检索结果-内蒙古大学图书馆

SSRN 2024年

作者： Duan, Juntao Li, Yuanzheng Li, Yang Liu, Zhiwei Zhao, Yong School of Artificial Intelligence and Automation Key Laboratory on Image Information Processing and Intelligent Control of Ministry of Education Huazhong University of Science and Technology Wuhan430074 China Key Laboratory of Modern Power System Simulation and Control & Renewable Energy Technology Ministry of Education Northeast Electric Power University Jilin132012 China

The increasing processing demands of information technology (IT) workloads cause the booming of data centers (DCs) in recent years. The servers in the DC emit much heat when processing the IT workloads and thus the DC temperature rises. The power consumption when controlling the DC temperature using the air conditioning (A/C) of the DC is high, which leads to expensive power bills. To reduce the power cost, using renewable energy (RE) to power DC has raised much attention in recent years. However, the intermittency of RE and the uncertainties of outside temperature pose operational challenges. Therefore, in this paper, a data-driven statistical-feasibility-based robust rolling optimization framework for the operation of hydrogen-DC microgrid (H2-DCMG) is proposed to control the DC temperature considering these uncertainties and the intermittency of RE. In the framework, the hydrogen energy storage system (HESS) is introduced to deal with the intermittency of RE, and robust optimization (RO) is adopted to deal with the uncertainty of outside temperature. The statistical feasibility is introduced into the framework to decrease the conservatism of RO, through relaxing the DC temperature constraints without harming normal DC operations. Moreover, we propose the Statistical-Guarantee-based Vertex Link (SGVL) algorithm to construct a polyhedron uncertain set of outside temperatures that can ensure the results of dispatch are economical and satisfy statistical feasibility. The constructed polyhedron uncertain set is linear, which reduces computational complexity in solving. A case study based on the real-world temperature dataset verifies the superiority of the SGVL algorithm on the aspect of the economic cost. It further validates the effectiveness of the proposed robust optimization framework for DC temperature control. © 2024, The Authors. All rights reserved.

关键词： Air conditioning

来源：评论

学校读者我要写书评

暂无评论

Parameter Tuning of PID controller of Servo system Based on Particle Swarm Optimization Algorithm

Parameter Tuning of PID Controller of Servo System Based on ...

引用

作者： Chen Lianbo Xiong Xinhong Zheng Yousheng Zhang Yanhui Zhang Guoqing Wu Xinyu Feng Wei Guangdong Provincial Key Lab of Robotics and Intelligent System Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences CAS Key Laboratory of Human-Machine-Intelligence Synergic Systems Shenzhen Institutes of Advanced Technology School of Logistics Engineering Wuhan University of Technology

In order to improve the control precision of permanent magnet synchronous motor servo drive, a Proportional-Integral-Differential(PID) control method based on particle swarm optimization(PSO) algorithm is proposed. Firstly, the mathematical model of the permanent magnet synchronous motor was established. Then the PSO algorithm was used to adjust the parameters of the PID controller. Finally, the simulation experiment was carried out under the MATLAB/Simulink environment to test its performance. Compared with the traditional manual parameters tuning, the PID controller based on PSO algorithm had better performance and better stability.

关键词： swarm Parameter Tuning of PID controller of Servo system Based on Particle Swarm Optimization Algorithm Swarm

来源：评论

学校读者我要写书评

暂无评论

ESNet: evolution and succession network for high-resolution salient object detection 24

ESNet: evolution and succession network for high-resolution ...

