University of Twente Student Theses


Machine operation prediction using CSI for Industrial IoT networks

Demosthenous, Avgerinos (2023) Machine operation prediction using CSI for Industrial IoT networks.

[img] PDF
Abstract:Modern manufacturing facilities are increasingly utilizing industrial Internet of Things networks, these networks enable various machines and devices to establish connections, thereby enhancing operational efficiency. One crucial aspect of these types of networks is the ability to predict machine operations allowing them to optimize schedules and improve overall productivity. This research paper will explore a novel idea of utilising Channel State Information in Industrial Internet of Things networks for the purpose of predicting the operational state of machines, specifically distinguishing between the set-up, active, and off states. Additionally, this research aims to explore optimal node positioning for the machine used and assess the impact of the environment on the model’s accuracy. To aid in this research, data is gathered from an industrial setting through uplink channels. The Channel State Information phase is utilized, and a Convolutional Neural Network is employed to analyze this information. The network classifies the collected data and predicts the state of the machine. To evaluate the effectiveness of the proposed approach, the approach is evaluated on average testing accuracy, precision, recall and f1-score. The findings demonstrate that the states can be accurately classified with an accuracy close to 90%. The optimal node position for this experiment is the southeast position relative to the machine. Furthermore, the study confirms that the environment has an influence on the experimental accuracy.
Item Type:Essay (Bachelor)
Faculty:EEMCS: Electrical Engineering, Mathematics and Computer Science
Subject:54 computer science
Programme:Computer Science BSc (56964)
Link to this item:
Export this item as:BibTeX
HTML Citation
Reference Manager


Repository Staff Only: item control page