Plastic part deformation detection method, device, computer equipment and storage medium

Abstract

The present application relates to a method, device, computer equipment and storage medium for detecting deformation of plastic parts. The method includes obtaining three-dimensional information of plastic parts, digitally transforming the three-dimensional information through spatial data processing technology to obtain three-dimensional shape data; performing data gridding processing on the three-dimensional shape data, and aligning it with a preset product model through shape matching technology, calculating the deviation value of each position of the plastic part, and generating a three-dimensional deviation heat map when the deviation value exceeds the preset tolerance range; collecting process parameter data in the production process of plastic parts, and based on the three-dimensional deviation heat map and process data, analyzing the influencing parameters through a preset deformation tracing model to generate key influencing factors; generating a parameter adjustment scheme based on the key influencing parameters, and then adaptively adjusting the process parameter data. The present application has the effect of improving the deformation detection and optimization efficiency of plastic parts.

Description

Technical Field

[0001] The present application relates to the technical field of plastic part quality inspection, and in particular to a plastic part deformation inspection method, device, computer equipment and storage medium. Background Art

[0002] At present, plastic parts production quality inspection technology is mainly used to determine whether the quality of plastic parts during the molding process meets the design standards. Plastic parts are prone to deformation due to uneven cooling, mold temperature differences or environmental factors. The deformation may cause dimensional deviations or surface defects in the finished product, affecting the actual application performance of the product.

[0003] Existing plastic part deformation detection technologies are mostly based on image recognition methods, which use industrial cameras to capture images of plastic parts and use image processing technology to identify deformation areas and their deviation distributions. However, this deformation detection method based on image recognition usually only focuses on the results of deformation and cannot deeply analyze the specific causes of deformation. In addition, in terms of adjustment and optimization of deformation problems, existing methods rely on manual experience adjustment and lack optimization solutions based on data modeling, resulting in low adjustment efficiency and insufficient accuracy.

[0004] The above-mentioned existing technical solutions have the following defects: the existing plastic part deformation detection method based on image recognition is difficult to trace the cause of deformation, resulting in poor optimization ability of the production process, so there is room for improvement. Summary of the invention

[0005] In order to improve the detection and optimization efficiency of plastic part deformation, the present application provides a plastic part deformation detection method, device, computer equipment and storage medium.

[0006] The above-mentioned invention objective of the present application is achieved through the following technical solutions: A plastic part deformation detection method, the plastic part deformation detection method comprising: Acquire three-dimensional information of the plastic part, and digitally transform the three-dimensional information through spatial data processing technology to obtain three-dimensional shape data; Performing data gridding processing on the three-dimensional shape data, and aligning it with a preset product model through shape matching technology, calculating the deviation value of each position of the plastic part, and generating a three-dimensional deviation heat map when the deviation value exceeds a preset tolerance range; Collecting process parameter data during the production of the plastic parts, and based on the three-dimensional deviation heat map and the process data, analyzing the influencing parameters through a preset deformation tracing model to generate key influencing factors; A parameter adjustment scheme is generated according to the key influencing parameters, and then the process parameter data is adaptively adjusted.

[0007] By adopting the above technical solution, by acquiring the three-dimensional information of the plastic part and digitally transforming the three-dimensional information through the spatial data processing technology, the geometric shape data of the plastic part can be completely and accurately obtained, avoiding the problem of incomplete or distorted data affecting the subsequent analysis, thereby laying a reliable data foundation for deviation analysis and deformation detection; by gridding the three-dimensional shape data and aligning it with the preset product model through shape matching technology, the geometric difference between the plastic part and the product model can be quickly located, and the deformation area and severity of the plastic part can be intuitively reflected, so that the production personnel can find problems in time and make targeted adjustments; by collecting the process parameter data in the production process of the plastic part, and analyzing the influencing parameters based on the three-dimensional deviation heat map and process data, the key process parameters that cause the deformation of the plastic part in the production process can be accurately identified, avoiding the inefficiency and misjudgment caused by the traditional experience-based adjustment, thereby realizing the scientific optimization of the production process; by generating parameter adjustment schemes according to the key influencing parameters and adaptively adjusting the process parameter data, the key process parameters can be dynamically optimized in the production process, and the accuracy and efficiency of the adjustment can be improved, thereby significantly reducing the probability of plastic part deformation, and improving product qualification rate and production efficiency.

[0008] In one example, the present application may be further configured as follows: the three-dimensional shape data is gridded, and aligned with a preset product model through shape matching technology, the deviation value of each position of the plastic part is calculated, and when the deviation value exceeds a preset tolerance range, a three-dimensional deviation heat map is generated, specifically including: The three-dimensional shape data is converted into a grid model with a regular topological structure by a grid processing technology; Using a shape matching algorithm, the mesh model and the preset product model are preliminarily aligned in position and direction through a global alignment technique, and local alignment optimization is performed through a local alignment technique; Calculating the deviation value distribution between the plastic part and the preset product model based on the geometric space difference, and marking the area exceeding the tolerance range as a high deviation area through layered threshold determination, thereby generating a deviation distribution result; A three-dimensional deviation heat map is generated according to the deviation distribution result, and the deviation amplitude and distribution range of each deviation area are marked by color gradient.

