检索结果-内蒙古大学图书馆

A novel robotic visual perception framework for underwater operation

Frontiers of Information Technology & Electronic engineering 2022年第11期23卷 1602-1619页

作者： Yue LU Xingyu CHEN Zhengxing WU Junzhi YU Li WEN State Key Laboratory of Management and Control for Complex Systems Institute of AutomationChinese Academy of SciencesBeijing 100190China Ytech Kuaishou TechnologyBeijing 100085China State Key Laboratory for Turbulence and Complex Systems Department of Advanced Manufacturing and RoboticsCollege of EngineeringPeking UniversityBeijing 100871China School of Mechanical Engineering and Automation Beihang UniversityBeijing 100191China

Underwater robotic operation usually requires visual perception(e.g.,object detection and tracking),but underwater scenes have poor visual quality and represent a special domain which can affect the accuracy of visual *** addition,detection continuity and stability are important for robotic perception,but the commonly used static accuracy based evaluation(i.e.,average precision)is insufficient to reflect detector performance across *** response to these two problems,we present a design for a novel robotic visual perception ***,we generally investigate the relationship between a quality-diverse data domain and visual restoration in detection *** a result,although domain quality has an ignorable effect on within-domain detection accuracy,visual restoration is beneficial to detection in real sea scenarios by reducing the domain ***,non-reference assessments are proposed for detection continuity and stability based on object ***,online tracklet refinement is developed to improve the temporal performance of ***,combined with visual restoration,an accurate and stable underwater robotic visual perception framework is ***-overlap suppression is proposed to extend video object detection(VID)methods to a single-object tracking task,leading to the flexibility to switch between detection and *** experiments were conducted on the ImageNet VID dataset and real-world robotic tasks to verify the correctness of our analysis and the superiority of our proposed *** codes are available at https://***/yrqs/VisPerception.

关键词： Underwater operation Robotic perception Visual restoration Video object detection

来源：评论

学校读者我要写书评

暂无评论

Accurate monitoring of machining process of Ti-6Al-4V using deep multi-task learning

Accurate monitoring of machining process of Ti-6Al-4V using ...

引用

International Conference on advanced Mechatronic systems (ICAMechS)

作者： Soyeon Park Sang Min Yang Gyeongho Kim Dong Min Kim Hoon Hee Lee Jae Gyeong Choi Sujin Jeon Sunghoon Lim Hyung Wook Park Department of Industrial Engineering UNIST Ulsan Republic of Korea Department of Mechanical Engineering UNIST Ulsan Republic of Korea Department of Mechanical Design Engineering Tech University of Korea Siheung Republic of Korea Extreme Process Control Group KITECH Jinju Republic of Korea Department of Industrial Engineering Graduate School of Artificial Intelligence Industry Intelligentization Institute UNIST Ulsan Republic of Korea Department of Industrial Engineering and Department of Mechanical Engineering Ulsan National Institute of Science and Technology Ulsan Republic of Korea

ISBN: (数字)9798350366204

ISBN: (纸本)9798350366211

Accurate machining process monitoring (MPM) is crucial to ensure manufacturing process stability and efficiency. In particular, tool wear, surface roughness, and cutting force comprise primary elements of MPM, which are physically interconnected and significantly affect machining quality and productivity. Hence, MPM should be performed through comprehensive consideration of the primary elements and their interactions. Yet, there is a lack of a unified approach to MPM that holistically predicts, which limits the practical applicability of MPM in real-world machining processes. Therefore, this work proposes a novel deep multi-task learning (MTL)-based method that integrates primary MPM elements by simultaneously predicting tool wear, surface roughness, and cutting force. To this end, the proposed method develops a probabilistic multitask likelihood that considers task uncertainty for seamless end-to-end training. The proposed method’s efficacy in MPM is validated with real-world datasets from an end-milling process of Ti-6Al-4V. The comprehensive experimental results demonstrate that the proposed method consistently shows superior prediction performance compared to existing single-task and MTL methods, indicating its effectiveness in real-world MPM.

