Yuqian YANG

Mr. Yuqian YANG

orcid

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

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

Representative Publications

View All Publications
11 January 2024 in IEEE Transactions on Instrumentation and Measurement
Verified
Journal Article
Closed access
JSJie Shen
Jie Shen
SYShusen Yang
Shusen Yang
CZCong Zhao
Cong Zhao
Xuebin RenXuebin Ren
Xuebin Ren
PZPeng Zhao
Peng Zhao
SWShuaijun Wu
Shuaijun Wu
Intelligent equipment fault diagnosis based on Federated Transfer Learning (FTL) attracts considerable attention from both academia and industry. It allows real-world industrial agents with limited samples to construct a fault diagnosis model without jeopardizing their raw data privacy. Existing approaches, however, can neither address the intense sample heterogeneity caused by different working conditions of practical agents, nor the extreme fault label scarcity, even zero, of newly deployed equipment. To address these issues, we present FedLED, the first unsupervised vertical FTL equipment fault diagnosis method, where knowledge of the unlabeled target domain is further exploited for effective unsupervised model transfer. Results of extensive experiments using data of real equipment monitoring demonstrate that FedLED obviously outperforms SOTA approaches in terms of both diagnosis accuracy (up to 4.13×) and generality. We expect our work to inspire further study on label-free equipment fault diagnosis systematically enhanced by target domain knowledge.

15 June 2022 in Applied Sciences
Verified
Journal Article
Open access
PDF file
JSJie Shen
Jie Shen
YHYijun Hao
Yijun Hao
YYYuqian YANG
Yuqian YANG
CZCong Zhao
Cong Zhao
Although fifth-generation (5G) wireless communication can ] support well a high data rate of transmission, issues such as base station (BS) failure and poor BS signals may cause serious interruption problems. This paper studies the user-BS selection strategy with received signal strength indication (RSSI)-based reliability in 5G wireless networks. First, reliability is defined on the basis of the RSSI and failure probability of the BS. The problem is modeled as a selection strategy optimization problem with BS capacity and receiving sensitivity as constraints. Second, the original problem can be transformed into a resource allocation problem with probabilistic constraints. For the situation where user distribution is known, we used dynamic programming to obtain the optimal BS selection strategy. For the situation where user distribution is unknown, starting from user trajectory data, we used the space–time density estimation method based on the Epanechnikov kernel to estimate user density and bring it into dynamic programming to obtain the optimal selection strategy. Simulation results show that our density estimation algorithm is more accurate than the commonly used density estimation algorithm. Compared with the distance-based optimization method, our RSSI-based optimization method also improved the communication signal quality under different scenarios.

14 March 2023 in Applied Sciences
Verified
Journal Article
Open access
PDF file
YYYuqian YANG
Yuqian YANG
BWBo Wang
Bo Wang
CZCong Zhao
Cong Zhao
For rapidly developing smart manufacturing, Industrial ICT Systems (IICTSs) have become critical to safe and reliable production, and effective monitoring of complex IICTSs in practice is necessary but challenging. Since such monitoring data are organized generally as semi-structural logs, log parsing, the fundamental premise of advanced log analysis, has to be comprehensively addressed. Because of unrealistic assumptions, high maintenance costs, and the incapability of distinguishing homologous logs, existing log parsing methods cannot simultaneously fulfill the requirements of complex IICTSs simultaneously. Focusing on these issues, we present LogParser, a deep learning-based framework for both online and offline parsing of IICTS logs. For performance evaluation, we conduct extensive experiments based on monitoring log sets from 18 different real-world systems. The results demonstrate that LogParser achieves at least a 14.5% higher parsing accuracy than the state-of-the-art methods.

