Injection molding data analysis method, device and equipment and storage medium
By acquiring and analyzing data during the injection molding process, using preset numerical analysis methods to generate data analysis reports, the problem that traditional methods cannot capture dynamic changes and rely on experience is solved, and the quality of injection molding data and decision-making accuracy are improved.
Patent Information
- Application Number
- CN202411234914.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-04
- Publication Date
- 2025-01-03
AI Technical Summary
Traditional injection molding data analysis methods cannot fully capture dynamic changes in the production process, resulting in unsatisfactory quality control results, excessive reliance on the experience of technicians, and affect the accuracy of decision-making.
By obtaining injection molding set values, statistical process control data and injection molding curve data during the injection molding process, using preset numerical analysis methods such as principal component analysis, calculate and analyze the target analysis value, and combine them to generate data analysis reports to improve Data quality and decision accuracy.
While fully capturing the dynamic changes in the production process, it reduces the dependence on the experience of technicians, improves the quality of injection molding data and the accuracy of decision-making, and solves the problems of large volumes of curved data and complex dimensions.
Smart Images
Figure CN119249077A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of data processing technology, and in particular to an injection molding data analysis method, device, equipment and storage medium. Background Art
[0002] Injection molding is a process widely used in the manufacture of plastic products. It injects molten plastic material into a precisely designed mold and forms the desired product shape after cooling and solidification. This process has a vital impact on the quality, precision and production efficiency of plastic products.
[0003] However, traditional injection molding data analysis methods mainly rely on simple linear regression or probability statistics methods, which often cannot fully capture the dynamic changes in the production process. It is also difficult to handle the injection molding machine data, which has gradually become large in volume and complex in dimension due to the rapid development of curve data sensors, resulting in unsatisfactory quality control effects. In addition, there is also an over-reliance on the experience and knowledge of technicians to make judgments, which leads to misleading analysis results and affects the accuracy of decision-making. Summary of the invention
[0004] The main purpose of this application is to provide an injection molding data analysis method, device, equipment and storage medium, aiming to improve the data quality of injection molding data, reduce dependence on the experience of technicians, and thus improve the accuracy of decision-making.
[0005] To achieve the above objectives, the present application proposes an injection molding data analysis method, the method comprising:
[0006] Obtain injection setting values, statistical process control data and injection curve data corresponding to each injection period during the injection molding process;
[0007] Based on each preset numerical analysis method, each of the injection molding setting values and each of the statistical process control data are calculated and analyzed to obtain a plurality of groups of first target analysis values;
[0008] Based on the injection curve data corresponding to each of the injection periods, a plurality of groups of second target analysis values are obtained;
[0009] The first target analysis values and the second target analysis values are associated and combined to obtain a third target analysis value.
[0010] In one embodiment, the preset numerical analysis method includes a principal component analysis method;
[0011] The method of calculating and analyzing the injection molding setting values and the statistical process control data based on the preset numerical analysis methods to obtain the first target analysis value includes:
[0012] Performing data standardization on each of the injection molding set values and each of the statistical process control data;
[0013] Based on the principal component analysis method, calculating the eigenvalues and eigenvectors corresponding to each of the injection molding setting values and each of the statistical process control data after data standardization;
[0014] The eigenvalues are sorted, and the eigenvectors corresponding to the eigenvalues with preset rankings are selected as the first target analysis values.
[0015] In one embodiment, the plurality of groups of second target analysis values are obtained based on the injection curve data corresponding to each of the injection periods, including:
[0016] Performing data standardization on each of the injection molding curve data;
[0017] Reconstructing the injection curve data corresponding to each of the injection periods after the data standardization to obtain a plurality of groups of curve reconstruction data;
[0018] The curve reconstruction data corresponding to each injection period is calculated and analyzed to obtain several groups of second target analysis values.
[0019] In one embodiment, the injection curve data corresponding to each injection period after the data standardization is reconstructed to obtain several groups of curve reconstruction data, including:
[0020] Obtain a statistical value calculation method for curve reconstruction;
[0021] Based on the statistical value calculation method, the injection curve data corresponding to each of the injection periods after the data standardization is calculated to obtain several groups of curve reconstruction data.
[0022] In one embodiment, the curve reconstruction data corresponding to each injection period is calculated and analyzed to obtain a plurality of groups of second target analysis values, including:
[0023] Determine a plurality of segmentation points of the curve reconstruction data, and calculate the information gain corresponding to any of the segmentation points;
[0024] Based on each of the injection molding periods, the importance scores corresponding to each of the information gains are grouped and then counted to determine the importance scores corresponding to each of the injection molding periods;
[0025] Based on the importance scores corresponding to the injection molding periods, several groups of second target analysis values are obtained.
[0026] In one embodiment, based on the importance scores corresponding to the injection molding periods, several groups of second target analysis values are obtained, including:
[0027] Sorting the importance scores corresponding to the injection molding periods, and determining the target injection molding period according to the sorting results;
[0028] Determining whether the curve reconstruction data corresponding to the target injection period meets the preset target value rule;
[0029] If so, the curve reconstruction data corresponding to the target injection period is used as the second target analysis value.
[0030] In one embodiment, after associating and combining the first target analysis values and the second target analysis values to obtain a third target analysis value, the method further includes:
[0031] Performing data visualization on the third target analysis value;
[0032] Based on the third target analysis value, generating a data analysis report;
[0033] The visualized third target analysis value and the data analysis report are pushed to a target user for viewing by the target user.
