Improving CNTs properties using computational intelligence algorithms

Carbon nanotubes (CNTs) have emerged in various applications due to their outstanding characteristics. The most common technique for producing CNTs with high yield and quality is known as chemical vapour deposition (CVD). However, manufacturers rely on conventional experimental studies to produce CNTs, which raise issues such as time, cost, and dealing with toxic materials. Alternatively, modelling and optimisation using metaheuristic algorithms are suggested to address these issues. This paper uses response surface methodology (RSM) for modelling work, while four metaheuristic algorithms are employed for optimisation. The regression and mathematical models, correlations, and significant CNTs process parameters are identified, analysed, and validated using RSM. The optimisation process and result are validated using different performance measure metrics and supported by other researchers. The CNTs yield and quality values improvement percentages in this paper are up to 36.45% compared to the referred original work.