Pultrusion track control automatic gluing method and system based on servo motor

Abstract

The present application provides a pultrusion strip trajectory control automatic gluing method and system based on a servo motor, relates to the technical field of trajectory control, and comprises the following steps: establishing a coordinate system to plan trajectory points by collecting three-dimensional model information of a workpiece; identifying reference feature points by using a visual sensor to perform space compensation; monitoring glue quantity and pressure parameters in real time, dynamically adjusting the speed of a servo motor and glue supply pressure; and uploading parameters to a control system to generate a quality evaluation report for trajectory optimization. The present application realizes accurate control of the gluing trajectory and uniformity of the glue quantity, and improves the gluing quality and production efficiency of the pultrusion strip.

Description

TECHNICAL FIELD

[0001] The present application relates to trajectory control technology, in particular to a pultrusion strip trajectory control automatic gluing method and system based on a servo motor. BACKGROUND

[0002] In the fields of aerospace, automobile manufacturing, construction, etc., pultrusion strips are widely used as an important composite material structural part. The connection and sealing of pultrusion strips usually require gluing treatment to ensure their structural integrity and sealing performance. The traditional pultrusion strip gluing process mainly relies on manual operation, and workers manually control the gluing gun along the surface of the pultrusion strip according to experience. With the improvement of industrial automation level, automatic gluing technology is gradually applied to the production process of pultrusion strips, replacing manual operation by mechanical arms or special equipment to improve gluing efficiency and quality.

[0003] However, the existing automatic gluing technology for pultrusion strips still has some obvious defects and deficiencies. First, the existing technology lacks accurate identification and compensation ability for the actual position of the pultrusion strip, resulting in mismatch between the gluing trajectory and the actual demand when the pultrusion strip has deformation or installation deviation, affecting the gluing quality. Second, the traditional gluing system cannot monitor and adjust key parameters such as glue amount and gluing pressure in real time during the gluing process, resulting in uneven distribution of glue amount on the gluing trajectory, especially in the corner and curved surface areas, which is prone to excessive or insufficient glue amount. Finally, the existing gluing system lacks a complete data collection and analysis mechanism, and cannot systematically evaluate and continuously optimize the gluing quality, making it difficult to form a closed-loop control of the gluing process, and unable to automatically optimize the gluing parameters and trajectory based on historical data.

[0004] Therefore, there is an urgent need for an automatic gluing method that can accurately identify the position of the pultrusion strip, adjust the gluing parameters in real time, and has data analysis and optimization functions, to improve the accuracy, uniformity and reliability of pultrusion strip gluing. SUMMARY

[0005] The embodiment of the present application provides a pultrusion strip trajectory control automatic gluing method and system based on a servo motor, which can solve the problems in the prior art.

[0006] In a first aspect, the embodiment of the present application provides a pultrusion strip trajectory control automatic gluing method based on a servo motor, comprising:

[0007] Collecting three-dimensional numerical model information of the pultrusion strip workpiece, establishing a coordinate system of the pultrusion strip workpiece according to the three-dimensional numerical model information, and planning a gluing trajectory point in the coordinate system;

[0008] The visual sensor is used to collect image information of the surface of the pultruded strip workpiece in real time, reference feature points on the surface of the pultruded strip workpiece are identified according to the image information, the reference feature points are registered with the coordinate system, actual position information of the glue applying track points is obtained, and the glue applying track points are compensated in space according to the actual position information;

[0009] According to the compensated glue applying track points, the glue applying device is controlled to perform glue applying operation; during the glue applying operation, the glue amount parameter and the glue applying pressure parameter of the glue applying gun are collected in real time, the motion speed of the servo motor and the glue supply pressure of the glue applying gun are dynamically adjusted according to the change trend of the glue amount parameter and the glue applying pressure parameter, so that the glue amount uniformity of the glue applying track is controlled within a preset track threshold range;

[0010] The compensated glue applying track points, the glue amount parameter and the glue applying pressure parameter are uploaded to a control system, the control system generates a glue applying quality evaluation report according to the uploaded parameters, and the glue applying quality evaluation report is used for optimization of subsequent glue applying tracks.

[0011] Three-dimensional digital model information of the pultruded strip workpiece is collected, a coordinate system of the pultruded strip workpiece is established according to the three-dimensional digital model information, and glue applying track points are planned in the coordinate system, including:

[0012] Based on the three-dimensional digital model information of the pultruded strip workpiece, a feature surface of the pultruded strip workpiece is extracted, the bottom plane of the pultruded strip workpiece is set as the XOY plane, the longest side direction of the pultruded strip workpiece is set as the positive direction of the X axis, and the direction perpendicular to the bottom plane is set as the positive direction of the Z axis, the coordinate origin is determined through the intersection line of the feature surface, and a local coordinate system of the pultruded strip workpiece is established.

[0013] Initial glue applying track points are generated in the local coordinate system, the initial glue applying track points are optimized according to a preset glue applying process requirement, a mapping relationship between the glue applying width and the glue applying speed is established, the glue applying speed of the glue applying track points is adaptively adjusted according to the mapping relationship, and optimized glue applying track points meeting the glue applying process requirement are generated.

[0014] Reference feature points on the surface of the pultruded strip workpiece are identified according to the image information, and the reference feature points are registered with the coordinate system, including:

[0015] Reference feature points are selected from the feature point candidate set according to a preset selection criterion, the selection criterion includes that the feature point response value is greater than a first threshold value, the feature point has the maximum response value within a local non-maximum suppression radius, and the distance between adjacent feature points is greater than a second threshold value.

[0016] establish a mapping relationship between the reference feature point and a theoretical coordinate system, the mapping relationship including converting the reference feature point coordinate in a camera coordinate system to a reference feature point coordinate in a world coordinate system through a rotation matrix and a translation vector;

[0017] optimizing the rotation matrix and the translation vector using a RANSAC algorithm, and obtaining an optimized rotation matrix and an optimized translation vector by minimizing the Euclidean distance between the actual coordinates and the theoretical coordinates of the reference feature points in the world coordinate system;

[0018] applying the optimized rotation matrix and the optimized translation vector to the newly collected feature points on the workpiece surface to realize real-time registration of the reference feature points and the coordinate system.

[0019] obtaining actual position information of the glue coating track points, and performing spatial compensation on the glue coating track points according to the actual position information, including:

[0020] collecting actual position point data and theoretical position point data of the glue coating track, comparing the actual position point data with the theoretical position point data, and calculating a track deviation of the glue coating track;

[0021] constructing a weighted least squares compensation model based on the track deviation, introducing a compensation gain parameter and a compensation constant term into the weighted least squares compensation model, calculating the compensation gain parameter and the compensation constant term with the position deviation, and generating an initial position compensation amount;

[0022] applying the initial position compensation amount to the theoretical position point data to obtain position data after initial compensation, collecting a compensation error between the position data after initial compensation and a target position, and adaptively adjusting the compensation gain parameter based on the compensation error and a preset compensation learning rate;

[0023] real-time collecting a glue coating speed parameter and a glue coating acceleration parameter during the glue coating process, establishing a mapping relationship between the glue coating speed parameter and the glue coating acceleration parameter and the position compensation amount after adaptive adjustment, and calculating an updated position compensation amount according to the mapping relationship;

[0024] setting a position compensation smoothing coefficient, performing weighted smoothing processing on the two updated position compensation amounts using the position compensation smoothing coefficient to generate a final position compensation amount, and superimposing the final position compensation amount on the theoretical position point data of the glue coating track to realize real-time position compensation of the glue coating track.

