A dynamic ensemble extreme learning machine model for aircraft engine health condition prediction
-
摘要: 提出一种动态集成极端学习机模型用于航空发动机健康状态预测.采用AdaBoost.RT集成学习算法对极端学习机(ELM)进行集成,在训练时采用每个训练样本的近邻样本对ELM的局域性能进行评估;在预测时首先确定新样本在训练样本集中的近邻样本,然后根据ELM在近邻样本上的性能来赋予集成权值实现弱学习机的动态集成.以燃油流量为指标进行航空发动机健康状态预测,动态集成ELM模型短期预测结果的平均相对误差绝对值(MAPE)为3.688%,小于单一ELM模型的3.830%以及静态集成ELM模型的3.719%;长期预测结果中动态集成ELM模型的MAPE为3.075%,小于单一ELM模型的4.355%以及静态集成ELM模型的3.884%.因此动态集成ELM模型更适用于航空发动机健康状态预测.Abstract: A dynamic ensemble extreme learning machine (ELM) model was proposed for aircraft engine health condition prediction. The AdaBoost.RT algorithm was used to integrate ELM to construct the ensemble model. During the training process, the neighboring samples of every training sample were employed to evaluate the local performance of ELM. In the prediction process, the neighboring samples of new samples in the training sample set were selected firstly, then the combined weights of ELM were determined by the performance on the neighboring samples, implementing the dynamic ensemble of the weak learning machine. Fuel flow was utilized as a health index for aircraft engine health condition prediction. For short term prediction, the mean absolute percentage error (MAPE) of the dynamic ensemble ELM model was 3.688%, less than the MAPE of the single ELM model and the static ensemble ELM model, which were 3.830% and 3.719%, respectively. And for long term prediction, the MAPE of the dynamic ensemble ELM model was 3.075%, also less than that of the single ELM model of 4.355% and the static ensemble ELM model of 3.884%. Thus, the dynamic ensemble ELM model is better for the aircraft engine health condition prediction.
-
[1] 丁刚,徐敏强,侯立国.基于过程神经网络的航空发动机排气温度预测[J].航空动力学报,2009,24(5):1035-1039. DING Gang,XU Minqiang,HOU Liguo.Prediction of aeroengine exhaust gas temperature using process neural network[J].Journal of Aerospace Power,2009,24(5):1035-1039.(in Chinese) [2] 金向阳,林琳,钟诗胜,等.航空发动机振动趋势预测的过程神经网络法[J].振动、测试与诊断,2011,31(3):331-334. JIN Xiangyang,LIN lin,ZHONG Shisheng,et al.Prediction of aeroengine vibration trend using process neural network[J].Journal of Vibration,Measurement and Diagnosis,2011,31(3):331-334.(in Chinese) [3] 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(1):70-74. CHEN Guo,YANG Yuwei.Artificial neural network multi-variable forecasting model of aero-engine complex wear trend[J].China Mechanical Engineering,2007(1):70-74.(in Chinese) [4] Schapire R E.The strength of weak learnability[J].Machine Learning,1990,5(2):197-227. [5] Freund Y,Schapire R E.A desicion-theoretic generalization of on-line learning and an application to boosting[J].Computational Learning Theory,1995,904:23-37. [6] Breiman L.Bagging predictors[J].Machine Learning,1996,24(2):123-140. [7] Solomatine D P,Shrestha D L.AdaBoost.RT:a boosting algorithm for regression problems[C]//Proceeding of 2004 IEEE International Joint Conference on Neural Networks.Budapest,Hungary:IEEE,2004:1163-1168. [8] Huang G B,Zhu Q Y,Siew C K.Extreme learning machine:theory and applications[J].Neurocomputing,2006,70:489-501. [9] Huang G B,Wang D H,Lan Y.Extreme learning machines:a survey[J].International Journal of Machine Learning and Cybernetics,2011,2(2):107-122. [10] SHI Lichen,BAO Lianglu.EEG-based vigilance estimation using extreme learning machines[J].Neurocomputing,2013,102:135-143. [11] TIAN Huixin,MAO Zhizhong.An ensemble ELM based on modified AdaBoost.RT algorithm for predicting the temperature of molten steel in ladle furnace[J].IEEE Transactions on Automation Science and Engineering,2010,7(1):73-80. [12] Drucker H.Improving regressors using boosting techniques[C]//Proceeding of the 14th International Conference on Machine Learning.San Francisco:Morgan Kaufmann Publishers Inc,1997:107-115. [13] YANG Yihsuan,LIN Yuching,SU Yafan,et al.Music emotion classification:a regression approach[C]//Proceeding of 2007 IEEE International Conference on Multimedia and Expo.Beijing:IEEE,2007:208-211. [14] Niall R,Patterson D.A fusion of stacking with dynamic integration[C]//Proceeding of 20th International Joint Conference on Artificial Intelligence.San Francisco:Morgan Kaufmann Publishers Inc,2007:2844-2849. [15] Puuronen S,Terziyan V,Tsymbal A.A dynamic integration algorithm for an ensemble of classifiers[C]//Proceeding of 11th International Symposium,Foundations of Intelligent Systems.Berlin Heidelberg:Springer,1999:592-600. [16] Alexey T,Puuronen S.Bagging and boosting with dynamic integration of classifiers[C]//Proceeding of 4th European Conference,Principles of Data Mining and Knowledge Discovery.Berlin Heidelberg:Springer,2000:116-125. [17] Niall R,Patterson D,Anand S,et al.Dynamic integration of regression models[C]//Proceeding of 5th International Multiple Classifier Systems Workshop.Berlin Heidelberg:Springer,2004:164-173. [18] ZHANG Chunxia,ZHANG Jiangshe.A local boosting algorithm for solving classification problems[J].Computational Statistics and Data Analysis,2008,52(4):1928-1941.
点击查看大图
计量
- 文章访问数: 1402
- HTML浏览量: 0
- PDF量: 979
- 被引次数: 0