A method for quick locking of automotive component molds and its locking structure

Abstract

This invention relates to a rapid locking method and locking structure for automotive component molds; characterized by comprising a fixed base, a locking cylinder, and a locking unit; in the motion control of the locking mechanism, a motion smoothing algorithm and a trajectory optimization algorithm are introduced to smooth the motion trajectory of the locking mechanism, reduce speed and acceleration changes during the motion process, reduce the vibration and impact of the locking mechanism itself, and improve the stability of the locking process, thereby ensuring the consistency of the locking position of the automotive component mold. After motion control optimization, the optimized motion trajectory data is transmitted to a machine vision system for subsequent locking process monitoring.

Description

Technical Field

[0001] This invention relates to the field of automobile manufacturing technology, and in particular to a method for quick locking of automobile component molds and its locking structure. Background Technology

[0002] In rapid locking methods for automotive component molds, the movement and positioning of the mold during the locking process are crucial for locking consistency. However, due to the differences in shape and size of automotive component molds, misalignment or wobbling can easily occur during locking, leading to deviations in locking position and force, which in turn affects product quality. This problem is particularly prominent in mass production, because even small deviations can accumulate and amplify with increasing production volume, ultimately resulting in a serious decline in product quality.

[0003] Furthermore, automotive component molds may be subject to external vibrations and impacts during the locking process, further exacerbating their instability in movement and positioning. These disturbances may originate from mechanical vibrations and airflow disturbances in the production environment, or from the movement and impacts of the locking mechanism itself. Achieving precise positioning and stable locking of automotive component molds in complex production environments is a pressing technical challenge that needs to be addressed.

[0004] Meanwhile, the rapid locking method for automotive component molds also faces a trade-off between efficiency and precision. On the one hand, to improve production efficiency, locking time needs to be shortened as much as possible; on the other hand, to ensure locking quality, precise positioning and stable clamping of the automotive component mold are required during the locking process. How to maximize locking efficiency while ensuring locking consistency is another technical problem worthy of in-depth research. Summary of the Invention

[0005] The technical problem to be solved by the present invention is to provide a method for quick locking of automotive component molds and its locking structure, which can solve the problem of the contradiction between efficiency and accuracy faced by traditional quick locking methods for automotive component molds.

[0006] To solve the above-mentioned technical problems, the technical solution of the present invention is: a method for quick locking of automotive component molds, the innovation of which is as follows: the specific locking method is as follows:

[0007] S1: Obtain the 3D model data of the automotive component mold to be locked, determine the shape features and size parameters of the automotive component mold, establish the corresponding data model of locking position and locking force, collect the position and posture information of the automotive component mold, and make corresponding compensation adjustments by controlling the locking mechanism;

[0008] S2: Use sensors to acquire vibration and airflow parameters in the production environment, establish a correlation model between production environment interference factors and locking accuracy, set vibration damping devices and buffer devices on the locking mechanism, and dynamically adjust the motion control strategy of the locking mechanism according to the real-time acquired vibration and airflow parameters.

[0009] S3: In the motion control of the locking mechanism, motion smoothing algorithm and trajectory optimization algorithm are introduced. By smoothing the motion trajectory of the locking mechanism, the speed and acceleration changes during the motion process are reduced, the vibration and impact are reduced, and the stability is improved. The optimized motion trajectory data is transmitted to the machine vision system for subsequent locking process monitoring.

[0010] S4: Employs high-speed industrial cameras and deep learning image processing algorithms for real-time monitoring. By processing and analyzing the acquired image data, it determines the locking position and locking status of automotive component molds in real time, and compares the locking position and status information obtained by the machine vision system with the optimized motion trajectory data.

[0011] S5: Using the results obtained in steps S1 to S4, establish a data correlation model between locking parameters and product quality. Through support vector machine and random forest machine learning algorithms, explore the correlation patterns between locking parameters and product quality, and optimize the setting of locking parameters for different automotive part molds and production conditions.

[0012] An innovative feature of a locking structure for automotive component molds is that it includes a fixed base, a locking cylinder, and a locking unit.

[0013] The fixed base includes a base plate, a cylinder fixing plate, and a lock head hinge seat. The base plate has a cuboid plate structure. The cylinder fixing plate is located near one end of the upper surface of the base plate, and the lock head hinge seat is located near the other end of the upper surface of the base plate. The cylinder fixing plate has a locking cylinder fixing hole and a through hole for accommodating the output end of the locking cylinder. The lock head hinge seat has a lock head hinge hole. A slide rail is located on the upper surface of the base plate between the cylinder fixing plate and the lock head hinge seat, and a slider is provided on the slide rail.

