Weixiong Peng
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Weixiong Peng has a total of 7 co-authors. Here are the top co-authors by number of shared publications:
- Bingyan Li
College of Mechanical and Electrical Engineering, Changchun University of Science and Technology, Changchun 130022, China
2 shared publications - Huiping Huang
Avic Xi’an Aircraft Industry Group Co., Ltd., Xi’an 710089, China
2 shared publications - Xiaoli Qiao
College of Mechanical and Electrical Engineering, Changchun University of Science and Technology, Changchun 130022, China
2 shared publications - Gongping Liu
Avic Xi’an Aircraft Industry Group Co., Ltd., Xi’an 710089, China
1 shared publication - Ping Wang
Avic Xi’an Aircraft Industry Group Co., Ltd., Xi’an 710089, China
1 shared publication - Wenzhi Xiao
College of Mechanical and Electrical Engineering, Changchun University of Science and Technology, Changchun 130022, China
1 shared publication
Latest Publications
- Open Access
- 27 February 2026
- Published by MDPI AG in Electronics
- Vol. 15 (5) , 994
An Enhanced Ant Colony Optimization Approach for Aerospace Cable Routing
To address the challenges of dense structural layouts, limited path feasibility, and stringent assembly constraints in cable routing within complex compartments of aerospace equipment, this paper proposes a cable path planning method that integrates Bidirectional Crossing Line Pruning (BCLP) with an improved ant colony optimization (IACO) algorithm. First, a hierarchical activation strategy for key obstacles is realized by constructing primary and extended crossing lines. On this basis, the BCLP algorithm is introduced, combining global perspective with local reduction capability to significantly reduce the complexity of the search space. Second, in line with cable assembly process requirements, a composite heuristic function is formulated by integrating obstacle-crossing cost and bending penalty. Additionally, a multi-objective-driven pheromone update model is developed to enhance the routing process’ feasibility and convergence performance. Experimental results across various aerospace cabling simulation scenarios demonstrate that the proposed method achieves an average reduction of 19.6% in multi-objective process cost and a 68.5% improvement in convergence efficiency compared to traditional visual graph methods combined with standard ACO. The approach provides effective support for the automation and intelligent planning of cable layouts in complex environments, offering strong potential for engineering applications.
- 27 February 2026
- Published by MDPI AG in Electronics
- Vol. 15 (5) , 994
Open AccessAn Enhanced Ant Colony Optimization Approach for Aerospace Cable Routing
To address the challenges of dense structural layouts, limited path feasibility, and stringent assembly constraints in cable routing within complex compartments of aerospace equipment, this paper proposes a cable path planning method that integrates Bidirectional Crossing Line Pruning (BCLP) with an improved ant colony optimization (IACO) algorithm. First, a hierarchical activation strategy for key obstacles is realized by constructing primary and extended crossing lines. On this basis, the BCLP algorithm is introduced, combining global perspective with local reduction capability to significantly reduce the complexity of the search space. Second, in line with cable assembly process requirements, a composite heuristic function is formulated by integrating obstacle-crossing cost and bending penalty. Additionally, a multi-objective-driven pheromone update model is developed to enhance the routing process’ feasibility and convergence performance. Experimental results across various aerospace cabling simulation scenarios demonstrate that the proposed method achieves an average reduction of 19.6% in multi-objective process cost and a 68.5% improvement in convergence efficiency compared to traditional visual graph methods combined with standard ACO. The approach provides effective support for the automation and intelligent planning of cable layouts in complex environments, offering strong potential for engineering applications.
- Open Access
- 18 December 2025
- Published by MDPI AG in Electronics
- Vol. 14 (24) , 4978
PVConv: Enhancing Depthwise Separable Convolution via Preference-Value Learning for Similar-Feature Discrimination
Depthwise Separable Convolution (DSC) is widely used due to its significant reduction in parameters and computational cost. However, the depthwise convolution process leads to a decrease in spatial information integration, limiting the network’s expressive power. To address this, we propose a novel Preference-Value Convolution (PVConv) to enhance DSC’s expressiveness. By integrating PVConv into DSC, we introduce the Preference-Value Depthwise Separable Convolution (PVDSC) structure. We integrate both DSC and PVDSC into the YOLOv8 framework and conduct experiments on a beverage container dataset containing visually similar object categories and background interference. Results show that, with minimal increase in parameters and computational cost, introducing preference values significantly improves detection accuracy, F1 score, and attention consistency, especially at high IoU thresholds (mAP@50:95), where object localization is greatly enhanced and certain metrics even surpass complex baseline models. Overall, PVConv significantly enhances the expressiveness of DSC-based networks while maintaining low computational overhead, with promising applications.
- 18 December 2025
- Published by MDPI AG in Electronics
- Vol. 14 (24) , 4978
Open AccessPVConv: Enhancing Depthwise Separable Convolution via Preference-Value Learning for Similar-Feature Discrimination
Depthwise Separable Convolution (DSC) is widely used due to its significant reduction in parameters and computational cost. However, the depthwise convolution process leads to a decrease in spatial information integration, limiting the network’s expressive power. To address this, we propose a novel Preference-Value Convolution (PVConv) to enhance DSC’s expressiveness. By integrating PVConv into DSC, we introduce the Preference-Value Depthwise Separable Convolution (PVDSC) structure. We integrate both DSC and PVDSC into the YOLOv8 framework and conduct experiments on a beverage container dataset containing visually similar object categories and background interference. Results show that, with minimal increase in parameters and computational cost, introducing preference values significantly improves detection accuracy, F1 score, and attention consistency, especially at high IoU thresholds (mAP@50:95), where object localization is greatly enhanced and certain metrics even surpass complex baseline models. Overall, PVConv significantly enhances the expressiveness of DSC-based networks while maintaining low computational overhead, with promising applications.