The IRMA Community
Newsletters
Research IRM
Click a keyword to search titles using our InfoSci-OnDemand powered search:
|
Integrating Generative AI and Digital Twin Technologies for Smart Fabrication and Autonomous Manufacturing Workflows
|
|
Author(s): Tripti choudhary (Hi.Tech Institute of Engineering and Technology, Ghaziabad, India), Kapil Kumar Sharma (Hi.Tech Institute of Engineering and Technology, Ghaziabad, India), Rahul Sharma (Hi.Tech Institute of Engineering and Technology, Ghaziabad, India), Deepti Choudhary (Hi.Tech Institute of Engineering and Technology, Ghaziabad, India), Arpita Singh (Hi.Tech Institute of Engineering and Technology, Ghaziabad, India)and Meenakshi Sharma (Inderprastha Engineering College, Ghaziabad, India)
Copyright: 2026
Pages: 32
Source title:
Next-Generation Electronic Textiles and Conductive Materials for Smart Wearables
Source Author(s)/Editor(s): Pranshu Saxena (Bennett University, India), Mandeep Singh (Bennett University, India), Sanjay Kumar Singh (University School of Automation and Robotics, Guru Gobind Singh Indraprastha University, East Delhi, India)and Mamoon Rashid (Bahrain Polytechnic, Bahrain)
DOI: 10.4018/979-8-3373-4287-0.ch013
Purchase
|
Abstract
The study presents a novel concept for Smart Fabrication and Autonomous Manufacturing Work-flows based on the convergence of Generative AI models and the Digital Twin paradigm. The aim is the prediction and optimization of the most significant machining parameters such as surface roughness, tool life, and energy consumption using advanced AI models and simulation of real-time machining with a responsive digital twin. 50 work-pieces' tool wear, surface finish, and energy consumption data were obtained. Four generative AI models VAE, GAN, Reinforcement Learning (RL), and CAM Code Transformer were trained and evaluated with respect to the RMSE, MAE, R2, and MAPE criteria. The RL model exhibited the highest accuracy and served as the digital twin input engine. The twin simulated machining operations dynamically with rein-forcement learning and allowed for proactive adjustment for performance enhancement. Compara-tive analysis revealed high correlation of predicted and measured values. Optimization using AI and digital twin improved tool life and efficiency
Related Content
|
Isha Gupta, Deepika Rawat, Chaitali Bhowmik, Monika Bansal, Nishi Jain.
© 2026.
30 pages.
|
|
Ranu Burad.
© 2026.
36 pages.
|
|
Pranshu Saxena, Mandeep Singh, Sanjay Kumar Singh, Aatif Jamshed, Pawan Kumar.
© 2026.
18 pages.
|
|
Manu Mehrotra, Manish Baboo Agarwal, Seema Agarwal, Shahjad Ali.
© 2026.
28 pages.
|
|
Mahadev Ajagalla, Tanya Patel, Vaishnavi Bisen.
© 2026.
36 pages.
|
|
Babitha Hemanth, C. Mehnaz Fathima, T. Kripa, A. B. Abhishek.
© 2026.
22 pages.
|
|
Mandeep Singh, Pranshu Saxena, Megha Sharma, Aruna Malik, Samayveer Singh.
© 2026.
24 pages.
|
|
|