Smart Feature Selection for Fault Detection in the MEMS Sensor Production Process Using Machine Learning Methods

DOI

10.2991/aisr.k.220201.005How to use a DOI?

Keywords

MEMS Inertial Sensor; BIG Data Analysis; Feature Engineering; Feature Selection; Machine Learning; Recursive Feature Algorithm; Principal Component Analysis

Abstract

Micro-electromechanical systems (MEMS) manufacturing is a highly complex process consisting of several hundred steps. The real-time data captured during those process control steps results in a huge data base. Analysis of that enormous amount of data in real-time with high sample rate during production for eventual fault detection and prediction is very challenging. The parameters are highly nonlinear and complex in nature. This makes it difficult for the traditional methods to find this hidden pattern. Advances in Machine Learning (ML) paves the path to investigate the vast dataset and find the hidden complex pattern for early failure prediction and root cause analysis. In the paper, we focus on exploring the applicability of ML methods for the prediction of the affected MEMS inertial sensors using different ML methods. We use statistical analysis to investigate the results to learn about the root cause effect. Finally, we investigate the optimal set of sub-parameters needed for the chosen methods to achieve maximum performance without over-fitting and redundancy.

Copyright

© 2022 The Authors. Published by Atlantis Press International B.V.

Open Access

This is an open access article under the CC BY-NC license.

Download article (PDF)

TY  - CONF
AU  - Itilekha Podder
AU  - Tamas Fischl
AU  - Udo Bub
PY  - 2022
DA  - 2022/02/02
TI  - Smart Feature Selection for Fault Detection in the MEMS Sensor Production Process Using Machine Learning Methods
BT  - Proceedings of the 2nd International Conference on Industry 4.0 and Artificial Intelligence (ICIAI 2021)
PB  - Atlantis Press
SP  - 21
EP  - 25
SN  - 1951-6851
UR  - https://doi.org/10.2991/aisr.k.220201.005
DO  - 10.2991/aisr.k.220201.005
ID  - Podder2022
ER  -