Transfer Learning With Neural Networks for Bearing Fault Diagnosis in Changing Working Conditions
Open accessThe DOI matches its Crossref record; 27 of the 27 references it cites were found in a registry or an index.
Abstract
Traditional machine learning algorithms have made great achievements in data-driven fault diagnosis. However, they assume that all the data must be in the same working condition and have the same distribution and feature space. They are not applicable for real-world working conditions, which often change with time, so the data are hard to obtain. In order to utilize data in different working conditions to improve the performance, this paper presents a transfer learning approach for fault diagnosis with neural networks. First, it learns characteristics from massive source data and adjusts the parameters of neural networks accordingly. Second, the structure of neural networks alters for the change of data distribution. In the same time, some parameters are transferred from source task to target task. Finally, the new model is trained by a small amount of target data in another working condition. The Case Western Reserve University bearing data set is used to validate the performance of the proposed transfer learning approach. Experimental results show that the proposed transfer learning approach can improve the classification accuracy and reduce the training time comparing with the conventional neural network method when there are only a small amount of target data.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“Compared with the diagnosis model just trained with a small number of target-domain samples, the fine-tuned diagnosis model presented the faster convergence rate and higher diagnosis accuracy.”
From Applications of machine learning to machine fault diagnosis: A review and roadmap (2020) · cites this paper as [438]
Citations
Cites
Huang, N. E., Shen, Z., Long, S. R., Wu, M. C., Shih, H. H., Zheng, Q., Yen, N.-C., Tung, C. C., & Liu, H. H. (1998) · Proceedings of the Royal Society of London. Series A: Mathematical, Physical and Engineering Sciences · doi:10.1098/rspa.1998.0193 · Cited by 23,564 · cited 2×
“Lei et al. [28] proposed a mechanical fault diagnosis model based on WPD and EMD.”
MethodPan, S. J., & Yang, Q. (2010) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2009.191 · Cited by 23,387 · cited 1×
“It has made great progresses in image, audio and text recognition [16]–[18].”
BackgroundWeiss, K., Khoshgoftaar, T. M., & Wang, D. (2016) · Journal of Big Data · doi:10.1186/s40537-016-0043-6 · Cited by 6,260
Robust Model-Based Fault Diagnosis for Dynamic Systems
Chen, J., & Patton, R. J. (1999) · The International Series on Asian Studies in Computer and Information Science · doi:10.1007/978-1-4615-5149-2 · Cited by 4,262 · cited 1×
“These fault diagnosis methods can be divided into model driven methods [1], [2] and data driven methods.”
MethodLearning and Transferring Mid-level Image Representations Using Convolutional Neural Networks
Oquab, M., Bottou, L., Laptev, I., & Sivic, J. (2014) · 2014 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2014.222 · Cited by 3,150 · cited 1×
“[20] combined convolutional neural networks with transfer learning to learn and transfer mid-level image representations.”
BackgroundGao, Z., Cecati, C., & Ding, S. X. (2015) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2015.2417501 · Cited by 3,135 · cited 1×
“These fault diagnosis methods can be divided into model driven methods [1], [2] and data driven methods.”
MethodBoosting for transfer learning
Dai, W., Yang, Q., Xue, G.-R., & Yu, Y. (2007) · Proceedings of the 24th international conference on Machine learning · doi:10.1145/1273496.1273521 · Cited by 1,724 · cited 1×
“[22] proposed a transfer learning framework called TrAdaBoost to select most useful and different samples as additional training data to improve the performance.”
BackgroundJia, F., Lei, Y., Lin, J., Zhou, X., & Lu, N. (2016) · Mechanical Systems and Signal Processing · doi:10.1016/j.ymssp.2015.10.025 · Cited by 1,710 · cited 1×
“[9] used deep neural networks to recognize faults by training the model with frequency spectra extracted from vibration signals.”
Self-taught learning: transfer learning from unlabeled data
Raina, R., Battle, A., Lee, H., Packer, B., & Ng, A. Y. (2007) · Proceedings of the 24th international conference on Machine learning · doi:10.1145/1273496.1273592 · Cited by 1,510 · cited 1×
“[21] designed selftaught learning to learn from unlabeled data and it improves classification accuracies of given image, audio and text classification tasks, respectively.”
