Oxidation reduction potential(ORP) is an important parameter in the process of biological oxidation pretreatment of gold

in order to achieve accurate forecast of it

a new method based on an improved shuffled frog leaping algorithm(SFLA) was proposed to optimize the parameters of support vector machine regression model.Based on the standard shuffled frog leaping algorithm

this proposed algorithm was referred to the idea of the backward difference to initialize the population and introduced the individual cognition of particle swarm to make local optimization.Then the improved SFLA algorithm was used to optimize the parameters of support vector machine regression to achieve the precision of ORP prediction.The simulation was made with production data of a gold mine in Xinjiang.The result showed that SVR based on the improved SFLA had a higher accuracy in ORP prediction.