Failure diagnosis with deep learning for predictive maintenance of industrial equipment applied : Constantine’s tramway "alstom
No Thumbnail Available
Date
2024
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
Université d'Oum El Bouaghi
Abstract
The transportation industry is undergoing a revolution to meet the ever-expanding hu- man mobility needs. Industry 4.0 technologies, such as artificial intelligence (AI), are being implemented to optimize industrial operations. Predictive maintenance, a pillar of Industry 4.0, uses data analytics to predict equipment failures before they occur. This ap- proach minimizes costly downtime and ensures smooth service by proactively scheduling maintenance. The challenge lies in finding the optimal balance. Performing maintenance too early results in unnecessary replacement of components, while delays risk catastrophic failures. This research addresses this challenge by developing a dedicated predictive main- tenance tool, with a case study on the Constantine tramway.
Our study is divided into two parts. First, we start with an Analysis of the Failure Modes, their Effects and their Criticality (FMECA). This helps us identify critical failure points inside trams and guides us in choosing the most relevant data to monitor.
Next, we present a dashboard of a computer-aided maintenance management system powered by deep learning. This intelligent dashboard analyzes data from selected sensors, extracts and displays their characteristics, predicts the health status of the car (healthy, defective) and even predicts future signals.
Ultimately, this all-in-one platform provides operators and engineers with valuable information for optimal tram maintenance
Description
Keywords
Industry 4.0; Predictive maintenance; Constantine’s Tramway; Fmeca analysis