[0014] The locking cylinder is mounted parallel to the base plate on the cylinder fixing plate;

[0015] The locking unit is installed on the output end of the locking cylinder; the locking unit includes a lock head connecting seat and a lock head; the lock head connecting seat is installed on the output end of the locking cylinder, the lock head connecting seat has a U-shaped structure, the opening direction of the lock head connecting seat is parallel to the base plate, and the upper and lower sides of the lock head connecting seat are through; a guide pin is horizontally arranged on the inner side wall of the lock head connecting seat near the opening end; the lower side of the lock head connecting seat is installed on the slider;

[0016] The lock head has a rectangular plate-like structure, is embedded in a lock head connecting seat, and extends out of the lock head connecting seat at one end; a hinge plate is provided on the bottom side of the lock head, and the hinge plate is mounted on the lock head hinge seat through a hinge shaft; an arc-shaped guide groove is opened on the lock head, and a guide pin on the lock head connecting seat is embedded in the arc-shaped guide groove on the lock head; a mold locking slot is provided at the end of the lock head extending out of the lock head connecting seat; the locking cylinder drives the lock head connecting seat to reciprocate along the extension direction of the slide rail, and the guide pin moves along the arc-shaped guide groove of the lock head to drive the lock head to rotate around the hinge, so as to lock or release the automotive part mold at the mold locking slot at the end of the lock head.

[0017] The advantages of this invention are:

[0018] 1) This invention addresses the accuracy and consistency issues in the locking process of automotive component molds. First, it acquires 3D model data of the component and establishes a data model of the locking position and force. During the locking process, it collects the component's position and posture information in real time and compares it with a preset position, compensating for any deviations. Simultaneously, it acquires environmental vibration and airflow parameters through sensors, establishing a correlation model between interference factors and locking accuracy, and employs vibration damping devices and adaptive compensation strategies to cope with external interference. Furthermore, this invention introduces a motion smoothing algorithm to optimize the locking mechanism trajectory and utilizes a machine vision system to monitor the locking status in real time. Finally, based on the collected data, it establishes a correlation model between locking parameters and product quality, optimizing parameter settings through machine learning algorithms. This invention achieves intelligent and refined control of the automotive component mold locking process, effectively improving locking accuracy and consistency, and ensuring product quality. Attached Figure Description

[0019] The present invention will now be described in further detail with reference to the accompanying drawings and specific embodiments.

[0020] Figure 1 This is a flowchart of a method for quickly locking an automotive component mold according to the present invention.

[0021] Figure 2 This is a schematic diagram of a quick locking method for automotive component molds according to the present invention.

[0022] Figure 3 This is another schematic diagram of a quick locking method for automotive component molds according to the present invention.

[0023] Figure 4 This is a diagram showing the locking structure of a quick locking method for automotive component molds according to the present invention.

[0024] Figure 5 This is a partial structural diagram of the locking structure of a quick locking method for automotive component molds according to the present invention. Detailed Implementation

[0025] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, 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. The components of the embodiments of the present invention described and shown in the accompanying drawings can generally be arranged and designed in various different configurations.

[0026] Therefore, the following detailed description of the embodiments of the invention provided in the accompanying drawings is not intended to limit the scope of the claimed invention, but merely to illustrate selected embodiments of the invention. All other embodiments obtained by those skilled in the art based on the embodiments of the invention without inventive effort are within the scope of protection of the invention.

[0027] like Figures 1 to 3 This illustrates a method for quickly locking automotive component molds;

[0028] The process involves acquiring 3D model data of the automotive component mold to be locked, and analyzing this data to determine its shape features and dimensional parameters. Based on these parameters, a data model is established specifying the corresponding locking position and force. During the locking process, the mold's pose information is acquired in real-time and compared with the preset locking position. This comparison determines whether the mold has shifted or wobbled. If so, the direction and amplitude of the shift or wobbling are acquired. Based on this information, the locking mechanism is adjusted to compensate for the shift. This adjustment ensures the final locking position of the automotive component mold is accurate, achieving a high-precision locking operation.

