Fault Diagnosis Method of Hydropower Units Based on Time-shifted Multiscale Fluctuation Dispersion Entropy and Improved Kernel Extreme Learning Machine

被引：0
|
作者：
Xu Z. [1 ]
Liu T. [1 ]
Ren S. [1 ]
Chen J. [1 ]
Wu F. [1 ]
Wang B. [1 ]
机构：
[1] School of Water Conservancy and Civil Eng., Northwest A & F Univ., Yangling
来源：
Gongcheng Kexue Yu Jishu/Advanced Engineering Sciences | 2024年 / 56卷 / 03期
关键词：
arithmetic optimization algorithm; fault diagnosis; hydropower units; kernel extreme learning machine; time-shifted multiscale fluctuation dispersion entropy;
D O I：
10.12454/j.jsuese.202200843
中图分类号：
学科分类号：
摘要：
Hydropower plays an important role in the reform of energy supply structure. With the continuous access of new energy sources such as wind, light and tide, the load operation range of hydropower units is widening, which leads to the increase of the probability of accidents of hydropower units. Therefore, it is of great practical significance to carry out the research on intelligent fault diagnosis of hydropower units. In this paper, aiming at the problem that the vibration signal of hydropower unit contains a large number of noise signals and interferes with fault diagnosis, a fault diagnosis method of hydropower unit based on time-shifted multi-scale fluctuation dispersion entropy and improved kernel extreme learning machine is proposed. Firstly, based on the multi-scale fluctuation dispersion entropy, the time-shift theory is used to replace the traditional coarse-grained process in the multiscale fluctuation dispersion entropy (MFDE), and the time-shift multiscale fluctuation dispersion entropy (TSMFDE) is proposed by combining the information entropy theory and the time-shift idea. Through simulation experiments, it is proved that the proposed method has good timing length robustness, noise resistance and feature extraction ability, and overcomes the problem of insufficient coarse–grained of traditional multi-scale entropy. Then, the arithmetic optimization algorithm (AOA) with strong portability, strong optimization ability and fast convergence speed is used to optimize the regularization parameters and kernel function parameters of kernel based extreme learning machine (KELM), and the AOA–KELM classifier is established to overcome the problem that the hyperparameters of KELM are difficult to adjust. Finally, through the simulation experiment of the rotor test bench, the features extracted by TSMFDE are input into the classifier to complete the pattern recognition work. The simulation results show that the proposed model achieves the highest diagnostic accuracy, reaching 100.0%. Compared with other popular models, the proposed model shows obvious advantages, which verifies that the proposed model has good diagnostic accuracy. © 2024 Sichuan University. All rights reserved.
引用
收藏
页码：41 / 51
页数：10
相关论文
共 27 条
  • [1] Yongjun Tang, Liu Dong, Xiao Zhihuai, Et al., Fault diagnosis of hydropower units based on convolutional neural network and singular value decomposition[J], China Rural Water and Hydropower, 2021, 2, pp. 175-181
  • [2] Gu Cheng, Xinyong Qiao, Huaying Li, Et al., Misfire fault diagnosis method for diesel engine based on MEMD and dispersion entropy[J], Shock and Vibration, pp. 1-14, (2021)
  • [3] He Kuidong, Chen Jia, Jin Yan, Et al., Application of EEMD multi-scale entropy and ELM in feature extraction of vibration signal of hydropower unit[J], China Rural Water and Hydropower, 2021, 5, pp. 176-182
  • [4] He Yangyang, Jia Rong, Li Hui, Et al., Vibration fault diagnosis of hydropower unit by using stochastic resonance and multidimensional permutation entropy[J], Journal of Hydroelectric Engineering, 34, 12, pp. 123-130, (2015)
  • [5] Azami H, Escudero J., Amplitude-and fluctuation–based dispersion entropy[J], Entropy, 20, 3, (2018)
  • [6] Azami H, Arnold S E, Sanei S, Et al., Multiscale fluctuation–based dispersion entropy and its applications to neurological diseases[J], IEEE Access, 7, pp. 68718-68733, (2019)
  • [7] Pham Tuan D., Time–shift multiscale entropy analysis of physiological signals[J], Entropy, 19, 6, (2017)
  • [8] Zhixin Fu, Gui Yin, Junpeng Zhu, Et al., Research on forecasting method of hydropower unit deterioration based on eemd and lstm[J], Acta Energiae Solaris Sinica, 43, 2, pp. 75-81, (2022)
  • [9] Xiyang Chen, Haiqiao Yan, Jianping Sun, Application of EMD–FFT in analyzing the vibration signals of hydro–generator units[J], Water Power, 40, 5, pp. 51-54, (2014)
  • [10] Xiaoyue Chen, Ge Dang, Huang Jiangping, Et al., The bionic intelligent fault diagnosis based on comprehensive differences mining for hydro turbine[J], Journal of Mechanical Strength, 42, 6, pp. 1271-1276, (2020)
123