Wen-An Zhang

Wen-An Zhang

Auto-generated profile, based on publicly available information

Wen-An Zhang

Zhejiang University of Technology

Research Focus & Metrics

Academic Career Length

21Years (2006-Present)

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

Representative Publications

View All Publications
17 May 2017 in IEEE Transactions on Systems, Man, and Cybernetics: Systems
Verified
Journal Article
Closed access
BCBo Chen
Bo Chen
DHDaniel W. C. Ho
Daniel W. C. Ho
WZWen-An Zhang
Wen-An Zhang
LYLi Yu
Li Yu
This paper studies the distributed dimensionality reduction fusion estimation problem for a class of cyber-physical systems (CPSs) under denial-of-service (DoS) attacks. The problem is modeled under the resource constraints (i.e., bandwidth or energy) for the defender and attacker. Based on a new attack and compensation model, a recursive distributed Kalman fusion estimator (DKFE) is designed for the addressed CPSs. Though the optimization objects of the defender and attacker are opposite, the corresponding optimization problems are established based on different available information. In this case, an explicit form of suboptimal dimensionality reduction is given against DoS attacks, while an effective attack strategy is proposed for the attacker. A stability condition is derived such that the mean square error of the designed DKFE is bounded. Two illustrative examples are given to show the effectiveness of the proposed methods.

20 October 2020 in IEEE Transactions on Automatic Control
Verified
Journal Article
Closed access
TLTongxiang Li
Tongxiang Li
BCBo Chen
Bo Chen
LYLi Yu
Li Yu
WZWen-An Zhang
Wen-An Zhang
An active security control approach is developed in this paper for cyber-physical systems (CPSs) under denialof-service (DoS) attacks, where DoS attacks exist in both the sensor-to-controller (S-C) channel and the controller-toactuator (C-A) channel. Due to the cost constraints of attacks, it is reasonable to consider that the number of maximum continuous DoS attacks in both the S-C and the C-A channels is bounded. Then, to defend the two-channel DoS attacks, an active security control strategy that makes full use of the unattacked intervals is designed to ensure that the control inputs are updated timely in each period. Meanwhile, a security controller that contains both the current and future control inputs is designed. Under the active security control strategy and the security controller, the addressed CPS under twochannel DoS attacks can be asymptotically stable without losing the control performance. Finally, both the simulations and experiments are given to demonstrate the effectiveness of the proposed active security control approach.

12 November 2021 in IEEE Transactions on Cybernetics
Verified
Journal Article
Closed access
DHDajian Huang
Dajian Huang
WZWen-An Zhang
Wen-An Zhang
FGFanghong Guo
Fanghong Guo
WLWeijiang Liu
Weijiang Liu
XSXiaoming Shi
Xiaoming Shi
This article presents an intelligent fault diagnosis method for wind turbine (WT) gearbox by using wavelet packet decomposition (WPD) and deep learning. Specifically, the vibration signals from the gearbox are decomposed using WPD and the decomposed signal components are fed into a hierarchical convolutional neural network (CNN) to extract multiscale features adaptively and classify faults effectively. The presented method combines the multiscale characteristic of WPD with the strong classification capacity of CNNs, and it does not need complex manual feature extraction steps as usually adopted in existing results. The presented CNN with multiple characteristic scales based on WPD (WPD-MSCNN) has three advantages: 1) the added WPD layer can legitimately process the nonstationary vibration data to obtain components at multiple characteristic scales adaptively, it takes full advantage of WPD and, thus, enables the CNN to extract multiscale features; 2) the WPD layer directly sends multiscale components to the hierarchical CNN to extract rich fault information effectively, and it avoids the loss of useful information due to hand-crafted feature extraction; and 3) even if the scale changes, the lengths of components remain the same, which shows that the proposed method is robust to scale uncertainties in the vibration signals. Experiments with vibration data from a production wind farm provided by a company using condition monitoring system (CMS) show that the presented WPD-MSCNN method is superior to traditional CNN and multiscale CNN (MSCNN) for fault diagnosis.

