摘要
针对反渗透脱盐水系统中的反渗透膜故障问题,提出了一种基于支持向量机(SVM)的故障诊断方法。为了解决SVM的参数优化问题,采用一种基于改进的混沌粒子群优化算法的支持向量机参数选择方法。将混沌理论引入粒子群优化算法中,提高种群的多样性和粒子搜索的遍历性,有效地提高了粒子群算法的收敛速度和精度,得到了优化的SVM模型。并将此模型应用于反渗透脱盐水系统的故障诊断中。仿真结果表明,改进的SVM分类器能有效地诊断出反渗透膜故障,并且取得了较高的准确率和诊断效率。
According to the reverse osmosis membrane fault problems in reverse osmosis water desalination system, a fault diagnosis method based on support vector machine(SVM) was introduced for fault diagnoses. To solve the problem of parameter optimization in SVM, an improved chaos particle swarm algorithm was proposed. The introduction of Chaos theory to particle swarm optimization algorithm may not only enhance the diversity of the population and particle global search ability, but also improve the convergence speed and accuracy of the particle swarm algorithm. The optimized SVM model was applied to the fault diagnosis of reverse osmosis water desalination system. The simulation results show that the improved SVM classifier can effectively diagnose the reverse osmosis membrane fault diagnosis and achieve a higher diagnostic accuracy and efficiency.
出处
《系统仿真学报》
CAS
CSCD
北大核心
2015年第5期1057-1063,共7页
Journal of System Simulation
基金
国家粮食局公益性科研项目(201313012)
关键词
反渗透脱盐水
支持向量机
混沌粒子群优化算法
故障诊断
reverse osmosis water desalination
support vector machine
chaos particle swarm optimization
fault diagnosis
