Research on Reaction State Identification of Rare Earth Molten Salt Based on Farneback-GRU
A method for identifying the reaction state of rare earth molten salt based on Farneback-GRU is proposed.The reaction intensity of rare earth molten salt is quantified by the Farneback dense optical flow method,scaling transformation,and mean filtering,and a nonlinear mapping model between rare earth molten salt motion field characteristics and the rare earth molten salt reaction state is established by the Gated Recurrent Unit(GRU)neural network.The accuracy of the model reaches 95.23％,which can well meet the testing standards of production enterprises.In addition,the performance indicators of the model show that the model has good robustness and provides important closed-loop feedback parameters for the online control of rare earth electrolyzers.
NETL
NSTL
万方数据
