[1]顾张清,黄清岩,任世锦,等.基于CELMDAN与IMOMEDA的微弱机械特征增强方法[J].常州大学学报(自然科学版),2025,37(03):75-86,92.[doi:10.3969/j.issn.2095-0411.2025.03.009]
 GU Zhangqing,HUANG Qingyan,REN Shijin,et al.Weak mechanical feature enhancement method combining CELMDAN with IMOMEDA[J].Journal of Changzhou University(Natural Science Edition),2025,37(03):75-86,92.[doi:10.3969/j.issn.2095-0411.2025.03.009]
点击复制

基于CELMDAN与IMOMEDA的微弱机械特征增强方法()
分享到:

常州大学学报(自然科学版)[ISSN:2095-0411/CN:32-1822/N]

卷:
第37卷
期数:
2025年03期
页码:
75-86,92
栏目:
计算机与信息工程
出版日期:
2025-05-28

文章信息/Info

Title:
Weak mechanical feature enhancement method combining CELMDAN with IMOMEDA
文章编号:
2095-0411(2025)03-0075-12
作者:
顾张清黄清岩任世锦郝国生
江苏师范大学 计算机科学与技术学院, 江苏 徐州 221116
Author(s):
GU Zhangqing HUANG Qingyan REN Shijin HAO Guosheng
School of Computer Science and Technology, Jiangsu Normal University, Xuzhou 221116, China
关键词:
微弱故障信号增强 改进的多点最优最小熵去卷积调整 自适应噪声完全集成局部均值分解 周期调制强度 煤矿提升机
Keywords:
weak mechanical signal enhancement improved multipoint optimal minimum entropy deconvolution adjusted complete ensemble local mean decomposition with adaptive noise periodic modulation intensity mine hoist
分类号:
TH 165
DOI:
10.3969/j.issn.2095-0411.2025.03.009
文献标志码:
A
摘要:
针对设备背景噪声影响机械故障检测的问题,提出一种融合自适应噪声完全集成局部均值分解(Complete Ensemble Local Mean Decomposition with Adaptive Noise, CELMDAN)与改进的多点最优最小熵去卷积调整(Improved Multipoint Optimal Minimum Entropy Deconvolution Adjusted, IMOMEDA )的微弱机械特征增强方法。该方法首先利用CELMDAN方法把复杂振动信号分解为多个单模态的乘积函数(Product Functions, PFs),解决了集成局部均值分解(Ensemble Local Mean Decomposition, ELMD)对信号施加噪声幅值和试错次数难以确定的问题。其次,提出一种具有鲁棒性较强、物理意义明确以及尺度不变性的周期调制强度(Periodic Modulation Intensity, PMI),以筛选出有效的PFs。接着,针对所选PFs中的噪声,提出IMOMEDA方法进行消除,该方法通过迭代估计最优模型参数,自适应地提取振动信号中的周期性故障瞬态特征,能够在频域中定位瞬态的谱峭度,从而抽取被背景噪声淹没的微弱故障特征。最后,以煤矿提升机为研究对象,设计了多种振动信号特征增强方法对比实验、机械运行状态诊断性能实验以及信号特征增强算法性能对比实验,多角度验证了本文方法的有效性。
Abstract:
To address the issue of equipment background noise degrading mechanical fault detection, a novel weak mechanical feature enhancement method was presented by combining complete ensemble local mean decomposition with adaptive noise(CELMDAN)with improved multipoint optimal minimum entropy deconvolution adjusted(IMOMEDA).Firstly, CELMDAN was utilized to decompose complex vibration signals into multiple single modal product functions(PFs), dealing with the problem of ensemble local mean decomposition(ELMD)difficult determination of noise amplitude imposed to signals and trial times. Secondly, a periodic modulation intensity(PMI)with strong robustness, clear physical meaning and scale invariance was proposed to screen out the effective PFs; then, the IMOMEDA method was proposed to eliminate the noise in the selected PFs. This method can adaptively extract periodic fault transient features from vibration signals by iteratively estimating the optimal model parameters, and the spectral kurtosis of transients in the frequency domain can be found. As a result, weak fault features submerged by background noise are effectively enhanced. The incipient fault related impact components can be the optimal IMOMEDA parameters. As a result, enhancement can be yielded in an iterative way. This method can locate the spectral kurtosis of transients in the frequency domain, thereby extracting weak fault features submerged by background noise. Finally, taking the coal mine hoist as the research object, we designed a variety of vibration signal feature enhancement method comparison experiments, mechanical operation state diagnosis performance experiments and signal feature enhancement algorithm comparison experiments, which verified the validity of this paper's method from multiple perspectives.

参考文献/References:

