检索结果-内蒙古大学图书馆

9th ECCOMAS Thematic Conference on Smart Structures and Materials, SMART 2019

作者： Yu, Miao Du, Xiumei Fu, Jie Huang, Chaoqun Key Lab for Optoelectronic Technology and Systems Ministry of Education College of Optoelectronic Engineering Chongqing University Chongqing400044 China

ISBN: (纸本)9788494919466

Speed bumps are widely used in roads to reduce the traffic accidents. However, the transient impact caused by the speed bumps may increase the health risk of drivers and passengers and damage of vehicle. In this paper, the traditional skyhook controller and skyhook controller with adaptive genetic algorithm (GAG) is designed to attenuate the unwanted vibration. For verifying the effectiveness of the skyhook controller with GAG, the road test of the B segment car installed with four MR dampers is undertaken. The time domain and time-frequency methods are both used to analysis the vibration, and the results demonstrate that the reduction of peak value of vertical acceleration of skyhook controller with GAG is better than that of skyhook controller, comparing with the uncontrolled system. © 2019 9th ECCOMAS Thematic Conference on Smart Structures and Materials, SMART 2019. All rights reserved.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

Fault detection and fault tolerant control of vehicle semi-active suspension system with magnetorheological dampers 8

Fault detection and fault tolerant control of vehicle semi-a...

引用

8th ECCOMAS Thematic Conference on Smart Structures and Materials, SMART 2017 and 6th International Conference on Smart Materials and Nanotechnology in Engineering, SMN 2017

作者： Peng, Youxiang Yu, Miao Xu, Xiaoying Du, Xiumei Fu, Jie Key Lab for Optoelectronic Technology and Systems College of Optoelectronic Engineering Chongqing University Ministry of Education Chongqing400044 China

ISBN: (纸本)9788494690938

In engineering application, the sensor or actuator fault will lead to seriously damage to mechanical systems. The research of sensor or actuator fault diagnosis and fault-tolerant control is very important to improve the safety and reliability of the system. The paper investigates the fault diagnosis and faulttolerant methods of vehicle suspension system with Magnetorheological (MR) damper (actuator). First of all, the quarter-vehicle suspension system model is established. Then, an unknown input observer (UIO) is employed to detect the actuator fault in the vehicle MR suspension system. Next, the correlation coefficient method is used to isolate the fault of actuator fault in the system. Lastly, the skyhook fault-tolerant controller is designed for control compensation. The simulation results under sine excitation, random excitation and pump excitation show that the perfomance of the proposed fault-tolerent controller always outweight that of without fault-tolerant when actuator occurs fault. © 2017 International Center for Numerical Methods in Engineering. All rights reserved.

关键词： Fault detection

来源：评论

学校读者我要写书评

暂无评论

Design and implementation of the control system for magnetorheological suspension of all-terrain vehicle 30

Design and implementation of the control system for magnetor...

引用

30th Chinese Control and Decision Conference, CCDC 2018

作者： Xue, Jijun Yu, Miao Du, Xiumei Xu, Xiaoying Fu, Jie Xing, Zhiwei Key Lab for Optoelectronic Technology and Systems Ministry of Education College of Optoelectronic Engineering Chongqing University Chongqing400044 China

ISBN: (纸本)9781538612439

Magneto-rheological (MR) semi-active control technique is a promising research topic of the intelligent suspension. In this paper, the control system for magneto-rheological suspension of domestic all-terrain vehicle (ATV)was entirely designed by incorporating the skyhook algorithm into DSP controllers, signal processing filters, analog-to-digital conversion circuits, and current drivers. Then the vehicle road test of ATV suspension using MR dampers in the place of hydraulic dampers. The results showed that the controller is significant to attenuate the root mean square (RMS) acceleration responses at the seat cushion. Consequently, thepresented control system can effectively improve the comfort of passengers and achieve the desired control objectives. © 2018 IEEE.

