Machine Learning for Predictive Maintenance: A Multiple Classifier Approach

By Gian Antonio Susto, Andrea Schirru, Simone Pampuri, Seán F. McLoone, Alessandro Beghi. IEEE Transactions on Industrial Informatics, 2015

716 citations recorded by the source corpus.

Subfields: Control and Systems Engineering, Mechanical Engineering

View Paper: https://www.semanticscholar.org/paper/19a28325b68346f7715e17a97eb71db1b2b3c1af

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Control and Systems Engineering

In Mechanical Engineering

Citations in the corpus

Transparency and trust in artificial intelligence systems (2020, background): “…intelligence (AI) and machine learning (ML) have become increasingly important for aiding human decision making in various fields, including medical diagnosis, political predictions, policing, predictive maintenance, and many more (Esteva et al., 2017; Nickerson & Rogers, 2014; Susto et al., 2015).”
Data-Driven Methods for Predictive Maintenance of Industrial Equipment: A Survey (2019, methodology): “A multiple classifier (MC) methodology based on an SVM was proposed in [23] for the PdM of semiconductor manufacturing (e.”
Automated Machine Learning in Practice: State of the Art and Recent Results (2019, background): “Industrial applications for example, such as predictive maintenance [5], [6] and defect detection [7], enable companies to be more proactive and improve efficiency.”
Machine learning in manufacturing: advantages, challenges, and applications (2016, methodology): “ML has been successfully utilized in various process optimization, monitoring and control applications in manufacturing, and predictive maintenance in different industries (Alpaydin, 2010; Gardner & Bicker, 2000; Kwak & Kim, 2012; Pham & Afify, 2005; Susto, Schirru, Pampuri, McLoone, & Beghi, 2015).”
Tackling Faults in the Industry 4.0 Era—A Survey of Machine-Learning Solutions and Key Aspects (2019, methodology): “, 2015 [62] Imbalanced data sets of integral type faults MC supervised method”
Time-to-Event Prediction with Neural Networks and Cox Regression (2019, background): “…time-to-event predictions can be found in a variety of settings such as survival prediction of cancer patients (e.g. Vigan et al., 2000), customer churn (e.g. den Poel and Larivire, 2004), credit scoring (e.g. Dirick et al., 2017), and failure times of mechanical systems (e.g. Susto et al., 2015).”
A comprehensive review of big data analytics throughout product lifecycle to support sustainable smart manufacturing: A framework, challenges and future research directions (2019, methodology): “Keywords: big data analytics; smart manufacturing; servitization; sustainable production; conceptual framework; product lifecycle Abbreviations ABC Artificial bee colony IoT Internet of things ABS Agent-based system IT Information technology ACO Ant colony optimization JIT Just-in-time AD Anomaly de”
TensorFlow Lite Micro: Embedded Machine Learning on TinyML Systems (2020, background): “PPG optical sensors, and other devices enable consumer and industrial applications, including predictive maintenance (Goebel et al., 2020; Susto et al., 2014), acoustic-anomaly detection (Koizumi et al.”
Compressing RNNs for IoT devices by 15-38x using Kronecker Products (2019, background): “, 2010; Ordonez & Roggen, 2016), and predictive maintenance (Ahmad et al., 2017; Susto et al., 2015).”
Giving Sensors a Voice: Multimodal JEPA for Semantic Time-Series Embeddings (2026, unknown): “Time series models play a pivotal role in critical real-world applications such as forecasting, classification, and anomaly detection across domains including manufacturing, energy, healthcare, and finance (Hannun et al., 2019; Susto et al., 2014; Ding et al., 2015).”
Time to Embed: Unlocking Foundation Models for Time Series with Channel Descriptions (2025, unknown): “Time series models play a pivotal role in critical real-world applications such as forecasting, classification, and anomaly detection across domains including manufacturing, energy, healthcare, and finance (Hannun et al., 2019; Susto et al., 2014; Ding et al., 2015).”