[0029] For example, firstly, a 3D scanner is used to scan the automotive component mold to be locked, obtaining its 3D model data. By analyzing the 3D model data, key shape features of the automotive component mold are extracted, such as planes, cylindrical surfaces, and conical surfaces, and the dimensional parameters of each feature, such as length, width, height, and diameter, are calculated. Based on the extracted shape features and dimensional parameters, a mathematical model is established to describe the locking position and required locking force of the automotive component mold. For example, for a cuboid-shaped automotive component mold, its mathematical model can be represented by a point and three vectors in a 3D coordinate system, where the point represents the locking position and the vectors represent the locking force in the length, width, and height directions. During the locking process, the pose information of the automotive component mold is collected in real time using a vision sensor and compared with the preset locking position in the mathematical model. During the comparison, a pose estimation algorithm, such as the ICP algorithm, can be used to calculate the deviation between the current pose and the preset pose of the automotive component mold. If the deviation exceeds a preset threshold (e.g., 2mm), it is determined that a shift or wobbling has occurred. Simultaneously, by analyzing the direction and magnitude of the positional deviation, the specific direction and amplitude of the offset or sway can be calculated. For example, if the deviation in the X direction is 3mm and the deviation in the Y direction is -1mm, then the offset direction is the positive X direction and the negative Y direction, and the amplitude is sqrt(3^2+1^2)=16mm. Based on the calculated direction and amplitude of the offset or sway, the locking mechanism is controlled to make compensation adjustments, with the adjustment amount being the same as the offset amount but in the opposite direction. For example, for the above offset situation, the locking mechanism needs to move 3mm in the negative X direction and 1mm in the positive Y direction, thereby adjusting the automotive part mold back to the preset locking position. Through this real-time compensation adjustment, it can be ensured that the positional accuracy of the automotive part mold after locking is controlled within 1mm, achieving high-precision locking operation.

[0030] The system acquires vibration and airflow parameter data from accelerometers and airflow sensors, inputs this data into a pre-established correlation model between production environment interference factors and locking accuracy, and obtains the estimated locking accuracy under the current production environment. It then determines whether the estimated locking accuracy meets a preset accuracy threshold. If it does, the locking mechanism is controlled to perform locking operations according to a standard motion control strategy. If the estimated accuracy does not meet the threshold, the vibration damping device and buffer device are activated. The vibration damping device adjusts the damping coefficient in real time based on the vibration parameters to actively dampen the locking mechanism and attenuate the impact of external vibrations on the locking accuracy. The buffer device uses elastic elements to absorb vibrations. Instantaneous impact force is avoided to prevent it from directly acting on the locking mechanism and causing displacement of the automotive component mold. After vibration reduction and buffering, data from the acceleration and airflow sensors are acquired again and input into the correlation model to re-estimate the locking accuracy. If the estimated accuracy is still not up to standard, the movement speed, acceleration, and torque parameters of the locking mechanism are dynamically adjusted based on the current vibration and airflow parameters. An adaptive compensation locking control strategy is used to further improve the locking accuracy. After locking is completed, the actual locking accuracy data is acquired and input into the machine learning algorithm to train and optimize the correlation model online, improving the prediction accuracy of the correlation model and providing an optimization basis for subsequent locking operations.

[0031] For example, during the locking operation, acceleration and airflow sensors collect vibration and airflow parameter data in real time at a sampling frequency of 1000Hz. The collected data is input into a correlation model between production environment interference factors and locking accuracy established based on a support vector machine algorithm. Through Gaussian kernel function mapping and sequential minimum optimization algorithm, the estimated locking accuracy under the current production environment is obtained within 10ms. The system determines whether the estimated locking accuracy meets the preset accuracy threshold of ±1mm. If the threshold is met, the locking mechanism is controlled to perform standard locking operations according to preset parameters of motion speed 5m / s, acceleration 2m / s², and torque 10N·m. If the estimated accuracy does not meet the threshold, the vibration damping device and buffer device are triggered. The vibration damping device uses a magnetorheological damper, which adjusts the damping coefficient from 0 to 50N·s / mm in real time according to the vibration frequency and amplitude through a fuzzy PID control algorithm to actively dampen the locking mechanism, attenuating more than 50% of the external vibration influence. The buffer device uses a shape memory alloy spring. When an instantaneous impact force greater than 10N is detected, the spring automatically compresses and deforms to absorb 80% of the impact energy, preventing the impact force from directly acting on the locking mechanism and causing displacement of the automotive component mold. After vibration reduction and buffering, the system acquires sensor data again and estimates the locking accuracy. If the accuracy still does not meet the requirement of ±1mm, the system dynamically adjusts the movement speed, acceleration, and torque parameters of the locking mechanism based on the deviation between the current vibration and airflow parameters and the preset template, achieving adaptive compensation control and further improving the locking accuracy to within ±0.5mm. After locking is completed, the system acquires the actual locking accuracy data measured by the laser displacement sensor and inputs it into a machine learning algorithm based on a long short-term memory network. The correlation model is trained and optimized online through the backpropagation algorithm, continuously improving the prediction accuracy of the correlation model and reducing the error between the predicted value and the measured value to within 5%, providing a precise optimization basis for subsequent locking operations.

