CN114535142B - Intelligent judgment method for size qualification of injection molding product based on data driving - Google Patents
Intelligent judgment method for size qualification of injection molding product based on data driving Download PDFInfo
- Publication number
- CN114535142B CN114535142B CN202210024752.6A CN202210024752A CN114535142B CN 114535142 B CN114535142 B CN 114535142B CN 202210024752 A CN202210024752 A CN 202210024752A CN 114535142 B CN114535142 B CN 114535142B
- Authority
- CN
- China
- Prior art keywords
- size
- injection molding
- data
- classification model
- value
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 66
- 238000001746 injection moulding Methods 0.000 title claims abstract description 56
- 238000012797 qualification Methods 0.000 title claims abstract description 19
- 238000012216 screening Methods 0.000 claims abstract description 54
- 238000013145 classification model Methods 0.000 claims abstract description 46
- 238000001514 detection method Methods 0.000 claims abstract description 22
- 238000005457 optimization Methods 0.000 claims abstract description 9
- 238000004140 cleaning Methods 0.000 claims abstract description 7
- 238000002790 cross-validation Methods 0.000 claims abstract description 7
- 238000012545 processing Methods 0.000 claims abstract description 5
- 238000002347 injection Methods 0.000 claims description 19
- 239000007924 injection Substances 0.000 claims description 19
- 238000004364 calculation method Methods 0.000 claims description 11
- 238000010606 normalization Methods 0.000 claims description 3
- 238000004519 manufacturing process Methods 0.000 description 3
- 230000007547 defect Effects 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 239000000853 adhesive Substances 0.000 description 1
- 230000001070 adhesive effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 210000003734 kidney Anatomy 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 239000000155 melt Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B07—SEPARATING SOLIDS FROM SOLIDS; SORTING
- B07C—POSTAL SORTING; SORTING INDIVIDUAL ARTICLES, OR BULK MATERIAL FIT TO BE SORTED PIECE-MEAL, e.g. BY PICKING
- B07C5/00—Sorting according to a characteristic or feature of the articles or material being sorted, e.g. by control effected by devices which detect or measure such characteristic or feature; Sorting by manually actuated devices, e.g. switches
- B07C5/34—Sorting according to other particular properties
- B07C5/342—Sorting according to other particular properties according to optical properties, e.g. colour
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B07—SEPARATING SOLIDS FROM SOLIDS; SORTING
- B07C—POSTAL SORTING; SORTING INDIVIDUAL ARTICLES, OR BULK MATERIAL FIT TO BE SORTED PIECE-MEAL, e.g. BY PICKING
- B07C5/00—Sorting according to a characteristic or feature of the articles or material being sorted, e.g. by control effected by devices which detect or measure such characteristic or feature; Sorting by manually actuated devices, e.g. switches
- B07C5/36—Sorting apparatus characterised by the means used for distribution
- B07C5/361—Processing or control devices therefor, e.g. escort memory
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Injection Moulding Of Plastics Or The Like (AREA)
Abstract
The invention discloses an intelligent judgment method for the size qualification of an injection molding product based on data driving, which comprises the following steps: s1, acquiring process data in an injection molding process, cleaning the acquired data set, and carrying out standardized processing on the data set to reconstruct a label; s2, determining the dimension of feature screening, screening features and reducing the dimension of input data by using a feature screening method based on a tree model and a chi-square detection feature screening method for the obtained data set; s3, screening a classification model by adopting 5-fold cross validation, and evaluating the classification performance of the screened classification model by using an ROC curve and an AUC value; s4, adding L1 regularization into a loss function of the classification model; s5, performing Bayesian optimization on the classification model, selecting the hyper-parameters most suitable for the injection molding data set, and improving the classification accuracy of the model; s6, applying to actual judgment. The invention is used for solving the problems of low efficiency and low accuracy of the manual detection of the size qualification of the injection molding product.
Description
Technical Field
The invention belongs to the technical field of injection molding, and particularly relates to an intelligent judgment method for the size qualification of an injection molding product based on data driving.
Background
The plastic has the characteristics of good plasticity, higher impact strength, good chemical stability and the like, so that the plastic product is widely applied to various industries and fields, wherein the plastic product manufactured by the injection molding process accounts for more than 60 percent. With the continuous update of internet technology, the concept of internet + intelligent manufacturing is more and more closely related to the injection molding process.
