本文基于人工神经元网络的计算特性,提出了一种具有学习能力的在线优化策略.这种方法不需要对优化对象进行机理建模或变量间的相关性分析,而直接从工艺管线的拓扑结构出发建立神经网络模型.整个优化过程采用增量跟踪运算方式,因而能自动适应工况的变化.文中以润滑油生产过程为例进行了仿真研究,结果表明本方法是有效的. In this paper, based on the computational characteristics of artificial neural network, an online optimization strategy with learning ability is proposed, which does not need to model the mechanism of optimization or the correlation between variables, but directly from the topology of the process pipeline The neural network model is set up and the whole optimization process is based on incremental tracking mode, which can automatically adapt to the changes of working conditions.In this paper, a simulation study of the production process of lubricating oil is carried out, and the results show that this method is effective.