(1. 中南大學(xué) 冶金與環(huán)境學(xué)院，長(zhǎng)沙 410083；
2. 有色金屬資源循環(huán)利用湖南省重點(diǎn)實(shí)驗(yàn)室，長(zhǎng)沙 410083；
3. 有色金屬資源循環(huán)利用湖南省工程研究中心，長(zhǎng)沙 410083)
摘 要: 銻的浸出率是氧化處理含銻硫化礦時(shí)的重要結(jié)論指標(biāo)，在氧化浸出過(guò)程中通過(guò)條件控制來(lái)得到更好的浸出率具有十分重要的意義，為了模擬和預(yù)測(cè)含銻硫化礦的氧化浸出過(guò)程，用人工神經(jīng)網(wǎng)絡(luò)模型對(duì)浸銻過(guò)程進(jìn)行模擬，建立起單隱層8節(jié)點(diǎn)的“5-8-1型”誤差逆向傳播神經(jīng)網(wǎng)絡(luò)模型，所建人工神經(jīng)網(wǎng)絡(luò)模型可以對(duì)反應(yīng)過(guò)程做出有效的模擬和預(yù)測(cè)，實(shí)驗(yàn)值與預(yù)測(cè)值的相關(guān)系數(shù)可達(dá)99%以上。并根據(jù)所建神經(jīng)網(wǎng)絡(luò)模型中不同輸入量在網(wǎng)絡(luò)中節(jié)點(diǎn)權(quán)重的不同，得出相關(guān)條件因素對(duì)銻浸出率的相對(duì)重要性從高到低依次為：鹽酸濃度，反應(yīng)溫度，攪拌速度，液固比，反應(yīng)時(shí)間。
關(guān)鍵字: 人工神經(jīng)網(wǎng)絡(luò)；浸銻過(guò)程；預(yù)測(cè)；相關(guān)系數(shù)；相對(duì)重要性
（1. School of Metallurgy and Environment, Central South University, Changsha 410083, China;
2. Hunan Key Laboratory of Nonferrous Metal Resources Recycling, Changsha 410083, China;
3. Hunan Engineering Research Center of Nonferrous Metal Resources Recycling, Changsha 410083, China）
Abstract:The leaching rate of antimony is an important index for the treatment of antimony sulfide ore. It is very important to obtain better leaching rate through conditional control in the process of oxidation leaching. In order to simulate and predict the oxidation leaching process of antimony containing sulfide ore, BP Neural network model was used to simulate the leaching process of antimony, and a 5-8-1 type model was established. The neural network model could predict the leaching efficiency of antimony in the process exactly, the correlation coefficient between experimental data and predicted data could reach 99%. According to the weights of inputs in the neural network model, the importances of different impacts are in the descending order: HCl concentration, temperature, stirring speed, liquid to solid ratio, time.
Key words: BP neural network model; leaching process of antimony; prediction; correlation coefficient; relative importance