[0032] Based on the motion control requirements of the locking mechanism, a motion smoothing algorithm is used to smooth the motion trajectory of the locking mechanism, resulting in smoothed motion trajectory data. Based on this smoothed motion trajectory data, a trajectory optimization algorithm is used to optimize the motion trajectory of the locking mechanism, resulting in optimized motion trajectory data. The optimized motion trajectory data includes information on velocity and acceleration changes. Based on the optimized motion trajectory data, the locking mechanism is controlled to move along the optimized trajectory, reducing vibration and impact during the locking mechanism's movement by minimizing velocity and acceleration changes. During the locking process, the motion parameters of the locking mechanism, including velocity and acceleration, are acquired in real time to determine if they meet the preset stability requirements. If not, the motion control parameters of the locking mechanism are adjusted. The locking position information of the automotive component mold is acquired and compared with the preset standard locking position to determine if the locking position meets the consistency requirements. If not, the motion control parameters of the locking mechanism are adjusted. The optimized motion trajectory data is transmitted to the machine vision system. Based on this data, the machine vision system monitors the locking process in real time, acquiring the actual motion trajectory of the locking mechanism and determining whether it matches the optimized trajectory. If they do not match, an alarm signal is generated. Based on the monitoring results from the machine vision system, machine learning algorithms are used to adaptively optimize the motion control parameters of the locking mechanism, including motion smoothing algorithm parameters and trajectory optimization algorithm parameters, continuously improving the smoothness of the locking process and the consistency of the locking position.

[0033] For example, based on the motion control requirements of the locking mechanism, a fifth-order polynomial interpolation algorithm is used to smooth the motion trajectory of the locking mechanism. By selecting appropriate trajectory sampling points, such as 1-second intervals, the least squares method is used to fit the smoothed motion trajectory curve equation, ensuring continuous changes in velocity and acceleration. Then, a gradient descent algorithm is used to optimize the smoothed motion trajectory. By setting velocity change thresholds of ±0.5 m / s and acceleration change thresholds of ±5 m / s², the trajectory parameters are iteratively optimized, reducing the velocity standard deviation by 20% and the acceleration standard deviation by 30%, thus obtaining the optimal motion trajectory. The locking mechanism is controlled to move along the optimized trajectory, and motion parameters are collected in real time. If the velocity exceeds ±0.3 m / s or the acceleration exceeds ±3 m / s², the PID algorithm adjusts the servo motor speed to make the motion smoother. Machine vision is used to acquire images of the locking position, and an edge detection algorithm is used to extract the contour and calculate the pixel coordinate deviation. If the deviation exceeds ±2 mm, feedback is provided to adjust the motion endpoint position. The optimized trajectory is transmitted to the vision system for real-time comparison and monitoring. If the actual trajectory deviates from the optimized trajectory by more than ±1 mm, an alarm is issued. Based on monitoring data, a neural network algorithm is used for self-learning optimization. By setting 1000 sets of training samples and adjusting the number of hidden layer nodes in the network to 50, the training error is reduced to below 5%, making the locking trajectory more precise and controllable, and realizing intelligent locking.

[0034] High-speed industrial cameras and deep learning image processing algorithms are used to monitor the locking process in real time. By processing and analyzing the acquired image data, the locking position and status of the automotive component mold are determined in real time. The locking position and status information obtained by the machine vision system is compared with the optimized motion trajectory data. Once an abnormal deviation is detected, an alarm mechanism is immediately triggered, and the locking parameters are automatically adjusted according to the deviation to ensure that the locking quality meets the requirements.