BackgroundTransfer Learning for Reinforcement Learning Domains: A Survey
Taylor, M. E., & Stone, P. (2009) · doi:10.5555/1577069.1755839 · Cited by 1,488 · cited 1×
“The aim of transfer is to take advantage of experience learnt in one task and improve the performance in a similar but different task [24].”
Background
Research works printed but not linked: 1
- 0, Bearing Data Center Seeded Fault Test Data
Cited by
Items 101–200 of 379
Wang, S., Yan, L., Du, S., Li, S., & Chen, X. (2025) · Measurement Science and Technology · doi:10.1088/1361-6501/adcce4 · Cited by 94
“In this case, there is not enough data to train and optimize the model [74].”
An Unsupervised Fault-Detection Method for Railway Turnouts
Guo, Z., Wan, Y., & Ye, H. (2020) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2020.2998863 · Cited by 61
“With the well-trained DAE model gBd for the source domain Bd , the following OC-TL algorithm is given to construct the DAE model gS j for the target domain Sj , which modifies the loss functions (6) and (8) in TL algorithms [48]–[51] (as”
BackgroundMethodInfluentialAdvancing machine fault diagnosis: a detailed examination of convolutional neural networks
Vashishtha, G., Chauhan, S., Sehri, M., Hebda-Sobkowicz, J., Zimroz, R., Dumond, P., & Kumar, R. (2024) · Measurement Science and Technology · doi:10.1088/1361-6501/ada178 · Cited by 56
“Following Choudhary et al [151], Zhiyu et al [152], Yang et al [153], Amarouayache et al [154], Han et al [155], Wang et al [156], Zhao et al [157], Wu et al [158], Zhang et al [159], Huang et al [160], Hasan et al [161], Lu et al [162] and Shao et al [163] 2”
Transfer Learning Based Fault Diagnosis with Missing Data Due to Multi-Rate Sampling
Chen, D., Yang, S., & Zhou, F. (2019) · Sensors · doi:10.3390/s19081826 · Cited by 56
“[32] a working condition another working condition feature migration presenting a transfer learning method based on neural networks for fault diagnosis of rolling bearings This paper incomplete data structurally complete data feature migration proposing a fault diagnosis framework of missing data based on transfer lea…”
BackgroundMethodBrusa, E. G. M., Delprete, C., & Maggio, L. G. D. (2021) · Applied Sciences · doi:10.3390/app112411663 · Cited by 55
“[38] and Hasan and Kim [39] employed TL to diagnose machine failures, by transferring knowledge between different working conditions.”
BackgroundMethodLiu, Z., Lu, B., Wei, H., Li, X., & Chen, L. (2019) · IEEE Sensors Journal · doi:10.1109/jsen.2019.2939360 · Cited by 55
Barusu, M. R., & Deivasigamani, M. (2020) · IEEE Sensors Journal · doi:10.1109/jsen.2020.3004515 · Cited by 55
“and rotor bar, the characteristic vibration frequencies are listed in Table II [20].”
BackgroundOnline Process Monitoring Based on Vibration-Surface Quality Map for Robotic Grinding
Lu, H., Zhao, X., Tao, B., & Yin, Z. (2020) · IEEE/ASME Transactions on Mechatronics · doi:10.1109/tmech.2020.2996939 · Cited by 47
“condition and have the same distribution and feature space [32], whereas the robotic grinding process is a time-varying condition,”
BackgroundGao, D.-W., Zhu, Y., Yan, K., Fu, H. C., Ren, Z., Kang, W., & Soares, C. G. (2023) · Mechanical Systems and Signal Processing · doi:10.1016/j.ymssp.2022.110089 · Cited by 48
One-shot neural architecture search for fault diagnosis using vibration signals
Li, X., Zheng, J., Li, M., Ma, W., & Hu, Y. (2021) · Expert Systems with Applications · doi:10.1016/j.eswa.2021.116027 · Cited by 46
Fault Diagnosis of Rolling Bearing Under Variable Working Conditions Based on CWT and T-ResNet
Diao, N., Wang, Z., Ma, H., & Yang, W. (2022) · Journal of Vibration Engineering & Technologies · doi:10.1007/s42417-022-00780-w · Cited by 45
“Directly applying the model trained on one working condition to another cannot achieve accurate fault diagnosis [11].”
MethodJia, S., Wang, J., Han, B., Zhang, G., Wang, X., & He, J. (2020) · IEEE Access · doi:10.1109/access.2020.2987933 · Cited by 46
“Furthermore, in several methods for fault diagnosis, the concept of transfer learning [26], [27] has been adopted to achieve a favorable diagnosis performance.”
