检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Kavas, Barış Balta, Efe C. Tucker, Michael R. Krishnadas, Raamadaas Rupenyan, Alisa Lygeros, John Bambach, Markus Department of Mechanical and Process Engineering ETH Zürich Zürich8092 Switzerland Control and Automation Group Inspire AG Zürich8005 Switzerland Department of Information Technology and Electrical Engineering Automatic Control Laboratory ETH Zürich Zürich8092 Switzerland ZHAW Centre for Artificial Intelligence Zürich University of Applied Sciences Switzerland

Open-loop control of laser powder bed fusion (LPBF) additive manufacturing (AM) has enabled the industrial production of complex and high-criticality parts for aerospace, power generation, medical, transportation, and other industries. This approach relies on static parameter sets obtained through extensive experimentation and a priori simulation on analog parts, with the hope that they remain stable and defect-free once transferred to the production parts. Closed-loop control of LPBF has the potential to enhance process stability further and reduce defect formation in the face of complex thermal histories, stochastic process noise, hardware drift, and unexpected perturbations. The controllers can be classified based on the spatial and temporal scales in which they operate, designated as layer-to-layer and in-layer controllers. However, the performance and effectiveness of controllers largely depend on the tuning of their parameters. Traditionally, controller tuning has been a manual, expertise-driven process that does not guarantee optimal controller performance and is often constrained by the non-transferability of settings between different systems. This study proposes the use of Bayesian Optimization (BO), a sample-efficient algorithm, to automate the tuning of an in-layer controller by leveraging the layer-to-layer repetitive nature of the LPBF process. Two alternative approaches are introduced: online tuning, which adjusts parameters iteratively during the process, and offline tuning, conducted in a representative setup such as laser exposures on a bare metal plate. The proposed methods are experimentally implemented on an in-layer PI controller and the performance of the resulting tuned controllers is investigated on two different wedge geometries that are prone to overheating. The results demonstrate that BO effectively tunes controllers using either method, where both significantly reduced overheating in controlled wedge specimens compared to those uncontro

关键词： controllers

来源：评论

学校读者我要写书评

暂无评论

Lightweight defect detection method of punched nickel-plated steel strip based on GhostNet

Lightweight defect detection method of punched nickel-plated...

引用

Pattern Recognition, Machine Vision and Intelligent Algorithms (PRMVIA), International Conference on

作者： Jianqi Li Yincong Liang Rui Du Jingying Wan Binfang Cao Huiting Liu Hunan Provincial Key Laboratory for Control Technology of Distributed Electric Propulsion Aircraft Hunan University of Arts and Sciences Changde China Hunan Provincial Key Laboratory for Control Technology of Distributed Electric Propulsion Aircraft Jishou University Changde China College of Computer and Electrical Engineering Hunan University of Arts and Sciences Changde China

Aiming at the problem that the defects generated in the production and transportation of punched nickel-plated steel strips are not easy to be detected by deep learning methods, a lightweight, low-redundancy, and high-precision detection method is proposed in this paper. Firstly, a feature extraction network based on GhostNet is constructed, which reduces the amount of computation and feature redundancy while ensuring accuracy. Then the ECA module is applied to the detection head to perform weighted fusion of the features of different channels for better differentiation. Finally, the YOLO detection head is used for multi-scale detection. In the experiment, the mAP of 84.86% was obtained by this method, which proves that this method can be applied to the actual steel strip defect: detection.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Learning to control Linear Systems can be Hard

arXiv

引用

arXiv 2022年

作者： Tsiamis, Anastasios Ziemann, Ingvar Morari, Manfred Matni, Nikolai Pappas, George J. Automatic Control Laboratory ETH Zurich Switzerland School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Sweden Department of Electrical and Systems Engineering University of Pennsylvania United States

In this paper, we study the statistical difficulty of learning to control linear systems. We focus on two standard benchmarks, the sample complexity of stabilization, and the regret of the online learning of the Linear Quadratic Regulator (LQR). Prior results state that the statistical difficulty for both benchmarks scales polynomially with the system state dimension up to system-theoretic quantities. However, this does not reveal the whole picture. By utilizing minimax lower bounds for both benchmarks, we prove that there exist non-trivial classes of systems for which learning complexity scales dramatically, i.e. exponentially, with the system dimension. This situation arises in the case of underactuated systems, i.e. systems with fewer inputs than states. Such systems are structurally difficult to control and their system theoretic quantities can scale exponentially with the system dimension dominating learning complexity. Under some additional structural assumptions (bounding systems away from uncontrollability), we provide qualitatively matching upper bounds. We prove that learning complexity can be at most exponential with the controllability index of the system, that is the degree of underactuation. Copyright © 2022, The Authors. All rights reserved.

