Technical Name Advanced Artificial-intelligence based forecasting technique to empower semiconductor supply chain and manufacturing network resilience
Project Operator National Tsing Hua University
Project Host 簡禎富
Summary
This developed technology integrated big data analytics, meta model, and XAI algorithm to develop more accurate demand and cycle time prediction for supply chain and production planner to reduce production costs in semiconductor industry and enhance network resilience via analyzing big data of supply chain, capacity portfolio and production data enabling automated feature engineering.
Scientific Breakthrough
This technology expands the applicability of previous technology by forecasting supply chain demand and production cycle time simultaneously. The integration of classifiers and XAI modules provides a comprehensive prediction including the demand quantity and manufacturing cycle time under future new process platforms and upcoming product portfolio.
Industrial Applicability
This technology can be effectively applied in the semiconductor manufacturing industry, covering supply chain management to advanced process control, addressing challenges such as supply chain complexity and production management inaccuracies. Through a hybrid strategy combining automated feature engineering, classifiers, and XAI, it accurately predicts demand and production cycle time, enhancing supply chain resilience, reducing production costs and increasing industry competitiveness.
Keyword Semiconductor industry Intelligent manufacturing Artificial Intelligence Explainable AI Meta model Ensemble learning Demand forecasting Advanced control system Cycle time prediction Supply chain resilience
  • Contact
  • Ying-Yu Lu