[0035] Step 1: Acquire a series of images in real time during the locking process of the automotive component mold using a high-speed industrial camera, obtaining a continuous image sequence of the locking process. Step 2: Input the acquired image data into a pre-trained deep learning model, which can be a convolutional neural network or a recurrent neural network. Through feature extraction and classification, determine the locking position coordinates and locking state category of the automotive component mold in each frame of the image. Step 3: Based on the recognition results of the deep learning model, acquire the real-time position and state changes of the automotive component mold during the locking process, forming time-series data reflecting the locking process. Step 4: Compare the locking position and state time-series data acquired by machine vision with the standard locking motion trajectory optimized according to the material characteristics and dimensional parameters of the automotive component mold. Calculate the similarity between the two time series using a dynamic time warping algorithm. Step 5: Set locking position deviation thresholds and locking state abnormality thresholds. When the similarity is lower than the threshold, it is judged as a locking deviation or locking abnormality, triggering an audible and visual alarm, and feeding back the deviation data to the control system. Step 6: Based on the locking deviation data, the control system uses an adaptive parameter optimization algorithm, such as particle swarm optimization, to adjust the operating parameters of the locking equipment, such as the locking force and locking time, to restore the locking process to its optimal state. Step 7: The adjusted locking process continues to be monitored by machine vision, and the locking data is entered into a sample set for continuous training and improvement of the deep learning model and motion trajectory optimization algorithm, thereby continuously improving the accuracy and stability of locking quality detection and control.

[0036] For example, a series of image data during the locking process of an automotive component mold is acquired in real time using a high-speed industrial camera. The camera sampling frequency is set to 200 frames / second, and the resolution is 1920×1080 pixels. The locking process is continuously acquired for 10 seconds, resulting in a sequence of 2000 images. The acquired image data is input into a pre-trained convolutional neural network model, which contains 5 convolutional layers and 3 fully connected layers. Through feature extraction and classification, the locking position coordinates (x, y) and locking status category (0 indicates not locked, 1 indicates locked) of the automotive component mold in each frame are determined with an accuracy of 98%. Based on the recognition results of the convolutional neural network model, the real-time position and status changes of the automotive component mold during the locking process are obtained, forming a time series containing 2000 (x, y, status) data points. The time series is compared with a standard locking motion trajectory (containing 2000 standard position coordinates and state values) optimized based on the material characteristics and dimensional parameters of the automotive component mold. A dynamic time warping algorithm is used to calculate the similarity between the two time series. When the similarity is below 95, it is judged as a locking deviation or locking anomaly, triggering an audible and visual alarm, and feeding back the deviation data (the difference between the actual value and the standard value) to the control system. The control system uses a particle swarm optimization algorithm to adaptively adjust the operating parameters of the locking device based on the deviation data, such as increasing the locking force from 1000N to 1050N and extending the locking time from 5s to 2s, so that the locking process recovers to the optimal state (similarity greater than 95) after 3 iterations. The adjusted locking process continues to be monitored in real time by machine vision, and the 2000 locking data points are entered into a sample set for incremental training of the convolutional neural network model and dynamic correction of the fitness function of the particle swarm optimization algorithm, continuously improving the accuracy and stability of locking quality detection and control.

[0037] The process involves acquiring 3D model data of automotive component molds, including their geometric dimensions and material properties, and converting this data into a unified digital representation to lay the foundation for subsequent analysis. Sensors are used to collect the position and orientation information of the automotive component molds on the production line to determine if they meet the locking process requirements. If not, adjustments are made promptly to ensure the accuracy of the locking position. Environmental parameters such as temperature, humidity, and vibration are acquired and their impact on locking quality is analyzed. When environmental parameters exceed preset thresholds, locking parameters are adjusted or corresponding measures are taken to reduce environmental interference. Machine vision technology is used to monitor the locking process in real time, acquiring key parameters such as locking torque and locking angle to determine if the locking quality meets requirements. If abnormalities occur, alarms are triggered and the causes are analyzed. Based on the locking parameters and product quality inspection results, a nonlinear correlation model between locking parameters and product quality is established using support vector machines and random forest machine learning algorithms to uncover the intrinsic relationship between the two. For different models of automotive component molds and production conditions, the optimal combination of locking parameters is analyzed through the correlation model to improve locking efficiency while ensuring product quality, achieving dynamic optimization of locking process parameters. The optimized locking parameters are applied to the production line, and the locking process and product quality are continuously monitored through machine vision technology. If deviations occur, feedback is provided in a timely manner and the parameters are adjusted to form a closed-loop control, thereby achieving intelligent and refined management of the locking process of automotive component molds.

