In this paper, a novel artificial neural network (ANN) based method is developed for the simultaneous estimation of thermal conductivity and thermal diffusivity. The objective is to monitor the thermophysical properties evolution of concentrating solar power (CSP) plant receiver materials during aging cycles to maintain the plant’s cost efficiency. Using standard methods, the simultaneous estimation of both properties is not possible since they are correlated quantities; so, it is necessary to use two devices or to deduce one property from the other, thus propagating the error made. The present method is based on the processing of photothermal experimental data thanks to a feedforward ANN used for classification and two feedforward ANN used for estimation. The impact on performance of the photothermal response length used as model input and the most suitable training examples has been evaluated. In addition, the networks’ topology has been optimized. The results are hopeful considering the use of experimental data (mean relative errors are between 8 and 20%) and the main levers for improvement are identified. The first step deals with the study of a large range of materials (polymers and metallic alloys). In a second phase, this method will be adjusted to CSP receiver material.
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.