[0025] controlling the glue coating device to perform glue coating work according to the compensated glue coating track points, including:

[0026] Real-time acquisition of the current spatial position and the current motion posture of the glue gun, calculation of the position deviation of the glue gun by comparing the current spatial position with the target spatial position, and calculation of the posture deviation of the glue gun by comparing the current motion posture with the target motion posture;

[0027] Setting of position compensation parameters and posture compensation parameters based on the position deviation and the posture deviation, superposition of the position compensation parameters to the target spatial position to obtain a compensated motion position, and superposition of the posture compensation parameters to the target motion posture to obtain a compensated motion posture;

[0028] Calculation of motion parameters of each axis servo motor of the glue applying device according to the compensated motion position and the compensated motion posture, wherein the motion parameters include the rotation speed, rotation direction and acceleration of each axis servo motor;

[0029] Generation of motion control instructions of each axis servo motor of the glue applying device based on the motion parameters, and driving of each axis servo motor of the glue applying device by the motion control instructions to drive the glue gun to perform glue applying along the glue applying track.

[0030] Uploading of the compensated glue applying track points, the glue amount parameters and the glue applying pressure parameters to a control system, and generation of a glue applying quality evaluation report by the control system according to the uploaded parameters, wherein the report includes:

[0031] Uploading of the compensated glue applying track points, the glue amount parameters and the glue applying pressure parameters to a control system;

[0032] Calculation of a uniformity index of the glue amount parameters, wherein the uniformity index is calculated based on the variance of single-point glue amount values and average glue amount values, and calculation of a stability index of the glue applying pressure, wherein the stability index is calculated based on the variation amplitude of adjacent time pressure values;

[0033] Establishment of a quality evaluation model according to the uniformity index, the stability index and the compensated glue applying track points, setting of weight coefficients of each index in the quality evaluation model, and calculation of a glue applying quality comprehensive score by weighted calculation of each index and the corresponding weight coefficient;

[0034] Classification of the glue applying quality based on the glue applying quality comprehensive score, and generation of a quality evaluation report according to the classification result of the glue applying quality.

[0035] A second aspect of the embodiment of the application provides a pultruded strip track control automatic glue applying system based on a servo motor, which comprises:

[0036] A first unit is configured to acquire three-dimensional numerical model information of a pultruded strip workpiece, establish a coordinate system of the pultruded strip workpiece according to the three-dimensional numerical model information, and plan glue applying track points in the coordinate system.

[0037] a second unit configured to collect image information of the surface of the pultruded strip workpiece in real time using a visual sensor, identify a reference feature point on the surface of the pultruded strip workpiece according to the image information, register the reference feature point with the coordinate system, obtain actual position information of the glue application track point, and perform spatial compensation on the glue application track point according to the actual position information;

[0038] a third unit configured to control a glue application device to perform glue application according to the compensated glue application track point, collect a glue amount parameter and a glue application pressure parameter of the glue application gun in real time during the glue application, dynamically adjust a movement speed of a servo motor and a glue supply pressure of the glue application gun according to a change trend of the glue amount parameter and the glue application pressure parameter, and control glue amount uniformity of the glue application track to be within a preset track threshold range;

[0039] a fourth unit configured to upload the compensated glue application track point, the glue amount parameter, and the glue application pressure parameter to a control system, and use the glue application quality evaluation report generated by the control system according to the uploaded parameters to optimize a subsequent glue application track.

[0040] In a third aspect, an electronic device is provided, including:

[0041] a processor;

[0042] a memory for storing processor-executable instructions;

[0043] The processor is configured to invoke the instructions stored in the memory to execute the method described above.

[0044] In a fourth aspect, a computer-readable storage medium is provided, which stores computer program instructions, and the computer program instructions are executed by a processor to implement the method described above.

[0045] The present application has the following advantages:

[0046] The method for automatically applying glue to a pultruded strip track based on a servo motor provided by the present application can accurately position the glue application position by collecting three-dimensional model information of the pultruded strip workpiece, establishing a coordinate system to plan a glue application track point, and performing spatial compensation in combination with image information collected in real time by a visual sensor, effectively solving the problem of inaccurate glue application caused by position deviation of the workpiece in a traditional glue application process, and improving the glue application positioning accuracy.

[0047] The present application realizes the uniformity control of the glue amount of the glue trajectory by dynamically adjusting the movement speed of the servo motor and the glue supply pressure of the glue gun through real-time collection of the glue amount parameter and the glue pressure parameter of the glue gun during the gluing operation, overcomes the technical defects of uneven glue amount and large glue quality fluctuation in the traditional gluing method, and significantly improves the consistency and stability of the gluing quality.

[0048] The present application uploads the compensated glue trajectory point, the glue amount parameter and the glue pressure parameter to the control system, generates a glue quality evaluation report and is used for subsequent optimization of the glue trajectory, constructs a closed-loop feedback optimization mechanism, enables the system to continuously learn and improve the gluing process parameters, realizes continuous optimization of the gluing process, greatly improves the production efficiency and product quality, and reduces the demand for manual intervention and production cost. BRIEF DESCRIPTION OF DRAWINGS

[0049] Figure 1 A flowchart of the automatic gluing method of the pultrusion strip trajectory control based on the servo motor of the embodiment of the present application is shown in

[0050] Figure 2 A pultrusion strip workpiece glue trajectory optimization flowchart based on the local coordinate system of the embodiment of the present application is shown in

[0051] Figure 3 A glue trajectory real-time position compensation flowchart based on the adaptive algorithm of the embodiment of the present application is shown in

[0052] Figure 4 A glue quality comprehensive evaluation flowchart based on the multi-parameter fusion of the embodiment of the present application is shown in DETAILED DESCRIPTION

[0053] To make the purpose, technical scheme and advantages of the embodiment of the present application clearer, the technical scheme in the embodiment of the present application will be described clearly and completely in combination with the drawings in the embodiment of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor belong to the scope of protection of the present application.

[0054] The technical scheme of the present application will be described in detail in specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described in some embodiments.

[0055] Figure 1 A flowchart of the automatic gluing method of the pultrusion strip trajectory control based on the servo motor of the embodiment of the present application is shown in Figure 1 As shown in the figure, the method comprises:

[0056] Collect three-dimensional digital model information of the pultruded strip workpiece, and establish a coordinate system of the pultruded strip workpiece according to the three-dimensional digital model information, and plan a glue coating track point in the coordinate system;

[0057] Real-time collection of image information of the surface of the pultruded strip workpiece by a visual sensor, identification of a reference feature point on the surface of the pultruded strip workpiece according to the image information, registration of the reference feature point with the coordinate system, acquisition of actual position information of the glue coating track point, and spatial compensation of the glue coating track point according to the actual position information;

[0058] Control of the glue coating device to perform glue coating work according to the compensated glue coating track point, real-time collection of a glue amount parameter and a glue coating pressure parameter of the glue coating gun during the glue coating work, dynamic adjustment of the movement speed of a servo motor and the glue supply pressure of the glue coating gun according to the change trend of the glue amount parameter and the glue coating pressure parameter, and control of the glue amount uniformity of the glue coating track within a preset track threshold range;

[0059] Upload the compensated glue coating track point, the glue amount parameter, and the glue coating pressure parameter to a control system, and generate a glue coating quality evaluation report by the control system according to the uploaded parameters, and use the glue coating quality evaluation report for subsequent optimization of the glue coating track.

