Bo Yang

Bo Yang

Auto-generated profile, based on publicly available information

Bo Yang

Department of Management Science and Data Science, Sichuan University, Chengdu, China

Research Focus & Metrics

Academic Career Length

11Years (2016-Present)

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

Representative Publications

View All Publications
3 July 2024 in IEEE Transactions on Industrial Electronics
Verified
Journal Article
Closed access
DZDong Zhao
Dong Zhao
BYBo Yang
Bo Yang
YLYueyang Li
Yueyang Li
FZFeifei Zhang
Feifei Zhang
Cyber attack detection plays a crucial role in ensuring cyber security of control systems. However, the reported methods for cyber attack detection often rely on large-scale upgrades of field modules or modification of specific monitoring signals. The resulting issues, such as impacts on system control performance or economic losses, make these methods challenging to be widely accepted in practice. To address this challenge, this article proposes a new replay attack detection scheme, combining dynamical system characteristics and data-driven implementation, while the scheme only needs to be implemented in the control and monitoring side. Specifically, considering the effect of replay attacks and the response of the control system, a dynamical delay estimation method is proposed for detecting replay attacks. Thus, the detection logic is established by characterizing and comparing the fluctuation ranges of dynamical delay. A sliding window is adopted for quantifying the dynamical delay between the input and output data of the cyber-physical control system. Moreover, the randomized algorithm method is introduced to determine the initial value of the delay estimation method, while the online updating of dynamical delay estimation is given for real-time replay attack detection. To highlight the replay attack effect, a novel window adaptive strategy is developed to achieve adaptive detection and tracking of replay attacks. Finally, the performance and effectiveness of the proposed detection method are verified through experiments on chlorosilane distillation.

28 June 2023 in IEEE Transactions on Instrumentation and Measurement
Verified
Journal Article
Closed access
YSYilin Shi
Yilin Shi
JLJince Li
Jince Li
HLHongguang Li
Hongguang Li
BYBo Yang
Bo Yang
Imbalanced data samples can adversely affect the performance of industrial process fault diagnosis models. Recently, it has become a valued challenge to expand data samples and reasonably assess their quality. To address this issue, this paper presents an imbalanced data augmentation and assessment method that integrates Wasserstein Time Generative Adversarial Network with Gradient Penalty (WTGAN-GP) and Maximum Information Coefficient with Improved Dynamic Time Warping Distance (MIC-IDTW) indicator. Firstly, the WTGAN-GP effectively tackles the scarcity of fault data by incorporating the Wasserstein distance with gradient penalty into TimeGAN, significantly enhancing the data generation capability and stability of the network. Additionally, the MIC-IDTW is established as a quantitative and interpretable indicator for assessing the quality of generated samples. Finally, this paper validates the performance of WTGAN-GP and MIC-IDTW in addressing the issue of imbalanced data in vibration fault diagnosis for an actual factory centrifugal air compressor. It is demonstrated that the proposed methods can effectively enhance various fault data in the presence of imbalanced fault samples and significantly improve the fault classification performance.

3 February 2022 in ISA Transactions
Verified
Journal Article
Closed access
YWYuehan Wang
Yuehan Wang
JLJince Li
Jince Li
BYBo Yang
Bo Yang
HLHong-Guang Li
Hong-Guang Li

1 November 2021 in Journal of Process Control
Verified
Journal Article
Closed access
HLHongguang Li
Hongguang Li
XTXiaojie Tang
Xiaojie Tang
WZWenjing Zhao
Wenjing Zhao
BYBo Yang
Bo Yang

31 July 2024 in IEEE Transactions on Industrial Informatics
Verified
Journal Article
Closed access
BYBo Yang
Bo Yang
SHShihao Hong
Shihao Hong
HWHairun Wang
Hairun Wang
DZDong Zhao
Dong Zhao
The current mainstream time series prediction methods exhibit commendable accuracy in prediction, but they often lack interpretability. One approach to address this issue is through the utilization of fuzzy cognitive maps for prediction. The multimodal fuzzy cognitive maps method stands out for its superior interpretability and adeptness in handling nonlinear and uncertain problems. However, the traditional modal segmentation method makes it difficult to effectively identify the modal information, affecting the method's effectiveness and accuracy. In this article, we proposed a novel multimodal fuzzy temporal cognitive maps time series prediction method based on complex dynamic slow independent symbol aggregation approximation. First, we constructed complex dynamic slow independent symbol aggregation approximation, which integrates slow features to obtain the modal information of the model. Then, the multimodal model parameters were determined by an optimization algorithm. Finally, a multimodal online matching mechanism based on slow feature tracking was proposed to address transitional states between modals. The validation based on two examples shows that the proposed method can effectively improve the prediction accuracy.

28 March 2025 in IEEE Journal of Emerging and Selected Topics in Industrial Electronics
Verified
Journal Article
Closed access
YSYilin Shi
Yilin Shi
Zukui LiZukui Li
Zukui Li
BYBo Yang
Bo Yang
Data-driven fault diagnosis is a critical component of industrial process monitoring. To more effectively capture the temporal relationships within multi-sensor data and the spatial relationships among sensors, this paper proposed a feature representation and fusion method for fault diagnosis in complex industrial processes. Firstly, a Gramian Angular Field (GAF) method with temporal weighting (TGAF) is developed to convert process time series signals into image sequences, where each sub-image is assigned corresponding temporal weights. Subsequently, features are represented from each sensor's image sequence, and a spatial-weighted multi-channel convolutional neural network (SMCNN) is employed to fuse these features and generate new feature embeddings. Finally, a fault diagnosis model is jointly trained to optimize and balance the weight loss across multiple channels. The effectiveness of the proposed method is validated by utilizing the Tennessee-Eastman (TE) process and Vinyl Acetate Monomer (VAM) process, showing significant enhancements in fault diagnosis accuracy and reliability compared to other similar methods.