Yisheng Zou

Yisheng Zou

Auto-generated profile, based on publicly available information

Yisheng Zou

School of Computing and Artificial Intelligence, Southwest Jiaotong University, Chengdu, China

Research Focus & Metrics

Academic Career Length

18Years (2009-Present)

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

Representative Publications

View All Publications
18 April 2025 in IEEE Transactions on Circuits and Systems for Video Technology
Verified
Journal Article
Closed access
GWGang Wang
Gang Wang
YZYisheng Zou
Yisheng Zou
SHSonglin He
Songlin He
YWYakun Wang
Yakun Wang
RDRuihong Dai
Ruihong Dai
Image anomaly detection and localization have received widespread interest in the community, and knowledge distillation (KD) has been widely explored. Recently, the reverse distillation (RD) paradigm has successfully mitigated the homogenization of anomaly representations in traditional KD arising from identical or similar teacher-student (T-S) architecture. However, in RD, the lack of an effective means to prevent anomalous patterns in the teacher encoder from being leaked into the student decoder undermines potential modeling discrepancies between the T-S model in anomaly representations. To settle this problem, we propose REverse distillation with latent Anomaly SuppressiON (REASON) method, preventing the student decoder from receiving anomalous patterns by extra means of anomaly filtering during the inference phase, and thus, the student model can only restore representations of anomaly-free images. Specifically, we construct a Siamese teacher encoder architecture, with one branch extracting features from anomaly-free samples and the other synthesizing anomaly features with spatial noise injection from the latent feature level. Next, we design a latent anomaly suppression module to recover normal features from perturbed anomalous features. In this sense, the follow-up student decoder will receive input without abnormal patterns. Thus, representations of the anomaly-free images can be described well, while those of the anomalous images can be well-differentiated between the T-S model. Furthermore, to enhance the model’s anomaly detection and localization capabilities, we propose multi-granularity KD loss to optimize the student decoder to focus on context and local details. Extensive experiments are performed on three benchmark datasets, i.e., MVTec AD, AeBAD, and OCT2017, and the results show the effectiveness and robustness of our proposed approach, which achieves superiority over the current state-of-the-art methods.

27 October 2021 in IEEE Transactions on Instrumentation and Measurement
Verified
Journal Article
Closed access
YZYisheng Zou
Yisheng Zou
SZShijiao Zhao
Shijiao Zhao
YLYongzhi Liu
Yongzhi Liu
ZLZhixuan Li
Zhixuan Li
XSXiaoxin Song
Xiaoxin Song
GDGuofu Ding
Guofu Ding
For data-driven remaining useful life (RUL) prediction of rolling bearing (RB), deep learning methods usually do not consider the difference in distribution due to different operating conditions, which adversely affects the prediction results. Recently, transfer learning has been a research hotspot, and it can mitigate the above problem effectively. However, for different bearings under the same working condition, the data distribution changes due to the location and time of failure. To solve these problems, a transfer prediction model based on the dynamic benchmark (DB) has been proposed to predict the RUL of bearings in this study. The method is divided into three processes. First, a fully convolutional variational autoencoder is used to perform unsupervised learning; next, a domain adaptation method based on the DB is employed for reconstruction; finally, extracted hidden layer features are input to the fully connected layer of the proposed model to obtain the final prediction result. The prediction and health management (PHM) Challenging 2012 and XJTU-SY RB accelerated life test datasets were used for verification. The results showed that the proposed method could significantly improve prediction accuracy and had good stability and generalizability.

27 July 2021 in Measurement Science and Technology
Verified
Journal Article
Closed access
YZYisheng Zou
Yisheng Zou
KSKeming Shi
Keming Shi
YLYongzhi Liu
Yongzhi Liu
GDGuofu Ding
Guofu Ding
KDKun Ding
Kun Ding
The intelligent diagnosis of rolling bearing (RB) faults under different working conditions has attracted significant attention. The two main limitations of existing domain-adaptation-based fault diagnosis methods for RBs are as follows. One is that the source domain transfer fault features contain a large amount of redundant information interfering with domain adaptation. The other is that discrepancies in the distribution between the same class fault samples under different working conditions lead to low transfer diagnosis accuracy. Aiming at overcoming these two limitations, in this study, a cross-domain transfer fault diagnosis model based on Wasserstein adversarial channel compression variational autoencoder (WACCVAE) is proposed. First, fault features are channel-compressed to reduce the interference of redundant features with domain adaptation; an improved variational autoencoder network with a channel compression of fault features—WACCVAE—is proposed. Secondly, the classification module function adopts an inter-class–intra-class distance constraint to improve the distribution alignment ability of same class fault samples for different working conditions. Overall, WACCVAE can accomplish the task of cross-condition transfer fault diagnosis in RBs.

