检索结果-南通市图书馆

Event co-reference resolution via a multi-loss neural network without using argument information

在线全文

学校读者我要写书评

暂无评论

Science China(Information Sciences) 2019年第11期62卷 31-39页

作者： Xinyu ZUO Yubo CHEN Kang LIU Jun ZHAO Institute of automation Chinese Academy of Sciences University of Chinese academy of Sciences

Event co-reference resolution is an important task in natural language processing, and nearly all the existing approaches for this task rely on event argument information. However, these methods tend to suffer from error propagation from event argument extraction. Additionally, not every event mention contains all arguments of an event, and the argument information may confuse the model where events contain arguments to detect an event co-reference in real text. Furthermore, the context information of an event is useful to infer the co-reference between events. Thus, to reduce the errors propagated from event argument extraction and use context information effectively, we propose a multi-loss neural network model that does not require any argument information relating to the within-document event co-reference resolution task; furthermore, it achieves a significantly better performance than the state-of-the-art methods.

关键词： event co-reference resolution neural network information extraction multi-loss function event extraction

Study and development of high peak power short pulse Nd:YAG laser for peening applications

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Science China(Technological Sciences) 2015年第7期58卷 1154-1161页

作者： QIAO HongChao ZHAO JiBin YANG Hao Shenyang Institute of automation Chinese Academy of Sciences

Because short pulse Nd:YAG laser of nanosecond pulse-width and high peak power has a unique capability to improve the mechanical properties of metal parts,a study on the development of high peak power short pulse from Nd:YAG laser along with its peening application has been *** design scheme of laser and the characteristic of laser beam transmission are presented and discussed.A pulse energy of 25 J with 15 ns pulse-width and a maximum peak power of 1660 k W laser system which use one oscillation and eight amplifiers has been *** beam has a max divergence angle of 0.03 mrad,a pulse-to-pulse pulse-width stability of±0.1 ns,and the pulse-to-pulse energy stability factors of less than±2.8%.A low value of divergence means an easier modification of a nearly hat-top laser beam intensity profile and an easier transmission of laser *** evaluate the performance of the laser system,several metal materials are *** peening quality and efficiency are analyzed by using an optical microscope,a transmission electron microscope,and an X-ray diffraction *** processing results show that the performance of this laser system is excellent.

关键词： YAG laser laser beam peak power laser peening

GENERATION METHOD FOR FIVE-AXIS NC SPIRAL TOOL PATH BASED ON PARAMETRIC SURFACE MAPPING

在线全文

学校读者我要写书评

暂无评论

Journal of Systems Science & Complexity 2013年第5期26卷 676-694页

作者： ZHOU Bo ZHAO Jibin LIU Weijun LI Lun Graduate University of the Chinese academy of Sciences Shenyang Institute of Automation Shenyang Institute of automation

A new spiral tool path generation algorithm for 5-axis high speed machining is proposed in this ***,the voltage contours are calculated to satisfy the machining parameters in the mapping parametric domain by means of the electrostatic field model of partial differential ***,the mapping rules are constructed and the machining trajectory is planned out in the standard parametric domain in order to map and generate the spiral trajectory in the corresponding parametric ***,this trajectory is mapped onto the parametric surface for the obtainment of the spiral tool *** spiral tool path can realize the machining of complicated parametric surface and trimmed surface without tool *** above-mentioned algorithm has been implemented in several simulations and validated successfully through the actual machining of a complicated *** results indicate that this method is superior to the existing machining methods to realize the high speed machining of the complicate-shaped cavity based on parametric surface and trimmed surface.

关键词： 5-axis NC machining mapping rule partial differential equations spiral tool path.

