@misc{MohamedRuanHeshmatHassanAbdelwahabetal., author = {Mohamed, Abdelrahim and Ruan, Hang and Heshmat Hassan Abdelwahab, Mohamed and Dorneanu, Bogdan and Xiao, Pei and Arellano-Garc{\´i}a, Harvey and Gao, Yang and Tafazolli, Rahim}, title = {An Inter-Disciplinary Modelling Approach in Industrial 5G/6G and Machine Learning Era}, series = {2020 IEEE International Conference on Communications Workshops (ICC Workshops)}, journal = {2020 IEEE International Conference on Communications Workshops (ICC Workshops)}, address = {Dublin, Ireland}, isbn = {978-1-7281-7440-2}, issn = {2474-9133}, doi = {10.1109/ICCWorkshops49005.2020.9145434}, pages = {1 -- 6}, abstract = {Recently, the fifth-generation (5G) cellular system has been standardised. As opposed to legacy cellular systems geared towards broadband services, the 5G system identifies key use cases for ultra-reliable and low latency communications (URLLC) and massive machine-type communications (mMTC). These intrinsic 5G capabilities enable promising sensor-based vertical applications and services such as industrial process automation. The latter includes autonomous fault detection and prediction, optimised operations and proactive control. Such applications enable equipping industrial plants with a sixth sense (6S) for optimised operations and fault avoidance. In this direction, we introduce an inter-disciplinary approach integrating wireless sensor networks with machine learning-enabled industrial plants to build a step towards developing this 6S technology. We develop a modular-based system that can be adapted to the vertical-specific elements. Without loss of generalisation, exemplary use cases are developed and presented including a fault detection/prediction scheme, and a sensor density-based boundary between orthogonal and non-orthogonal transmissions. The proposed schemes and modelling approach are implemented in a real chemical plant for testing purposes, and a high fault detection and prediction accuracy is achieved coupled with optimised sensor density analysis.}, language = {en} }