26 July 2024 in Science Advances
Verified
Journal Article
Open access
YQYe Qiu
Ye Qiu
FWFangnan Wang
Fangnan Wang
ZZZhuang Zhang
Zhuang Zhang
KSKuanqiang Shi
Kuanqiang Shi
YSYi Song
Yi Song
HWHuaping Wu
Huaping Wu
Replicating human somatosensory networks in robots is crucial for dexterous manipulation, ensuring the appropriate grasping force for objects of varying softness and textures. Despite advances in artificial haptic sensing for object recognition, accurately quantifying haptic perceptions to discern softness and texture remains challenging. Here, we report a methodology that uses a bimodal haptic sensor to capture multidimensional static and dynamic stimuli, allowing for the simultaneous quantification of softness and texture features. This method demonstrates synergistic measurements of elastic and frictional coefficients, thereby providing a universal strategy for acquiring the adaptive gripping force necessary for scarless, antislippage interaction with delicate objects. Equipped with this sensor, a robotic manipulator identifies porcine mucosal features with 98.44% accuracy and stably grasps visually indistinguishable mature white strawberries, enabling reliable tissue palpation and intelligent picking. The design concept and comprehensive guidelines presented would provide insights into haptic sensor development, promising benefits for robotics.

17 June 2020 in IEEE Transactions on Industrial Electronics
Verified
Journal Article
Closed access
JZJunwei Zhu
Junwei Zhu
CGCao-Yuan Gu
Cao-Yuan Gu
SDSteven X. Ding
Steven X. Ding
WZWen-An Zhang
Wen-An Zhang
Xin WangXin Wang
Xin Wang
LYLi Yu
Li Yu
In a networked multi-axis motion control task, faults in any motor will cause the performance degradation of cooperative operation, which may considerably affect the whole network and the quality of products. The main objective of this paper is to propose an improved observer-based fault-tolerant tracking control approach for industrial multi-agent systems. Firstly, a group of new distributed intermediate estimators is presented, where the design structure is modified to enhance the feasibility of the estimation scheme. It is shown that the both of the nominal distributed intermediate estimator and the traditional extended state observer are special cases of the proposed estimator. Secondly, the estimation performance can be improved significantly via an online reinforcement learning estimation strategy, whose core is an adaptive switching mechanism integrated with a function block of source fault mode localization. Benefiting from satisfactory estimation results, good fault-tolerant tracking control performance can be guaranteed despite of multiple faults and disturbances. The application to a networked multi-axis motion control system demonstrates the effectiveness and superiority of the proposed method.

11 July 2024 in IEEE Transactions on Intelligent Transportation Systems
Verified
Journal Article
Closed access
FHFo Hu
Fo Hu
LZLekai Zhang
Lekai Zhang
XYXusheng Yang
Xusheng Yang
WZWen-An Zhang
Wen-An Zhang
Detecting driver fatigue is critical for ensuring traffic safety. Electroencephalography (EEG) is the golden standard for brain activity measurement and is considered a good indicator of detecting driver fatigue. However, the current driver fatigue detection algorithm has limitations in mining and fusing the spatiotemporal characteristics of EEG signals. In this paper, we propose a multi-branch deep learning network named spatio-temporal fusion network with brain region partitioning strategy (STFN-BRPS) to improve the accuracy and robustness of driver fatigue recognition. Initially, we develop a recurrent multi-scale convolution module (RMSCM) comprising a multi-scale convolution sub-module, a CNN-Bi-LSTM sub-module, and a residual structure branch. RMSCM effectively extracts highly discriminative long short-term temporal feature information. Secondly, we propose a dynamic graph convolution module and a spatial graph edges’ importance weight assignment method based on brain region partitioning strategy, which can acquire intrinsic spatial feature information between electrodes. Thirdly, we design a feature fusion module (FFM) that utilizes channel attention to fuse long short-term temporal and spatial features. FFM learns and prioritizes the significance and relevance of each channel in the fused features. Finally, the fused spatio-temporal features are passed into the classification module to obtain the predicted driver fatigue state. Extensive comparison and ablation studies are conducted on EEG signals collected from real-world driving scenarios. The results demonstrate that the proposed STFN-BRPS model delivers superior classification performance compared to the mainstream methods. This study establishes a benchmark for EEG-based driver fatigue detection and related deep-learning modeling work.