BP神经网络优化微生物浸矿工艺

以低品位黄铜矿溶液为原料，浸矿制备Cu2＋能有效提高低品位黄铜矿的利用价值。基于浸矿过程中存在多因素影响的现象，通过正交试验与神经网络分析方法，对浸矿条件（接种量、矿石品位、Fe2＋添加量及浸矿溶液pH）实行优化。结果表明：在正交试验组中最佳试验结果为浸矿产128．753mg／LCu^2＋；BP神经网络优化后的最佳实验组合为微生物接种量12％、矿石品位0．3％、添加Fe^2＋24g/L及浸矿溶液pH1．7，该条件下验证试验产Cu^2＋ 141．352mg／L，通过正交试验及神经网络优化提高了微生物浸出低品位黄铜矿酸性溶液Cu^2＋的产量。

Optimization of bioleaching conditions with back-propagation artificial neural network

Chalcopyrite hydrolyte was used as bioleaching material for the production of copper ion and it could increase the value of low grade chalcopyrite. In this paper, the orthogonal experimental design and back-propagation artificial neural network （BP-ANN） were employed to evaluate the optimal bioleaching results affected by parameters of inoculum rate, ore grade, and Fe （Ⅱ） addition, and leaching solution pH. The results showed the optimal bioleaching condition predicted by each approach, and the orthogonal experimental design showed that 128.753 mg/L copper ion was optimal under the condition. It showed that BP-ANN performed the experiment to be better than orthogonal experimental design. Under the opti- mal conditions （inoculum rate 12% , ore grade 0. 3% , Fe2＋ addition 24 g/L, and leaching solution pH 1.7 ） , the yield of copper ion was achieved in a 500 mL flask.