Process Monitoring

With the development and popularity of sensors installed in manufacturing systems, complex data are collected during manufacturing …

We propose a novel tensor-based process control and monitoring method for semiconductor manufacturing. This method addresses high-dimensional image-based overlay errors using limited control recipes and monitors control residuals to manage high-dimensional disturbances. The effectiveness of the proposed method is validated through extensive simulations and real case studies.

This paper proposes a covariate-regulated sparse subspace learning (CSSL) model to address the challenges of complex, time-varying cross-correlation in multivariate functional data, and demonstrates its application in process monitoring and fault isolation using SCADA data from wind turbines.

This study proposes a knowledge-infused monitoring strategy at the epitaxy stage of solar cell manufacturing processes to improve solar conversion efficiency (SCE) by using a customized nonlinear model and extracting key process features.

This paper proposes an in-process method for detecting process changes affecting product quality in solar cell manufacturing, focusing on the epitaxy stage and using multichannel sensing signals.