Benlian Xu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Benlian Xu has a total of 60 co-authors. Here are the top co-authors by number of shared publications:
Mingli Lu
Suzhou University of Technology
11 shared publications- Mingli Lu
Changshu Institute of Technology, Suzhou, China
10 shared publications - Brett Douglas Nener
Department of Electrical, Electronic and Computer Engineering, University of Western Australia, Perth, Australia
6 shared publications - Jian Shi
School of Electrical and Automatic Engineering, Changshu Institute of Technology, Suzhou, China
6 shared publications - Jinliang Cong
School of Electrical Engineering and Automation, Changshu Institute of Technology, Suzhou, China
6 shared publications Jian Shi
Suzhou University of Technology
5 shared publications
Latest Publications
- 11 June 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Control Systems Letters
- Vol. 10, 1147-1152
A Bayesian Game Framework for Service Function Chaining in NFV With Incomplete Information
Service function chain (SFC) routing in Network Function Virtualization (NFV) is challenging when users share physical servers but keep their traffic profiles private. This letter formulates SFC routing as a Bayesian game where each traffic load is a private type. We prove that the game is a weighted Bayesian Potential Game and derive, via the semi-tensor product, a closed-form Bayesian Potential Function, ensuring the existence of a pure Bayesian Nash Equilibrium (BNE). The ex-ante transformation reduces BNE computation to finite potential minimisation, enabling distributed strict best-response convergence without disclosure of realised traffic types. In a 2-user, 8-function NFV example, the proposed BNE attains a cost within 1.3% of the full-information oracle, reduces expected total cost by 3.9% over a mean-load baseline and by 26.6% over congestion-blind greedy routing.
- 11 June 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Control Systems Letters
- Vol. 10, 1147-1152
A Bayesian Game Framework for Service Function Chaining in NFV With Incomplete Information
Service function chain (SFC) routing in Network Function Virtualization (NFV) is challenging when users share physical servers but keep their traffic profiles private. This letter formulates SFC routing as a Bayesian game where each traffic load is a private type. We prove that the game is a weighted Bayesian Potential Game and derive, via the semi-tensor product, a closed-form Bayesian Potential Function, ensuring the existence of a pure Bayesian Nash Equilibrium (BNE). The ex-ante transformation reduces BNE computation to finite potential minimisation, enabling distributed strict best-response convergence without disclosure of realised traffic types. In a 2-user, 8-function NFV example, the proposed BNE attains a cost within 1.3% of the full-information oracle, reduces expected total cost by 3.9% over a mean-load baseline and by 26.6% over congestion-blind greedy routing.
- Open Access
- 6 June 2026
- Published by Elsevier in SSRN Electronic Journal
Sample-adaptive fusion of local, temporal, and global diagnostic cues for gear fault diagnosis in heavy-duty rotational transfer devices
Gear fault diagnosis in heavy-duty rotational transfer devices is challenging because vibration signals are strongly affected by intermittent motion, load variation, structural coupling, and external disturbances. Under such conditions, discriminative fault information is usually distributed across localized transients, temporal evolution patterns, and long-range contextual dependencies, which limits the effectiveness of single-view models and fixed fusion strategies. To address this issue, this study proposes a sample-adaptive multi-cue diagnosis framework that explicitly organizes fault diagnosis around three complementary cue types: local, temporal, and global cues. Dedicated cue encoders are used to extract these heterogeneous fault-related representations, and a gated fusion mechanism is introduced to adaptively determine their contributions for each input sample. To improve deployment feasibility, a compact three-channel subset is further constructed from the original ten-channel sensing system. Experiments on a self-developed rotational transfer device gear dataset show that the proposed framework achieves reliable classification under known operating conditions and maintains 97.1% accuracy under unseen operating conditions. The method also remains robust under moderate noise corruption and outperforms representative baselines and ablation variants. Additional validation on the SEU bearing dataset further confirms its cross-scenario applicability and interpretable fusion behavior. These results demonstrate that the proposed framework offers an adaptive and interpretable soft-computing solution for robust fault diagnosis under complex industrial conditions.
