The ZD6 turnout switch machine is an important part of rail transit signaling equipment. It is one of the most widely used turnout switch machine models to switch train tracks. Any abnormality in its operation could result in serious consequences, such as train derailment. To achieve condition-based maintenance of ZD6 turnout switch machines, this paper proposes a multimodal lightweight end-to-end deep learning framework for anomaly detection in ZD6 turnout switch machines. The input data for this framework are multimodal, comprising two-dimensional time-frequency diagrams obtained by a short-time Fourier transform of the armature current of a ZD6 turnout switch machine series-excited direct current motor, as well as one-dimensional data manually extracted from the armature current characteristics. This framework uses partial convolution and depthwise separable convolution to achieve lightweight processing. SimAM’s parameter-free attention mechanism enhances the network’s feature extraction capabilities. Experimental verification based on a dataset collected from the armature current of two actual ZD6-D and ZD6-G turnout switch machines demonstrates that the proposed anomaly detection framework performs well and has high application value.
LiYTaoXSunY.A fault diagnosis method for turnout switch machines based on sound signals. Electronics2024; 13: 4839.
2.
ZhouNChengYWangZ, et al. CFFsgram: a candidate fault frequencies-based optimal demodulation band selection method for axle-box bearing fault diagnosis. Measurement2023; 207: 112368.
3.
HuangYHuangCDingJLiuZ.Fault diagnosis on railway vehicle bearing based on fast extended singular value decomposition packet. Measurement2020; 152: 107277.
4.
SunYCaoYLiuH, et al. Condition monitoring and fault diagnosis strategy of railway point machines using vibration signals. Transp Saf Environ2022; 5: tdac048.
5.
SunYCaoYLiP, et al. Vibration-based fault diagnosis for railway point machines using VMD and multiscale fluctuation-based dispersion entropy. Chin J Electron2024; 33: 803–813.
6.
HeYHeDLaoZ, et al. Few-shot fault diagnosis of turnout switch machine based on flexible semi-supervised meta-learning network. Knowledge Based Syst2024; 294: 111746.
7.
LaoZHeDWeiZ, et al. Intelligent fault diagnosis for rail transit switch machine based on adaptive feature selection and improved LightGBM. Eng Fail Anal2023; 148: 107219.
8.
BianCYangSHuangT, et al. Degradation state mining and identification for railway point machines. Reliab Eng Syst Saf2019; 188: 432–443.
9.
LiuCPanJWangJ.An LSTM-based anomaly detection model for the deformation of concrete dams. Struct Health Monit2024; 23: 1914–1925.
10.
CaiCGuoXRenJXueY.Small-sample damage detection of bleacher structure based on GAN and MSS-CNN models. Struct Health Monit2025; 24: 1122–1148.
11.
ZhangF-LLiXKimC-WMuH-Q.Multicase structural damage classification based on semisupervised generative adversarial network. Struct Health Monit2025; 24: 2475–2503.
12.
HeYHeDLaoZ, et al. A class-center fine-tuning prototypical network for few-shot fault diagnosis of turnout switch machine driven by multi-source signals. Measurement2025; 242: 115920.
13.
MengQWenWBaiYLiuY.A fault detection method for electrohydraulic switch machine based on oil-pressure-signal-sectionalized feature extraction. Entropy2022; 24: 848.
14.
CaoYSunYLiPSuS.Vibration-based fault diagnosis for railway point machines using multi-domain features, ensemble feature selection and SVM. IEEE Trans Veh Technol2024; 73: 176–184.
15.
LiMHeiXJiW, et al. A fault-diagnosis method for railway turnout systems based on improved autoencoder and data augmentation. Sensors (Basel)2022; 22: 9438.
16.
DuLLiuSCaoTZhangT. Research on turnout fault diagnosis model based on GADF-CNN-MAML. In: 2024 5th international conference on artificial intelligence and computer engineering (ICAICE). Wuhu, China: IEEE, 2024, pp.1057–1062.
17.
