Xuewen Zhang

Xuewen Zhang

Auto-generated profile, based on publicly available information

Xuewen Zhang

Fellow IEEE

Research Focus & Metrics

Academic Career Length

20Years (2007-Present)

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

Representative Publications

View All Publications
21 December 2020 in IEEE Transactions on Industrial Informatics
Verified
Journal Article
Closed access
XZXuewen Zhang
Xuewen Zhang
YQYan Qin
Yan Qin
Chau YuenChau Yuen
Chau Yuen
LJLahiru Jayasinghe
Lahiru Jayasinghe
XLXiang Liu
Xiang Liu
For health prognostic task, ever-increasing efforts have been focused on machine learning based methods, which are capable of yielding accurate remaining useful life (RUL) estimation for industrial equipment or components without exploring the degradation mechanism. A prerequisite ensuring the success of these methods depends on a wealth of run-to-failure data; however, run-to-failure data may be insufficient in practice. That is, conducting a substantial amount of destructive experiments not only is of high cost but also may cause catastrophic consequences. Out of this consideration, an enhanced RUL framework focusing on data self-generation is put forward for both noncyclic and cyclic degradation patterns for the first time. It is designed to enrich data from a data-driven way, generating realistic-like time-series to enhance current RUL methods. First, high-quality data generation is ensured through the proposed convolutional recurrent generative adversarial network, which adopts a two-channel fusion convolutional recurrent neural network. Next, a hierarchical framework is proposed to combine generated data into current RUL estimation methods. Finally, in this article the efficacy of the proposed method is verified through both noncyclic and cyclic degradation systems. With the enhanced RUL framework, an aero-engine system following noncyclic degradation has been tested using three typical RUL models. State-of-the-art RUL estimation results are achieved by enhancing capsule network with generated time-series. Specifically, estimation errors evaluated by the index score function have been reduced by 21.77 $\%$ and 32.67 $\%$ for the two employed operating conditions, respectively. Besides, the estimation error is reduced to zero for the lithium-ion battery system, which presents cyclic degradation.

10 June 2007
Verified
Conference Paper
Closed access
PDF file
ZZZhisheng Zhou
Zhisheng Zhou
SWShiyan Wei
Shiyan Wei
XZXuewen Zhang
Xuewen Zhang
XZXian Zhao
Xian Zhao
This paper proposes a segmentation method based on K-mean and SOM network. Firstly remote sensing image is decomposed by wavelet transform at multiple-scale. Secondly the directional eigenvector of the image is constructed based on the wavelet transform. At coarser scale, we construct 4-dimension eigenvector with feature images, and the images are roughly segmented by K-means algorithm. Then we construct 4-dimension eigenvector with other feature images at fine scale. Based on the results in K-means segmentation and the eigenvector of remote-sensing images at fine scale the images are segmented by SOM network. The experiments about the images segmentation are done in two different ways, one of which is K-means and SOM network simultaneously, and the other of which is mere K-mean. The experiments show that the former has better segmentation results and higher efficiency.

1 July 2012
Verified
Conference Paper
Closed access
SZShuang Zhou
Shuang Zhou
XZXuewen Zhang
Xuewen Zhang
JZJunping Zhang
Junping Zhang
HCHao Chen
Hao Chen
A new scheme integrating segmentation into classification to analyze hyperspectral images is presented in this paper, particularly for images with a very few number of labels and largely adjacent spatial structures. Using pixel-wise semi-supervised support vector machine, the image is classified, and segmented by modified C-V level set in this method. Afterwards, classification and segmentation images are combined with neighborhood voting. Experiments are conducted on a 200-band AVIRIS image of the Northwestern Indiana's Indian Pine site. The integration of the spatial information from the level set segmentation provides classification images with more homogeneous regions and improves the classification accuracy, comparing to the general pixel-wise supervised and semi-supervised classification.

17 November 2020
Verified
Book Chapter
Closed access
PDF file
ZZZhiqiang Zhang
Zhiqiang Zhang
WYWenxin Yu
Wenxin Yu
JZJinjia Zhou
Jinjia Zhou
XZXuewen Zhang
Xuewen Zhang
JTJialiang Tang
Jialiang Tang
ZYZhuo Yang
Zhuo Yang

11 January 2021 in arXiv
Verified
Preprint
Open access
PDF file
XZXuewen Zhang
Xuewen Zhang
YQYan Qin
Yan Qin
Chau YuenChau Yuen
Chau Yuen
LJLahiru Jayasinghe
Lahiru Jayasinghe
XLXiang Liu
Xiang Liu
For health prognostic task, ever-increasing efforts have been focused on machine learning-based methods, which are capable of yielding accurate remaining useful life (RUL) estimation for industrial equipment or components without exploring the degradation mechanism. A prerequisite ensuring the success of these methods depends on a wealth of run-to-failure data, however, run-to-failure data may be insufficient in practice. That is, conducting a substantial amount of destructive experiments not only is high costs, but also may cause catastrophic consequences. Out of this consideration, an enhanced RUL framework focusing on data self-generation is put forward for both non-cyclic and cyclic degradation patterns for the first time. It is designed to enrich data from a data-driven way, generating realistic-like time-series to enhance current RUL methods. First, high-quality data generation is ensured through the proposed convolutional recurrent generative adversarial network (CR-GAN), which adopts a two-channel fusion convolutional recurrent neural network. Next, a hierarchical framework is proposed to combine generated data into current RUL estimation methods. Finally, the efficacy of the proposed method is verified through both non-cyclic and cyclic degradation systems. With the enhanced RUL framework, an aero-engine system following non-cyclic degradation has been tested using three typical RUL models. State-of-art RUL estimation results are achieved by enhancing capsule network with generated time-series. Specifically, estimation errors evaluated by the index score function have been reduced by 21.77%, and 32.67% for the two employed operating conditions, respectively. Besides, the estimation error is reduced to zero for the Lithium-ion battery system, which presents cyclic degradation.