Rolling bearing fault diagnosis is critical for rotating machinery safety, but weak fault characteristics are often buried in background noise, complicating feature extraction and fault diagnosis. This study proposes a novel diagnosis method integrating a tunable spiral spring coupling device (TSSCD) for feature enhancement and a convolutional neural network (CNN) for classification. The TSSCD comprises a spiral spring, coaxial repelling magnets, and a tuning mechanism. By adjusting the magnet distance, its resonant frequency is tuned to match the bearing’s fault characteristic frequency, amplifying weak fault signals while suppressing high-frequency noise. The theoretical model of the TSSCD, encompassing the spiral spring’s linear stiffness and magnetic repulsion, is established and experimentally validated. Results show its natural frequency tunable from 103 to 135 Hz, with good agreement between theory and experiments. The TSSCD was then mounted on a rolling bearing experimental rig to collect signals under four types of test bearings. TSSCD-enhanced and raw signals were input into a simplified CNN. The CNN achieved 99.51% average accuracy with enhanced signals, 3.17% higher than the 96.34% accuracy with raw signals. This method eliminates the need for complex traditional feature extraction, features easy TSSCD installation, and exhibits strong robustness, providing a new way to integrate physical vibration control with deep learning for high-precision fault diagnosis.
XuYDZhenDGuJX, et al. Autocorrelated envelopes for early fault detection of rolling bearings. Mech Syst Signal Process2021; 146: 30.
2.
LvMYanCFKangJX, et al. Multiple faults separation and identification of rolling bearings based on time-frequency spectrogram. Struct Health Monit2024; 23: 2040–2067.
3.
LeiYGJiaFLinJ, et al. An intelligent fault diagnosis method using unsupervised feature learning towards mechanical big data. IEEE Trans Ind Electron2016; 63: 3137–3147.
4.
MallaCPanigrahiI.Review of condition monitoring of rolling element bearing using vibration analysis and other techniques. J Vib Eng Technol2019; 7: 407–414.
5.
ZhouPLuSLLiuF, et al. Novel synthetic index-based adaptive stochastic resonance method and its application in bearing fault diagnosis. J Sound Vib2017; 391: 194–210.
6.
GlowaczAGlowaczWGlowaczZ, et al. Early fault diagnosis of bearing and stator faults of the single-phase induction motor using acoustic signals. Measurement2018; 113: 1–9.
7.
ZhangWLiCHPengGL, et al. A deep convolutional neural network with new training methods for bearing fault diagnosis under noisy environment and different working load. Mech Syst Signal Process2018; 100: 439–453.
8.
XuGJHouDMQiHY, et al. High-speed train wheel set bearing fault diagnosis and prognostics: a new prognostic model based on extendable useful life. Mech Syst Signal Process2021; 146: 107050.
9.
OttewillJROrkiszM.Condition monitoring of gearboxes using synchronously averaged electric motor signals. Mech Syst Signal Process2013; 38: 482–498.
10.
ZhengJDPanHYTongJY, et al. Generalized refined composite multiscale fuzzy entropy and multi-cluster feature selection based intelligent fault diagnosis of rolling bearing. ISA Trans2022; 123: 136–151.
11.
ZhangMJiangZNFengK.Research on variational mode decomposition in rolling bearings fault diagnosis of the multistage centrifugal pump. Mech Syst Signal Process2017; 93: 460–493.
12.
YanRQGaoRXChenXF.Wavelets for fault diagnosis of rotary machines: a review with applications. Signal Process2014; 96: 1–15.
13.
GuJPengYXLuH, et al. An optimized variational mode decomposition method and its application in vibration signal analysis of bearings. Struct Health Monit2022; 21: 2386–2407.
14.
ZhangCLZhuRHTuZS, et al. Weak signal enhancement and extraction based on hybrid resonant sparse decomposition and tri-stable stochastic resonance method. Mech Syst Signal Process2025; 224: 112210.
15.
ZhangCLZhuRHTuZS, et al. A novel second-order tri-stable stochastic resonance system with synchronized potential-well width-depth variation and its application. Chaos Soliton Fract2025; 201: 117394.
16.
ZhangCLLaiZHZhaoYF, et al. Parametric study and multi-parameter optimization of a generalized second-order tri-stable stochastic resonance system. Nonlinear Dyn2024; 112: 2661–2681.
17.
ZhengXXXuHS. Fault diagnosis of wind turbine rolling bearing based on wavelet and hilbert transforms. In: Proceedings of the 31st Chinese control conference, Hefei, China, 25–27 July 2012, pp. 5290–5293. New York, NY: IEEE.
18.
ZanTPangZLWangM, et al. Research on early fault diagnosis of rolling bearing based on VMD. In: 2018 6TH International conference on mechanical, automotive and materials engineering (CMAME), 10–12 October 2018, pp. 41–45. New York, NY: IEEE.
19.
WenCZhouCD.The feature extraction of rolling bearing fault based on wavelet packet-EMD energy distribution. Fluid Dyn Mech Electr Control Eng2012; 233: 234–238.
20.
Ben AliJFnaiechNSaidiL, et al. Application of empirical mode decomposition and artificial neural network for automatic bearing fault diagnosis based on vibration signals. Appl Acoust2015; 89: 16–27.
21.
HeMHeD.Deep learning based approach for bearing fault diagnosis. IEEE Trans Ind Appl2017; 53: 3057–3065.
22.
ZhangYHZhouTTHuangXF, et al. Fault diagnosis of rotating machinery based on recurrent neural networks. Measurement2021; 171: 108774.