- 6 June 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessSample-adaptive fusion of local, temporal, and global diagnostic cues for gear fault diagnosis in heavy-duty rotational transfer devices
Gear fault diagnosis in heavy-duty rotational transfer devices is challenging because vibration signals are strongly affected by intermittent motion, load variation, structural coupling, and external disturbances. Under such conditions, discriminative fault information is usually distributed across localized transients, temporal evolution patterns, and long-range contextual dependencies, which limits the effectiveness of single-view models and fixed fusion strategies. To address this issue, this study proposes a sample-adaptive multi-cue diagnosis framework that explicitly organizes fault diagnosis around three complementary cue types: local, temporal, and global cues. Dedicated cue encoders are used to extract these heterogeneous fault-related representations, and a gated fusion mechanism is introduced to adaptively determine their contributions for each input sample. To improve deployment feasibility, a compact three-channel subset is further constructed from the original ten-channel sensing system. Experiments on a self-developed rotational transfer device gear dataset show that the proposed framework achieves reliable classification under known operating conditions and maintains 97.1% accuracy under unseen operating conditions. The method also remains robust under moderate noise corruption and outperforms representative baselines and ablation variants. Additional validation on the SEU bearing dataset further confirms its cross-scenario applicability and interpretable fusion behavior. These results demonstrate that the proposed framework offers an adaptive and interpretable soft-computing solution for robust fault diagnosis under complex industrial conditions.
- Open Access
- 19 May 2026
- Published by Elsevier in SSRN Electronic Journal
Integrated multi-objective interval optimization for emergency facility location and worker allocation under uncertainty
Facility location problems are fundamental to logistics and urban management, requiring the optimization of conflicting objectives such as cost minimization and service maximization. However, real-world facility location decisions are subject to various uncertainties, including demand fluctuations, resource availability, and unpredictable incidents, which can affect long-term planning and system stability. To address this, our study models a multi-interval optimization problem under parameter perturbation and employs a multi-objective interval optimization evolutionary algorithm to solve it. To further enhance decision robustness, an asymmetric perturbation scheme is introduced to model potential variations more accurately, and a worker allocation mechanism is designed to optimize resource distribution under limited capacity constraints. To validate our approach, experiments were conducted on benchmark datasets and realistic data from Gusu District, Suzhou. The results demonstrate the model's superior performance in balancing optimality and robustness across different scenarios, effectively mitigating the impacts of uncertainty.
- 19 May 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessIntegrated multi-objective interval optimization for emergency facility location and worker allocation under uncertainty
Facility location problems are fundamental to logistics and urban management, requiring the optimization of conflicting objectives such as cost minimization and service maximization. However, real-world facility location decisions are subject to various uncertainties, including demand fluctuations, resource availability, and unpredictable incidents, which can affect long-term planning and system stability. To address this, our study models a multi-interval optimization problem under parameter perturbation and employs a multi-objective interval optimization evolutionary algorithm to solve it. To further enhance decision robustness, an asymmetric perturbation scheme is introduced to model potential variations more accurately, and a worker allocation mechanism is designed to optimize resource distribution under limited capacity constraints. To validate our approach, experiments were conducted on benchmark datasets and realistic data from Gusu District, Suzhou. The results demonstrate the model's superior performance in balancing optimality and robustness across different scenarios, effectively mitigating the impacts of uncertainty.
