Lu Xinyun

Dr. Lu Xinyun


Research Focus & Metrics

Academic Career Length

1Year (2026-Present)

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

Representative Publications

View All Publications
13 April 2026 in Aerospace
Verified
Journal Article
Open access
PDF file
JTJinwu Tong
Jinwu Tong
HCHan Cao
Han Cao
LXLu Xinyun
Lu Xinyun
XZXin Zhang
Xin Zhang
BGBingbing Gao
Bingbing Gao
Accurate surface defect detection is essential for ensuring the measurement accuracy and assembly reliability of aero-engine components during manufacturing and assembly processes. Bearings, as critical rotating components in aero-engines, are highly sensitive to surface defects that may lead to stress concentration and premature failure. However, complex defect types, low-contrast textures, and multi-scale characteristics pose significant challenges for existing lightweight visual inspection models. To address these issues, this paper proposes an improved lightweight detection model, termed DMR-YOLO, based on YOLOv8n. A Diverse Branch Block (DBB) is introduced to enhance multi-scale feature extraction and improve the representation of complex defect patterns. A Multi-Level Channel Attention (MLCA) mechanism is embedded to strengthen discriminative feature channels and suppress background interference caused by low-contrast textures. In addition, a ResidualADown module is designed to preserve critical feature information during downsampling, improving the detection of subtle defects. Experimental results on a bearing surface defect dataset show that the proposed model achieves an mAP of 89.3%, representing a 2.8% improvement over YOLOv8n while maintaining real-time inference at 138.6 FPS. Moreover, generalization tests conducted on a steel surface defect dataset demonstrate the robustness and transferability of the proposed method across different datasets.

5 February 2026 in Sensors
Verified
Journal Article
Open access
PDF file
JTJinwu Tong
Jinwu Tong
LZLifan Zha
Lifan Zha
LXLu Xinyun
Lu Xinyun
LPLi Peng
Li Peng
SJSun Jin
Sun Jin
SLShujun Liu
Shujun Liu
To address the performance degradation of the traditional Extended Kalman Filter (EKF) in state estimation for sensorless brushless DC motor (BLDC) control under dynamic operating conditions, such as sudden speed and load changes—a degradation caused primarily by model mismatches—this paper proposes an Adaptive Extended Kalman Filter (AEKF) algorithm. The proposed algorithm incorporates a robust weighting strategy based on the Mahalanobis distance and a dynamically adjusted adaptive forgetting factor. This integration establishes an estimation mechanism capable of online updating of the innovation covariance, thereby enhancing the state observer’s adaptability to system uncertainties and external disturbances. Simulation results demonstrate that, compared to the traditional EKF, the designed AEKF algorithm significantly improves the estimation accuracy of rotor position and speed under various operating conditions, including low-speed start-up, speed step changes, and sudden load applications. Furthermore, it accelerates dynamic response, suppresses overshoot, and enhances the system’s disturbance rejection robustness. This work provides an effective state estimation solution for high-dynamic performance sensorless control of BLDC.

30 March 2026 in Sensors
Verified
Journal Article
Open access
PDF file
JTJinwu Tong
Jinwu Tong
XZXin Zhang
Xin Zhang
LXLu Xinyun
Lu Xinyun
HCHan Cao
Han Cao
LYLengtao Yao
Lengtao Yao
BGBingbing Gao
Bingbing Gao
To address the challenges of steel surface defect detection—characterized by fine-grained textures, substantial scale variations, and complex background interference—conventional lightweight detectors often struggle to balance real-time navigation requirements with high-precision spatial localization on mobile inspection platforms. In this work, we propose KDM-YOLO, a lightweight visual localization and detection method built upon YOLOv10n, designed to provide an efficient perception engine for autonomous inspection robots. The proposed approach enhances the baseline through three key perspectives: feature extraction, context modeling, and multi-scale fusion. Specifically, KWConv is introduced to strengthen the representation of fine-grained texture and edge cues; C2f-DRB is employed to enlarge the effective receptive field and improve long-range dependency perception to reduce missed detections; and a multi-scale attention fusion (MSAF) module is inserted before the detection head to adaptively integrate spatial details with semantic context while suppressing redundant background responses. Ablation studies confirm that each module contributes to performance gains, and their combination yields the best overall results. Comparative experiments further demonstrate that KDM-YOLO significantly improves detection performance while retaining a compact model size and high inference speed. Compared with the YOLOv10n baseline, Precision, Recall and mAP@50 are increased to 91.0%, 93.9%, and 95.4%, respectively, with a parameter count of 3.29 M and an inference speed of 155.6 f/s. These results indicate that KDM-YOLO achieves an ideal balance between the accuracy and computational efficiency required for embedded navigation platforms, providing an effective solution for online autonomous inspection and real-time localization of steel surface defects.

20 September 2026 in Energies
Verified
Journal Article
Open access
PDF file
SHShuonan Hou
Shuonan Hou
LXLu Xinyun
Lu Xinyun
ZSZHENGWEI SHEN
ZHENGWEI SHEN
XZXiaopei Zhang
Xiaopei Zhang
Jiancun LiuJiancun Liu
Jiancun Liu
Extreme events threaten distribution network security. When remote-controlled switches (RCSs) lose remote operability during extreme events while remaining manually operable, faulted areas may no longer be isolated through remote switching alone. This paper proposes a multi-stage resilience enhancement method that coordinates RCSs and switch operation crews under RCS fault conditions. A four-stage framework is established, comprising pre-event prevention, degradation, fault isolation, and service restoration. Normal RCSs can be remotely opened to shrink the faulted zone during isolation, while faulty RCSs remain frozen and can change their switching states only through on-site crew intervention during restoration. A unified operation constraint is formulated for the isolation stage, and a crew-assisted switching constraint links crew presence at faulty-RCS locations to their switching operability during restoration. The problem is cast as a scenario-based mixed-integer linear program minimizing expected weighted load shedding across all post-event stages. Case studies on the modified IEEE 33-bus system demonstrate the effectiveness of the proposed method under different RCS availability conditions. Under the same line-fault configuration, loss of RCS remote operability increases cumulative weighted load shedding by 28.09% and delays complete load restoration by one time interval. The reported four-scenario computation required approximately 7128 s.