(1. 東北大學(xué)自動(dòng)化研究中心，沈陽(yáng)110006 2. 寶山鋼鐵公司自動(dòng)化研究所，上海201900)
摘 要: 轉(zhuǎn)爐煉鋼終點(diǎn)溫度和成分是轉(zhuǎn)爐煉鋼的控制目標(biāo)，它與吹氧量、鐵水加入量等多個(gè)變量之間存在著嚴(yán)重的非線性關(guān)系，且無(wú)法在線連續(xù)測(cè)量。作者提出了基于RBF神經(jīng)網(wǎng)絡(luò)的轉(zhuǎn)爐煉鋼終點(diǎn)溫度及碳含量預(yù)報(bào)模型，并結(jié)合某鋼鐵企業(yè)一座180 t 轉(zhuǎn)爐的實(shí)際數(shù)據(jù)進(jìn)行模型驗(yàn)證研究。結(jié)果表明，該方法收斂速度快，預(yù)報(bào)精度高。
關(guān)鍵字: 轉(zhuǎn)爐；煉鋼；預(yù)報(bào)；神經(jīng)網(wǎng)絡(luò)
（1. Research Center of Automation, Northeastern University, Shenyang 110006, P.R.China
2. Automatic Institute, Baoshan Iron and Steel Company, Shanghai 201900, P.R.China）
Abstract:The endpoint temperature and carbon content of basic oxygen furnace (BOF) are the control objects of the BOF steelmaking process. There exists serious non-linearity among them and blowing oxygen etc, and the online continue measurement can not be made. The predictive model of endpoint temperature and carbon content of the BOF steelmaking based on RBF neural network was put forward, and the research of verifying the model was made by comparing the predictive value with the practical data of an 180t converter in a factory. The results show that the method has fast convergence speed and accurate prediction.
Key words: BOF; steelmaking; prediction; neural network