23.
KordestaniMSamadiMFSaifM, et al. A new fault diagnosis of multifunctional spoiler system using integrated artificial neural network and discrete wavelet transform methods. IEEE Sens J2018; 18: 4990–5001.
24.
ZhouHLiuRDLiYX, et al. A rolling bearing fault diagnosis method based on a convolutional neural network with frequency attention mechanism. Struct Health Monit2024; 23: 2475–2495.
25.
ChenYQiangYChenJ, et al. FMRGAN: feature mapping reconstruction GAN for rolling bearings fault diagnosis under limited data condition. IEEE Sens J2024; 24: 25116–25131.
26.
ZhongDGuoWHeD. An intelligent fault diagnosis method based on STFT and convolutional neural network for bearings under variable working conditions. In: 2019 Prognostics and system health management conference (PHM-QINGDAO 2019), 25–27 October 2019, pp. 1–6. New York, NY: IEEE.
27.
JiaZYYuBJ.A fault diagnosis method for rolling bearings of wind turbine generators based on MCGAN data enhancement. SN Appl Sci2023; 5: 259.
28.
LiangPFDengCWuJ, et al. Compound fault diagnosis of gearboxes via multi-label convolutional neural network and wavelet transform. Comput Ind2019; 113: 103132.
29.
ChengYWLinMXWuJ, et al. Intelligent fault diagnosis of rotating machinery based on continuous wavelet transform-local binary convolutional neural network. Knowl Based Syst2021; 216: 106796.
30.
ZouDLLiuGYRaoZS, et al. Design of a multi-stable piezoelectric energy harvester with programmable equilibrium point configurations. Appl Energy2021; 302: 117585.
31.
XieXDWangZJLiuDZ, et al. An experimental study on a novel cylinder harvester made of L-shaped piezoelectric coupled beams with a high efficiency. Energy2020; 212: 118752.
32.
FuHLYeatmanEM.Rotational energy harvesting using bi-stability and frequency up-conversion for low-power sensing applications: theoretical modelling and experimental validation. Mech Syst Signal Process2019; 125: 229–244.
33.
TianHGFanWSZhangWM, et al. Enhanced performance of piezoelectric energy harvester incorporating surface protrusions. Energy2026; 342: 139613.
34.
MaharjanPBhattaTRaselMS, et al. High-performance cycloid inspired wearable electromagnetic energy harvester for scavenging human motion energy. Appl Energy2019; 256: 113987.
35.
SunRQZhouSXChengL.Ultra-low frequency vibration energy harvesting: mechanisms, enhancement techniques, and scaling laws. Energy Convers Manag2023; 276: 116585.
36.
FangHLiDJDuanLY, et al. Passive vibration suppression in a coupled linear-bistable continuous module excited near resonance. Arch Appl Mech2020; 90: 2449–2464.
37.
ZhaoFJiJCYeK, et al. Increase of quasi-zero stiffness region using two pairs of oblique springs. Mech Syst Signal Process2020; 144: 106975.
38.
LiMChengWXieRL.A quasi-zero-stiffness vibration isolator using a cam mechanism with user-defined profile. Int J Mech Sci2021; 189: 105938.
39.
LinYBHuangSQChenBY, et al. A novel drum-shaped metastructure aided weak signal enhancement method for bearing fault diagnosis. Mech Syst Signal Process2024; 209: 111077.
40.
ZhangJLiXLiR, et al. Internal resonance of a two-degree-of-freedom tuned bistable electromagnetic actuator. Chaos Soliton Fract2021; 143: 110612.
41.
ZhuYQZhangZYZhangPX, et al. A magnetically coupled piezoelectric-electromagnetic low-frequency multidirection hybrid energy harvester. Micromachines2022; 13: 761.
42.
YanBMaHYZhangL, et al. A bistable vibration isolator with nonlinear electromagnetic shunt damping. Mech Syst Signal Process2020; 136: 106504.
43.
MannBPSimsND.Energy harvesting from the nonlinear oscillations of magnetic levitation. J Sound Vib2009; 319: 515–530.
44.
LiuHQianYLeeC.A multi-frequency vibration-based MEMS electromagnetic energy harvesting device. Sens Actuators A Phys2013; 204: 37–43.
45.
WangQZhouJWangK, et al. A compact quasi-zero-stiffness device for vibration suppression and energy harvesting. Int J Mech Sci2023; 250: 108284.
46.
PodderPAmannARoyS.Combined effect of bistability and mechanical impact on the performance of a nonlinear electromagnetic vibration energy harvester. IEEE/ASME Trans Mechatron2016; 21: 727–739.
47.
RuanYDLiangXHuaXY, et al. Isolating low-frequency vibration from power systems on a ship using spiral phononic crystals. Ocean Eng2021; 225: 108804.
48.
LuWNLiangBChengY, et al. Deep model based domain adaptation for fault diagnosis. IEEE Trans Ind Electron2017; 64: 2296–2305.
49.
DaoFZengYQianJ.Fault diagnosis of hydro-turbine via the incorporation of bayesian algorithm optimized CNN-LSTM neural network. Energy2024; 290: 130326.
50.
WangHLiuZPengD, et al. Attention-guided joint learning CNN with noise robustness for bearing fault diagnosis and vibration signal denoising. ISA Trans2022; 128: 470–484.
51.
ZhangGYiTZhangTQ, et al. A multiscale noise tuning stochastic resonance for fault diagnosis in rolling element bearings. Chin J Phys2018; 56: 145–157.