[0009] By adopting the above technical solution, the three-dimensional shape data is converted into a grid model with a regular topological structure through grid processing technology, and the discrete point cloud structure in the original data can be converted into a regular geometric model, thereby improving the accuracy and consistency of shape expression, thereby providing a higher-precision data basis for subsequent deviation calculation; by using the shape matching algorithm to align the grid model with the preset product model in position and direction, the global position matching can be quickly completed and the local detail deviation can be optimized to ensure that the geometric features of the plastic part and the product model are highly consistent, thereby making the deviation analysis results more accurate; by calculating the deviation value distribution of the plastic part and the product model based on the geometric space difference, and marking the high deviation area through hierarchical threshold determination, the deformation area beyond the tolerance range can be clearly identified, avoiding missing local problems due to overall judgment, thereby more efficiently performing deformation control; by generating a three-dimensional deviation heat map and marking the deviation amplitude and distribution range through color gradients, the deviation characteristics of the plastic part can be displayed in an intuitive way, helping production personnel to quickly locate the problem area, thereby shortening the detection time and improving processing efficiency.

[0010] In one example, the present application can be further configured as follows: the deviation value distribution between the plastic part and the preset product model is calculated based on the geometric space difference, and the area exceeding the tolerance range is marked as a high deviation area through a hierarchical threshold determination, thereby generating a deviation distribution result, specifically including: Using a spatial point difference algorithm, the geometric spatial difference between each grid point in the grid model and the corresponding position of the preset product model is calculated point by point, and the deviation value of each grid point is recorded; Comparing the deviation value with a preset tolerance range, and performing grading processing on the deviation value through a stratified threshold determination algorithm to obtain deviation distribution grading data; According to the deviation distribution classification data, high deviation areas are marked as specific levels, and deviation weights are assigned to highlight key deformation areas, and the deviation distribution data is smoothed to generate the deviation distribution result.

[0011] By adopting the above technical solution, by using the spatial point difference algorithm to calculate the geometric space difference between each grid point in the grid model and the corresponding position of the product model point by point, the deviation data between the plastic part and the product model can be obtained efficiently and accurately, avoiding the problems caused by insufficient calculation accuracy in traditional methods, thereby ensuring the credibility of the deviation analysis results; by comparing the deviation value with the preset tolerance range and grading the deviation value through a hierarchical threshold judgment algorithm, the deformation of the plastic part can be classified according to the degree of deviation, helping production personnel to quickly distinguish high-deviation areas that need to be treated as priority, thereby optimizing the efficiency of problem handling; by marking high-deviation areas according to the deviation distribution classification data and assigning deviation weights, and at the same time smoothing the deviation distribution data, it is possible to highlight the key deformation areas and improve the overall continuity and visualization of the data, thereby enhancing the application value of the deviation data in subsequent production optimization.

[0012] In one example, the present application may be further configured as follows: the construction of the preset deformation tracing model specifically includes: Acquire historical production data, organize the historical production data into a multidimensional time series data set, perform cluster analysis based on cooling temperature difference gradient, classify the historical production data according to the analysis results, and obtain a model training data set; A multivariate regression algorithm is adopted, with the model training data set as input, to analyze the correlation between production process parameters and deviation distribution, and to extract influencing factors and the influence weights of the influencing factors, thereby constructing the deformation tracing model.

[0013] By adopting the above technical solution, by acquiring historical production data and organizing it into a multidimensional time series data set, the scattered production data can be structured, providing a complete data basis with a time dimension for subsequent analysis, thereby better supporting the analysis of deformation causes; by performing cluster analysis based on the cooling temperature difference gradient and classifying the historical data, the production data can be grouped according to the temperature difference characteristics, improving the feature expression ability of the model training data, so that the model can more accurately predict the cause of deformation; by adopting a multivariate regression algorithm to analyze the correlation between production process parameters and deviation distribution, the key process parameters and their weights that affect deformation can be accurately identified, avoiding analysis difficulties caused by the complex correlation between parameters, thereby providing a scientific basis for process optimization; by constructing a deformation traceability model, a quantitative relationship between process parameters and deformation characteristics can be established, thereby significantly improving the degree of automation and accuracy of deformation analysis.

[0014] In one example, the present application may be further configured as follows: performing cluster analysis based on the cooling temperature difference gradient, classifying the historical production data according to the analysis results, and obtaining a model training data set, specifically including: Extracting temperature distribution data of the cooling mold from the historical production data, and calculating the temperature difference gradient of different areas of the cooling mold during the cooling process; Based on the temperature difference gradient, the corresponding temperature difference data are grouped using a cluster analysis algorithm to divide them into a high temperature difference group, a medium temperature difference group and a low temperature difference group; In each temperature difference group, the spatial position characteristics and deviation amplitude characteristics of the three-dimensional deviation are extracted according to the corresponding deviation distribution data, and the spatial position characteristics and the deviation amplitude characteristics are associated with the production process parameters, and then organized into the model training data set containing the grouping identifier.

[0015] By adopting the above technical solution, by extracting the cooling mold temperature distribution data in the historical production data and calculating the temperature difference gradient, the temperature change in the cooling process can be quantified in the form of a gradient, avoiding the influence of the clustering effect due to discontinuous or incomplete temperature data, thereby more accurately expressing the cooling characteristics; by grouping the temperature difference data based on the temperature difference gradient using the clustering analysis algorithm, it is possible to effectively distinguish high temperature difference, medium temperature difference and low temperature difference groups, improve the classification accuracy of the model training data, and thus enhance the prediction ability of the deformation traceability model; by extracting the spatial position characteristics and deviation amplitude characteristics of the deviation distribution in each temperature difference group and associating them with the production process parameters, it is possible to establish a direct correlation between the deviation characteristics and the process parameters, provide high-quality feature data for model training, and thus significantly improve the prediction performance and applicability of the model.

