Prognostics and Health Management of Wafer Chemical-Mechanical Polishing System using Autoencoder
This work addresses cost-saving in semiconductor manufacturing by enabling predictive maintenance, but it is incremental as it builds on existing autoencoder methods for a specific dataset.
The paper tackled the problem of predicting wafer surface wear in a semiconductor polishing system using the PHM 2016 dataset, where they proposed an autoencoder-based clustering method that improved regression performance by creating a more compact feature distribution, achieving better results compared to baselines and state-of-the-art approaches.
The Prognostics and Health Management Data Challenge (PHM) 2016 tracks the health state of components of a semiconductor wafer polishing process. The ultimate goal is to develop an ability to predict the measurement on the wafer surface wear through monitoring the components health state. This translates to cost saving in large scale production. The PHM dataset contains many time series measurements not utilized by traditional physics based approach. On the other hand task, applying a data driven approach such as deep learning to the PHM dataset is non-trivial. The main issue with supervised deep learning is that class label is not available to the PHM dataset. Second, the feature space trained by an unsupervised deep learner is not specifically targeted at the predictive ability or regression. In this work, we propose using the autoencoder based clustering whereby the feature space trained is found to be more suitable for performing regression. This is due to having a more compact distribution of samples respective to their nearest cluster means. We justify our claims by comparing the performance of our proposed method on the PHM dataset with several baselines such as the autoencoder as well as state-of-the-art approaches.