Adaptive design of experiments guided by an active learning approach

Abstract

Fault detection in a manufacturing process is often challenging due to a lack of system background information. Design of Experiments (DoE) are used for effective planning of experiments to get knowledge of the unknown system. Those DoE lead to many experiments to depict the complex relationships of the reasons and effects. The challenge is the optimization to reduce the number of experiments while maintaining accuracy. This paper presents a novel approach for a guided DoE based on a Deep Active Learning (DeepAL) strategy to drastically downsize the number of experiments in order to avoid high execution costs. The DeepAL uses a new approach in uncertainty rating of the experiment space by using diversity rating to improve a faster generalization of the system approximation. Empirical evaluations show on average 60% better performance of the novel approach in combination with Bayesian neural networks compared to other methods.