MethodLiu, X., Chen, J., Zhang, K., Liu, S., He, S., & Zhou, Z. (2022) · Knowledge-Based Systems · doi:10.1016/j.knosys.2022.109272 · Cited by 46
Li, F., Chen, J., Pan, J. H., & Pan, T. (2020) · Measurement Science and Technology · doi:10.1088/1361-6501/ab6ade · Cited by 44
“Traditional machine learning algorithms are based on two conditions [10–12]: (i) large amounts of labeled data are available; (ii) all the data used to train the model and tested by the model follow the same distribution.”
BackgroundKnowledge transfer in fault diagnosis of rotary machines
Liu, G., Shen, W., Gao, L., & Kusiak, A. (2022) · IET Collaborative Intelligent Manufacturing · doi:10.1049/cim2.12047 · Cited by 44
Fault Diagnosis under Variable Working Conditions Based on STFT and Transfer Deep Residual Network
Du, Y., Wang, A., Wang, S., He, B., & Meng, G. (2020) · Shock and Vibration · doi:10.1155/2020/1274380 · Cited by 50
“Recently, aiming at solving the problem of transferring the generalization knowledge from the related tasks to the target tasks, transfer learning is developed [32, 33].”
BackgroundHasan, M. J., Islam, M. M. M., & Kim, J.-M. (2020) · Measurement · doi:10.1016/j.measurement.2020.108478 · Cited by 45
Maggio, L. G. D. (2022) · Sensors · doi:10.3390/s23010211 · Cited by 45
Li, Y., Chen, Y., Shao, H., & Zhang, H. (2023) · Reliability Engineering & System Safety · doi:10.1016/j.ress.2023.109514 · Cited by 46
Grover, C., & Turk, N. (2021) · Engineering Science and Technology an International Journal · doi:10.1016/j.jestch.2021.08.006 · Cited by 41
A new intelligent bearing fault diagnosis model based on triplet network and SVM
Yang, K., Zhao, L., & Wang, C. (2022) · Scientific Reports · doi:10.1038/s41598-022-08956-w · Cited by 46
Deep transfer learning strategy for efficient domain generalisation in machine fault diagnosis
Asutkar, S., & Tallur, S. G. (2023) · Scientific Reports · doi:10.1038/s41598-023-33887-5 · Cited by 47
Fault Detection of Bearing by Resnet Classifier with Model-Based Data Augmentation
Qian, L., Pan, Q. L., Lv, Y., & Zhao, X. (2022) · Machines · doi:10.3390/machines10070521 · Cited by 41
Yuan, R. B., Lv, Y., Li, H., & Song, G. (2019) · IEEE Access · doi:10.1109/access.2019.2939546 · Cited by 39
“When output values differ from expected values, it would start to propagate backwards and optimize its topology and network weight by selflearning and self-adjustment [56], [57].”
BackgroundA Novel Lightweight Relation Network for Cross-Domain Few-Shot Fault Diagnosis
Tang, T., Qiu, C., Yang, T., Wang, J., Zhao, J., Chen, M., Wu, J., & Wang, L. (2022) · Measurement · doi:10.1016/j.measurement.2023.112697 · Cited by 38
Ni, Y., Li, S., & Guo, P. (2025) · Scientific Reports · doi:10.1038/s41598-025-99346-5 · Cited by 40
Hu, J., Chen, M., Tang, H., & Zhang, J. (2024) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2024.108287 · Cited by 44
Rezazadeh, N., Perfetto, D., Oliveira, M. D., Luca, A. D., & Lamanna, G. (2024) · Structural Health Monitoring · doi:10.1177/14759217241295951 · Cited by 37
“Zhang et al. 20 enhanced the performance of a neural network for fault detection in rotor systems by fine-tuning it.”
Sepulveda, N. F. E., & Sinha, J. K. (2020) · Machines · doi:10.3390/machines8040066 · Cited by 37
“[12] Several bearing-related faults at different operational conditions (fault size, motor load, rotor speed) Transfer learning in ANN”
BackgroundMethodRuan, D., Chen, Y., Gühmann, C., Yan, J., & Li, Z. (2022) · Electronics · doi:10.3390/electronics11040622 · Cited by 37
Tayyab, S. M., Chatterton, S., & Pennacchi, P. (2022) · Sensors · doi:10.3390/s22052026 · Cited by 40
“proposed a transfer learning approach with neural networks for bearing fault diagnosis in changing working conditions when there is only a small amount of target data available [45].”