[0060] In an alternative embodiment, collecting three-dimensional digital model information of the pultruded strip workpiece, and establishing a coordinate system of the pultruded strip workpiece according to the three-dimensional digital model information, and planning a glue coating track point in the coordinate system includes:

[0061] Extracting a feature surface of the pultruded strip workpiece based on the three-dimensional digital model information of the pultruded strip workpiece, setting a bottom plane of the pultruded strip workpiece as an XOY plane, setting a longest side direction of the pultruded strip workpiece as a positive direction of an X-axis, setting a direction perpendicular to the bottom plane as a positive direction of a Z-axis, determining a coordinate origin through an intersection of the feature surfaces, and establishing a local coordinate system of the pultruded strip workpiece;

[0062] Generating an initial glue coating track point in the local coordinate system, optimizing the initial glue coating track point according to a preset glue coating process requirement, establishing a mapping relationship between a glue coating width and a glue coating speed, adaptively adjusting the glue coating speed of the glue coating track point according to the mapping relationship, and generating an optimized glue coating track point meeting the glue coating process requirement.

[0063] Collect three-dimensional digital model information of the pultruded strip workpiece. This can be achieved by full-scan of the pultruded strip workpiece by a three-dimensional laser scanner. For example, a three-dimensional laser scanner with a precision of 0.05 mm is used to scan the pultruded strip workpiece from different angles at a collection rate of 50,000 points per second to obtain point cloud data. Subsequently, the collected point cloud data is filtered, denoised, and gridded by point cloud processing software to generate a three-dimensional digital model of the pultruded strip workpiece.

[0064] Based on the acquired three-dimensional model information, it is necessary to extract the feature surface of the pultruded strip workpiece to establish a local coordinate system. Feature surface extraction can be achieved through a region growing algorithm, which takes a point in the point cloud data as a seed point and gradually expands the region according to the similarity of the normal vector and the spatial distance threshold until a complete planar feature is formed. In practical applications, the normal vector angle threshold can be set to 5 degrees and the distance threshold to 0.2 mm, so as to accurately identify the various planar features of the pultruded strip workpiece. For a typical L-shaped pultruded strip workpiece, the bottom plane, side plane and end face can be identified as feature surfaces.

[0065] During the coordinate system establishment process, the bottom plane of the pultruded strip workpiece is set as the XOY plane. The specific operation is to calculate the normal vector of the bottom plane through principal component analysis, and the normal vector is the direction of the Z axis. In practical applications, at least three non-collinear points on the bottom plane can be selected, and the plane equation is fitted through the least squares method to determine the accurate position and normal vector direction of the bottom plane.

[0066] When determining the X-axis direction, it is necessary to identify the longest side of the pultruded strip workpiece. This can be achieved through an edge detection algorithm. First, the Canny edge detection algorithm is applied on the bottom plane to extract the edge line, then the Hough transform is used to identify the straight line segment, and the length of each straight line segment is calculated to select the longest straight line segment direction as the positive direction of the X-axis. For example, for a pultruded strip workpiece with a length of 1000 mm and a width of 50 mm, the 1000 mm edge can be clearly identified as the longest edge through edge detection.

[0067] When determining the coordinate origin, it is necessary to achieve it through the intersection of feature surfaces. For example, the intersection of the bottom plane and two side surfaces can be calculated, and the intersection point of these intersection lines can be used as the coordinate origin. In practical applications, the intersection line equation can be obtained by solving the plane equation set, and the intersection point coordinates can be obtained by solving the intersection line equation set. For a pultruded strip workpiece with a rectangular cross section, the intersection point of the bottom plane and two adjacent side surfaces can be selected as the coordinate origin to establish a complete local coordinate system.

[0068] Initial glue application trajectory points are generated in the established local coordinate system. The initial trajectory point generation can be based on the geometric features of the pultruded strip workpiece, such as setting trajectory points at fixed intervals along the edges that need to be glued. For straight edges, an equal distance sampling method can be used, such as setting a trajectory point every 5 mm; for curved edges, the sampling interval can be adjusted dynamically according to the curvature variation, with more sampling points in areas with high curvature and fewer sampling points in areas with low curvature, ensuring smooth transition of the glue application trajectory.

[0069] The initial gluing track points are optimized according to preset gluing process requirements. The process requirements include gluing width, thickness uniformity, gluing continuity, etc. During the optimization process, a B-spline curve fitting algorithm can be applied to smooth the track points, reduce the mutation points in the track, and improve the smoothness of gluing. At the same time, transition points are added at the corners to ensure smooth passage of the gluing mechanism. For example, for a 90-degree corner, a 10mm radius arc transition can be added, and 5 transition points are evenly distributed on the arc.

[0070] Establishing the mapping relationship between the gluing width and the gluing speed is the key to achieving uniform gluing. Through experimental data analysis, the corresponding relationship between the gluing width and the gluing speed can be obtained. For example, when the gluing pressure is kept at 0.3MPa, the corresponding gluing width is 3mm when the gluing speed is 10mm / s, the corresponding gluing width is 2.5mm when the gluing speed is 15mm / s, and the corresponding gluing width is 2mm when the gluing speed is 20mm / s. This mapping relationship can be stored in the form of a lookup table for real-time calling.

[0071] According to the established mapping relationship, the gluing speed of the gluing track points is adjusted adaptively. In the actual gluing process, if it is detected that the gluing width required at the current position is 2.8mm, the system will automatically adjust the gluing speed to about 12mm / s according to the mapping relationship. For complex-shaped pultruded strip workpieces, different positions may require different gluing widths, and the system will dynamically adjust the gluing speed according to the specific requirements of each track point to ensure the consistency of the gluing quality.

[0072] Through the above steps, the optimized gluing track points that meet the gluing process requirements are finally generated. These track points contain position coordinates and corresponding gluing speed information, which can be directly used to control the gluing mechanism to perform gluing operations. For example, for an L-shaped pultruded strip workpiece with a length of 1000mm and a width of 50mm, gluing is required on both inner side edges, and the final number of track points is about 400, with a gluing speed range of 10-20mm / s, which can achieve uniform gluing effect with a width of 2-3mm and a thickness of 0.5mm.

[0073] Figure 2 The local coordinate system-based pultruded strip workpiece gluing track optimization flowchart of the embodiment of the present application is as follows:

[0074] The figure shows a flow chart of the process of trajectory planning and optimization of the glue application for a pultruded strip workpiece. The figure describes two main steps: first, a local coordinate system is established by obtaining the three-dimensional model information of the pultruded strip workpiece to determine the feature surface, defining the workpiece bottom plane as the XOY plane, setting the longest side direction of the workpiece as the positive direction of the X axis, and setting the direction perpendicular to the bottom plane as the positive direction of the Z axis. The coordinate origin is determined by the intersection of the feature surfaces, thereby establishing a complete local coordinate system. The second step is to generate initial glue application trajectory points in this established local coordinate system, and then optimize these trajectory points according to the pre-set glue application process requirements. In the optimization process, a mapping relationship between the glue application width and the glue application speed is established, and based on this mapping relationship, the glue application speed of the glue application trajectory points is adaptively adjusted, and finally the optimized glue application trajectory points that meet the process requirements are generated. The two steps are closely connected, forming a complete glue application trajectory planning and optimization process.

