Feature-Based Multi-Class Classification and Novelty Detection for Fault Diagnosis of Industrial Machinery

Francesca Calabrese,Lorenzo Visentini,Francesco Gabriele Galizia,Alberto Regattieri,Marco Bortolini

doi:10.3390/app11209580

Abstract

Given the strategic role that maintenance assumes in achieving profitability and competitiveness, many industries are dedicating many efforts and resources to improve their maintenance approaches. The concept of the Smart Factory and the possibility of highly connected plants enable the collection of massive data that allow equipment to be monitored continuously and real-time feedback on their health status. The main issue met by industries is the lack of data corresponding to faulty conditions, due to environmental and safety issues that failed machinery might cause, besides the production loss and product quality issues. In this paper, a complete and easy-to-implement procedure for streaming fault diagnosis and novelty detection, using different Machine Learning techniques, is applied to an industrial machinery sub-system. The paper aims to offer useful guidelines to practitioners to choose the best solution for their systems, including a model hyperparameter optimization technique that supports the choice of the best model. Results indicate that the methodology is easy, fast, and accurate. Few training data guarantee a high accuracy and a high generalization ability of the classification models, while the integration of a classifier and an anomaly detector reduces the number of false alarms and the computational time.

Highlights

IntroductionPublisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations
Datasets corresponding to all available machinery conditions are considered in the training phase in order to select the best feature subset, the best classification model, and the best anomaly detection model in the hypothesis to know all the machinery behaviors
As one of the main goals of the present study is to provide an industrial solution that is easy to implement, and as both precision and recall of Decision Tree (DT) are slightly worse than those of the Support Vector Machine (SVM), the DT has been chosen for the online fault diagnosis

Summary

Introduction

Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. Fault Diagnosis (FD) has been extensively studied in recent years, especially datadriven approaches applied to condition monitoring data. In this approach, fault diagnosis consists of collecting sensor data from machinery and finding the relationships between their values and specific machine’s faults. In a recent review on intelligent fault diagnosis [1], the authors analyzed more than four hundred articles. They showed that the research focus has moved from traditional signal processing and Machine Learning (ML)

Objectives

Methods

Results

Conclusion