[0034] In addition, to achieve the above-mentioned purpose, the present application also proposes an injection molding data analysis device, the injection molding data analysis device comprising:
[0035] An acquisition module is used to acquire the injection setting values, statistical process control data and injection curve data corresponding to each injection period in the injection molding process;
[0036] A first calculation module, used for calculating and analyzing each of the injection molding setting values and each of the statistical process control data based on each preset numerical analysis method to obtain a plurality of groups of first target analysis values;
[0037] A second calculation module, used for obtaining a plurality of groups of second target analysis values based on the injection curve data corresponding to each of the injection periods;
[0038] The analysis module is used to associate and combine the first target analysis values and the second target analysis values to obtain a third target analysis value.
[0039] In addition, to achieve the above-mentioned purpose, the present application also proposes an injection molding data analysis device, which includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the injection molding data analysis method as described above.
[0040] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, which is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the injection molding data analysis method described above are implemented.
[0041] In addition, to achieve the above-mentioned purpose, the present application also provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, the steps of the injection molding data analysis method described above are implemented.
[0042] The present application provides an injection molding data analysis method, device, equipment and storage medium. The injection molding data analysis method obtains the injection molding set values, statistical process control data and injection molding curve data corresponding to each injection molding period in the injection molding process, and then calculates and analyzes each of the injection molding set values and each of the statistical process control data based on each preset numerical analysis method to obtain a plurality of groups of first target analysis values, and then obtains a plurality of groups of second target analysis values based on the injection molding curve data corresponding to each of the injection molding periods, and then associates and combines each of the first target analysis values and each of the second target analysis values to obtain a third target analysis value, thereby fully capturing the dynamic changes in the production process while solving the problems of the huge amount of curve data that cannot be applied, the excessive number of dimensions of abnormal data and the inability to know which dimensions need to be filtered, thereby improving the data quality of the injection molding data, reducing the reliance on the experience of technical personnel, and improving the accuracy of decision-making. BRIEF DESCRIPTION OF THE DRAWINGS
[0043] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.
[0044] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.
[0045] Figure 1 A schematic diagram of a process flow provided for Example 1 of the injection molding data analysis method of the present application;
[0046] Figure 2 A schematic diagram of a process flow provided for Example 2 of the injection molding data analysis method of this application;
[0047] Figure 3 A brief flow chart of curve data analysis provided by the injection molding data analysis method of this application;
[0048] Figure 4A brief flow chart of the injection molding data analysis method provided in this application;
[0049] Figure 5 This is a schematic diagram of the module structure of the injection molding data analysis device according to an embodiment of the present application;
[0050] Figure 6 Schematic diagram of the equipment structure of the hardware operating environment involved in the injection molding data analysis method in the embodiment of the present application.
[0051] The purpose, features and advantages of this application will be further described in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION
[0052] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not used to limit the present application.
[0053] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.
[0054] It should be noted that the execution subject of this embodiment can be a computing service device with data processing, network communication and program running functions, such as a tablet computer, a personal computer, a mobile phone, etc., or an electronic device capable of realizing the above functions, a big data service platform, an injection molding data analysis system, etc. The following takes the injection molding data analysis system as an example to illustrate this embodiment and the following embodiments.
[0055] Based on this, the present application embodiment provides an injection molding data analysis method, referring to Figure 1 , Figure 1 A schematic diagram of the process flow provided for Example 1 of the injection molding data analysis method of the present application.
[0056] In this embodiment, the injection molding data analysis method includes steps S11 to S14:
[0057] Step S11, obtaining injection setting values, statistical process control data and injection curve data corresponding to each injection period in the injection process;
[0058] It should be noted that the injection molding process refers to the entire production process of injecting molten plastic material into a mold and then cooling and solidifying it to form a plastic product. The injection molding phase refers to a specific time period or stage in the injection molding process. For example, in one embodiment, the injection molding phase includes 11 phases, namely, mold closing phase, neutron 1 to 4 advancement phase, injection phase, pressure holding phase, melt phase, post-loosening phase, cooling phase, neutron 1 to 4 retreat phase, mold opening phase, push-in phase, and push-out phase, which can be set according to actual conditions and are not limited here.
[0059] It should be further explained that each injection molding period has its specific process requirements and parameter settings, and the injection molding set value refers to the parameter value pre-set on the injection molding machine, including the time, position, speed, rotation speed, pressure, temperature, control mode, process type, number of segments, number of times, enable, etc. in each injection molding process, which is not limited here. In addition, the statistical process control (SPC) data refers to the data collected in real time during the injection molding process for monitoring and controlling production quality, including the time, position, pressure, mode, etc. in each injection molding process and the temperature of different components.
[0060] Furthermore, the injection molding curve data refers to detailed process data collected during the injection molding process, usually presented in the form of a time series. In one embodiment, there are 22 injection molding curve data, including 3 in-mold pressures, 4 in-mold temperatures, 3 male molds, 3 female mold temperatures, 1 mold temperature machine water flow, 1 cold water temperature, 1 hot water temperature, 1 return water temperature, 1 actual screw position, 1 injection head injection pressure, 1 total circulating water volume, 1 total circulating hot water volume and 1 total circulating cold water volume curve data, so as to provide detailed information on the changes of various parameters over time in the production process.