关键词： Training Productivity Accuracy Uncertainty Force Machining Multitasking Surface roughness Rough surfaces Surface treatment

来源：评论

学校读者我要写书评

暂无评论

CHANCE CONSTRAINED PROBABILITY MEASURE OPTIMIZATION: PROBLEM FORMULATION, EQUIVALENT REDUCTION, AND SAMPLE-BASED APPROXIMATION

arXiv

引用

arXiv 2023年

作者： Shen, Xun Wu, Yuhu Ito, Satoshi Imura, Jun-Ichi School of Control Science and Engineering Dalian University of TechnologyDalian China Graduate School of Engineerning Osaka University Osaka Japan Department of Statistical Inference and Mathematics The Institute of Statistical Mathematics Tokyo Japan

Choosing decision variables deterministically (deterministic decision-making) can be regarded as a particular case of choosing decision variables probabilistically (probabilistic decision-making). It is necessary to investigate whether probabilistic decision-making can further improve the expected decision-making performance than deterministic decision-making when chance constraints exist. The problem formulation of optimizing a probabilistic decision under chance constraints has not been formally investigated. In this paper, for the first time, the problem formulation of Chance Constrained Probability Measure Optimization (CCPMO) is presented towards realizing optimal probabilistic decision-making under chance constraints. We first prove the existence of the optimal solution to CCPMO. It is further shown that there is an optimal solution of CCPMO with the probability measure concentrated on two decisions, leading to an equivalently reduced problem of CCPMO. The reduced problem still has chance constraints due to uncertain disturbance. We then propose the sample-based smooth approximation method to solve the reduced problem. Samples of model uncertainties are used to establish an approximate problem of the reduced problem. Algorithms for general nonlinear programming problems can solve the approximate problem. The solution of the approximate problem is an approximate solution of CCPMO. A numerical example of controlling a quadrotor in turbulent conditions has been conducted to validate the proposed probabilistic decision-making under chance constraints. © 2023, CC BY-NC-SA.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Trajectory Tracking of Tractor-Trailer Wheeled Mobile Robots via Dynamic Feedback Linearization in Forward and Backward Motion

Trajectory Tracking of Tractor-Trailer Wheeled Mobile Robots...

引用

International Conference on control, Instrumentation, and Automation

作者： Mohammad Olyai Khalil Alipour Bahram Tarvirdizadeh Majid Sorouri Mohammad Ghamari Department of Mechatronics Eng. School of Intelligent Systems Engineering College of Interdisciplinary Science and Technology Advanced Service Robots (ASR) Laboratory University of Tehran Tehran Iran Department of Electronic Engineering Maynooth University Maynooth Co. Kildare Ireland Department of Computer and Mechatronics Engineering Science and Research Branch Islamic Azad University Tehran Iran Electrical Engineering Department California Polytechnic State University San Luis Obispo CA USA

ISBN: (数字)9798331509972

ISBN: (纸本)9798331509989

One type of wheeled mobile robot widely used in public transportation and for carrying high payloads is the tractor-trailer wheeled robots (TTWRs). This study considers a differentially-driven tractor under pure rolling conditions, which is subject to nonholonomic constraints. controlling a TTWR in both backward and forward motion is challenging due to inherent instability. To address this issue and achieve trajectory tracking control for these systems, this paper employs dynamic feedback linearization (DFL) to overcome the limitations of static feedback linearization (SFL). The system’s response will be examined under various trajectories and initial conditions for both forward and backward motion.

关键词： Trajectory tracking Dynamics Wheels Kinematics Reinforcement learning Feedback linearization Trajectory Mobile robots Public transportation Payloads

来源：评论

学校读者我要写书评

暂无评论

Noise-induced alternations and data-driven parameter estimation of a stochastic perceptual model

引用

The European Physical Journal Special Topics 2024年第3期234卷 707-719页

作者： Wang, Xiaolong Feng, Jing Liu, Qi Xu, Yong School of Mathematics and Statistics Shaanxi Normal University Xi’an China School of Mathematics and Statistics Northwestern Polytechnical University Xi’an China MOE Key Laboratory for Complexity Science in Aerospace Northwestern Polytechnical University Xi’an China School of Science Xi’an University of Posts and Telecommunications Xi’an China Department of Systems and Control Engineering Tokyo Institute of Technology Tokyo Japan

Neural systems are inherently noisy and our perceptual system can be then influenced from time to time. In this paper, we considered a perceptual model perturbed by Lévy colored noise, which is much easier to be satisfied in real-world environments than the general Gaussian noise. To elucidate the mechanism underlying the alternation behaviors induced by noise, we characterized the perceptual dynamics in terms of three statistical measures: the mean dominance duration, the number of alternations and the predominance of each interpretation. Numerical simulations showed that the stability index as well as the scale factor and the correlation time of the noise can lead to distinct changes in these measures. Then, attention was paid to data-driven parameter estimation which has typically received less attention than the exploration of stochastic behaviors. A distinctive neural network was proposed to give rise to joint estimates of system parameters and noise parameters, which can also give the measurement to describe the accuracy of estimation. The good performances of our method are shown by simulation tests.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Prediction of endometrial cancer MRI images based on deep learning and improved Bayesian extreme learning machine ensemble learning 5

Prediction of endometrial cancer MRI images based on deep le...

