A Framework for Root Cause Detection in Batch Processing Manufacturing  

Oleh:

Chien, Chen-Fu ; Chuang, Shih-Chung ; Hsu, Chia-Yu ; Liu, Qiao-Wen

Jenis: Article from Proceeding
Dalam koleksi: The 14th Asia Pacific Industrial Engineering and Management Systems Conference (APIEMS), 3-6 December 2013 Cebu, Philippines, page 1-8.
Topik: Batch processing; Troubleshooting; Random forest; Longitudinal data analysis
Fulltext: 1300.pdf (398.75KB)

Isi artikel

To detect root causes and eliminate yield-loss early is the key factor for enterprise to maintain its competitive advantages and get more benefit. However, because the data structure got more complicated as each passing day, it is almost impossible to artificially diagnose whole production system nowadays and so the automatic or semi-automatic statistical analysis frameworks have to be employed to fast screen whole system and capture the suspected root causes. A number of approaches had been proposed for fault diagnosis for conventional manufacturing problems; nevertheless, they are not absolutely suitable to deal with the data collected from a batch processing manufacturing such as semiconductor manufacturing. Thus, this study aims to propose a batch processing model based framework to effectively, efficiently and robustly detect the root causes for the batch processing system. Finally, the proposed approach has been validated by two simulation cases.

Opini Anda

Klik untuk menuliskan opini Anda tentang koleksi ini!

Kembali