Special Issue "Failure Detection Algorithms, Methods and Models for Industrial Environments"

Submission Deadline: 30 December 2022
Submit to Special Issue
Guest Editors
Prof. Robertas Damasevicius, Silesian University of Technology, Poland
Prof. Rytis Maskeliunas, Kaunas University of Technology, Lithuania
Dr. Mohammed A. A. Al-qaness, Wuhan University, China

Summary

This special issue focuses on the failure, anomaly detection, or even novelty detection within the industrial manufacturing environments through a myriad of multimodal senseless and sensor-based signal processing methods, models and algorithms. Such technique has recently received further push in installment due to the development of the smart Internet of Things (IoT) solutions, following explosive growth of big data and to rapid improvement of machine learning techniques, especially deep learning, in the last decade. Anomaly detection is recognized as one of the essential techniques in an application for preventive maintenance of the industrial machine as well as for predictive maintenance of useful life (or time to failure) prediction and quality control. This special issue aims to explore standalone approaches (not being an integral part of the manufacturing equipment itself) following the principle of sustained development of Industry 4.0 digitizing the process while keeping integral parts of the old equipment.

 

Potential topics include but are not limited to the following: 


l  Sensor-based and senseless anomaly detection, localization, and tracking

l  Machine learning for failure sensing in real-life industrial applications

l  Sensor enhancement for real-life manufacturing environment applications

l  Manufacturing environment classification through fault detection

l  Time-variant analysis of fault detection in manufacturing environments

l  Emerging fault detection applications in industrial environments

l  Fault processing in smart manufacturing

l  Signal decomposition methods for anomaly and failure detection



Keywords
Anomaly detection; failure detection; fault localization and tracking; condition monitoring; smart manufacturing; predictive maintenance