[0061] Specifically, the injection setting value can be directly obtained in the software program of the injection molding computer, and the statistical process control data can be obtained through sensors such as temperature, pressure, and flow, and then the data is collected and summarized through the PLC (Programmable Logic Controller) data acquisition card, so that the acquisition program uses the gateway to obtain the collected data of the PLC through the OPC-UA protocol, wherein the gateway establishes a connection with the PLC through interfaces such as Ethernet and serial ports to ensure real-time access to the PLC data, and then after data collection, the gateway reads data including sensor readings, equipment status, operating parameters, and setting parameters, so that the built-in data processing module of the gateway cleans, converts and stores the original data, and packages the processed data into a format suitable for uploading, and then obtains the statistical process control data and the injection molding curve data. Here, there is no restriction on the acquisition method of the injection molding setting value, statistical process control data, and injection molding curve data corresponding to each injection molding period, and it can be set according to actual conditions.
[0062] Step S12, based on each preset numerical analysis method, calculating and analyzing each of the injection molding setting values and each of the statistical process control data to obtain a plurality of groups of first target analysis values;
[0063] It should be noted that the preset numerical analysis method refers to a series of mathematical or statistical methods that have been determined before the start of data analysis, which are used to process and analyze the data collected during the injection molding process, including but not limited to: statistical process control (SPC) analysis, principal component analysis (PCA), covariance analysis method, Pearson analysis method, Spearman rank correlation coefficient analysis method, correlation and regression analysis, time series analysis, and machine learning algorithms (such as decision trees, random forests, neural networks, etc.). It should be further noted that the first target analysis value refers to the analysis result obtained by analyzing the injection molding set value and statistical process control (SPC) data.
[0064] Specifically, data standardization is performed on each of the injection molding setting values and each of the statistical process control data, and then based on the principal component analysis method, the eigenvalues and eigenvectors corresponding to each of the injection molding setting values and each of the statistical process control data after data standardization are calculated, so that each of the eigenvalues is sorted, and the eigenvector corresponding to the eigenvalue with a preset ranking is selected as the first target analysis value in the same calculation method group.
[0065] Furthermore, if the preset numerical analysis method includes a covariance analysis method, the covariance between each injection molding setting value and the statistical process control data is calculated, and then sorted according to the absolute value of the covariance. The larger the absolute value, the more important the value is, and the eigenvector corresponding to the eigenvalue of the preset ranking is selected as the first target analysis value in the same calculation method group.
[0066] Furthermore, if the preset numerical analysis method includes the Pearson analysis method, the correlation between the dependent variable X and the output Y is calculated according to the Pearson correlation coefficient formula, and then sorted according to the calculated correlation coefficient, and the eigenvector corresponding to the eigenvalue of the preset ranking is selected as the first target analysis value in the same calculation method group.
[0067] Step S13, obtaining a plurality of groups of second target analysis values based on the injection curve data corresponding to each of the injection periods;
[0068] It should be noted that the second target analysis value refers to the analysis result obtained by analyzing the injection curve data.
[0069] Specifically, each of the injection molding curve data is standardized, and then the injection molding curve data corresponding to each of the injection molding periods after the data standardization is reconstructed to obtain several groups of curve reconstruction data, and then the curve reconstruction data corresponding to each of the injection molding periods is calculated and analyzed to obtain several groups of second target analysis values.
[0070] Step S14: Associatively combine the first target analysis values and the second target analysis values to obtain a third target analysis value.
[0071] It should be noted that the third target analysis value refers to the final analysis result obtained after correlating and comprehensively analyzing the first target analysis values and the second target analysis values, which can be used to comprehensively evaluate the overall performance and product quality of the injection molding process, identify and prioritize the most critical process variables, provide decision support for further process optimization and automation, and predict and prevent potential production problems, etc., thereby helping to achieve process control, quality improvement and increased production efficiency, enabling users to better understand and control the production process, thereby improving product consistency and reliability.
[0072] Specifically, each of the first target analysis values and each of the second target analysis values are associated and combined to obtain a third target analysis value, wherein data alignment is required for each of the first target analysis values and each of the second target analysis values to ensure that the first target analysis value and the second target analysis value are from the same injection molding cycle or time period, so as to perform effective comparison and improve the accuracy and data quality of subsequent data analysis.
[0073] This embodiment obtains the injection setting values, statistical process control data and injection curve data corresponding to each injection period in the injection molding process, and then calculates and analyzes each of the injection setting values and each of the statistical process control data based on preset numerical analysis methods to obtain several groups of first target analysis values, and then obtains several groups of second target analysis values based on the injection curve data corresponding to each of the injection molding periods, and then associates and combines each of the first target analysis values and each of the second target analysis values to obtain a third target analysis value, thereby fully capturing the dynamic changes in the production process while solving the problems of large amount of curve data that cannot be applied, too many dimensions of abnormal data and inability to know which dimensions need to be filtered, thereby improving the data quality of injection molding data, reducing reliance on the experience of technical personnel, and improving the accuracy of decision-making.
[0074] In a feasible implementation manner, the preset numerical analysis method includes a principal component analysis method; the calculation and analysis of each of the injection molding setting values and each of the statistical process control data based on each of the preset numerical analysis methods to obtain a first target analysis value includes:
[0075] Step S21, performing data standardization on each of the injection molding setting values and each of the statistical process control data;
[0076] Specifically, data standardization is performed on each of the injection molding set values and each of the statistical process control data, such as abnormal value filtering, single value filtering, physical meaning unclear filtering, missing value ratio filtering, etc., which are not limited here and can be set according to actual conditions.
