CAJ | 학술논문

采用正交试验法确定人工神经网络(ANN)训练样本集的输入参数,利用基于严格机理模型的低温甲醇洗模拟系统(RPS)进行模拟计算,得到样本的输出期望值后,对改进的BP网络进行训练.结果表明,ANN成功地模拟了低温甲醇洗系统,其模型可作为“黑箱”模型代替RPS的严格模型.运用复合形法基于ANN模型对低温甲醇洗系统的重要工艺条件进行优化,可节省计算时间.优化结果表明,装置的CO2产量提高,氨冷负荷降低;所描述的优化策略可用于解决大型实际复杂系统的操作条件优化问题.这一结果为工厂优化操作指明了方向.
채용정교시험법학정인공신경망락(ANN)훈련양본집적수입삼수,이용기우엄격궤리모형적저온갑순세모의계통(RPS)진행모의계산,득도양본적수출기망치후,대개진적BP망락진행훈련.결과표명,ANN성공지모의료저온갑순세계통,기모형가작위“흑상”모형대체RPS적엄격모형.운용복합형법기우ANN모형대저온갑순세계통적중요공예조건진행우화,가절성계산시간.우화결과표명,장치적CO2산량제고,안랭부하강저;소묘술적우화책략가용우해결대형실제복잡계통적조작조건우화문제.저일결과위공엄우화조작지명료방향.
The modified back-propagation artificial neural network (ANN) istrained by the training sample sets given by orthogonal experiment to get the input parameters and the rectisol process simulator (RPS) based on exact mathematical models is used to obtain the output parameters. The training results show that ANN is succ essful in simulating the rectisol process and can be used as ″black box″ model to replace the rigorous RPS models. Complex algorithm is used to optimize the critical process conditions of rectisol system, which uses the trained ANN as am athematical model, so that the optimization problem is greatly simplified and the computational time decreases significantly. The optimization results show that the product quantity of CO2 is increased and the load of refrigerated ammonia is reduced. These results can be used to guide the operation of ammonia plant. The practical problems such as the optimization of operation conditions of large and complicated systems can be solved by the strategy described in this paper.