检索结果-内蒙古大学图书馆

第42届中国控制会议

作者： Zheng Zhang Dong Guo Hongwei Zheng Hong Wang Qingdong Li Xiwang Dong Zhang Ren School of Automation Science and Electrical Engineering Science and Technology on Aircraft Control LaboratoryBeihang University Beijing Institute of Control Engineering Institute of Artificial Intelligence Beihang University

This paper proposes a distributed tracking framework for high-maneuvering and malicious maneuvering target based on the sensor *** some of sensors in the network can only observe partial system output,the collective observability is *** on the collective observability,the distributed target tracking algorithm is designed by local filter phase and consensus fusion *** local filter phase,the local estimate results can be obtained by each sensor *** on the target kinematic and sensor observation equations,the Kalman-like estimation algorithm is proposed to obtain the local estimate *** most of the exist distributed state estimation(DSE) algorithms,the excellent target tracking performance is based on the assumption that the fusion times is infinity in consensus fusion *** practical application,however,the consensus fusion phase should be completed during two sampling ***,based on the finite-time stability theory,the error covariance matrix is processed as the solution of discrete-time algebraic Riccati equation(DARE).Then the stability of the proposed algorithm with finite-time consensus fusion is ***,a numerical example for tracking maneuvering target is given to validate the effectiveness.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Reinforcement Learning Speed control Algorithm Based on Giants Teaching Mechanism for JT9D Low Pressure Shaft

Reinforcement Learning Speed Control Algorithm Based on Gian...

引用

Annual Conference of Industrial Electronics Society

作者： Changyi Xu Mingyu Huo Xiaokang Zhang School of Control Science and Engineering Dalian University of Technology Dalian China School of Mechatronic Engineering and Automation Shanghai University Shanghai China

As a benchmark of the aviation industry, JT9D aero engine is a general object to study the new algorithms. controlling the low pressure shaft speed is of great significance to the output power of JT9D. But the traditional PID controller often has overshoot. This kind of “vibration” is a challenge to the various parts of the sophisticated aero engine. Solving this control problem with the help of reinforcement learning algorithms has become a new research direction. The basic framework of reinforcement learning is to explore a strategy that maximizes the expected reward through the continuous interaction between Agent and Environment. But in the interacting process, the behavior of Agent may be dangerous, especially when the interactive Environment is a complex or sophisticated system, such as aero engine. In order to solve the above problem, inspired by the inheritance and development of knowledge in human society, this paper proposes a reinforcement learning algorithm with giants teaching mechanism. To examine the effectiveness, this paper takes the JT9D aero engine as the Environment to verify the effect on the speed control of the low pressure shaft. And the experiments of Proportion Integral Differential(PID) and Soft Actor-Critic(SAC) algorithms are also studied as a comparison. Experimental results show that our algorithm is more effective in limiting low pressure shaft speed overshoot and avoiding algorithm runaway.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Two-Stage Representation Refinement Based on Convex Combination for 3-D Human Poses Estimation

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第12期5卷 6500-6508页

作者： Chen, Luefeng Cao, Wei Zheng, Biao Wu, Min Pedrycz, Witold Hirota, Kaoru China University of Geosciences School of Automation Wuhan430074 China Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Wuhan430074 China Ministry of Education Engineering Research Center of Intelligent Technology for Geo-Exploration Wuhan430074 China University of Alberta Department of Electrical and Computer Engineering EdmontonABT6G 2R3 Canada Macau University of Science and Technology Institute of Systems Engineering Taipa999078 China Istinye University Research Center of Performance and Productivity Analysis Istanbul34010 Turkey Tokyo Institute of Technology Yokohama226-8502 Japan

In the human pose estimation task, on the one hand, 3-D pose always has difficulty in dividing different 2-D poses if the view is limited;on the other hand, it is hard to reduce the lifting ambiguity because of the lack of depth information, it is an important and challenging problem. Therefore, two-stage representation refinement based on the convex combination for 3-D human pose estimation is proposed, in which the two-stage method includes a dense-spatial-temporal convolutional network and a local-to-refine network. The former is applied to determine the features between each video frame;the latter is used to get the different scales of pose details. It aims to address the difficulty of estimating 3-D human pose from 2-D image sequences. In such a way, it can better use the relations between every frame in the sequence of the pose video to produce more accurate results. Finally, we combine the above network with a block called convex combination to help refine the 3-D pose location. We test the proposed approach on both Human3.6m and MPII datasets. The result confirms that our method can achieve better performance than improved CNN supervision, a simple yet effective baseline, and coarse-to-fine volumetric prediction. Besides, a robustness test experiment is carried out for the proposed method while the input is interrupted. The result verifies that our method shows better robustness. © 2024 IEEE.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

A Multi-Output Long-Term Prediction Intervals Construction Method for Linz-Donawitz Gas Tanks

A Multi-Output Long-Term Prediction Intervals Construction M...