[0016] In one example, the present application may be further configured as follows: generating a parameter adjustment scheme according to the key influencing parameters, and then adaptively adjusting the process parameter data, specifically includes: Determine the key process parameters that affect the deviation distribution of plastic parts according to the weights and influence ranges of the key influencing parameters, wherein the key process parameters include cooling time, mold temperature distribution, injection pressure, etc.; With respect to the cooling time and the mold temperature distribution, a temperature adjustment scheme is generated by optimizing the cooling strategy, and with respect to the injection pressure, a pressure adjustment scheme is generated by optimizing the pressure change pattern during the injection molding process, thereby obtaining the parameter adjustment scheme; The process parameter data is adjusted according to the parameter adjustment scheme to reduce the probability of deformation of the plastic part.

[0017] By adopting the above technical scheme, by determining the key process parameters that affect the deviation distribution of plastic parts according to the weights and influence ranges of the key influencing parameters, it is possible to accurately screen the parameters that have the greatest impact on deformation, avoid the interference of irrelevant or minor parameters on the adjustment strategy, and thus improve the targeted optimization; by generating a temperature adjustment scheme for the cooling time and mold temperature distribution, and generating a pressure adjustment scheme for the injection pressure, it is possible to formulate targeted optimization strategies based on the action mechanisms of different parameters, thereby effectively improving the cooling uniformity and the stability of the injection molding process; by adjusting the process parameter data according to the adjustment scheme, it is possible to dynamically optimize the key process parameters in the production process, avoid the lag and error of traditional manual adjustment, thereby reducing the probability of deformation, and improving production efficiency and the molding quality of plastic parts.

[0018] The second object of the invention is achieved by the following technical solutions: A plastic part deformation detection device, the plastic part deformation detection device comprising: A three-dimensional information acquisition module is used to obtain three-dimensional information of the plastic part, and digitally transform the three-dimensional information through spatial data processing technology to obtain three-dimensional shape data; A shape deviation analysis module, for performing data gridding processing on the three-dimensional shape data, aligning it with a preset product model through shape matching technology, calculating the deviation value of each position of the plastic part, and generating a three-dimensional deviation heat map when the deviation value exceeds a preset tolerance range; A process data analysis module, used for collecting process parameter data in the production process of the plastic parts, and based on the three-dimensional deviation heat map and the process data, analyzing the influencing parameters through a preset deformation tracing model to generate key influencing factors; The parameter adjustment module is used to generate a parameter adjustment scheme according to the key influencing parameters, and then adaptively adjust the process parameter data.

[0019] By adopting the above technical solution, by acquiring the three-dimensional information of the plastic part and digitally transforming the three-dimensional information through the spatial data processing technology, the geometric shape data of the plastic part can be completely and accurately obtained, avoiding the problem of incomplete or distorted data affecting the subsequent analysis, thereby laying a reliable data foundation for deviation analysis and deformation detection; by gridding the three-dimensional shape data and aligning it with the preset product model through shape matching technology, the geometric difference between the plastic part and the product model can be quickly located, and the deformation area and severity of the plastic part can be intuitively reflected, so that the production personnel can find problems in time and make targeted adjustments; by collecting the process parameter data in the production process of the plastic part, and analyzing the influencing parameters based on the three-dimensional deviation heat map and process data, the key process parameters that cause the deformation of the plastic part in the production process can be accurately identified, avoiding the inefficiency and misjudgment caused by the traditional experience-based adjustment, thereby realizing the scientific optimization of the production process; by generating parameter adjustment schemes according to the key influencing parameters and adaptively adjusting the process parameter data, the key process parameters can be dynamically optimized in the production process, and the accuracy and efficiency of the adjustment can be improved, thereby significantly reducing the probability of plastic part deformation, and improving product qualification rate and production efficiency.

[0020] The third objective of the present application is achieved through the following technical solutions: A computer device comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above-mentioned plastic part deformation detection method when executing the computer program.

[0021] The fourth objective of the present application is achieved through the following technical solutions: A computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the above-mentioned plastic part deformation detection method are implemented.

