检索结果-内蒙古大学图书馆

第三十八届中国控制会议

作者： Liuyang Jiang Wenxing Fu Hai Zhang Zheng Li Longyun Chi School of Automation Science and Electrical Engineering Beihang University Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory National Airspace Management Center

Robust adaptive Kalman filter(RAKF) is a method that can not only compensate for the model errors but also resist the measurement outliers. The method reduces the influence of the measurement outliers on the filtering system by reducing the weight of the abnormal observation. After the processing of robust estimation, all the errors are attributed to the inaccuracy of the model. Since the robust estimation is not theoretically quantitative that it can only reduce the observation error to a certain extent, the remaining observation errors are compensated as the model errors, resulting in new estimation errors. To address this problem, a method for detecting the model error is proposed as a trigger condition for RAKF to compensate for the model error,and this constitutes an improved robust adaptive Kalman filter(IRAKF) algorithm. The new algorithm performs the model errors compensation stricter than the original method. The efficacy of the improved algorithm is demonstrated via a traffic running testing with GPS/INS tight integration navigation system. Simulation results indicate that the improved algorithm can effectively reduce the inaccurate adaptive procedure and obtain relatively accurate and stable filtering results.

关键词： Adaptive Kalman Filter Robust Estimation Improved Model Errors Tight Integrated Navigation

来源：评论

学校读者我要写书评

暂无评论

A Generic Anti-Windup Design Under Linear Active Disturbance Rejection control Scheme

A Generic Anti-Windup Design Under Linear Active Disturbance...

引用

Electrical, Automation and Computer Engineering (ICEACE), International Conference on

作者： Li Hui Xu Cheng Ji Hua Yin Zhide Hu Wanhai Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory Beijing China The 3rd Research Academy of CASIC Beijing China

A generic anti-windup compensation strategy under Linear Active Disturbance Rejection control scheme is proposed. The difference, between the controller output and the actuator output, after multiplied by a tunable parameter, together with controller output, is fed back to the extended state observer to compensate controller windup. While windup problem arises in control system, the controller output is expectedly produced, and the disadvantageous influence of nonlinearity on closed-loop dynamics is distinctly alleviated. The approach is employed to a near space vehicle with fin-deflection saturation. The numerical simulations show that the proposed approach has the better effectiveness in active disturbance rejection control designed situation than some previous anti-windup compensation strategy.

关键词：

来源：评论

学校读者我要写书评

暂无评论

WATNet: A Wavelet-Aware Lightweight Hybrid Model for Fast Low-Light Enhancement 7

WATNet: A Wavelet-Aware Lightweight Hybrid Model for Fast Lo...

引用

7th Asian Conference on Artificial Intelligence technology, ACAIT 2023

作者： Wang, Qiangqiang Huang, Peiliang Li, Lei Han, Longfei Anhui University AHU-IAI Ai Joint Laboratory Hefei China Hefei Comprehensive National Science Center Institute of Artificial Intelligence Hefei China Northwestern Polytechnical University School of Automation Xi'an China Science And Technology On Complex System Control And Intelligent Agent Cooperation Laboratory Beijing China Beijing Technology And Business University Beijing China University of Science And Technology of China School of Information Science And Technology Hefei China

ISBN: (纸本)9798350359145

Low-light enhancement task is an essential component of computer low-level visual tasks, which involves processing images captured under dim lighting conditions to make them appear as if they were taken under normal illumination. Currently, deep neural networks have become the mainstream approach for image processing. However, recent works have devoted considerable efforts to designing high-performance models, which often come with high computational complexity and inference time, making real-time processing unfeasible. We observed that some convolutional methods are due to the need for deep layers which results in a large number of parameters. Moreover, enhancing details and removing noise in low-light images remains an open challenge. In order to solve the above problems, we propose a lightweight baseline that combines CNN and sparse grid attention transformer blocks to enable the model to capture a global receptive field at an early stage. Specifically, we propose a High-Frequency Wavelet-aware Block(HFWB) that focuses on processing high-frequency information in the wavelet domain to refine details and suppress noise. With a processing time of only 10.6ms, the performance of our model outperforms that of the current state-of-the-art lightweight models on benchmark low-light datasets. Compared to state-of-the-art models in the LOL dataset, our model achieves a reduction in inference time of over 90% and requires only about 1% of the FLOPS. © 2023 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Failure Mode and Effects Analysis of UAV Power system Based on Generalized Dempster-Shafer Structures

Failure Mode and Effects Analysis of UAV Power System Based ...

