Machine learning-assisted surrogate model for developing MIMO quantitative relationship in plastic injection molding

doi:10.1007/s40436-025-00560-1

Abstract

Abstract: Plastic injection molding (IM) is a typical multiple-input multiple-output (MIMO) complex manufacturing process widely used in modern industrial production. Determining the critical process parameters and establishing the MIMO quantitative relationship between them and the plastic product quality are two fundamental problems in IM process decision analytics. Focusing on high-dimensional process parameters and multidimensional quality indicators in the IM process, this study developed a machine learning-assisted surrogate model that integrated joint mutual information (JMI) and multi-output support vector regression (MSVR). Firstly, a JMI-based sequential search algorithm was developed to measure the association relationship between each process parameter and a multidimensional quality indicator set, and automatically select the critical process parameters of the IM process. It can effectively filter redundant information from raw industrial datasets and provide essential input features for the development of surrogate models. The MSVR model was then developed to capture the MIMO quantitative relationship between the selected critical process parameters and multidimensional quality indicator set. The proposed method can preserve complete independent variable information and avoid losing the relevance of data during training. Finally, the effectiveness of the model was verified using a real-world IM process dataset.

The full text can be downloaded at https://doi.org/10.1007/s40436-025-00560-1

Key words: Plastic injection molding (IM), Multiple-input multiple-output (MIMO) modeling, Process optimization, Machine learning application, Intelligent decision analytics

Yan-Ning Sun, Hai-Bo Qiao, Zeng-Gui Gao, Li-Lan Liu, Wei Qin. Machine learning-assisted surrogate model for developing MIMO quantitative relationship in plastic injection molding[J]. Advances in Manufacturing, 2026, 14(2): 514-528.