关键词： Shock absorbers Acceleration Control systems Roads Damping Algorithms

来源：评论

学校读者我要写书评

暂无评论

Fuzzy-neural network control for a magnetorheological elastomer vibration control system with sinusoidal excitations 9

Fuzzy-neural network control for a magnetorheological elasto...

引用

9th ECCOMAS Thematic Conference on Smart Structures and Materials, SMART 2019

作者： Fu, Jie Bai, Junfeng Yang, Zening Dai, Zhenyu Liu, Jing Yu, Miao Key Lab for Optoelectronic Technology and Systems Ministry of Education College of Optoelectronic Engineering Chongqing University Chongqing400044 China

ISBN: (纸本)9788494919466

This paper presents the design method of a fuzzy-neural network controller (FNNC) for a MRE vibration control system with sinusoidal excitations to improve the vibration attenuation. A semi-active FC is designed to obtain the conrolled force based on the feedback signals of the relative displacement and absolute displacement of the isolation structure, then the BP neural network with good learning capability is employed to emulate the dynamic behaviours of output force of fuzzy controller (FC), excitation displacement, velocity and controlled current applied to the coil in MRE isolator. The acceleration responses of the system with FNNC are evaluated by physical experiments, the results indicate that the FNNC could maintain satisfying control effect in the presence sinusoidal excitations and is also more optimal than conventional FC, the reason is that the neural network controller can approximate the nonlinear function relationship among the controlled force, excitation displacement, velocity and controlled current, but the function relationship is only considered as the linear function in conventional FC. © 2019 9th ECCOMAS Thematic Conference on Smart Structures and Materials, SMART 2019. All rights reserved.

关键词： Fuzzy inference

来源：评论

学校读者我要写书评

暂无评论

Inverse modelling of magnetorheological elastomer isolator with recurrent neural network and genetic algorithms for real-time control 8

Inverse modelling of magnetorheological elastomer isolator w...

引用

8th ECCOMAS Thematic Conference on Smart Structures and Materials, SMART 2017 and 6th International Conference on Smart Materials and Nanotechnology in Engineering, SMN 2017

作者： Liao, Guanyao Fu, Jie Lai, Junjie Bai, Junfeng Yu, Miao Key Lab for Optoelectronic Technology and Systems College of Optoelectronic Engineering Ministry of Education Chongqing University Chongqing400044 China

ISBN: (纸本)9788494690938

Due to the controllability of stiffness and damping under the applied external magnetic field, magnetorheological elastomer (MRE) isolator has been proved effectively in the field of vibration control. For the realization of vibration control system, an accurate inverse model of MRE isolator is particularly important. However, the existing researches mainly focus on forward model for MRE isolators, including parametric and non-parametric models. But to date, there are few papers published on the inverse modelling of a MRE isolator. Feedforward neural networks have been applied to emulate the inverse dynamic behaviours of magneto-rheological dampers due to their good learning capability. But the data used for the training and validating of neural network is generated from numerical simulation of the parametric models proposed for an MR damper, which may be great differences from the practical application. In addition, the feedforward neural network is a static network, and has lower accuracy and poorer capacity of resisting disturbance. In this paper, a recurrent neural network (RNN) named Jordan network is proposed to approximate the inverse dynamic behaviours of a MRE isolator in shear-compression mixed mode by combining the genetic algorithms to search for the optimal network configuration. The dynamic characterization test system of the MRE mixed mode isolator is established, and the output forces of the isolator are obtained under different loading conditions (variable displacement with amplitudes and frequencies). Different from the direct current in forward mode of MRE isolator, the current used for training and validating of the network model is sinusoidal signal, which is also approximate to the real-time control application well. Experimental results show that the proposed Jordan network with genetic algorithms can represent inverse dynamic behaviours of the MRE isolator satisfactorily. © 2017 International Center for Numerical Methods in Engineering. All r

关键词： Real time control

来源：评论

学校读者我要写书评

暂无评论

Multi-Scale Deformable Context Fusion Pyramid Network for Object Detection in Aerial Images 8

Multi-Scale Deformable Context Fusion Pyramid Network for Ob...