[0077] Step S22, based on the principal component analysis method, calculating the eigenvalues and eigenvectors corresponding to each of the injection molding setting values and each of the statistical process control data after data standardization;
[0078] It should be noted that the principal component analysis method refers to the PCA (Principal Component Analysis) method, which is used to simplify the complexity of a data set while retaining as much variability of the original data set as possible, and to reduce the dimension of the data by identifying patterns in the data.
[0079] Specifically, the covariance matrix corresponding to each of the injection molding setting values and each of the statistical process control data after data standardization is calculated, and then the eigenvalues and eigenvectors corresponding to each of the injection molding setting values and each of the statistical process control data after data standardization are calculated based on the covariance matrix.
[0080] Step S23, sorting the eigenvalues, and selecting the eigenvector corresponding to the eigenvalue with a preset ranking as the first target analysis value.
[0081] Specifically, each of the eigenvalues is sorted by size, and the eigenvector corresponding to the eigenvalue with a preset ranking is selected as the first target analysis value in the same calculation method group, wherein the preset ranking can be set according to actual conditions, such as taking the eigenvector corresponding to the top ten eigenvalues as the first target analysis value, etc., and there is no limitation here.
[0082] This embodiment performs data standardization on each of the injection molding setting values and each of the statistical process control data, and then calculates the eigenvalues and eigenvectors corresponding to each of the injection molding setting values and each of the statistical process control data after data standardization, thereby sorting each of the eigenvalues, and selecting the eigenvectors corresponding to the eigenvalues with a preset ranking as the first target analysis value, thereby simplifying the model by reducing the dimension of the data while retaining the variability in the original data to reflect the dynamic changes in the production process, thereby helping to remove redundant information and solve the problem of too many dimensions of abnormal data and inability to know which dimensions need to be filtered, thereby extracting the features that best represent the variability of the data set and effectively improving data quality.
[0083] Based on this, the present application embodiment provides an injection molding data analysis method, referring to Figure 2 , Figure 2A schematic diagram of the flow chart provided for Example 2 of the injection molding data analysis method of the present application.
[0084] In a feasible implementation manner, the plurality of groups of second target analysis values are obtained based on the injection curve data corresponding to each injection period, including:
[0085] Step S31, performing data standardization on each of the injection molding curve data;
[0086] Specifically, data standardization is performed on each of the injection molding curve data, such as outlier filtering, single value filtering, physical meaning unclear filtering, missing value ratio filtering, etc., which is not limited here and can be set according to actual conditions.
[0087] Step S32, reconstructing the injection curve data corresponding to each of the injection periods after the data standardization to obtain a plurality of groups of curve reconstruction data;
[0088] It should be noted that, in one embodiment, since each curve data sensor collects data every 25 ms, each curve data column will have thousands of values (if executed for 30 seconds, there will be at least 1,200 data). If all the curve data are put into the intelligent algorithm for calculation, the dimension is obviously too large. Therefore, it is necessary to optimize the injection molding curve data to solve the problem of the huge amount of curve data that cannot be applied.
[0089] It should be further explained that the curve reconstruction data refers to a set of new and more representative data sets obtained after processing and converting the original injection curve data during the data analysis process.
[0090] Specifically, a statistical value calculation method for curve reconstruction is obtained, and then based on the statistical value calculation method, the injection curve data corresponding to each injection period after data standardization is calculated to obtain several groups of curve reconstruction data.
[0091] Step S33, calculating and analyzing the curve reconstruction data corresponding to each of the injection periods to obtain a plurality of groups of second target analysis values.
[0092] Specifically, several segmentation points of the curve reconstruction data are determined, and the information gain corresponding to any segmentation point is calculated, and then based on each injection molding period, the importance scores corresponding to each information gain are grouped and statistically analyzed to determine the importance scores corresponding to each injection molding period, so as to obtain several groups of second target analysis values based on the importance scores corresponding to each injection molding period.
[0093] This embodiment performs data standardization on each of the injection molding curve data, and then reconstructs the injection molding curve data corresponding to each of the injection molding periods after the data standardization to obtain several groups of curve reconstruction data, and then performs calculation and analysis on the curve reconstruction data corresponding to each of the injection molding periods to obtain several groups of second target analysis values, thereby solving the problem that the curve data volume is too large to be applied, and extracting key features in the injection molding curve data, such as peak values, change trends, etc., thereby effectively improving data consistency, improving the accuracy and reliability of analysis results, and facilitating subsequent data processing and analysis.
[0094] In a feasible implementation manner, the injection curve data corresponding to each injection period after the data standardization is reconstructed to obtain several groups of curve reconstruction data, including:
[0095] Step S41, obtaining a statistical value calculation method for curve reconstruction;
[0096] It should be noted that the statistical value calculation method refers to a series of statistical techniques used to analyze and interpret data sets. The statistical value calculation method describes the characteristics and distribution of data by calculating various statistics in the data set, including but not limited to the following: maximum value, minimum value, first quartile (Q1), median, third quartile (Q3), variance and standard deviation, etc.
[0097] Specifically, the statistical value calculation method for curve reconstruction can be obtained according to the configuration of the technician or by reading the pre-stored configuration of the system, which is not limited here.
