Abstract—Semiconductor manufacturing is one of the most technologically and highly complicated manufacturing processes. Traditional machine learning algorithms such as uni-variate and multivariate analyses have long been deployed as a tool for creating predictive model to detect faults. In the past decade major collaborative research projects have been undertaken between fab industries and academia in the areas of predictive modeling. In this paper we review some of these research areas and thus propose machine learning techniques to automatically generate an accurate predictive model to predict equipment faults during the wafer fabrication process of the semiconductor industries. This research paper aims at constructing a decision model to help detecting as quickly as possible any equipment faults in order to maintain high process yields in manufacturing. In this research, we use WEKA tool and R languages for implementing our proposed method and other five machine learning discovery techniques.
Index Terms—redictive model, semiconductor manufacturing process, machine learning, data classification, feature selection, R language, and python language.
Sathyan Munirathinam is with Micron Technology and PhD researcher at Bharathiar University, India (e-mail: Sathyan.Munirathinam@gmail.com).
Balakrishnan Ramadoss is with National Institute of Technology, Trichy, India (e-mail: brama@nitt.edu).
[PDF]
Cite: Sathyan Munirathinam and Balakrishnan Ramadoss, "Predictive Models for Equipment Fault Detection in the Semiconductor Manufacturing Process," International Journal of Engineering and Technology vol. 8, no. 4, pp. 273-285, 2016.
