Lin Huo

Lin Huo

Auto-generated profile, based on publicly available information

Lin Huo

Faculty of Mechanical and Electrical Engineering, Kunming University of Science and Technology, Kunming, China

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
21 April 2023 in IEEE Sensors Journal
Verified
Journal Article
Closed access
LHLin Huo
Lin Huo
JMJianlin Mao
Jianlin Mao
SWSen Wang
Sen Wang
HSHongjun San
Hongjun San
The signal acquisition and analysis of the structure vibration can effectively diagnose the operation status and fault type. The visual inspection method has the advantage of non-destructive testing and providing full-field vibration information for monitoring the vibration of rotating machinery. However, the accuracy requirements for measuring the small displacements generated by the low-amplitude vibration of high-speed rotating machinery are extremely high. It remains a challenge to achieve accurate, precise, and fast extraction of high-frequency and small-amplitude micro-vibrations using visual-based displacement measurement methods. Therefore, this paper proposes the object detection model, the Vibration Displacement Detection Network (VDDNet), for measuring vibration displacement of rotating bodies. VDDNet reduces the required computational complexity of the actual detection target and optimizes the quality of vibration displacement measurement. Additionally, by introducing an attention module and adopting different learning strategies to share rotating body target features, the real-time and accuracy of vibration monitoring are ensured. Furthermore, the evaluation method used in this paper comprehensively considers detection accuracy, real-time performance in deep learning methods, and displacement capture accuracy in vibration displacement monitoring. Actual vibration experimental results demonstrate that the proposed method is minimally affected by illumination and can achieve a better real-time capture accuracy of rotor micro-displacements, further proving its effectiveness and feasibility, which is helpful in advancing related research in this field.

1 May 2023 in IEEE Transactions on Instrumentation and Measurement
Verified
Journal Article
Closed access
LHLin Huo
Lin Huo
JMJianlin Mao
Jianlin Mao
HSHongjun San
Hongjun San
SWSen Wang
Sen Wang
RLRuiqi Li
Ruiqi Li
Vision-based structural displacement monitoring of rotor has attracted extensive attention from scholars due to its non-contact, non-damage, and multi-point synchronous measurement advantages. However, there is a lack of one comprehensive dataset and benchmark for rotor detection since the problem of limited acquisition equipment or on-site environment in the industrial field. For that, a large benchmark for rotor’s vibration displacement detection is introduced in this paper. Firstly, a rotor vibration displacement detection network (RDNet) for rotating structures is proposed and state-of-the-art performance is achieved. Secondly, the evaluation criteria are designed to evaluate the rotor image detection accuracy using the mean Average Precision@0.5:0.95 (mAP@0.5:0.95), the Frames Per Second (FPS), and the Normalized Root Mean Squared Error (NRMSE) as performance indicators. Thirdly, a dataset namely Rotor V1.0 is built, which contains three frames (high, middle, and low) of 13,500 rotor images. It is the rotor dataset for vibration displacement monitoring of rotating structures. Lastly, the baseline performance resulted from traditional methods (i.e., match template and support vector machines) and deep learning methods (i.e., CenterNet, Faster Region-convolutional neural networks (Faster R-CNN), RetinaNet, Single Shot MultiBox Detector (SSD), and You only look once (YOLO)) are reported and analyzed. It is hoped that RDNet, evaluation criteria, and the novel Rotor V1.0 dataset can promote the implementation of visual vibration measurement tasks in industrial sites.

9 August 2024 in Applied Intelligence
Verified
Journal Article
Closed access
PDF file
LHLin Huo
Lin Huo
JMJianlin Mao
Jianlin Mao
HSHongjun San
Hongjun San
SZShufan Zhang
Shufan Zhang
R李Rui 李
Rui 李
LFLixia Fu
Lixia Fu

3 March 2026 in IEEE Robotics and Automation Letters
Verified
Journal Article
Closed access
LHLin Huo
Lin Huo
JMJianlin Mao
Jianlin Mao
HSHongjun San
Hongjun San
RLRuiqi Li
Ruiqi Li
ZXZhiwei Xuan
Zhiwei Xuan
Continuous-space multi-agent path finding (MAPF) presents severe challenges for deep reinforcement learning (DRL), as joint state–action spaces grow exponentially and fine-grained inter-agent coordination is required. Applying mean-field approximation can reduce input complexity from $\mathcal {O}(N^{2}~d)$ to $\mathcal {O}(Nd)$, but naively averaging neighbors may weaken critical local interactions, limiting planning success. To address this, we propose the Mean-Field Multi-Agent Reinforcement Pathfinding Framework (MAMFRPF), which integrates mean-field interaction compression, a dual-stream local mean-field critic, trust-region policy optimization, and a sparse-reward design. The dual-stream critic compensates for information loss caused by mean-field averaging, improving planning success by over 20 percentage points under partial observability, while training time is reduced by roughly 7%. Trust-region optimization ensures monotonic policy improvement, and the sparse-reward mechanism accelerates long-horizon credit assignment. Experiments on continuous MAPF benchmarks show that MAMFRPF outperforms strong baselines by 15% in success rate, scales with agent density, and generalizes across diverse spatial layouts.