Image-Based Deep Learning for Manufacturing Fault Condition Detection

In this presentation, we explore applying deep learning to analyzing manufacturing parameter data to detect fault conditions. The manufacturing parameter data contains multivariate time series sensor signals from a fabrication line. Due to practical manufacturing limitations, datasets are often incomplete, imbalanced and/or not well-formed for deep learning models. To overcome these challenges, we apply new data augmentation methods to train a deep CNN for fault condition classification using deep generative models. We also propose an efficient method to convert multiple time series sensor inputs into a two-dimensional image representation to enable the use of image-based CNNs. Our experiment results show the fault classification accuracy improvement obtained by applying these techniques.