检索结果-内蒙古大学图书馆

IEEE International Conference on Robotics and automation (ICRA)

作者： Hu Cao Guang Chen Zhijun Li Jianjie Lin Alois Knoll Chair of Robotics Artificial Intelligence and Real-Time Systems Technische Universität München München Germany State Key Laboratory of Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Tongji University Shanghai China University of Science and Technology of China China

This paper proposes an efficient, fully convolutional neural network to generate robotic grasps by using 300×300 depth images as input. Specifically, a residual squeeze-and-excitation network (RSEN) is introduced for deep feature extraction. Following the RSEN block, a multi-scale spatial pyramid module (MSSPM) is developed to obtain multi-scale contextual information. The outputs of each RSEN block and MSSPM are combined as inputs for hierarchical feature fusion. Then, the fused global features are upsampled to perform pixel-wise learning for grasping pose estimation. The experimental results on Cornell and Jacquard grasping datasets indicate that the proposed method has a fast inference speed of 5ms while achieving high grasp detection accuracy of 96.4% and 94.8% on Cornell and Jacquard, respectively, which strikes a balance between accuracy and running speed. Our method also gets a 90% physical grasp success rate with a UR5 robot arm.

关键词： automation Conferences Pose estimation Grasping Manipulators Feature extraction Inference algorithms

来源：评论

学校读者我要写书评

暂无评论

control theoretically explainable application of autoencoder methods to fault detection in nonlinear dynamic systems

arXiv

引用

arXiv 2022年

作者： Li, Linlin Ding, Steven X. Liang, Ketian Chen, Zhiwen Xue, Ting School of Automation and Electrical Engineering University of Science and Technology Beijing Beijing100083 China Institute for Automatic Control and Complex Systems University of Duisburg-Essen Duisburg47057 Germany Key Laboratory of Energy Saving Control and Safety Monitoring for Rail Transportation of Hunan Provincial School of Automation Central South University Changsha410083 China College of Electrical Engineering and Automation Shandong University of Science and Technology Qingdao266590 China

This paper is dedicated to control theoretically explainable application of autoencoders to optimal fault detection in nonlinear dynamic systems. Autoencoder-based learning is a standard machine learning method and widely applied for fault (anomaly) detection and classification. In the context of representation learning, the so-called latent (hidden) variable plays an important role towards an optimal fault detection. In ideal case, the latent variable should be a minimal sufficient statistic. The existing autoencoder-based fault detection schemes are mainly application-oriented, and few efforts have been devoted to optimal autoencoder-based fault detection and explainable applications. The main objective of our work is to establish a framework for learning autoencoder-based optimal fault detection in nonlinear dynamic systems. To this aim, a process model form for dynamic systems is firstly introduced with the aid of control theory, which also leads to a clear system interpretation of the latent variable. The major efforts are made on the development of a control theoretic solution to the optimal fault detection problem, in which an analog concept to minimal sufficient statistic, the so-called lossless information compression, is introduced and proven for dynamic systems and fault detection specifications. In particular, the existence conditions for such a latent variable are derived, based on which a loss function and further a learning algorithm are developed. This learning algorithm enables optimally training of autoencoders to achieve an optimal fault detection in nonlinear dynamic systems. A case study on three-tank system is given at the end of this paper to illustrate the capability of the proposed autoencoder-based fault detection and to explain the essential role of the latent variable in the proposed fault detection system. Copyright © 2022, The Authors. 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

Micro-displacement Amplifying Mechanism of a Piezoelectric Single Crystal Actuator and Its Motion Characterization

Micro-displacement Amplifying Mechanism of a Piezoelectric S...

