A feature extraction method for remnant particles based on non-negative tensor factorization in aerospace electronic equipments

The existence of remnant particles negatively impacts the reliability of aerospace electronic equipments. The universal method to detect remnant particles is particle impact noise detection (PIND). Random vibration can be introduced to the PIND system to improve the detecting performance, and it can also provide acoustic and acceleration signals. In this paper, a new feature extraction method for remnant particles based on Non-negative Tensor Factorization (NTF) is proposed. The proposed method combines different kinds of tested signals, which not only promotes the detection performance but also figures out the material and weight of the remnant particles. We perform a set of experiments. The experimental results show that the proposed method can effectively identify the type of remnant.