Analysis of Machine Learning based Condition Monitoring Schemes Applied to Complex Electromechanical Systems

Arellano-Espitia, Francisco; Gonzalez-Abreu, Artvin-Darien; Delgado-Prieto, Miguel; Saucedo-Dorantes, Juan José; Osornio-Ríos, Roque Alfredo

doi:10.1109/etfa46521.2020.9212026

Cited by 1 publication

(1 citation statement)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Regarding the third point, in recent years the fast-growth of algorithms based on Artificial Intelligence (AI) have made it possible to generate numerous data-based models of advanced detection, particularly in the field of electromechanical systems maintenance. These methods, mainly based on neural networks (NN) and more specifically deep-learning (DL), have been attracting more and more attention due to their unique advantages, such as pattern extraction and characterization of complex systems [3][4]. However, due to current difficulties in the adoption of real convergence between IT and OT, there exist a classical separation between the algorithmic and the machinery behavior from a logical point of view.…”

Section: Introductionmentioning

confidence: 99%

Diagnosis Electromechanical System by Means CNN and SAE: An Interpretable-Learning Study

Arellano-Espitia

Delgado-Prieto

Martinez-Viol

et al. 2022

2022 IEEE 5th International Conference on Industrial Cyber-Physical Systems (ICPS)

Self Cite

View full text Add to dashboard Cite

Cyber-physical systems are the response to the adaptability, scalability and accurate demands of the new era of manufacturing called Industry 4.0. They will become the core technology of control and monitoring in smart manufacturing processes. In this regard, the complexity of industrial systems implies a challenge for the implementation of monitoring and diagnosis schemes. Moreover, the challenges that is presented in technological aspects regarding connectivity, data management and computing are being resolved through different IT-OT (information technology and operational technology) convergence proposals. These solutions are making it possible to have large computing capacities and low response latency. However, regarding the logical part of information processing and analysis, this still requires additional studies to identify the options with a better complexity-performance trade-off. The emergence of techniques based on artificial intelligence, especially those based on deep-learning, has provided monitoring schemes with the capacity for characterization and recognition in front of complex electromechanical systems. However, most deep learning-based schemes suffer from critical lack of interpretability lying to low generalization capabilities and overfitted responses. This paper proposes a study of two of the main deep learning-based techniques applied to fault diagnosis in electromechanical systems. An analysis of the interpretability of the learning processes is carried out, and the approaches are evaluated under common performance metrics.

show abstract

Section: Introductionmentioning

confidence: 99%