
浏览全部资源
扫码关注微信
1.河南农业职业学院机电工程系,郑州 451450
2.河南农业大学机电工程学院,郑州 451450
卢云飞,男,1983年生,河南洛阳人,硕士,讲师;主要研究方向为农业装备智能化、轴承故障诊断;lu_yyff@sina.com。
余泳昌(通信作者),男,1965年生,河南新郑人,博士,教授;主要研究方向为农业机械化及农业装备智能化、轴承故障诊断;yilushun168168@126.com。
收稿:2026-04-07,
修回:2026-06-15,
录用:2026-06-16,
网络首发:2026-10-13,
移动端阅览
卢云飞,余泳昌,王煜,等.基于改进EWT算法的农机设备滚动轴承故障诊断[J].机械传动,XXXX,XX(XX):1-9.
LU Yunfei,U Yongchang,WANG Yu,et al.Rolling bearing fault diagnosis of agricultural machinery equipment based on the improved EWT algorithm[J].Journal of Mechanical Transmission,XXXX,XX(XX):1-9.
目的
2
针对农机设备滚动轴承低速重载工况下振动信号频带划分易受低频背景能量干扰、故障诊断精度与稳定性下降的问题,提出一种谱平滑与低频能量增强协同优化的改进经验小波变换(Smoothed Energy-Weighted Empirical Wavelet Transform
SEW-EWT)算法。
方法
2
首先,对原始信号进行傅里叶变换获取幅值谱,采用高斯核卷积平滑抑制高频随机尖峰,基于平滑谱局部极值初定频带边界,引入能量比例阈值剔除低能量伪分段,提升频带划分稳定性;其次,在保持滤波器组能量守恒前提下,构造低频加权增强函数,对低频区间赋予更高权重,强化弱冲击特征的模态能量占比,实现关键分量自适应纯化;然后,选取有效模态进行希尔伯特变换并提取包络谱特征,为故障状态判别提供输入;最后,基于包含4种运行状态的滚动轴承试验数据集验证算法诊断性能。
结果
2
结果表明,SEW-EWT的精确率、召回率与F1-score分别达97.2%、97.8%和97.5%,较传统EWT提升约3.8%;误差均方值稳定在0.03左右,较基线方法下降约30%;识别准确率均值达97.75%,标准差降至0.58%,较EWT降低约66.3%;与主流诊断方法相比,整体准确率高出3.25~8.0个百分点,各类故障识别表现均衡。该算法可提升低速工况下轴承故障特征可辨识性与诊断一致性,为农机设备滚动轴承状态监测提供参考。
Objective
2
Under low-speed and heavy-load conditions
the frequency band division of vibration signals of rolling bearings in agricultural machinery equipment is easily disturbed by low-frequency background energy
which reduces the accuracy and stability of fault diagnosis. To solve this problem
an improved empirical wavelet transform (SEW-EWT) algorithm with collaborative optimization of spectral smoothing and low-frequency energy enhancement was proposed.
Methods
2
Firstly
the amplitude spectrum was obtained by Fourier transform of the original signal. Gaussian kernel convolution smoothing was adopted to suppress high-frequency random spikes. The frequency band boundaries were initially determined based on local extrema of the smoothed spectrum
and an energy proportion threshold was introduced to eliminate low-energy pseudo-segments
so as to improve the stability of frequency band division. Secondly
on the premise of maintaining the energy conservation of the filter bank
a low-frequency weighted enhancement function was constructed. Higher weights were assigned to the low-frequency interval to strengthen the modal energy proportion of weak impact features and realize adaptive purification of key components. Then
Hilbert transform was performed on the selected effective modes and envelope spectrum features were extracted to provide input for fault state discrimination. Finally
the diagnostic performance of the algorithm was verified based on a rolling bearing test dataset containing 4 operating states.
Results
2
The results show that the precision
recall and F1-score of SEW-EWT reach 97.2%
97.8% and 97.5% respectively
which are about 3.8% higher than those of traditional EWT. The mean square error is stable at about 0.03
which is about 30% lower than that of the baseline method. The average recognition accuracy reaches 97.75%
and the standard deviation drops to 0.58%
which is about 66.3% lower than that of EWT. Compared with mainstream diagnostic methods
the overall accuracy is 3.25 to 8.0 percentage points higher
with balanced recognition performance for various faults. This algorithm can improve the identifiability of bearing fault features and diagnostic consistency under low-speed conditions
and provides reference for condition monitoring of rolling bearings in agricultural machinery equipment.
Xie F Y , Sun E G , Wang L L , et al . Rolling bearing fault diagnosis in agricultural machinery based on multi-source locally adaptive graph convolution [J]. Agriculture , 2024 , 14 ( 8 ): 1333 .
Xie F Y , Wang Y , Wang G , et al . Fault diagnosis of rolling bearings in agricultural machines using SVD-EDS-GST and ResViT [J]. Agriculture , 2024 , 14 ( 8 ): 1286 .
黎会鹏 , 徐波 , 黄璞 . 一种自适应的机械振动信号变分模态分析方法 [J]. 电子测量技术 , 2025 , 48 ( 8 ): 116 - 125 .
Li Huipeng , Xu Bo , Huang Pu . An adaptive variational mode analysis method for mechanical vibration signals [J]. Electronic Measurement Technology , 2025 , 48 ( 8 ): 116 - 125 .
李占龙 , 刘林霞 , 李虹 , 等 . 基于VMD-Teager的非平稳振动时频特性研究 [J]. 兵器装备工程学报 , 2021 , 42 ( 1 ): 150 - 156 .
