Equipment deterioration modeling and cause diagnosis in semiconductor manufacturing. Issue 6 (18th February 2021)

• Record Type: Journal Article
• Authors: Rostami, Hamideh; Blue, Jakey; Chen, Argon; Yugma, Claude
• Is Part Of: International journal of intelligent systems. Volume 36:Issue 6(2021)
• Page Start: 2618
• Page End: 2638
• Publication Date: 2021-02-18
• Subjects: equipment deterioration -- fault detection and ‎classification -- smart manufacturing -- wavelet decomposition; Artificial intelligence -- Periodicals; Expert systems (Computer science) -- Periodicals; Intelligence artificielle -- Périodiques; Systèmes experts (Informatique) -- Périodiques; 006.3
• DOI: 10.1002/int.22395
• Languages: English
• ISSNs: 0884-8173

Abstract

Abstract: Condition‐based monitoring (CBM) as a new control scheme suggests characterizing the machine condition and triggering the corresponding control actions. CBM includes prognostic and diagnostic modules. In this study, the framework of equipment deterioration modeling and monitoring for batch processes is proposed with two objectives in the semiconductor industry. The first one is to characterize equipment behavior by exploiting the temporal data of batch processes. The second one is to model the deterioration trend with the most related causes. With the best‐fitted mother wavelet, wavelet packet decomposition transforms the temporal data into macro and micro level domains to identify two types of deterioration. The determinant of the correlation matrix of the decomposed signals is calculated as the equipment condition, and the factors that account for the deterioration are identified through a stepwise searching algorithm. A case study shows that the proposed methodology can identify influencing factors and model deterioration.