引用

Asian control Conference

作者： Chunling Zhang Jing Wang Fanxing Meng Yanping Mei Ze Wang School of Electronics and Automation City Institute Dalian University of Technology Dalian China School of Control Science and Engineering Dalian University of Technology Dalian China

ISBN: (数字)9789887581598

ISBN: (纸本)9798331540845

As one of the most crucial secondary energy resources in steel industry, Linz Donawitz converter gas (LDG) draws greatly attention for which the utilization has a close relationship with the energy saving for the enterprise. And accurate prediction for the gas tank levels can be deemed as scientific guidance for energy scheduling and optimization operations. Considering a LDG system of a steel plant in China, a granular computing-based multi-output long-term prediction intervals (Pls) method is proposed to estimate the future trend of gas tank levels. A hybrid collaborative fuzzy clustering model is constructed which utilizing horizontal and vertical structure for fully describes both the relationship between the tank and the related influence factors, and also the mutual impact of the multiple tank levels. Furthermore, by means of the longitudinal expansion on the clustering centers, the prediction horizon is extended from the pointwise mode to the interval values. Then after the optimization along with fuzzy inference and defuzzification, a multi-output long-term Pls construction on the LDG gas tank levels is finally addressed. The results of the experiments and on-site system application indicate the effectiveness and practicability of the proposed method.

关键词： Job shop scheduling Accuracy Processor scheduling Computational modeling Collaboration Steel industry Market research

来源：评论

学校读者我要写书评

暂无评论

Identification of Abnormal Operating Conditions in Fused Magnesium Furnaces Using a Deep Multiview TSK Fuzzy System

Identification of Abnormal Operating Conditions in Fused Mag...

引用

2024 China automation Congress, CAC 2024

作者： Xi, Chao Wu, Gaochang Fan, Zizhu Xu, Feng Wang, Hui Tang, Xiaokun School of Electrical and Automation Engineering East China Jiaotong University Nanchang China State Key Laboratory of Synthetical Automation for Process Industries Northeastern University Shenyang China College of Computer Science and Technology Shanghai University of Electric Power Shanghai China Key Laboratory of Advanced Control and Optimization of Jiangxi Province East China Jiaotong University Nanchang China

ISBN: (纸本)9798350368604

The smelting process of the fused magnesium furnace(FMF) is prone to semi-molten abnormal conditions, which may lead to low product quality and production efficiency, and is also prone to safety accidents. At present, the operating conditions of FMF mainly rely on manual observation of the furnace shell features for diagnosis, and it is hard to timely and effectively identify abnormalities in the smelting process. Given the difficulty in identifying abnormal operating conditions of FMF, this paper proposes a deep multiview fuzzy classification method(DMFC) that can automatically identify abnormal operating conditions. First, based on the three-phase current data, CNN and Transformer are used to extract features as multiple views. Secondly, the Takagi-Sugeno-Kang(TSK) fuzzy model is used as a single-view model, and the evidence theory is used for dynamic fusion of multiple views. This method can effectively fuse multiple deep features, and has strong scalability and a certain degree of interpretability. Through verification of the real historical data of multiple FMFs, our model has relatively high accuracy, false detection rate(FDR), and missed detection rate(MDR). © 2024 IEEE.

关键词： Smelting

来源：评论

学校读者我要写书评

暂无评论

. Improved Lightweight Vehicle and Pedestrian Target Detection Algorithm for YOLOv8

. Improved Lightweight Vehicle and Pedestrian Target Detecti...

引用

Data Driven control and Learning Systems (DDCLS)

作者： Honghai Ji Yue Lu Lingling Fan Shida Liu Ye Ren Li Wang School of Electronics & Control Engineering North China University of Technology Beijing China School of Automation Beijing Information Science and Technology University Beijing China

ISBN: (数字)9798350361674

ISBN: (纸本)9798350361681

In the context of road scenes, detecting targets poses challenges such as mutual occlusion, small sizes, and dense distributions, leading to difficulties in detection and target loss. To address these issues, a road scene target detection algorithm is proposed based on improvements to YOLOv8. Firstly, a lightweight VanillaNet is employed as the backbone feature extraction network. Secondly, an SENet module is introduced in the Feature Fusion Network (Neck) to enhance the model's learning ability in deep-level features, thereby addressing detection challenges caused by mutual occlusion of targets. Finally, the MPDIoU loss function is chosen to replace the original YOLOv8 loss function for model optimization. Experiments are conducted using images from the Pascal VOC dataset, specifically samples of Person, Car, Bus, Motorcycle, and Bicycle categories, for training and testing. The experimental results indicate that the improved algorithm exhibits a 3.5% increase in average precision compared to the original YOLOv8 algorithm, with notable improvements in target omission and false detection scenarios.

