(663c) Systematic Fault Detection and Classification in Semiconductor Manufacturing Process

Semiconductor manufacturing is composed of various processes such as photo lithography, dry etch, diffusion, ion implantation, thin film deposition, cleaning and chemical mechanical planarization. Among these processes, plasma related processes occupy more than 30% of the whole manufacturing steps. Rapidly progressed and continuous shrinkage of the chip size makes 14nm semiconductor device commercialization, which enables developing microprocessors for smart device as smartphone, medical instrument and IoTs (Internet of Things). However, the physical difficulties expected in materials and patterning technology to cross the 10nm threshold by inherent complexity of plasma, lack of plasma sensors. Cost-effective manufacturing through monitoring and control in plasma etching that many different approaches applied in equipment and process control, new sensor systems, in-situ and integrated metrology and fab automation to improve yield while simultaneously decreasing circuit geometries. Systematic fault detection and classification (FDC) is introduced to an automatic determination of abnormal equipment state, execution of alarms, and assignment of the cause of detected faults. So FDC reduces uncertainty in process operation, noise reduction, metrology accuracy and stability will be increased. In this study, we used MSPC methodology such as principal component analysis (PCA), factor analysis (FA) and mixture model of k-means clustering to process mode classification, detecting the fault, and revealing causal relationship will lead to minimized tool downtime and increased throughput within a system. The application and performance of the proposed method in fault detection and classification will be shown by lab scale CCP (Capacitance Coupled Plasma) chamber operation examples.