銅轉(zhuǎn)爐吹煉中的應(yīng)用
(中南大學(xué) 信息科學(xué)與工程學(xué)院，長(zhǎng)沙 410083)
摘 要: 為實(shí)現(xiàn)銅轉(zhuǎn)爐吹煉過(guò)程中的關(guān)鍵操作參數(shù)的準(zhǔn)確預(yù)測(cè)，構(gòu)造一種基于核偏最小二乘法的動(dòng)態(tài)預(yù)測(cè)模型，并提出一種適用于動(dòng)態(tài)建模的在線式異常樣本剔除方法。該動(dòng)態(tài)預(yù)測(cè)模型使用滑動(dòng)窗方法不斷更新建模數(shù)據(jù)，再利用核偏最小二乘法對(duì)動(dòng)態(tài)模型的參數(shù)進(jìn)行辨識(shí)，最后根據(jù)反饋的前次計(jì)算誤差對(duì)本次預(yù)測(cè)值進(jìn)行修正。仿真研究結(jié)果表明：該動(dòng)態(tài)預(yù)估模型具有較好的泛化能力和較強(qiáng)的魯棒性，并具有較好預(yù)測(cè)精度(風(fēng)量預(yù)測(cè)的相對(duì)均方根誤差小于10%，氧量預(yù)測(cè)的相對(duì)均方根誤差小于19%)。目前，該預(yù)測(cè)模型被用于某轉(zhuǎn)爐的吹煉輔助決策系統(tǒng)中。
關(guān)鍵字: 動(dòng)態(tài)預(yù)測(cè)模型；在線式異常樣本剔除；核偏最小二乘法；關(guān)鍵操作量預(yù)測(cè)；銅轉(zhuǎn)爐吹煉
least squares for copper converting
（School of Information Science and Engineering, Central South University, Changsha 410083, China）
Abstract: In order to predict accurately the key operational parameters in copper converting process, a dynamical prediction model based on kernel partial least squares was constructed, and a method of online eliminating abnormal samples for dynamical model was presented. Firstly, moving widow method was utilized to update samples continuously in dynamical prediction model. Then, kernel partial least squares was used to identify parameters of dynamical model. Lastly, the prediction values were modified according to the last feedback computing errors. The simulation result shows that this dynamical prediction model has the performances like, better generalization, stronger robust, and preferable accuracy (the relative root mean square error of air is lower than 10%, and the relative root mean square error of oxygen is lower than 19%). Now, the prediction model is applied in the assistant decision-making system for a copper converter.
Key words: dynamical prediction model; online eliminating abnormal samples; kernel partial least squares method; copper converting
