一种基于关联熵融合与改进回声状态网络的故障预测方法

PDF(1581 KB)

振动与冲击 ›› 2019, Vol. 38 ›› Issue (2) : 226-233.

论文

王浩天1,2，段修生3，单甘霖2，孙健4，邱锦涛1

作者信息 +

Prognostic algorithm based on the relative entropy fusion and modified ESN

WANG Haotian1,2,DUAN Xiusheng3，SHAN Ganlin2,SUN Jian4 ,QIU Jintao1

Author information +

文章历史 +

摘要

针对液压泵退化特征维数高、预测效果不佳的问题，本文提出了一种基于关联熵融合与改进ESN的故障预测方法。首先，以关联熵为基础，构建特征层级融合算法，以充分利用所提取的退化特征信息，在提高特征简洁度的基础上，进一步改善预测特征性能；在此基础上，对ESN储备池结构进行优化，重新定义邻接矩阵元素取值，建立改进的ESN预测模型，以改善网络的泛化能力，提高预测精度。最后，通过对液压泵性能退化试验的应用分析，验证了该方法的有效性。

Abstract

To deal with the shortcomings of high dimensional features and unsatisfying fault predicting effect in conventional hydraulic pumps fault diagnosis methods,a novel prognostic method based upon the relative entropy fusion and modified echo state network(ESN) was proposed.On the basement of relative entropy,a features fusion algorithm was presented for making full use of degradation feature informations for the sake of improving the prognostic feature performance based on the simplifying of features.Furthermore,the structure of the reserve pool in ESN was modified,and neighboring matrix elements were redefined.Then,a modified ESN predicting model was established to raise the network performance and increase the predicting accuracy.The proposed method was verified by its application in hydraulic pump performance degradation experiments.

导出引用

王浩天1,2，段修生3，单甘霖2，孙健4，邱锦涛1. 一种基于关联熵融合与改进回声状态网络的故障预测方法[J]. 振动与冲击, 2019, 38(2): 226-233

WANG Haotian1,2,DUAN Xiusheng3，SHAN Ganlin2,SUN Jian4,QIU Jintao1. Prognostic algorithm based on the relative entropy fusion and modified ESN[J]. Journal of Vibration and Shock, 2019, 38(2): 226-233

