Wafer manufacturing is a complex and time taking process. The multivariate time-series data collected from many soft sensors in the process are highly noisy and imbalanced. Thus, wafer classification is a challenging task. To overcome this challenge, we propose an effective ensemble approach with transformer and long short term memory (LSTM) based deep learning techniques for wafer classification. Though deep learning is a promising technique to analyze the data and make effective predictions, but not widely integrated in manufacture industries for soft sensing due to insufficient research. Also the research community has not been exposed to accessing the real and large scale wafer data that is highly noisy and imbalanced. Our proposed approach is an ensemble of four models, namely, multilayer LSTM, multilayer perceptron classifier, transformer, and feed forward neural network. We finally ensemble all of these models using ROC-AUC scores by adjusting the weights based on skewness of the models to obtain effective performance. We perform an exhaustive empirical analysis of the proposed approach and obtain a best ROC score of 0.748 that is significantly better compared to the baseline models.

The sensors are used to analyze the quality of wafers in wafer manufacturing industries. The data from sensors is very helpful in framing solutions to predict the pass or fail status of the wafer by classifying high dimensional sensor data using machine learning techniques. In this work, we propose a stacked long short term memory (LSTM) approach i.e., a seq2seq architecture suitable for time-series data. We perform an exhaustive empirical analysis of the proposed model on the Seagate soft sensing dataset. The evaluation metric used is ROC-AUC score. The proposed stacked LSTM approach gave a best ROC-AUC score of 0.7445 on validation data and 0.729 on test data, which is significantly better than the baseline models.