A review: use of evolutionary algorithm for optimisation of machining parameters

Optimisation of machining parameters is crucial to ensure higher productivity and optimum outcomes in machining processes. By optimising machining parameters, a particular machining process can produce better machining outcomes within equivalent resources. This paper reviews past studies to achieve the desired outputs; minimum surface roughness (SR), highest material removal rate (MRR), lowest production cost, and the shortest production time of machining processes and various optimisation attempts in terms of varying parameters that affect the outcomes. The review deliberates the optimisation methods employed and analyses the performance discussing the relevant parameters that must have been considered by past researchers. To date, most studies have been focusing on optimising conventional machining processes such as turning, milling, and drilling. Optimisation works have been performed parametrically, experimentally, and numerically, where discrete variations of the parameters are investigated, while others are remained constant. Lately, evolutionary algorithm, statistical approaches such as genetic algorithm (GA), particle swarm optimisation (PSO), and cuckoo search algorithm (CSA) have been utilised in simultaneous optimisation of the parameters of the desired outputs and its great potential in optimising machining processes is recognisable.

Automated summary

Importance: Optimisation of machining parameters is crucial for higher productivity and better outcomes. Research content: Review of past studies focusing on minimum surface roughness, highest material removal rate, lowest production cost, and shortest production time. Optimisation methods: Traditional methods include parametric, experimental, and numerical approaches, while recent studies have utilized evolutionary algorithms, genetic algorithms, and other statistical methods for optimisation.