引用

IEEE International Conference on Unmanned systems (ICUS)

作者： Zhuo Zhang Mingrui Hao School of Electronics and Information Northwestern Polytechnical University Xian China Science and Technology on Complex System Control Intelligent Agent Cooperation Laboratory Beijing China

ISBN: (纸本)9781728137933

The unmanned aerial vehicle(UAV) power system consists of components that provide flight power for the UAV, which mainly includes three parts: motor, electronic speed controller(ESC), and battery. Since the UAV always operates in the open air, which requires high stability of the power system, the failure mode and effects analysis(FMEA) is particularly significant and it has been widely used to examine potential failures in systems or components. However, the traditional FMEA method has many unreasonable points. In order to better deal with the uncertainty and improve the stability of the UAV power system, we propose a FMEA method which is based on the generalized Dempster-Shafer structures, the failure modes are comprehensively analyzed and the risks are ranked by combining the characteristic information of risk factors with the generalized evidence theory. The new method can not only deal with the uncertainty of risk assessment, but also further improve the reliability of effects analysis. In addition, the FMEA experiment of the UAV power system is carried out in this paper. The experimental results show that the method is effective for practical applications.

关键词： Failure mode and effects analysis Generalized dempster-Shafer stucture Fuzzy set theory Unmanned aerial vehicle power system Failure Mode and Effect Analysis Unmanned Aerial Vehicle drone honey bees Fuzzy Set Theory FAILURE MODES power systems Power system stability

来源：评论

学校读者我要写书评

暂无评论

Edge-guided image estimation for array Gm-APD Lidar in smoky environment using multi-scale depth images 6

Edge-guided image estimation for array Gm-APD Lidar in smoky...

引用

6th Optics Young Scientist Summit, OYSS 2023

作者： Zhang, Yinbo Li, Sining Sun, Jianfeng Jiang, Peng Zhang, Hailong Liu, Zhihui Zhu, Yuebing National Key Laboratory of Science and Technology on Tunable Laser Institute of Opto-Electronic Harbin Institute of Technology Heilongjiang Harbin150001 China Zhengzhou Research Institute of Harbin Institute of Technology Henan Zhengzhou450000 China Science and Technology on Complex System Control Intelligent Agent Cooperation Laboratory Beijing100074 China Sichuan Jiuzhou Electrical Group Company Limited Sichuan Mianyang621000 China

ISBN: (纸本)9781510672642

Limited statistical frame number and strong backscatter interference from smoke result in a photon-starved regime, severely limiting the depth imaging capability of array Gm-APD lidar in smoky environment. Here, we propose a depth image estimation algorithm that can significantly improve the integrity of targets in dense smoke environments when signal photons are starved. At the signal level, the algorithm improves the accuracy of extracting signal photons by constructing multi-scale superpixels. At the image level, using edge information of depth images at different scales to guide and fill the original scale depth image achieves efficient noise reduction and improves target integrity. It has been successfully demonstrated under different attenuation lengths and statistical frame numbers. Compared with other state-of-the-art methods, the proposed algorithm has maximum target recovery and structural similarity, especially for the attenuation length (AL) is 3.6 and statistical frame number is 1500 (imaging time is 75ms). This study is of great significance for the fast depth imaging of dynamic targets by array Gm-APD lidar in dense smoke environments. © COPYRIGHT SPIE. Downloading of the abstract is permitted for personal use only.

关键词： Optical radar

来源：评论

学校读者我要写书评

暂无评论

Line-point feature based structure-preserving image stitching

Line-point feature based structure-preserving image stitchin...

引用

Chinese Automation Congress (CAC)

作者： Longyun Chi Xujun Guan Xiaorong Shen Hai Zhang School of Automation Science and Electrical Engineering Beihang University Beijing China Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory Beijing China

The naturalness of the panoramic image is an important criterion for evaluating the result of image stitching. When the overlapping region of the image has a low-texture area, the alignment is hard to accomplish due to incorrect and inadequate feature point matching pairs, and the salient structures are easily destroyed due to the unreasonable position of the optimal seam. To solve the problem, we use line segment matching information to assist the alignment of low-texture regions and use superpixel segmentation regions to filter the unreliable point correspondences. An improved seam-finding algorithm is finally used to blend images together. The experimental results demonstrate that the proposed method can get more natural stitching results.

关键词： Image segmentation Strain Feature extraction Information filters Matched filters Optimization

来源：评论

学校读者我要写书评

暂无评论

Application of Neutrosophic Multiple Criteria Decision Making in Unmanned system

Application of Neutrosophic Multiple Criteria Decision Makin...

引用

IEEE International Conference on Unmanned systems (ICUS)

作者： Yu Zhong Jiajia Zhao School of Electronics and Information Northwestern Polytechnical University Xi’an China Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory Bejing China

ISBN: (纸本)9781728137933

The multiple criteria decision making (MCDM) is universal and applicable for plenty of unmanned systems which are widely concerned in civil and military fields due to their adaptability and safety. The contributing factors of decision making in unmanned systems are complicated due to the inhomogeneity and nondeterminacy of environment and the relative importance of criteria. Consequently, these critical factors fail to be considered felicitously in many traditional methods. In this paper, a neutrosophic MCDM approach is proposed to mitigate this matter. The neutrosophic set generated from collected information of multiple sources would be fused by the aggregation operator to obtain the decision matrix, then the weights of criteria would be obtained via the proposed method based on the decision matrix, and the decision results could be determined by the aggregation operator and defuzzification method of aggregated neutrosophic set. The application of neutrosophic set can handle numerous uncertain matters in unmanned systems. Finally, an example was provided to illustrate the reasonableness and stability of the proposed approach.

