|
|||||
|
|
| 基于改进PSO-SVM参数优化的发动机起动过程辨识 | |
| 引用本文： | 王冠超,杨春,徐波,王文博,孙波. 基于改进PSO-SVM参数优化的发动机起动过程辨识[J]. 燃气涡轮试验与研究, 2011, 24(1): 35-41 |
| 作者姓名： | 王冠超 杨春 徐波 王文博 孙波 |
| 作者单位： | 1. 海军驻长春地区航空军事代表室,吉林,长春,300000 2. 海军航空工程学院,研究生管理大队,山东,烟台,264001 3. 91467部队,山东,青岛,266041 4. 92514,部队,山东,烟台,264001 |
| 摘 要： | 针对影响支持向量机辨识性能的核函数及相关参数,找出使辨识结果最佳的核函数;结合两种措施改进粒子群算法,优化相关参数,选择最佳的参数组合.对比 BP 神经网络和支持向量机对发动机起动过程的辨识结果,得到支持向量机的辨识精度和收敛时间优于 BP 神经网络,与起动数据基本一致.在训练样本存在噪声的情况下,验证了所建辨识模型具... |
| 关 键 词： | 发动机起动 BP神经网络 支持向量机 辨识 改进粒子群 |
Engine Start Identification Based on Parameter Optimization of Improved PSO-SVM |
|
| WANG Guan-chao,YANG Chun,XU bo,WANG Wen-bo,SUN Bo. Engine Start Identification Based on Parameter Optimization of Improved PSO-SVM[J]. Gas Turbine Experiment and Research, 2011, 24(1): 35-41 | |
| Authors: | WANG Guan-chao YANG Chun XU bo WANG Wen-bo SUN Bo |
| Affiliation: | WANG Guan-chao1,YANG Chun2,XU bo3,WANG Wen-bo4,SUN Bo2(1.Aeronautical Military Deputy Office of Navy in Changchun,Changchun 300000,China,2.Graduate Student Brigade,Naval Aeronautical and Astronautical University,Yantai 264001,3.The 91245 Unit of PLA,Qingdao 266061,4.The 92514 Unit of PLA,China) |
| Abstract: | For kernel function and relative parameters of affecting SVM identification performance,the best result has been found.Relative parameters are optimized by combining improved PSO with two methods.Parameters affecting identification performance and the best parameter selection are defined.Contrasting engine start identification results of BP neural network and SVM,identification precision and converage time of SVM which are consistent with starting data are superior to BP neural network.And generalized perfo... |
| Keywords: | engine starting BP neural network SVM identification improved PSO |
| 本文献已被 CNKI 万方数据 等数据库收录！ | |