引用

5th International Conference on Frontiers Technology of Information and Computer, ICFTIC 2023

作者： Wang, Ximiao Hu, Qinghui Dai, Xisheng Li, Peijun Chen, Yuan Guangxi University of Science and Technology Institute of Intelligent Systems and Control Guangxi Province Liuzhou City545006 China Guilin University of Aerospace Technology School of Computer Science and Engineering Guangxi Province Guilin City541004 China Jiangmen Central Hospital Department of Radiology Guangdong Province Jiangmen City529000 China Jiangmen Central Hospital Department of Gynecology Guangdong Province Jiangmen City529000 China

ISBN: (纸本)9798350309034

For the prediction of deep myometrial invasion (DMI) in endometrial cancer (EC), this study proposes an ensemble learning method which combines deep learning (DL) and improved Bayesian extreme learning machine (BELM). Firstly, the MRI images of endometrial cancer are preprocessed to meet the requirements. Secondly, the deep features relevant to the task are extracted from the images by using convolutional kernels. Finally, the bootstrap resampling method is employed to repeatedly sample multiple training subsets from the training set. The improved Bayesian extreme learning machine is used as the base classifier to train multiple independent sub-models. An ensemble learning classifier is constructed using an ensemble strategy to improve the prediction accuracy and stability of the model. Experimental results show that the proposed method achieves an AUC of 0.758 on the internal validation set and 0.740 on the external validation set, which demonstrat good generalization ability and stability of the proposed method. © 2023 IEEE.

关键词： Bayesian Extreme Learning Machine Deep Learning Deep Myometrial Invasion Endometrial Cancer Ensemble Learning

来源：评论

学校读者我要写书评

暂无评论

Path Following of a Tractor-Trailer System via Dynamic Extension in Forward and Backward Motion

Path Following of a Tractor-Trailer System via Dynamic Exten...

引用

RSI/ISM International Conference on Robotics and Mechatronics (ICROM)

作者： Mohammad Olyai Khalil Alipour Bahram Tarvirdizadeh Majid Sorouri Mohammad Ghamari Department of Mechatronics Eng. Advanced Service Robots (ASR) Laboratory School of Intelligent Systems Engineering College of Interdisciplinary Science and Technology University of Tehran Tehran Iran Department of Electronic Engineering Maynooth University Maynooth Co. Kildare Ireland Department of Computer and Mechatronics Engineering Science and Research Branch Islamic Azad University Tehran Iran Electrical Engineering Department California Polytechnic State University San Luis Obispo CA USA

ISBN: (数字)9798331529734

ISBN: (纸本)9798331529741

Tractor-trailer wheeled robots (TTWRs) have gained significant attention across various industries and control studies due to their complex dynamics and non-minimum phase behavior, which pose substantial control challenges. This study investigates the control of a differentially-driven tractor to follow a specified path under pure rolling conditions in both forward and backward motion. Notably, it has been established that using static feedback linearization (SFL) leads to instability during backward motion. In contrast, this research uses dynamic feedback linearization (DFL), also known as dynamic extension, for controlling the tractor-trailer system in both directions for the first time. Our findings demonstrate that the internal dynamics of the system remain stable in both forward and backward motions, enabling successful adherence to the desired path.

关键词： Industries Mechatronics Service robots Dynamics Wheels Optimal control Reinforcement learning Agricultural machinery Feedback linearization Mobile robots

来源：评论

学校读者我要写书评

暂无评论

Flexible control of the Interline DC Power Flow controller Using Virtual Capacitor in VSC-HVDC Grids

Flexible Control of the Interline DC Power Flow Controller U...

引用

Power Electronic and Drive systems and Technologies Conference (PEDSTC)

作者： Mirhamed Pourmirasghariyan Mirsajed Pourmirasghariyan Seyed Saeid Heidari Yazdi Seyyed Yousef Mousazadeh Mousavi Kumars Rouzbehi G. B. Gharehpetian Departement of Electrical and Computer Engineering Amirkabir University of Technology Tehran Iran School of Electrical and Computer Engineering College of Engineering University of Tehran Tehran Iran Department of Electrical & Computer Engineering School of Engineering and Digital Science Nazarbayev University Nur-Sultan Kazakhstan Faculty of Engineering and Technology University of Mazandaran Sari Iran Department of Systems and Automatic Control Engineering University of Seville Seville Spain

The performance of Interline DC Power Flow controllers (IDC-PFCs) in Voltage Source Converters (VSC)-based High Voltage Direct Current (HVDC) grids, can be affected due to different issues. The current limitation of HVDC lines, the voltage limitation of HVDC buses, and DC voltage of the IDC-PFC intermediary capacitor prevent effective and efficient operation of IDC-PFCs. In this paper, it is shown that this issue can be overcome by using a virtual capacitor in parallel with the IDC-PFC intermediary capacitor. Also, an energy control-based scheme is proposed for the operation of IDC-PFCs in VSC-HVDC grid. The benefits of using the virtual capacitor are: widening the operational area of the IDC-PFCs for the determined duty cycle and injecting more voltage in series to the interconnected HVDC line to control the related HVDC line current. The proposed solution is successfully evaluated on a CIGRE three-terminal VSC-HVDC grid which is modeled by linearized space-state equations.