[0022] In summary, this application includes the following beneficial technical effects: 1. By acquiring the three-dimensional information of plastic parts and digitally transforming the three-dimensional information through spatial data processing technology, the geometric shape data of plastic parts can be completely and accurately obtained, avoiding the impact of incomplete or distorted data on subsequent analysis, thereby laying a reliable data foundation for deviation analysis and deformation detection; by gridding the three-dimensional shape data and aligning it with the preset product model through shape matching technology, the geometric difference between the plastic part and the product model can be quickly located, and the deformation area and severity of the plastic part can be intuitively reflected, so that production personnel can find problems in time and make targeted adjustments; by collecting process parameter data in the production process of plastic parts and analyzing the influencing parameters based on the three-dimensional deviation heat map and process data, the key process parameters that cause the deformation of plastic parts in the production process can be accurately identified, avoiding the inefficiency and misjudgment caused by traditional experience-based adjustments, thereby achieving scientific optimization of the production process; by generating parameter adjustment plans based on key influencing parameters and adaptively adjusting the process parameter data, the key process parameters can be dynamically optimized in the production process, and the accuracy and efficiency of the adjustment can be improved, thereby significantly reducing the probability of plastic part deformation and improving product qualification rate and production efficiency; 2. By using grid processing technology to convert three-dimensional shape data into a grid model with a regular topological structure, the discrete point cloud structure in the original data can be converted into a regular geometric model, improving the accuracy and consistency of shape expression, thereby providing a more accurate data basis for subsequent deviation calculations; by using the shape matching algorithm to align the grid model with the preset product model in position and direction, the global position matching can be quickly completed and the local detail deviation can be optimized to ensure that the geometric features of the plastic parts and the product model are highly consistent, thereby making the deviation analysis results more accurate; by calculating the deviation value distribution of the plastic parts and the product model based on the geometric space difference, and marking the high deviation area through hierarchical threshold determination, the deformation area beyond the tolerance range can be clearly identified to avoid missing local problems due to overall judgment, thereby more efficiently controlling deformation; by generating a three-dimensional deviation heat map and marking the deviation amplitude and distribution range through color gradients, the deviation characteristics of plastic parts can be displayed in an intuitive way, helping production personnel to quickly locate problem areas, thereby shortening detection time and improving processing efficiency; 3. By using the spatial point difference algorithm to calculate the geometric space difference between each grid point in the grid model and the corresponding position of the product model point by point, the deviation data between the plastic part and the product model can be obtained efficiently and accurately, avoiding the problems caused by insufficient calculation accuracy in traditional methods, thereby ensuring the credibility of the deviation analysis results; by comparing the deviation value with the preset tolerance range and grading the deviation value through the hierarchical threshold judgment algorithm, the deformation of plastic parts can be classified according to the degree of deviation, helping production personnel to quickly distinguish high-deviation areas that need to be treated as priority, thereby optimizing the efficiency of problem handling; by marking high-deviation areas according to the deviation distribution classification data and assigning deviation weights, and smoothing the deviation distribution data at the same time, it can highlight the key deformation areas and improve the overall continuity and visualization of the data, thereby enhancing the application value of deviation data in subsequent production optimization. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 is a flow chart of a method for detecting deformation of a plastic part in one embodiment of the present application; Figure 2 is a flowchart for implementing step S20 in the method for detecting deformation of a plastic part in one embodiment of the present application; Figure 3 is a flowchart for implementing step S23 in the plastic part deformation detection method in one embodiment of the present application; Figure 4 It is a flowchart for implementing the construction of a deformation tracing model of a plastic part deformation detection method in one embodiment of the present application; Figure 5 is a flowchart for implementing step S301 in the method for detecting deformation of a plastic part in one embodiment of the present application; Figure 6 is a flowchart for implementing step S40 in the method for detecting deformation of a plastic part in one embodiment of the present application; Figure 7 This is a principle block diagram of a plastic part deformation detection device in one embodiment of the present application; Figure 8 It is a schematic diagram of a device in an embodiment of the present application. DETAILED DESCRIPTION

[0024] The present application is further described in detail below in conjunction with the accompanying drawings.

[0025] In one embodiment, if Figure 1 As shown, the present application discloses a method for detecting deformation of a plastic part, which specifically includes the following steps: S10: Acquire three-dimensional information of the plastic part, and digitally transform the three-dimensional information through spatial data processing technology to obtain three-dimensional shape data.

[0026] Specifically, by obtaining the geometric data of the external surface of the plastic part, the collected geometric point cloud is preprocessed, including denoising, deleting discrete data points and supplementing missing data points, to complete the cleaning of the three-dimensional space point cloud data, and then the point cloud data is converted into standardized three-dimensional shape data to ensure that the three-dimensional shape can completely and accurately represent the appearance characteristics of the plastic part for subsequent analysis.

[0027] S20: The three-dimensional shape data is processed into data grids, and is aligned with a preset product model through shape matching technology, and the deviation value of each position of the plastic part is calculated. When the deviation value exceeds a preset tolerance range, a three-dimensional deviation heat map is generated.

[0028] Specifically, the three-dimensional shape data is gridded and reconstructed, and the point cloud data is interpolated and topologically reconstructed to generate a regular three-dimensional grid model, and the gridded model is optimized to ensure the continuity and integrity of the shape data; the grid model is geometrically aligned with the preset product model, and the position and direction of the plastic part model and the standard model are gradually adjusted to eliminate global deviations and achieve precise alignment; after the alignment is completed, the geometric deviation of the plastic part is calculated point by point, and the areas beyond the tolerance range are identified by analyzing the spatial difference between the actual position of each point on the plastic part and the position of the standard model, and the data of these areas are used to generate a heat map to visualize the deviations, using different color gradients to show the magnitude and distribution of the deviations.

[0029] S30: Collect process parameter data during the production of plastic parts, and analyze the influencing parameters through a preset deformation traceability model based on the three-dimensional deviation heat map and process data to generate key influencing factors.

[0030] Specifically, by collecting temperature data in the cooling stage during the production process, the temperature change law of each area of ​​the mold during the cooling process is recorded, and the process parameters in the injection molding process, including injection pressure, injection speed and holding time, as well as production environment parameters such as temperature, humidity and equipment vibration, are collected at the same time. Combined with the deviation information in the three-dimensional deviation heat map, the deformation traceability model is input for multidimensional data analysis to extract the key process parameters that have a greater impact on the deformation of plastic parts. By calculating the contribution rate of each parameter to the deviation area, the parameters that have the greatest impact on the deformation are screened out as the key influencing factors.

[0031] S40: Generate a parameter adjustment plan according to the key influencing parameters, and then adaptively adjust the process parameter data.

[0032] Specifically, based on the extracted key influencing factors and their influence weights on the deviation distribution, an adjustment plan is formulated, including the adjustment of cooling time, cooling uniformity and injection pressure curve; combined with the specific deviation area characteristics, the mold temperature control strategy during the cooling process is optimized, and the deformation probability of plastic parts is reduced by adjusting the pressure holding time and speed change curve during the injection stage. The adjustment plan is fed back into the production process, and the process parameters are automatically adjusted and optimized.

[0033] In one embodiment, if Figure 2 As shown, in step S20, the three-dimensional shape data is meshed and aligned with the preset product model through shape matching technology, and the deviation value of each position of the plastic part is calculated. When the deviation value exceeds the preset tolerance range, a three-dimensional deviation heat map is generated, which specifically includes: S21: The three-dimensional shape data is converted into a mesh model with a regular topological structure through mesh processing technology.