[0075] In an optional embodiment, identifying the reference feature points on the surface of the pultruded strip workpiece according to the image information, and registering the reference feature points with the coordinate system comprises:

[0076] Screening reference feature points from the feature point candidate set according to a pre-set screening criterion, the screening criterion including that the feature point response value is greater than a first threshold value, the feature point has the maximum response value within a local non-maximum suppression radius, and the distance between adjacent feature points is greater than a second threshold value;

[0077] Establishing a mapping relationship between the reference feature points and the theoretical coordinate system, the mapping relationship including converting the reference feature point coordinates in the camera coordinate system to the reference feature point coordinates in the world coordinate system through a rotation matrix and a translation vector;

[0078] Optimizing the rotation matrix and the translation vector using the RANSAC algorithm, and obtaining the optimized rotation matrix and the optimized translation vector by minimizing the Euclidean distance between the actual coordinates and the theoretical coordinates of the reference feature points in the world coordinate system;

[0079] Applying the optimized rotation matrix and the optimized translation vector to the newly collected feature points on the workpiece surface to realize real-time registration of the reference feature points with the coordinate system.

[0080] Obtaining image information of the surface of the pultruded strip workpiece through image processing technology, and identifying a feature point candidate set therefrom. In order to screen high-quality reference feature points from the feature point candidate set, the present embodiment adopts multiple screening criteria.

[0081] The reference feature points are selected from the feature point candidate set according to a preset selection criterion. The selection criterion includes three aspects: the feature point response value is greater than a first threshold value, the feature point has the maximum response value within a local non-maximum suppression radius, and the distance between adjacent feature points is greater than a second threshold value. In actual application, the first threshold value can be set to 0.015, which means that the response value of the feature point must be greater than 0.015 to be considered as an effective feature point. The local non-maximum suppression radius can be set to 5 pixels, which ensures that within the radius, only the feature point with the maximum response value is retained. The second threshold value can be set to 10 pixels, which ensures that there is sufficient distance between adjacent feature points to avoid excessive density of feature points.

[0082] When the system detects 100 feature point candidates on the workpiece surface, 30 reference feature points that meet the conditions can be selected by applying the above selection criterion. These reference feature points have high response values, are the most prominent in the local area, and maintain appropriate distances from each other, which is beneficial for subsequent coordinate system registration.

[0083] After the reference feature points are selected, a mapping relationship between the feature points and the theoretical coordinate system needs to be established. The mapping relationship includes converting the coordinates of the reference feature points in the camera coordinate system to the coordinates of the reference feature points in the world coordinate system through a rotation matrix and a translation vector. In the camera coordinate system, assume that the coordinates of a reference feature point are (x_c, y_c, z_c), which can be converted to the coordinates (x_w, y_w, z_w) in the world coordinate system through the rotation matrix R and the translation vector T.

[0084] In actual operation, the rotation matrix R is a 3x3 matrix representing the rotation relationship of the camera coordinate system relative to the world coordinate system, and the translation vector T is a three-dimensional vector representing the displacement of the origin of the camera coordinate system relative to the origin of the world coordinate system. Through these two parameters, the conversion between coordinate systems can be realized.

[0085] In order to improve the accuracy of coordinate conversion, the RANSAC algorithm is used to optimize the rotation matrix and the translation vector in this embodiment. The RANSAC algorithm randomly selects sample points from the reference feature point set through iteration, calculates the rotation matrix and the translation vector, and then evaluates the applicability of these parameters. Specifically, the system minimizes the Euclidean distance between the actual coordinates of the reference feature points in the world coordinate system and the theoretical coordinates to obtain the optimized rotation matrix and the optimized translation vector.

[0086] In the implementation of the RANSAC algorithm, the number of iterations can be set to 1000, and the inlier threshold can be set to 2.5 pixels. This means that if a feature point has a Euclidean distance of less than 2.5 pixels from its theoretical position after conversion, it is considered an inlier. The goal of the algorithm is to find the rotation matrix and the translation vector that maximize the number of inliers.

[0087] For example, assume there are 30 reference feature points, after optimization by the RANSAC algorithm, there may be 25 inliers and 5 outliers. The average Euclidean distance error of these inliers may be 1.2 pixels, indicating high registration accuracy. The optimized rotation matrix may be close to the identity matrix, and the translation vector may be (2.3, -1.5, 0.8), representing the displacement of the camera coordinate system relative to the world coordinate system.

[0088] Applying the optimized rotation matrix and translation vector to the newly collected feature points on the workpiece surface, real-time registration of the reference feature points with the coordinate system is achieved. This step enables the system to continuously track the feature points on the workpiece surface and accurately map them into the world coordinate system.

[0089] In actual application scenarios, when the workpiece moves or the camera position changes, the system can collect new images in real time, extract feature points, and convert these feature points to the world coordinate system through the optimized rotation matrix and translation vector. This real-time registration capability is of great significance for industrial applications that require precise positioning, such as automated assembly, quality inspection, etc.

[0090] Through the above method, the system can accurately identify the reference feature points on the surface of the pultruded strip workpiece and accurately register them with the coordinate system, providing a reliable foundation for subsequent workpiece positioning, dimension measurement, defect detection, etc. This method has high precision and robustness, and can adapt to changes in different lighting conditions and workpiece surface states, meeting the strict requirements of industrial production.

[0091] In an optional implementation, the actual position information of the glue applying track points is acquired, and the space compensation of the glue applying track points according to the actual position information includes:

[0092] The actual position point data and the theoretical position point data of the glue applying track are collected, the actual position point data is compared with the theoretical position point data, and the track deviation of the glue applying track is calculated;

[0093] A weighted least squares compensation model is constructed based on the track deviation, a compensation gain parameter and a compensation constant term are introduced into the weighted least squares compensation model, the compensation gain parameter and the compensation constant term are calculated with the position deviation, and an initial position compensation amount is generated;

[0094] The initial position compensation amount is applied to the theoretical position point data to obtain the position data after the first compensation, the compensation error between the position data after the first compensation and the target position is collected, and the compensation gain parameter is adaptively adjusted based on the compensation error and a preset compensation learning rate;

[0095] The gluing speed parameter and the gluing acceleration parameter in the gluing process are collected in real time, a mapping relationship between the gluing speed parameter and the gluing acceleration parameter and the position compensation quantity adjusted adaptively is established, and an updated position compensation quantity is calculated according to the mapping relationship;

[0096] A position compensation smoothing coefficient is set, the adjacent two updated position compensation quantities are weighted and smoothed by using the position compensation smoothing coefficient, a final position compensation quantity is generated, and the final position compensation quantity is superimposed to the theoretical position point data of the gluing track to realize real-time position compensation of the gluing track.

[0097] Actual position point data and theoretical position point data of the gluing track are collected. The actual position point data can be obtained by a position sensor installed on the gluing equipment, for example, a high-precision laser displacement sensor can be used, and the measurement accuracy can reach ±0.01 mm. The theoretical position point data is a set of gluing path points planned in advance according to product design drawings. In actual application, multiple position sensors can be installed on the gluing equipment to collect position data in X, Y and Z directions respectively, and the sampling frequency is set to 100 Hz to ensure the real-time and accuracy of data collection.