BackgroundToma, R. N., Piltan, F., Im, K., Shon, D., Yoon, T. H., Yoo, D.-S., & Kim, J.-M. (2022) · Sensors · doi:10.3390/s22134881 · Cited by 38
“Data Segmentation A simple preprocessing method is applied to convert 1-D original time-series current signal data into 2-D images by applying an adjustable sliding window mechanism [58] to extract useful features and reduce the computational time of the method.”
Method1D CNN-Based Transfer Learning Model for Bearing Fault Diagnosis Under Variable Working Conditions
Hasan, M. J., Sohaib, M., & Kim, J.-M. (2018) · Advances in intelligent systems and computing · doi:10.1007/978-3-030-03302-6_2 · Cited by 43
Ren, H., Liu, W. Y., Shan, M., Wang, X., & Wang, Z. (2020) · Renewable Energy · doi:10.1016/j.renene.2020.12.111 · Cited by 36
Sparse filtering based domain adaptation for mechanical fault diagnosis
Zhang, Z., Chen, H., Li, S., & An, Z. (2020) · Neurocomputing · doi:10.1016/j.neucom.2020.02.049 · Cited by 36
Maurya, S., Singh, V., Verma, N. K., & Mechefske, C. K. (2020) · IEEE Transactions on Automation Science and Engineering · doi:10.1109/tase.2020.3028151 · Cited by 38
A novel multi-adversarial cross-domain neural network for bearing fault diagnosis
Jin, G., Xu, K., Chen, H., Jin, Y., & Zhu, C. (2021) · Measurement Science and Technology · doi:10.1088/1361-6501/abd900 · Cited by 35
Transformer-Enabled Cross-Domain Diagnostics for Complex Rotating Machinery With Multiple Sensors
Zhang, Y., Ren, Z., Feng, K., Yu, K., Ma, H., & Liu, Z. (2023) · IEEE/ASME Transactions on Mechatronics · doi:10.1109/tmech.2023.3237233 · Cited by 35
“[25]establishedatransferlearningapproachbased ontheneuralnetworkforbearingdiagnosisunderdifferent operatingconditions.”
Li, J., Li, X., He, D., & Qu, Y. (2019) · Proceedings of the Institution of Mechanical Engineers Part O Journal of Risk and Reliability · doi:10.1177/1748006x19867776 · Cited by 34
“Zhang et al. 32 applied the method of transfer learning (TL) to make diagnostic methods quickly adaptable to other working conditions.”
MethodLi, F., Chen, J., He, S., & Zhou, Z. (2021) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2021.3097408 · Cited by 38
Unsupervised multiple-target domain adaptation for bearing fault diagnosis
Bai, G., Xing, T., We, S., Chi, H., Zhong, Z., Sun, L., & Sun, L. (2025) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2025.111063 · Cited by 35
Hasan, M. J., Sohaib, M., & Kim, J.-M. (2020) · Sensors · doi:10.3390/s20247205 · Cited by 35
Deep Transfer Learning Framework for Bearing Fault Detection in Motors
Kumar, P., Kumar, P., Hati, A. S., & Kim, H. S. (2022) · Mathematics · doi:10.3390/math10244683 · Cited by 33
“Zhang et al. [27] have proposed a bearing FD using transfer learning (TL) in variable operating conditions.”
MethodZhang, Q., Qi, Z., Cui, P., Xie, M., & Din, J. (2023) · Electric Power Systems Research · doi:10.1016/j.epsr.2023.109501 · Cited by 36
Zhou, J. H., Zheng, L., Wang, Y., & Gogu, C. (2020) · IEEE Access · doi:10.1109/access.2020.2990739 · Cited by 33
“Recently, studies regarding using pre-trained deep network based on transfer learning in the field of fault diagnostics also emerged [45].”
BackgroundCNNs Combined With a Conditional GAN for Mura Defect Classification in TFT-LCDs
Lu, H.-P., & Su, C. (2021) · IEEE Transactions on Semiconductor Manufacturing · doi:10.1109/tsm.2020.3048631 · Cited by 32
“Fine-tuning has been applied to a variety of defect imaging modalities or disease-specific classification tasks [22], [23].”
