Project Scope
Learn the operating principles, alarm structures, and performance indicators of selected burn-in equipment.
Collect, clean, structure, and validate equipment alarm-log data.
Develop trigger logic and automated notifications for selected JTS equipment, burn-in board, and socket alarms.
Apply statistical and predictive methods to identify factors affecting availability, downtime, and Parts per Jam.
Evaluate the feasibility of socket-masking automation and relevant Agentic AI solutions.
Learning Opportunities
Gain practical knowledge of semiconductor test processes and burn-in equipment.
Develop experience with Python, Structured Query Language, Microsoft Power BI, and Microsoft Power Automate.
Learn predictive analytics, data visualization, trigger validation, and performance monitoring.
Explore Generative AI, Microsoft Copilot, and Agentic AI for engineering automation.
Deliverables
Validated alarm database with defined trigger logic.
An automated notification and visualization workflow.
A predictive methodology for identifying equipment downtime patterns.
A socket-masking automation feasibility study.
An effectiveness analysis covering machine downtime and Parts per Jam performance.
Impact of the Project
Improve visibility of equipment alarm and downtime patterns.
Enable earlier identification of equipment conditions affecting availability.
Identify opportunities to improve Parts per Jam and reduce downtime.
Demonstrate AI-Enabled Test Engineering workflows.
Skillsets Required
Familiarity with Python, Structured Query Language, Microsoft Power BI, or Microsoft Power Automate.
Basic knowledge of statistics, predictive analytics, and data visualization.
Familiarity with Generative AI, Microsoft Copilot, Agentic AI, or AI-Enabled workflows.
Strong analytical, systems-thinking, problem-solving, and communication skills.