关键词： Linear systems

来源：评论

学校读者我要写书评

暂无评论

Consistent and Asymptotically Statistically-Efficient Solution to Camera Motion Estimation

arXiv

引用

arXiv 2024年

作者： Zeng, Guangyang Zeng, Qingcheng Li, Xinghan Mu, Biqiang Chen, Jiming Shi, Ling Wu, Junfeng The School of Data Science Chinese University of Hong Kong Shenzhen Shenzhen518172 China The College of Control Science and Engineering The State Key Laboratory of Industrial Control Technology Zhejiang University Hangzhou310027 China Key Laboratory of Systems and Control Institute of Systems Science Academy of Mathematics and Systems Science Chinese Academy of Sciences Beijing100190 China The Department of Electronic and Computer Engineering Hong Kong University of Science and Technology Hong Kong

Given 2D point correspondences between an image pair, inferring the camera motion is a fundamental issue in the computer vision community. The existing works generally set out from the epipolar constraint and estimate the essential matrix, which is not optimal in the maximum likelihood (ML) sense. In this paper, we dive into the original measurement model with respect to the rotation matrix and normalized translation vector and formulate the ML problem. We then propose a two-step algorithm to solve it: In the first step, we estimate the variance of measurement noises and devise a consistent estimator based on bias elimination;In the second step, we execute a one-step Gauss-Newton iteration on manifold to refine the consistent estimate. We prove that the proposed estimate owns the same asymptotic statistical properties as the ML estimate: The first is consistency, i.e., the estimate converges to the ground truth as the point number increases;The second is asymptotic efficiency, i.e., the mean squared error of the estimate converges to the theoretical lower bound - Cramer-Rao bound. In addition, we show that our algorithm has linear time complexity. These appealing characteristics endow our estimator with a great advantage in the case of dense point correspondences. Experiments on both synthetic data and real images demonstrate that when the point number reaches the order of hundreds, our estimator outperforms the state-of-the-art ones in terms of estimation accuracy and CPU time. Copyright © 2024, The Authors. All rights reserved.

关键词： Maximum likelihood estimation

来源：评论

学校读者我要写书评

暂无评论

引用

Photonics Research 2022年第3期10卷 678-686页

作者： Hongqiang Zhou Xin Li Zhentao Xu Xiaowei Li Guangzhou Geng Junjie Li Yongtian Wang Lingling Huang Beijing Engineering Research Center of Mixed Reality and Advanced Display School of Optics and PhotonicsBeijing Institute of TechnologyBeijing 100081China Beijing Aerospace Automatic Control Institute Beijing 100143China Laser Micro/Nano-Fabrication Laboratory School of Mechanical EngineeringBeijing Institute of TechnologyBeijing 100081China Institute of Physics Chinese Academy of SciencesBeijing 100191China show less

Metasurface holography is becoming a universal platform that has made a considerable impact on nanophotonics and information optics,due to its advantage of large capacity and multiple ***,we propose a correlated triple amplitude and phase holographic encryption based on an all-dielectric *** develop an optimized holographic algorithm to obtain quantitatively correlated triple holograms,which can encrypt information in multiple wavelength and polarization *** apply the“static”and“dynamic”pixels in our design,*** kinds of isotropic square nanofins are selected,one functioning as a transmitter and the other functioning as a blocker counterintuitively at both working wavelengths,while another anisotropic rectangle nanofin can transmit or block light in co-polarization selectively,mimicking“dynamic”amplitude ***,such“dynamic”nanofins can simultaneously function as a phase modulator in cross-polarization only at the transmission *** is,through smart design,different dielectric meta-atoms functioning as spectral filters as well as phase contributors can compositely achieve triple hybrid amplitude and phase *** strategy promises to be applied in compact large-capacity information storage,colorful holographic displays,optical encryption,multifunctional imaging devices,and so on.

关键词： holographic phase dielectric

来源：评论

学校读者我要写书评

暂无评论

Safe reinforcement learning task planning with uncertain duration and resource consumption in limited daytime for lunar rovers

Safe reinforcement learning task planning with uncertain dur...

