Internet Archive Scholar

Train a correct BP neural network as the input layer and as the training sample

2022 Academic Journal of Computing & Information Science  

Preserved Fulltext

fulltext thumbnail
Web Archive Capture PDF (331.2 kB)
https://web.archive.org/web/20220919030644/https://francis-press.com/uploads/papers/DomfiYhSgzaFsJDqJqc9j1wA8DGN3obptcElBjSl.pdf

A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL. The file type is application/pdf.

For this problem, we train a correct BP neural network with the number of layers, material and thickness of each layer, emission spectrum pollution index as the input layer, as the training sample, and comprehensive thermal efficiency as the output layer, to obtain the network mapping relationship between comprehensive thermal efficiency and design parameters of multilayer structure. Then, through particle swarm optimization algorithm and genetic algorithm, six layers are obtained, which adopt
more » ... ilica silicon silica germanium silicon germanium structure, with refractive index of 21.7832 and thickness of 130.819. Currently, the corresponding thermoelectric conversion efficiency is the highest.
doi:10.25236/ajcis.2022.050612 fatcat:pfdz2ynjurapxp2dl2ruww6qqu
Citation

"Train a correct BP neural network as the input layer and as the training sample." Academic Journal of Computing & Information Science 5.6 (2022)