https://orcid.org/0000-0002-0997-1650
![Sample our Physical Sciences journals, sign in here to start your FREE access for 14 days]({"type":"image" , "src" : "/sda/110819/TOC-Subject-Sample-2021-Physical-Sciences.jpg"})
ABSTRACT
The world’s population growth has led to increased demand for products, which requires enormous energy consumption. Therefore, energy savings are becoming a primary objective for industrial sectors. This study uses artificial intelligence, specifically response surface methodology (RSM), artificial neural networks (ANN) and genetic algorithms (GA), to optimise machining parameters in the mechanical manufacturing sector. The findings demonstrate that the use of artificial intelligence can reduce the amount of energy used in machining operations, increasing both productivity and cost. According to the analysis of variance, the depth of cut ap and the feed rate Vf are the most influential factors on total specific energy consumed (TSEC). Meanwhile, spindle speed is the most influential factor for energy efficiency (EE). EE increases when there is an increase in the rate of material removal as opposed to decreasing total specific energy. The study also shows that the multi-objective optimisation with the genetic algorithm can reduce TSEC by 44.13% and increase EE by 14.63%. The optimal cutting parameters given by the genetic algorithm are the spindle speed, feed, depth of cut and number of teeth.
Nomenclature
| N | = | Spindle speed (rev/min) (rpm) |
| Vc | = | Cutting speed (m/min) |
| Vf | = | Feed rate (mm/min) |
| ap | = | Depth of cut (mm) |
| ae | = | Cutting width (mm) |
| Z | = | Number of teeth |
| N | = | Spindle rotational speed (rpm) |
| Fc | = | Cutting force (N) |
| TEC | = | Total Energy Consumed (J) |
| CEC | = | Cutting Energy Consumed (J) |
| TPC | = | Total Power Consumed (W) |
| TSEC | = | Total Specific Energy Consumed (J/mm3) |
| SCE | = | Specific Cutting Energy (J/mm3) |
| CPC | = | Cutting Power Consumed (W) |
| NLP | = | No-Load Power (W) |
| MRR | = | Material Removal Rate (mm3/s) |
| EE | = | Energetic Efficiency (%) |
| RMS | = | Response Surface Methodology |
| ANN | = | Artificial Neural Networks |
| GA | = | Genetic Algorithm |
| LM | = | Levenberg-Marquardt algorithm |
| R | = | Correlation coefficient |
| SEcc | = | Specific Energy cutting consumed (J/mm3) |
| NSGA-II | = | Non dominated Sorting Genetic Algorithm |
Disclosure statement
No potential conflict of interest was reported by the author(s).
Data availability statement
All data generated or analysed during this study are available in this article.