Deep-Learning-Based Methodology for Fault Diagnosis in Electromechanical Systems

TLDR

Fault diagnosis in manufacturing systems is a critical challenge in smart manufacturing, where complex electromechanical systems and multi‑fault scenarios demand advanced monitoring; deep‑learning‑based data fusion offers promise but is limited by model structure and hyper‑parameter selection. This study introduces a novel deep‑learning methodology for fault diagnosis in electromechanical systems. The methodology employs unsupervised stacked auto‑encoders for feature extraction and supervised discriminant analysis for fault classification. The proposed approach is easy to apply and highly adaptable to available data.

Abstract

Fault diagnosis in manufacturing systems represents one of the most critical challenges dealing with condition-based monitoring in the recent era of smart manufacturing. In the current Industry 4.0 framework, maintenance strategies based on traditional data-driven fault diagnosis schemes require enhanced capabilities to be applied over modern production systems. In fact, the integration of multiple mechanical components, the consideration of multiple operating conditions, and the appearance of combined fault patterns due to eventual multi-fault scenarios lead to complex electromechanical systems requiring advanced monitoring strategies. In this regard, data fusion schemes supported with advanced deep learning technology represent a promising approach towards a big data paradigm using cloud-based software services. However, the deep learning models' structure and hyper-parameters selection represent the main limitation when applied. Thus, in this paper, a novel deep-learning-based methodology for fault diagnosis in electromechanical systems is presented. The main benefits of the proposed methodology are the easiness of application and high adaptability to available data. The methodology is supported by an unsupervised stacked auto-encoders and a supervised discriminant analysis.