http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Wang Shanshan,Zou Xinyi,Zhu Wei,Zeng Liang 대한전기학회 2023 Journal of Electrical Engineering & Technology Vol.18 No.4
The safe operation of the power grid system depends partly on regular inspections of transmission lines, in which the insulator is one of the most important inspections objects. The manual inspection of transmission lines is a chaotic process that is both time and cost-consuming since it involves an accurate manual inspection by an expert. For insulator defect detection, an improved YOLOv4 algorithm is proposed. First, a new data augmentation method is proposed to solve the problem of insufficient sample size. Then, the size of the anchor boxes is redesigned base on the K-means algorithm to further improve the detection precision. Finally, an insulator defects detection network is constructed based on YOLOv4. Experimental results show that the detection precision of the improved network is 37.2% higher after data enhancement and anchor boxes redesign. In addition, the detection method proposed in this paper is superior to other popularity detection algorithms, including the single shot detector, region-convolutional neural networks (Faster-RCNN) and released version of you only look once (YOLO). The value of mean average precision is 99.08% and frame per second is 56. The robustness test results demonstrate that our proposed algorithm performs well under different light intensities and complex environmental backgrounds, and can accurately detect all targets, which is significantly better than other comparative algorithms. In terms of detection accuracy, test speed and robustness, our proposed algorithm meets the requirements of industrial field applications of insulator defect detection.
Cooperative Task Scheduling and Planning Considering Resource Conflicts and Precedence Constraints
Donghui Li,Hu Su,Xinyi Xu,Qingbin Wang,Jie Qin,Wei Zou 한국정밀공학회 2023 International Journal of Precision Engineering and Vol.24 No.9
The robot-task-sequencing planning problem is investigated in this paper, where multi-robot tasks with resource conflicts and precedence constraints are involved making the problem challenging and complex. An effective approach is proposed to minimize the production cycle time while handling the high complexity effectively. The approach decouples the entire problem into simpler ones and then solves them separately to obtain the final solution. Firstly, given the multi-robot tasks, how to coordinate the operation of each single robot is determined. This is achieved by searching the shortest path in the graph where the tasks are organized in the optimal order without the consideration of resource constraints. Then, the resource allocation is modeled as a constrained assignment problem with the objective of minimal cycle time, which is solved with graph optimization. Consequently, the best-fit robot configurations for task execution are selected according to a heuristic optimality metric, based on which the task execution sequence obtained in previous steps is re-optimized. Finally, the robots involved in the task are regarded as a whole to deduce feasible trajectories. Experimental results demonstrate that the proposed approach can generate solutions where the robot can complete the given tasks effectively with feasible scheduling. Moreover, the proposed approach is successfully implemented in a pragmatic system which tests signals at both ends of components in a circuit board.
Zhengqiu Zhu,Lingshan Chen,Wenjun Liu,Yiyun Wu,Chong Zou,Xinyi Zhang,Shanshan He,Yinping Wang,Bixiao Shen,Xuehui Ma,Hui Gao,Yun Luan,Hui Huang 대한초음파의학회 2022 ULTRASONOGRAPHY Vol.41 No.3
Purpose: The present study investigated the association between Systematic COronary Risk Evaluation (SCORE)-estimated cardiovascular risk and carotid stiffening in a middle-aged population using ultrafast pulse wave velocity (ufPWV).Methods: This study enrolled 683 participants without known cardiovascular disease or diabetes mellitus who underwent ufPWV measurements. Clinical interviews, physical examinations, laboratory findings, carotid intima-media thickness (cIMT), pulse wave velocity (PWV) at the beginning of systole (PWV-BS), and PWV at the end of systole (PWV-ES) were assessed. Each participant underwent an assessment of SCORE risk based on major cardiovascular risk factors (CVRFs), including age, sex, smoking, systolic blood pressure (SBP), and total cholesterol (TC). Crude and adjusted odds ratios (ORs) with 95% confidence intervals and ordinal logistic regression were used. Overall CVRFs were adjusted to assess ORs.Results: cIMT and carotid stiffening in PWV-BS and PWV-ES were significantly different between sex subgroups (all P<0.05), but only PWV-ES increased gradually in age and SCORE-estimated risk subgroups (all P<0.05). Compared with cIMT (r=0.388, P<0.001) and PWV-BS (r=0.159, P<0.001), PWV-ES was more strongly correlated with SCORE categories (r=0.405, P<0.001). Higher PWV-ES values were associated with SCORE categories independently of sex, SBP, TC, and smoking in moderate-risk and high-risk subgroups (OR, 1.63; P<0.001 and OR, 2.12; P=0.024, respectively), but were not independent of age in all risk subgroups (all P>0.05).Conclusion: Carotid stiffening quantified by ufPWV is linked to SCORE categories, and elevated PWV-ES may aid in cardiovascular risk stratification.