TrendMD

References

[1] Sun YN, Chen Y, Wang WY et al (2021) Modelling and prediction of injection molding process using copula entropy and multi-output SVR. In: IEEE 17th international conference on automation science and engineering, IEEE, lyon, France. https://doi.org/10.1109/CASE49439.2021.9551391
[2] Qin Y, Zhao C, Gao F (2018) An intelligent non-optimality self-recovery method based on reinforcement learning with small data in big data era. Chemom Intell Lab Syst 176:89-100
[3] Sáez-Comet C, Fontdecaba E, Cuadrado N et al (2022) Injection molding and characterization of microtextures on polycarbonate using laser textured inserts. Mater Manuf Process 38:618-628
[4] Manjunath M, Pillappan SS, Kurse S (2023) Process parameter analysis of double pass friction stir composite welds. Mater Manuf Process 39(2):174-187
[5] Manoj A, Miriyala SS, Mitra K (2023) Multi-objective optimization through a novel Bayesian approach for industrial manufacturing of polyvinyl acetate. Mater Manuf Process 38(15):1955-1963
[6] Lockner Y, Hopmann C, Zhao W (2022) Transfer learning with artificial neural networks between injection molding processes and different polymer materials. J Manuf Process 73:395-408
[7] Zhao NY, Lian JY, Wang PF et al (2022) Recent progress in minimizing the warpage and shrinkage deformations by the optimization of process parameters in plastic injection molding: a review. Int J Adv Manuf Technol 120:85-101
[8] Selvaraj SK, Raj A, Mahadevan RR et al (2022) A review on machine learning models in injection molding machines. Adv Mater Sci Eng 1:1949061. https://doi.org/10.1155/2022/1949061
[9] Farahani S, Khade V, Basu S et al (2022) A data-driven predictive maintenance framework for injection molding process. J Manuf Process 80:887-897
[10] Gim J, Turng LS (2022) A review of current advancements in high surface quality injection molding: measurement, influencing factors, prediction, and control. Polymer Test 115:107718. https://doi.org/10.1016/j.polymertesting.2022.107718
[11] Gim J, Yang H, Turng LS (2023) Transfer learning of machine learning models for multi-objective process optimization of a transferred mold to ensure efficient and robust injection molding of high surface quality parts. J Manuf Process 87:11-24
[12] Zhou X, Zhang Y, Mao T et al (2017) Monitoring and dynamic control of quality stability for injection molding process. J Mater Process Technol 249:358-366
[13] Jiang Q, Yan X, Yi H et al (2020) Data-driven batch-end quality modeling and monitoring based on optimized sparse partial least squares. IEEE Trans Ind Electron 67:4098-4107
[14] Sun YN, Qin W, Xu HW et al (2022) A multiphase information fusion strategy for data-driven quality prediction of industrial batch processes. Inf Sci 608:81-95
[15] Wang J, Xu C, Zhang J et al (2022) Big data analytics for intelligent manufacturing systems: a review. J Manuf Syst 62:738-752
[16] Lee DH, Yang JK, Lee CH et al (2019) A data-driven approach to selection of critical process steps in the semiconductor manufacturing process considering missing and imbalanced data. J Manuf Syst 52:146-156
[17] Xu H, Zhang J, Lv Y et al (2020) Hybrid feature selection for wafer acceptance test parameters in semiconductor manufacturing. IEEE Access 8:17320-17330
[18] Qin W, Zhuang Z, Guo L et al (2022) A hybrid multi-class imbalanced learning method for predicting the quality level of diesel engines. J Manuf Syst 62:846-856
[19] Rao H, Shi X, Rodrigue AK et al (2019) Feature selection based on artificial bee colony and gradient boosting decision tree. Appl Soft Comput 74:634-642
[20] Mokhtia M, Eftekhari M, Saberi-Movahed F (2020) Feature selection based on regularization of sparsity based regression models by hesitant fuzzy correlation. Appl Soft Comput 91:106255. https://doi.org/10.1016/j.asoc.2020.106255
[21] Wang Y, Cang S, Yu H (2019) Mutual information inspired feature selection using kernel canonical correlation analysis. Expert Syst Appl 4:100014. https://doi.org/10.1016/j.eswax.2019.100014
[22] Qin W, Zha D, Zhang J (2018) An effective approach for causal variables analysis in diesel engine production by using mutual information and network deconvolution. J Intell Manuf 31:1661-1671
[23] Wang J, Zheng P, Zhang J (2020) Big data analytics for cycle time related feature selection in the semiconductor wafer fabrication system. Comput Ind Eng 143:106362. https://doi.org/10.1016/j.cie.2020.106362
[24] Ribeiro B (2005) Support vector machines for quality monitoring in a plastic injection molding process. IEEE Trans Syst Man Cybern Part C Appl Rev 35:401-410
[25] Lu N, Gao F (2005) Stage-based process analysis and quality prediction for batch processes. Ind Eng Chem Res 44:3547-3555