[0098] Step S42, based on the statistical value calculation method, the injection curve data corresponding to each of the injection periods after the data standardization is calculated to obtain a plurality of groups of curve reconstruction data.
[0099] Specifically, in one embodiment, the curve data is reconstructed by using the statistical method of each injection molding process phase (a total of 11 phases), that is, in ascending order of time, according to the statistical value calculation method, the maximum value, minimum value, Q1 quartile, median, Q3 quartile, variance, standard deviation, etc. corresponding to the injection molding curve data of each injection molding period are calculated, thereby obtaining several groups of curve reconstruction data.
[0100] It is understandable that each curve data column will have thousands of values (if executed for 30 seconds, there will be at least 1200 data), so through curve data reconstruction, 22*1200=26400 data ("22" refers to the injection curve data of "3 mold pressures, 4 mold temperatures, 3 male molds, 3 female mold temperatures, 1 mold temperature machine water flow, 1 cold water temperature, 1 hot water temperature, 1 return water temperature, 1 actual screw position, 1 injection head injection pressure, 1 injection head ... The calculation formula includes "22 data of "curve data of total circulating water, total circulating hot water and total circulating cold water" and "22*11*7=1694 data" (calculated based on sampling for 30 seconds), where "11" in the calculation formula refers to 11 phases, and "7" represents the "maximum value, minimum value, Q1 quartile, median, Q3 quartile, variance, standard deviation" corresponding to the injection curve data of each injection molding period, thereby directly reducing the data volume by 93.5%.
[0101] This embodiment obtains a statistical value calculation method for curve reconstruction, and then calculates the injection curve data corresponding to each injection period after data standardization based on the statistical value calculation method to obtain several groups of curve reconstruction data, thereby simplifying a large amount of time series data into numerical values that are easier to analyze and understand, reducing the complexity of data processing, so as to predict product quality trends, provide support for production decisions, and at the same time reduce the consumption of computing resources and improve the speed of data processing.
[0102] In a feasible implementation manner, the curve reconstruction data corresponding to each injection period is calculated and analyzed to obtain several groups of second target analysis values, including:
[0103] Step S51, determining a number of segmentation points of each of the curve reconstruction data, and calculating the information gain corresponding to any of the segmentation points;
[0104] It should be noted that the split point refers to a series of values selected based on the equidistant range of feature values or based on other criteria (such as quantiles). The information gain is an important indicator used to measure the ability of a feature to classify a data set. The importance of each feature (curve data) can be measured based on the information gain, where the greater the information gain, the more important the feature.
[0105] Specifically, in one embodiment, for a curve reconstruction data (in the form of a curve), 10 segmentation points with equal distances are selected according to a preset value range, and then the information gain corresponding to each segmentation point is calculated, wherein the total entropy of the data set and the conditional entropy corresponding to the curve reconstruction data (in the form of a curve) are first calculated by the total entropy calculation formula of the data set and the conditional entropy calculation formula, and the total entropy calculation formula of the data set is specifically as follows:
[0106]
[0107] Wherein, H(D) refers to the total entropy of the data set, n is the total number of categories, and C i is the i-th category of the data set, P(C i ) is the C i The proportion occupied.
[0108] The conditional entropy calculation formula is as follows:
[0109]
[0110] Among them, H(D|X) refers to the conditional entropy after segmenting the data set under various values of X, X represents one of the variables in the data set, m is the total number of segmentation points of X, P(X=j) represents the probability of X in the jth value range, and H(D|X=j) represents the total entropy of the data set in the jth value range of X.
[0111] Then, the information gain is calculated according to the information gain calculation formula, the total entropy of the data set and the conditional entropy. The information gain calculation formula is as follows:
[0112] IG(D,X)=H(D)-H(D|X)
[0113] Among them, the IG(D,X) refers to information gain, the H(D) refers to the total entropy of the data set, and the H(D|X) refers to the conditional entropy.
[0114] Step S52, based on each of the injection molding periods, grouping and statistically analyzing the importance scores corresponding to each of the information gains to determine the importance scores corresponding to each of the injection molding periods;
[0115] It should be noted that the importance score is used to evaluate the importance or contribution of a feature, period or stage in data analysis.
[0116] Specifically, the information gains of all curve reconstruction data are sorted to determine their importance, and then the curve reconstruction data are grouped according to the phase in the injection molding process, so as to calculate the importance score corresponding to the phase in the injection molding process after grouping.
[0117] Step S53, obtaining a plurality of groups of second target analysis values based on the importance scores corresponding to the injection molding periods.
[0118] Specifically, the importance scores corresponding to the injection molding periods are sorted, and the target injection molding period is determined according to the sorting results, and then it is judged whether the curve reconstruction data corresponding to the target injection molding period meets the preset target value rule. If so, the curve reconstruction data corresponding to the target injection molding period is used as the second target analysis value. The determination process of the second target analysis value can refer to Figure 3 .
[0119] This embodiment determines several segmentation points of the curve reconstruction data, calculates the information gain corresponding to any segmentation point, and then groups and statistics the importance scores corresponding to each information gain based on each injection molding period to determine the importance score corresponding to each injection molding period, and then obtains several groups of second target analysis values based on the importance scores corresponding to each injection molding period, which helps to focus on the most important injection molding period, thereby improving the efficiency of analysis and decision-making, reducing ineffective labor in unimportant periods, and thus improving the quality of decision-making, ensuring the effectiveness and practicality of the analysis results. In addition, the identified critical periods and target analysis values can be integrated into the automation system to realize automatic monitoring and adjustment of the production process.
