Application of Machine Learning for Prediction and Process Optimization—Case Study of Blush Defect in Plastic Injection Molding

Ardestani, Alireza Mollaei; Azamirad, Ghasem; Shokrollahi, Yasin; Calaon, Matteo; Hattel, Jesper Henri; Külahçı, Murat; Soltani, Roya; Tosello, Guido

doi:10.3390/app13042617

Cited by 10 publications

(5 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Ardestani et al [19] analyzed eight process parameters (flow rate, melt temperature, mold temperature, holding pressure, runner diameter, gate diameter, gate angle, and included angle) for producing PVC bushings. They employed both the ANOVA and ANN techniques.…”

Section: Literature Review a ML Studies On Injection Moldingmentioning

confidence: 99%

“…Further, ML techniques can predict the quality of injection-molded products by analyzing the data generated throughout the production process. Previous research in injection molding has often involved developing single ML models for quality prediction or process optimization [12][13][14][15][16][17][18][19][20]. However, the current trend is toward utilizing ensemble model and, combining multiple models to enhance overall prediction accuracy [21][22][23][24].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Double Ensemble Technique for Improving the Weight Defect Prediction of Injection Molding in Smart Factories

Koo,

Choi,

Yoo

2023

IEEE Access

View full text Add to dashboard Cite

The growing move toward smart factories can leverage industrial big data to enhance productivity. In particular, research is being conducted on injection molding and utilizing machine learning techniques to analyze molding process data, discover optimal molding conditions, and predict and improve product quality. This study aims to identify the key factors influencing the weight defects of injection-molded products and demonstrate the potential use of the double ensemble technique for better prediction accuracy of weight defects. We obtain the key factors influencing weight defects prediction, barrel H2 temp real, metering time, and fill time using gain ratio analysis. Subsequently, we develop single models using machine learning algorithms, including decision tree, random forest, logistic regression, the Bayesian network, and the artificial neural network. Ensemble models, including bagging and boosting and double ensemble models are developed to compare their performance with that of single models. The findings indicate that ensemble models outperform the prediction accuracy of the single models. The double ensemble technique demonstrates the greatest improvements in prediction accuracy over the single models. These results showcase the potential of applying the double ensemble technique to other injection molding areas and suggest that adopting this technique will contribute to establishing other smart factories that will enhance both productivity and cost competitiveness.

show abstract

Section: Literature Review a ML Studies On Injection Moldingmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Double Ensemble Technique for Improving the Weight Defect Prediction of Injection Molding in Smart Factories

Koo,

Choi,

Yoo

2023

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Tsai et al [12] used Moldex3D and the Taguchi method for optimising the mould filling rate for injection moulding of PVC and reported that the temperature of the part increased due to the injection rate. Ardestan et al [13] tried to optimise the blush defect in PVC bushings made using injection moulding by using ANN, PSO, and GA. They validated their outcome using FEA and reported runner diameter as the most influential factor.…”

Section: Introductionmentioning

confidence: 99%

Weight Optimization of Plastic Injection Moulded Electrical Wire Casing Thermoplastic using Hybrid RSM-Tunicate Swarm Algorithm

Barua,

Jeet,

Mishra

et al. 2023

E3S Web Conf.

View full text Add to dashboard Cite

The need for fire-retardant material for electrical wire covers and cases is increasing as the global population continues to expand at an alarming rate. In addition to having good fire and chemical resistance, CPVC (chlorinated polyvinyl chloride) is widely accessible in a assortment of forms and sizes, comprising rods, sheets, and tubes. Plastic injection moulding (PIM) provides a method that allows for the production of CPVC items at a rapid pace and at a low cost. When these mouldings are lightweight, they may reduce the amount of non-biodegradable materials that are used in their construction. The present research gives an insight into the CPVC material moulding for electrical wire casing elbows using an injection moulding machine, which was previously unexplored. Four plastic injection moulding parameters were considered in order to reduce the weight of the elbow, including injection pressure, mould closing speed, mould pressure, and backpressure. The 27 tests were piloted in line with Response Surface Methodbased Box-Behnken Design, and the factors were optimised using Tunicate Swarm Algorithm, which was recently developed. In the case of the plastic injection-moulded item, the analysis of variance revealed that the most significant parameter in the weight reduction was the material used. It has been determined that mould pressure is the most critical factor impacting the weight of the item when it is manufactured. As a result, the optimum manufacture of injection-moulded CPVC components will be facilitated, resulting in optimised weight while also minimising production time and raw material waste for electrical wire casing.

show abstract

“…However, FEM simulations can be expensive, especially for highly nonlinear analyses or complex geometries. Consequently, substantial endeavors have been devoted to substituting FEM with machine learning (ML) techniques, commonly employed for surrogate modeling [10][11][12][13][14][15][16][17] of pertinent quantities of interest.…”

Section: Introductionmentioning

confidence: 99%

Deep Learning-based Prediction of Stress and Strain Maps in Arterial Walls for Improved Cardiovascular Risk Assessment

Shokrollahi,

Dong,

et al. 2023

Preprint

View full text Add to dashboard Cite

Conducting computational stress-strain analysis using finite element methods (FEM) is a common approach when dealing with the complex geometries of atherosclerosis, which is a leading cause of global mortality and complex cardiovascular disease. The considerable expense linked to FEM analysis encourages the substitution of FEM with a considerably faster data-driven machine learning (ML) approach. This study investigated the potential of end-to-end deep learning tools as a more effective substitute for FEM in predicting stress-strain fields within 2D cross sections of arterial wall. We first proposed a U-Net based fully convolutional neural network (CNN) to predict the von Mises stress and strain distribution based on the spatial arrangement of calcification within arterial wall cross-sections. Further, we developed a conditional generative adversarial network (cGAN) to enhance, particularly from the perceptual perspective, the prediction accuracy of stress and strain field maps for arterial walls with various calcification quantities and spatial configurations. On top of U-Net and cGAN, we also proposed their ensemble approaches to further improve the prediction accuracy of field maps. Our dataset, consisting of input and output images, was generated by implementing boundary conditions and extracting stress-strain field maps. The trained U-Net models can accurately predict von Mises stress and strain fields, with structural similarity index scores (SSIM) of 0.854 and 0.830 and mean squared errors of 0.017 and 0.018 for stress and strain, respectively, on a reserved test set. Meanwhile, the cGAN models in a combination of ensemble and transfer learning techniques demonstrate high accuracy in predicting von Mises stress and strain fields, as evidenced by SSIM scores of 0.890 for stress and 0.803 for strain. Additionally, mean squared errors of 0.008 for stress and 0.017 for strain further support the model's performance on a designated test set. Overall, this study developed a surrogate model for finite element analysis, which can accurately and efficiently predict stress-strain fields of arterial walls regardless of complex geometries and boundary conditions.

show abstract

Application of Machine Learning for Prediction and Process Optimization—Case Study of Blush Defect in Plastic Injection Molding

Cited by 10 publications

References 39 publications

Double Ensemble Technique for Improving the Weight Defect Prediction of Injection Molding in Smart Factories

Double Ensemble Technique for Improving the Weight Defect Prediction of Injection Molding in Smart Factories

Weight Optimization of Plastic Injection Moulded Electrical Wire Casing Thermoplastic using Hybrid RSM-Tunicate Swarm Algorithm

Deep Learning-based Prediction of Stress and Strain Maps in Arterial Walls for Improved Cardiovascular Risk Assessment

Contact Info

Product

Resources

About