[0098] The collected actual position point data and the theoretical position point data are compared to calculate the track deviation of the gluing track. For example, for a sampling point, if the theoretical position is (10.00 mm, 20.00 mm, 5.00 mm) and the actual measured position is (10.15 mm, 19.92 mm, 5.08 mm), the track deviation of the point is (0.15 mm, -0.08 mm, 0.08 mm). Through the deviation analysis of multiple points on the gluing track, a complete track deviation data set can be obtained.

[0099] Based on the obtained track deviation data, a weighted least squares compensation model is constructed. In the model, a compensation gain parameter and a compensation constant term are introduced. The compensation gain parameter is used to adjust the amplitude of compensation, and the compensation constant term is used to correct the inherent bias of the system. In actual application, the compensation gain parameter can be initially set to 0.8, and the compensation constant term can be initially set to the average value of the deviation in each direction. The compensation gain parameter and the compensation constant term are calculated with the position deviation to generate an initial position compensation quantity. Specifically, for the compensation quantity in the X direction, the deviation in the X direction is multiplied by the compensation gain parameter, and then the compensation constant term in the X direction is added to obtain the compensation quantity in the X direction. The compensation quantity calculation methods in Y direction and Z direction are similar.

[0100] The calculated initial position compensation amount is applied to the theoretical position point data to obtain the position data after the first compensation. For example, if the theoretical position of a point is (10.00 mm, 20.00 mm, 5.00 mm), the initial compensation amount in the X direction is 0.15 mm, the initial compensation amount in the Y direction is -0.08 mm, and the initial compensation amount in the Z direction is 0.08 mm, then the position data after the first compensation is (10.15 mm, 19.92 mm, 5.08 mm).

[0101] The compensation error between the position data after the first compensation and the target position is collected. The target position usually refers to the ideal gluing position required by product design. Based on the compensation error and the preset compensation learning rate, the compensation gain parameter is adaptively adjusted. The compensation learning rate can be set to 0.05, indicating the step size of adjusting the compensation gain parameter each time. If the compensation error is large, the compensation gain parameter is increased; if the compensation error is small or overcompensation occurs, the compensation gain parameter is decreased. Through multiple iterations, the compensation gain parameter gradually converges to the optimal value.

[0102] The gluing speed parameter and the gluing acceleration parameter during the gluing process are collected in real time. The gluing speed parameter can be obtained through the speed sensor of the gluing equipment, and the gluing acceleration parameter can be calculated by differentiating the speed data. In actual application, the gluing speed is usually set in the range of 10-50 mm / s, and the acceleration is generally not more than 200 mm / s². The mapping relationship between the gluing speed parameter and the gluing acceleration parameter and the position compensation amount after adaptive adjustment is established, and the updated position compensation amount is calculated according to the mapping relationship.

[0103] For example, when the gluing speed is 30 mm / s, the position compensation amount in the X direction may need to be increased by 0.05 mm; when the gluing acceleration is 100 mm / s², the position compensation amount in the Y direction may need to be increased by 0.03 mm. By establishing such a mapping relationship, the position compensation amount can be dynamically adjusted according to the real-time gluing speed and acceleration, improving the accuracy of compensation.

[0104] The position compensation smoothing coefficient is set to perform weighted smoothing processing on the adjacent two updated position compensation amounts. The position compensation smoothing coefficient can be set to 0.7, indicating that the new compensation amount accounts for 70% of the final compensation amount, and the compensation amount at the previous moment accounts for 30% of the final compensation amount. Through smoothing processing, the mutation of the compensation amount can be avoided, and the gluing trajectory can be more smooth and continuous.

[0105] The position compensation smoothing coefficient is used to perform weighted smoothing on two adjacent updated position compensation values ​​to generate the final position compensation value. For example, if the current X-direction compensation value calculated is 0.18mm, the previous X-direction compensation value is 0.15mm, and the position compensation smoothing coefficient is 0.7, then the final X-direction compensation value is 0.18mm × 0.7 + 0.15mm × 0.3 = 0.171mm.

[0106] The final position compensation is added to the theoretical position data of the gluing track to achieve real-time position compensation of the gluing track. For example, if the theoretical position of a point is (10.00mm, 20.00mm, 5.00mm), the final compensation amounts in the X, Y, and Z directions are 0.171mm, -0.075mm, and 0.084mm, respectively. The compensated position is (10.171mm, 19.925mm, 5.084mm). This method can achieve high-precision real-time compensation of the gluing track, improving gluing quality and efficiency.

[0107] Figure 3 This is a flow chart of real-time position compensation of the gluing track based on the adaptive algorithm according to an embodiment of the present invention:

[0108] The figure describes a complete position compensation process: first, the actual position point data and theoretical position point data of the gluing trajectory are obtained through the data acquisition system, and the trajectory deviation is calculated through comparative analysis; then, based on these deviation data, a weighted least squares compensation model is constructed, and the compensation gain parameter and compensation constant term are introduced into the model, and the initial position compensation amount is generated by calculation; then, the initial compensation amount is applied to the theoretical position point to obtain the compensated position data, and the compensation error is calculated by comparing the target position, and the compensation gain parameter is adaptively adjusted according to the error and the preset compensation learning rate; during the gluing process, the gluing speed and acceleration parameters are collected in real time, and a mapping relationship is established between these dynamic parameters and the adjusted position compensation amount, and the updated position compensation amount is calculated; finally, by setting the position compensation smoothing coefficient, the adjacent updated compensation amounts are weighted and smoothed to generate the final position compensation amount, and it is superimposed on the theoretical trajectory to achieve real-time position compensation of the gluing trajectory.

[0109] In an optional embodiment, controlling the gluing device to perform the gluing operation according to the compensated gluing trajectory point includes:

[0110] The current spatial position and current motion posture of the glue gun are collected in real time, and the position deviation of the glue gun is calculated by comparing the current spatial position with the target spatial position, and the posture deviation of the glue gun is calculated by comparing the current motion posture with the target motion posture;

[0111] Set position compensation parameters and attitude compensation parameters based on the position deviation and the attitude deviation, superimpose the position compensation parameters on the target space position to obtain a compensated motion position, and superimpose the attitude compensation parameters on the target motion attitude to obtain a compensated motion attitude.

[0112] Calculate motion parameters of each axis servo motor of the glue applying device according to the compensated motion position and the compensated motion attitude, the motion parameters including rotation speed, rotation direction and acceleration of each axis servo motor.

[0113] Generate motion control instructions of each axis servo motor of the glue applying device based on the motion parameters, and drive each axis servo motor of the glue applying device to drive the glue gun to perform glue applying work along the glue applying track through the motion control instructions.

[0114] When the glue applying device performs glue applying work, the current space position and the current motion attitude of the glue gun need to be collected in real time. The current space position is obtained by a position sensor installed on the glue gun, which can be an optical encoder, a laser range finder or a visual positioning system, etc. For example, the space position of the nozzle of the glue gun is represented by three-dimensional coordinates (x, y, z) in millimeters. The current motion attitude is obtained by an attitude sensor, such as a gyroscope, an accelerometer or an attitude measurement unit. The attitude can be represented by Euler angles (α, β, γ), which correspond to the rotation angles around the x-axis, y-axis and z-axis respectively, in degrees. The collection frequency is set to 100 Hz, i.e. data is collected every 10 milliseconds, ensuring that the system can respond to changes in position and attitude in a timely manner.