BackgroundHemmer, M., Khang, H. V., Robbersmyr, K. G., Waag, T. I., & Meyer, T. (2018) · Designs · doi:10.3390/designs2040056 · Cited by 33
“Further, TL is very helpful for a bearing fault diagnosis if the available data for training and validation are limited in industry [16].”
BackgroundMethodMichau, G., & Fink, O. (2019) · International Journal of Prognostics and Health Management · doi:10.36001/ijphm.2019.v10i4.2613 · Cited by 31
“Some works aim at adapting the target features to match the source by means of a transformation (Fernando, Habrard, Sebban & Tuytelaars, 2013; Xie, Zhang, Duan & Wang, 2016; Zhang, Tao, Wu & Guan, 2017), others combine both alignment and feature learning in a single task.”
BackgroundDeep transfer learning for failure prediction across failure types
Li, Z., Kristoffersen, E., & Li, J. (2022) · Computers & Industrial Engineering · doi:10.1016/j.cie.2022.108521 · Cited by 34
Iqbal, M., & Madan, A. K. (2023) · Journal of Vibration Engineering & Technologies · doi:10.1007/s42417-023-00930-8 · Cited by 31
“…mentioned to identify fault bearings with different features and benefits, including extreme learning machines (ELM) [52], transformation learning [53], linear discriminant analysis [54], random forest [55], and CNN [56], the Generative Adversarial Network (GAN) was proposed [57] manifold…”
Cross-domain knowledge transfer in industrial process monitoring: A survey
Chai, Z., Zhao, C., & Huang, B. (2025) · Journal of Process Control · doi:10.1016/j.jprocont.2025.103408 · Cited by 32
Unsupervised Fault Detection in Varying Operating Conditions
Michau, G., & Fink, O. (2019) · IEEE Conference on Prognostics and Health Management · doi:10.1109/icphm.2019.8819383 · Cited by 30
“Some works have focused on inferring models or statistical features relevant at the fleet level and to fine tune them for each unit [7]–[9].”
BackgroundMulti-source domain adaptation for image classification
Karimpour, M., Saray, S. N., Tahmoresnezhad, J., & Aghababa, M. P. (2020) · Machine Vision and Applications · doi:10.1007/s00138-020-01093-2 · Cited by 33
Application of Rotating Machinery Fault Diagnosis Based on Deep Learning
Cui, W., Meng, G., Wang, A., Zhang, X., & Ding, J. (2021) · Shock and Vibration · doi:10.1155/2021/3083190 · Cited by 35
Explainable fault diagnosis of oil-gas treatment station based on transfer learning
Liu, J., Hou, L., Zhang, R., Sun, X., Yu, Q., Yang, K., & Zhang, X. (2022) · Energy · doi:10.1016/j.energy.2022.125258 · Cited by 31
Self-citationRobust Detection of Bearing Early Fault Based on Deep Transfer Learning
Mao, W., Zhang, D., Tian, S. I. P., & Tang, J. (2020) · Electronics · doi:10.3390/electronics9020323 · Cited by 30
“[15] proposed a deep transfer learning method for fault diagnosis.”
A multi scale meta-learning network for cross domain fault diagnosis with limited samples
Wang, Y., & Liu, S. (2024) · Journal of Intelligent Manufacturing · doi:10.1007/s10845-024-02365-8 · Cited by 31
“However, preprocessing the original signal and manually extracting features may lose some information of the signal, which means that the original signal is not fully utilized (Zhang et al., 2017a, b).”
Probabilistic bearing fault diagnosis using Gaussian process with tailored feature extraction
Liang, M., & Zhou, K. (2021) · The International Journal of Advanced Manufacturing Technology · doi:10.1007/s00170-021-08392-6 · Cited by 31
Fault Identification for a Closed-Loop Control System Based on an Improved Deep Neural Network
Sun, B., Wang, J., He, Z., Zhou, H., & Gu, F. (2019) · Sensors · doi:10.3390/s19092131 · Cited by 33
Li, X., Zheng, J., Li, M., Ma, W., & Hu, Y. (2021) · Sensors · doi:10.3390/s21020450 · Cited by 30
“(b) Operating conditions of actual industrial equipment are often changing, which results in different distributions of collected datasets [15].”