Tool path planning based on conformal parameterization for meshes

在线全文

学校读者我要写书评

暂无评论

Chinese Journal of Aeronautics 2015年第5期28卷 1555-1563页

作者： Zhao Jibin Zou Qiang Li Lun Zhou Bo Shenyang Institute of automation Chinese Academy of Sciences University of Chinese academy of Sciences

The similarity property of conformal parameterization makes it able to locally preserve the shapes between a surface and its parameter domain, as opposed to common parameterization methods. A parametric tool path planning method is proposed in this paper through such parameterization of triangular meshes which is furthermore based on the geodesic on meshes. The parameterization has the properties of local similarity and free boundary which are exploited to simplify the formulas for computing path parameters, which play a fundamentally important role in tool path planning, and keep the path boundary-conformed and smooth. Experimental results are given to illustrate the effectiveness of the proposed methods, as well as the error analysis.

关键词： Conformal parameterization Error analysis Local similarity:Tool path Triangular mesh

Multi-feature hierarchical topic models for human behavior recognition

在线全文

学校读者我要写书评

暂无评论

Science China(Information Sciences) 2014年第9期57卷 87-101页

作者： LI HePing ZHANG Feng ZHANG ShuWu Institute of automation Chinese Academy of Sciences

Human behavior recognition is one important task of image processing and surveillance *** main challenge of human behavior recognition is how to effectively model behaviors on condition of unconstrained videos due to tremendous variations from camera motion,background clutter,object appearance and so *** this paper,we propose two novel Multi-Feature Hierarchical Latent Dirichlet Allocation models for human behavior recognition by extending the bag-of-word topic models such as the Latent Dirichlet Allocation model and the Multi-Modal Latent Dirichlet Allocation *** two proposed models with three hierarchies including low-level visual features,feature topics,and behavior topics can effectively fuse two different types of features including motion and static visual features,avoid detecting or tracking the motion objects,and improve the recognition performance even if the features are extracted with a great amount of ***,we adopt the variational EM algorithm to learn the parameters of these *** on the YouTube dataset demonstrate the effectiveness of our proposed models.

关键词： hierarchical Bayesian model behavior analysis human behavior recognition latent Dirichlet allocation multi-feature hierarchical topic model

Nonlinear Longitudinal Attitude Control of an Unmanned Seaplane with Wave Filtering

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

International Journal of automation and computing 2016年第6期13卷 634-642页

作者： Huan Du Guo-Liang Fan Jian-Qiang Yi Institute of automation Chinese Academy of Sciences

A new longitudinal attitude control system design for an unmanned seaplane in the severe sea states is presented in this paper. We develop a nonlinear passive observer, which is used to achieve wave filtering and state estimation. Moreover, the observer can be extended to achieve adaptive wave filtering in varying sea states. Using the estimated low-frequency states, a backstepping sliding mode controller is designed to keep the longitudinal attitude of the unmanned seaplane stable. The stability of the total closed loop system is analyzed by using Lyapunov theory. Simulations are performed in different wave conditions, including Seastate 3 and Seastate 5. The simulations results show that the proposed longitudinal attitude controller can improve the anti-waves capability effectively. Moreover, adaptive wave filter has a significant advantage over a filter with fixed model parameters in varying sea states.

关键词： observer backstepping unmanned sliding attitude longitudinal guaranteed disturbance filtering desired

An Integrated Approach to Hypersonic Entry Attitude Control

在线全文

学校读者我要写书评

暂无评论

International Journal of automation and computing 2014年第1期11卷 39-50页

作者： Zhi-Qiang Pu Ru-Yi Yuan Xiang-Min Tan Jian-Qiang Yi Institute of automation Chinese Academy of Sciences

