Forecasting of Product Quality Through Anomaly Detection

Abstract

Forecasting of product quality by means of anomaly detection is crucial in real-world applications such as manufacturing systems. In manufacturing systems, the quality is assured through tests performed on sample units randomly chosen from a batch of manufactured units. One of the major issues is to detect defective units among the sample test units as early as possible in terms of test time and of course as accurate as possible. Traditional way of detecting defective units is to make use of human experts during test. However, human intervention is prone to errors and it is time consuming. On the other hand, automated systems are efficient alternatives and of assistance to human experts. There are on-line and off-line approaches for automated systems. Our ultimate aim is to design a system that automates the detection of defective units among the sampled freezer units manufactured in high volumes in a factory of one of the leading home appliances manufacturers. We start by analyzing the data of the test units sampled from the batches of freezer units. For analysis, we first embedded data in two-dimensional space to observe if there are any structures exist in the data. Clustering was then applied to see if the data can be grouped into two classes without their labels. As off-line approaches, state-of-the-art classifier methods including one-class-classifier are employed. Finally, a deep learning method for time-series analysis combined with a classifier is applied as an on-line method.