[0038] For example, firstly, a 3D scanner is used to scan the automotive part mold to obtain its 3D point cloud data. The point cloud density is set to 1mm, and the scanning accuracy reaches 0.5mm. Then, Geomagic Design X software is used to post-process the point cloud data, converting it into a NURBS surface model through a surface reconstruction algorithm and extracting its geometric dimension information. Simultaneously, a material composition analyzer is used to determine the material composition of the automotive part mold, and combined with the material mechanical property test data, material attribute information is added to the 3D model. Next, vision sensors are installed on the production line to collect the position and attitude information of the automotive part mold. An attitude estimation algorithm is used to determine whether its deviation is within 1°. If it exceeds this, the robotic arm automatically adjusts. For temperature and humidity environmental parameters, high-precision sensors are used to collect data in real time. When the temperature exceeds 30℃ or the humidity exceeds 70%, an alarm is automatically triggered, and the workshop air conditioning and dehumidification equipment are adjusted. During the locking process, the machine vision system monitors the locking torque and angle in real time at a rate of 50 frames per second. A threshold segmentation algorithm is used to determine whether the torque is within the standard range. If the deviation exceeds 5%, an alarm is triggered. Locking parameters and quality inspection results are input into a machine learning model. A nonlinear correlation model between locking parameters and product quality is established using the support vector machine algorithm. The model's hyperparameters are optimized through grid search and cross-validation, achieving an accuracy of over 95%. Finally, a genetic algorithm is used to search for the optimal combination of locking parameters, with product quality and locking efficiency as optimization objectives. After 100 iterations, the optimal parameter combination is obtained and applied to the production line. A closed-loop control system continuously monitors the locking process. If three consecutive quality inspection results exceed the tolerance, the locking parameters are automatically adjusted to ensure stable product quality.

[0039] like Figures 4 to 5 A locking structure for an automotive component mold includes a fixed base 1, a locking cylinder 2, and a locking unit 3;

[0040] The fixed base 1 includes a base plate 11, a cylinder fixing plate 12, and a lock head hinge seat 13. The base plate 11 has a cuboid plate structure. The cylinder fixing plate 12 is provided on the upper surface of the base plate 11 near one end, and the lock head hinge seat 13 is provided on the upper surface of the base plate 11 near the other end. The cylinder fixing plate 12 has a locking cylinder fixing hole and a through hole for accommodating the output end of the locking cylinder 2. The lock head hinge seat 13 has a lock head hinge hole. A slide rail 14 is provided on the upper surface of the base plate 11 between the cylinder fixing plate 12 and the lock head hinge seat 13, and a slider is provided on the slide rail 14.

[0041] The locking cylinder 2 is mounted parallel to the base plate 11 on the cylinder fixing plate;

[0042] The locking unit 3 is installed on the output end of the locking cylinder 2; the locking unit 3 includes a lock head connecting seat 31 and a lock head 32; the lock head connecting seat 31 is installed on the output end of the locking cylinder 2, the lock head connecting seat 31 has a U-shaped structure, the opening direction of the lock head connecting seat 31 is parallel to the base plate 11, and the upper and lower sides of the lock head connecting seat 31 are connected; a guide pin 33 is horizontally arranged on the inner side wall of the lock head connecting seat 31 near the opening end; the lower side of the lock head connecting seat 31 is installed on the slider;

[0043] The lock head 32 has a rectangular plate-like structure. The lock head 32 is embedded in the lock head connecting seat 31 and one end extends out of the lock head connecting seat 31. A hinge plate is provided on the bottom side of the lock head, and the hinge plate is mounted on the lock head hinge seat 13 through a hinge shaft. An arc-shaped guide groove 34 is opened on the lock head 32, and the guide pin on the lock head connecting seat is embedded in the arc-shaped guide groove 34 on the lock head. A mold locking slot 35 is provided at one end of the lock head extending out of the lock head connecting seat 31. The locking cylinder 2 drives the lock head connecting seat 31 to move back and forth along the extension direction of the slide rail 14. The guide pin 33 moves along the arc-shaped guide groove 34 of the lock head to drive the lock head 32 to rotate around the hinge, so as to lock or release the automotive part mold at the mold locking slot 35 at the end of the lock head 32.

[0044] Those skilled in the art should understand that this invention is not limited to the above embodiments. The embodiments and descriptions in the specification are merely illustrative of the principles of the invention. Various changes and modifications can be made to this invention without departing from its spirit and scope, and all such changes and modifications fall within the scope of the invention as claimed. The scope of protection of this invention is defined by the appended claims and their equivalents.

