摘要
对微粒群优化算法(PSO)进行分析,提出一种增强型微粒群优化算法(EPSO).用EPSO和PSO对几种常用函数的优化问题进行测试比较,结果表明EPSO比PSO更容易找到全局最优解,优化效率和优化性能明显提高.将EPSO用于催化裂化装置主分馏塔粗汽油干点软测量,建立了基于EPSO算法的粗汽油干点神经网络软测量模型.研究结果表明,基于EPSONN的软测量模型比基于BPNN的软测量模型具有更高的精度和更好的性能.
An enhanced particle swarm optimization algorithm (EPSO) is proposed based on the analysis of PSO. Both EPSO and PSO are used to resolve several well-known and widely used test function optimization problems. Results show that EPSO has greater efficiency, better performance and more advantages in many aspects than PSO. Then, EPSO is applied to train artificial neural network (NN) to construct a practical soft-sensor of gasoline endpoint of main fractionator of fluid catalytic cracking unit. The obtained results show that the proposed method is feasible and effective in soft-sensor of gasoline endpoint.
出处
《控制与决策》
EI
CSCD
北大核心
2005年第4期377-381,共5页
Control and Decision
基金
教育部博士点专项基金项目(20030251003).
关键词
微粒群优化
增强型微粒群优化
神经网络
软测量
Artificial intelligence
Computer simulation
Fluid catalytic cracking
Gas fuel measurement
Optimization