This paper presents an integrated approach based on dynamic inversion(DI)and active disturbance rejection control(ADRC)to the entry attitude control of a generic hypersonic vehicle(GHV).DI is frstly used to cancel the nonlinearities of the GHV entry model to construct a basic attitude *** enhance the control performance and system robustness to inevitable disturbances,ADRC techniques,including the arranged transient process(ATP),nonlinear feedback(NF),and most importantly the extended state observer(ESO),are integrated with the basic DI *** one primary task,the stability and estimation error of the second-order nonlinear ESO are analyzed from a brand new perspective:the nonlinear ESO is treated as a specifc form of forced Li′enard *** qualitative properties of the Li′enard system are utilized to yield comprehensive theorems on nonlinear ESO solution behaviors,such as the boundedness,convergence,and existence of periodic *** portraits of ESO estimation error dynamics are given to validate our *** last,three groups of simulations,including comparative simulations with modeling errors,Monte Carlo runs with parametric uncertainties,and a six degrees-of-freedom reference entry trajectory tracking are executed,which demonstrate the superiority of the proposed integrated controller over the basic DI controller.

关键词： Hypersonic vehicle attitude control dynamic inversion active disturbance rejection control stability analysis

Finite Time Convergent Wavelet Neural Network Sliding Mode Control Guidance Law with Impact Angle Constraint

在线全文

学校读者我要写书评

暂无评论

International Journal of automation and computing 2015年第6期12卷 588-599页

作者： Qing-Chun Li Wen-Sheng Zhang Gang Han Ying-Hua Zhang Institute of automation Chinese Academy of Sciences

This paper presents a novel guidance law to intercept non-maneuvering targets with impact angle and lateral acceleration command constraints. Firstly, we formulate the impact angle control to track the desired line-of-sight(LOS) angle, which is achieved by selecting the missile s lateral acceleration to enforce the sliding mode on a sliding surface at impact time. Secondly, we use the Lyapunov stability theory to prove the stability and finite time convergence of the proposed nonlinear sliding surface. Thirdly, we introduce the wavelet neural network(WNN) to adaptively update the additional control command and reduce the high-frequency chattering of sliding mode control(SMC). The proposed guidance law, denoted WNNSMC guidance law with impact angle constraint,combines the SMC methodology with WNN to improve the robustness and reduce the chattering of the system. Finally, numerical simulations are performed to demonstrate the validity and effectiveness of the WNNSMC guidance law.

关键词： Guidance law sliding mode control wavelet neural n

Parallel Driving in CPSS:A Unified Approach for Transport automation and Vehicle Intelligence

在线全文

学校读者我要写书评

暂无评论

IEEE/CAA Journal of Automatica Sinica 2017年第4期4卷 577-587页

作者： Fei-Yue Wang Nan-Ning Zheng Dongpu Cao Clara Marina Martinez Li Li Teng Liu IEEE State Key Laboratory of Management and Control for Complex Systems Institute of AutomationChinese Academy of Sciences Research Center for Military Computational Experiments and Parallel Systems Technology National University of Defense Technology Institute of Artificial Intelligence and Robotics Xi’an Jiaotong University Advanced Vehicle Engineering Center Cranfield University Department of automation Tsinghua University State Key Laboratory of Management and Control for Complex Systems Institute of AutomationChinese Academy of Sciences Qingdao Huituo Intelligent Machine Company

The emerging development of connected and automated vehicles imposes a significant challenge on current vehicle control and transportation systems. This paper proposes a novel unified approach, Parallel Driving, a cloud-based cyberphysical-social systems(CPSS) framework aiming at synergizing connected automated driving. This study first introduces the CPSS and ACP-based intelligent machine systems. Then the parallel driving is proposed in the cyber-physical-social space,considering interactions among vehicles, human drivers, and information. Within the framework, parallel testing, parallel learning and parallel reinforcement learning are developed and concisely reviewed. Development on intelligent horizon(iHorizon)and its applications are also presented towards parallel *** proposed parallel driving offers an ample solution for achieving a smooth, safe and efficient cooperation among connected automated vehicles with different levels of automation in future road transportation systems.

关键词： ACP theory connected automated driving cyber-physical-social systems(CPSS) iHorizon parallel driving parallel horizon parallel learning parallel reinforcement learning parallel testing