xiao li

Dr. xiao li


Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

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

Representative Publications

View All Publications
2 November 2023 in Measurement Science and Technology
Verified
Journal Article
Open access
PDF file
XLxiao li
xiao li
FZFeng-Liang Zhang
Feng-Liang Zhang
Fault diagnosis is a crucial technology for ensuring the reliable and efficient operation of industrial systems. With the advancement of industrial informatization and intelligence, fault diagnosis methods have the trend shifting from traditional signal processing to deep learning. However, traditional deep learning models are not suitable for industrial scenarios with limited labeled data, imbalanced categories. To address these challenges, this paper proposes a novel approach based on semi-supervised generative adversarial networks (SGANs) to systematically study the fault diagnosis of rolling bearings in the case of unlabeled samples and sparsely labeled samples. In this work, the vibration time-domain vibration signal of the bearing is firstly transformed into a spectrum signal through the fast Fourier transform. This transformed signal is then fed into the GAN model to extract multi-layer sensitive features, providing a deeper understanding of the underlying fault characteristics. Subsequently, the SGAN method utilizes unsupervised learning via spectral clustering algorithms to automatically classify fault patterns in industrial equipment. Furthermore, it enhances semi-supervised learning by incorporating limited label information through softmax functions, effectively discerning the authenticity of unlabeled data. For the effectiveness of SGAN for bearing fault diagnosis, two diverse datasets are utilized including the widely-used Case Western Reserve University dataset and data acquired from South Ural State University. Compared to alternative models, the results underscore SGAN’s robustness, achieving high recognition accuracy and clustering performance. The proposed methodology contributes to the advancement of fault diagnosis technologies by combining unsupervised and semi-supervised learning techniques.

2 September 2024 in Measurement Science and Technology
Verified
Journal Article
Closed access
XLxiao li
xiao li
YDYu-Xia Dong
Yu-Xia Dong
WXWei Xiang
Wei Xiang
The utilization of building information modeling (BIM) within digital technology facilitates the creation of three-dimensional representations for monitoring data in large-scale civil infrastructure. In response to the need for intelligent structural management, this study establishes a structural health monitoring (SHM) system and foundational framework based on digital twins. This framework integrates information from various sources and facilitates collaborative efforts for structural operation and maintenance. Additionally, the SHM system integrates actual monitoring measurements and early warning mechanisms to consolidate multi-source monitoring data with BIM. Through real-time analysis, the system provides insights into the operational status of bridges, capturing geometric, physical, and performance evolution characteristics. To construct the system, engineering challenges are initially digitized, with appropriate sensors deployed on real bridge structures to monitor dynamic (acceleration) and static (strain, displacement) physical information during bridge operation. Subsequently, through wireless communication and data storage technologies, the monitored physical data serves as input for mode identification and early warning algorithms, facilitating the acquisition of structural performance information. Finally, three-dimensional display technology enables real-time calculation and rendering of BIM models, fostering the exchange and interaction of monitoring and BIM information, thus enhancing the intelligence of SHM system.

15 April 2024 in Measurement Science and Technology
Verified
Journal Article
Closed access
XLxiao li
xiao li
YDYu-Xia Dong
Yu-Xia Dong
FZFeng-Liang Zhang
Feng-Liang Zhang
Modal analysis is a fundamental and essential research direction in the field of structural engineering. The ultimate goal is to determine the modal parameters of the structures. However, the existing modal analysis algorithms often require a large number of parameter adjustments and manual intervention during operation, which cannot be fully automated. In order to realize the automatic identification of modal parameters, the automatic operational modal identification method (AOMI) is proposed based on the interpolated power spectral density estimation (IPSE). To achieve more precise spectrum analysis in the low-frequency band, IPSE is employed to perform Fourier transform on the original frequency domain segment with optimized frequency resolution. This enhances the sharpness of the obtained spectrum in the low-frequency range, making peak frequencies more discernible. Subsequently, the scale-space peak picking algorithm is used to automatically obtain the peak of the power spectral density (PSD), thus enabling the automatic identification of the natural frequency. Finally, the frequency domain decomposition method (FDD) is used to identify modal parameters based on the natural frequencies. The effectiveness of AOMI is verified through the modal identification of the old steel truss bridge and the three layer framework. Under the environmental excitation, the frequencies identified by the IPSE method is close to that of FDD, Bayesian fast fourier transform (FFT) and covariance driven stochastic subspace identification (SSI-COV). Furthermore, the PSD obtained through IPSE has sharper peak than that of FDD and the Welch’s method. The damping ratio identification accuracy and modal assurance criterion (MAC) are satisfactory in AOMI, which can improve the automatic performance.

1 July 2024 in IEEE Sensors Journal
Verified
Journal Article
Closed access
XLxiao li
xiao li
FZFeng-Liang Zhang
Feng-Liang Zhang
JLJun Lei
Jun Lei
WXWei Xiang
Wei Xiang
Damage identification based on deep learning has become a hot topic recently. Damage identification and classification methods based on neural networks are much concerned, and so reducing manual participation in labeling data as much as possible has been attracted increasing attention. This paper presents the work on developing a damage detection method by using limited information features to improve the performance of clustering in unsupervised learning. In order to improve the accuracy of unsupervised clustering algorithm, a damage classification method is proposed by using measured data based on deep learning network. A generative adversarial network (GAN) is introduced into the unsupervised clustering process, which is able to extract effective multi-scale features and had better generalization ability. The structure and training method of GAN-SC are studied, and GAN and Spectral Clustering(SC) algorithm are combined for damage diagnosis. The proposed GAN-SC framework harnesses the synergy of GAN’s ability to extract effective multi-scale features and SC’s potential to generate virtual labels, improving generalization capabilities. Some signal preprocessing methods are used to reduce the noise of the original data while retaining the high features of the fault data as much as possible. The proposed method is verified by a numerical bridge dataset and a popular experiment dataset from the Western Reserve University, using cluster evaluation indices (NMI and ARI). The results show that the superior recognition capabilities of GAN-SC emphasizes its potential for real-world applications in structural damage detection by generating virtual labels through spectral clustering.

6 February 2024
Verified
Book Chapter
Closed access
PDF file
WXWei Xiang
Wei Xiang
XLxiao li
xiao li
FZFeng-Liang Zhang
Feng-Liang Zhang