Claims

1. A method for rapid locking of automotive component molds, characterized in that: The specific locking method is as follows: S1: Obtain the 3D model data of the automotive component mold to be locked, determine the shape features and size parameters of the automotive component mold, establish the corresponding data model of locking position and locking force, collect the position and posture information of the automotive component mold, and make corresponding compensation adjustments by controlling the locking mechanism; S2: Use sensors to acquire vibration and airflow parameters in the production environment, establish a correlation model between production environment interference factors and locking accuracy, set vibration damping devices and buffer devices on the locking mechanism, and dynamically adjust the motion control strategy of the locking mechanism according to the real-time acquired vibration and airflow parameters. S3: In the motion control of the locking mechanism, motion smoothing algorithm and trajectory optimization algorithm are introduced. By smoothing the motion trajectory of the locking mechanism, the speed and acceleration changes during the motion process are reduced, the vibration and impact are reduced, and the stability is improved. The optimized motion trajectory data is transmitted to the machine vision system for subsequent locking process monitoring. S4: Employs high-speed industrial cameras and deep learning image processing algorithms for real-time monitoring. By processing and analyzing the acquired image data, it determines the locking position and locking status of automotive component molds in real time, and compares the locking position and status information obtained by the machine vision system with the optimized motion trajectory data. S5: Using the results obtained in steps S1 to S4, establish a data correlation model between locking parameters and product quality. Through support vector machine and random forest machine learning algorithms, explore the correlation patterns between locking parameters and product quality, and optimize the setting of locking parameters for different automotive part molds and production conditions. The specific methods in S2 include: The vibration and airflow parameter data collected by the accelerometer and airflow sensor are acquired, and the vibration and airflow parameter data are input into the pre-established correlation model between production environment interference factors and locking accuracy to obtain the estimated locking accuracy under the current production environment. Determine whether the estimated locking accuracy meets the preset accuracy threshold. If it meets the threshold, control the locking mechanism to perform the locking operation according to the standard motion control strategy. If the estimated accuracy does not meet the threshold, the vibration damping device and the buffer device will be triggered to work. The vibration damping device adjusts the damping coefficient in real time according to the magnitude of the vibration parameters to actively dampen the locking mechanism and reduce the impact of external vibration on the locking accuracy. The buffer device uses elastic elements to absorb instantaneous impact force, preventing the impact force from acting directly on the locking mechanism and causing displacement of the automotive part mold position; After vibration reduction and buffering, the data from the acceleration sensor and airflow sensor are acquired again and input into the correlation model to re-estimate the locking accuracy. If the estimated accuracy is still not up to standard, the movement speed, acceleration and torque parameters of the locking mechanism are dynamically adjusted according to the current vibration and airflow parameters. The locking accuracy is further improved through an adaptive compensation locking control strategy. After locking is completed, the actual locking accuracy data is obtained and input into the machine learning algorithm to train and optimize the correlation model online, thereby improving the prediction accuracy of the correlation model and providing an optimization basis for subsequent locking operations.

2. The method for quick locking of an automotive component mold according to claim 1, characterized in that: The specific methods in S1 include: Obtain the 3D model data of the automotive component mold to be locked, and determine the shape features and dimensional parameters of the automotive component mold by analyzing the 3D model data; Based on the shape characteristics and dimensional parameters of automotive component molds, establish a data model for the corresponding locking position and locking force; During the locking process, the position and orientation information of the automotive component mold is collected in real time, and the collected position and orientation information is compared with the preset locking position. By comparing the pose information with the preset locking position, it can be determined whether the automotive part mold has shifted or shaken; If the judgment result is that the automotive part mold has shifted or shaken, then obtain the direction and amplitude information of the shift or shaking; Based on the obtained information on the direction and amplitude of the offset or sway, the locking mechanism is controlled to make corresponding compensation adjustments; By adjusting the locking mechanism, the final locking position of the automotive part mold is ensured to be accurate, thus completing a high-precision automotive part mold locking operation.