参考文献

[1] Paolo C, Alvin A. Gray box modeling of an excavator’s variable displacement hydraulic pump for fast simulation of excavation cycles. Control Engineering Practice 2013; 21(4): 483-494.
[2] Jian Sun, Hongru Li, Baohua Xu. Degradation feature extraction of the hydraulic pump based on high-frequency harmonic local characteristic-scale decomposition sub-signal separation and discrete cosine transform high-order singular entropy [J]. Advances in Mechanical Engineering, 2016, 8(7): 1-12.
[3] Jian Sun, Hongru Li, Baohua Xu. A degradation feature extraction method for hydraulic pumps based upon MUWDF and MF-DFA [J]. Journal of Failure Analysis and Prevention, 2016, 16(4): 583-593.
[4] 孙健, 李洪儒, 田再克. 基于敏感分量融合的液压泵退化特征提取方法[J]. 仪器仪表学报, 2016, 37(6): 1290-1298.
Jian Sun, Hongru Li, Zaike Tian. A degradation fault feature extraction method for hydraulic pumps based on fusion of sensitive components [J]. Chinese Journal of Scientific Instrument, 2016, 37(6): 1290-1298.
[5] Wensheng Chen, Xiuli Dai, Binbin Pan, et al. A novel discriminant criterion based on feature fusion strategy for face recognition [J]. Neurocomputering, 2015,159:67-77.
[6] Ying Zhang, Hongfu Zuo, Fang Bai. Classification of fault location and performance degradation of a roller bearing [J]. Measurement, 2013,46(3): 1178-1189.
[7] Jaouher Ben Ali, Lotfi Saidi, Aymen Mouelhi, et al. Linear feature selection and classification using PNN and SFAM neural networks for a nearly online diagnosis of bearing naturally progressing degradations [J]. Engineering Applications of Aritificial Intelligence, 2015, 42(1): 67-81.
[8] Maciej Tabaszewski, Czeslaw Cempel. Using a set of GM(1,1) models to predict values of diagnostic symptoms [J]. Mechanical Systems and Signal Processing, 2015, 52: 416-425.
[9] Tzu Li Tien. A research on the grey prediction modle GM(1, n) [J]. Applied Mathematics and Computation, 2012, 218(9): 4903-4916.
[10] Jihong Yan, Chaozhong Guo, Xing Wang. A dynamic multi-scale Markov model based methodology for remaining life prediction [J]. Mechanical Systems and Signal Processing, 2011, 25(4): 1364-1376
[11] Mitchell Yuwono, Yong Qin, Jing Zhou, et al. Automatic bearing fault diagnosis using particle swarm clustering and hidden Markov model [J]. Engineering Applications of Artificial Intelligence, 2016, 47(1): 88-100.
[12] 严峰, 陈晓, 王新民, 等. 改进的离散小波-优化极限学习机在倾转旋翼机故障诊断中的应用[J]. 兵工学报, 2014, 35(11): 1914-1921.
YAN Feng, CHEN Xiao, WANG Xin-min, et al. Fault diagnosis of tiltrotor aircraft via improved discrete wavelet-OMELM [J]. ACTA ARMAMENTARII, 2014, 35(11): 1914-1921.
[13] Xinying Wang, Min Han. Online sequential extreme learning machine with kernels for nonstationary time series prediction [J]. Neurocomputing, 2014, 145: 90-97.
[14] Jaeger H, Hass H, Harnessing nonlinearity: predicting chaotic systems and saving energy in wireless communication, Science, 304(5667)(2004)78-80.
[15] Jaemann Park, Dongsoo Cho, Seunghyun Kim, et al. Utilizing online learning based on echo-state networks for the control of a hydraulic excavator [J]. Mechatronics, 2014, 24(8): 986-1000.
[16] Yingjie Liang, Wen Chen. A relative entropy method to measure non-exponential random data [J]. Physics Letters, Section A: General, Atomc and Solid State Physics, 2015, 379(3): 95-99.
[17] M.Zarinbal, M.H.Fazel Zarandi, I.B.Turksen. Relative entropy fuzzy c-means clustering. Information Science, 260(2014)74-97.
[18] Jian Sun, Hongru Li, Baohua Xu. The morphological undecimated wavelet decomposition – discrete cosine transform composite spectrum fusion algorithm and its application on hydraulic pumps [J]. Measurement, 2016, 94: 794-805.
[19] Shuxian Lun, Xianshuang Yao, Hongyun Qi, et al. A novel model of leaky integrator echo state network for time-series prediction [J]. Neurocomputing, 2015, 159(1): 58-66.
[20] 李丁园, 刘富, 乔俊飞. 一种基于脑网络的分层模块化回声状态网络[J]. 机械工程学报, 2015, 51(22): 128-134.
LI Dingyuan, LIU Fu, QIAO Junfei. A hierarchical modular echo state network based on brain networks [J]. Journal of Mechanical Engineering, 2015, 51(22): 128-134.
[21] 彭宇, 王建民, 彭喜元. 基于回声状态网络的时间序列预测方法研究[J]. 电子学报, 2010, 38(2A): 148-154.
PENG Yu, WANG Jianmin, PENG Xiyuan. Research on time series prediction with echo state networks [J]. ACTA Electronica Sinica, 2010, 38(2A): 148-154.
[22] Guangye Zhou, Chengren Li, Tingting Li, et al. Outer synchronization investigation between WS and NW small-world networks with difference node numbers [J]. Physica A: Statistical Mechanics and its Applications, 2016, 457: 506-513.
[23] Okan Erkaymaz, Mahmut Ozer. Impact of small-network topology on the conventional artificial neural network for the diagnosis of diabetes [J]. Chaos, Solitons and Fractals, 2016, 83(1): 178-185.
[24] Wentsao Pan, A new Fruit Fly Optimization Algorithm: Tacking the financial distress model as an example [J]. Knowledge-Based Systems, 2012, 26: 69-74.