Automated Simulation Model Formulation for Semiconductor Manufacturing: A Knowledge-based Approach

Yan Xiaoxuan

Abstract

Having prospered for decades due to the robust global demand of personal computer, server, industrial and automotive markets, the semiconductor industry will continue to drive the economic growth of Singapore in the manufacturing sector. (Leow, 2018). Scheduling efficiency in manufacturing operations plays the pivot role in maintaining a continued edge in the competitive industry. Several main challenges have been identified about the scheduling complexities in semiconductor industry, including manufacturing complexity, uncertainty and variability, long-time horizons and operational idiosyncrasy. There is currently a large body of research targeting at this intricate but vital field. However, simulation-aided approaching in addressing larger scale scheduling problems have not been widely explored. In this paper, a knowledge-based system (KBS) that aids the simulation model formulation process for semiconductor manufacturing is invented to bridge this gap.

The formulation is not a straight forward process considered the complexities and challenges mentioned as above. Besides the technical difficulties, division of expertise poses further difficulties in model formulation, since the simulation model designer may not be entirely familiar with the shop-floor operations, while the shop-floor engineer may not be entirely familiar with simulation model architecture. This knowledge gap gave rise to the feasibility of designing and developing an intelligent KBS system, thus to merge the expertise from separate domains. On the one hand, a genetic construct of the shop-floor operations would be integrated into the knowledge base; on the other hand, simulation modelling, software engineering and project management expertise from industrial and system engineering would strategically consolidate the entire system architecture.

To bridge the gap, this study has achieved a comprehensive knowledge-based system that enables users to establish a comprehensive simulation model formulation, which is specifically applied to the semiconductor shop-floor operations. The model formulation consists of not only the hierarchical structure of the entities enclosed in the fab, but also detailed entity specifications, including static and dynamic information, as well as inter-modular events. By far, no related work has developed the knowledge-based for model formulation in the semiconductor industry, which qualifies this piece of work as being both innovative and highly value-added to the semiconductor industry. Major areas of contribution of this study include: a systematic documentation of the semiconductor manufacturing process under object-oriented paradigm under the knowledge base; an automated modelling process with additional problem structuring inference algorithm; and lastly, the application of AI concepts, specifically the knowledge-based system, in the field of simulation modelling.