Fault diagnosis of one-way valve of high-pressure diaphragm pump based on CEEMDAN multi-scale permutation entropy and SO-RELM
LI Rui1,2, FAN Yugang1,2
1.College of Information Engineering&Automation, Kunming University of Science and Technology, Kunming 650500, China;
2.Yunnan Provincial Key Lab of Artificial Intelligence, Kunming 650500, China
Abstract:The check valve of high-pressure diaphragm pump is affected by load, friction, impact and other factors, and the vibration signal generated by operation is non-stationary and nonlinear. In order to extract the nonlinear dynamic characteristics of equipment from the vibration signal, multi-scale permutation entropy (MPE) is introduced into the fault diagnosis of check valve of high-pressure diaphragm pump.The multi-scale permutation entropy feature of vibration signal is extracted to establish the fault diagnosis model of structure optimization regularized extreme learning machine (SO-RELM). The model uses K-means to optimize the RELM structure and improve the accuracy and stability of model recognition. Firstly, adaptive complementary ensemble empirical mode decomposition with adaptive noise (CEEMDAN) is used to adaptively decompose the vibration signal of high-pressure diaphragm pump check valve into multiple intrinsic mode functions (IMF), taking the correlation coefficient as the index, the components with rich fault characteristic information are preferred; Then, the multi-scale permutation entropy of IMFs is calculated to extract the nonlinear dynamic characteristics of the signal; Finally, based on multi-scale permutation entropy, a fault diagnosis model based on SO-RELM is established.The experimental results show that CEEMDAN multi-scale permutation entropy can accurately characterize the nonlinear dynamic characteristics of the operation state of the check valve of the high-pressure diaphragm pump. The SO-RELM fault model based on CEEMDAN multi-scale permutation entropy can effectively identify the working condition type of the check valve of the high-pressure diaphragm pump, and the accuracy is 98.89%.
李瑞1,2,范玉刚1,2. 基于CEEMDAN多尺度排列熵和SO-RELM的高压隔膜泵单向阀故障诊断[J]. 振动与冲击, 2023, 42(5): 127-135.
LI Rui1,2, FAN Yugang1,2. Fault diagnosis of one-way valve of high-pressure diaphragm pump based on CEEMDAN multi-scale permutation entropy and SO-RELM. JOURNAL OF VIBRATION AND SHOCK, 2023, 42(5): 127-135.
[1] 牟竹青,黄国勇,吴建德,等. 基于DEMD的高压隔膜泵单向阀早期故障诊断[J]. 振动•测试与诊断,2018,38(04): 758-764+873.
MOU Zhu-qing, HUANG Guo-yong, WU Jian-de,et al.Early fault diagnosis of high pressure diaphragm pump check valve based on differential empirical mode decomposition[J]. Journal of Vibration, Measurement & Diagnosis,2018,38(04):758-764+ 873
[2] 周成江. 矿浆管道输送系统的隔膜泵单向阀故障诊断研究[D]. 昆明理工大学,2020.
[3] ZHOU C J, MA J, WU J D. Research on fault diagnosis of check valve based on CEEMD compound screening and improved SECPSO[J]. Journal of Computers,2019,30 (5): 128-144.
[4] WEI X Y,ZHENG W.An integrated approach for fetal heart rate estimation from abdominal electrocar diogram signal [J].Chinese Journal of Electronics, 2019,28(06):1198-1203.
[5] ZHAO Y, ZHANG H W. Displacement measurement method based on laser self-mixing interference in the presence of speckle [J].Chinese Optics Letters,2020, 18(05):15-19.
[6] 王亚萍,匡宇麒,葛江华,等. CEEMD和小波半软阈值相结合的滚动轴承降噪[J]. 振动•测试与诊断,2018,38(01): 80-86+207.
WANG Ya-ping, KUANG Yu-qi, GE Jiang-hua, et al. Fauit diagnosis of bearings combining OEEMD with teager energy operator demodulation[J]Journal of Vibration,Measurement & Diagnosis, 2018, 38(01): 80-86+207.
[7] 董利超,郭兴明,郑伊能. 基于CEEMD的心音信号小波包去噪算法研究[J].振动与冲击,2019,38(09): 192-198+222.
DONG Li-chao, GUO Xing-ming, ZHENG Yi-neng. Wavelet packet de-noising algorithm for heart sound signals based on CEEMD[J]. Journal of vibration and shock, 2019,38(09): 192-198+222.
[8] 蒋玲莉,谭鸿创,李学军,等. 基于CEEMDAN排列熵与SVM的螺旋锥齿轮故障识别[J].振动•测试与诊断,2021,41(01): 33-40+198-199.
