Zan Wang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Zan Wang has a total of 3 co-authors. Here are the top co-authors by number of shared publications:
- Hui Lu
School of Electronic and Information Engineering, Beihang University, Beijing, China
2 shared publications - Yuhui Shi
Southern University of Science and Technology
2 shared publications - Xianpeng Wang
Northeastern University
1 shared publication
Latest Publications
- 8 August 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 73 (00189456) , 1-13
Unmanned Aerial Vehicle Flight Data Anomaly Detection Based on Multirate-Aware LSTM
With the widespread use of unmanned aerial vehicle (UAV), health status monitoring is critical for flight safety, making anomaly detection a focus of attention. In general, UAV flight data are multi-rate multivariate time series (MR-MTS) acquired by multiple sensors at different sampling rates, while the existing methods are mainly designed for multivariate time series (MTS). Moreover, traditional methods that tune MR-MTS to MTS may artificially change naturally occurring temporal dependencies. To address these challenges, a novel Multi-Rate Aware LSTM, called MRA-LSTM, is proposed for UAV flight data anomaly detection. First, without manual tuning, a multi-rate aware structure is proposed to directly model MR-MTS UAV flight data. Second, to avoid the higher-rate variates “masking” the multiple temporal dependencies present in the lower-rate variates, a multiscale update mechanism is proposed to trade-off information entropy from different rates. Finally, a hierarchical state excitation is proposed to adaptively control the importance of each inferred compressed representation to the output module. Experimental results demonstrate the effectiveness of the proposed method, as well as its superiority to other state-of-the-art peer competitors.
- 8 August 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 73 (00189456) , 1-13
Unmanned Aerial Vehicle Flight Data Anomaly Detection Based on Multirate-Aware LSTM
With the widespread use of unmanned aerial vehicle (UAV), health status monitoring is critical for flight safety, making anomaly detection a focus of attention. In general, UAV flight data are multi-rate multivariate time series (MR-MTS) acquired by multiple sensors at different sampling rates, while the existing methods are mainly designed for multivariate time series (MTS). Moreover, traditional methods that tune MR-MTS to MTS may artificially change naturally occurring temporal dependencies. To address these challenges, a novel Multi-Rate Aware LSTM, called MRA-LSTM, is proposed for UAV flight data anomaly detection. First, without manual tuning, a multi-rate aware structure is proposed to directly model MR-MTS UAV flight data. Second, to avoid the higher-rate variates “masking” the multiple temporal dependencies present in the lower-rate variates, a multiscale update mechanism is proposed to trade-off information entropy from different rates. Finally, a hierarchical state excitation is proposed to adaptively control the importance of each inferred compressed representation to the output module. Experimental results demonstrate the effectiveness of the proposed method, as well as its superiority to other state-of-the-art peer competitors.
- 28 November 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 73 (00189456) , 1-12
Lightweight CNN Architecture Design Based on Spatial–Temporal Tensor and Its Application in Bearing Fault Diagnosis
Bearing is a failure-prone component in rotating machinery equipment, and various task conditions make bearing fault diagnosis (BFD) a challenging task. Despite the great success of convolutional neural network (CNN) in feature extraction, most of them are based on manual tuning, and it is not easy to determine a unified CNN architecture with an effective balance between accuracy and computational resources [parameters and floating point operations (FLOPs)]. In this article, an automatic CNN architecture design method called AUTO-CNN is proposed to address the above issues. First, a novel representation learning method (RLM) based on spatial–temporal tensors (STTs) is proposed, in which AUTO-CNN can use 2-D multiscale convolutions to capture more feature hierarchy, i.e., temporal variabilities and spatial characteristics. Second, unlike most of the current nontask-specific studies that establish deeper and more complex networks for better performance, this article investigates lightweight CNNs with limited resources under task-specific applications. Finally, to speed up the design process, an efficient hierarchical encoding strategy and space exploration strategy are proposed to avoid inefficient architecture generation and reduce CNNs training time. Experiments on four real-world BFD tasks demonstrate that the proposed method outperforms the peer competitors, including machine learning, deep learning, and other CNN-based methods.
- 28 November 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 73 (00189456) , 1-12
Lightweight CNN Architecture Design Based on Spatial–Temporal Tensor and Its Application in Bearing Fault Diagnosis
Bearing is a failure-prone component in rotating machinery equipment, and various task conditions make bearing fault diagnosis (BFD) a challenging task. Despite the great success of convolutional neural network (CNN) in feature extraction, most of them are based on manual tuning, and it is not easy to determine a unified CNN architecture with an effective balance between accuracy and computational resources [parameters and floating point operations (FLOPs)]. In this article, an automatic CNN architecture design method called AUTO-CNN is proposed to address the above issues. First, a novel representation learning method (RLM) based on spatial–temporal tensors (STTs) is proposed, in which AUTO-CNN can use 2-D multiscale convolutions to capture more feature hierarchy, i.e., temporal variabilities and spatial characteristics. Second, unlike most of the current nontask-specific studies that establish deeper and more complex networks for better performance, this article investigates lightweight CNNs with limited resources under task-specific applications. Finally, to speed up the design process, an efficient hierarchical encoding strategy and space exploration strategy are proposed to avoid inefficient architecture generation and reduce CNNs training time. Experiments on four real-world BFD tasks demonstrate that the proposed method outperforms the peer competitors, including machine learning, deep learning, and other CNN-based methods.