The brake pads of high-speed trains operate under complex and variable conditions, and the collected brake signals are easily affected by noise, making monitoring the health status of brake pads more difficult. A multi-representation adaptation network for online monitoring the health status of high-speed train brake pads, which are affected by noise under variable working conditions, is proposed in this study. First, a parameter-sharing deep residual network is used to extract the friction block features of the source and target domain data. Then, the features are mapped to different low-dimensional feature spaces through the inception adaptation module, and multiple representations are obtained. The network applies conditional maximum mean discrepancy to align representations of the source and target domains, thus learning multiple domain-invariant representations. Hence, the network acquires more knowledge of the friction block status and attenuates the interference of noise signals on the status monitoring. The friction block vibration data were collected from various brake disc speeds, and variable working condition-transfer experiments under the influence of noise were performed on the brake friction and bearing datasets. The results show that the proposed network outperforms other transfer methods, which can better extract and identify the status features of the friction block under the noise interference.
ZhangMZhangXMoJ, et al. Brake uneven wear of high-speed train intelligent monitoring using an ensemble model based on multi-sensor feature fusion and deep learning. Eng Failure Anal2022; 137.
2.
XiangZYMoJLOuyangH, et al. Contact behaviour and vibrational response of a high-speed train brake friction block. Tribol Int2020; 152: 106540.
3.
YinJWuYLuC, et al. The influence of friction blocks connection configuration on high-speed railway brake systems performance. Tribol Lett2021; 69: 1–19.
4.
TangBMoJLXuJW, et al. Effect of perforated structure of friction block on the wear, thermal distribution and noise characteristics of railway brake systems. Wear2019; 426: 1176–1186.
5.
SunZYuanXFuX, et al. Multi-scale capsule attention network and joint distributed optimal transport for bearing fault diagnosis under different working loads. Sensors2021; 21: 6696.
6.
LeeJSKimHMKimSI, et al. Evaluation of structural integrity of railway bridge using acceleration data and semi-supervised learning approach. Eng Struct2021; 239: 112330.
7.
LiDWangYYanWJ, et al. Acoustic emission wave classification for rail crack monitoring based on synchrosqueezed wavelet transform and multi-branch convolutional neural network. Struct Health Monit - Int J2021; 20: 1563–1582.
8.
ChenSXZhouLNiYQ. Wheel condition assessment of high-speed trains under various operational conditions using semi-supervised adversarial domain adaptation. Mech Syst Signal Process2022; 170: 108853.
9.
JegadeeshwaranRSugumaranV. Fault diagnosis of automobile hydraulic brake system using statistical features and support vector machines. Mech Syst Signal Process2015; 52: 436–446.
10.
LiuZZhangMLiuF, et al. Multidimensional feature fusion and ensemble learning-based fault diagnosis for the braking system of heavy-haul train. IEEE Trans Ind Inf2020; 17: 41–51.
11.
HuRZhangMMengX, et al. Deep subdomain generalisation network for health monitoring of high-speed train brake pads. Eng Appl Artif Intell2022; 113: 104896.
12.
LiWChenZHeG. A novel weighted adversarial transfer network for partial domain fault diagnosis of machinery. IEEE Trans Ind Inf2020; 17: 1753–1762.
13.
LiuSWangHTangJ, et al. Research on fault diagnosis of gas turbine rotor based on adversarial discriminative domain adaption transfer learning. Measurement2022; 196: 111174.
14.
ShiYDengADingX, et al. Multisource domain factorization network for cross-domain fault diagnosis of rotating machinery: an unsupervised multisource domain adaptation method. Mech Syst Signal Process2022; 164: 108219.
15.
YangSKongXWangQ, et al. A multi-source ensemble domain adaptation method for rotary machine fault diagnosis. Measurement2021; 186: 110213.
16.
JinGXuKChenH, et al. A novel multi-adversarial cross-domain neural network for bearing fault diagnosis. Meas Sci Technol2021; 32: 055102.
17.