The quality of the injection molding product is related to a plurality of factors, the mutual influence among the factors is realized, the direct judgment of a certain index of the injection molding product is required, and the defects of poor stability, low accuracy and low efficiency of the traditional method by means of limited experience and a simple formula are more and more obvious. Therefore, an intelligent method based on data driving appears in the large environment of Internet plus intelligent manufacturing, and the intelligent method based on data driving not only can predict the machine failure of the injection molding machine, but also can directly judge some indexes of injection molding products.
The size of the injection molding product is the key point of quality detection of the injection molding product, the determination of the size qualification of the injection molding product mainly depends on manual detection at the present stage in China, the manual detection needs to measure the size of the injection molding product by using a detection tool, the speed is low, the investment of manpower and material resources is huge, and the missed determination and the misdetermination are easy to cause, so that the data in the injection molding processing process are used as a drive, and the establishment of a classification model suitable for an injection molding data set is a problem to be solved urgently.
Disclosure of Invention
The invention mainly aims to overcome the defects and shortcomings of the prior art, and provides an intelligent judgment method for the size qualification of an injection molding product based on data driving, so as to solve the problems of low efficiency and low accuracy of manual detection on the size qualification of the injection molding product.
In order to achieve the above purpose, the present invention adopts the following technical scheme:
the intelligent judgment method for the size qualification of the injection molding product based on data driving comprises the following steps:
s1, acquiring process data in an injection molding process, cleaning the acquired data set, and carrying out standardized processing on the data set to reconstruct a label;
s2, determining the dimension of feature screening and screening features by using a feature screening method based on a tree model and a chi-square detection feature screening method by using the acquired data set;
s3, screening a classification model by adopting 5-fold cross validation, and evaluating the classification performance of the screened size classification model by using an ROC curve and an AUC value to obtain an optimal size classification model;
s4, adding L1 regularization into a loss function of the optimal size classification model to prevent overfitting;
s5, performing Bayesian optimization on the optimal size classification model, selecting the hyper-parameters most suitable for the injection molding data set, and improving the classification accuracy of the classification model;
s6, applying the optimal size classification model to intelligent judgment of the size qualification of the injection molding product, sorting the importance degree of the characteristics affecting the size of the injection molding product, and helping to judge the failure area and reduce the failure detection time when the size of the injection molding product is problematic.
Further, in step S1, the data cleaning includes filling or deleting the missing values, constructing the difference feature, and deleting the unchanged feature.
Further, in step S1, the normalization process specifically includes:
the min-max standardization is used for carrying out linear change on the original acquired data, so that the result value is mapped between [0,1], and the calculation formula is as follows:
wherein x represents the original value, x * The normalized value is represented by min, the minimum value in the whole feature, and max, the maximum value in the whole feature.
Further, in step S1, the reconstruction tag specifically includes:
the label is marked 1 when the dimensional data of the injection molded article is within the allowable tolerance range and 0 when the dimensional data of the injection molded article is outside the allowable tolerance range.
Further, in step S2, feature screening based on the tree model specifically includes:
the importance degree of the features is ordered by the change amount of the base purity, and the calculation formula is as follows:
ΔGini(A)＝Gini(D)-Gini(D-A)
wherein Gini (D) represents the genii purity, P, of dataset D i Representing the probability of the total number of samples of category i, Δgini (D-a) being the decrease in the base purity after the addition of feature a, the larger this value indicating the greater the correlation of feature a with the tag, gini (D-a) determining the base purity after feature a for data set D;
the chi-square detection characteristic screening method specifically comprises the following steps:
the importance degree of the features is ordered according to the chi-square value, and the calculation formula is as follows:
wherein ,xi Representing the actual value and E representing the theoretical value.
Further, in step S2, the dimension of the feature screening is determined specifically as follows:
when a feature screening method based on a tree model is used, taking the average value of Δgini as a threshold value; when using chi-square detection feature screening methods, the average of chi-square values is used as the threshold.
Further, in step S3, the 5-fold cross-validation method specifically includes:
the injection molded data set was split into 5 data sets, the average of 5 MSEs was calculated, and the average MSE was used to screen the existing classification model commonly used for industrial data.
Further, in step S3, the classification performance of the screened size classification model is evaluated by using ROC curve and AUC value, specifically:
the following criteria were evaluated: true class TP, missed FP, false FN, true negative class TN, ratio TPR of samples classified as good to all good, ratio FPR of samples classified as bad to all bad, and Accuracy.
