Heterogranular multivariate analytics for detecting and controlling the root causes of the mismatching machines in semiconductor manufacturing

In all manufacturing industries, parallel machines/chambers at a single production area are expected to perform identically and, most importantly, to yield similar product quality. However, this is usually not the case in real practice, especially when it is a highly complex industry as is the case for semiconductor fabrication. In this paper, a systematic approach is proposed to detect the root causes of machine/chamber mismatching in real time by exploiting all the available data, such as product measurements, machine sensor readings and maintenance data.