Combinational Forecast Method Based on PSO-LSSVM in Spectrometric Oil Analysis of the Aircraft Engine
-
摘要: 油样光谱分析是航空发动机磨损状态监测与故障诊断的重要技术,基于光谱数据的航空发动机状态预测有利于发现航空发动机的早期磨损故障。根据光谱数据特征,选取AR模型、BP神经网络模型以及GM(1,1)预测模型作为基础模型,建立了基于最小二乘支持向量机的组合预测模型,同时,用粒子群算法对LSSVM的正则化参数以及核函数参数进行了优化。最后利用两组实际的航空发动机光谱分析数据对模型进行了验证,与基础模型的对比结果充分表明,提出的带粒子群优化的最小二乘支持向量机(the Least Squares Support Vector Machines with Particle SwarmOptimization-PSO-LSSVM)的非线性变权重组合预测模型具有更好的预测精度。Abstract: The spectrometric oil analysis (SOA) is an important technique for aircraft engine state monitoring andfault diagnosis,and forecasting aircraft engine state through SOA results has an advantage of finding out aircraft en-gine wear fault early. According to the characteristics of the SOA data,the combinational forecast model was set upbased on the least squares support vector machine after Auto Regressive (AR) model,GM(1, 1) model and backpropagation(BP) neural network model. In addition,the particle swarm algorithm was used to optimize the regular-ization parameter of least squares support vector machines(LSSVM) and the parameter of kernel function. Finally,two time series of SOA data were used to verify this model. By comparying with the foundation models,the result ofcombinational forecasting model shows better effect and higher precision of forecast by using the non-linear variableweight and the least squares support vector machines with particle swarm optimization.
-
[1] 尹树悦,陈东林. 航空发动机磨损趋势预测的 GM(1,1)模型方法[J]. 润滑与密封,2005,(5):96~97 [2] 陈果,杨虞微. 航空发动机复杂磨损趋势的神经网络多变量预测模型[J]. 中国机械工程,2007,18(1):70~74 [3] Bates J M,Granger C W J. Combination of forecasts[J]. Jour-nal of Operational Research Quarterly,1969,(20 ): 451~468 [4] 唐小我. 组合预测误差信息矩阵研究[J]. 电子科技大学学报,1992,21(4):448~454 [5] 马永开,唐小我,杨桂元. 非负权重最优组合预测方法的基本理论研究[J]. 运筹与管理,1997,6(2):1~8 [6] 陈华友,侯定丕. 基于预测有效度的优性组合预测模型的研究[J]. 中国科学技术大学学报,2002,32(2):172~180 [7] 王应明. 基于相关性的组合预测方法研究[J]. 预测,2002,21(2):58~62 [8] 邓乃扬,田英杰. 支持向量机—理论、 算法与拓展[M]. 北京:科学出版社,2009:182~184 [9] 胡金海,谢寿生. 基于 AR 模型对滑油中金属含量的预测[J].燃气涡轮实验与研究,2003,16(1):32~36 [10] Shi Y,Eberhart R C. Particle swarm optimization: developmentsapplications and resources[A]. Proceedings of the IEEE Con-gress on Evolutionary Computation[C],Piscataway,USA:IEEE Service Center,2001:81~86 [11] 张选平,杜玉平,秦国强,覃征. 一种动态改变惯性权的自适应粒子群算法[J]. 西安交通大学学报,2005,10,39(10):1039~1042 [12] 吴今培,肖健华. 智能故障诊断与专家系统[M]. 北京:科学出版社,1997
点击查看大图
计量
- 文章访问数: 209
- HTML全文浏览量: 32
- PDF下载量: 3
- 被引次数: 0