Li Zhanlong , Liu Linxia , Li Hong , et al . Research on time-frequency characteristics of non-stationary vibration based on VMD-teager [J]. Journal of Ordnance Equipment Engineering , 2021 , 42 ( 1 ): 150 - 156 .
苏泓臣 , 杨辰昕 , 边豪杰 , 等 . 基于自适应经验小波变换的轴承故障诊断研究 [J]. 核科学与工程 , 2025 , 45 ( 3 ): 510 - 518 .
Su Hongchen , Yang Chenxin , Bian Haojie , et al . Study on bearing fault diagnosis based on the improved empirical wavelet transform [J]. Nuclear Science and Engineering , 2025 , 45 ( 3 ): 510 - 518 .
Lv Y C , Wang J Y , Zhang C Q , et al . Composite fault feature extraction for gears based on MCKD-EWT adaptive wavelet threshold noise reduction [J]. Measurement and Control , 2025 , 58 ( 2 ): 185 - 195 .
Chen Q , Zheng S , Wu X , et al . Feature extraction of bearing weak fault based on sparse coding theory and adaptive EWT [J]. Applied Sciences , 2022 , 12 ( 21 ): 10807 .
Gao Z Q , Zheng J D , Pan H Y , et al . Translational Gaussian wavelet transform and its application to the fault diagnosis of rolling bearing [J]. Nonlinear Dynamics , 2025 , 113 ( 20 ): 27483 - 27499 .
李继猛 , 王慧 , 李铭 , 等 . 基于改进的自适应无参经验小波变换的滚动轴承故障诊断 [J]. 计量学报 , 2020 , 41 ( 6 ): 710 - 716 .
Li Jimeng , Wang Hui , Li Ming , et al . Rolling bearing fault diagnosis based on improved adaptive parameterless empirical wavelet transform [J]. Acta Metrologica Sinica , 2020 , 41 ( 6 ): 710 - 716 .
谢俊文 , 童靳于 , 郑近德 , 等 . 变转速极低标签率下旋转机械故障诊断的图注意力网络 [J]. 振动与冲击 , 2024 , 43 ( 19 ): 242 - 248 .
Xie Junwen , Tong Jinyu , Zheng Jinde , et al . Entropy-graph attention network for semi-supervised fault diagnosis of rotating machinery under extremely low label rate and variable rotating speed conditions [J]. Journal of Vibration and Shock , 2024 , 43 ( 19 ): 242 - 248 .
Xiao L , Yang X X , Yang X D . A graph neural network-based bearing fault detection method [J]. Scientific Reports , 2023 , 13 : 5286 .
陈丽芳 , 曹柯欣 , 张思鹏 , 等 . 群智能优化算法最新进展 [J]. 计算机工程与应用 , 2024 , 60 ( 19 ): 46 - 67 .
Chen Lifang , Cao Kexin , Zhang Sipeng , et al . Recent progress of swarm intelligent optimization algorithms [J]. Computer Engineering and Applications , 2024 , 60 ( 19 ): 46 - 67 .
袁峰 , 纪鑫 , 陈勇军 , 等 . SVD-EWT方法在滚动轴承故障信号分析中的应用 [J]. 煤矿机械 , 2025 , 46 ( 2 ): 175 - 179 .
Yuan Feng , Ji Xin , Chen Yongjun , et al . Application of SVD-EWT method in rolling bearing fault signal analysis [J]. Coal Mine Machinery , 2025 , 46 ( 2 ): 175 - 179 .
王丛丛 , 马清悦 . 一种融合多策略改进粒子群算法结合EWT的轴承故障诊断方法 [J]. 机电工程 , 2026 , 43 ( 1 ): 82 - 91 .
Wang Congcong , Ma Qingyue . A bearing fault diagnosis method integrating a multi-strategy enhanced particle swarm algorithm with EWT [J]. Journal of Mechanical & Electrical Engineering Magazine , 2026 , 43 ( 1 ): 82 - 91 .
Zhang R J , Li R , Liu C , et al . Fault diagnosis method for wind turbine rolling bearings based on adaptive deep learning [J]. Journal of Vibroengineering , 2025 , 27 ( 6 ): 957 - 977 .
Zhu J , Li O , Chen M H , et al . Fault diagnosis of wind turbine rolling bearings based on DCS-EEMD-SSA [J]. Journal of Failure Analysis and Prevention , 2024 , 24 ( 5 ): 2495 - 2508 .
何晓良 , 苏春 , 张玉茹 . 基于改进VMD和SVM方法的滚动轴承故障诊断 [J]. 东南大学学报(自然科学版) , 2026 , 56 ( 2 ): 322 - 332 .
He Xiaoliang , Su Chun , Zhang Yuru . Fault diagnosis for rolling bearing based on improved VMD and SVM [J]. Journal of Southeast University (Natural Science Edition) , 2026 , 56 ( 2 ): 322 - 332 .
Wang B , Wang X Q . IMSB and 1D-CNN fusion for rolling bearing fault diagnosis under rotational frequency interference [J]. Engineering Research Express , 2026 , 8 ( 3 ): 035222 .
Lai S J , Cheung T H , Fung K C , et al . Fault diagnosis of rolling bearings using denoising multi-channel mixture of CNN and mamba-enhanced adaptive self-attention LSTM [J]. Sensors , 2025 , 25 ( 21 ): 6652 .
Peng L H , Liu F , Lv Z L , et al . Phoneme-inspired acoustic frame embedded lightweight transformer for rolling bearing fault diagnosis [J]. Mechanical Systems and Signal Processing , 2026 , 248 : 114030 .
0
浏览量
3
下载量
0
CSCD
关联资源
相关文章
相关作者
相关机构
京公网安备11010802024621