Failure Causality Diagnostic in Industrial Systems through Automated Machine Learning

In the context of modern industrial systems, efficient failure management is crucial to maintain operational integrity, minimize downtime, and optimize maintenance. This paper explores the application of Automated Machine Learning (AutoML) to enhance both the diagnostic and the prognostic of failure causality in industrial systems. Different failure causes are detected by failure causality diagnostics, and the upcoming failure could be prevented by failure causality prognostics. In fact, future failures could be avoided by preventing their causalities. Traditional machine learning (ML) approaches require significant manual intervention for model selection, hyperparameter tuning, and feature engineering, which can be time-consuming and cost-consuming. AutoML, on the other hand, automates these processes, enabling faster and more accurate predictions while reducing the need for extensive domain expertise. AutoML could be applied for prognostics, predicting the remaining useful life (RUL) of components and foreseeing future failures. This paper integrates AutoML into real-time failure diagnostics, identifying the root causes of system malfunctions using historical and sensor data. The Steel Plates Faults industrial real-world data set is considered to be surveyed for fault detection using AutoML. The run times and accuracy acquired by AutoML are stated to clarify its superiority.

Keywords: Failure causality, Machine learning, Automated machine learning, Diagnostic, Health monitoring, competing risks, Steel plates faults.