引用

2024 IAF Space Operations Symposium at the 75th International Astronautical Congress, IAC 2024

作者： Lu, Siyao Xu, Rui Gao, Ai Li, Zhaoyu Liu, Jiamou Zhang, Libo Zhao, Zhijun Zhu, Shengying Li, Yuqiong School of Aerospace Engineering Beijing Institute of Technology 5th Zhongguancun South Street Haidian Distinct Beijing Beijing100081 China Key Laboratory of Autonomous Navigation and Control for Deep Space Exploration Beijing Institute of Technology Ministry of Industry and Information Technology Beijing100081 China School of Computer Science University of Auckland 34 Princes Street Auckland1010 New Zealand Beijing Institute of Spacecraft Engineering Beijing Beijing100094 China Institute of Mechanics Chinese Academy of Sciences 15th North Fourth Ring West Road Haidian District Beijing100190 China

ISBN: (纸本)9798331312183

The International Lunar Research Station will be established near the south pole through advanced unmanned rovers at the beginning period. The south pole of the moon has short daytime, so the efficiency of remote control is inadequate. However, the duration and power resource usage of the lunar rover moving on the lunar surface remains uncertain because of different loading weight of collection and changes of terrain in moving. What’s more, a lunar rover needs to move back to the base before nighttime without sunlight to provide energy, while the whole time of working on the moon also needs optimization. We select to solve the planning problem with reinforcement learning (RL) due to its capability in tackling uncertainty and optimization. However, traditional reinforcement learning cannot guarantee safety with time uncertainty, resource uncertainty, and constraints due to the soft constraints in optimization. Therefore, we propose a new way through safe reinforcement learning of task planning and resource collection optimization among tasks with uncertain duration and resource collection. We consider a scenario of in-situ material utilization for the lunar base, where there are tasks of moving, charging, collecting, material delivering, and material receiving, all of which have uncertain duration in execution and every task must be done during the daytime except the charging. Resource collection is related to power consumption in moving so it will be decided according to the remaining power. We further propose an architecture on reinforcement learning to let rovers decide the next step instantaneously according to the expected task duration, the remaining time, and the remaining power. Maximizing the amount of material delivered is an optimization target in training while keeping the rovers safe to work only in the daytime without an empty battery. In our experiment, we intend that our way works well in the uncertainties, and it will lead the rover to finish tasks w

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Critical Test Cases Generalization for Autonomous Driving Object Detection Algorithms

Critical Test Cases Generalization for Autonomous Driving Ob...

引用

IEEE Symposium on Intelligent Vehicle

作者： Zhengmin Jiang Jia Liu Ming Sang Huiyun Li Yi Pan Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen China University of Chinese Academy of Sciences (UCAS) Beijing China Guangdong-Hong Kong-Macao Joint Laboratory of Human-Machine Intelligence-Synergy Systems Dean of Computer Science and Control Engineering Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen China

ISBN: (数字)9798350348811

ISBN: (纸本)9798350348828

Visual-based object detection has become a crucial component in the realm of autonomous vehicles. However, conducting reliable testing for such systems remains unresolved. In this paper, we advocate for the application of causal inference to investigate the pivotal environmental factors influencing detection accuracy. Through the integration of diffusion models, we address the specialized conditional generalization of hazardous testing images. Our approach involves the construction of observational data to attribute key factors and fine-tune the diffusion model. Additionally, we introduce an optimal prompt words search method that strikes a balance between test coverage and level of challenge. Subsequently, leveraging these optimal prompts, we propose a cost-effective testing image generation through both "Text2Scene" and "Image2Scene" fashions. The experimental results indicate that, on the generalized dataset, the performance of object detection algorithms is the poorest, with the average detection accuracy decreasing from 0.81 to 0.285. Moreover, retraining object detection models on our generalized critical test cases can ultimately enhance algorithm performance, achieving a median accuracy improvement of up to 8.13%. Overall, our research proposes a novel approach to generalize test cases, thereby contributing to the advancement and deployment of safer autonomous vehicles.

关键词： Training Accuracy Search methods Text to image Object detection Diffusion models Inference algorithms

来源：评论

学校读者我要写书评

暂无评论

Audio Deepfake Detection Based on a Combination of F0 Information and Real Plus Imaginary Spectrogram Features 1

Audio Deepfake Detection Based on a Combination of F0 Inform...