BackgroundAutonomous Assessment of Delamination Using Scarce Raw Structural Vibration and Transfer Learning
Khan, A., Khalid, S., Raouf, I., Sohn, J.-W., & Kim, H. S. (2021) · Sensors · doi:10.3390/s21186239 · Cited by 28
Zhang, Z., Shao, M., Ma, C., Lv, Z., & Zhou, J. (2022) · Nonlinear Dynamics · doi:10.1007/s11071-022-07341-6 · Cited by 28
Lei, T., Pan, F., Hu, J., Xu, H., & Li, B. (2025) · Scientific Reports · doi:10.1038/s41598-025-88353-1 · Cited by 32
“Parameter-based transfer learning technique, for variable condition motor bearing fault diagnosis scenarios, include Zhang et al. and Hasan et al.‘s fine-tuning of fault diagnosis models using samples under target working conditions 21,22 .”
Semi-Supervised Transfer Learning Method for Bearing Fault Diagnosis with Imbalanced Data
Zong, X., Yang, R., Wang, H., Du, M., You, P., Wang, S., & Su, H. (2022) · Machines · doi:10.3390/machines10070515 · Cited by 26
Jiang, L., Zheng, C., & Li, Y. (2022) · Measurement Science and Technology · doi:10.1088/1361-6501/ac7d3d · Cited by 25
“Zhang et al [25] fine-tuned the improved deep neural network (DNN) model with a small number of samples in the target domain and achieved high fault diagnosis accuracy.”
A Balanced Adversarial Domain Adaptation Method for Partial Transfer Intelligent Fault Diagnosis
Wang, Y., Liu, Y., Chow, T. W. S., Gu, J., & Zhang, M. (2022) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2022.3214490 · Cited by 30
“Furthermore, those methods get satisfactory performance based on the assumption that the labeled training data and the unlabeled test data are subject to the same probability distribution [3].”
BackgroundTransfer Learning-Based Fault Diagnosis under Data Deficiency
Cho, S. H., Kim, S., & Choi, J.-H. (2020) · Applied Sciences · doi:10.3390/app10217768 · Cited by 25
“The id a is that by initializing the parameters with thos of the source domain, the accuracy and training efficiency can be improved substantially [10].”
BackgroundInfluentialChen, R., Zhu, Y., Yang, L., Hu, X., & Chen, G. (2022) · IEEE Sensors Journal · doi:10.1109/jsen.2022.3165398 · Cited by 24
Xiao, H., Dong, L., Wang, W., & Ogai, H. (2022) · IEEE Sensors Journal · doi:10.1109/jsen.2022.3186885 · Cited by 24
Incipient Fault Diagnosis Based on DNN with Transfer Learning
Chen, D., Yang, S., & Zhou, F. (2018) · International Conference on Control, Automation and Information Sciences (ICCAIS) · doi:10.1109/iccais.2018.8570702 · Cited by 24
“Literature [21] presented a transfer learning approach for fault diagnosis with shallow neural network in a variety of working conditions.”
BackgroundConvolutional Neural Network Based Two-Layer Transfer Learning for Bearing Fault Diagnosis
Zhang, W., Zhang, P., He, X., & Zhang, D. (2022) · IEEE Access · doi:10.1109/access.2022.3213657 · Cited by 23
“A transfer learning approach based on deep neural networks was presented by Zhang et al. [18], which can fine-tune the network classification layer through a small amount of labelled target data for rolling bearing fault diagnosis.”
MethodConvolutional Neural Networks for Fault Diagnosis Using Rotating Speed Normalized Vibration
Wei, D., Wang, K., Heyns, S., & Zuo, M. J. (2019) · Applied condition monitoring · doi:10.1007/978-3-030-11220-2_8 · Cited by 25
Robustness of transfer learning to image degradation
Ren, S., & Li, C. Q. (2021) · Expert Systems with Applications · doi:10.1016/j.eswa.2021.115877 · Cited by 24
Tan, S., Wang, K., Shi, H., & Song, B. (2022) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2022.3222511 · Cited by 24
“Transfer learning can not only improve the generalization ability of the model but also greatly reduce the computational cost of model retraining [7].”
BackgroundBraig, M., & Zeiler, P. (2022) · IEEE Access · doi:10.1109/access.2022.3233220 · Cited by 24
“Other parameter-based transfer learning approaches using more machine learning methods include [130], [131], and [132] for condition diagnosis and [133] and [134] for condition prognosis.”
