为实现对液压泵特征参数的在线预测,提出一种贯序正则极端学习机(SRELM),并研究了基于SRELM的预测方法。SRELM根据结构风险最小化原理实现网络训练,其网络权值可随新样本的逐次加入而递推求解,具有泛化能力强与训练速度快的优点,因此适于特征参数的在线预测。基于SRELM的预测方法利用特征参数训练SRELM模型,以逐次增加新数据的方式对SRELM模型进行在线训练,并利用训练后的SRELM模型对未来时刻的特征参数进行外推预测。液压泵特征参数预测实例表明,基于SRELM的特征参数预测方法具有预测精度高与计算效率高的优点,其综合性能优于基于传统迭代式神经网络的预测方法与基于支持向量机的预测方法。
In order to accurately predict the feature parameters of a hydraulic pump, a new algorithm called sequential regularized extreme learning machine (SRELM) is proposed and a prediction method based on SRELM is studied. On the basis of structural risk minimization theory, SRELM balances the empirical risk and structural risk to enhance the generalization performance of conventional extreme learning machine (ELM). In comparison with the regularized extreme learning machine (RELM), SRELM can complete the training procedure recursively without retraining when there are sequential training samples. Thus, SRELM is suitable for on-line feature parameter prediction. In the SRELM-based prediction method, feature parameters of the hydraulic pump are used to train an SRELM model. The latest feature parameter is adopted iteratively to update the prediction model and then the trained prediction model is used to predict future feature parameters. Experiments on the hydraulic pump feature parameter prediction indicate that the SRELM-based prediction method has better performance in prediction accuracy and computational cost in comparison with conventional neural-network-based prediction and support-vector-machine-based prediction.
[1] 曾声奎, Michael G. Pecht, 吴际. 故障预测与健康管理(PHM)技术的现状与发展[J]. 航空学报, 2005, 26(5): 626-632. Zeng Shengkui, Michael G. Pecht, Wu Ji. Status and perspectives of prognostics and health management technologies[J]. Acta Aeronautica et Astronautica Sinica, 2005, 26(5): 626-632. (in Chinese)
[2] 孙博, 康锐, 张叔农. 基于特征参数趋势进化的故障诊断和预测方法[J]. 航空学报, 2008, 29(2): 393-398. Sun Bo, Kang Rui, Zhang Shunong. An approach to diagnostics and prognostics based on evolutionary feature parameters [J]. Acta Aeronautica et Astronautica Sinica, 2008, 29(2): 393-398. (in Chinese)
[3] Caesarendra W, Niu G, Yang B S. Machine condition prognosis based on sequential Monte Carlo method[J]. Expert Systems with Applications, 2010, 37(3): 2412-2420.
[4] Tran V T, Yang B S, Tan A C C. Multi-step ahead direct prediction for the machine condition prognosis using regression trees and neuro-fuzzy systems[J]. Expert Systems with Applications, 2009, 36(5): 9378-9387.
[5] Feng F Z, Zhu D D, Jiang P C, et al. GA-EMD-SVR condition prediction for a certain diesel engine//Proceedings of Prognostics and Health Management Conference. 2010: 1-8.
[6] Zhao F G, Chen J, Guo L, et al. Neuro-fuzzy based condition prediction of bearing health[J]. Journal of Vibration and Control, 2009, 15(7): 1079-1091.
[7] 李本威, 张赟, 孙涛. 基于免疫粒子群算法的滑油屑末支持向量机预测模型设计[J]. 航空动力学报, 2009, 24(7): 1639-1643. Li Benwei, Zhang Yun, Sun Tao. Design of forecasting model for aero-engine lubrication debris support vector machines based on immune-particle swarm optimization algorithm[J]. Journal of Aerospace Power, 2009, 24(7): 1639-1643. (in Chinese)
[8] 胡金海, 谢寿生, 骆广琦, 等. 基于支持向量机方法的发动机性能趋势预测[J]. 推进技术, 2005, 26(3): 260-264. Hu Jinhai, Xie Shousheng, Luo Guangqi, et al. Study of support vector machines for aeroengine performance trend forecasting[J]. Journal of Propulsion Technology, 2005, 26(3): 260-264. (in Chinese)
[9] Huang G B, Zhu Q Y, Siew C K. Extreme learning machine: theory and applications[J]. Neurocomputing, 2006, 70(1-3): 489-501.
[10] Liang N Y, Huang G B, Saratchandran N, et al. A fast and accurate on-line sequential learning algorithm for feedforward networks[J]. IEEE Transactions on Neural Networks, 2006, 17(6): 1411-1423.
[11] Miche Y, Soriamaa A, Bas P, et al. OP-ELM: optimally pruned extreme learning machine[J]. IEEE Transactions on Neural Networks, 2010, 21(1): 158-162.
[12] Liu N, Wang H. Ensemble based extreme learning machine[J]. IEEE Signal Processing Letters, 2010, 17(8): 754-757.
[13] Lan Y, Soh C Y, Huang G B. Constructive hidden nodes selection of extreme learning machine for regression[J]. Neurocomputing, 2010, 73(16-18): 3191-3199.
[14] Malathi V, Marimuthu N S, Baskar S. Intelligent approaches using support vector machine and extreme learning machine for transmission line protection [J]. Neurocomputing, 2010, 73(10-12): 2160-2167.
[15] 邓万宇, 郑庆华, 陈琳, 等. 神经网络极速学习方法研究[J]. 计算机学报, 2010, 33(2): 279-287. Deng Wanyu, Zheng Qinghua, Chen Lin, et al. Research on extreme learning of neural networks[J]. Chinese Jour- nal of Computers, 2010, 33(2): 279-287. (in Chinese)
[16] 张贤达. 矩阵分析与应用[M]. 北京: 清华大学出版社, 2005. Zhang Xianda. Matrix analysis and applications[M]. Beijing: Tsinghua University Press, 2005. (in Chinese)
CJA