Sustainable machining of superalloy in minimum quantity lubrication environment: leveraging GEP-PSO hybrid optimization algorithm

• Published in: International journal of advanced manufacturing technology Vol. 130; no. 9-10; pp. 4575 - 4601
• Main Authors: Sen, Binayak, Debnath, Shantanu, Bhowmik, Abhijit
• Format: Journal Article
• Language: English
• Published: London Springer London 01.02.2024; Springer Nature B.V
• Subjects: Algorithms; CAE) and Design; Carbon; Computer-Aided Engineering (CAD; Cutting speed; Dry machining; Emission analysis; Emissions; Energy consumption; Engineering; Gene expression; Industrial and Production Engineering; Mathematical models; Mechanical Engineering; Media Management; Nickel base alloys; Optimization; Original Article; Particle swarm optimization; Process parameters; Sunflower oil; Superalloys; Surface roughness; Tool wear; Sustainable manufacturing; Superalloy; Gene expression programming (GEP); Silica nanofluid; Particle swarm optimization (PSO)
• ISSN: 0268-3768; 1433-3015
• DOI: 10.1007/s00170-024-12962-9

The present research focuses on establishing a sustainable manufacturing paradigm through the development of a model for optimizing machining parameters under a minimum quantity lubricating environment. The variables considered for investigation encompass cutting speed, feed, and depth of cut. To gauge the sustainability, five key indicators were assessed: total energy consumption, total carbon emission, total machining cost, surface roughness, and tool wear incurred during the machining of Inconel 690. Besides, in order to proficiently oversee machining parameters, the essential integration of modeling and optimization strategies assumes paramount significance. Consequently, a combined approach employing Gene Expression Programming (GEP) in conjunction with Particle Swarm Optimization (PSO) was adopted. GEP was employed to model the observed outcomes in relation to the design variables. Subsequently, the PSO technique was applied to ascertain the optimal configuration of machining parameters. Notably, a confirmation test demonstrated a minimal average discrepancy (less than 3%) between the experimental and GEP-PSO predicted results, showcasing the robustness of the hybrid optimization approach. Finally, machining with silica-doped sunflower oil in optimized machining conditions yields 20% energy reduction, 18.68% lower carbon emissions, an 11.76% cost decrement, a 20.21% reduction in surface roughness, and a 31.71% drop in tool wear, as compared to dry machining, making it an eco-friendly and cost-effective option for superalloy machining.