A Fault Diagnosis Method for Quadruped Robot Based on Hybrid Deep Neural Networks
Abstract
The complex and precise mechanical mechanism of quadruped robots is prone to faults, which brings challenges to the reliability and stability of the system. Therefore, it is of significant to develop the fault diagnosis method for quadruped robots, which can provide effective fault information for active fault-tolerant control. In this article, we propose a novel fault detection and isolation method for quadruped robots based on convolution neural networks, gated recurrent units, and attention networks, which can detect and isolate joint faults in real time. The proposed method can automatically learn meaningful high-level spatial and temporal features from sensors data. The effectiveness of the method is verified by the Laikago robot compound fault data.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Learning-based methods such as neural-adaptive control in manipulators have significant computational demands.
“Studies have reported significant demands from learning-based methods, such as neural-adaptive control in manipulators [10]”
From Hybrid Fault-Tolerant Control in Cooperative Robotics: Advances in Resilience and Scalability (2025) · cites this paper as [10]
Active fault-tolerant control's high computational demands, often requiring GPU acceleration, pose challenges for real-time deployment.
“Despite these strengths, AFTC's high computational demands-often requiring Graphics Processing Unit (GPU) acceleration-pose challenges for real-time deployment [10].”
From Hybrid Fault-Tolerant Control in Cooperative Robotics: Advances in Resilience and Scalability (2025) · cites this paper as [10]
Neural processing can spike computational demands by up to 300%.
“and neural processing can spike computational demands by up to 300% [10]”
From Hybrid Fault-Tolerant Control in Cooperative Robotics: Advances in Resilience and Scalability (2025) · cites this paper as [10]
Radial Basis Function networks with a 0.01 learning rate approximate uncertainties with Lyapunov stability, excelling in UAV swarms with rapid recovery.
“Radial Basis Function (RBF) networks with a 0.01 learning rate approximate uncertainties with Lyapunov stability, excelling in UAV swarms with rapid recovery [10,27].”
From Hybrid Fault-Tolerant Control in Cooperative Robotics: Advances in Resilience and Scalability (2025) · cites this paper as [10]
Cites
Why do deep convolutional networks generalize so poorly to small image transformations?
Azulay, A., & Weiss, Y. (2018) · arXiv · doi:10.48550/arxiv.1805.12177 · Cited by 428 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
Hybrid Fault-Tolerant Control in Cooperative Robotics: Advances in Resilience and Scalability
Urrea, C. (2025) · Actuators · doi:10.3390/act14040177 · Cited by 19 · see citing works
- Authors
- Wang, Z., Li, H., Chen, Z., & Han, Q.-L.
- Affiliations
- Northwestern Polytechnical University (CN)
- Swinburne University of Technology (AU)
- Venue
- IEEE Transactions on Industrial Informatics
- Published
- 2025-04
- Volume
- 21
- Issue
- 4
- Pages
- 3027-3036
- ISSN
- 1551-3203 (ISSN-L)
- 1941-0050
- OpenAlex
- W4406522567
- Cited by
- 29
- References
- 1
- Citations by year
- 2026: 14 · 2025: 15
- FWCI
- 10.65
- Type
- journal article
- Language
- en
- Open access
- closed
- Licence
- Locations
- IEEE Transactions on Industrial Informatics (publishedVersion)
- Funders
- National Natural Science Foundation of China (U22B2039, 62273281, 61922068)
- Aoxiang Youth Scholar Program (23GH0202058)
- Topics
- Physical Sciences › Engineering › Control and Systems Engineering › Fault Detection and Control Systems
- Physical Sciences › Engineering › Control and Systems Engineering › Machine Fault Diagnosis Techniques
- Physical Sciences › Engineering › Biomedical Engineering › Robotic Locomotion and Control
- Keywords
- quadruped robot, fault diagnosis, fault detection and isolation, joint fault, convolutional neural networks, gated recurrent unit, attentional networks, hybrid deep neural network, real-time fault detection, compound faults, active fault-tolerant control
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
