We deposited undoped ZnO films on the glass substrate at a low temperature (<70 ∘ C) using cathode arc plasma deposition (CAPD) and the grey-relational Taguchi method was used to determine the processing parameters of ZnO thin films. The Taguchi method with an L9 orthogonal array, signal-to-noise ( / ) ratio, and analysis of variance (ANOVA) is employed to investigate the performances in the deposition operations. The effect and optimization of deposition parameters, comprising the Ar : O 2 gas flow ratio of 1 : 6, 1 : 8, and 1 : 10, the arc current of 50 A, 60 A, and 70 A, and the deposition time of 5 min, 10 min, and 15 min, on the electrical resistivity and optical transmittance of the ZnO films are studied. The results indicate that, by using the grey-relational Taguchi method, the optical transmittance of ZnO thin films increases from 88.17% to 88.82% and the electrical resistivity decreases from 5.12 × 10 −3 Ω-cm to 4.38 × 10 −3 Ω-cm, respectively.
An experimental design utilizing artificial neural networks (ANNs), the Taguchi method, and the genetic algorithm (GA) is proposed to obtain optimal processing parameters for cathode arc plasma deposition of ZnO thin films on a glass substrate. The Taguchi method's orthogonal array is used to minimize the number of required experiments and to gather the experimental data. An ANN is then used to construct a system model based on the experimental data. Finally, the GA is used to determine the optimal process parameters. The average resistivity obtained from the optimal processing parameters is 3.19 × 10 −3 -cm and the average transmittance obtained is 86.04%, both of which improve on results obtained using the Taguchi method alone (3.69 × 10 −3 -cm and 85.41%). This indicates that the proposed design is a viable approach for determining the optimal process parameters.Note to Practitioners-This paper seeks to identify the optimal process parameters for the deposition of ZnO thin films on a glass substrate using cathode arc plasma deposition (CAPD). Current approaches for determining better process parameters for thin film deposition include trial-and-error or experimental design methods. However, these approaches are time-consuming, costly, and do not guarantee improved results. This paper combines the modeling and optimization methods to address this issue by using the artificial neural network, Taguchi method, and genetic algorithm to identify the optimal process parameters for a ZnO thin film using CAPD. Experimental results show considerable promise and the authors welcome feedback and questions.Index Terms-Artificial neural network (ANN), cathode arc plasma deposition (CAPD), genetic algorithm (GA), Taguchi method, ZnO thin film.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.