关键词： Fluctuations HVDC transmission Capacitors High-voltage techniques Boosting Mathematical models Power conversion

来源：评论

学校读者我要写书评

暂无评论

Evaluation of Hydrogen Ions Flowing through Protonic Ceramic Fuel Cell Using Ytterbium-Doped Barium Zirconate as electrolyte

Evaluation of Hydrogen Ions Flowing through Protonic Ceramic...

引用

243rd ECS Meeting

作者： Okuyama, Yuji Harada, Yoshiaki Mikami, Yuichi Yamauchi, Kosuke Kuroha, Tomohiro Shimada, Hiroyuki Yamaguchi, Yuki Mizutani, Yasunobu Research Center for Sustainable Energy & Environmental Engineering Faculty of Engineering University of Miyazaki 1-1 Gakuenkibanadai-nishi Miyazaki889-2192 Japan Department of Environmental Robotics Mechanical Systems and Informatics Course Graduate School of Engineering University of Miyazaki 1-1 Gakuenkibanadai-nishi Miyazaki889-2192 Japan Interdisciplinary Graduate School of Agriculture and Engineering University of Miyazaki 1-1 Gakuenkibanadai-nishi Miyazaki889-2192 Japan Technology Division Panasonic Holdings Corporation 3-1-1 Yagumo-naka-machi Osaka Moriguchi City570-8501 Japan Innovative Functional Materials Research Institute National Institute of Advanced Industrial Science and Technology 4-205 Sakurazaka Moriyama-ku Aichi Nagoya463-8560 Japan

ISBN: (纸本)9781607685395

To measure the proton current in a PCFC (protonic ceramic fuel cell), the proton current detector was developed using a proton conducting oxide. The amount of proton current that flowed in the PCFC can be measured by an apparatus developed based on the electromotive force of an electrochemical cell using 10 mol% In-doped CaZrO3 (hydrogen sensor) and Y-stabilized zirconia (oxygen sensor). The water vapor pressure on the cathode changed when hydrogen ions pass through the PCFC. The hydrogen ion current can be determined by monitoring the water vapor pressure. The electronic leakage was then estimated from the hydrogen ion current and external current. We measured the current of hydrogen flowing through protonic ceramic fuel cell using ytterbium-doped barium zirconate as the electrolyte. Hydrogen ions and holes were found to leak under the OCV at 700°C. The electronic leakage was found to be suppressed with the increasing electrolyte film thickness. On the other hand, no leakage of hydrogen and holes was observed at 500°C. © The Electrochemical Society.

关键词： Ions

来源：评论

学校读者我要写书评

暂无评论

controlling Organic Carbon Increase in Oxygenated Marine Sediments by Using Decarburization Slag

SSRN

引用

SSRN 2024年

作者： Mahmood, Mukseet Kato, Natsuki Nakai, Satoshi Gotoh, Takehiko Nishijima, Wataru Umehara, Akira Department of Oceanography and Coastal Sciences Louisiana State University LA United States Graduate School of Advanced Science and Engineering Hiroshima University Hiroshima Japan Environmental Research and Management Center Hiroshima University Hiroshima Japan

The chemical oxygen demand (COD) in the Seto Inland Sea, Japan has increased in the recent decades due to the increase of bottom dissolve oxygen (DO) concentration which stimulated several autotrophic microorganisms, specially sulfur oxidizing bacteria (SOB). This increased SOB activity due to the oxygenation of the bottom sediment synthesized new organic matter (OM) which contributed dissolved organic carbon to the overlying seawater. This phenomenon further led to hypoxia in some subareas in the Seto Inland Sea. Higher pH or alkaline environment has been found to be an unfavorable condition for SOB. In this research, we used decarburization slag to elevate the pH of sediment to control the SOB activity and consequently reduce OM production in the sediment. Microbial community analysis showed less SOB activity in the slag added aerated sediment which accounts for the controlled increase of OM in the sediment. An additional experiment was conducted with Magnesium oxide to confirm whether elevated pH can control the OM increase in sediment due to rising DO. All these results showed that decarburization slag can elevate the pH of the sediment to a certain level which can control the SOB activity followed by controlled increase of OM in the sediment. © 2024, The Authors. All rights reserved.

关键词： Slags

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：