DengHLuYYangT, et al. Unmanned aerial vehicles anomaly detection model based on sensor information fusion and hybrid multimodal neural network. Eng Appl Artif Intell2024; 132: 107961.
18.
ChengLChenBXiangL, et al. A novel transformer network for anomaly detection of wind turbine. Measurement2025; 256: 118118.
19.
WeiT-RChangAKangY, et al. Multimodal deep learning for enhanced breast cancer diagnosis on sonography. Comput Biol Med2025; 194: 110466.
20.
WangJLinFNanD, et al. Transmission line fault identification method based on weighted federated learning and multimodal residual network. Int J Electr Power Energy Syst2025; 170: 110860.
21.
YuHWuHFangX, et al. SR-CIBN: semantic relationship-based consistency and inconsistency balancing network for multimodal fake news detection. Neurocomputing2025; 635: 129997.
22.
YuYWangJLiuW, et al. Multimodal multitask similarity learning for vision language model on radiological images and reports. Neurocomputing2025; 636: 130018.
23.
ZamanWSiddiqueMFKhanSUKimJ-M.A new dual-input CNN for multimodal fault classification using acoustic emission and vibration signals. Eng Fail Anal2025; 179: 109787.
24.
GuanYMengZSunD, et al. 2MNet: Multi-sensor and multi-scale model toward accurate fault diagnosis of rolling bearing. Reliab Eng Syst Saf2021; 216: 108017.
25.
KimS-GParkTKangRKwakY.Domain-collaborative multimodal transformer for fault diagnosis of rotating machines under noisy environments. Adv Eng Inf2025; 68: 103763.
26.
LiDPangZChenY, et al. FD-MVLLM: Fault diagnosis based on multimodal vibration data and large language model for bearing system. Mech Syst Signal Process2025; 239: 113226.
27.
ZhangWLiuZJiaZ, et al. Application of a multimodal deep learning model based on recursive fusion feature map with transformer–TCN for complex fault diagnosis of flying wing UAV actuators. IEEE Trans Instrum Meas2025; 74: 1–17.
28.
ChenJKaoShHeH, et al. Run, don’t walk: chasing higher flops for faster neural networks. In: 2023 IEEE/CVF conference on computer vision and pattern recognition (CVPR). Vancouver, BC, Canada: IEEE, 2023, pp.12021–12031.
29.
WangHJuXZhuHLiH.SEFormer: a lightweight CNN-transformer based on separable multiscale depthwise convolution and efficient self-attention for rotating machinery fault diagnosis. Comput Mater Con2025; 82: 1417–1437.
30.
YangLZhangR-YLiLXieX. SimAM: a simple, parameter-free attention module for convolutional neural networks. In: MarinaMTongZ (eds.). Proceedings of the 38th international conference on machine learning. Proceedings of Machine Learning Research: PMLR, 2021, pp.11863–11874.
31.
ZhuJChenXHeK, et al. Transformers without normalization. In: Proceedings of the computer vision and pattern recognition conference. Nashville, TN: IEEE, 2025, pp.14901–14911.
32.
HowardASandlerMChenB, et al. Searching for MobileNetV3. In: 2019 IEEE/CVF international conference on computer vision (ICCV). Seoul, Korea (South): IEEE, 2019, pp.1314–1324.
33.
QinDLeichnerCDelakisM, et al. MobileNetV4: universal models for the mobile ecosystem. In: Computer Vision – ECCV 2024. Milan, Italy: Springer Nature Switzerland, 2025, pp.78–96.
34.
HeKZhangXRenS, et al. Deep residual learning for image recognition. In: 2016 IEEE conference on computer vision and pattern recognition (CVPR). Las Vegas, NV, USA: IEEE, 2016, pp.770–778.
35.
MaXDaiXBaiY, et al. Rewrite the stars. In: 2024 IEEE/CVF conference on computer vision and pattern recognition (CVPR). Seattle, WA, USA: IEEE, 2024, pp.5694–5703.
36.
ChenZLiuJDuZ, et al. A noise-resilient fault diagnosis method based on optimized residual networks. IEEE Trans Instrum Meas2025; 74: 1–10.