[1] BERROUCHE Y, VASHISHTHA G, CHAUHAN S, et al. Local damage detection in rolling element bearings based on a single ensemble empirical mode decomposition[J]. Knowledge-Based Systems, 2024, 301: 112265.
[2] YAO Q T, BING H K, ZHU G P, et al. A novel stochastic process diffusion model for wind turbines condition monitoring and fault identification with multi-parameter information fusion[J]. Mechanical Systems and Signal Processing, 2024, 214: 111397-111418.
[3] ALSHORMAN O, IRFAN M, ABDELRAHMAN R B, et al. Advancements in condition monitoring and fault diagnosis of rotating machinery: a comprehensive review of image-based intelligent techniques for induction motors[J]. Engineering Applications of Artificial Intelligence, 2024, 130: 107724-107742.
[4] CHANG X D, PENG Y X, ZHU Z C, et al. Breaking failure analysis and finite element simulation of wear-out winding hoist wire rope[J]. Engineering Failure Analysis, 2019, 95: 1-17.
[5] GUO J C, SHI Z Q, LI H Y, et al. Transient impulses enhancement based on adaptive multi-scale improved differential filter and its application in rotating machines fault diagnosis[J]. ISA Transactions, 2022, 120: 271-292.
[6] LUO J S, YU D J, LIANG M. Application of multi-scale chirplet path pursuit and fractional Fourier transform for gear fault detection in speed up and speed-down processes[J]. Journal of Sound and Vibration, 2012, 331(22): 4971-4986.
[7] GAI J B, SHEN J X, HU Y F, et al. An integrated method based on hybrid grey wolf optimizer improved variational mode decomposition and deep neural network for fault diagnosis of rolling bearing[J]. Measurement, 2020, 162: 107901-107913.
[8] FENG Z P, YU X N, ZHANG D, et al. Generalized adaptive mode decomposition for nonstationary signal analysis of rotating machinery: principle and applications[J]. Mechanical Systems and Signal Processing, 2020, 136: 106530-106545.
[9] 王增才, 王树梁, 任锴胜, 等. 基于EEMD的提升机天轮轴承故障诊断方法[J]. 煤炭学报, 2012, 37(4): 689-694.
[10] WANG L, LIU Z W, MIAO Q, et al. Complete ensemble local mean decomposition with adaptive noise and its application to fault diagnosis for rolling bearings[J]. Mechanical Systems and Signal Processing, 2018, 106: 24-39.
[11] CHEN Z Y, MAURICIO A, LI W H, et al. A deep learning method for bearing fault diagnosis based on cyclic spectral coherence and convolutional neural networks[J]. Mechanical Systems and Signal Processing, 2020, 140: 106683-106698.
[12] HAN M H, PAN J L. A fault diagnosis method combined with LMD, sample entropy and energy ratio for roller bearings[J]. Measurement, 2015, 76: 7-19.
[13] LIU W Y, GAO Q W, YE G, et al. A novel wind turbine bearing fault diagnosis method based on integral extension LMD[J]. Measurement, 2015, 74: 70-77.
[14] WANG C G, LI H K, OU J Y, et al. Identification of planetary gearbox weak compound fault based on parallel dual-parameter optimized resonance sparse decomposition and improved MOMEDA[J]. Measurement, 2020, 165: 108079-108093.
[15] MIAO Y H, ZHAO M, LIN J, et al. Application of an improved maximum correlated kurtosis deconvolution method for fault diagnosis of rolling element bearings[J]. Mechanical Systems and Signal Processing, 2017, 92: 173-195.
[16] WANG Z J, DU W H, WANG J Y, et al. Research and application of improved adaptive MOMEDA fault diagnosis method[J]. Measurement, 2019, 140: 63-75.
[17] ZHAO M, JIA X D. A novel strategy for signal denoising using reweighted SVD and its applications to weak fault feature enhancement of rotating machinery[J]. Mechanical Systems and Signal Processing, 2017, 94: 129-147.
[18] 唐贵基, 曾鹏飞, 朱爽. 基于ASMVMD和MOMEDA的齿轮特征提取方法[J]. 机电工程, 2024, 41(12): 2174-2184.
[19] FENG Y, ZHANG X F, JIANG H, et al. Compound fault diagnosis of a wind turbine gearbox based on MOMEDA and parallel parameter optimized resonant sparse decomposition[J]. Sensors(Basel, Switzerland), 2022, 22(20): 8017.
[20] QUISPE J C, MORALES J, ORDUNA E, et al. Time-frequency multiresolution of fault-generated transient signals in transmission lines using a morphological filter[J]. Protection and Control of Modern Power Systems, 2023, 8: 22.
[21] SUN Y, LI S C, GAO H L, et al. Transfer learning: a new aerodynamic force identification network based on adaptive EMD and soft thresholding in hypersonic wind tunnel[J]. Chinese Journal of Aeronautics, 2023, 36(8): 351-365.
[22] MOBKI H, NIA E S. Condition monitoring of a 3-phase electromotor with early-stage fault based on EMD and CEEMDAN analysis of current signal[J]. Journal of Failure Analysis and Prevention, 2024, 24(5): 2432-2454.
[23] 牛一捷, 李花, 邓武, 等. 基于TQWT和稀疏表示的滚动轴承故障诊断方法[J]. 交通运输工程学报, 2021, 21(6): 237-246.
[24] ZHANG T, TIAN J, XUE Z F, et al. A novel feature extraction method based on TQWT and instantaneous energy variation for Parkinson's disease detection[J]. Biomedical Signal Processing and Control, 2023, 85: 105087.
[25] LI Y B, XU M Q, WEI Y, et al. Rotating machine fault diagnosis based on intrinsic characteristic-scale decomposition[J]. Mechanism and Machine Theory, 2015, 94: 9-27.
[26] CHEN T Q, GUESTRIN C. XGBoost: a scalable tree boosting system[C]//Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. San Francisco:ACM, 2016: 785-794.
[27] SCHAPIRE R E. The strength of weak learnability[J]. Machine Learning, 1990, 5(2): 197-227.
[28] 黄智濒. 现代决策树模型及其编程实践: 从传统决策树到深度决策树[M]. 北京: 机械工业出版社, 2022.
[29] WANG D H, ZHANG Y, ZHAO Y. LightGBM: an effective miRNA classification method in breast cancer patients[C]//Proceedings of International Conference on Computational Biology and Bioinformatics. New York: ACM, 2017: 7-11.

备注/Memo

备注/Memo:
收稿日期: 2024-11-16。
作者简介: 顾张清(2001—),男,江苏南通人,硕士生。通信联系人:任世锦(1971—),316588499@qq.com
更新日期/Last Update: 1900-01-01