Skip to main content

A seminar by Dr. Akhil Garg

Title: Improving Environmental Sustainability of Manufacturing Systems by a Robust Optimization Approach
Speaker: Dr. Akhil Garg, NTU, Singapore
Time and Date: 9:30am, Friday, September 4, 2015
Venue: Room 217, ME Building

Abstract: Besides productivity, environmental sustainability is also an important aspect for accessing the performance of any manufacturing industry. Growing demand of customers for better product quality has resulted in an increase in power consumption and thus a lower environmental performance. Optimization of both product quality and power consumption is needed for improving economic and environmental performance of the manufacturing processes. However, for achieving the global multi-objective optimization, the models formulated must be able to generalize the data accurately. In this context, an optimization approach of multi-gene genetic programming (MGGP) can be used to formulate the models for product quality (surface roughness and tool life) and power consumption. MGGP develops the model structure and its coefficients based on the principles of genetic algorithm (GA). However, MGGP have not been able to gain full prominence because it tends to produce over-fitting models.

In this talk, four variants/methods of MGGP are proposed to counter the four shortcomings identified, namely (1) inappropriate procedure of formulation of the MGGP model, (2) inappropriate complexity measure of the MGGP model, (3) difficulty in model selection, and (4) ensuring greater trustworthiness of prediction ability of the model on unseen samples. A robust optimization approach was also developed by applying these four variants of MGGP and the M5' method in parallel. The statistical comparison with other methods such as MGGP, support vector regression and artificial neural network reveals that the generalization ability achieved from the four variants of MGGP and robust optimization approach is better than those of the other methods. The conducted sensitivity and parametric analysis validates the robustness of the models by unveiling the non-linear relationships between the outputs (surface roughness, tool life and power consumption) and input parameters. The study concludes that the proposed model with better generalization ability when optimized gives an accurate optimum input settings that minimises power consumption of manufacturing process and thus improves its environmental sustainability.

Speaker's Bio. in Brief: Dr. Akhil Garg is currently pursuing Post doctorate from Nanyang Technological University (NTU), Singapore. He has completed his PhD from School of Mechanical and Aerospace Engineering, NTU, Singapore in January 2015. Prior to this, he has received his Bachelor's degree (B.Tech) in Mechanical Engineering from National Institute of Technology (NIT), Rourkela, in 2010. His research interests include robust multi-objective optimization of manufacturing processes, Developing variants of genetic programming, Green supply chain management, etc.

News Category