MethodPre-Processing Method to Improve Cross-Domain Fault Diagnosis for Bearing
Kim, T., & Chai, J. (2021) · Sensors · doi:10.3390/s21154970 · Cited by 22
Liu, W., Ren, H., Shaheer, M. A., & Awan, J. A. (2021) · International Journal of Precision Engineering and Manufacturing-Green Technology · doi:10.1007/s40684-020-00293-5 · Cited by 20
“[19] learned features from the source data to train the neural network, and transferred some network parameters to the target task to adjust the new model.”
BackgroundBrusa, E. G. M., Delprete, C., & Maggio, L. G. D. (2022) · Mechanics of Advanced Materials and Structures · doi:10.1080/15376494.2022.2102274 · Cited by 21
Transfer Learning-Based Fault Detection System of Permanent Magnet Synchronous Motors
Skowron, M. (2024) · IEEE Access · doi:10.1109/access.2024.3463970 · Cited by 20
“Examples of this approach are discussed in this study [43], [44], [45], [46], [47], [48], [49].”
Latent space alignment based domain adaptation (LSADA) for fault diagnosis of rotating machinery
Kim, Y. C., Ko, J. U., Lee, J., Kim, T.-H., Jung, J. H., & Youn, B. D. (2024) · Advanced Engineering Informatics · doi:10.1016/j.aei.2024.102862 · Cited by 20
Quality Monitoring and Root Cause Diagnosis for Industrial Processes Based on Lasso-SAE-CCA
Dong, J., Sun, R., Peng, K., Shi, Z. J., & Ma, L. (2019) · IEEE Access · doi:10.1109/access.2019.2926067 · Cited by 20
“In recent years, artificial intelligence as a popular direction in artificial intelligence, machine learning achieves lots of results in the fields of knowledge map, speech recognition, natural language processing, image recognition, computer vision, etc [13].”
BackgroundGuo, F., Zhang, Y.-C., Wang, Y., Ren, P.-J., & Wang, P. (2021) · Mathematical Problems in Engineering · doi:10.1155/2021/8891424 · Cited by 29
A Diagnosis Method for the Compound Fault of Gearboxes Based on Multi-Feature and BP-AdaBoost
Zhang, Y., Jia, Y., Wu, W., Cheng, Z., Su, X., & Lin, A. (2020) · Symmetry · doi:10.3390/sym12030461 · Cited by 21
Dong, J., Su, D., Gao, Y., Wu, X., Jiang, H., & Chen, T. (2023) · Measurement Science and Technology · doi:10.1088/1361-6501/acc04a · Cited by 19
“Zhao et al [30] achieved improved prediction accuracy of source domain data by training the model using a large amount of source domain data and later fine-tuning the model using a small amount of target domain data.”
Souza, A. C. O. E., de Souza, M. B., Jr., & da Silva, F. V. (2023) · Evolving Systems · doi:10.1007/s12530-023-09523-y · Cited by 19
“Zhang et al. (2017) evaluated the performance of TL for bearing fault diagnosis when the working conditions change (such as the bearing fault diameters and the motor load and speed).”
Xu, Z., Zhao, K., Zhang, W., Miao, W., Sun, K., Wang, J., & Bashir, M. B. (2025) · Journal of Industrial Information Integration · doi:10.1016/j.jii.2025.100854 · Cited by 19
Convolutional Autoencoder-Based Flaw Detection for Steel Wire Ropes
Zhang, G., Tang, Z., Zhang, J., & Gui, W. (2020) · Sensors · doi:10.3390/s20226612 · Cited by 19
“Flaw detection is an important and challenging task in many disciplines, such as hot strip mill rolling [1], the maintenance of bearings in rotary machinery systems [2,3], minerals processing [4], and the maintenance of steel wire ropes (SWRs) [5].”