Further, the step S4 specifically includes:
adding L1 regularization into a loss function of the LR model to prevent the model from being over-fitted, wherein the loss function has a formula of:
wherein, I omega I 1 For the L1 regularization term, α is the coefficient before the regularization term.
Further, in step S5, the super parameters of the size classification model are optimized by using a bayesian optimization method, so as to obtain the super parameters most suitable for the size data set of the injection molding product, and the best size classification model is obtained, so that the classification accuracy is the highest.
Compared with the prior art, the invention has the following advantages and beneficial effects:
1. the invention takes an injection molding process data set as a drive, and combines a machine-learned classification model to directly carry out intelligent judgment on the qualification of the size of an injection molding product, based on the intelligent judgment, the size data in the data set is reconstructed, and the qualification and the disqualification are taken as labels; screening a classification model which is most suitable for the size of the injection molding product by comparing the combination of different feature screening and models; for the phenomenon that the model is over-fitted due to the fact that the monitoring parameters in the injection molding data set can be linearly or nonlinearly represented by the process parameters, L1 regularization is added into a loss function of the model, and the sparse matrix is used for preventing the model from being over-fitted; finally, performing Bayesian optimization on the whole model, selecting the most suitable super-parameter value of the injection molding data set, and improving the classification accuracy of the classification model; the importance of the features influencing the size is ordered by a feature screening method based on a tree model, and when the size of the injection molding product is unqualified, the factors influencing the large size of the injection molding product can be checked preferentially, so that the overhaul time is shortened.
Drawings
FIG. 1 is a flow chart of the method of the present invention;
FIG. 2 is a flow chart of 5-fold cross-validation;
FIG. 3 is a classification model ROC curve combined with tree-model-based feature screening;
FIG. 4 is a classification model ROC curve combined with chi-square detection feature screening;
FIG. 5 is a ranking of feature importance based on tree model feature screening.
Detailed Description
The present invention will be described in further detail with reference to examples and drawings, but embodiments of the present invention are not limited thereto.
Examples
As shown in fig. 1, the intelligent determining method for the size qualification of the injection molding product based on data driving comprises the following steps:
s1, acquiring process data in an injection molding process, cleaning the acquired data set, and carrying out standardized processing on the data set to reconstruct a label;
the data cleaning comprises filling or deleting missing values, constructing difference value features, deleting unchanged features and the like. In this embodiment, the missing values in each feature are counted, when the missing value in the feature is greater than 50%, the feature is deleted, and when the missing value is less than 50%, the missing value is filled with the average value.
The standardized treatment is specifically as follows:
the min-max normalization is used for carrying out linear change on the original data, so that the result value is mapped between [0,1], and the calculation formula is as follows:
wherein x represents the original value, x * The normalized value is represented by min, the minimum value in the whole feature, and max, the maximum value in the whole feature.
The reconstruction tag specifically comprises:
the label is marked 1 when the dimensional data of the injection molded article is within the allowable tolerance range and 0 when the dimensional data of the injection molded article is outside the allowable tolerance range.
S2, determining the dimension of feature screening by using a feature screening method based on a tree model and a chi-square detection feature screening method by using the acquired data set, screening features and reducing the dimension of input data;
the feature screening based on the tree model specifically comprises the following steps:
the importance degree of the features is ordered by the change amount of the base purity, and the calculation formula is as follows:
ΔGini(A)＝Gini(D)-Gini(D-A)
wherein Gini (D) representsThe data set D has a Kidney purity, P i Representing the probability of the total number of samples of category i, Δgini (D-a) being the decrease in the base purity after the addition of feature a, the larger this value indicating the greater the correlation of feature a with the tag, gini (D-a) determining the base purity after feature a for data set D;
the chi-square detection characteristic screening method specifically comprises the following steps:
the importance degree of the features is ordered according to the chi-square value, and the calculation formula is as follows:
wherein ,xi Representing the actual value and E representing the theoretical value.
In this embodiment, the dimensions for determining feature screening are specifically:
when a feature screening method based on a tree model is used, screening out features larger than a threshold value by taking an average value of delta Gini as the threshold value to obtain 19-dimensional features; when the chi-square detection feature screening method is used, the average value of chi-square values is used as a threshold value, features with the chi-square values larger than the threshold value are screened out, 19-dimensional features are obtained, the feature dimensions obtained by combining the two feature screening methods are 19, and finally the screened feature dimensions are determined to be 19.