[26] Gunther JC, Conner JS, Seborg DE (2009) Process monitoring and quality variable prediction utilizing PLS in industrial fed-batch cell culture. J Process Control 19:914-921
[27] Zhao C, Wang F, Gao F (2009) Improved calibration investigation using phase-wise local and cumulative quality interpretation and prediction. Chemom Intell Lab Syst 95:107-121
[28] Vuolio T, Visuri VV, Sorsa A et al (2023) Machine learning assisted identification of grey-box hot metal desulfurization model. Mater Manuf Process 38(15):1983-1996
[29] Dhason R, Roy S, Datta S (2023) Surrogate model assisted design optimization of composite bone plates to achieve selective stress shielding. Mater Manuf Process 38(16):2034-2043
[30] Wang G, Ledwoch A, Hasani RM et al (2019) A generative neural network model for the quality prediction of work in progress products. Appl Soft Comput 85:105683. https://doi.org/10.1016/j.asoc.2019.105683
[31] Chiu CC, Yao Y (2013) Multiway elastic net (MEN) for final product quality prediction and quality-related analysis of batch processes. Chemom Intell Lab Syst 125:153-165
[32] Sheng XC, Xiong WL (2019) Soft sensor design based on phase partition ensemble of LSSVR models for nonlinear batch processes. Math Biosci Eng 17:1901-1921
[33] Finkeldey F, Volke J, Zarges JC et al (2020) Learning quality characteristics for plastic injection molding processes using a combination of simulated and measured data. J Manuf Process 60:134-143
[34] Xu HW, Qin W, Sun YN et al (2023) Attention mechanism-based deep learning for heat load prediction in blast furnace ironmaking process. J Intell Manuf 35(3):1207-1220
[35] Zhou P, Zhang R, Xie J et al (2021) Data-driven monitoring and diagnosing of abnormal furnace conditions in blast furnace ironmaking: an integrated PCA-ICA method. IEEE Trans Ind Electron 68:622-631
[36] Xu HW, Qin W, Lv YL et al (2022) Data-driven adaptive virtual metrology for yield prediction in multibatch wafers. IEEE Trans Ind Inform 18:9008-9016
[37] García V, Sánchez JS, Rodríguez-Picón LA et al (2019) Using regression models for predicting the product quality in a tubing extrusion process. J Intell Manuf 30:2535-2544
[38] Sun YN, Qin W, Hu JH et al (2023) A causal model-inspired automatic feature-selection method for developing data-driven soft sensors in complex industrial processes. Engineering 22:82-93
[39] Sun YN, Chen QL, Hu JH et al (2023) An integrated CRN-SVR approach for the quality consistency improvement in a diesel engine assembly process. Int J Comput Integr Manuf 37(9):1126-1141
[40] Duttweiler DL (2000) Proportionate normalized least-mean-squares adaptation in echo cancelers. IEEE Trans Speech Audio Process 8:508-518
[41] Salem OAM, Liu F, Chen YPP et al (2021) Feature selection and threshold method based on fuzzy joint mutual information. Int J Approx Reason 132:107-126
[42] Lall S, Sinha D, Ghosh A et al (2021) Stable feature selection using copula based mutual information. Pattern Recognit 112:107697. https://doi.org/10.1016/j.patcog.2020.107697
[43] Zhou H, Zhang Y, Zhang Y et al (2018) Feature selection based on conditional mutual information: minimum conditional relevance and minimum conditional redundancy. Appl Intell 49:883-896
[44] Shen X, Du SC, Sun YN et al (2023) Advance scheduling for chronic care under online or offline revisit uncertainty. IEEE Trans Autom Sci Eng 21(4):5297-5310
[45] Han M, Ren W, Liu X (2015) Joint mutual information-based input variable selection for multivariate time series modeling. Eng Appl Artif Intell 37:250-257
[46] Bennasar M, Hicks Y, Setchi R (2015) Feature selection using joint mutual information maximization. Expert Syst Appl 42:8520-8532
[47] Drucker H, Burges CJC, Kaufman L et al (1997) Support vector regression machines. Proc NIPS 9:155-161
[48] Pérez-Cruz F, Camps-Valls G, Soria-Olivas E et al (2002) Multi-dimensional function approximation and regression estimation. In: International conference on artificial neural networks, Springer, Berlin. https://doi.org/10.1007/3-540-46084-5_123
[49] Bao Y, Xiong T, Hu Z (2014) Multi-step-ahead time series prediction using multiple-output support vector regression. Neurocomputing 129:482-493
[50] Sánchez-Fernández M, de-Prado-Cumplido M, Arenas-García J et al (2004) SVM multiregression for nonlinear channel estimation in multiple-input multiple-output systems. IEEE Trans Signal Process 52:2298-2307
[51] Vapnik VN (1999) An overview of statistical learning theory. IEEE Trans Neural Netw 10:988-999
[52] Xu S, An X, Qiao X et al (2013) Multi-output least-squares support vector regression machines. Pattern Recognit Lett 34:1078-1084