原油煉制中減壓塔側(cè)線產(chǎn)品是精制潤(rùn)滑油的原料，其粘度測(cè)量對(duì)生產(chǎn)有重要意義。通
過(guò)統(tǒng)計(jì)分析得出了影響側(cè)線產(chǎn)品粘度的主要因素，并采用支持向量機(jī)回歸方法建立粘度軟測(cè)量模型。針對(duì)支持向量機(jī)訓(xùn)練參數(shù)確定問(wèn)題，提出了采用差分進(jìn)化算法的搜索策略，使模型訓(xùn)練參數(shù)的調(diào)整過(guò)程按預(yù)定目標(biāo)自動(dòng)快速優(yōu)化。所構(gòu)建的粘度軟測(cè)量模型預(yù)報(bào)精度較高，趨勢(shì)跟蹤性能良好。
關(guān)鍵詞：軟測(cè)量；減壓塔；粘度；支持向量機(jī)；差分進(jìn)化；

Abstract: The measurement of viscosity is important for the side-draw product quality of vacuum distillation column in oil refinery. The main factors, which influence the viscosity, were analyzed by statistic methods. Then soft-sensor models were developed based on support vector regression. A search method based on differential evolution was proposed to select proper training parameters. Using this strategy, the parameters can be optimized automatically and efficiently. The developed model got high accuracy and good trend tracking performance on the real industrial data.
Keywords: soft sensor; vacuum distillation column; viscosity; support vector machine;
differential evolution;