引用

IEEE International Conference on Mechatronics and automation

作者： Tianlu Zhang Zhangming Du Chao Zhou Zhiqiang Cao Shuo Wang Long Cheng State Key Laboratory of Management and Control for Complex System Institute of Automation Chinese Academy of Sciences University of Chinese Academy of Sciences Beijing China State Key Laboratory of Management and Control for Complex System Institute of Automation Chinese Academy of Sciences Beijing China

ISBN: (数字)9781728164168

ISBN: (纸本)9781728164175

Piezoelectric single crystal actuator is useful in the micro- and nano-scaled. But the range of the operation is limited. The paper presented the amplifying mechanism of the single crystal actuator in order to amplify the output of the piezoelectric actuator in micro- and nano-applications. Due to the single crystal's expansion when the applied signals decrease, the paper developed the adjustable spring that added to the amplifying mechanism. This paper tested the characteristics of the amplifying mechanism by designed a set of experiment device. The input and output displacement of the amplifying mechanism driven by kinds of signals were measured. It can concluded that the amplifying mechanism achieve the positive and negative displacement response and show its accuracy and stable. These excellent properties of the amplifying mechanism amplify the micro-displacement and expand the operating range of single crystal actuator in micro- and nano-positioning applications.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Nonparametric Different-Feature Selection Using Wasserstein Distance

Nonparametric Different-Feature Selection Using Wasserstein ...

引用

International Conference on Tools for Artificial Intelligence (ICTAI)

作者： Wenbo Zheng Fei-Yue Wang Chao Gou State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences School of Intelligent Systems Engineering Sun Yat-sen University

ISBN: (数字)9781728192284

ISBN: (纸本)9781728185361

In this paper, we propose a feature selection method that characterizes the difference between two kinds of probability distributions. The key idea is to view the feature selection problem as a sparsest k-subgraph problem that considers Wasserstein distance between the studied two probability distributions. Our method does not presume any specific parametric models on the data distribution and is non-parametric. It outperforms existing Kullback-Leibler divergence based approaches, since we do not require two distributions to overlap. This relaxation makes our method work in many problems in which Kullback-Leibler divergence based methods fail. We also design a fast calculation algorithm using dynamic programming. Our experimental results show that our method outperforms the current method in both computation accuracy and speed.

关键词： Heuristic algorithms Conferences Tools Feature extraction Probability distribution Dynamic programming Parametric statistics

来源：评论

学校读者我要写书评

暂无评论

Experimental Analysis and Mathematical Model for Quantitative Characterization of Fractures Induced by Hydraulic Fracturing

SSRN

引用

SSRN 2023年

作者： Jia, Li Peng, Shoujian Wu, Bin Xu, Jiang Yan, Fazhi Chen, Yuexia Jiao, Feng State Key Laboratory of Coal Mine Disaster Dynamics and Control Chongqing University Chongqing400030 China State and Local Joint Engineering Laboratory of Methane Drainage in Complex Coal Gas Seam School of Resources and Safety Engineering Chongqing University Chongqing400030 China College of Safety and Emergency Management Engineering Taiyuan University of Technology Shanxi Taiyuan030024 China School of Emergency Technology and Management North China Institute of Science and Technology Beijing101601 China

Hydraulic fracturing (HF) is a widely used reservoir reconstruction technology in unconventional oil and gas development. Quantitative characterization of hydraulic fracturing fracture (HFF) is an important way to explore the mechanism of HFF extension and evaluate the stimulation effect of HF. In this study, based on the development of HF physical simulation experiment and the establishment of mathematical calculation model, the quantitative characterization of fractures induced by HF was systematically explored. The HFF communication area, reservoir reconstruction volume, fractal dimension and other overall fracture geometry parameters were established. The local geometric characterization parameters of HF such as fracture aperture and fracture occurrence were created. To solve the problem that the calculation of the diameter of the central axis ball was tedious and can not completely describe the crack opening, a method to estimate the crack opening using the shape diameter function (SDF) was established, and its systematic error was corrected. The mathematical calculation model of HFF seepage properties was established, which is applicable to any complex planar fracture network and provides a new numerical calculation tool for simulating the flow in the fracture. The characteristics of HFF under different compression and shear loads were compared. With the increase of shear stress level, the complexity of HFF topological structure shows a trend of first increasing and then decreasing. The spatial complexity of HFF increases monotonously with the increase of shear stress level. The flow rate is less affected by the expansion scope and spatial complexity of HFF, and was mainly controlled by the size of fracture initiation area. © 2023, The Authors. All rights reserved.