[0115] After obtaining the current space position and the current motion attitude, the system compares them with the preset target space position and target motion attitude, and calculates the position deviation and the attitude deviation. The position deviation is calculated as the difference between the current space position and the target space position in three coordinate axes, i.e. Δx, Δy and Δz. The attitude deviation is calculated as the angle difference between the current motion attitude and the target motion attitude in three rotation axes, i.e. Δα, Δβ and Δγ. For example, if the target position is (100.0, 150.0, 50.0) mm and the current position is (100.5, 149.8, 50.3) mm, the position deviation is (0.5, -0.2, 0.3) mm; if the target attitude is (30.0, 45.0, 60.0) degrees and the current attitude is (29.8, 45.2, 60.1) degrees, the attitude deviation is (-0.2, 0.2, 0.1) degrees.

[0116] Based on the calculated position deviation and attitude deviation, the system sets position compensation parameters and attitude compensation parameters. The position compensation parameter setting adopts a proportional-integral-derivative (PID) control algorithm, which is calculated according to the size, trend of change and cumulative error of the position deviation. Specifically, for each coordinate axis, the position compensation parameter is equal to the position deviation multiplied by the proportional coefficient Kp, plus the integral of the position deviation multiplied by the integral coefficient Ki, and plus the differential of the position deviation multiplied by the differential coefficient Kd. In this embodiment, the proportional coefficient Kp of the x-axis direction is set to 1.2, the integral coefficient Ki is set to 0.05, and the differential coefficient Kd is set to 0.08; the parameters of the y-axis and z-axis are set similarly. The setting of the attitude compensation parameter also adopts a similar PID control algorithm, but the parameter values are different, for example, the proportional coefficient of rotation around the x-axis is set to 1.5, the integral coefficient is set to 0.03, and the differential coefficient is set to 0.1.

[0117] After calculating the position compensation parameters and the attitude compensation parameters, the position compensation parameters are superimposed on the target space position to obtain the compensated motion position; the attitude compensation parameters are superimposed on the target motion attitude to obtain the compensated motion attitude. For example, if the target position is (100.0, 150.0, 50.0) mm, the position compensation parameters are (-0.6, 0.3, -0.2) mm, and the compensated motion position is (99.4, 150.3, 49.8) mm; if the target attitude is (30.0, 45.0, 60.0) degrees, the attitude compensation parameters are (0.3, -0.2, 0.1) degrees, and the compensated motion attitude is (30.3, 44.8, 60.1) degrees.

[0118] According to the compensated motion position and the motion attitude, the system needs to calculate the motion parameters of the servo motors of each axis of the glue applying device. The glue applying device usually includes a 6-degree-of-freedom mechanical arm, and each degree of freedom corresponds to a servo motor. Through inverse kinematics algorithm, the spatial position and attitude are converted into joint angles. For example, for a 6-axis mechanical arm, the compensated motion position (99.4, 150.3, 49.8) mm and the motion attitude (30.3, 44.8, 60.1) degrees can be converted into 6 joint angle values: θ1=28.5 degrees, θ2=35.2 degrees, θ3=62.7 degrees, θ4=15.3 degrees, θ5=40.1 degrees, and θ6=55.8 degrees.

[0119] Based on the joint angle values, the motion parameters of each axis servo motor are calculated, including speed, direction and acceleration. The speed calculation is based on the difference between the current joint angle and the target joint angle, as well as the preset motion time. For example, if the first axis current angle is 25.0 degrees, the target angle is 28.5 degrees, and the preset motion time is 0.2 seconds, the required angular velocity is (28.5-25.0) / 0.2=17.5 degrees / second. Considering the reduction ratio of the motor (such as 50:1), the actual speed of the motor is 17.5x50=875 degrees / second, which is equivalent to 2.43 revolutions / second. The direction is determined according to the positive and negative of the angle change, and the positive value represents clockwise rotation, and the negative value represents counterclockwise rotation. The acceleration is set as the rate of change of the speed, and the trapezoidal speed curve is usually used, that is, the mode of first acceleration, uniform speed running, and then deceleration, and the acceleration and deceleration are both set to 5 times / second of the speed, that is, 17.5x5=87.5 degrees / second² in this example.

[0120] Based on the calculated motion parameters, the system generates motion control instructions for each axis servo motor of the glue applying device. The control instructions are in the form of pulse+direction, or in the form of industrial field bus protocol such as EtherCAT, PROFINET, etc. The control instructions contain motor number, target position, running speed, acceleration, etc. For example, for the first axis motor, the control instruction may contain: motor number=1, target position=28.5 degrees (converted to encoder pulse number), running speed=17.5 degrees / second, acceleration=87.5 degrees / second². These control instructions are sent to each axis servo driver through the controller, and the driver controls the motor to move according to the specified parameters after receiving the instructions.

[0121] Through the above motion control instructions, each axis servo motor of the glue applying device drives the glue gun to perform glue applying along the compensated glue applying trajectory. During the glue applying process, the system continuously performs real-time acquisition of position and attitude, deviation calculation, parameter compensation and control instruction generation, forming a closed loop control, ensuring that the glue gun always moves according to the expected trajectory, and improving the glue applying precision and quality. In practical application, this method can control the glue applying position accuracy within ±0.1mm and the attitude accuracy within ±0.1 degree, meeting the requirements of high-precision glue applying operation.

[0122] In an alternative embodiment, the compensated glue applying trajectory points, the glue amount parameters and the glue applying pressure parameters are uploaded to a control system, and the control system generates a glue applying quality evaluation report according to the uploaded parameters, which includes:

[0123] The compensated glue applying trajectory points, the glue amount parameters and the glue applying pressure parameters are uploaded to a control system;

[0124] A uniformity index of the glue amount parameter is calculated, the uniformity index being calculated based on a variance of a single-point glue amount value and an average glue amount value, and a stability index of the gluing pressure is calculated, the stability index being calculated based on a variation amplitude of pressure values at adjacent time points;

[0125] A quality evaluation model is established according to the uniformity index, the stability index and the compensated gluing track point, a weight coefficient of each index being set in the quality evaluation model, and a gluing quality comprehensive score being calculated through weighted calculation of each index and the corresponding weight coefficient;

[0126] The gluing quality is graded based on the gluing quality comprehensive score, and a quality evaluation report is generated according to a grading result of the gluing quality.

[0127] After the gluing system completes track compensation, the key parameters in the gluing process are collected by a data acquisition module. These parameters include compensated gluing track point coordinate data, real-time glue amount parameters and gluing pressure parameters. The data acquisition module packages these parameters into a data packet in a standard format and uploads them to a central control system through industrial Ethernet or wireless communication. After receiving the data, the control system first performs data verification to ensure the integrity and validity of the data, and then stores the data in a dedicated parameter database to prepare for subsequent quality evaluation.

[0128] After the control system receives the parameter data, it begins to calculate the uniformity index of the glue amount parameter. The system extracts all glue amount parameter values from the database, assuming that there are n sampling points, and the glue amount values of each point are g 1 , g 2 ...g n . The system first calculates the average glue amount value g_avg, which is the arithmetic mean of all glue amount values. Then, the system calculates the difference between the glue amount value of each point and the average glue amount value, and the sum of the squares of these differences, and then divides the sum by the number of sampling points to obtain the variance value. The uniformity index is obtained by normalizing the variance value, so that its value range is between 0 and 1, where 0 represents complete non-uniformity and 1 represents complete uniformity. For example, in a certain gluing process, the system collects 100-point glue amount data, the average glue amount is 5.2 milliliters, the calculated variance is 0.18, and the normalized uniformity index is 0.92, indicating that the glue amount distribution is quite uniform.

