检索结果-南通市图书馆

Generalized gradient projection neural networks for nonsmooth optimization problems

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(Information Sciences) 2010年第5期53卷 990-1005页

作者： LI GuoCheng 1 , SONG ShiJi 2 ? & WU Cheng 2 1 department of Mathematics, beijing Information Science and Technology university, beijing 100192, china 2 department of automation, tsinghua university, beijing 100084, china 1. department of Mathematics Beijing Information Science and Technology University Beijing 100192 China2. Department of Automation Tsinghua University Beijing 100084 China

Generalized gradient projection neural network models are proposed to solve nonsmooth convex and nonconvex nonlinear programming problems over a closed convex subset of R n . By using Clarke’s generalized gradient, the neural network modeled by a differential inclusion is developed, and its dynamical behavior and optimization capabilities both for convex and nonconvex problems are rigorously analyzed in the framework of nonsmooth analysis and the differential inclusion theory. First for nonconvex optimization problems, the quasi convergence results similar to those achieved by previous work are proved. For convex optimization problems, the global convergence results are proved, i.e. any trajectory of the neural network converges to an asymptotically stable equilibrium point, which is an optimal solution of the primal problem whenever it exists. This result remains valid even if the initial condition is chosen outside the feasible set. In addition, an asymptotic control result involving a Tykhonov like regularization shows that any trajectory of the revised neural network can be forced to converge toward a particular optimal solution of the primal problem. Finally, two simulation optimization algorithms for solving the optimization and control problems are designed respectively, and three typical simulation experiments are illustrated to present the accuracy and efficiency of theoretical convergence results of this paper.

关键词： nonsmooth optimization problem generalized gradient projection networks differential inclu sions convergence

Fault prediction model based on evidential reasoning approach

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(Information Sciences) 2010年第10期53卷 2032-2046页

作者： SI XiaoSheng 1,2 , HU ChangHua 1 & ZHOU ZhiJie 1,2 1 Unit 302, Xi’an Institute of Hi-Tech, Shaanxi, Xi’an 710025, china 2 department of automation, tsinghua university, beijing 100084, china 1. Unit 302 Xi’an Institute of Hi-Tech Shaanxi Xi’an 710025 China2. Department of Automation Tsinghua University Beijing 100084 China

In order to deal with fault prediction problems that involve both quantitative and qualitative in-formation for nonlinear complex system, a new fault prediction model is established based on the evidential reasoning (ER) approach, and an optimal learning algorithm for training ER-based prediction model is pre-sented based on the mean square error (MSE) criterion. This prediction model inherits the advantages of ER approach, which can deal with precise data, incomplete data and fuzzy data with nonlinear characteristic. In this model, the input signals transformed using rule based information transformation technique, are aggregated by analytical ER approach, and then the outputs of prediction model are constructed according to the types of system outputs. In addition, two fault decision criteria are defined to conduct fault identification. To overcome the difficulty in determining model parameters accurately and subjectively, a nonlinear optimization model is constructed and the optimal parameters are obtained. Two experimental studies are conducted to evaluate the performance of the proposed model. The results show that the established prediction model and the presented parameters optimization methods can deal with fault prediction problem effectively.

关键词： fault prediction evidential reasoning belief distribution nonlinear optimization

Study on an intelligent fault-tolerant technique for multiple satellite configured navigation under highly dynamic conditions

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(Information Sciences) 2011年第3期54卷 529-541页

作者： WANG ShiCheng 1 , ZHAO Xin 1 , MIN HaiBo 1 , LIU ZhiGuo 1 & SI XiaoSheng 2 1 High-Tech Institute of Xi’an, Xi’an 710025, china 2 department of automation, tsinghua university, beijing 100084, china 1. High-Tech Institute of Xi’an Xi’an 710025 China2. Department of Automation Tsinghua University Beijing 100084 China

