the minimum value of the workpiece in the X-axis direction; The width of the workpiece. This represents the maximum value of the workpiece in the Y-axis direction. This represents the minimum value of the workpiece in the Y-axis direction. The height of the workpiece. This represents the maximum value of the workpiece in the Z-axis direction. This is the minimum value of the workpiece in the Z-axis direction.

[0024] It should be understood that during the plane fitting process, the surface shape of the workpiece is accurately reconstructed through the calculation of the normal vector and error analysis. By calculating the error at each workpiece point, the clamping point can be selected more scientifically.

[0025] Step S20: Based on the workpiece shape error value, remove uneven areas to obtain the second set of 3D point cloud data. Based on the visual intelligence algorithm, perform plane fitting on the second set of 3D point cloud data to obtain candidate clamping points, and select the candidate clamping point with the lowest workpiece shape error value to obtain the optimized clamping point. It should be noted that in step S20, the step of obtaining candidate clamping points by performing plane fitting on the second set of 3D point cloud data based on the visual intelligence algorithm specifically includes: the visual intelligence algorithm specifically adopts the random sampling consensus algorithm, and the fitting plane adopts the formula... ,in, For three-dimensional coordinate variables, To fit the normal vector components of the plane, To fit the distance from the plane to the point, .

[0026] It should be understood that the process of eliminating uneven areas improves the accuracy of clamping point selection. By eliminating non-compliant areas based on workpiece shape error values, areas with uneven surfaces or irregular shapes can be effectively excluded. If these areas were used for clamping, they would lead to insufficient clamping force or unstable clamping, thereby reducing overall production efficiency. Through this optimization, the workpiece clamping point can be selected more precisely, ensuring the stability and efficiency of the clamping process.

[0027] For example, in a batch of workpieces of different shapes, the clamping points selected through this step can be automatically adjusted according to the actual shape and surface errors of the workpieces. For workpieces with curved or complex surfaces, traditional methods may require multiple manual adjustments to the fixture position and clamping force. However, with the technical method of this invention, the optimal clamping point can be quickly found and the required clamping force can be predicted simply by automatically analyzing point cloud data and calculating shape errors, thereby improving clamping accuracy and reducing unnecessary manual operation time.

[0028] Step S30: Based on the optimized clamping point, combined with the workpiece geometric feature value, workpiece position information, workpiece shape error value, and historical clamping force data, a clamping force prediction model is constructed to predict the optimized clamping force; It should be noted that in step S30, the clamping force prediction model is constructed using the random forest algorithm, and the formula is: curvature, history ,in, To optimize the clamping force, To optimize the clamping point, This refers to the preset number of decision trees in the random forest algorithm used. () is the first The output of the decision tree is: curvature is the workpiece shape error value, and history is the historical clamping force data.

[0029] It should be understood that, through learning from historical data, the random forest regression model can not only predict the clamping force based on the current geometric characteristics and shape errors of the workpiece, but also optimize the clamping force adjustment scheme by combining the experience of historical clamping forces. In this way, the fixture system can automatically adjust and adapt to different workpiece shapes, improving the automation level and efficiency of the production line.

[0030] For example, suppose a workpiece on a production line has the following geometric characteristics: length 500mm, width 200mm, height 50mm, curvature error of 0.03, and historical clamping force data of 28N. Using a random forest regression model and combining this input data, the system can predict that the required clamping force for the workpiece is 30N. The fixture system can then automatically adjust to this clamping force, ensuring a stable and efficient clamping process.

[0031] Step S40: Monitor the workpiece offset during the clamping process in real time using visual inspection method, and adjust the fixture position in combination with PID control algorithm; It should be noted that step S40, which involves real-time monitoring of the workpiece's offset during the clamping process using visual inspection, includes: The second set of 3D point cloud data was processed using Python's OpenCV library. Use the PyTorch deep learning object detection model YOLO to identify the positional offset of the workpiece; The offset is calculated based on the predicted and actual locations.

[0032] It should be understood that the visual inspection method in this process combines computer vision and deep learning technologies. Through efficient image processing and target recognition, the system can monitor the workpiece offset in real time on the production line. The PID control algorithm adjusts the position of the fixture in real time based on the detected offset, ensuring the stability and efficiency of the clamping process and avoiding clamping instability caused by workpiece offset.

[0033] For example, suppose the workpiece shifts by 1mm during clamping. After the YOLO model detects this shift, the PID control algorithm will immediately adjust the clamp to ensure the workpiece returns to the predetermined target point. The visual inspection and PID control in this process form a closed loop, ensuring precise execution of each clamping operation and improving the automation and stability of the production line.

[0034] Step S50: After the current clamping task is completed, the Q-learning method is used to switch clamping tasks and optimize the initial adjustment parameters of the clamp for the next clamping task.