- 1 April 2026
- Published by Springer Nature
- p. 515-530
Safe Load Transportation Using Quadrotor with Robust Trajectory Tracking Control
- 1 April 2026
- Published by Springer Nature
- p. 515-530
Safe Load Transportation Using Quadrotor with Robust Trajectory Tracking Control
- 30 January 2026
- Published by Elsevier in Expert Systems with Applications
- Vol. 311
Dynamic 3D Gaussian SLAM via motion suppression and incremental optimization
- 30 January 2026
- Published by Elsevier in Expert Systems with Applications
- Vol. 311
Dynamic 3D Gaussian SLAM via motion suppression and incremental optimization
- 15 October 2025
- Published by Elsevier in Expert Systems with Applications
- Vol. 299
DC-SLAM: Dual-category dynamic feature suppression for RGB-D VSLAM
- 15 October 2025
- Published by Elsevier in Expert Systems with Applications
- Vol. 299
DC-SLAM: Dual-category dynamic feature suppression for RGB-D VSLAM
- 1 October 2025
- Published by Springer Nature
- p. 353-365
Thermal-Aware CBS for Multi-AGV Path Planning in Semiconductor Intelligent Warehousing
- 1 October 2025
- Published by Springer Nature
- p. 353-365
Thermal-Aware CBS for Multi-AGV Path Planning in Semiconductor Intelligent Warehousing
- 31 July 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 26 (11) , 18734-18746
HV-BEV: Decoupling Horizontal and Vertical Feature Sampling for Multi-View 3D Object Detection
Vision-based multi-view perception systems, especially those using bird’s-eye view (BEV) representations, have become increasingly important in autonomous driving. Current state-of-the-art methods typically transform image features from multiple camera views into the BEV space via explicit or implicit depth estimation. However, they often rely on uniform or fixed-height sampling and lack height-aware priors, making them insensitive to the fact that different object categories occupy distinct local height ranges. Furthermore, most approaches treat BEV features as independent across grid locations, overlooking the structured correlations between different parts of an object in 3D space. These limitations hinder accurate spatial reasoning in both vertical and horizontal dimensions. To address these issues, we propose HV-BEV, a novel BEV perception framework that decouples the feature sampling process into Horizontal feature aggregation and Vertical adaptive height-aware reference point sampling. Specifically, for horizontal modeling, we dynamically construct a set of relevant neighboring points on the ground-aligned plane for each 3D reference point, facilitating structured cross-view feature aggregation and promoting consistent representation of large or partially visible objects. For vertical modeling, we introduce an adaptive height-aware module that leverages historical information to guide 3D reference points to focus on the plausible height regions where objects of interest are likely to appear, replacing fixed uniform height sampling. Extensive experiments on the nuScenes dataset demonstrate the effectiveness of our method. Our HV-BEV framework consistently outperforms baselines, achieving 50.5% mAP and 59.8% NDS on the nuScenes test set. Code is available at https://github.com/Uddd821/HV-BEV
- 31 July 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 26 (11) , 18734-18746
HV-BEV: Decoupling Horizontal and Vertical Feature Sampling for Multi-View 3D Object Detection
Vision-based multi-view perception systems, especially those using bird’s-eye view (BEV) representations, have become increasingly important in autonomous driving. Current state-of-the-art methods typically transform image features from multiple camera views into the BEV space via explicit or implicit depth estimation. However, they often rely on uniform or fixed-height sampling and lack height-aware priors, making them insensitive to the fact that different object categories occupy distinct local height ranges. Furthermore, most approaches treat BEV features as independent across grid locations, overlooking the structured correlations between different parts of an object in 3D space. These limitations hinder accurate spatial reasoning in both vertical and horizontal dimensions. To address these issues, we propose HV-BEV, a novel BEV perception framework that decouples the feature sampling process into Horizontal feature aggregation and Vertical adaptive height-aware reference point sampling. Specifically, for horizontal modeling, we dynamically construct a set of relevant neighboring points on the ground-aligned plane for each 3D reference point, facilitating structured cross-view feature aggregation and promoting consistent representation of large or partially visible objects. For vertical modeling, we introduce an adaptive height-aware module that leverages historical information to guide 3D reference points to focus on the plausible height regions where objects of interest are likely to appear, replacing fixed uniform height sampling. Extensive experiments on the nuScenes dataset demonstrate the effectiveness of our method. Our HV-BEV framework consistently outperforms baselines, achieving 50.5% mAP and 59.8% NDS on the nuScenes test set. Code is available at https://github.com/Uddd821/HV-BEV
- Open Access
- 10 March 2025
- Published by Springer Nature in Complex & Intelligent Systems
- Vol. 11 (4) , 1-14
Modelling object mask interaction for compositional action recognition
- 10 March 2025
- Published by Springer Nature in Complex & Intelligent Systems
- Vol. 11 (4) , 1-14
Open AccessModelling object mask interaction for compositional action recognition
- Open Access
- 17 February 2025
- Published by Springer Nature in Journal of Intelligent & Robotic Systems
- Vol. 111 (1) , 1-18
An Inpainting SLAM Approach for Detecting and Recovering Regions with Dynamic Objects
- 17 February 2025
- Published by Springer Nature in Journal of Intelligent & Robotic Systems
- Vol. 111 (1) , 1-18
Open AccessAn Inpainting SLAM Approach for Detecting and Recovering Regions with Dynamic Objects