关键词： Training Accuracy Pedestrians Roads Motorcycles Object detection Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Detection of Melanoma Based on Improved YOLOv8

Detection of Melanoma Based on Improved YOLOv8

引用

Data Driven control and Learning Systems (DDCLS)

作者： Honghai Ji Xuechen Zheng Shuangshuang Xiong Lingling Fan Li Wang School of Electronics & Control Engineering North China University of Technology Beijing China School of Automation Beijing Information Science and Technology University Beijing China

ISBN: (数字)9798350361674

ISBN: (纸本)9798350361681

The incidence of skin cancer is increasing globally, with melanoma being the most formidable form of skin cancer. Melanoma originates from melanocytes, which exhibit a high degree of visual similarity. Moreover, dermoscopy image data often suffer from hair occlusion and the lesion area appears relatively small in the images, making it challenging for traditional methods to achieve accurate recognition and detection results. In this regard, we propose a YOLOv8 framework based on multi-scale sequence fusion(MSSF) for melanoma detection. This approach enhances the Neck structure of YOLOv8 and improves the network's ability to extract multi-scale information by introducing the Multi-scale Sequence Fusion module. In addition, we implemented a morphological black hat based hair processing method to reduce hair occlusion. In the ISIC datasets, compared with the unimproved algorithm, the mean average precision(Map) at 50 IoU is increased by 5.7%, Map between 50 and 95 IoU is increased by 7.5%, and the number of parameters is decreased by 12.5%.

关键词： Hair YOLO Learning systems Visualization Solid modeling Accuracy Image recognition

来源：评论

学校读者我要写书评

暂无评论

Digital Twin-Driven Degradation Modeling Method for control Moment Gyroscope Health Management

Digital Twin-Driven Degradation Modeling Method for Control ...

引用

IEEE International Conference on Big Data Computing Service and Applications (BigDataService)

作者： Runhao Cui Xucong Huang Peng Zhang Diyin Tang School of Automation Science and Electrical Engineering Beihang University Beijing China Beijing Institute of Control Engineering Beijing China

Prognosis and health management (PHM) of control moment gyroscope (CMG) plays a crucial role in ensuring the operational efficiency and safety of spacecraft. In order to improve the accuracy of PHM and supplement abundant monitoring data, this paper proposes a digital twin-driven degradation modeling method, which establishes a detailed simulation model based on degradation mechanisms at the CMG component level. The digital twin model not only provides a large amount of high-quality data for performance evaluation, but also serves as an important reference for on-orbit CMG state assessment. Finally, a case of estimating virtual sensor degradation information based on reinforcement learning is used to demonstrate the effectiveness of the proposed digital twin method.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Path Planning Using Improved Hybrid A* Algorithm for Mobile Robots

Path Planning Using Improved Hybrid A* Algorithm for Mobile ...

引用

System Simulation Technology and its Application (CCSSTA), IEEE China Conference on

作者： Zikang Cheng Jingbo Xue Bo Wang Guangzhong Dong Jingwen Wei Chunlin Chen Department of Control Science and Intelligence Engineering Nanjing University Naning China School of Mechanical Engineering and Automation Harbin Institute of Technology Shenzhen Shenzhen China

ISBN: (数字)9798350366600

ISBN: (纸本)9798350366617

The Hybrid A* algorithm is suitable for Ackermann-type mobile robots with nonholonomic constraints. However, in practical path planning, such issues as long search times, inefficient search efficiency, and excessive planning path changes causing unstable robot motion still exist. To improve the effectiveness of path planning, this paper optimizes the Hybrid A* algorithm by using variable search step size and designing a path evaluation function during node expansion. Path planning experiments are conducted based on simulation and physical experimental platforms. The results show that the improved algorithm reduces the search nodes and planning time, effectively enhancing the algorithm’s search performance and efficiency. In addition, it avoids pose errors caused by reverse driving, ensuring the priority and smoothness of forward driving, and achieves efficient and stable path planning for Ackermann-type mobile robots.

关键词： Robot motion Path planning Planning Systems simulation Mobile robots

来源：评论

学校读者我要写书评

暂无评论

Adaptive Model Predictive control for Yaw System of Variable-speed Wind Turbines

引用

Journal of Modern Power Systems and Clean Energy 2021年第1期9卷 219-224页

作者： Dongran Song Qing Chang Songyue Zheng Sheng Yang Jian Yang Young Hoon Joo the School of Automation Central South Universityand Hunan Provincial Key Laboratory of Power Electronics Equipment and GridChangsha 410083China the School of Energy Science and Engineering Central South UniversityChangsha 410083China the School of IT Information and Control Engineering Kunsan National UniversityKunsan 54150Korea

Due to varying characteristics of the wind condition, the performance of the wind turbines can be optimized by adapting the parameters of the control system. In this letter, an adaptive technique is proposed for the novel model predictive control(MPC) for the yaw system of the wind turbines. The control horizon is adapted to the one with the best predictive performance among multiple control horizons. The adaptive MPC is demonstrated by simulations using real wind data, and its performance is compared with the baseline MPC at fixed control horizon. Results show that the adaptive MPC provides better comprehensive performance than the baseline ones at different preview time of wind directions. Therefore, the proposed adaptive technique is potentially useful for the wind turbines in the future.

关键词： Wind turbine yaw system wind direction adaptive model predictive control

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：