S3, screening a classification model by adopting 5-fold cross validation, and evaluating the classification performance of the screened classification model by using an ROC curve and an AUC value to obtain an optimal classification model;
the 5-fold cross verification method specifically comprises the following steps:
the injection molded dataset was split into 5 datasets, the average of 5 MSEs was calculated, and the classification model was screened for average MSEs.
In this embodiment, as shown in fig. 2, by dividing the training set into 5 sets of data sets, taking one data set at a time as a test set, taking the other 4 sets of data sets as training sets, calculating 5 times in total, obtaining an MSE at each time, and finally calculating an average value of 5 MSEs, where the calculation formula is as follows:
the average MSE of 7 classification models was obtained as shown in table 1 below.
TABLE 1
Calculating the average value of the seven models to be 0.951, taking 0.951 as a threshold value, and selecting a classification model larger than the threshold value to finish preliminary screening.
And evaluating the classification performance of the screened classification model by using an ROC curve and an AUC value, wherein the classification performance is as follows:
evaluating indexes such as a true class TP, a missed class FP, a false positive FN, a true negative class TN, a ratio TPR of samples of qualified products to all qualified products, a ratio FPR of samples of unqualified products to qualified products to all unqualified products, and an Accuracy Accuracy; wherein, the index calculation formula is:
in step S4, the ROC curve obtained under the combination of the feature screening method and the classification model based on the tree model is shown in fig. 3, the ROC curve obtained under the combination of the feature screening method and the classification model based on the chi-square detection is shown in fig. 4, and comparing the two sets of ROC curves to find the point (0, 1) closest to the ROC curve of the LR model under the feature screening method of the tree model or the feature screening of the chi-square detection, which indicates that the LR model is more suitable for size classification of injection-molded products. The obtained AUC values based on the two feature screening are shown in the following table 2, and the AUC values of each model under the feature screening based on the tree model are found to be generally higher than the AUC values of the feature screening based on chi-square detection by comparing the AUC values under the two feature screening, so that the feature screening method based on the tree model is more suitable for classifying the size qualification of injection molding products.
TABLE 2
S4, adding L1 regularization into a loss function of the classification model to prevent overfitting;
because of the problem of multiple collinearity easily generated on the injection molding data set, the monitoring parameters in the injection molding data can be represented by machine parameters linearly or nonlinearly, such as the nozzle pressure is related to the injection starting point, the injection maximum pressure, the melt adhesive time and the like; the temperature in the die cavity is related to the die temperature, barrel temperature, hot runner temperature, etc. The parameters are mutually interfered when the model is fitted, so that the model is easy to be over-fitted, L1 regularization is added into a loss function of the LR model, the model is effectively prevented from being over-fitted through a sparse matrix, and the loss function has the formula:
wherein, I omega I 1 For the L1 regularization term, α is the coefficient before the regularization term.
S5, performing Bayesian optimization on the classification model, selecting the hyper-parameters most suitable for the injection molding data set, and improving the classification accuracy of the model;
and optimizing the hyper-parameters of the final model, such as regular term coefficients, type weight parameters and the like by using a Bayesian optimization method, calculating the mean value and the variance of the function value at each point mainly through Gaussian process regression, constructing an acquisition function according to the mean value and the variance, determining at which point each iteration is sampled, and obtaining the hyper-parameters which are most suitable for the size data set of the injection molding product through continuous iteration to obtain the best size classification model so as to ensure that the classification accuracy is highest. As shown in table 3 below, the comparison was made before and after the optimization.
TABLE 3 Table 3
S6, applying the optimal classification model to intelligent judgment of the size qualification of the injection molding product, sorting the importance degree of the characteristics affecting the size of the injection molding product, and helping to judge the fault area and reduce the time of fault investigation when the size of the injection molding product is problematic.
The obtained optimal injection molding product size classification model sorts the importance degree of the features through a feature screening method based on a tree model in the model, as shown in fig. 5, it can be seen that the size is more sensitive to the data collected by the sensor because the data collected by the sensor is more close to the production practice, and the nozzle pressure is the factor affecting the maximum size, and then the pressure in the mold cavity and the circulating water temperature of the mold temperature machine can be seen from the figure, so that when the size of the injection molding product is problematic, whether the nozzle is damaged, whether the mold is damaged and whether the mold temperature machine is normally operated can be checked preferentially, thereby helping fault checking and reducing maintenance time.