The probability of pseudo-range information being faulty will increase when there is increased noise in the receiver due to highly dynamic conditions. In this paper, an intelligent fault-tolerant federated Kalman filter (IFFKF) is presented to solve the problem of invalid position information as a result of the uncertainty in the category and quantity of failed satellites in a multiple configured satellite system. At the same time, a corresponding intelligent fault-tolerant system structure based on a cell-level fusion mode of operation was designed. Furthermore, a fault diagnosis strategy is proposed to deal with gradually or suddenly changing faults. By monitoring the residual and the residual rate, an observation quality gene is obtained using a fuzzy logic control system, and the local filter is adaptively adjusted on-line. Consequently, any filtering divergence arising from a gradually changing fault can, to a large extent, be prevented. The results show that the proposed algorithm and structure can achieve reliable positioning by fully utilizing new multiple satellites, monitoring and managing the gradual fault, as well as detecting and isolating any sudden fault in a synchronous manner. As such, the proposed algorithm has the potential to improve the reliability of a multiple satellite configured navigation system.

关键词： multiple satellite configured systems fuzzy logic control intelligent fault-tolerant filtering federated filtering fault detection and isolation

Real-time reliability prediction for dynamic systems with both deteriorating and unreliable components

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 in china(Series F) 2009年第11期52卷 2234-2246页

作者： XU ZhengGuo1,2, JI YinDong2,3 & ZHOU DongHua1,2? 1 department of automation, tsinghua university, beijing 100084, china 2 tsinghua National Laboratory for Information Science and Technology, tsinghua university, beijing 100084, china 3 Research Institute of Information Technology (RIIT), tsinghua university, beijing 100084, china department of automation Tsinghua University Beijing 100084 China tsinghua National Laboratory for Information Science and Technology Tsinghua University Beijing 100084 China Research Institute of Information Technology (RIIT) Tsinghua University Beijing 100084 China

As an important technology for predictive maintenance, failure prognosis has attracted more and more attentions in recent years. Real-time reliability prediction is one effective solution to failure prognosis. Considering a dynamic system that is composed of normal, deteriorating and unreliable components, this paper proposes an integrated approach to perform real-time reliability prediction for such a class of systems. For a deteriorating component, the degradation is modeled by a time-varying fault process which is a linear or approximately linear function of time. The behavior of an unreliable component is described by a random variable which has two possible values corresponding to the operating and malfunction conditions of this component. The whole proposed approach contains three algorithms. A modified interacting multiple model particle filter is adopted to estimate the dynamic system＇s state variables and the unmeasurable time-varying fault. An exponential smoothing algorithm named the Holt＇s method is used to predict the fault process. In the end, the system＇s reliability is predicted in real time by use of the Monte Carlo strategy. The proposed approach can effectively predict the impending failure of a dynamic system, which is verified by computer simulations based on a three-vessel water tank system.

关键词： reliability failure prognostics dynamic systems fault prediction particle filtering interacting multiple model exponential smoothing,predictive maintenance

在线全文

学校读者我要写书评

暂无评论

时延Hopfield神经网络稳定性分析

系统工程与电子技术 2003年第3期25卷 323-325页

作者：张帆慕春棣曹喜滨邹经湘清华大学计算机科学与技术系北京100084 清华大学自动化系北京100084 哈尔滨工业大学航天工程与力学系黑龙江哈尔滨150001

根据李亚普诺夫稳定函数建立了时延神经网络渐近稳定性判据的充分条件。给出了其详细的证明及其3个推论。该判据实用性很强,不仅适用于对称和不对称的关联矩阵,而且适用于零增益的激励函数。通过两个例子表明这个判据比已有的一些判据... 详细信息

根据李亚普诺夫稳定函数建立了时延神经网络渐近稳定性判据的充分条件。给出了其详细的证明及其3个推论。该判据实用性很强,不仅适用于对称和不对称的关联矩阵,而且适用于零增益的激励函数。通过两个例子表明这个判据比已有的一些判据更积极,更具有实用性。

关键词： Hopfield神经网络渐近稳定时延神经网络稳定性李亚普诺夫函数

Controller Study of DES Petri Net with Uncontrollable Transition

在线全文

学校读者我要写书评

暂无评论

Controller Study of DES Petri Net with Uncontrollable Transi...