[0035] It should be noted that in step S50, the Q-learning method uses the following formula:

[0036] in, For state The updated Q value corresponding to the next action A is executed. A represents the state variables of the current workpiece's optimized clamping force, optimized clamping point, and workpiece geometric feature values; A represents the adjustment actions that the fixture needs to perform. For state The Q value of the next action A is used to represent the optimality measure of task switching; To determine the degree of influence of the newly learned Q-value on the old value, For the reward function, As a discount factor, For the next state The maximum Q value.

[0037] It should be understood that through continuous iteration and updates of Q-learning, the system can autonomously adjust the optimal position and clamping force of the fixture when facing different workpieces and different production tasks. In complex production environments, this optimization mechanism can effectively reduce clamping force adjustment errors during task switching and improve the level of automation.

[0038] For example, suppose that during workpiece clamping, the workpiece's position or clamping force requirement deviates. Traditional methods might require multiple manual adjustments, while Q-learning automatically optimizes the fixture adjustment strategy based on historical task data. For instance, if the fixture required numerous adjustments in previous tasks, Q-learning will reduce the number of future adjustments through a reward mechanism, thus making the fixture adjustment process smoother and more efficient.

[0039] Example 2: Furthermore, the intelligent fixture control system for production lines provided by the present invention, employing an intelligent fixture control method for production lines as described in the above embodiments, can solve a technical problem related to intelligent fixture control for production lines. Compared with the prior art, the beneficial effects of the intelligent fixture control system for production lines provided by the present invention are the same as those of the intelligent fixture control method for production lines provided in the above embodiments, and other technical features in the intelligent fixture control system for production lines are the same as those disclosed in the methods of the above embodiments, and will not be repeated here.

[0040] Example 3: This invention provides an intelligent fixture control device for a production line. Please refer to... Figure 2A production line intelligent fixture control device includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, which, when executed by the at least one processor, enable the at least one processor to perform a production line intelligent fixture control method as described in Embodiment 1 above. The production line intelligent fixture control device in this embodiment may include, but is not limited to, mobile terminals such as mobile phones, laptops, digital radio receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), and in-vehicle terminals (e.g., in-vehicle navigation terminals), as well as fixed terminals such as digital TVs and desktop computers. This production line intelligent fixture control device is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of this invention. A production line intelligent fixture control device may include a processing unit 1001 (e.g., a central processing unit, a graphics processing unit, etc.) that can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 1002 or a program loaded from a storage device 1003 into a random access memory (RAM) 1004. The RAM 1004 also stores various programs and data required for the operation of the production line intelligent fixture control device. The processing unit 1001, ROM 1002, and RAM 1004 are interconnected via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to the I / O interface 1006: input devices 1007 including, for example, a touch screen, touchpad, keyboard, mouse, image sensor, microphone, accelerometer, gyroscope, etc.; output devices 1008 including, for example, a liquid crystal display (LCD), speaker, vibrator, etc.; storage devices 1003 including, for example, magnetic tape, hard disk, etc.; and communication devices 1009. Communication device 1009 allows a production line intelligent fixture control device to communicate wirelessly or wiredly with other devices to exchange data. While the figure shows a production line intelligent fixture control device with various systems, it should be understood that implementation or possession of all the systems shown is not required. More or fewer systems may be implemented alternatively.

[0041] Example 4: This invention also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the intelligent fixture control method for a production line as described above. The computer program product provided by this invention can solve a technical problem related to intelligent fixture control for a production line. Compared with the prior art, the beneficial effects of the computer program product provided by this invention are the same as those of the intelligent fixture control method for a production line provided in the above embodiments, and will not be repeated here.

[0042] In particular, according to the embodiments disclosed in this invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this invention include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device, or installed from storage device 1003, or installed from ROM 1002. When the computer program is executed by processing device 1001, it performs the functions defined in the methods of the embodiments disclosed in this invention.

[0043] It should be understood that the various parts disclosed in this invention can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics may be combined in any suitable manner in one or more embodiments or examples.

[0044] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, this invention also intends to include these modifications and variations.

Claims

1. A method for controlling intelligent fixtures on a production line, characterized in that, The methods include: Step S10: Use a laser scanner to acquire the first set of 3D point cloud data of the workpiece operated by the intelligent fixture on the production line, and use the point cloud processing algorithm to calculate the geometric feature value of the workpiece, the position information of the workpiece and the shape error value of the workpiece. Step S20: Based on the workpiece shape error value, remove uneven areas to obtain the second set of 3D point cloud data. Based on the visual intelligence algorithm, perform plane fitting on the second set of 3D point cloud data to obtain candidate clamping points, and select the candidate clamping point with the lowest workpiece shape error value to obtain the optimized clamping point. Step S30: Based on the optimized clamping point, combined with the workpiece geometric feature value, workpiece position information, workpiece shape error value, and historical clamping force data, a clamping force prediction model is constructed to predict the optimized clamping force; Step S40: Monitor the workpiece offset during the clamping process in real time using visual inspection method, and adjust the fixture position in combination with PID control algorithm; Step S50: After the current clamping task is completed, the Q-learning method is used to switch clamping tasks and optimize the initial adjustment parameters of the clamp for the next clamping task.