[0120] In a feasible implementation manner, based on the importance scores corresponding to the injection molding periods, several groups of second target analysis values are obtained, including:
[0121] Step S61, sorting the importance scores corresponding to the injection molding periods, and determining the target injection molding period according to the sorting results;
[0122] It should be noted that the target injection period refers to an injection period whose importance score meets the conditions.
[0123] Specifically, the importance scores corresponding to the injection molding periods are ranked, and the target injection molding period is determined according to the ranking results. For example, the top two injection molding periods in the ranking results are used as the target injection molding period. The ranking can be set according to actual conditions and is not limited here.
[0124] Step S62, determining whether the curve reconstruction data corresponding to the target injection period meets the preset target value rule;
[0125] It should be noted that the preset target numerical rule refers to a pre-set rule that conforms to numerical analysis, including that the number of data groups is less than a certain value (N1) or the number of groupings exceeds a certain value (N2), wherein N1 and N2 can be defined based on experience, or can be predicted and evaluated based on a large model to obtain the optimal number, which is not limited here and can be set according to actual conditions.
[0126] Step S63: If yes, the curve reconstruction data corresponding to the target injection period is used as the second target analysis value.
[0127] It can be understood that the amount of data can be further reduced by this method. Continuing with the above example, the original 22*1200=26400 data is reduced to 22*11*7=1694 data, and then to 22*2*7=308, where "2" in the calculation formula means that in one embodiment, only the top 2 injection molding periods in importance are retained, which reduces the total amount of data by 99% while retaining the specificity of the data.
[0128] This embodiment sorts the importance scores corresponding to the injection molding periods, determines the target injection molding period according to the sorting results, and then judges whether the curve reconstruction data corresponding to the target injection molding period meets the preset target numerical value rules. If so, the curve reconstruction data corresponding to the target injection molding period is used as the second target analysis value, and then useless phase data is removed, thereby completing the secondary dimensionality reduction of the curve data, improving the pertinence and practicality of data analysis, and at the same time, the production process can be optimized according to the key data after dimensionality reduction to improve the generation efficiency, thereby achieving a double improvement in production efficiency and product quality.
[0129] In a feasible implementation manner, after associating and combining the first target analysis values and the second target analysis values to obtain a third target analysis value, the method further includes:
[0130] Step S71, visualizing the third target analysis value;
[0131] Specifically, according to the data type and analysis target of the third target analysis value, the most suitable chart type (such as line chart, bar chart, scatter plot, etc.) is determined, and then data visualization is performed through preset data visualization tools such as Excel, Tableau, PowerBI, Python (Matplotlib, Seaborn, Plotly, etc.), and R language (ggplot2, etc.).
[0132] Step S72, generating a data analysis report based on the third target analysis value;
[0133] It should be noted that the data analysis report refers to a document specifically for the data analysis results of the injection molding production process, which usually includes a detailed analysis of the data collected during the injection molding process to identify trends, problems and improvement opportunities in production efficiency, product quality, equipment performance, etc.
[0134] Specifically, the third target analysis value is subjected to in-depth analysis, including statistical analysis, trend analysis, comparative analysis, etc., to identify key indicators and findings, such as outliers, key trends, potential problems, etc., and then the analysis results are adapted to a preset report template library, and the adapted data analysis report is reviewed to ensure the accuracy of the data in the report, the rationality of the analysis, and the clarity of the report.
[0135] Step S73: Push the visualized third target analysis value and the data analysis report to the target user for viewing by the target user.
[0136] Specifically, the visualized third target analysis value and the data analysis report are pushed to the target user, wherein the push can be performed through APP notification, injection molding machine display screen and other methods for data display, so that the target user can view it, which can be set according to actual conditions and is not limited here.
[0137] This embodiment visualizes the third target analysis value and generates a data analysis report based on the third target analysis value, so that the visualized third target analysis value and the data analysis report are pushed to the target user for viewing by the target user, thereby enabling the user to quickly identify problems presented by the data, improve information understanding, and enhance decision support, thereby effectively improving decision-making efficiency, enhancing user trust in data analysis and decision-making process, and improving user satisfaction.
[0138] For example, to help understand the implementation process of the injection molding data analysis method, please refer to Figure 4 , Figure 4 A simplified flow chart showing the injection molding data analysis method of this application.
[0139] It should be noted that the examples in the figures are only used to understand the present application and do not constitute a limitation on the injection molding data analysis method of the present application. More simple transformations based on this technical concept are all within the scope of protection of the present application.
[0140] It should be understood that the order of execution of the steps in the above embodiment does not necessarily 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 embodiment of the present invention.
[0141] This application also provides an injection molding data analysis device, please refer to Figure 5 , the injection molding data analysis device comprises:
[0142] An acquisition module 51 is used to acquire injection setting values, statistical process control data and injection curve data corresponding to each injection period in the injection process;
[0143] A first calculation module 52, for calculating and analyzing each of the injection molding setting values and each of the statistical process control data based on each preset numerical analysis method, to obtain a plurality of groups of first target analysis values;
[0144] A second calculation module 53, used for obtaining a plurality of groups of second target analysis values based on the injection curve data corresponding to each of the injection periods;
[0145] The analysis module 54 is used to associate and combine the first target analysis values and the second target analysis values to obtain a third target analysis value.
