Logo image
Integration of deep reinforcement learning with simulation optimization applied to semiconductor backend assembly scheduling problem
期刊文章

Integration of deep reinforcement learning with simulation optimization applied to semiconductor backend assembly scheduling problem

C.-C. Chiu, C.-M. Lai, Y.-S. Liao 和 W.-C. Yeh
Swarm and Evolutionary Computation, 卷.100
2026
Web of Science ID: WOS:001648461900002

摘要

Deep reinforcement learning Dynamic dispatching Semiconductor backend assembly scheduling problem Simplified swarm optimization and optimal replication allocation strategy Simulation optimization Decision making Electric load dispatching Heuristic algorithms Job shop scheduling Machine learning Semiconductor device manufacture Swarm intelligence Allocation strategy Assembly-scheduling problems Back-end assembly Dynamic dispatching Reinforcement learnings Semiconductor backend Semiconductor backend assembly scheduling problem Simplified swarm optimization and optimal replication allocation strategy Simulation optimization Swarm optimization Computational efficiency
This study investigates the semiconductor backend assembly scheduling problem, a critical challenge in make-to-order manufacturing where minimizing flow time is essential. The problem features identical and unrelated parallel machines, setup times, and entity transformations (e.g., wafers diced into dies, dies bonded to substrates, substrates packed into magazines). Additional complexities—including batch formation, job splitting, and machine eligibility—further increased the difficulty, rendering it an NP-hard extension of the hybrid flow shop problem. Traditional heuristic algorithms and simulation based optimization often face scalability and efficiency limitations in large-scale applications. To address these challenges, we propose an integrated framework that combines deep reinforcement learning with simulation-based optimization, supported by simplified swarm optimization and an optimal replication allocation strategy. Simplified swarm optimization explores the solution space, while optimal replication allocation directs simulation resources towards promising solutions, enhancing efficiency. Deep reinforcement learning strengthens the framework by dynamically adjusting dispatching rules, accelerating decision-making, and avoiding local optima. Experiments on 18 datasets from a Taiwanese semiconductor factory demonstrated that the proposed approach substantially reduces average flow time while preserving computational efficiency, offering an effective solution to this complex scheduling problem. © 2025 Elsevier B.V.

檔案與連結 (1)

url
https://www.scopus.com/inward/record.uri?eid=2-s2.0-105025164190&doi=10.1016%2fj.swevo.2025.102252&partnerID=40&md5=9e8ced76a169e7166d45c009044fd434檢視

相關連結

指標

1 檢視次數

詳細資料

Logo image