引用

Proceedings of the 41st International Conference on machine Learning

作者： Hongyu Liu Runmin Cong Hua Li Qianqian Xu Qingming Huang Wei Zhang Institute of Information Science Beijing Jiaotong University & Beijing Key Laboratory of Advanced Information Science and Network Technology Beijing China School of Control Science and Engineering Shandong University & Key Laboratory of Machine Intelligence and System Control Ministry of Education Jinan China School of Computer Science and Technology Hainan University Hainan China Key Laboratory of Intelligent Information Processing Institute of Computing Technology CAS Beijing China School of Computer Science and Technology University of Chinese Academy of Sciences Beijing China

Preserving details and avoiding high computational costs are the two main challenges for the High-Resolution Salient Object Detection (HRSOD) task. In this paper, we propose a two-stage HRSOD model from the perspective of evolution and succession, including an evolution stage with Low-resolution Location Model (LrLM) and a succession stage with High-resolution Refinement Model (HrRM). The evolution stage achieves detail-preserving salient objects localization on the low-resolution image through the evolution mechanisms on supervision and feature; the succession stage utilizes the shallow high-resolution features to complement and enhance the features inherited from the first stage in a lightweight manner and generate the final high-resolution saliency prediction. Besides, a new metric named Boundary-Detail-aware Mean Absolute Error (MAEBD) is designed to evaluate the ability to detect details in high-resolution scenes. Extensive experiments on five datasets demonstrate that our network achieves superior performance at real-time speed (49 FPS) compared to state-of-the-art methods. Our code is publicly available at: https://***/rmcong/ESNet_ICML24.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Research on Position Sensorless control of PMSM Based on Improved SMO

Research on Position Sensorless Control of PMSM Based on Imp...

引用

作者： Zhang Guoqing Xiong Xinhong Zheng Yousheng Zhang Yanhui Chen Lianbo Wu Xinyu Feng Wei Guangdong Provincial Key Lab of Robotics and Intelligent System Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences CAS Key Laboratory of Human-Machine-Intelligence Synergic Systems Shenzhen Institutes of Advanced Technology School of Logistics Engineering Wuhan University of Technology

The sliding mode observer（SMO） can effectively achieve the permanent magnet synchronous motor（PMSM） to perform position sensorless control, but there are still drawbacks of system chattering and high complexity. In this paper, an improved SMO is established based on hyperbolic tangent function and Kalman filter. The system chattering is effectively suppressed, and the accuracy of position and speed observation error is significantly improved without phase compensation. It is found that the convergence rate of the hyperbolic tangent function has a strong correlation with the system chattering degree and the speed observation error. When a is between 3 and 4, the speed error accuracy of the improved SMO is the optimum situation.

关键词：

来源：评论

学校读者我要写书评

暂无评论

FIRE: A Dataset for Feedback Integration and Refinement Evaluation of Multimodal Models

arXiv

引用

arXiv 2024年

作者： Li, Pengxiang Gao, Zhi Zhang, Bofei Yuan, Tao Wu, Yuwei Harandi, Mehrtash Jia, Yunde Zhu, Song-Chun Li, Qing Beijing Key Laboratory of Intelligent Information Technology School of Computer Science & Technology Beijing Institute of Technology China State Key Laboratory of General Artificial Intelligence BIGAI China State Key Laboratory of General Artificial Intelligence Peking University China Department of Electrical and Computer System Engineering Monash University Australia Guangdong Laboratory of Machine Perception and Intelligent Computing Shenzhen MSU-BIT University China Department of Automation Tsinghua University China

Vision language models (VLMs) have achieved impressive progress in diverse applications, becoming a prevalent research direction. In this paper, we build FIRE, a feedback-refinement dataset, consisting of 1.1M multi-turn conversations that are derived from 27 source datasets, empowering VLMs to spontaneously refine their responses based on user feedback across diverse tasks. To scale up the data collection, FIRE is collected in two components: FIRE-100K and FIRE-1M, where FIRE-100K is generated by GPT-4V, and FIRE-1M is freely generated via models trained on FIRE-100K. Then, we build FIRE-Bench, a benchmark to comprehensively evaluate the feedback-refining capability of VLMs, which contains 11K feedback-refinement conversations as the test data, two evaluation settings, and a model to provide feedback for VLMs. We develop the FIRE-LLaVA model by fine-tuning LLaVA on FIRE-100K and FIRE-1M, which shows remarkable feedback-refining capability on FIRE-Bench and outperforms untrained VLMs by 50%, making more efficient user-agent interactions and underscoring the significance of the FIRE dataset. Copyright © 2024, The Authors. All rights reserved.

