Anomaly Detection in Smart-Manufacturing Era: A Review

Abstract

With the continuous expansion of smart manufacturing environments, where shared data are readily available in real time, the implementation of anomaly detection strategies has become increasingly necessary. However, this task has also become more complex due to the multitude of diverse scenarios and methods that need to be considered.This paper presents a comprehensive state-of-the-art review of anomaly detection methods in manufacturing, supported by experiments conducted on a repository of real manufacturing datasets. We provide a practical classification framework specifically tailored to smart manufacturing environments, which describes recent and successful methods and algorithms that have been applied to real scenarios.Furthermore, we introduce an experimental evaluation by executing a wide range of anomaly detection algorithms based on Neural Metworks, Autoencoders, Support Vector Machines, Isolation Forest and Gradient Boosting among others.

Keywords: Industry 4.0, Manufacturing, Industrial Internet of Things, Anomaly Detection, Smart Manufacturing, Machine learning, Artificial intelligence, Neural Networks, Autoencoders, One-Class Support Vector Machines, Isolation Forest, Gradient Boosting