With the widespread application of industrial robots in smart manufacturing and industrial automation, the topic of fault diagnosis for key components of robots is gaining increasing attention. Servo drivers not only provide power and control for industrial robots, enabling them to perform complex tasks, but their rich built-in signal sources could also be adopted for fault diagnosis. This paper proposes a fault diagnosis method that integrates vibration and electrical signal information, aiming to detect faults in servo motor bearings by fully exploring the potential of built-in signals from servo drivers. By designing time-frequency features for efficiently fusing multiple physical signals, the proposed multi-source frequency temporal associative (MSFTA) network enhances the perception and collaborative processing capabilities of multidimensional information. The focus is on extracting deep features from different physical dimensions and mechanisms (such as torque, speed, current, and vibration signals) and constructing coupling and complementary mechanisms for joint analysis of time-frequency information from multiple sources. Finally, experimental results under varying speeds and load conditions demonstrate the effectiveness of the proposed method, showing promising application prospects in the field of industrial robotics.
ZhangXWangFZhouY, et al. The optimized local sparse parallel multi-channel deep convolutional neural network-LSTM and the application in bearing fault diagnosis under noise and variable working condition. Proc IMechE, Part C: J Mechanical Engineering Science2025; 239(1): 205–218.
2.
LiCZhouJWuX, et al. Adaptive feature mode decomposition method for bearing fault diagnosis under strong noise. Proc IMechE, Part C: J Mechanical Engineering Science2025; 239(2): 508–519.
3.
LeiCWanHYuY, et al. Fault diagnosis method of rolling bearing under variable operating conditions based on MFCCNN. Proc IMechE, Part C: J Mechanical Engineering Science2025; 239: 2637–2648.
4.
ZhangXLiangWBaiJ, et al. Intelligent fault diagnosis of roller bearing based on dual-flow convolutional neural network. Proc IMechE, Part C: J Mechanical Engineering Science2024; 238: 8889–8902.
5.
DengLWangGZhaoC, et al. MARNet: multi-head attention residual network for rolling bearing fault diagnosis under noisy condition. Proc IMechE, Part C: J Mechanical Engineering Science2024; 238(19): 9726–9747.
6.
NazariSShokoohiSMoshtaghJ.A current noise cancellation method based on integration of stator synchronized currents for bearing fault diagnosis. IEEE Trans Instrum Meas2024; 73: 1–8.
7.
LuoXWangHHanT, et al. FFT-Trans: enhancing robustness in mechanical fault diagnosis with Fourier transform-based transformer under noisy conditions. IEEE Trans Instrum Meas2024; 73: 1–12.
8.
LiangKZhaoMLinJ, et al. A novel indicator to improve fast kurtogram for the health monitoring of rolling bearing. IEEE Sens J2020; 20(20): 12252–12261.
9.
HuangXZhangJChengM.Fault detection of servo motor bearing based on speed signal under variable-speed conditions. IEEE Trans Instrum Meas2024; 73: 1–12.
10.
HuangXZhangJWuY, et al. Speed signature analysis for servo motor bearing fault detection under dynamic load conditions. IEEE Trans Power Electron2025; 40: 7275–7285.
11.
WangCWangMYangB, et al. A novel methodology for fault size estimation of ball bearings using stator current signal. Measurement2021; 171: 108723.
12.
LuSHeQZhaoJ.Bearing fault diagnosis of a permanent magnet synchronous motor via a fast and online order analysis method in an embedded system. Mech Syst Signal Process2018; 113: 36–49.
13.
GaoTYangJTangQ.A multi-source domain information fusion network for rotating machinery fault diagnosis under variable operating conditions. Inf Fusion2024; 106: 102278.
14.
HanYDengXZhengJ, et al. Thermal error prediction for vertical machining centers using decision-level fusion of multi-source heterogeneous information. Machines2024; 12(8): 509.
15.
ZhangXLiuJZhangX, et al. Multiscale channel attention-driven graph dynamic fusion learning method for robust fault diagnosis. IEEE Trans Ind Inform2024; 20(9): 11002–11013.