关键词： Fireclay

来源：评论

学校读者我要写书评

暂无评论

Transformer-Based Fusion of RGB and Depth Images for Terrain Recognition

Transformer-Based Fusion of RGB and Depth Images for Terrain...

引用

International Conference on Biomimetic intelligence and Robotics & Medical Robotics Forum, ICBIR+MRF 2024

作者： Chen, Hui Chen, Chunjie Wang, Zhuo Yang, Fangliang Pan, Heng Wu, Xinyu Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen518055 China Shenzhen College of Advanced Technology University of Chinese Academy of Sciences Shenzhen518055 China Guangdong Provincial Key Lab of Robotics and Intelligent System Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen518055 China Guangdong-Hong Kong-Macao Joint Laboratory of Human-Machine Intelligence-Synergy Systems Shenzhen518055 China

This research aims to explore key issues in the field of walking robots and exoskeletons. By using a depth camera to record human walking data in different terrains and employing RGB and depth information for image classification, our approach utilizes both early fusion and late fusion methods to explore their impact on terrain classification. This approach achieved fast and accurate performance in recognizing terrain. We captured data for walking upstairs, downstairs, upward ramps, downward ramps and level ground and used the vision transformer for data fusion. This work compares the performance of unimodal RGB model, unimodal deep model, Pre-Fusion model and Post-Fusion model in terms of accuracy, recall and processing frequency, with accuracies of 0.954, 0.934, 0.976, and 0.976, respectively. The results show that the Post-Fusion model slightly outperforms the Pre-Fusion model in terms of accuracy and recall with more reliable classification performance. To understand the attention mechanism better, we've been visualizing the weights of the model, observing how different attention heads may capture different features of the data from various dimensional perspectives. The visualization helps in interpreting the model's focus and how it distinguishes between features of different nature, such as color texture and spatial depth. These findings can inform the ongoing refinement of terrain classification systems for applications in robotics and autonomous navigation. © 2024 The Authors.

关键词： RGB color model

来源：评论

学校读者我要写书评

暂无评论

The big data analysis of rail equipment accidents based on the maximal information coefficient

引用

Journal of Transportation Safety and Security 2020年第7期12卷 959-976页

作者： Shao, Fubo Yang, Shuguo Sun, Bangcheng Jia, Limin Dong, Yulin Wang, Dong School of Mathematics and Physics Qingdao University of Science and Technology Qingdao China Institute of Artificial Intelligence and Control Qingdao University of Science and Technology Qingdao China The Post-Doctor Station of the CRRC Corporation Limited Beijing China CRRC Academy Co. Ltd Beijing China State Key Laboratory of Rail Traffic Control and Safety Beijing Jiaotong University Beijing China College of Mathematics and Systems Science Shandong University of Science and Technology Qingdao China Institute of Transportation System Science and Engineering Beijing Jiaotong University Beijing China

With more electrical and electronic equipment applied into the railway system, much more data can be collected and then the big data era of railway is coming. By employing the maximal information coefficient (MIC), the big data analysis of rail equipment accidents is studied to investigate the effect of the updating of rail equipment. The rail equipment accident data set of 25 years (from 1990 to 2014) is separated into three subsets corresponding to the period of the occurrence time of accidents. For every subset, the contributing factors to accident damage, to accident severity, and to accident cause are analyzed, respectively. The results show that the variation trend of the number of rail equipment accidents is more consistent with the variety of railroad service miles rather than carloads. And the factor of highway-rail grade crossings is an important one which accords with the facts. However, a seemingly surprising result is found that there will be more contributing factors to accident severity and to accident causes with more equipment applied into the railway system as time goes on. © 2019, © 2019 Taylor & Francis Group, LLC and The University of Tennessee.

关键词： Big data rail equipment accident temporal analysis the maximal information coefficient

来源：评论

学校读者我要写书评

暂无评论

A New Anomaly Detector of Flare Pilot Based on Siamese Network

A New Anomaly Detector of Flare Pilot Based on Siamese Netwo...

