Zhenfeng Lu

Zhenfeng Lu

Auto-generated profile, based on publicly available information

Zhenfeng Lu

School of Mechanical Electronic and Information Engineering, China University of Mining and Technology, Beijing, China

Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

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

Representative Publications

View All Publications
13 January 2022 in IEEE Transactions on Industrial Informatics
Verified
Journal Article
Closed access
Xian TaoXian Tao
Xian Tao
DZDapeng Zhang
Dapeng Zhang
WMWenzhi Ma
Wenzhi Ma
ZHZhanxin Hou
Zhanxin Hou
ZLZhenFeng Lu
ZhenFeng Lu
CAChandranath Adak
Chandranath Adak
Unsupervised anomaly detection in real industrial scenarios is challenging since the small amount of defect-free images contain limited discriminative information, and anomaly defects are unpredictable. Although nowadays image reconstruction-based methods are widely being used in various anomaly detection applications, they cannot effectively learn semantic representation, which leads to imperfect reconstruction. In this article, anomaly detection is formulated as a joint problem of feature reconstruction and inpainting in the dual-siamese framework. The proposed approach forces the network to model the feature distribution from the normal area and capture the semantic context for discriminating normal and abnormal areas. It first uses a Siamese architecture to capture discriminative features of defect-free samples and its corresponding defective samples generated by the defect random generation module. A dense feature fusion module is then employed to obtain the dense feature representation of dual input. The second Siamese network is proposed to reconstruct and inpaint the dual-dense features of the previous stage. Compared to the existing methods that mostly employ single image reconstruction, it is beneficial to simultaneously reconstruct and inpaint the information of dense discriminative features. The experimental results on the MVTec AD datasets and some major real industrial datasets demonstrate that our method achieves state-of-the-art inspection accuracy.

28 April 2021 in IEEE Sensors Journal
Verified
Journal Article
Closed access
ZLZhenfeng Lu
Zhenfeng Lu
junfeng Fanjunfeng Fan
junfeng Fan
ZHZhanxin Hou
Zhanxin Hou
SDSai Deng
Sai Deng
CZChao Zhou
Chao Zhou
FJFengshui Jing
Fengshui Jing
The teaching programming mode and offline programming mode of welding robot are essential parts in today's manufacturing industry. However, these modes can't meet the automation requirements and adaptive ability of welding robot. To achieve 3D path acquisition of weld seam for robot autonomous programming, a fast and accurate offline 3D seam extraction method is proposed based on monocular structured light sensor. In this method, gray code and phase-shift code raster images are projected to the workpiece, and the 3D coordinates of the weld are calculated by collecting the workpiece images with raster patterns. The path fitting of robot is completed by polynomial fitting method. The novel monocular structured light sensor used by this paper has compact structure and small volume, and can adapt to a variety of welding working scenes. The combination of gray code and phase shift code makes the measurement accurate and fast, and achieves the effect of full resolution decoding. The experimental results show that the proposed method can complete the task of 3D weld extraction and path fitting, which has the characteristics of high efficiency and strong robustness.

7 June 2021 in IEEE Transactions on Instrumentation and Measurement
Verified
Journal Article
Closed access
Xian TaoXian Tao
Xian Tao
MWma wenzhi
ma wenzhi
ZLZhenfeng Lu
Zhenfeng Lu
ZHZhanxin Hou
Zhanxin Hou
The detection of conductive particle images is an important part of the chip on glass (COG) process and can be used to ensure the performance of electrical connections. The segmentation of conductive particles is essential but a difficult task, since the scale and edge of the conductive particles on the chip and the imaging effect are different. In recent years, methods based on deep learning have become the representative method of image segmentation. However, the currently existing methods cannot fully consider the characteristics of conductive particles and have high model complexity. In this article, a multi-frequency feature learning-based convolutional neural network (CNN) is proposed. The entire network structure consists of a basic U-Net module and multi-frequency module (MFM), which are used to enhance multi-frequency feature fusion of conductive particles and accelerate network training. At the same time, for the feature of particle shape, an active contour without edge (ACWE) loss function is designed to extract the fine contour feature of particles. Experimental results on three datasets show the superiority of the proposed method over the major existing mainstream methods with respect to the three performance indicators: recall, precision, and Intersection-over-Union (IoU).

20 November 2017 in Robotics and Computer-Integrated Manufacturing
Verified
Journal Article
Closed access
GYGuotao Yin
Guotao Yin
ZZZhenghe Zhu
Zhenghe Zhu
HGHu Gong
Hu Gong
ZLZhenfeng Lu
Zhenfeng Lu
HYHuashan Yong
Huashan Yong
WHWei He
Wei He