10 January 2025 in IEEE Transactions on Transportation Electrification
Verified
Journal Article
Closed access
YCYanwen Chen
Yanwen Chen
CZCong Zhao
Cong Zhao
SYShusen Yang
Shusen Yang
PZPeng Zhao
Peng Zhao
Xuebin RenXuebin Ren
Xuebin Ren
SWShuaijun Wu
Shuaijun Wu
On-site lithium-ion batteries’ state-of-health (SoH) estimation is of crucial importance for reliable operations of electric vehicles (EVs). Yet, due to the low quality of unlabeled real-time field data, diverse operating environments of in-service EVs, and limited computational capability of onboard devices, existing techniques established on data from well-controlled experimental environments are not practical for real-world EVs’ SoH estimation. Accurate and rapid SoH estimation based on field data of in-service EVs still remains quite challenging. To tackle this challenge, we present an on-site SoH estimation (OSE) method using in-service EV field data through a new knowledge-embedded deep transfer learning (DTL) model. Initially, a universal data preprocessing approach integrating mechanism knowledge is designed to process low-quality data under diverse operating environments. Then, we develop a domain-adaptive hybrid deep neural network (DAHDNN) model suitable for unlabeled field data, which can be deployed via an edge cloud collaborative framework to meet actual computational capability. We demonstrate the superiority of our method across four real datasets, where OSE’s estimation error is decreased by up to 78.5% compared with the state-of-the-art methods. The results indicate that the proposed method has good generalizability and reliability for SoH estimation on real-time field data.

23 December 2024 in IEEE Transactions on Industrial Informatics
Verified
Journal Article
Closed access
YYYuqian YANG
Yuqian YANG
CZCong Zhao
Cong Zhao
SYShusen Yang
Shusen Yang
XZXu Zongben
Xu Zongben
The advent of 5G wireless technology marks a significant milestone in telecommunications, enhancing consumer and industrial applications through Industry 4.0 technologies. The radio access network (RAN) and its downlink throughput are vital for Internet service providers. However, ensuring 5G RAN downlink throughput reliability requires robust failure diagnosis strategies for quick identification and resolution, posing challenges in cost efficiency, expert trustworthiness, and adaptability. We present 5G RAN Downlink Throughput Abnormality Diagnosis (5GR-DTAD), a diagnostic framework that fusing domain expertise with machine learning techniques, incorporating both feed-forward and long short-term memory (LSTM) neural networks. Experimental results on real-world data from multiple base stations show that 5GR-DTAD outperforms existing methods in precision, recall, and F1 scores by up to 29.85%, 42.28%, and 35.74%, respectively. 5GR-DTAD improves diagnostic accuracy while minimizing reliance on labeled data, offering an adaptable and cost-effective solution for various 5G RAN conditions.

12 June 2026 in IEEE Transactions on Industrial Informatics
Verified
Journal Article
Closed access
Xuebin RenXuebin Ren
Xuebin Ren
QHQing Han
Qing Han
SYShusen Yang
Shusen Yang
YYYuqian YANG
Yuqian YANG
Federated learning (FL) empowers numerous industrial applications by analyzing tremendous data from distributed smart devices. To reduce communication costs and training delays, momentum-based optimizers are often adopted in FL for training acceleration. Meanwhile, considering frequent model exchange in FL, differential privacy (DP) is also utilized to provide a rigorous privacy guarantee. Therefore, it is promising to combine momentum-based FL with DP for achieving efficient and private FL. However, besides impacting the FL model utility, the added noise would also exacerbate the overshoot issue in momentum-based FL optimization. To this end, we propose KF4FL, a DP-enhanced and momentum-accelerated FL framework by exploring the application of Kalman filter (KF), which can achieve both high model utility and stable FL training without compromising the privacy guarantee. Specifically, KF4FL is a two-fold KF scheme consisting of a gradient noise filtering for reducing the impact of noise in model utility, and a parameter overshoot filtering for stability enhancement in momentum-based training. Besides, by adapting the KF variant of Kalman-consensus information filter, we further propose KF4FL+, an efficient extension of KF4FL in the decentralized FL setting. Extensive experiments demonstrate that KF4FL can reduce up to 5$\%$ accuracy loss and 20$\%$ convergence time than the state-of-the-art methods. KF4FL+ further improves consensus efficiency by 10$\%$ under sparse network topologies.