Modular implementation of artificial neural network in predicting in-flight particle characteristics of an atmospheric plasma spray process

摘要: This paper presents a modular implementation of an artificial neural network to model the atmospheric plasma spray process in predicting in-flight particle characteristics from input processing parameters. The influence structure and properties thermal coating and, thus, are considered important parameters comprehend, simulate predict manufacturing process. allows simplification optimized with enhanced ability generalise network. As well, underlying relationship between each output respect is explored. Smaller networks constructed that achieves better, or some cases, similar results. training found be more robust stable along fewer fluctuations values also respond variations number hidden layer neurons definite trend. predictable trend enhances reliability application modelling overcomes variability non-linearity associated