3. The method for quick locking of an automotive component mold according to claim 1, characterized in that: The specific methods in S3 include: Based on the motion control requirements of the locking mechanism, a motion smoothing algorithm is used to smooth the motion trajectory of the locking mechanism to obtain smoothed motion trajectory data. Based on the smoothed motion trajectory data, a trajectory optimization algorithm is used to optimize the motion trajectory of the locking mechanism to obtain optimized motion trajectory data, which includes information on velocity and acceleration changes. Based on the optimized motion trajectory data, the locking mechanism is controlled to move according to the optimized motion trajectory. By reducing speed and acceleration changes, the vibration and impact during the movement of the locking mechanism are reduced. During the locking process, the motion parameters of the locking mechanism, including speed and acceleration, are acquired in real time to determine whether the motion parameters meet the preset stability requirements. If not, the motion control parameters of the locking mechanism are adjusted. Obtain the locking position information of the automotive component mold, compare the locking position information with the preset standard locking position, and determine whether the locking position meets the consistency requirements. If not, adjust the motion control parameters of the locking mechanism. The optimized motion trajectory data is transmitted to the machine vision system. The machine vision system monitors the locking process in real time based on the motion trajectory data, obtains the actual motion trajectory of the locking mechanism, and determines whether the actual motion trajectory is consistent with the optimized motion trajectory. If they are inconsistent, an alarm signal is generated. Based on the monitoring results of the machine vision system, machine learning algorithms are used to adaptively optimize the motion control parameters of the locking mechanism, including motion smoothing algorithm parameters and trajectory optimization algorithm parameters, to continuously improve the smoothness of the locking process and the consistency of the locking position.

4. The method for quick locking of an automotive component mold according to claim 1, characterized in that: The specific methods in S4 include: Step 1: Acquire a series of image data in real time during the locking process of automotive component molds using a high-speed industrial camera to obtain a continuous image sequence of the locking process; Step 2: Input the collected image data into a pre-trained deep learning model, which can be a convolutional neural network or a recurrent neural network. Through feature extraction and classification, determine the locking position coordinates and locking status category of the car part mold in each frame of the image. Step 3: Based on the recognition results of the deep learning model, obtain the real-time position and state changes of the automotive component mold during the locking process, forming time series data reflecting the locking process; Step 4: Compare the locking position and state time series data acquired by machine vision with the standard locking motion trajectory optimized according to the material characteristics and shape parameters of the automotive part mold, and calculate the similarity between the two time series using the dynamic time warping algorithm. Step 5: Set the locking position deviation threshold and the locking state abnormality threshold. When the similarity is lower than the threshold, it is judged as locking deviation or locking abnormality, triggering an audible and visual alarm and feeding back the deviation data to the control system. Step 6: Based on the locking deviation data, the control system uses a parameter adaptive optimization algorithm and a particle swarm optimization algorithm to adjust the operating parameters of the locking device, the magnitude of the locking force, and the locking time, so that the locking process is restored to the optimal state. Step 7: Continue to monitor the adjusted locking process using machine vision, and record the locking data into the sample set for continuous training and improvement of the deep learning model and motion trajectory optimization algorithm, thereby continuously improving the accuracy and stability of locking quality detection and control.

5. The method for quick locking of an automotive component mold according to claim 1, characterized in that: The specific methods in S5 include: Acquire 3D model data of automotive component molds, including their geometric dimensions and material properties, and convert them into a unified digital representation to lay the foundation for subsequent analysis; Sensors are used to collect the position and orientation information of automotive component molds on the production line to determine whether they meet the locking process requirements. If they do not meet the requirements, adjustments are made in a timely manner to ensure the accuracy of the locking position. Acquire temperature, humidity, and vibration parameters of the production environment, analyze their impact on locking quality, and adjust locking parameters or take corresponding measures in a timely manner when environmental parameters exceed preset thresholds to reduce the interference of environmental factors. Machine vision technology is used to monitor the locking process in real time, obtain key parameters such as locking torque and locking angle, determine whether the locking quality meets the requirements, and promptly alarm and analyze the cause if any abnormality occurs. Based on the locking parameters and product quality inspection results, a nonlinear correlation model between the locking parameters and product quality is established using support vector machine and random forest machine learning algorithms to explore the intrinsic relationship between the two. For different types of automotive component molds and production conditions, the optimal combination of locking parameters is analyzed through correlation modeling to improve locking efficiency while ensuring product quality, thereby achieving dynamic optimization of locking process parameters. The optimized locking parameters are applied to the production line, and the locking process and product quality are continuously monitored through machine vision technology. If deviations occur, feedback is provided in a timely manner and the parameters are adjusted to form a closed-loop control, thereby achieving intelligent and refined management of the locking process of automotive component molds.

Images