[0034] Specifically, the three-dimensional point cloud data is converted into a regular grid structure through triangulation technology, the interpolation algorithm is used to supplement the locally missing grid areas, and the mesh smoothing technology is used to eliminate the rough areas of the mesh model. The generated mesh model is optimized to have good continuity and regular topological structure, ensuring that the mesh model can accurately represent the geometric characteristics of the plastic part surface for subsequent shape matching and deviation analysis.

[0035] S22: Using the shape matching algorithm, the mesh model and the preset product model are preliminarily aligned in position and direction through global alignment technology, and local alignment optimization is performed through local alignment technology.

[0036] Specifically, the geometric center of mass of the mesh model and the preset product model is calculated, the centers of mass of the two are aligned, and the preliminary alignment operation on a global scale is completed by calculating the rotation matrix and the translation matrix. After the global alignment is completed, the least squares method is used to perform local alignment optimization for the deviation areas of local geometric details to further improve the alignment accuracy and ensure that the mesh model is highly consistent with the preset product model in local geometric structure.

[0037] S23: Calculate the deviation value distribution between the plastic part and the preset product model based on the geometric space difference, and mark the area exceeding the tolerance range as a high deviation area through layered threshold determination, thereby generating a deviation distribution result.

[0038] Specifically, the geometric space distance between each grid point in the plastic part grid model and the corresponding product model point is calculated, and the calculated deviation value is compared with the preset tolerance range. The grid points are graded according to the size of the deviation value, and the high deviation area is marked as a significant abnormal area. At the same time, the deviation value distribution results are recorded as deviation distribution data for subsequent visualization.

[0039] S24: Generate a three-dimensional deviation heat map according to the deviation distribution result, and identify the deviation amplitude and distribution range of each deviation area by color gradient.

[0040] Specifically, by mapping the deviation distribution data to the surface of the three-dimensional model, using color gradient to represent the deviation amplitude of different areas, displaying the high deviation area as a more eye-catching part, and smoothing the heat map display effect through interpolation algorithm, the three-dimensional deviation heat map can intuitively show the range and degree of deformation of plastic parts, while eliminating the heat map discontinuity caused by local data anomalies.

[0041] In one embodiment, if Figure 3 As shown, in step S23, the deviation value distribution between the plastic part and the preset product model is calculated based on the geometric space difference, and the area exceeding the tolerance range is marked as a high deviation area through the layered threshold determination, thereby generating a deviation distribution result, which specifically includes: S231: Using a spatial point difference algorithm, calculate the geometric spatial difference between each grid point in the grid model and the corresponding position of the preset product model point by point, and record the deviation value of each grid point.

[0042] Specifically, the grid model and the preset product model are compared point by point, and the Euclidean distance between the three-dimensional coordinates of each grid point and the corresponding model point is calculated using the spatial point difference algorithm. The calculated geometric difference is recorded as the deviation value, and the distribution of the grid points is calibrated at the same time to ensure that the difference calculation of each grid point corresponds to the preset model one by one. For example, in the complex curved surface area of ​​the plastic part, the coordinates of the grid points are accurately aligned through the interpolation method to avoid calculation errors caused by uneven grid distribution, and finally a complete data set containing the deviation values ​​of all grid points is generated.

[0043] S232: Compare the deviation value with the preset tolerance range, and classify the deviation value through a hierarchical threshold determination algorithm to obtain deviation distribution classification data.

[0044] Specifically, the deviation value of each recorded grid point is compared with the tolerance range set by the user, and the hierarchical threshold judgment algorithm is used to classify the deviation values ​​according to their size. For example, the deviation values ​​are divided into three levels: low deviation, medium deviation and high deviation, which correspond to the areas within the tolerance range, close to the tolerance range and beyond the tolerance range respectively. At the same time, during the classification process, the judgment result is optimized by dynamically adjusting the threshold to adapt to the inspection requirements of different plastic parts. The graded data is stored as deviation distribution classification data to ensure that subsequent analysis can accurately identify the importance of the deviation area.

[0045] S233: According to the deviation distribution classification data, the high deviation area is marked as a specific level, and the deviation weight is assigned to highlight the key deformation area, and the deviation distribution data is smoothed to generate a deviation distribution result.

[0046] Specifically, by analyzing the deviation distribution grading data, the grid points belonging to the high deviation area are individually marked as a specific level with the highest priority. At the same time, weight values ​​are assigned to these high deviation areas to reflect their contribution to the overall deformation. For example, higher weights are assigned to deviation areas of critical sizes to facilitate subsequent focused processing. The deviation data is then optimized using a smoothing algorithm, and the influence of isolated outliers or small-area noise data is eliminated through interpolation methods, ensuring that the generated deviation distribution results have higher consistency and visualization effects, so as to intuitively present the overall characteristics of the plastic part deformation.

[0047] In one embodiment, if Figure 4 As shown, in step S30, the construction of the preset deformation tracing model specifically includes: S301: Acquire historical production data, organize the historical production data into a multidimensional time series data set, perform cluster analysis based on cooling temperature difference gradient, classify the historical production data according to the analysis results, and obtain a model training data set.

[0048] Specifically, historical process data and deviation distribution data, including mold cooling temperature data, injection pressure curve, and ambient temperature and humidity, are extracted from multiple batches of production records. These data are stored in time series, and the mold temperature difference during the cooling process is analyzed. The cluster analysis method is used to divide the data into high temperature difference group, medium temperature difference group, and low temperature difference group according to the cooling temperature difference gradient. In each group, the deviation area characteristics and the corresponding process parameters are combined to generate a classified data set for training the deformation traceability model.

