Tao Wen

Tao Wen

Auto-generated profile, based on publicly available information

Tao Wen

Beijing Jiaotong University

Research Focus & Metrics

Academic Career Length

16Years (2011-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
3 March 2021 in IEEE Transactions on Industrial Informatics
Verified
Journal Article
Closed access
XMXue Ma
Xue Ma
Chenglin WenChenglin Wen
Chenglin Wen
TWTao Wen
Tao Wen
The federated learning (FL) method based on model aggregation can balance data and protect data privacy, but the existing method is difficult to achieve the same effectiveness as the centralized learning method under data sharing. In addition, it is difficult for the existing federated model to realize the real-time update of the clients' network parameters, because it inhibits the optimal performance of the client. Therefore, this article proposes an asynchronous update paradigm of FL with real-time identification of the client's network parameters to tackle the shortcomings. First, we adopt the linear fusion method based on sequential filtering and fuse the parameters of federated center asynchronously considering communication delay, which can approach the diagnostic accuracy based on the centralized learning. Second, we establish the real-time identification method for the clients based on linear filtering with the new labeled samples obtained at nonequal intervals, which expects the client to acquire better performance. Finally, we test the fault classification ability of the proposed method based on the actual collected fault dataset and the test platform of bearing fault dataset.

14 July 2021 in IEEE Transactions on Intelligent Transportation Systems
Verified
Journal Article
Closed access
TWTao Wen
Tao Wen
GXGuo Xie
Guo Xie
YCYuan Cao
Yuan Cao
BCBaigen Cai
Baigen Cai
With the increasing demand for rail transit, wireless communication technologies are playing a growing significant role in train control systems, which enables the railway systems to provide a higher capacity and more efficient services. However, due to the nature of radio frequency propagation, the quality of the train-to-ground wireless connections is highly dependent on a well-planned deployment of the wayside access points. To improve both the accuracy and the efficiency in railway network planning, in this paper, a deep learning technology is exploited to model the wireless propagation, which was very difficult to deterministically predict at a fast speed in our previous research due to the high computation demanding. In this proposed wireless propagation model, Kalman filter is utilized to update the neural network parameters online, which makes this model can meet the variation of the environment. The numeric evaluation result shows that the deep neural network based wireless channel model can precisely predict the outage probability with a very low computational cost.

21 January 2019 in IEEE Transactions on Intelligent Transportation Systems
Verified
Journal Article
Closed access
TWTao Wen
Tao Wen
DDDeyi Dong
Deyi Dong
QCQianyu Chen
Qianyu Chen
LCLei Chen
Lei Chen
CRClive Roberts
Clive Roberts
In railway condition monitoring, feature classification is a very critical step, and the extracted features are used to classify the types and levels of the faults. To achieve better accuracy and efficiency in the classification, the extracted features must be properly selected. In this paper, maximal information coefficient is employed in two different stages to establish a new feature selection method. By using this proposed two-stage feature selection method, strong features with low redundancy are reserved as the optimal feature subset, which results in the classification process having a more moderate computational cost and good overall performance. To evaluate this proposed two-stage selection method and prove its advantages over others, a case study focusing on the rolling bearing is carried out. The result shows that the proposed selection method can achieve a satisfactory overall classification performance with low-computational cost.

30 November 2022 in IEEE/ASME Transactions on Mechatronics
Verified
Journal Article
Closed access
DWDaichao Wang
Daichao Wang
YLYibin Li
Yibin Li
LJLei Jia
Lei Jia
YSYan Song
Yan Song
TWTao Wen
Tao Wen
The bearing is the key component of rotating mechanical equipment, so the fault diagnosis of bearings is important to improve the reliability and safety of equipment operation. In recent years, feature fusion method has been extensively explored in the health monitoring and fault diagnosis of bearings. However, almost all the existing feature-fusion-based fault diagnosis methods extract features from different signals independently and concatenating them simply. It will lead to the failure of achieving the expected diagnostic accuracy because the complementary fault information is not fully mined and fused. This article proposes a novel bearing fault diagnosis approach based on mutual attention and bilinear model to address these issues. The features extracted from different input are interactive through mutual attention and are fused by the bilinear model, so the complementary fault features are effectively extracted and fine-grained fused. Experiments are conducted on the Paderborn bearing dataset to verify the effectiveness of the proposed method. Results show that the proposed method can effectively extract complementary fault features from different signals and deeply fuse them, and its diagnosis accuracy is up to 99.86%. Its performance is much better than that of simple concatenation and the feature fusion methods proposed in the reference.

1 September 2023 in Chinese Journal of Electronics
Verified
Journal Article
Closed access
XCXiaohan Chen
Xiaohan Chen
Xiaoxi HuXiaoxi Hu
Xiaoxi Hu
TWTao Wen
Tao Wen
YCYuan Cao
Yuan Cao
In the railway transportation industry, fault diagnosis of railway point machines (RPMs) is vital. Because operational vibration signals can reflect the condition of various faults in mechanical devices, vibration sensing and monitoring and more importantly, vibration signal-based fault diagnosis for RPMs have attracted the attention of scholars and engineers. Most vibration signal-based fault-diagnosis methods for RPMs rely on data collected using high-sampling-rate sensors and manual feature extraction, hence are costly and insufficiently robust. To overcome these shortcomings, we propose a double-scale wide first-layer kernel convolutional neural network (DS-WCNN) for RPMs fault diagnosis using inexpensive and low-sampling-rate vibration sensors. The proposed wide first-layer kernels, which extract features from vibration observations, are particularly suitable for low-sampling-rate signals. Meanwhile, the proposed double-scale structure improves accuracy and noise suppression by combining two types of timescale features. Sufficient experiments, including noise addition and comparison, were conducted to demonstrate the robustness and accuracy of the proposed algorithm.

1 July 2020 in Chinese Journal of Electronics
Verified
Journal Article
Open access
PDF file
YSYongkui Sun
Yongkui Sun
YCYuan Cao
Yuan Cao
GXGuo Xie
Guo Xie
TWTao Wen
Tao Wen
Railway point machines (RPMS) are one of the key equipments in the railway system to switch different routes for the trains. Condition monitoring for RPMs is a vital measure to keep train operation safe and reliable. Taking convenience and low cost into consideration, a novel intelligent condition monitoring method for RPMs based on sound analysis is proposed. Time-domain and frequency-domain features are obtained, and normalized using z-score standardization method to eliminate the influences of different dimensions. Binary particle swarm optimization (BPSO) is utilized to select the most significant discrimination feature subset. The effects of the selected optimal features are verified using Support vector machine (SVM), 1-Nearest neighbor (1NN), Random forest (RF), and Naive Bayes (NB). Experiment results indicate SVM performs best on identification accuracy and computing cost compared with the other three classifiers. The identification accuracies on normal switching and reverse switching processes reach 100% and 99.67%, respectively, indicating the feasibility of the proposed method.