JIANG Lin-li, TAN Hong-chuang, LI Xue-jun,et al. Cutting life model of hollow shaft based on dual-frequency vibration system[J]. Journal of Vibration, Measurement & Diagnosis, 2021, 41(01): 33-40+198-199.
[9] VANRAJ S, DHAMI S, PABLA B S. Non-contact incipient fault diagnosis method of fixed-axis gearbox based on CEEMDAN[J]. Royal Society Open Science, 2017,4(8): 2054-2073.
[10] ZHANG J C, REN W K, JIN N D. Rescaled Range Permutation Entropy: A Method for Quantifying the Dynamical Complexity of Extreme Volatility in Chaotic Time Series[J].Chinese Physics Letters,2020, 37(09): 30-35.
[11] Li Y J, ZHNG W H, QING X. A rolling bearing fault diagnosis strategy based on improved multiscale permutation entropy and least squares SVM[J]. Journal of Mechanical Science and Technology,2017, 31(6):2711-2722.
[12] 刘备,胡伟鹏,邹孝,等. 基于变分模态分解与多尺度排列熵的生物组织变性识别[J].物理学报,2019,68(02): 259-267.
LIU Bei, HU Wei-peng, ZOU Xiao, et al. Recognition of denatured biological tissue based on variational mode decomposition and multi-scale permutation entropy[J]. Acta Phys. Sin, 2019,68(02):259-267.
[13] 谭鸿创,杨大炼,蒋玲莉,等. 基于MPE局部保持投影与ELM的螺旋锥齿轮故障诊断[J].电子测量与仪器学报,2020,34(02): 44-52.
TAN Hong-chuang,YANG Da-lian,JIANG Lin-li,et al. Fault diagnosis of spiral bevel gear based on MPE locality preserving projections and ELM[J]. Journal of electronic measurement and instrumentation,2020, 34(02): 44-52.
[14] 董治麟,郑近德,潘海洋,等.一种时移多尺度排列熵与ELM相结合的滚动轴承故障诊断方法[J].机械科学与技术,2021,40(10): 1523-1529.
DONG Zhi-lin, ZHENG Jin-de, PAN Hai-yang,et al. A Rolling Bearing Fault Diagnosis Method of Time-shifted Multi-scale Permutation Entropy Combining with ELM[J].Mechanical Science and Technology for Aerospace Engineering,2021,40(10): 1523-1529.
[15] WANG X S, ZHAO J J, CHENG Y H, et al.Joint Feature Representation and Classifier Learning Based Unsupervised Domain Adaption ELM[J].Chinese Journal of Electronics, 2021, 30(01): 109-118.
[16] YU T J, YAN X F. Robust multi-layer extreme learning machine using bias-variance tradeoff[J]. Journal of Central South University,2020,27(12): 3744-3753.
[17] PENG T, ZHANG C, ZHOU J Z. Negative correlation learning-based RELM ensemble model integrated with OVMD for multi-step ahead wind speed forecasting[J]. Renewable Energy,2020,156(3): 804- 819.
[18] XIA R F, CHEN Y F, FENG Y J. A Method to Measure Thermal Conductivity of Vacuum Insulation Panel Using Enhanced Extreme Learning Machine Model[J]. Journal of Thermal Science,2020,29(03): 623-631.
[19] FANGY H, CHEN H S, LIN Y, et al. Classification of northeast China cold vortex activity paths in early summer based on K-means clustering and their climate impact[J].Advances in Atmospheric Sciences,2021,38(03): 400-412.
[20] 陈寿宏,易木兰,张雨璇,等. 基于优化DBSCAN聚类算法的晶圆图预处理[J].控制与决策,2021,36(11): 2713-2721.
CHEN Shou-hong, YI Mu-lan, ZHANG Yu-xuan,et al. Wafer map preprocessing based on optimized DBSCAN clustering algorithm[J].Control and Decision,2021,36(11): 2713-2721.
[21] 潘震,黄国勇,吴漫. 基于参数优化VMD和增强多尺度排列熵的单向阀故障诊断[J]. 振动与冲击,2020,39(15): 118-125.
PAN Zhen, HUANG Guo-yong, WU Man. Check valve fault diagnosis based on VMD parametric optimization and enhanced multi-scale permutation entropy[J].Journal of vibration and shock, 2020, 39(15): 118-125.
[22] YU H Y,XU Z,WANG Y L,et al. The use of KPCA over subspaces for cross-scale superpixel based hyperspectral image classification[J].Remote Sensing Letters,2021,12(5):470-477.