[0049] S302: Using a multivariate regression algorithm and taking the model training data set as input, the correlation between the production process parameters and the deviation distribution is analyzed, and the influencing factors and the influence weights of the influencing factors are extracted to construct a deformation traceability model.

[0050] Specifically, the model training data set is input into the multivariate regression algorithm for fitting training. The key influencing factors, such as cooling time and injection pressure, are extracted by calculating the contribution rate of each process parameter to the deviation value, and each parameter is assigned a corresponding weight value. Finally, a deformation traceability model is formed that can describe the relationship between process parameters and deviation distribution, providing data support for the optimization of subsequent production processes.

[0051] In one embodiment, if Figure 5 As shown, in step S301, cluster analysis is performed based on the cooling temperature difference gradient, and the historical production data is classified according to the analysis results to obtain a model training data set, which specifically includes: S3011: extracting temperature distribution data of the cooling mold from historical production data, and calculating temperature difference gradients of different areas of the cooling mold during the cooling process.

[0052] Specifically, by analyzing the cooling temperature data in multiple batches of production records, calculating the temperature difference change curves of different areas of the mold during the cooling process, recording the dynamic change trend of the temperature difference, and combining the geometric characteristics of the mold, the temperature difference gradient is used as the key feature of cluster analysis to provide basic data for subsequent data classification.

[0053] S3012: Based on the temperature difference gradient, the corresponding temperature difference data are grouped using a cluster analysis algorithm to divide the data into a high temperature difference group, a medium temperature difference group, and a low temperature difference group.

[0054] Specifically, the temperature difference data are grouped according to similarity through a clustering algorithm, and the high temperature difference, medium temperature difference and low temperature difference are classified using the K-means algorithm to generate the corresponding cooling characteristics for each group, and the deviation distribution and process parameter information are added to each group for the subsequent generation of training data sets.

[0055] S3013: In each temperature difference group, the spatial position characteristics and deviation amplitude characteristics of the three-dimensional deviation are extracted according to the corresponding deviation distribution data, and the spatial position characteristics and deviation amplitude characteristics are associated with the production process parameters, and then organized into a model training data set containing grouping identifiers.

[0056] Specifically, by analyzing the three-dimensional deviation distribution results in each temperature difference group, the spatial characteristics and deviation amplitude of the key deviation area are extracted, and these deviation characteristics are associated and integrated with the corresponding production process parameters to generate a training data set marked with grouping information for subsequent traceability model training.

[0057] In one embodiment, if Figure 6 As shown, in step S40, a parameter adjustment scheme is generated according to the key influencing parameters, and then the process parameter data is adaptively adjusted, specifically including: S41: According to the weight and influence range of the key influencing parameters, determine the key process parameters that affect the deviation distribution of plastic parts. The key process parameters include cooling time, mold temperature distribution and injection pressure.

[0058] Specifically, by analyzing the parameter weight results output by the deformation traceability model, cooling time and mold temperature difference are identified as the main process parameters affecting deformation. At the same time, injection pressure is analyzed as an auxiliary parameter. Combined with the influence range of these parameters, a basic parameter set for the optimization strategy is generated.

[0059] S42: With respect to the cooling time and the mold temperature distribution, a temperature adjustment plan is generated by optimizing the cooling strategy. With respect to the injection pressure, a pressure adjustment plan is generated by optimizing the pressure change pattern during the injection molding process, thereby obtaining a parameter adjustment plan.

[0060] Specifically, the temperature gradient in the mold is reduced by optimizing the flow rate and temperature distribution of the coolant. Combined with the optimization of the pressure rise rate during the injection molding process, a complete parameter adjustment solution is generated to improve the stability of the process.

[0061] S43: Adjusting the process parameter data according to the parameter adjustment scheme to reduce the probability of deformation of the plastic part.

[0062] Specifically, by inputting the optimization results in the parameter adjustment scheme into the process control module, the cooling and injection molding parameters in the production process are updated in real time. After verifying the effect of the parameter adjustment, a process standardization strategy is formed to reduce the probability of plastic part deformation and improve molding quality.

[0063] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0064] In one embodiment, a plastic part deformation detection device is provided, and the plastic part deformation detection device corresponds to the plastic part deformation detection method in the above embodiment. Figure 7 As shown, the plastic part deformation detection device includes a three-dimensional information acquisition module, a shape deviation analysis module, a process data analysis module, and a parameter adjustment module. The detailed description of each functional module is as follows: The three-dimensional information acquisition module is used to obtain the three-dimensional information of the plastic parts, and digitally transform the three-dimensional information through spatial data processing technology to obtain three-dimensional shape data; The shape deviation analysis module is used to process the 3D shape data into data grids, align it with the preset product model through shape matching technology, calculate the deviation value of each position of the plastic part, and generate a 3D deviation heat map when the deviation value exceeds the preset tolerance range; The process data analysis module is used to collect process parameter data during the production of plastic parts, and analyze the influencing parameters through a preset deformation traceability model based on the three-dimensional deviation heat map and process data to generate key influencing factors; The parameter adjustment module is used to generate parameter adjustment schemes according to key influencing parameters, and then adaptively adjust the process parameter data.