引用

1st International Workshop on Deepfake Detection for Audio Multimedia, DDAM 2022

作者： Xue, Jun Fan, Cunhang Lv, Zhao Tao, Jianhua Yi, Jiangyan Zheng, Chengshi Wen, Zhengqi Yuan, Minmin Shao, Shegang School of Computer Science and Technology Anhui University Hefei China NLPR Institute of Automation Chinese Academy of Sciences Beijing China Institute of Acoustics Chinese Academy of Sciences Beijing China Qiyuan Laboratory Beijing China National Environmental Protection Engineering and Technology Center for Road Traffic Noise Control Research Institute of Highway Ministry of Transport Beijing China

ISBN: (纸本)9781450394963

Recently, pioneer research works have proposed a large number of acoustic features (log power spectrogram, linear frequency cepstral coefficients, constant Q cepstral coefficients, etc.) for audio deepfake detection, obtaining good performance, and showing that different subbands have different contributions to audio deepfake detection. However, this lacks an explanation of the specific information in the subband, and these features also lose information such as phase. Inspired by the mechanism of synthetic speech, the fundamental frequency (F0) information is used to improve the quality of synthetic speech, while the F0 of synthetic speech is still too average, which differs significantly from that of real speech. It is expected that F0 can be used as important information to discriminate between bonafide and fake speech, while this information cannot be used directly due to the irregular distribution of F0. Insteadly, the frequency band containing most of F0 is selected as the input feature. Meanwhile, to make full use of the phase and full-band information, we also propose to use real and imaginary spectrogram features as complementary input features and model the disjoint subbands separately. Finally, the results of F0, real and imaginary spectrogram features are fused. Experimental results on the ASVspoof 2019 LA dataset show that our proposed system is very effective for the audio deepfake detection task, achieving an equivalent error rate (EER) of 0.43%, which surpasses almost all systems. © 2022 Association for Computing Machinery.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Study of photophysical properties of Cdq2 thin film

引用

Materials Today: Proceedings 2022年 66卷 202-204页

作者： Lougdali, M. El Kouari, Y. Anoua, R. Zazoui, M. El Oudghiri-Idrissi, I. Abboud, Y. Zawadzka, A. Sahraoui, B. Laboratory of Materials Energy and Control System Faculty of Sciences and Technology Hassan II University of Casablanca Mohammedia B.P 146 Morocco Department of Automatic and Measurement Faculty of Physics Astronomy and Informatics Nicolaus Copernicus University Torun Poland Laboratory of Engineering Sciences for Energy National School of Applied Sciences of El Jadida El Jadida BP 1166 Morocco Faculty of Sciences Ben M'sik University of Hassan II of Casablanca Casablanca Morocco Centre for Modern Interdisciplinary Technologies Nicolaus Copernicus University Wilenska 4 Torun 87-100 Poland MOLTECH-Anjou UMR 6200 CNRS UNIV Angers 2 bd Lavoisier Angers 49045 France

In this work, the morphological and optical properties of the cadmium (II) bis(8-hydroxyquinoline) (Cdq2) thin film are presented. The film was elaborated by physical deposition technique. The Atomic Force Microscopy (AFM) image shows a homogenous surface. The transmittance was measured in the range of 300–1200 nm with UV–visible spectroscopy. The emission of the film was characterized via the photoluminescence spectroscopy, a strong luminescence has been found. The measurements done at low temperatures show a decrease of the intensity of luminescence in the temperature range of 77–300 K. © 2022

关键词： Thin films

来源：评论

学校读者我要写书评

暂无评论

Research on Black-Box Adversarial Attack Based on Transformer

Research on Black-Box Adversarial Attack Based on Transforme...

引用

Frontiers technology of Information and computer (ICFTIC), IEEE International Conference on

作者： Wenjuan Zheng Hanxu Luo YuXin Ji Haipeng Li Longjian Cong Master of Computer Vision National Key Laboratory of Aerospace Intelligent Control Technology Beijing China Beijing Aerospace Automatic Control Institute Beijing China Department of Information Engineering Wuhan University of Technology Wuhan Hubei Province China

The classic adversarial samples of black-box attacks are all aimed at the models of Convolutional neural networks (CNNs), but they do not perform well on the new recognition networks based on Transformer. In this paper, we propose an adversarial sample generation algorithm based on Vision transformers (VITs)‘ self-attention mechanism and patch partition. We noticed that different blocks in the VIT have uneven attention distribution, so we first generated a patch-based attention map and performed threshold segmentation, which is used as a mask to perform data enhancement operations based on patches with high weight and patches with low weight, and then exchanged information between patches to generate adversarial samples. The experiment of simulating black-box attack shows that the adversarial samples generated by the algorithm in this paper have a high success rate in all kinds of models based on Transformer of attacks, and also perform well on CNNs.

关键词： Closed box Benchmark testing Transformers Partitioning algorithms Convolutional neural networks Convergence

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：