引用

8th International Conference on Robotics and Artificial Intelligence, ICRAI 2022

作者： Cao, Kun Pan, Jieyun Zhao, Bingxin Li, Weihong Zhang, Tianyang Key Lab of Optoelectronic Technology & Systems of Education Ministry Chongqing University Chongqing China

ISBN: (纸本)9781450397544

In recent years, although many methods have made good progress in the object detection of aerial images, it is still difficult to improve the detection accuracy due to the large scale variation, exceptional aspect ratios and a large number of small and dense objects in aerial images. In this paper, we propose a Multi-Scale Deformable Context Fusion Pyramid Network (Multi-Scale DCFPN) for the object detection of aerial images. In the proposed Multi-Scale DCFPN, we design a Multi-Scale Deformable Context Fusion (MDCF) module, which injects context information into Feature Pyramid Network (FPN) in a residual manner. In particularly, MDCF module consists of a set of parallel Adaptive Deformable Context (ADC) module with special dilated rates and Adaptive Context Fusion (ACF) module. ADC module focus on the objects with exceptional aspect ratios by introducing a deformable paradigm, and ACF module adaptively combines the multi-scale context instead of summation. To verify the effectiveness of the proposed method, we execute some comparative experiments on aerial public datasets NWPU VHR-10 and DIOR, and the mAP increased by 3.5 and 1.0 points compared with the baseline, respectively. The experimental results also show that the proposed method outperforms the state-of-the-art methods. © 2022 Association for Computing Machinery.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Solution-processed,flexible and broadband photodetector based on CsPbBr_(3)/PbSe quantum dot heterostructures

引用

Journal of Materials Science & technology 2021年第9期68卷 216-226页

作者： Jinming Hu Shengyi Yang Zhenheng Zhang Hailong Li Chandrasekar Perumal Veeramalai Muhammad Sulaman Muhammad Imran Saleem Yi Tang Yurong Jiang Libin Tang Bingsuo Zou Beijing Key Laboratory of Nanophotonics and Ultrafine Optoelectronic Systems School of PhysicsBeijing Institute of TechnologyBeijing100081China Key Laboratory of Advanced Optoelectronic Quantum Design and Measurement.Ministry of Education Beijing Institute of Technology.Beijing100081China Kunming Institute of Physics Kunming650223China Beijing Key Laboratory for Precision Optoelectronic Measurement Instrument and Technology School of Optics and PhotonicsBeijing Institute of TechnologyBeijing100081China MOE Key Lab of New Processing Technology for Nonferrous Metals and Materials and Guangxi Key Lab of Processing for Nonferrous Metals and Featured Materials School of Physical Science and TechnologyGuangxi UniversityNanning530004China

Due to their promising applications in foldable displays,optical communication equipment and environmental monitoring systems,flexible and broadband optoelectronic devices have gained extensive attention in recent ***,a flexible and broadband photodetector based on CsPbBr_(3)/PbSe quantum dot(QD) heterostructures is firstly *** integrated QD heterostructures possess consecutive detection range from ultraviolet(UV) to long-wave length infrared(LW-IR) regions with efficient light absorption and chemical stability,in comparison with the pristine PbSe *** material characterizations reveal the improved exciton dissociation,carrier transport and carrier lifetime of the QD *** photodetector Ag/CsPbBr_(3)/PbSe/Ag demonstrate a high responsivity of 7.17 A/W with a specific detectivity of 8.97 × 10^(12) Jones under 25 μW/cm^(2) 365 nm illumination at 5 ***,it could maintain 91.2 %(or 94.9 %) of its initial performance even after bending for thousands of times(or exposing in ambient air for 4 weeks).More importantly,its re s ponse time is shortened more than three orders of magnitude as that of pristine PbSe QDs-based ***,it provides a feasible and promising method for the next-generation high-performance broadband photodetectors via constructing heterostructures of various QDs.