引用

Chinese Automation Congress (CAC)

作者： Xiaotian Xie Ke Gu Junfei Qiao Faculty of Information Technology Beijing University of Technology Beijing China Engineering Research Center of Intelligent Perception and Autonomous Control Ministry of Education Beijing Key Laboratory of Computational Intelligence and Intelligent System Beijing China Beijing Artificial Intelligence Institute Beijing China

ISBN: (数字)9781728176871

ISBN: (纸本)9781728176888

The flare pilot is the key to ensure that the flare system is ignited at any time. At present, domestic and foreign companies mainly use thermocouples, flame ionization detectors and other sensors to detect the working condition of the flare pilot. These electronic components have the hysteretic and vulnerable problems due to extreme heat, thermal shock and vibration, which may well further lead to the failure to ignite the flare gas with flare pilot in time and cause production accidents. In view of the above problems, this paper proposes an anomaly detector of flare pilot based on deep learning technology. First of all, we made an anomaly detection database for flare pilot, which was shot in a domestic petrochemical company. Then, we designed a specific siamese network based on the triplet loss function for learning the similarity between the samples, in order to apply to the curing scene of the flare pilot. Finally, it is determined whether the flare pilot is abnormal according to the similarity between the input picture and the positive and negative samples. Experimental results demonstrate that the proposed method can be effectively used for the anomaly detection of flare pilot.

关键词： Databases Anomaly detection Petrochemicals Feature extraction Employee welfare Detectors Combustion

来源：评论

学校读者我要写书评

暂无评论

A Review of Rotation Mechanical Fault Diagnosis Research Based on Deep Domain Adaptation

A Review of Rotation Mechanical Fault Diagnosis Research Bas...

引用

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

作者： Shun Zhang Gang Xie Juan Tian Hui Shi Xiaohong Zhang Xiaoyin Nie Xinlin Xie Shanxi Key Laboratory of Advanced Control and Equipment Intelligence Taiyuan China dept. of Electronic and Information Engineering Taiyuan University of Science and Technology Taiyuan China Division of Industrial and System Engineering Taiyuan China

With the rapid development of computer technology and the Internet of Things (IoT), a large amount of data containing both healthy and faulty states can be collected from existing devices in factories. However, the usable faulty state data is scarce. Transfer learning makes it possible to train efficient and reliable neural networks with a small number of samples. Domain adaptation, as a branch of transfer learning, can effectively realize knowledge transfer between small sample data. Starting from three subcategories of deep learning-based domain adaptation methods, this article summarizes the latest research achievements and provides insights into future research directions.

关键词：

来源：评论

学校读者我要写书评

暂无评论

PI2-CMA Based Trajectory Planning Method for the Tractor-Trailer Vehicle

PI2-CMA Based Trajectory Planning Method for the Tractor-Tra...

引用

Pattern Recognition and Artificial intelligence (PRAI), International Conference on

作者： You Wang Zehao Wang Jingchuan Wang Rui Guo Peng Xiao Institute of Medical Robotics and Department of Automation Ministry of Education Shanghai Jiao Tong University Key Laboratory of System Control and Information Processing Shanghai China State Grid Intelligence Technology CO. LTD

The motion primitive-based state lattice trajectory planning method has been widely used in the field of trajectory planning. However, due to the limitations of the search space and resolution of motion primitives, and the lack of consideration of scenario information during offline generation of motion primitives, the tractor-trailer vehicles can easily fall into "jackknife phenomenon" when making large pose adjustments in narrow scenarios, which brings dilemma for trajectory planning. In this paper, a trajectory planning algorithm is proposed based on a general model of tractor-trailer vehicle, which combines global planning and local optimization. The method first generates a series of motion primitives, including forward and backward driving conditions, and then an A ∗ based global state lattice planner is used to obtain a planning result, which is imported as the initial solution into the local trajectory optimizer based on PI 2 − CMA (Path Integral Policy Improvement with Covariance Matrix Adaptation) algorithm and dynamic potential method. Experiments show that this method significantly improves the performance in the obstacle avoidance, "jackknife phenomenon" avoidance and curvature compared to traditional motion primitive-based state lattice planning methods.

关键词：

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：