[0065] Optionally, the shape deviation analysis module specifically includes: A mesh processing submodule, used for converting three-dimensional shape data into a mesh model with a regular topological structure through mesh processing technology; The shape matching submodule is used to use the shape matching algorithm to perform preliminary registration of the position and direction of the mesh model and the preset product model through the global alignment technology, and to perform local alignment optimization through the local alignment technology; The geometric difference calculation submodule is used to calculate the deviation value distribution between the plastic part and the preset product model based on the geometric space difference, and mark the area exceeding the tolerance range as a high deviation area through hierarchical threshold determination, thereby generating the deviation distribution result; The deviation heat map generation submodule is used to generate a three-dimensional deviation heat map based on the deviation distribution results, and to identify the deviation amplitude and distribution range of each deviation area through color gradient.

[0066] Optionally, the geometric difference calculation submodule specifically includes: A spatial difference calculation unit is used to calculate the geometric spatial difference between each grid point in the grid model and the corresponding position of the preset product model point by point using a spatial point difference algorithm, and record the deviation value of each grid point; A threshold grading processing unit is used to compare the deviation value with a preset tolerance range, and to grade the deviation value through a hierarchical threshold determination algorithm to obtain deviation distribution graded data; The deviation area marking unit is used to mark the high deviation area as a specific level according to the deviation distribution classification data, and assign deviation weights to highlight the key deformation area, and smooth the deviation distribution data to generate the deviation distribution result.

[0067] Optionally, the construction of a preset deformation tracing model includes: The production data sorting module is used to obtain historical production data and sort the historical production data into a multi-dimensional time series data set, perform cluster analysis based on the cooling temperature difference gradient, classify the historical production data according to the analysis results, and obtain a model training data set; The model building module is used to adopt a multivariate regression algorithm, take the model training data set as input, analyze the correlation between the production process parameters and the deviation distribution, and extract the influencing factors and the influence weights of the influencing factors, and then build a deformation traceability model.

[0068] Optionally, the production data sorting module specifically includes: The temperature distribution extraction submodule is used to extract the temperature distribution data of the cooling mold in the historical production data and calculate the temperature difference gradient of different areas of the cooling mold during the cooling process; The temperature difference data clustering submodule is used to group the corresponding temperature difference data into high temperature difference group, medium temperature difference group and low temperature difference group based on the temperature difference gradient using the clustering analysis algorithm; The data association and integration submodule is used to extract the spatial position characteristics and deviation amplitude characteristics of the three-dimensional deviation in each temperature difference group according to the corresponding deviation distribution data, and associate the spatial position characteristics and deviation amplitude characteristics with the production process parameters, and then organize them into a model training data set containing grouping identifiers.

[0069] Optionally, the parameter adjustment module specifically includes: The key parameter analysis submodule is used to determine the key process parameters that affect the deviation distribution of plastic parts according to the weight and influence range of the key influencing parameters. The key process parameters include cooling time, mold temperature distribution and injection pressure, etc. The parameter optimization submodule is used to generate a temperature adjustment plan by optimizing the cooling strategy for cooling time and mold temperature distribution, and to generate a pressure adjustment plan by optimizing the pressure change pattern during the injection molding process for injection pressure, thereby obtaining a parameter adjustment plan; The process parameter adjustment submodule is used to adjust the process parameter data according to the parameter adjustment scheme to reduce the probability of deformation of the plastic part.

[0070] For the specific definition of the plastic part deformation detection device, please refer to the definition of the plastic part deformation detection method above, which will not be repeated here. Each module in the above-mentioned plastic part deformation detection device can be implemented in whole or in part by software, hardware and their combination. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0071] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 8As shown. The computer device includes a processor, a memory, a network interface and a database connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a plastic part deformation detection method is implemented.

[0072] In one embodiment, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the following steps when executing the computer program: Obtain the three-dimensional information of the plastic part, and digitally transform the three-dimensional information through spatial data processing technology to obtain three-dimensional shape data; The 3D shape data is processed into data grids and aligned with the preset product model through shape matching technology to calculate the deviation value of each position of the plastic part. When the deviation value exceeds the preset tolerance range, a 3D deviation heat map is generated. Collect process parameter data during the production of plastic parts, and analyze the influencing parameters through a preset deformation traceability model based on the 3D deviation heat map and process data to generate key influencing factors; Generate parameter adjustment plans based on key influencing parameters, and then adaptively adjust the process parameter data.

[0073] In one embodiment, a computer readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented: Obtain the three-dimensional information of the plastic part, and digitally transform the three-dimensional information through spatial data processing technology to obtain three-dimensional shape data; The 3D shape data is processed into data grids and aligned with the preset product model through shape matching technology to calculate the deviation value of each position of the plastic part. When the deviation value exceeds the preset tolerance range, a 3D deviation heat map is generated. Collect process parameter data during the production of plastic parts, and analyze the influencing parameters through a preset deformation traceability model based on the 3D deviation heat map and process data to generate key influencing factors; Generate parameter adjustment plans based on key influencing parameters, and then adaptively adjust the process parameter data.

[0074] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0075] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0076] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A method for detecting deformation of a plastic part, characterized in that: The plastic part deformation detection method comprises: Acquire three-dimensional information of the plastic part, and digitally transform the three-dimensional information through spatial data processing technology to obtain three-dimensional shape data; Performing data gridding processing on the three-dimensional shape data, and aligning it with a preset product model through shape matching technology, calculating the deviation value of each position of the plastic part, and generating a three-dimensional deviation heat map when the deviation value exceeds a preset tolerance range; Collecting process parameter data during the production of the plastic parts, and based on the three-dimensional deviation heat map and the process data, analyzing the influencing parameters through a preset deformation tracing model to generate key influencing factors; A parameter adjustment scheme is generated according to the key influencing parameters, and then the process parameter data is adaptively adjusted.

