A general probability-forecasting framework for final product quality of complex processes

There are several complex processes in the whole production cycle of some industrial products. Usually these complex processes require complicated production technics since the products cannot be processed in a batch manner. In this sense, it is difficult to control the ratio of each final quality level. To eliminate this effect in predicting the final quality level of products with several complex processes, a general probability-forecasting framework is proposed based on the support vector machine (SVM) model. In our framework, we first develop a model for SVM classification based on a two-phase heuristic method improved for SVM parameter optimization, and then an online probabilistic prediction model of each final quality level and a cost analysis scheme are presented respectively. Based on the proposed framework, our simulation experiment demonstrates the effectiveness of the improved SVM model in predicting the probabilities of final quality level of multi-processes and reducing the production cost of the whole process.

[1]  Robert Tibshirani,et al.  Classification by Pairwise Coupling , 1997, NIPS.

[2]  Sheng-De Wang,et al.  Choosing the kernel parameters for support vector machines by the inter-cluster distance in the feature space , 2009, Pattern Recognit..

[3]  Don R. Hush,et al.  Polynomial-Time Decomposition Algorithms for Support Vector Machines , 2003, Machine Learning.

[4]  Chih-Jen Lin,et al.  A Practical Guide to Support Vector Classication , 2008 .

[5]  Chunhui Zhao,et al.  Improved Batch Process Monitoring and Quality Prediction Based on Multiphase Statistical Analysis , 2008 .

[6]  Vladimir Vapnik,et al.  Statistical learning theory , 1998 .

[7]  Yuan Yao,et al.  Multiway elastic net (MEN) for final product quality prediction and quality-related analysis of batch processes , 2013 .

[8]  Chih-Jen Lin,et al.  Probability Estimates for Multi-class Classification by Pairwise Coupling , 2003, J. Mach. Learn. Res..

[9]  Durmus Karayel,et al.  Prediction and control of surface roughness in CNC lathe using artificial neural network , 2009 .

[10]  J. Platt.  Sequential Minimal Optimization : A Fast Algorithm for Training Support Vector Machines , 1998 .

[11]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.

[12]  Habibollah Haron,et al.  Prediction of surface roughness in the end milling machining using Artificial Neural Network , 2010, Expert Syst. Appl..

[13]  Óscar Martín,et al.  Quality prediction of resistance spot welding joints of 304 austenitic stainless steel , 2009 .

[14]  Wen-Chin Chen,et al.  A neural network-based approach for dynamic quality prediction in a plastic injection molding process , 2008, Expert Syst. Appl..

[15]  Hsuan-Tien Lin,et al.  A note on Platt’s probabilistic outputs for support vector machines , 2007, Machine Learning.

[16]  John Platt,et al.  Probabilistic Outputs for Support vector Machines and Comparisons to Regularized Likelihood Methods , 1999 .

[17]  Chi Zhang,et al.  A general framework for monitoring complex processes with both in-control and out-of-control information , 2015, Comput. Ind. Eng..

[18]  Furong Gao,et al.  Review of Recent Research on Data-Based Process Monitoring , 2013 .

[19]  Ying-wei Zhang,et al.  Complex process quality prediction using modified kernel partial least squares , 2010 .

[20]  Chih-Jen Lin,et al.  LIBSVM: A library for support vector machines , 2011, TIST.