Prediction of praseodymium/neodymium multicomponent content based on IHHO-ELM
Shuiping Zhang, Zhixiong Zhong, Wang Bi, Qihan Zhang · 2023
In order to solve the current situation that it is difficult to detect praseodymium/neodymium elements in rare earth mixed solutions in real time, a multicomponent content prediction method for praseodymium/neodymium elements based on IHHO-ELM is proposed. Tent mapping and reverse learning strategy are introduced in the initialisation stage of the population, and the parameters such as weights and thresholds of the limit learning machine are selected using the improved HHO algorithm, which retains the algorithm’s optimization seeking mechanism and improves the convergence speed on the basis of improving the algorithm’s performance. Meanwhile, the simulation simulation experiments are carried out with the images of praseodymium/neodymium two rare earth extraction solutions possessing ionic colour characteristics as an example, and the experimental data are obtained and then compared and analysed. The analysed results show that the method proposed in this paper can effectively reduce the measurement error and has high prediction accuracy and stability, which has certain theoretical significance and practical value for the rare earth extraction industry.