摘要
综合基本微粒群优化算法(Particle Swarm Optimization,PSO)和模拟退火(Simulated Annealing,SA)算法,提出了一种新型的协同进化方法(SAPSO)。通过PSO和SA两种算法的协同搜索,可以有效地克服微粒群算法的早熟收敛。用SAPSO训练神经网络,并将其用于延迟焦化装置粗汽油干点和高压聚乙烯熔融指数的软测量建模。与几种常见建模方法比较,结果表明该软测量模型具有更高的测量精度和更好的泛化性能,能够满足现场测量要求。
A novel cooperative evolutionary algorithm （SAPSO） is proposed by taking advantage of both Particle Swarm Optimization （PSO） and Simulated Annealing （SA） algorithm.It can validly overcome the premature problem in PSO through cooperative search between PSO and SA.Then,SAPSO is employed to train artificial neural network and applied to soft-sensing of gasoline endpoint of delayed coking plant and melt-index of High Pressure Low-density Polyethylene yield.Its performance is compared with existing soft sensor modeling methods.The simulation results show that this model has higher measuring preeision as well as better generalization ability, and can satisfy the need of spot measurement.
出处
《计算机工程与应用》
CSCD
北大核心
2009年第31期241-244,共4页
Computer Engineering and Applications
关键词
微粒群优化算法
模拟退火
神经网络
软测量
Particle Swarm Optimization（ PSO ） algorithm
Simulated Annealing（SA）
Neural Network（NN ）
soft-sensor