16.
CenZHuSHouY, et al. Remaining useful life prediction of machinery based on improved sample convolution and interaction network. Eng Appl Artif Intell2024; 135: 108813.
17.
XuZDuMZhangY, et al. DTST: A dual-aspect time series transformer model for fault diagnosis of space power system. IEEE Trans Instrum Meas2024; 73: 1–10.
18.
JiangLShiCShengH, et al. Lightweight CNN architecture design for rolling bearing fault diagnosis. Meas Sci Technol2024; 35(12): 126142.
19.
WangRDongEChengZ, et al. Transformer-based intelligent fault diagnosis methods of mechanical equipment: a survey. Open Phys2024; 22(1): 20240015.
20.
LiuHXuQHanX, et al. Attention on the key modes: machinery fault diagnosis transformers through variational mode decomposition. Knowl Syst2024; 289: 111479.
21.
KKKMandavaS. Real-time bearing fault classification of induction motor using enhanced inception ResNet-V2. Appl Artif Intell2024; 38: 2378270.
22.
JamilMAKhanamS.Influence of one-way ANOVA and Kruskal–Wallis based feature ranking on the performance of ML classifiers for bearing fault diagnosis. J Vib Eng Technol2024; 12(3): 3101–3132.
23.
SabirRRosatoDHartmannS, et al. LSTM based bearing fault diagnosis of electrical machines using motor current signal. In 2019 18th IEEE International Conference on Machine Learning and Applications (ICMLA), IEEE, 2019: pp.613–618.
24.
WangQChenQChenL, et al. Dual-weight attention-based multi-source multi-stage alignment domain adaptation for industrial fault diagnosis. Meas Sci Technol2024; 35: 096105.
25.
JinYYangJYangX, et al. Cross-domain bearing fault diagnosis method based on SMOTENC and deep transfer learning under imbalanced data. Meas Sci Technol2024; 35(1): 015121.
26.
GaoTYangJZhangB, et al. A fault diagnosis method based on feature-level fusion of multi-sensor information for rotating machinery. Meas Sci Technol2024; 35(3): 036109.
27.
DuanZWuTGuoS, et al. Development and trend of condition monitoring and fault diagnosis of multi-sensors information fusion for rolling bearings: a review. Int J Adv Manuf Technol2018; 96: 803–819.
28.
WangCMaXZhouJ, et al. Multilevel information fusion for induction motor fault diagnosis. IEEE Access2019; 7: 151210–151221.
29.
ZhangHWangCDengW, et al. Engine fault diagnosis based on multi-sensor information fusion using Dempster–Shafer evidence theory. Measurement2020; 158: 107729.
30.
ZhangYWangKShaoH, et al. A multisensor information fusion method for high-reliability fault diagnosis of rotating machinery. IEEE Trans Ind Inform2021; 17(9): 6381–6391.
31.
SunYWenGHouT, et al. A hydraulic motor fault diagnosis method based on weighted multi-channel information fusion. Measurement2022; 190: 110686.
32.
ZhaoRYanRChenZ, et al. Multitask convolutional neural network with information fusion for bearing fault diagnosis and localization. Mech Syst Signal Process2020; 139: 106613.
33.
ZouFZhangHSangS, et al. An anti-noise one-dimension convolutional neural network learning model applying on bearing fault diagnosis. Measurement2021; 186: 110236.
34.
ZhaoHSunSJinB.Sequential fault diagnosis based on LSTM neural network. IEEE Access2018; 6: 12929–12939.
35.
HanYZhangFLiZ, et al. MT-ConvFormer: a multi-task bearing fault diagnosis method using a combination of CNN and transformer. IEEE Trans Instrum Meas2025; 74: 1–16.
36.
LiOLeiJQinC, et al. A novel multi-channel CNN-LSTM and transformer-based network for diesel engine misfire diagnosis under different noise conditions. Sci China Technol Sci2024; 67(9): 2965–2967.
