Qi, X.F. and Ye, Y.F., 2020. Optimization for improved accuracy of material type identification in hydraulic metal structure. In: Guido Aldana, P.A. and Kantamaneni, K. (eds.), Advances in Water Resources, Coastal Management, and Marine Science Technology. Journal of Coastal Research, Special Issue No. 104, pp. 251–254. Coconut Creek (Florida), ISSN 0749-0208.

In Hydraulic and Hydro-Power Engineering, the material of metal structure is very important to the safety of the engineering, so it is necessary to improve the identification ability of metal materials. With the aim of improving the accuracy of eddy current technology for metal species identification, this paper proposes a metal type identification model based on a convolutional neural network (CNN) architecture. After data were collected from iron, 201 stainless steel and 304 stainless steel using an eddy current probe at eight random frequencies, the data were processed to generate images for CNN training and testing. Finally, the experimental results show that the proposed model has a positive effect on the metal identification process.