針對(duì)SMB 色譜分離過(guò)程中組分純度難于實(shí)時(shí)在線測(cè)量的問(wèn)題,建立了一種基于BP 神經(jīng)網(wǎng)絡(luò)的軟測(cè)量模型。首先對(duì)實(shí)際生產(chǎn)中的原始數(shù)據(jù)，經(jīng)過(guò)過(guò)失誤差剔除及濾波處理后得到一套訓(xùn)練數(shù)據(jù)和校驗(yàn)數(shù)據(jù)組成訓(xùn)練樣本，然后采用BP 神經(jīng)網(wǎng)絡(luò)進(jìn)行訓(xùn)練，得到組分純度的非參數(shù)模型。為加快網(wǎng)絡(luò)收斂速度，采用改進(jìn)BP算法對(duì)其進(jìn)行訓(xùn)練。在MATLAB 工作平臺(tái)上進(jìn)行了大量的仿真研究，對(duì)該模型進(jìn)行驗(yàn)證，仿真結(jié)果表明，該
方法的有效性。
關(guān)鍵詞：模擬移動(dòng)床;軟測(cè)量;人工神經(jīng)元網(wǎng)絡(luò);BP 算法;改進(jìn)BP 算法
Abstract: In order to realize the online measurement in SMB separation process, a soft sensor model based on BP neural network which measures two components purity is built up. First by filter process of practical primal data, the training samples are gained. Then the nonparametric model on component purity is developed by use of BP neural network. Improved BP algorithm is applied to fast convergence. Much computer simulation on Matlab validates this method.
Keywords: Simulated moving bed; Soft-sensor; Artificial neural network (ANN); BP algorithm; Improved BP algorithm