Next Article in Journal
Comparison and Ranking of Metaheuristic Techniques for Optimization of PI Controllers in a Machine Drive System
Previous Article in Journal
Natural Versus Anthropic Influence on North Adriatic Coast Detected by Geochemical Analyses
Previous Article in Special Issue
Planetary Gearbox Fault Diagnosis Based on ICEEMD-Time-Frequency Information Entropy and VPMCD
Open AccessArticle

Degradation State Recognition of Piston Pump Based on ICEEMDAN and XGBoost

by Rui Guo 1,2,*, Zhiqian Zhao 1,3, Tao Wang 1,4, Guangheng Liu 1,4, Jingyi Zhao 2,4 and Dianrong Gao 3
1
Hebei Provincial Key Laboratory of Heavy Machinery Fluid Power Transmission and Control, Yanshan University, Qinhuangdao 066004, China
2
The State Key Laboratory of Fluid Power and Mechatronic Systems, Zhejiang University, Hangzhou 310027, China
3
Key Laboratory of Advanced Forging and Stamping Technology and Science, Yanshan University, Qinhuangdao 066004, China
4
Hebei Key Laboratory of Special Delivery Equipment Yanshan University, Qinhuangdao 066004, China
*
Author to whom correspondence should be addressed.
Appl. Sci. 2020, 10(18), 6593; https://doi.org/10.3390/app10186593
Received: 15 August 2020 / Revised: 16 September 2020 / Accepted: 17 September 2020 / Published: 21 September 2020
(This article belongs to the Special Issue Advances in Machine Fault Diagnosis)
Under different degradation conditions, the complexity of natural oscillation of the piston pump will change. Given the difference of the characteristic values of the vibration signal under different degradation states, this paper presents a degradation state recognition method based on improved complete ensemble empirical mode decomposition with adaptive noise (ICEEMDAN) and eXtreme gradient boosting (XGBoost) to improve the accuracy of state recognition. Firstly, ICEEMDAN is proposed to alleviate the mode mixing phenomenon, which decomposes the vibration signal and obtain the intrinsic mode functions (IMFs) with less noise and more physical meaning, and subsequently the optimal IMF is found by using the correlation coefficient method. Then, the time domain, frequency domain, and entropy of the effective IMF are calculated, and the new characteristic values which can represent the degradation state are selected by principal component analysis (PCA) that it realizes dimension reduction. Finally, the above-mentioned characteristic indexes are used as the input of the XGBoost algorithm to achieve the recognition of the degradation state. In this paper, the vibration signals of four different degradation states are generated and analyzed through the piston pump slipper degradation experiment. By comparing the proposed method with different state recognition algorithms, it can be seen that the method based on ICEEMDAN and XGBoost is accurate and efficient, the average accuracy rate can reach more than 99%. Therefore, this method can more accurately describe the degradation state of the piston pump and has a highly practical application value. View Full-Text
Keywords: piston pump; degraded state recognition; slipper; improved complete ensemble empirical mode decomposition with adaptive noise; principal component analysis; eXtreme gradient boosting piston pump; degraded state recognition; slipper; improved complete ensemble empirical mode decomposition with adaptive noise; principal component analysis; eXtreme gradient boosting
Show Figures

Figure 1

MDPI and ACS Style

Guo, R.; Zhao, Z.; Wang, T.; Liu, G.; Zhao, J.; Gao, D. Degradation State Recognition of Piston Pump Based on ICEEMDAN and XGBoost. Appl. Sci. 2020, 10, 6593.

Show more citation formats Show less citations formats
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Search more from Scilit
 
Search
Back to TopTop