Hybrid predictive model of gold concentration for hydrometallurgy leaching process

作者：Zhang Jun^*; Mao Zhizhong; Jia Runda; Zhang Yanfen

来源：Chinese Journal of Scientific Instrument, 2013, 34(3): 629-634.

• Concentration Measurement
• Cyanidation leaching
• Hybrid modeling
• Hydrometallurgy leaching
• Mass conservation equations
• Mechanism modeling
• Tikhonov regularization
• Tikhonov regularization method

Gold cyanidation leaching process is the important step of hydrometallurgical gold extraction, which is a complex chemical process. Establishing accurate and reliable mathematic model is the precondition to implement the optimization and control of the leaching process. A dynamic hybrid serial model for gold cyanidation leaching process is proposed in this paper. Mass conservation equation is used to establish the dynamic mechanism model of gold cyanidation leaching process; neural network is used to estimate the unknown parameters in the mechanism model, which are gold dissolving rate and cyanide ion consumption rate; and finally the dynamic hybrid serial model of gold cyanidation leaching process is obtained. Because of the immeasurability of kinetic reaction rates, the Tikhonov regularization method is used to estimate the kinetics reaction rates of gold and cyanide ion in gold cyanidation leaching process, which can effectively reduce the influence of the noise in concentration measurement value on kinetic reaction rate estimation. Simulation experiment result shows that the predictive performance of the proposed hybrid model is superior to those of pure mechanism model and neural network black-box model. The hybrid model can predict the concentration of all the components in gold cyanidation leaching process precisely, which lays an important model foundation for the control and optimization of gold cyanidation leaching process.

• 出版日期2013
• 单位东北大学