Session: 03-16-01: Securing Advanced Manufacturing: Cybersecurity and Edge Computing for Industrial IoT

Paper Number: 165593

Cloud-Based Collaborative CNC Manufacturing With Integrated Tool Wear Monitoring for Industry 4.0 

This research presents an innovative manufacturing framework that leverages cloud technologies to enable collaborative production in CNC networks. The framework is designed to address the evolving demands of modern manufacturing by fostering innovation, agility, and efficiency in CNC operations. By integrating intelligent systems such as Artificial Intelligence (AI) and Internet of Things (IoT), the framework aims to enhance decision-making, optimize processes, and promote a connected, data-driven production environment leading to a true I4.0 system.

An up to date review of recently published work on Industry 4.0 readiness in manufacturing systems has been carried out, followed by an assessment of challenges and suitability for implementation, with a particular focus on the Kingdom of Saudi Arabia (KSA). A demo Industry 4.0 sample factory is proposed as an experimental setup to study and discuss current practices and challenges in the industry.

At the core of this framework is a network of cooperating computational entities in close contact with the physical world, utilizing Internet-based data-accessing and data-processing services. This cyber-physical production system (CPPS) relies on the latest developments in computer science, information and communication technologies, and manufacturing science to realize the Industry 4.0 concept.

The research also addresses the critical issue of tool wear in CNC machining processes. Within the monitoring of the machine health, an advanced Tool Wear Condition Monitoring (TWCM) system is proposed, integrating machine learning with variational mode decomposition to dynamically predict tool wear progression during the turning process. The study involves machining AISI 1045 unalloyed carbon steel using a TNMG carbide insert, with vibration signals analyzed to extract correlations between surface roughness and tool wear behavior.

The TWCM system employs Auto-ML to identify and select variational mode decomposition modes strongly correlated with flank wear (VB). Power spectral density (PSD) analysis of the selected modes provides insights into wear-induced frequency variations. Machine learning models, including an ensemble approach, utilize these features to achieve high prediction accuracy, with the ensemble model attaining an R² of 0.98.

This integrated approach demonstrates the potential for real-time tool wear monitoring in CNC manufacturing, contributing to improved surface quality, reduced production time, and lower costs. The framework's emphasis on scalability allows for seamless integration and expansion of manufacturing capabilities, while its focus on sustainability promotes eco-friendly practices and resource efficiency.

By combining cloud-based collaborative CNC manufacturing with advanced tool wear monitoring, this research provides a comprehensive solution for the challenges faced in modern manufacturing. The proposed framework and experimental setup will serve as a foundation for future research in the field, offering valuable insights into the implementation of Industry 4.0 concepts in CNC manufacturing environments.

 

Presenting Author: Samir Mekid King Fahd University of Petroleum and Minerals

Presenting Author Biography: prof

Authors:

Imran - King Fahd University of Petroleum and Minerals
Mourad Nouioua kfupm
Samir Mekid King Fahd University of Petroleum and Minerals