It should also be noted that in this specification, terms such as "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (10)
1. The intelligent judgment method for the size qualification of the injection molding product based on data driving is characterized by comprising the following steps of:
s1, acquiring process data in an injection molding process, cleaning the acquired data set, and carrying out standardized processing on the data set to reconstruct a label;
s2, determining the dimension of feature screening and screening features by using a feature screening method based on a tree model and a chi-square detection feature screening method by using the acquired data set;
s3, screening a classification model by adopting 5-fold cross validation, and evaluating the classification performance of the screened size classification model by using an ROC curve and an AUC value to obtain an optimal size classification model;
s4, adding L1 regularization into a loss function of the optimal size classification model to prevent overfitting;
s5, performing Bayesian optimization on the optimal size classification model, selecting the hyper-parameters most suitable for the injection molding data set, and improving the classification accuracy of the classification model;
s6, applying the optimal size classification model to intelligent judgment of the size qualification of the injection molding product, sorting the importance degree of the characteristics affecting the size of the injection molding product, and helping to judge the failure area and reduce the failure detection time when the size of the injection molding product is problematic.
2. The intelligent determination method for dimensional eligibility of a data-driven injection molded article according to claim 1, wherein in step S1, the data cleaning includes filling or deleting missing values, constructing difference features, and deleting unchanged features.
3. The intelligent determining method for size eligibility of injection molded products based on data driving according to claim 1, wherein in step S1, the normalization process specifically comprises:
the min-max standardization is used for carrying out linear change on the original acquired data, so that the result value is mapped between [0,1], and the calculation formula is as follows:
wherein x represents the original value, x * The normalized value is represented by min, the minimum value in the whole feature, and max, the maximum value in the whole feature.
4. The intelligent determination method for size eligibility of an injection molded product based on data driving according to claim 1, wherein in step S1, the reconstruction tag specifically comprises:
the label is marked 1 when the dimensional data of the injection molded article is within the allowable tolerance range and 0 when the dimensional data of the injection molded article is outside the allowable tolerance range.
5. The intelligent determining method for size eligibility of injection molded products based on data driving according to claim 1, wherein in step S2, feature screening based on a tree model is specifically:
the importance degree of the features is ordered by the change amount of the base purity, and the calculation formula is as follows:
ΔGini(A)＝Gini(D)-Gini(D-A)
wherein Gini (D) represents the genii purity, P, of dataset D i Samples of class iThe probability of the total number, Δgini (a), is the decrease in the base purity after adding feature a, the larger this value indicates the greater the correlation of feature a with the tag, gini (D-a) determines the base purity after feature a for data set D;
the chi-square detection characteristic screening method specifically comprises the following steps:
the importance degree of the features is ordered according to the chi-square value, and the calculation formula is as follows:
wherein ,xi Representing the actual value and E representing the theoretical value.
6. The intelligent determination method for size eligibility of an injection molded product based on data driving according to claim 5, wherein in step S2, the dimensions of the feature screening are determined specifically as follows:
when a feature screening method based on a tree model is used, taking the average value of Δgini (a) as a threshold value; when using chi-square detection feature screening methods, the average of chi-square values is used as the threshold.
7. The intelligent determining method for the size qualification of an injection molded product based on data driving according to claim 1, wherein in step S3, the 5-fold cross validation method specifically comprises:
the injection molded data set was split into 5 data sets, the average of 5 MSEs was calculated, and the average MSE was used to screen the existing classification model commonly used for industrial data.
8. The intelligent determination method for size eligibility of injection molded products based on data driving according to claim 1, wherein in step S3, classification performance of the screened size classification model is evaluated by ROC curve and AUC value, specifically:
the following criteria were evaluated: true class TP, missed FP, false FN, true negative class TN, ratio TPR of samples classified as good to all good, ratio FPR of samples classified as bad to all bad, and Accuracy.
9. The intelligent determining method for the size eligibility of the injection molded product based on data driving according to claim 1, wherein the step S4 is specifically:
adding L1 regularization into a loss function of the LR model to prevent the model from being over-fitted, wherein the loss function has a formula of:
wherein, I omega I 1 For the L1 regularization term, α is the coefficient before the regularization term.