[0146] The injection molding data analysis device is also used for:
[0147] Performing data standardization on each of the injection molding set values and each of the statistical process control data;
[0148] Based on the principal component analysis method, calculating the eigenvalues and eigenvectors corresponding to each of the injection molding setting values and each of the statistical process control data after data standardization;
[0149] The eigenvalues are sorted, and the eigenvectors corresponding to the eigenvalues with preset rankings are selected as the first target analysis values.
[0150] The injection molding data analysis device is also used for:
[0151] Performing data standardization on each of the injection molding curve data;
[0152] Reconstructing the injection curve data corresponding to each of the injection periods after the data standardization to obtain a plurality of groups of curve reconstruction data;
[0153] The curve reconstruction data corresponding to each injection period is calculated and analyzed to obtain several groups of second target analysis values.
[0154] The injection molding data analysis device is also used for:
[0155] Obtain a statistical value calculation method for curve reconstruction;
[0156] Based on the statistical value calculation method, the injection curve data corresponding to each of the injection periods after the data standardization is calculated to obtain several groups of curve reconstruction data.
[0157] The injection molding data analysis device is also used for:
[0158] Determine a plurality of segmentation points of the curve reconstruction data, and calculate the information gain corresponding to any of the segmentation points;
[0159] Based on each of the injection molding periods, the importance scores corresponding to each of the information gains are grouped and then counted to determine the importance scores corresponding to each of the injection molding periods;
[0160] Based on the importance scores corresponding to the injection molding periods, several groups of second target analysis values are obtained.
[0161] The injection molding data analysis device is also used for:
[0162] Sorting the importance scores corresponding to the injection molding periods, and determining the target injection molding period according to the sorting results;
[0163] Determining whether the curve reconstruction data corresponding to the target injection period meets the preset target value rule;
[0164] If so, the curve reconstruction data corresponding to the target injection period is used as the second target analysis value.
[0165] The injection molding data analysis device is also used for:
[0166] Performing data visualization on the third target analysis value;
[0167] Based on the third target analysis value, generating a data analysis report;
[0168] The visualized third target analysis value and the data analysis report are pushed to a target user for viewing by the target user.
[0169] The injection molding data analysis device provided by the present application adopts the injection molding data analysis method in the above embodiment, and can solve the technical problems in the background technology. Compared with the prior art, the beneficial effects of the injection molding data analysis device provided by the present application are the same as the beneficial effects of the injection molding data analysis method provided by the above embodiment, and the other technical features in the injection molding data analysis device are the same as the features disclosed in the above embodiment method, which will not be repeated here.
[0170] The present application provides an injection molding data analysis device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the injection molding data analysis method in the above-mentioned embodiment one.
[0171] Reference below Figure 6, which shows a schematic diagram of the structure of an injection molding data analysis device suitable for implementing the embodiment of the present application. The injection molding data analysis device in the embodiment of the present application may include but is not limited to mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 6 The injection molding data analysis device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.
[0172] like Figure 6 As shown, the injection molding data analysis device may include a processing device 1001 (e.g., a central processing unit, a graphics processor, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM: Read Only Memory) 1002 or a program loaded from a storage device 1003 to a random access memory (RAM: Random Access Memory) 1004. In RAM1004, various programs and data required for the operation of the injection molding data analysis device are also stored. The processing device 1001, ROM1002, and RAM1004 are connected to each other through a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Generally, the following systems can be connected to the I / O interface 1006: an input device 1007 including, for example, a touch screen, a touch pad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; an output device 1008 including, for example, a liquid crystal display (LCD: Liquid Crystal Display), a speaker, a vibrator, etc.; a storage device 1003 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 1009. The communication device 1009 can allow the injection molding data analysis device to communicate with other devices wirelessly or by wire to exchange data. Although the figure shows an injection molding data analysis device with various systems, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems can be implemented or provided instead.
[0173] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.
[0174] The injection molding data analysis device provided by the present application adopts the injection molding data analysis method in the above embodiment, which can solve the technical problems in the background technology. Compared with the prior art, the beneficial effects of the injection molding data analysis device provided by the present application are the same as the beneficial effects of the injection molding data analysis method provided by the above embodiment, and the other technical features in the injection molding data analysis device are the same as the features disclosed in the method of the previous embodiment, which will not be repeated here.
[0175] It should be understood that the various parts disclosed in this application can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.
[0176] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.
[0177] The present application provides a computer-readable storage medium having computer-readable program instructions (ie, computer programs) stored thereon, and the computer-readable program instructions are used to execute the injection molding data analysis method in the above-mentioned embodiment.
[0178] The computer-readable storage medium provided in the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems or devices, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination of the above.
[0179] The computer-readable storage medium may be included in the injection molding data analysis device; or may exist independently without being assembled into the injection molding data analysis device.
[0180] The computer-readable storage medium carries one or more programs. When the one or more programs are executed by the injection molding data analysis device, the injection molding data analysis device:
[0181] Obtain injection setting values, statistical process control data and injection curve data corresponding to each injection period during the injection molding process;
[0182] Based on each preset numerical analysis method, each of the injection molding setting values and each of the statistical process control data are calculated and analyzed to obtain a plurality of groups of first target analysis values;
[0183] Based on the injection curve data corresponding to each of the injection periods, a plurality of groups of second target analysis values are obtained;
[0184] The first target analysis values and the second target analysis values are associated and combined to obtain a third target analysis value.