关键词： Decision making Correlation Uncertainty Nonhomogeneous media Stability criteria Space vehicles

来源：评论

学校读者我要写书评

暂无评论

Multi-Stage Marine Ship Recognition Based on Stackable Residual Network

Multi-Stage Marine Ship Recognition Based on Stackable Resid...

引用

International Conference on Fuzzy systems and Knowledge Discovery (FSKD)

作者： Wanwan Yu Junping Zhang Linlin Wang Yunqiao Xi Hongfeng Xu Linxiu Chen Mingrui Hao School of Electronics and Information Engineering Harbin Institute of Technology Harbin China Science and Technology on Complex System Control and Intelligent Agent Cooperation Laboratory Beijing China

Marine ship recognition has always been an important research field. The ships can be usually recognized by analyzing their attribute characteristics. However, in the actual process of recognition, many ship recognition methods using a single model cannot meet the requirements of this task due to the complexity of ship types, diversity of interference factors and different information obtained from distance differences. Therefore, we propose a multi-stage ship recognition scheme. First, the single radiation emitter feature recognition network model is designed for long-distance recognition. Second, the fusion feature network model for short distance recognition. The proposed network is mainly constructed with the residual units, which not only simplify the training of deep networks and facilitate the spread of information, but also can solve the vanishing gradient and exploding gradient problem. The simulation experimental results show that the proposed network model has better performance than typical methods and has great potential in applications.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Flexible Physical Camouflage Generation Based on a Differential Approach

arXiv

引用

arXiv 2024年

作者： Li, Yang Tan, Wenyi Wang, Tingrui Liang, Xinkai Pan, Quan School of Automation Northwestern Polytechnical University Xi’an710072 China Laboratory of Science and Technology on Complex System Control and Intelligent Agent Cooperation Beijing China

To achieve attacks on object detection in the physical world, many existing studies focus on adversarial camouflage generation techniques, which involve applying adversarial textures onto the surface of the target. However, the neural renderers used in previous works cannot realistically simulate the physical world, and most texture rendering processes are implemented on 2D images, without fully considering the influence of the structural information of 3D models on texture overlay. To address these challenges, we introduce a novel neural rendering approach specifically tailored for adversarial camouflage within a versatile 3D rendering framework. Our method, named Flexible Physical-camouflage Attack (FPA), goes beyond traditional techniques by faithfully simulating lighting conditions, material variations of the camouflage, the angle and distance between the target and the camera, ensuring a nuanced and realistic representation of textures on a 3D target. To achieve this, we employ a generative approach that learns adversarial patterns from a diffusion model. This involves combining specially designed adversarial loss, smoothness loss, non-printable score loss, and concealment constraint loss to ensure the adversarial, printability, and concealable nature of camouflage in the physical world. Furthermore, we showcase the effectiveness of the proposed camouflage in sticker mode, demonstrating its ability to cover the target without compromising adversarial information. Through empirical and physical experiments, FPA exhibits strong performance in terms of attack success rate and transferability. Additionally, the designed sticker-mode camouflage, coupled with a concealment constraint, adapts to the environment, yielding diverse styles of texture. Our findings highlight the versatility and efficacy of the FPA approach in adversarial camouflage applications. Copyright © 2024, The Authors. All rights reserved.

关键词： Camouflage

来源：评论

学校读者我要写书评

暂无评论

Brain Storming Optimization Algorithm for Heating Dispatch Scheduling of Thermal Power Plant 29

Brain Storming Optimization Algorithm for Heating Dispatch S...

引用

第29届中国控制与决策会议

作者： Lu Kang Yali Wu Xinrui Wang Xiaohua Feng School of Automation and Information Engineering Xi'an University of Technology Shannxi Province Key Laboratory of Complex System Control and Intelligent Information Processing School of Marine Science and Technology Northwestern Polytechnical University

ISBN: (纸本)9781509046584

In the traditional scheduling mode of the current thermal power plants,only the power load distribution of the unit was *** there was no enough guidance to the heat source *** can not meet the current energy-saving and emission-reduction *** this paper,an optimal heat load dispatching model is set up under the premise of power load distribution of thermal power *** kinds of heat loads including to high-pressure,medium-pressure and low-pressure are taken into account in the scheduling *** to the characteristics of the problem,Brain Storming Optimization(BSO) algorithm is used to get the optimal distribution *** comparison with the original scheme shows the correctness of the model and the optimization ***,the optimization ability and effectiveness of brain storming optimization algorithm in solving complex optimization problems are verified by comparing the proposed algorithm with the other different optimization algorithms,such as Particle Swarm Optimization(PSO) and Differential Evolution(DE) algorithm.

关键词： Heating Dispatching Brain Storming Optimization Algorithm Load Distribution

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：