Rotating Machinery Condition Optimization Prediction Method of Variable Weight Combination RBF Model Research
-
摘要: 针对现有各种非平稳非线性特征旋转机械运行状态预测方法适用性差、精度不高的难点问题,提出一种旋转机械运行状态优化组合模型变权重RBF预测方法,该方法通过对单一预测模型进行优选,对输入样本进行加权处理,采用径向基神经网络进行变权重组合模型动态建模,从而充分利用了已知的有效信息,强调了新旧信息对设备未来运行状态发展产生的不同影响.经实测数据验证,获得了比单一预测模型及定权重RBF组合预测方法精度更高的预测结果.该方法程序实现简便,预测精度高,对预测问题的适用性广.Abstract: In order to improve the forecast accuracy and adaptability for rotating machinery working conditions with unsteady and nonlinear features,an optimization prediction method of variable weight RBF combination model was suggested.This model was built based on variable weight RBF network.The samples were weighted according to the time to output and the combined models were selected according to the average relative error while the model built.As a result,the sufficient effective information was used,and the fact that new and old information taking different effect on the future state was stressed.The method was verified by measured data.The accuracy of variable weight RBF combination forecasting method was better than single RBF model and single weight combination forecasting methods.This method is simple to program and more adaptable on prediction with high farecast accuracy.
-
Keywords:
- model /
- variable weight /
- condition prediction /
- RBF network
-
-
[1] BATES J M,GRANGER C W J.The combination offorecasts[J].Journal of Operational Research Quarterly,1969,20(4):451-468.
[2] 陈华友.组合预测权系数确定的一种合作对策方法[J].预测,2003,22(1):75-77.CHEN Hua-you.A kind of cooperative games methoddetermining weights of combination forecasting[J].Forecasting,2003,22(1):75-77.(in Chinese) [3] 许丽佳,王厚军,龙兵.故障组合预测模型研究[J].电子测量与仪器学报,2007,21(5):6-10.XU Li-jia,WANG Hou-jun,LONG Bing.Study of faultintegrated forecasting model[J].Journal of ElectronicMeasurement and Instrument,2007,21(5):6-10.(inChinese) [4] HANSEN B E.Least-squares forecast averaging[J].Journal of Econometrics,2008,146(2):342-350.
[5] 韩东,许葆华,马献果.基于绝对误差的线性组合预测研究[J].河北科技大学学报,2010,31(6):497-500,522.HAN Dong,XU Bao-hua,MA Xian-guo.Research onlinear combination forecasting based on absolute error[J].Journal of Hebei University of Science and Technology,2010,31(6):497-500,522.(in Chinese) [6] 唐小我,曹长修.组合预测方法研究的若干新结果[J].预测,1992,11(5):39-46.TAGN Xiao-wo,CAO Chang-xiu.Some new results ofcombination forecasting study[J].Forecasting,1992,11(5):39-46.(in Chinese) [7] 徐小力,徐洪安,曹爱东.旋转机组的基于变权重神经网络组合预测模型[J].中国机械工程,2003,14(4):68-71.XU Xiao-li,XU Hong-an,CAO Ai-dong.A combinedpredicting model based on neural network of variableweighting modulus to rotary sets[J].China MechanicalEngineering,2003,14(4):68-71.(in Chinese) [8] 臧淑英,梁欣,冯仲科.变权组合预测模型的建立及其在区域生态风险预测中的应用[J].北京林业大学学报,2007,29(增刊2):203-208.ZAGN Shu-ying,LIANG Xin,FENG Zhong-ke.Establishment of the changeable weight combinationforecasting model and its application in regional ecologicalrisk forecasting[J].Journal of Beijing Forestry University,2007,29(Suppl 2):203-208.(in Chinese) [9] 刘志杰,季令,叶玉玲,等.基于径向基神经网络的集装箱吞吐量组合预测[J].同济大学学报:自然科学版,2007,35(6):739-744.LIU Zhi-jie,JI Ling,YE Yu-ling,et al.Combinedforecast method of port container throughput based on RBFneural network[J].Journal of Tongji University:NaturalScience,2007,35(6):739-744.(in Chinese) [10] 唐纪,王景.组合预测方法评述[J].预测,1999,18(2):42-43.TAGN Ji,WAGN Jing.Recite on combination forecastingmethod[J].Forecasting,1999,18(2):42-43.(inChinese) [11] 王吉芳,徐小力,费仁元,等.基于径向基神经网络的设备运行状态新信息加权预测模型研究[J].制造业自动化,2011,33(4):76-80.WANG Ji-fang,XU Xiao-li,FEI Ren-yuan,et al.Rescarching on prediction model of the new informationweighted for mechanical equipment running-state based onRBF neural network[J].Manufacturing Automation,2011,33(4):76-80.(in Chinese)
计量
- 文章访问数: 17
- HTML全文浏览量: 0
- PDF下载量: 8