关键词： Fracture

来源：评论

学校读者我要写书评

暂无评论

Short Term Traffic Flow Forecast Based on CM-GRU Networks

Short Term Traffic Flow Forecast Based on CM-GRU Networks

引用

2019 IEEE International Conference on Service Operations and Logistics, and Informatics, SOLI 2019

作者： Guo, Zhongzheng Zhong, Weifeng Zhu, Fenghua Li, Xiaoshuang Wang, Fei-Yue Xiong, Gang State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China Institute of Automation Harbin University of Science and Technology Harbin China

ISBN: (纸本)9781728128535

Intelligent transportation systems (ITS) have developed for a long time. The rise of deep learning has brought new vitality of the ITS. However, traffic flow data is usually time-correlated and highly randomized. The data distribution will also change dynamically. To actualize the forecasting of traffic flow accurately, we use the historical traffic information to predict the messages of the traffic flow at any time interval. This paper proposes an efficient traffic flow forecast architecture based on deep learning. The method combines the gated recurrent unit (GRU, a type of recurrent neural network) layers and one-dimension convolution layers. Since the performance of these models has a strong dependence on hyper-parameters, this paper conducts a large-scale search of the hyper-parameter space. At the same time, experiments on flow data show that the method proposed in this paper can achieve a better prediction accuracy. Experiments also show lower test errors compared with the existing approaches. © 2019 IEEE.

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

Exploration on the Characteristics of 3d Crack Network Expansion Induced by Hydraulic Fracturing: A Hybrid Approach Combining Experiments and Algorithms

SSRN

引用

SSRN 2023年

作者： Jia, Li Peng, Shoujian Wu, Bin Xu, Jiang Yan, Fazhi Chen, Yuexia State Key Laboratory of Coal Mine Disaster Dynamics and Control Chongqing University Chongqing400030 China State and Local Joint Engineering Laboratory of Methane Drainage in Complex Coal Gas Seam School of Resources and Safety Engineering Chongqing University Chongqing400030 China College of Safety and Emergency Management Engineering Taiyuan University of Technology Shanxi Taiyuan030024 China School of Emergency Technology and Management North China Institute of Science and Technology Beijing101601 China

To realize the efficient development and utilization of unconventional energy, it is very necessary to explore the characteristics of 3D crack network expansion during sandstone hydraulic fracturing (HF). In this paper, through the physical simulation tests of sandstone HF under different shear stress levels, based on the CT image data acquisition, the 3D reconstruction of the HF specimen was realized, and the recognition algorithms of the 3D crack network were established. Based on the crack branch and bipartite graph representation, the graph theory representation method of crack network was improved, that is, the intersection of crack branch and crack branch and the extension of intersection line were used as the precursors of the elements in the two vertex sets U and V of bipartite graph , respectively, so that the topological structure representation method with crack branch as the basic element was extended to 3D crack network. Combined with topology and fractal theory, a quantitative characterization method of crack network was established, which comprehensively considers topological structure parameters and fractal dimension. With the increase of the shear stress level, the fractal dimension of the crack increases linearly, and the parameters of the crack topological structure increase first and then decrease. © 2023, The Authors. All rights reserved.

关键词： Hydraulic fracturing

来源：评论

学校读者我要写书评

暂无评论

Suppressing Stick-Slip Vibration of Drill-String System Subject to Actuator Saturation

Suppressing Stick-Slip Vibration of Drill-String System Subj...