[0129] The stability index of the gluing pressure is calculated. The system extracts all pressure parameter values from the database, assuming that there are m time points of pressure values, respectively p 1 , p 2 ...p n . The system calculates the variation amplitude of pressure values at adjacent time points, i.e. |p 2 -p 1 |, |p3 -p 2 |...|p n -p -1 |。The system calculates the average of these variation amplitudes and compares them with the preset standard variation amplitude to obtain a stability index. The stability index is also normalized so that its value range is between 0 and 1, where 0 represents complete instability and 1 represents complete stability. For example, during the same gluing process, the system collects pressure data at 200 time points, and the calculated average variation amplitude is 0.05 MPa. The preset standard variation amplitude is 0.1 MPa, and the normalized stability index after normalization processing is 0.88, indicating that the pressure control is relatively stable.

[0130] Based on the calculated uniformity index, stability index, and compensated gluing trajectory points, the system establishes a quality evaluation model. This model uses a weighted scoring method to assign different weight coefficients to each index. In this embodiment, the weight coefficient of the uniformity index is set to 0.4, the weight coefficient of the stability index is set to 0.3, and the weight coefficient of the trajectory accuracy index is set to 0.3.

[0131] The trajectory accuracy index is calculated by comparing the deviation of the compensated gluing trajectory points and the ideal trajectory points, and is also normalized to between 0 and 1. The system multiplies each index by the corresponding weight coefficient and then sums them up to obtain a comprehensive gluing quality score. For example, the uniformity index of a certain gluing process is 0.92, the stability index is 0.88, and the trajectory accuracy index is 0.95, so the comprehensive score is 0.92 x 0.4 + 0.88 x 0.3 + 0.95 x 0.3 = 0.917.

[0132] Based on the comprehensive gluing quality score, the gluing quality is classified. The classification standard is set as follows: the comprehensive score is above 0.9 for A level (excellent), between 0.8 and 0.9 for B level (good), between 0.7 and 0.8 for C level (qualified), and below 0.7 for D level (unqualified). According to this standard, the gluing quality in the above example is rated as A level.

[0133] According to the classification results, a quality evaluation report is generated, including the gluing time, gluing area, specific values of each index, comprehensive score, quality level, and improvement suggestions. For different levels of evaluation results, the system gives corresponding improvement suggestions. For example, for B level results, the system may suggest optimizing the glue amount control parameters; for C level results, the system may suggest checking the pressure control system of the gluing equipment; for D level results, the system may suggest stopping for maintenance and recalibrating the equipment.

[0134] The quality evaluation report is saved in the form of an electronic document in the system database, can be displayed in real time through the user interface, or sent to relevant personnel through the network. The system also compares the evaluation results with historical data to analyze the trend of the glue application quality and provide decision support for production management. In this way, the glue application system can achieve comprehensive evaluation and continuous improvement of the glue application quality, and improve product quality and production efficiency.

[0135] Figure 4 A flowchart of the glue application quality comprehensive evaluation process based on multi-parameter fusion according to an embodiment of the present application is shown in the following figure:

[0136] The figure shows a complete workflow diagram of a glue application quality evaluation system. The process starts with the data collection stage, where the system first synchronously uploads the position-compensated and optimized glue application trajectory point data, real-time monitored glue amount parameter data, and glue application pressure parameter data to the central control system for unified processing and analysis. In the data processing stage, the system calculates two key quality indicators: the uniformity indicator of the glue amount parameter and the stability indicator of the glue application pressure. The uniformity indicator is obtained by calculating the variance between the single-point glue amount value of each glue application point and the average glue amount value of the entire glue application process. This indicator can effectively reflect the consistency of the glue amount distribution during the glue application process. The stability indicator is determined by analyzing the variation amplitude of the pressure values at adjacent time points. This indicator can accurately reflect the fluctuation of the glue application pressure. Based on these processed indicator data and the position-compensated and optimized glue application trajectory point information, the system constructs a comprehensive quality evaluation model. In this evaluation model, the system assigns appropriate weight coefficients to different evaluation indicators. By weighting the quality indicators and their corresponding weight coefficients, the system finally obtains a comprehensive score reflecting the overall glue application quality level. This multi-parameter fusion evaluation method not only comprehensively reflects the quality status of the glue application process, but also provides reliable data support for subsequent process parameter optimization and equipment state monitoring.

[0137] In a second aspect of the embodiment of the present application, a pultrusion strip trajectory control automatic glue application system based on a servo motor is provided, which comprises:

[0138] A first unit is configured to collect three-dimensional numerical model information of a pultrusion strip workpiece, establish a coordinate system of the pultrusion strip workpiece according to the three-dimensional numerical model information, and plan glue application trajectory points in the coordinate system.

[0139] A second unit is configured to collect image information of the surface of the pultrusion strip workpiece in real time using a vision sensor, identify reference feature points on the surface of the pultrusion strip workpiece according to the image information, register the reference feature points with the coordinate system, obtain actual position information of the glue application trajectory points, and perform spatial compensation on the glue application trajectory points according to the actual position information.

[0140] The third unit is configured to control the glue applying device to perform the glue applying operation according to the compensated glue applying track point; during the glue applying operation, the glue amount parameter and the glue applying pressure parameter of the glue applying gun are collected in real time, and the motion speed of the servo motor and the glue supply pressure of the glue applying gun are dynamically adjusted according to the change trend of the glue amount parameter and the glue applying pressure parameter, so that the glue amount uniformity of the glue applying track is controlled within the preset track threshold range.

[0141] The fourth unit is configured to upload the compensated glue applying track point, the glue amount parameter and the glue applying pressure parameter to a control system, and the control system generates a glue applying quality evaluation report according to the uploaded parameters, and uses the glue applying quality evaluation report for subsequent optimization of the glue applying track.

[0142] In a third aspect, an electronic device is provided, comprising:

[0143] a processor;

[0144] a memory for storing processor-executable instructions;

[0145] The processor is configured to invoke the instructions stored in the memory to execute the method described above.

[0146] In a fourth aspect, a computer-readable storage medium is provided, which stores computer program instructions, and the computer program instructions are executed by a processor to implement the method described above.

[0147] The present application can be a method, device, system and / or computer program product. The computer program product can include a computer readable storage medium having computer readable program instructions stored therein, which are used to perform various aspects of the present application.