[0185] Computer program code for performing the operations of the present application may be written in one or more programming languages or a combination thereof, including object-oriented programming languages such as Java, Smalltalk, C++, and conventional procedural programming languages such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).
[0186] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.
[0187] The modules involved in the embodiments described in this application may be implemented by software or hardware, wherein the name of the module does not constitute a limitation on the unit itself in some cases.
[0188] The readable storage medium provided in the present application is a computer-readable storage medium, which stores computer-readable program instructions (i.e., computer programs) for executing the above-mentioned injection molding data analysis method, and can solve the technical problems in the background technology. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in the present application are the same as the beneficial effects of the injection molding data analysis method provided in the above-mentioned embodiment, and will not be repeated here.
[0189] An embodiment of the present application provides a computer program product, including a computer program, which implements the steps of the injection molding data analysis method as described above when executed by a processor.
[0190] The computer program product provided in this application can solve the technical problems in the background technology. Compared with the prior art, the beneficial effects of the computer program product provided in the embodiment of this application are the same as the beneficial effects of the injection molding data analysis method provided in the above embodiment, which will not be repeated here.
[0191] The above descriptions are only some embodiments of the present application, and are not intended to limit the patent scope of the present application. All equivalent structural changes made using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect applications in other related technical fields are included in the patent protection scope of the present application.
Claims
1. A method for analyzing injection molding data, characterized in that: include: Obtain injection setting values, statistical process control data and injection curve data corresponding to each injection period during the injection molding process; Based on each preset numerical analysis method, each of the injection molding setting values and each of the statistical process control data are calculated and analyzed to obtain a plurality of groups of first target analysis values; Based on the injection curve data corresponding to each of the injection periods, a plurality of groups of second target analysis values are obtained; The first target analysis values and the second target analysis values are associated and combined to obtain a third target analysis value.
2. The injection molding data analysis method according to claim 1, characterized in that: The preset numerical analysis method includes a principal component analysis method; The method of calculating and analyzing the injection molding setting values and the statistical process control data based on the preset numerical analysis methods to obtain the first target analysis value includes: Performing data standardization on each of the injection molding set values and each of the statistical process control data; Based on the principal component analysis method, calculating the eigenvalues and eigenvectors corresponding to each of the injection molding setting values and each of the statistical process control data after data standardization; The eigenvalues are sorted, and the eigenvectors corresponding to the eigenvalues with preset rankings are selected as the first target analysis values.
3. The injection molding data analysis method according to claim 1, characterized in that: Based on the injection molding curve data corresponding to each injection molding period, a plurality of groups of second target analysis values are obtained, including: Performing data standardization on each of the injection molding curve data; Reconstructing the injection curve data corresponding to each of the injection periods after the data standardization to obtain a plurality of groups of curve reconstruction data; The curve reconstruction data corresponding to each injection period is calculated and analyzed to obtain several groups of second target analysis values.
4. The injection molding data analysis method according to claim 3, characterized in that: The injection molding curve data corresponding to each injection molding period after the data standardization is reconstructed to obtain several groups of curve reconstruction data, including: Obtain a statistical value calculation method for curve reconstruction; Based on the statistical value calculation method, the injection curve data corresponding to each of the injection periods after the data standardization is calculated to obtain several groups of curve reconstruction data.
5. The injection molding data analysis method according to claim 3, characterized in that: The curve reconstruction data corresponding to each injection period is calculated and analyzed to obtain several groups of second target analysis values, including: Determine a plurality of segmentation points of the curve reconstruction data, and calculate the information gain corresponding to any of the segmentation points; Based on each of the injection molding periods, the importance scores corresponding to each of the information gains are grouped and then counted to determine the importance scores corresponding to each of the injection molding periods; Based on the importance scores corresponding to the injection molding periods, several groups of second target analysis values are obtained.
6. The injection molding data analysis method according to claim 5, characterized in that: Based on the importance scores corresponding to the injection molding periods, several groups of second target analysis values are obtained, including: Sorting the importance scores corresponding to the injection molding periods, and determining the target injection molding period according to the sorting results; Determining whether the curve reconstruction data corresponding to the target injection period meets the preset target value rule; If so, the curve reconstruction data corresponding to the target injection period is used as the second target analysis value.
7. The injection molding data analysis method according to claim 1, characterized in that: After associating and combining the first target analysis values and the second target analysis values to obtain a third target analysis value, the method further includes: Performing data visualization on the third target analysis value; Based on the third target analysis value, generating a data analysis report; The visualized third target analysis value and the data analysis report are pushed to a target user for viewing by the target user.
8. An injection molding data analysis device, characterized in that: include: An acquisition module is used to acquire the injection setting values, statistical process control data and injection curve data corresponding to each injection period in the injection molding process; A first calculation module, used for calculating and analyzing each of the injection molding setting values and each of the statistical process control data based on each preset numerical analysis method to obtain a plurality of groups of first target analysis values; A second calculation module, used for obtaining a plurality of groups of second target analysis values based on the injection curve data corresponding to each of the injection periods; The analysis module is used to associate and combine the first target analysis values and the second target analysis values to obtain a third target analysis value.
9. An injection molding data analysis device, characterized in that: The injection molding data analysis device comprises: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the injection molding data analysis method according to any one of claims 1 to 7.
10. A storage medium, characterized in that: The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the injection molding data analysis method according to any one of claims 1 to 7 are implemented.