引用

第40届中国控制会议

作者： Zhaoqing He Chengda Lu Min Wu Jun Gao School of Automation China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education CCTEG Xi'an Research Institute

In this paper, the actuator saturation of drill-rig is considered in the mitigation of stick-slip vibration of the drill-string system. Firstly, the dynamic of stick-slip vibration is described by the combination of a multi-degree-of-freedom drill-string model and a bit-rock interaction model. To suppress stick-slip vibration while reducing the effect of saturation on control performance, a dynamic output feedback controller with an anti-windup compensator is introduced. Then, stability analysis of the resulting closed-loop system is carried out. By solving an optimization problem, the gain matrix of the anti-windup compensator is obtained. Finally, a case study is used to show the effectiveness of the method.

关键词： Drill-string system actuator saturation stick-slip vibration anti-windup compensator

来源：评论

学校读者我要写书评

暂无评论

On the 3d Fluid Behavior During Cbm Coproduction in a Multi Pressure System: Insights from Experimental Analysis and Mathematical Models

SSRN

引用

SSRN 2023年

作者： Dai, Shijie Xu, Jiang Jia, Li Chen, Jieren Yan, Fazhi Chen, Yuexia Peng, Shoujian State Key Laboratory of Coal Mine Disaster Dynamics and Control Chongqing University Chongqing400030 China State and Local Joint Engineering Laboratory of Methane Drainage in Complex Coal Gas Seam School of Resources and Safety Engineering Chongqing University Chongqing400030 China College of Safety and Emergency Management Engineering Taiyuan University of Technology Shanxi Taiyuan030024 China School of Emergency Technology and Management North China Institute of Science and Technology Beijing101601 China

To investigate the dynamic response characteristics of coalbed methane (CBM) reservoirs with multi pressure system induced by coproduction, physical simulation experiments were conducted on CBM coproduction under both conventional and constant-rate coproduction modes using a self-built experimental platform. The results showed that constant-rate coproduction can significantly extend the stable coproduction period of CBM compared to conventional coproduction, but it may have an inhibitory effect on certain reservoirs, which is negatively correlated with the initial reservoir pressure. Constant-rate coproduction can cause disturbance effects on reservoir pressure, leading to an increase in the expansion resistance of the pressure-reduction funnel during coproduction, and even the appearance of the pressure-buildup funnel of low-pressure reservoirs. A calculation principle for the 3D fluid flow parameters was developed by considering the dynamic permeability and the pressure gradient of the reservoir. The 3D fluid flow parameters were employed to quantitatively characterize the spatial and temporal evolution of fluid relative flow velocity and deflection angle in the reservoir during coproduction. Near the far end of the wellbore, the fluid flowed nearly horizontally, while near the wellbore, the fluid flowed towards or away from the wellbore center due to different levels of disturbance. © 2023, The Authors. All rights reserved.

关键词： Coal bed methane

来源：评论

学校读者我要写书评

暂无评论

Sliding Mode control for Flexible-link Manipulators Based on Adaptive Neural Networks

引用

International Journal of automation and computing 2018年第2期15卷 239-248页

作者： Hong-Jun Yang Min Tan State Key Laboratory of Management and Control for Complex Systems Institute of AutomationChinese Academy of Sciences

This paper mainly focuses on designing a sliding mode boundary controller for a single flexible-link manipulator based on adaptive radial basis function （RBF） neural network. The flexible manipulator in this paper is considered to be an Euler-Bernoulli beam. We first obtain a partial differential equation （PDE） model of single-link flexible manipulator by using Hamiltons approach. To improve the control robustness, the system uncertainties including modeling uncertainties and external disturbances are compensated by an adaptive neural approximator. Then, a sliding mode control method is designed to drive the joint to a desired position and rapidly suppress vibration on the beam. The stability of the closed-loop system is validated by using Lyapunov＇s method based on infinite dimensional model, avoiding problems such as control spillovers caused by traditional finite dimensional truncated models. This novel controller only requires measuring the boundary information, which facilitates implementation in engineering practice. Favorable performance of the closed-loop system is demonstrated by numerical simulations.

关键词： Sliding mode control adaptive control neural network flexible manipulator partial differential equation （PDE）.

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：