关键词： Quantum dots Broadband detection Flexible photodetectors Fast photoresponse speed Heterostructures

来源：评论

学校读者我要写书评

暂无评论

A dynamic feature weighting method for mangrove pests image classification with heavy-tailed distributions 4

A dynamic feature weighting method for mangrove pests image ...

引用

4th International Conference on Vision, Image and Signal Processing, ICVISP 2020

作者： Wang, Zixu Gong, Weiguo Li, Weihong Key Lab of Optoelectronic Technology and Systems of Education Ministry Chongqing University Chongqing China

ISBN: (纸本)9781450389532

Most of the data in agriculture and forest obey heavy-tailed distribution, in which the data distribution is extremely imbalanced and the amount of most classes is poor. In this paper, we propose a feature centroid based dynamic feature weighting method between head and tail classes for mangrove pest images classification. In the proposed method, firstly, we design a convolutional neural network to extract the clustering centroid as a representation of the subclass. Secondly, we use the centroid feature memory to achieve the dynamic feature weighting through extraction, injection and fusion, which enrich the feature space of the tail classes while retaining identity. Thirdly, to localize the pests in natural background, we optimize the weakly-supervised localization algorithm with a multiscale local maximum index strategy to extract saliency maps. Furthermore, to carry out our research we establish a heavy-tailed distributed image dataset named MIPDGC based on mangrove forest pest. The experimental results prove that the dynamic feature weighting method can obtain higher classification accuracy and better performance than other general methods on the classification accuracy of the MIPDGC. © 2020 ACM.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

Correlation Demodulation for Optical Fiber Fabry-Perot Based on Microwave Photonic and Frequency-Swept Interference

Correlation Demodulation for Optical Fiber Fabry-Perot Based...

引用

Optica Sensing Congress 2023, AIS, FTS, HISE, Sensors, ES 2023 - Part of Optical Sensors and Sensing Congress 2023

作者： Chen, Yuru Lei, Xiaohua Li, Rui Lv, Shaojie Liu, Xianming Zhang, Peng The Key Lab of Optoelectronic Technology & Systems Ministry of Education College of Optoelectronic Engineering Chongqing University Chongqing400044 China

The Fabry-Perot cavity length is demodulated when the sensor interference frequency equals to the microwave frequency. The demodulation method that combines frequency-swept interference with microwave photonic is more... 详细信息

ISBN: (纸本)9781957171241

关键词： Demodulation

来源：评论

学校读者我要写书评

暂无评论

Semantic Segmentation of Large-Scale Point Clouds by Encoder-Decoder Shared MLPs with Weighted Focal Loss 21

Semantic Segmentation of Large-Scale Point Clouds by Encoder...

引用

21st IEEE International Conference on Cognitive Informatics and Cognitive Computing, ICCI*CC 2022

作者： Pan, Jieyun Cao, Kun Zhao, Bingxin Li, Weihong Zhang, Tianyang Chongqing University Key Lab of Optoelectronic Technology and Systems of Education Ministry Chongqing China

ISBN: (纸本)9781665490849

It is essential to do the semantic segmentation task on large-scale outdoor point clouds under the demand of autonomous driving and other applications. Because there is a serious imbalance among different semantic classes, it become a challenging problem. In this paper, we propose a point-based encoder-decoder shared multi-layer perceptrons (MLPs) network with weighted focal loss for semantic segmentation of large-scale point clouds. In the proposed network, we design a residual encoding block which is composed of a relative position encoding block and two neighbor features gathering and combined pooling blocks to aggregate rich neighboring points information. To alleviate the categories imbalance problem, we adopt class-balanced sampler to get the input point cloud block per iteration and use weighted focal loss in the training process. We conducted the experiments on Toronto-3D dataset and the results show that our method achieved an overall accuracy (OA) with 95.70%, a mean intersection over union (mIoU) with 71.85% when input data only contains coordinate information, and an OA with 97.81 %, a mIoU with 81.16% when input data contains both of coordinate and color information. © 2022 IEEE.

关键词： Semantic Segmentation

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：