Automated Discovery of Laser Dicing Processes with Bayesian Optimization for Semiconductor Manufacturing

2025-11-28

AI Summary

In semiconductor wafer laser dicing, adapting new materials requires weeks of expert-driven parameter tuning, resulting in low efficiency and difficulty balancing cutting speed, separation quality, and die integrity. Method: This paper proposes the first high-dimensional constrained multi-objective Bayesian optimization framework tailored for the industrial LASER1205 system. It introduces a novel two-fidelity evaluation strategy to minimize destructive testing, integrates multi-objective utility modeling, sequential high-dimensional search, and automated experimental闭环. Contribution/Results: Validated on bare silicon and production wafers, the method autonomously discovers process parameters matching or surpassing expert configurations—significantly improving cutting speed while ensuring die mechanical strength and structural integrity. The entire workflow requires only technician-level operation, enabling fully autonomous generation of production-ready dicing recipes.

Technology Category

• Search and Optimization: Mixed Discrete/Continuous Search
• Constraint Satisfaction and Optimization: Distributed CSP/Optimization
• Machine Learning: Optimization

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems

Abstract

Laser dicing of semiconductor wafers is a critical step in microelectronic manufacturing, where multiple sequential laser passes precisely separate individual dies from the wafer. Adapting this complex sequential process to new wafer materials typically requires weeks of expert effort to balance process speed, separation quality, and material integrity. We present the first automated discovery of production-ready laser dicing processes on an industrial LASER1205 dicing system. We formulate the problem as a high-dimensional, constrained multi-objective Bayesian optimization task, and introduce a sequential two-level fidelity strategy to minimize expensive destructive die-strength evaluations. On bare silicon and product wafers, our method autonomously delivers feasible configurations that match or exceed expert baselines in production speed, die strength, and structural integrity, using only technician-level operation. Post-hoc validation of different weight configurations of the utility functions reveals that multiple feasible solutions with qualitatively different trade-offs can be obtained from the final surrogate model. Expert-refinement of the discovered process can further improve production speed while preserving die strength and structural integrity, surpassing purely manual or automated methods.

Problem

• Automating laser dicing process discovery for semiconductor wafer manufacturing
• Reducing weeks of expert effort to balance speed, quality and material integrity
• Solving high-dimensional constrained optimization for production-ready laser configurations

Innovation

• Automated laser dicing process discovery using Bayesian optimization
• Two-level fidelity strategy minimizing destructive evaluations
• Autonomous configuration matching expert performance in production