BackgroundApplication of Fault Diagnosis of Seawater Hydraulic Pump Based on Transfer Learning
Miao, Y., Jiang, Y., Huang, J., Zhang, X., & Han, L. (2020) · Shock and Vibration · doi:10.1155/2020/9630986 · Cited by 19
A new bearing fault diagnosis method using elastic net transfer learning and LSTM
Song, X., Zhu, D., Pan, L., & An, L. (2021) · Journal of Intelligent & Fuzzy Systems · doi:10.3233/jifs-210503 · Cited by 19
Lu, H., Zhao, X., Tao, B., & Ding, H. (2021) · Mechanical Systems and Signal Processing · doi:10.1016/j.ymssp.2021.108480 · Cited by 21
Gellrich, S., Filz, M.-A., Wilde, A.-S., Beganovic, T., Mattheus, A., Abraham, T., & Herrmann, C. A. (2021) · Procedia CIRP · doi:10.1016/j.procir.2021.11.153 · Cited by 19
Son, S., Lee, H., Jeong, D., Sun, K. H., & Oh, K. (2024) · Mechanical Systems and Signal Processing · doi:10.1016/j.ymssp.2025.112561 · Cited by 19
Combining Deep Learning with Signal-image Encoding for Multi-Modal Mental Wellbeing Classification
Woodward, K., Kanjo, E., & Tsanas, A. (2023) · ACM Transactions on Computing for Healthcare · doi:10.1145/3631618 · Cited by 20
“Finally, b 1 and b 2 represent the bias vectors of the hidden and output layer, respectively [100]: Batch normalisation has been used within the network to normalise the inputs of each layer so they have a mean of 0 and standard deviation of 1 this enables the models to train quicker, allows for…”
MethodIntelligent Anomaly Detection of Machine Tools based on Mean Shift Clustering
Netzer, M., Michelberger, J., & Fleischer, J. (2020) · Procedia CIRP · doi:10.1016/j.procir.2020.03.043 · Cited by 18
Dutta, S., Basu, B., & Talukdar, F. A. (2021) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2021.3108230 · Cited by 18
“To diagnose motor faults, deep learning approaches such as neural-fuzzy logic [17], deep auto-encoder network [18], artificial neural network (ANN) [19] and convolutional neural network (CNN) [20] have been reported.”
Khan, A., Kim, J.-S., & Kim, H. S. (2021) · Mathematics · doi:10.3390/math10010080 · Cited by 19
Multisource cross-domain fault diagnosis of rolling bearing based on subdomain adaptation network
Wang, Z., Huang, W., Chen, Y., Jiang, Y., & Peng, G. (2022) · Measurement Science and Technology · doi:10.1088/1361-6501/ac7941 · Cited by 19
“On the other hand, the above models also have limitations when dealing with changing operating conditions [13].”
Li, F., Wang, L., Wang, D., Jun, W., & Zhao, H. (2023) · Measurement Science and Technology · doi:10.1088/1361-6501/aced5b · Cited by 17
Ahsan, M., & Bismor, D. (2022) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2022.3192254 · Cited by 17
Intelligent Embedded Load Detection at the Edge on Industry 4.0 Powertrains Applications
Akhtari, S., Pickhardt, F., Pau, D. P., Pietro, A. D., & Tomarchio, G. (2019) · IEEE International Forum on Research and Technology for Society and Industry (RTSI) · doi:10.1109/rtsi.2019.8895598 · Cited by 17
“As discribed in detail in [8], screwing or glewing the sensorboard to the drivebox have shown good results.”
Background
Metadata
- Authors
- Zhang, R., Tao, H., Wu, L., & Guan, Y.
- Affiliations
- Capital Normal University (CN)
- Venue
- IEEE Access
- Published
- 2017
- Volume
- 5
- Pages
- 14347-14357
- ISSN
- 2169-3536 (ISSN-L)
- OpenAlex
- W2731372149
- Cited by
- 378
- References
- 27
- Citations by year
- 2026: 23 · 2025: 29 · 2024: 37 · 2023: 48 · 2022: 62 · 2021: 62 · 2020: 58 · 2019: 44 · 2018: 14 · 2017: 1
- FWCI
- 20.10
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Locations
- IEEE Access (publishedVersion)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Funders
- National Natural Science Foundation of China (61202027)
- Beijing Natural Science Foundation of China (4122015)
- Project of Construction of Innovative Teams and Teacher Career Development for Universities and Colleges under Beijing Municipality (IDHT20150507)
- Topics
- Physical Sciences › Engineering › Control and Systems Engineering › Machine Fault Diagnosis Techniques
- Physical Sciences › Engineering › Control and Systems Engineering › Fault Detection and Control Systems
- Physical Sciences › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
- Keywords
- transfer learning, bearing fault diagnosis, artificial neural networks, changing working conditions, domain adaptation, distribution shift, vibration signal classification
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.