A guided differential dilated convolutional network for fault diagnosis of hydraulic manipulators
| |||||||||||||
Daocheng FU1, Xu YANG1, Haitao LIU2, Yugang REN3, Xianpeng SHI3, Limin ZHU4. A guided differential dilated convolutional network for fault diagnosis of hydraulic manipulators[J]. Journal of Zhejiang University Science A, 1998, -1(-1): .
@article{title="A guided differential dilated convolutional network for fault diagnosis of hydraulic manipulators",
author="Daocheng FU1, Xu YANG1, Haitao LIU2, Yugang REN3, Xianpeng SHI3, Limin ZHU4",
journal="Journal of Zhejiang University Science A",
volume="-1",
number="-1",
pages="",
year="1998",
publisher="Zhejiang University Press & Springer",
doi="10.1631/jzus.A2600200"
}
%0 Journal Article
%T A guided differential dilated convolutional network for fault diagnosis of hydraulic manipulators
%A Daocheng FU1
%A Xu YANG1
%A Haitao LIU2
%A Yugang REN3
%A Xianpeng SHI3
%A Limin ZHU4
%J Journal of Zhejiang University SCIENCE A
%V -1
%N -1
%P
%@ 1673-565X
%D 1998
%I Zhejiang University Press & Springer
%DOI 10.1631/jzus.A2600200
TY - JOUR
T1 - A guided differential dilated convolutional network for fault diagnosis of hydraulic manipulators
A1 - Daocheng FU1
A1 - Xu YANG1
A1 - Haitao LIU2
A1 - Yugang REN3
A1 - Xianpeng SHI3
A1 - Limin ZHU4
J0 - Journal of Zhejiang University Science A
VL - -1
IS - -1
SP -
EP - 0
%@ 1673-565X
Y1 - 1998
PB - Zhejiang University Press & Springer
ER -
DOI - 10.1631/jzus.A2600200
Abstract: fault diagnosis for hydraulic manipulators plays a crucial role in ensuring operational safety but still faces challenges in fault localization. To address this issue, a guided differential dilated convolutional network (GDDCN) is proposed in this paper. First, a novel interference masking mechanism is designed to provide dual guidance for feature extraction and classification. Then, a learnable differential kernel with the center parameter fixed at zero and side parameters opposite in sign is designed to adaptively extract gradient features. Afterward, a multiscale gated dilated convolution module is developed to capture global temporal features across multiple scales and achieve gated feature fusion. Finally, the fused features are fed into a fully connected classification module for fault classification. The results show that the GDDCN achieves diagnosis of the faulty joint with an average accuracy of 99.39% on a hydraulic manipulator platform. The superiority and effectiveness of the GDDCN is further confirmed through comparative and ablation studies.
Full Text:
<9>
CLC number:
On-line Access: 2026-07-20
Received: 2026-04-02
Revision Accepted: 2026-06-17
Crosschecked: 0000-00-00
Cited: 0
Clicked: 6
Open peer comments: Debate/Discuss/Question/Opinion
<1>