The semiconductor value chain is becoming more complex, with increased time for testing and verification, increased timelines for debugging, and the lack of end-to-end traceability. It is thus crucial for semiconductor manufacturers to constantly reduce scrap, analyze yield & equipment performance, and track & analyze wafer lot composition / genealogy. There is a plethora of data from sensors and enterprise business applications such as MES, ERP, etc., which could help predict a potential business impact. A data-driven approach utilizing Machine Learning / Artificial Intelligence (AI) plays a key role in this context.
Jointly developed by Oracle and LTI, these SaaS-based analytical applications collect and analyze the Operational Technology (OT), and information technology (IT) data from enterprise business applications using ML / AI techniques, to detect patterns and correlations, thus helping maximize yields and minimize cycle times. They also facilitate end-to-end tracking and analysis of wafer lot composition & genealogy across the various stages of manufacturing process.
Embedded data management platform that ingests data from machines and equipment, and enterprise applications such as MES, LIMS, ERP, SCM, HCM and CRM
Data contextualization and preparation of OT and IT data
End-to-end model lifecycle management for analyzing KPIs such as yield, quality, cycle time, scrap, etc.
Predictive analytics helping predict a potential yield loss and downstream risks
Genealogy and traceability analysis across the end-to-end manufacturing process
End-to-end visibility of the manufacturing process
Rapid root cause analysis, with instant access to pertinent information about material, machine, product, and process
Actionable insights into operational inefficiencies
Proactive approach to address potential issues
Easy identification of impacted products and customers