摘要提出了一種綜合改進(jìn)的BP 神經(jīng)網(wǎng)絡(luò)算法，該算法在訓(xùn)練時(shí)對(duì)不同的連接權(quán)和閾值采用不同的學(xué)習(xí)速率，由此建立了乙二醇精制塔塔釜乙二醇濃度的神經(jīng)網(wǎng)絡(luò)軟測(cè)量模型。結(jié)果表明該算法能有效提高乙二醇濃度BP 神經(jīng)網(wǎng)絡(luò)軟測(cè)量模型的收斂精度。
關(guān)鍵詞BP 神經(jīng)網(wǎng)絡(luò)算法改進(jìn)乙二醇濃度軟測(cè)量模型
Abstract A comprehensively improved BP algorithm is issued in this paper. According to this algorithm，different learning rates are applied to different
connection weights and threshold values when a BP network is trained. A neural network model is setup to be used on soft sensing of the concentration of
the ethylene glycol of the MEG column. Practice shows that this proposed algorithm is effectively able to improve the convergence precision of the BP
neural network in soft sensing for the concentration of ethylene glycol.
Keywords BP neural network Improved algorithm Concentration of ethylene glycol Soft sensing model