[0148] Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present application, and not to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: it can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacement to part or all of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for automatic glueing based on servo motor control of a pultruded strip trajectory, characterized in that, The application relates to a real-time position compensation method for a glue coating trajectory of a pultrusion strip workpiece. The method comprises the following steps: collecting three-dimensional model information of the pultrusion strip workpiece, establishing a coordinate system of the pultrusion strip workpiece according to the three-dimensional model information, and planning glue coating track points in the coordinate system; visual sensors are used to collect image information of the surface of the pultrusion strip workpiece in real time, reference feature points on the surface of the pultrusion strip workpiece are identified according to the image information, the reference feature points are matched with the coordinate system, actual position information of the glue coating track points is obtained, space compensation is performed on the glue coating track points according to the actual position information, and the method comprises the following steps: actual position point data and theoretical position point data of the glue coating track are collected, the actual position point data is compared with the theoretical position point data, and a track deviation of the glue coating track is calculated; a weighted least square compensation model is constructed based on the track deviation, a compensation gain parameter and a compensation constant term are introduced into the weighted least square compensation model, the compensation gain parameter and the compensation constant term are calculated with the position deviation, and initial position compensation amounts are generated; the initial position compensation amounts are applied to the theoretical position point data, position data after primary compensation is obtained, compensation errors between the position data after primary compensation and target positions are collected, the compensation gain parameter is adaptively adjusted based on the compensation errors and a preset compensation learning rate, glue coating speed parameters and glue coating acceleration parameters in the glue coating process are collected in real time, the glue coating speed parameters and the glue coating acceleration parameters are matched with the position compensation amounts after adaptive adjustment, updated position compensation amounts are calculated according to the matching relationship, a position compensation smoothing coefficient is set, the position compensation smoothing coefficient is used to perform weighted smoothing processing on adjacent two updated position compensation amounts, final position compensation amounts are generated, the final position compensation amounts are superimposed to the theoretical position point data of the glue coating track, and real-time position compensation of the glue coating track is realized, the glue coating device is controlled to perform glue coating work according to the compensated glue coating track points, during the glue coating work, glue amount parameters and glue coating pressure parameters of the glue coating gun are collected in real time, the movement speed of a servo motor and the glue supply pressure of the glue coating gun are dynamically adjusted according to the change trend of the glue amount parameters and the glue coating pressure parameters, the glue amount uniformity of the glue coating track is controlled within a preset track threshold range, and the method comprises the following steps: the current spatial position and the current movement posture of the glue coating gun are collected in real time, the position deviation of the glue coating gun is calculated by comparing the current spatial position with a target spatial position, and the posture deviation of the glue coating gun is calculated by comparing the current movement posture with a target movement posture; position compensation parameters and posture compensation parameters are set based on the position deviation and the posture deviation, the position compensation parameters are superimposed to the target spatial position to obtain a compensated movement position, and the posture compensation parameters are superimposed to the target movement posture to obtain a compensated movement posture; movement parameters of servo motors of the glue coating device are calculated according to the compensated movement position and the compensated movement posture, the movement parameters comprise the rotation speed, the rotation direction and the acceleration of the servo motors. Generate a motion control instruction of each axis servo motor of the glue applying device based on the motion parameter, drive each axis servo motor of the glue applying device to drive the glue applying gun to perform the glue applying operation along the glue applying track through the motion control instruction; Upload the compensated glue applying track point, the glue amount parameter and the glue applying pressure parameter to a control system, and generate a glue applying quality evaluation report according to the uploaded parameters, and use the glue applying quality evaluation report for subsequent optimization of the glue applying track.

2. The method of claim 1, wherein, Collect three-dimensional digital model information of the pultruded strip workpiece, establish a coordinate system of the pultruded strip workpiece according to the three-dimensional digital model information, and plan a glue applying track point in the coordinate system, including: Extract a feature surface of the pultruded strip workpiece based on the three-dimensional digital model information of the pultruded strip workpiece, set a bottom plane of the pultruded strip workpiece as an XOY plane, set a longest side direction of the pultruded strip workpiece as a positive direction of an X axis, set a direction perpendicular to the bottom plane as a positive direction of a Z axis, determine a coordinate origin through an intersection line of the feature surfaces, and establish a local coordinate system of the pultruded strip workpiece; Generate an initial glue applying track point in the local coordinate system, optimize the initial glue applying track point according to a preset glue applying process requirement, establish a mapping relationship between a glue applying width and a glue applying speed, adaptively adjust a glue applying speed of the glue applying track point according to the mapping relationship, and generate an optimized glue applying track point meeting the glue applying process requirement.

3. The method of claim 1, wherein, Identify a reference feature point on a surface of the pultruded strip workpiece according to the image information, and register the reference feature point with the coordinate system, including: Screen the reference feature point from the feature point candidate set according to a preset screening criterion, and the screening criterion includes that a feature point response value is greater than a first threshold value, the feature point has a maximum response value within a local non-maximum suppression radius, and a distance between adjacent feature points is greater than a second threshold value; Establish a mapping relationship between the reference feature point and a theoretical coordinate system, and the mapping relationship includes converting reference feature point coordinates in a camera coordinate system to reference feature point coordinates in a world coordinate system through a rotation matrix and a translation vector; Optimize the rotation matrix and the translation vector through a RANSAC algorithm, and obtain an optimized rotation matrix and an optimized translation vector by minimizing Euclidean distances between actual coordinates and theoretical coordinates of the reference feature points in the world coordinate system; Apply the optimized rotation matrix and the optimized translation vector to newly collected feature points on the workpiece surface, and realize real-time registration of the reference feature point with the coordinate system.

4. The method of claim 1, wherein, Upload the compensated glue applying track point, the glue amount parameter and the glue applying pressure parameter to a control system, and generate a glue applying quality evaluation report according to the uploaded parameters, including: Upload the compensated glue applying track point, the glue amount parameter and the glue applying pressure parameter to a control system; Calculate a uniformity index of the glue amount parameter, and the uniformity index is calculated based on a variance between a single-point glue amount value and an average glue amount value, and simultaneously calculate a stability index of the glue applying pressure, and the stability index is calculated based on a variation amplitude of pressure values at adjacent time points; A quality evaluation model is established according to the uniformity index, the stability index and the compensated glue applying track points, and weight coefficients of each index are set in the quality evaluation model; a glue applying quality comprehensive score is obtained through weighted calculation of each index and the corresponding weight coefficient; The glue applying quality is graded based on the glue applying quality comprehensive score, and a quality evaluation report is generated according to the grading result of the glue applying quality.

5. A servo motor based pultrusion trajectory control automatic glue application system for implementing the method of any of the preceding claims 1-4, characterized in that, Comprise: A first unit is configured to collect three-dimensional numerical model information of a pultruded strip workpiece, establish a coordinate system of the pultruded strip workpiece according to the three-dimensional numerical model information, and plan glue applying track points in the coordinate system; A second unit is configured to collect image information of the surface of the pultruded strip workpiece in real time by using a visual sensor, identify reference feature points on the surface of the pultruded strip workpiece according to the image information, register the reference feature points with the coordinate system, obtain actual position information of the glue applying track points, and perform spatial compensation on the glue applying track points according to the actual position information; A third unit is configured to control a glue applying device to perform glue applying operation according to the compensated glue applying track points; During the glue applying operation, the glue amount parameter and the glue applying pressure parameter of the glue applying gun are collected in real time, the motion speed of a servo motor and the glue supply pressure of the glue applying gun are dynamically adjusted according to the change trend of the glue amount parameter and the glue applying pressure parameter, so that the glue amount uniformity of the glue applying track is controlled within a preset track threshold range; A fourth unit is configured to upload the compensated glue applying track points, the glue amount parameter and the glue applying pressure parameter to a control system, and the control system generates a glue applying quality evaluation report according to the uploaded parameters, and uses the glue applying quality evaluation report for subsequent optimization of the glue applying track.

6. An electronic device, comprising: Comprise: A processor; A memory for storing processor-executable instructions; The processor is configured to invoke the instructions stored in the memory to execute the method of any one of claims 1 to 4.

7. A computer-readable storage medium having stored thereon computer program instructions, wherein, The computer program instructions are executed by the processor to implement the method of any one of claims 1 to 4.

Images