核动力装置蒸汽发生器水位的分层模糊自适应控制

2009中国控制与决策会议

作者： Tao Ze~(1,2),Zhang Hua~1 1.School of Mechanical Engineering,Shenyang Ligong university,Shenyang 110168,china 2.department of automation,tsinghua university,beijing 100084,china

＜正＞A detailed analysis of supervisory control with place and transition hybrid constraints for Petri net based discrete event system with uncontrollable transitions,and a new method for constructing a Petri net feedback controller based on part design and Petri net reduction technique is *** are classified into admissible and inadmissible ***-Transformation method is proposed to transform the inadmissible constraint into admissible one to construct the *** method eases the design of controller and holds remarkable advantages especially for systems with large scale,because it only considers local incident matrix related to the place and transition constraints and uncontrollable ***,the method is proved to be simple and efficient through some examples.

关键词： Petri net controller structural conflict admissible constraint uncontrollable transition

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

控制与决策 2002年第6期17卷 933-936页

作者：滕树杰张乃尧崔震华清华大学自动化系北京100084 清华大学工程物理系北京100084

针对压水堆核动力装置蒸汽发生器的水位控制提出一种分层模糊自适应控制方案。该方案中 2个模糊控制器分层连接 ,每个模糊控制器均采用典型模糊控制单元 ,使得模糊规则个数和可调参数个数大大减少 ,便于在线学习和实时控制。给出了分层... 详细信息

针对压水堆核动力装置蒸汽发生器的水位控制提出一种分层模糊自适应控制方案。该方案中 2个模糊控制器分层连接 ,每个模糊控制器均采用典型模糊控制单元 ,使得模糊规则个数和可调参数个数大大减少 ,便于在线学习和实时控制。给出了分层模糊控制器的解析表达式及可调参数的在线学习方法。在快速加负荷和突然甩负荷的仿真实验中 ,该方案的控制效果明显优于已有的变参数 PID控制 ,验证了该方案的有效性。

关键词：核动力装置蒸汽发生器水位分层模糊自适应控制核电站

在线全文

学校读者我要写书评

暂无评论

一种基于模糊运算的多目标多传感器跟踪算法

系统工程与电子技术 2004年第11期26卷 1573-1577页

作者：唐亮谢维信黄建军黄敬雄清华大学自动化系北京100084 深圳大学信息工程学院广东深圳518060

为在测量误差较大的情况下实现多传感器多目标跟踪,提出了一种基于模糊运算的融合算法。系统由多类型传感器组成,单个传感器测量范围小,测量误差大,并且数据传输时延大。利用非单值模糊逻辑系统计算数据模糊关联,采用参数曲线最小二乘... 详细信息

为在测量误差较大的情况下实现多传感器多目标跟踪,提出了一种基于模糊运算的融合算法。系统由多类型传感器组成,单个传感器测量范围小,测量误差大,并且数据传输时延大。利用非单值模糊逻辑系统计算数据模糊关联,采用参数曲线最小二乘跟踪法拟合目标运动轨迹,实现了一种在多种传感器并存的模糊传感器阵列中,集中式点迹序贯融合的方法。给出了实现该方法的具体步骤,实验证明该方法是行之有效的。

关键词：多传感器模糊运算模糊传感器模糊逻辑系统融合算法跟踪算法单值时延多目标跟踪序贯

基于强跟踪滤波器的液压伺服系统实时故障诊断

在线全文

学校读者我要写书评

暂无评论

系统仿真学报 2009年第23期21卷 7553-7556页

作者：胡文金周东华重庆科技学院电子信息工程学院重庆401331 清华大学自动化系北京100084

为了在线监测运行工况和提高其可靠性,研究了液压伺服系统的实时故障诊断模型和方法。使用强跟踪滤波器联合估计系统的状态和未知时变参数,使用修正的贝叶斯算法检测故障和估计出故障的幅值,从而建立故障诊断模型和实现液压伺服系统的... 详细信息

为了在线监测运行工况和提高其可靠性,研究了液压伺服系统的实时故障诊断模型和方法。使用强跟踪滤波器联合估计系统的状态和未知时变参数,使用修正的贝叶斯算法检测故障和估计出故障的幅值,从而建立故障诊断模型和实现液压伺服系统的实时故障诊断。仿真结果证实了模型的合理性和可行性,参数估计误差小于1.2%。该方法对模型参数的不确定性具有较强的鲁棒性,能正确检测和分离液压伺服系统的故障。

关键词：液压伺服系统故障诊断强跟踪滤波器参数估计