2. The intelligent fixture control method for a production line as described in claim 1, characterized in that, In step S10, the formula for calculating the workpiece shape error value is: in, For point The workpiece shape error value at that location, For the first set of 3D point cloud data, the first point on the workpiece surface The height of each point For point The average height of points on the workpiece surface within a local area of ​​a preset size. For point The number of points within a local area of ​​a preset size. For point The magnitude of the normal vector at that point.

3. The intelligent fixture control method for a production line as described in claim 1, characterized in that, Step S20, which involves obtaining candidate gripping points by performing plane fitting on the second set of 3D point cloud data based on a visual intelligence algorithm, specifically includes: the visual intelligence algorithm employs a random sampling consensus algorithm, and the fitting plane uses the formula... ,in, For three-dimensional coordinate variables, To fit the normal vector components of the plane, To fit the distance from the plane to the point, .

4. The intelligent fixture control method for a production line as described in claim 2, characterized in that, In step S10, the geometric features of the workpiece are calculated using the first 3D point cloud data of the workpiece combined with the minimum bounding rectangle method. The calculation formula is as follows: ,in, The length of the workpiece, This represents the maximum value in the X-axis direction. This is the minimum value in the X-axis direction; The width of the workpiece. This represents the maximum value in the Y-axis direction. This is the minimum value in the Y-axis direction; The height of the workpiece. This represents the maximum value in the Z-axis direction. It is the minimum value in the Z-axis direction.

5. The intelligent fixture control method for a production line as described in claim 4, characterized in that, In step S30, the clamping force prediction model is constructed using the random forest algorithm, employing the formula: curvature, history ,in, To optimize the clamping force, To optimize the clamping point, This refers to the preset number of decision trees in the random forest algorithm used. ( ) is the first The output of the decision tree is: curvature is the workpiece shape error value, and history is the historical clamping force data.

6. The intelligent fixture control method for a production line as described in claim 5, characterized in that, Step S40, which involves real-time monitoring of the workpiece's offset during the clamping process using visual inspection, includes: The second set of 3D point cloud data was processed using Python's OpenCV library. Use the PyTorch deep learning object detection model YOLO to identify the positional offset of the workpiece; The offset is calculated based on the predicted and actual locations.

7. The intelligent fixture control method for a production line as described in claim 6, characterized in that, In step S50, the Q-learning method uses the following formula: in, For state The updated Q value corresponding to the next action A is executed. A represents the state variables of the current workpiece's optimized clamping force, optimized clamping point, and workpiece geometric feature values; A represents the adjustment actions that the fixture needs to perform. For state The Q value of the next action A is used to represent the optimality measure of task switching; To determine the degree of influence of the newly learned Q-value on the old value, For the reward function, As a discount factor, For the next state The maximum Q value.

8. A production line intelligent fixture control system, characterized in that, The intelligent fixture control system for the production line includes: The data acquisition module is used to acquire the first set of 3D point cloud data of the workpiece operated by the intelligent fixture on the production line using a laser scanner, and to calculate the workpiece geometric feature value, workpiece position information and workpiece shape error value using a point cloud processing algorithm. The clamping point selection module is used to determine and eliminate uneven areas based on the workpiece shape error value to obtain a second set of 3D point cloud data. Based on the visual intelligence algorithm, the second set of 3D point cloud data is fitted to a plane to obtain candidate clamping points, and the candidate clamping point with the lowest workpiece shape error value is selected to obtain the optimized clamping point. The clamping force prediction module is used to build a clamping force prediction model based on the optimized clamping point, workpiece geometric feature value, workpiece position information, workpiece shape error value, and historical clamping force data, and predict the optimized clamping force. The clamping process offset monitoring and adjustment module is used to monitor the workpiece offset in real time during the clamping process through visual inspection and adjust the clamp position in combination with PID control algorithm; The task switching optimization module is used to monitor the workpiece's offset during the clamping process in real time using visual inspection and to adjust the fixture position using a PID control algorithm.

9. A production line intelligent fixture control device, characterized in that, The intelligent fixture control device for the production line includes: a memory, a processor, and an intelligent fixture control program for the production line stored in the memory and executable on the processor. When the intelligent fixture control program for the production line is executed by the processor, it implements the intelligent fixture control method for the production line as described in any one of claims 1 to 7.

10. A computer program product, characterized in that, The computer program product includes a production line intelligent fixture control program, which, when executed by a processor, implements the production line intelligent fixture control method as described in any one of claims 1 to 7.

Images