2. The method for detecting deformation of a plastic part according to claim 1, characterized in that: The three-dimensional shape data is gridded and aligned with a preset product model through shape matching technology, the deviation value of each position of the plastic part is calculated, and when the deviation value exceeds a preset tolerance range, a three-dimensional deviation heat map is generated, which specifically includes: The three-dimensional shape data is converted into a grid model with a regular topological structure by a grid processing technology; Using a shape matching algorithm, the mesh model and the preset product model are preliminarily aligned in position and direction through a global alignment technique, and local alignment optimization is performed through a local alignment technique; Calculating the deviation value distribution between the plastic part and the preset product model based on the geometric space difference, and marking the area exceeding the tolerance range as a high deviation area through layered threshold determination, thereby generating a deviation distribution result; A three-dimensional deviation heat map is generated according to the deviation distribution result, and the deviation amplitude and distribution range of each deviation area are marked by color gradient.

3. The method for detecting deformation of a plastic part according to claim 2, characterized in that: The calculation of the deviation value distribution between the plastic part and the preset product model based on the geometric space difference, and marking the area exceeding the tolerance range as a high deviation area through layered threshold determination, thereby generating a deviation distribution result, specifically includes: Using a spatial point difference algorithm, the geometric spatial difference between each grid point in the grid model and the corresponding position of the preset product model is calculated point by point, and the deviation value of each grid point is recorded; Comparing the deviation value with a preset tolerance range, and performing grading processing on the deviation value through a stratified threshold determination algorithm to obtain deviation distribution grading data; According to the deviation distribution classification data, high deviation areas are marked as specific levels, and deviation weights are assigned to highlight key deformation areas, and the deviation distribution data is smoothed to generate the deviation distribution result.

4. The method for detecting deformation of a plastic part according to claim 1, characterized in that: The construction of the preset deformation tracing model specifically includes: Acquire historical production data, organize the historical production data into a multidimensional time series data set, perform cluster analysis based on cooling temperature difference gradient, classify the historical production data according to the analysis results, and obtain a model training data set; A multivariate regression algorithm is adopted, with the model training data set as input, to analyze the correlation between production process parameters and deviation distribution, and to extract influencing factors and the influence weights of the influencing factors, thereby constructing the deformation tracing model.

5. The method for detecting deformation of a plastic part according to claim 4, characterized in that: The cluster analysis is performed based on the cooling temperature difference gradient, and the historical production data is classified according to the analysis results to obtain a model training data set, which specifically includes: Extracting temperature distribution data of the cooling mold from the historical production data, and calculating the temperature difference gradient of different areas of the cooling mold during the cooling process; Based on the temperature difference gradient, the corresponding temperature difference data are grouped using a cluster analysis algorithm to divide them into a high temperature difference group, a medium temperature difference group and a low temperature difference group; In each temperature difference group, the spatial position characteristics and deviation amplitude characteristics of the three-dimensional deviation are extracted according to the corresponding deviation distribution data, and the spatial position characteristics and the deviation amplitude characteristics are associated with the production process parameters, and then organized into the model training data set containing the grouping identifier.

6. The method for detecting deformation of a plastic part according to claim 1, characterized in that: Generating a parameter adjustment scheme according to the key influencing parameters and then adaptively adjusting the process parameter data specifically includes: Determine the key process parameters that affect the deviation distribution of plastic parts according to the weights and influence ranges of the key influencing parameters, wherein the key process parameters include cooling time, mold temperature distribution, injection pressure, etc.; With respect to the cooling time and the mold temperature distribution, a temperature adjustment scheme is generated by optimizing the cooling strategy, and with respect to the injection pressure, a pressure adjustment scheme is generated by optimizing the pressure change pattern during the injection molding process, thereby obtaining the parameter adjustment scheme; The process parameter data is adjusted according to the parameter adjustment scheme to reduce the probability of deformation of the plastic part.

7. A plastic part deformation detection device, characterized in that: The plastic part deformation detection device comprises: A three-dimensional information acquisition module is used to obtain three-dimensional information of the plastic part, and digitally transform the three-dimensional information through spatial data processing technology to obtain three-dimensional shape data; A shape deviation analysis module, for performing data gridding processing on the three-dimensional shape data, aligning it with a preset product model through shape matching technology, calculating the deviation value of each position of the plastic part, and generating a three-dimensional deviation heat map when the deviation value exceeds a preset tolerance range; A process data analysis module, used for collecting process parameter data in the production process of the plastic parts, and based on the three-dimensional deviation heat map and the process data, analyzing the influencing parameters through a preset deformation tracing model to generate key influencing factors; The parameter adjustment module is used to generate a parameter adjustment scheme according to the key influencing parameters, and then adaptively adjust the process parameter data.

8. The plastic part deformation detection device according to claim 7, characterized in that: The shape deviation analysis module specifically includes: A grid processing submodule, used for converting the three-dimensional shape data into a grid model with a regular topological structure through a grid processing technology; A shape matching submodule, for performing preliminary registration of the position and direction of the grid model and the preset product model by using a shape matching algorithm through a global alignment technology, and performing local alignment optimization through a local alignment technology; A geometric difference calculation submodule, used to calculate the deviation value distribution between the plastic part and the preset product model based on the geometric space difference, and mark the area exceeding the tolerance range as a high deviation area through layered threshold determination, thereby generating a deviation distribution result; The deviation heat map generation submodule is used to generate a three-dimensional deviation heat map according to the deviation distribution result, and to identify the deviation amplitude and distribution range of each deviation area by color gradient.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the plastic part deformation detection method according to any one of claims 1 to 6 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the plastic part deformation detection method according to any one of claims 1 to 6 are implemented.

Images