ZhuangFQiZDuanK, et al. A comprehensive survey on transfer learning. Proc IEEE2020; 109: 43–76.
18.
LiWHuangRLiJ, et al. A perspective survey on deep transfer learning for fault diagnosis in industrial scenarios: theories, applications and challenges. Mech Syst Signal Process2022; 167: 108487.
19.
LiXZhangWDingQ, et al. Multi-layer domain adaptation method for rolling bearing fault diagnosis. Signal Process2019; 157: 180–197.
20.
LiuYZShiKMLiZX, et al. Transfer learning method for bearing fault diagnosis based on fully convolutional conditional Wasserstein adversarial networks. Measurement2021; 180: 109553.
21.
ZhuJChenNShenC. A new deep transfer learning method for bearing fault diagnosis under different working conditions. IEEE Sens J2020; 20: 8394–8402.
22.
LiXZhangWDingQ. A robust intelligent fault diagnosis method for rolling element bearings based on deep distance metric learning. Neurocomputing2018; 310: 77–95.
23.
ChenZHeGLiJ, et al. Domain adversarial transfer network for cross-domain fault diagnosis of rotary machinery. IEEE Trans Instrum Meas2020; 69: 8702–8712.
24.
HeKZhangXRenS, et al. Deep residual learning for image recognition. In: IEEE conference on computer vision and pattern recognitionNV, USA: Las Vegas, 2016, pp. 770–778.
25.
BorgwardtKMGrettonARaschMJ, et al. Integrating structured biological data by Kernel maximum mean discrepancy. Bioinformatics2006; 22: e49–e57.
26.
ElhamifarEVidalR. Sparse subspace clustering: algorithm, theory, and applications. IEEE Trans Pattern Anal Mach Intell2013; 35: 2765–2781.
27.
ZhuYZhuangFWangJ, et al. Multi-representation adaptation network for cross-domain image classification. Neural Netw2019; 119: 214–221.
28.
LongMWangJDingG, et al. Transfer feature learning with joint distribution adaptation. In: IEEE international conference on computer visionSydney, Australia, 2013, pp. 2200–2207.
29.
HuangGLiuZVan Der MaatenL, et al. Densely connected convolutional networks. In: IEEE conference on computer vision and pattern recognitionHonolulu, HI, USA, 2017, pp. 4700–4708.
30.
LongMZhuHWangJ, et al. Deep transfer learning with joint adaptation networks. In: International conference on machine learning, Sydney, Australia, 06–11 Aug 2017, pp. 2208–2217.
31.
PeiZCaoZLongM, et al. Multi-adversarial domain adaptation. In: Thirty-second AAAI conference on artificial intelligence, New Orleans, LA, USA, 02–07 Feb 2018, pp. 3934–3941.
32.
ZhangXZhangMXiangZ, et al. Research on diagnosis algorithm of mechanical equipment brake friction fault based on MCNN-SVM. Measurement2021; 186: 110065.
33.
ZhangWLiCPengG, 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.
34.
AlazzawiOWangDS. A novel structural damage identification method based on the acceleration responses under ambient vibration and an optimized deep residual algorithm. Struct Health Monit - Int J2022; 21: 2587–2617.
35.
LindauerMEggenspergerKFeurerM, et al. SMAC3: a versatile bayesian optimization package for hyperparameter optimization. J Mach Learn Res2022; 23: 1–9.
36.
SunHChenXWangL, et al. C2DAN: an improved deep adaptation network with domain confusion and classifier adaptation. Sensors2020; 20: 3606.
37.
ZhangWWangFJiangY, et al. Cross-subject EEG-based emotion recognition with deep domain confusion. In: International conference on intelligent robotics and applications. Shenyang, China, 2019, pp. 558–570.
38.
LiFTangTTangB, et al. Deep convolution domain-adversarial transfer learning for fault diagnosis of rolling bearings. Measurement2021; 169: 108339.
39.
SmithWARandallRB. Rolling element bearing diagnostics using the Case Western Reserve University data: a benchmark study. Mech Syst Signal Process2015; 64: 100–131.
