Digital Twin-Based Optimization of Operational Parameters for Cluster Tools in Semiconductor Manufacturing

Abstract

Manufacturing and supply chain management are becoming increasingly important in the semiconductor industry. Cluster tools are essential equipment in semiconductor production and are used for microscopic operations, such as the surface treatment of wafers. In particular, the operational parameters of cluster tools directly affect productivity, and various efforts are underway to optimize them at manufacturing sites. However, there are still many challenges in this process. In this study, we propose a framework for optimizing the operational parameters of cluster tools in semiconductor manufacturing using digital twin technology to address these challenges. The framework predicts productivity through manufacturing simulations based on operational parameters in a digital twin environment, analyzes the factors affecting productivity, and determines the optimal operational parameters. The study demonstrates that the cycle time of cluster tools in wafer fabrication can be significantly reduced through the proposed approach based on digital twins. The application of this framework is expected to contribute to cost reduction, productivity improvement, and enhancement of industrial competitiveness at semiconductor manufacturing sites.

Keywords

• Cluster tool
• digital twin
• finite state machine
• hill climbing algorithm
• semiconductor manufacturing