10. The intelligent judging method for the size qualification of the injection molding product based on the data driving according to claim 1, wherein in the step S5, the super parameters of the size classification model are optimized by using a Bayes optimization method to obtain the super parameters which are most suitable for the size data set of the injection molding product, and the best size classification model is obtained, so that the classification accuracy is highest.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210024752.6A CN114535142B (en) | 2022-01-11 | 2022-01-11 | Intelligent judgment method for size qualification of injection molding product based on data driving |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210024752.6A CN114535142B (en) | 2022-01-11 | 2022-01-11 | Intelligent judgment method for size qualification of injection molding product based on data driving |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114535142A CN114535142A (en) | 2022-05-27 |
| CN114535142B true CN114535142B (en) | 2023-09-26 |
Family
ID=81669969
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210024752.6A Active CN114535142B (en) | 2022-01-11 | 2022-01-11 | Intelligent judgment method for size qualification of injection molding product based on data driving |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114535142B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109257383A (en) * | 2018-11-09 | 2019-01-22 | 中国人民解放军战略支援部队信息工程大学 | A kind of BGP method for detecting abnormality and system |
| CN113379135A (en) * | 2021-06-18 | 2021-09-10 | 浙江大学 | Intelligent production line product quality low-delay integrated prediction method and system based on cloud edge collaborative computing |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8095498B2 (en) * | 2008-12-17 | 2012-01-10 | International Business Machines Corporation | Data mining model interpretation, optimization, and customization using statistical techniques |
-
2022
- 2022-01-11 CN CN202210024752.6A patent/CN114535142B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109257383A (en) * | 2018-11-09 | 2019-01-22 | 中国人民解放军战略支援部队信息工程大学 | A kind of BGP method for detecting abnormality and system |
| CN113379135A (en) * | 2021-06-18 | 2021-09-10 | 浙江大学 | Intelligent production line product quality low-delay integrated prediction method and system based on cloud edge collaborative computing |
Non-Patent Citations (1)
| Title |
|---|
| 基于特征选择和贝叶斯优化LightGBM 的注塑制品尺寸预测;宋建等;工程塑料应用;第第49卷卷(第第8期期);第54-60页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114535142A (en) | 2022-05-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111460728B (en) | Method and device for predicting residual life of industrial equipment, storage medium and equipment | |
| CN108875772B (en) | Fault classification model and method based on stacked sparse Gaussian Bernoulli limited Boltzmann machine and reinforcement learning | |
| CN107562696B (en) | On-line detection and control method for tire product quality | |
| US11966847B2 (en) | Method for constructing efficient product surface defect detection model based on network collaborative pruning | |
| CN109145948A (en) | A kind of injection molding machine putty method for detecting abnormality based on integrated study | |
| CN109783898A (en) | A kind of intelligent optimization method of injection molding manufacturing technique parameter | |
| CN111768000A (en) | Industrial process data modeling method for online adaptive fine-tuning deep learning | |
| CN1752984A (en) | Determination method of plastic injection technological parameter and injection moulding machine | |
| CN108241925A (en) | A kind of discrete manufacture mechanical product quality source tracing method based on outlier detection | |
| CN112085108B (en) | Photovoltaic power station fault diagnosis algorithm based on automatic encoder and K-means clustering | |
| CN113515512A (en) | Quality control and improvement method for industrial internet platform data | |
| CN112749840A (en) | Method for acquiring reference value of energy efficiency characteristic index of thermal power generating unit | |
| CN113103535A (en) | GA-ELM-GA-based injection molding part mold parameter optimization method | |
| CN114535142B (en) | Intelligent judgment method for size qualification of injection molding product based on data driving | |
| WO2023108514A1 (en) | Spectral peak automatic detection and reconstruction method and system in tea near-infrared spectral analysis | |
| US11816556B1 (en) | Method for predicting air quality index (AQI) based on a fusion model | |
| CN113177578A (en) | Agricultural product quality classification method based on LSTM | |
| CN116340936A (en) | ICS intrusion detection system and method integrating reinforcement learning and feature selection optimization | |
| CN111860631B (en) | Article identification method adopting error factor reinforcement mode to optimize loss function | |
| CN110175166A (en) | A kind of tobacco rolls up the confirmation method of abnormal quality between hired car | |
| CN114239378A (en) | Injection molding product size prediction method based on custom LightGBM model loss | |
| CN114841262A (en) | Rolling bearing fault diagnosis method based on DS evidence theory | |
| CN115116616A (en) | Intra-group optimization based multiple interpolation breast cancer deletion data interpolation model | |
| CN108133261B (en) | Automobile rubber hose mandrel quality evaluation method based on BP neural network | |
| CN115266152B (en) | Automobile tire lateral force detection method and system based on deep learning |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |