Heuristic Optimization Algorithm for Automated Control Design of Bioleaching of Chalcopyrite

Microbially assisted recovery of copper from low-grade chalcopyrite has been reported to be a very difficult process, conventional hydrometallurgical methods were limited by many parameters. This study focus on the design and the training of a Multi-Layer Perceptron classifier for the optimized preparation conditions for bioleaching of chalcopyrite. The proposed approach uses the heuristic Backpropagation Neural Network generation and training (BPNN) algorithm to generate the neural network system. The optimization conditions for bioleaching of chalcopyrite in the system were discussed based on the artificial neural network model, in which the input conditions were selected as stirring speed, volume of inoculum, and process pH. The highest Cu dissolution of bioleaching was regarded as the optimization aim, along with constraints of each factor's bounds. The highest copper recovery of 32.1% is obtained at pH 1.5, stirring speed of 140r/min, and 13% (v/v) inoculum concentration. The BP model based on heuristic optimization algorithm for bioleaching of chalcopyrite has practicability.