14 June 2021 in Proceedings of the Institution of Mechanical Engineers, Part F: Journal of Rail and Rapid Transit
Verified
Journal Article
Closed access
PDF file
YLYongzhi Liu
Yongzhi Liu
YZYi Sheng Zou
Yi Sheng Zou
YWYu Wu
Yu Wu
HZHao Yang Zhang
Hao Yang Zhang
GDGuo Fu Ding
Guo Fu Ding
The existing bearing temperature fault detection and early warning system has a high false alarm rate and insufficient early warning ability. For this reason, in this study, a method for detecting the abnormal bearing temperature of high-speed trains based on spatiotemporal fusion decision-making was proposed. First, the temperature characteristics of similar bearings were compared and analyzed with different spatial distributions. Then, a bearing abnormal temperature rise detection model based on the analytic hierarchy process (AHP) entropy method was proposed. Second, the temperature characteristics of the same bearings were compared and analyzed with different time distributions. A real-time prediction model of high-speed train bearing temperature anomalies based on Bi-directional Long Short-Term Memory (BILSTM) was proposed. Finally, the D-S evidence theory was used to combine the anomaly detection model based on the AHP entropy method and the anomaly detection model based on BILSTM real-time prediction. Through the comprehensive diagnosis and decision-making of high-speed train bearings from two dimensions of space and time, a more comprehensive and accurate anomaly detection model was realized. The experimental results showed that the spatiotemporal comparison fusion decision model successfully eliminated the misjudgment phenomenon of single-dimension model diagnosis and that it has good early warning ability.

5 October 2022 in IEEE Transactions on Instrumentation and Measurement
Verified
Journal Article
Closed access
ZLZhixuan Li
Zhixuan Li
KZKai Zhang
Kai Zhang
YLYongzhi Liu
Yongzhi Liu
YZYisheng Zou
Yisheng Zou
GDGuofu Ding
Guofu Ding
The transfer learning (TL) method represented by domain adaptation (DA) can effectively improve the prediction accuracy of rolling bearings’ remaining useful life (RUL) under different working conditions. However, the difference in the bearing degradation process under the same working conditions limits the reliability and generalization of the transfer RUL prediction model. Owing to the aforementioned problems, this study proposed an RUL transfer predicting method for rolling bearings based on working conditions’ common benchmark. An attention mechanism autoencoder (AMAE) is proposed to extract the common benchmark under each working condition and improve the commonness between deep features. The dynamic benchmark constraint (DBC) under the same working conditions was proposed to ensure the reliability of a common benchmark and improve the prediction accuracy in the process of benchmark transfer under different working conditions. Verified by Xi’an Jiaotong University (XJTU) and the Changxing Sumyoung Technology Co., Ltd. (SY) bearing datasets, the proposed method can effectively obtain a common benchmark that can be used for DA under various working conditions. In the experimental design of six sets of RUL prediction tests under different working conditions, more than 50% of the experimental tasks have better prediction results using the proposed method. The proposed approach increases the overall prediction accuracy to 11.74% compared with the method without DA. Experimental results show that the proposed method can better meet the needs of intelligent operation and maintenance in practical engineering

4 November 2020 in Shock and Vibration
Verified
Journal Article
Open access
PDF file
YLYongzhi Liu
Yongzhi Liu
YZYi-Sheng Zou
Yi-Sheng Zou
YJYu-Liang Jiang
Yu-Liang Jiang
Hui YuHui Yu
Hui Yu
GDGuo-Fu Ding
Guo-Fu Ding
Intelligent mechanical fault diagnosis has developed very fast in recent years due to the advancement and application of deep learning technologies. Thus, there are many deep learning network models that have been explored in fault classification and diagnosis. However, there are still limitations in research on the relationship between fault location, fault type, and fault severity. In this paper, a novel method for diagnosis of bearing fault using hierarchical multitask convolution neural networks (HMCNNs) is proposed, taking into account the mentioned relationships. The HMCNN model includes a main task and multiple subtasks. In the HMCNN model, a weighted probability is used to reduce the classification error propagation among multitasks to improve the fault diagnosis accuracy. The validity of the proposed method is verified on bearing datasets. Experimental results show that the proposed method is very effective and superior to the existing methods.