Backstepping-based adaptive dynamic programming for missile-target guidance systems with state and input constraints

In this paper, a novel backstepping-based adaptive dynamic programming (ADP) method is developed to solve the problem of intercepting a maneuver target in the presence of full-state and input constraints. To address state constraints, a barrier Lyapunov function is introduced to every backstepping procedure. An auxiliary design system is employed to compensate the input constraints. Then, an adaptive backstepping feedforward control strategy is designed, by which the tracking problem for strict-feedback systems can be reduced to an equivalence optimal regulation problem for affine nonlinear systems. Secondly, an adaptive optimal controller is developed by using ADP technique, in which a critic network is constructed to approximate the solution of the associated Hamilton–Jacobi–Bellman (HJB) equation. Therefore, the whole control scheme consists of an adaptive feedforward controller and an optimal feedback controller. By utilizing Lyapunov's direct method, all signals in the closed-loop system are guaranteed to be uniformly ultimately bounded (UUB). Finally, the effectiveness of the proposed strategy is demonstrated by using a simple nonlinear system and a nonlinear two-dimensional missile-target interception system.     

Transmission line circuit models for inhomogeneous optical fiber

The dispersion characteristics of inhomogeneous dielectric waveguides are studied using a transverse transmission line representation. With the techniques of distributed circuit analysis the behavior of graded index optical fiber is explained using network theoretic ideas. Specifically, network models are developed through which insight as to the mechanisms underlying the dispersion characteristics of such structures is gained from a transmission line filter analogy. For the case of circular geometries, new approximations for the radial Bessel functions are presented which again results in a simple transmission line filter.     

Neural network-based sensor fault estimation and active fault-tolerant control for uncertain nonlinear systems

In this work, we developed a novel active fault-tolerant control (FTC) design scheme for a class of nonlinear dynamic systems subjected simultaneously to modelling imperfections, parametric uncertainties and sensor faults. Modelling imperfections and parametric uncertainties are dealt with using an adaptive radial basis function neural network (RBFNN) that estimates the uncertain part of the system dynamics. For sensor fault estimation (FE), a nonlinear observer based on the estimated dynamics is designed. A scheme to estimate sensor faults in real-time using the nonlinear observer and an additional RBFNN is developed. The convergence properties of the RBFNN, used in the fault FE part, are improved by using a sliding surface function. For FTC design, a sliding surface is designed that incorporates the real-time sensor FE. The resulting sliding mode control (SMC) technique-based FTC law uses the estimated dynamics and real-time sensor FE. A double power-reaching law is adopted to design the switching part of the control law to improve the convergence and mitigate the chattering associated with the SMC. The FTC works well in the presence and absence of sensor faults without the requirement for controller reconfiguration. The stability of the proposed active FTC law is proved using the Lyapunov method. The developed scheme is implemented on a nonlinear simulation of an unmanned aerial vehicle (UAV). The results show good performance of the proposed unified FE and the FTC framework.     

Aspect-based sentiment analysis with alternating coattention networks

Aspect-based sentiment analysis aims to predict the sentiment polarities of specific targets in a given text. Recent researches show great interest in modeling the target and context with attention network to obtain more effective feature representation for sentiment classification task. However, the use of an average vector of target for computing the attention score for context is unfair. Besides, the interaction mechanism is simple thus need to be further improved. To solve the above problems, this paper first proposes a coattention mechanism which models both target-level and context-level attention alternatively so as to focus on those key words of targets to learn more effective context representation. On this basis, we implement a Coattention-LSTM network which learns nonlinear representations of context and target simultaneously and can extracts more effective sentiment feature from coattention mechanism. Further, a Coattention-MemNet network which adopts a multiple-hops coattention mechanism is proposed to improve the sentiment classification result. Finally, we propose a new location weighted function which considers the location information to enhance the performance of coattention mechanism. Extensive experiments on two public datasets demonstrate the effectiveness of all proposed methods, and our findings in the experiments provide new insight for future developments of using attention mechanism and deep neural network for aspect-based sentiment analysis.     

Nonlinear process monitoring based on generic reconstruction-based auto-associative neural network

A significant concern with statistical fault diagnosis is the large number of false alarms caused by the smearing effect. Although the reconstruction-based approach effectively solves this problem, most of them only focus on linear rather than nonlinear systems. In the present work, a generic reconstruction-based auto-associative neural network (GRBAANN) is proposed that uses the reconstruction-based approach to isolate simple and complex faults for nonlinear systems. Nevertheless, in GRBAANN, it is challenging to acquire a trivial solution for the reconstruction-based index, which is equivalent to a complex vector fixed-point problem. In this regard, the Steffensen method is employed to deal with this problem with an accelerated iterative process, which is appropriate for both single and multiple variable faults. The variable selection procedure is time-consuming but imperative for reconstruction-based approaches, with no exception to the proposed method. In order to ensure the real-time diagnosis for large-scale systems, the Sequential floating forward selection method with memory is proposed to minimize the computation time of the variable selection procedure. The effectiveness of the proposed GRBAANN scheme is illustrated through a validation example and an industrial example. Comparisons with the state-of-art methods are also presented.     

Decentralized neural identification and control for uncertain nonlinear systems: Application to planar robot

This paper presents a discrete-time decentralized neural identification and control for large-scale uncertain nonlinear systems, which is developed using recurrent high order neural networks (RHONN); the neural network learning algorithm uses an extended Kalman filter (EKF). The discrete-time control law proposed is based on block control and sliding mode techniques. The control algorithm is first simulated, and then implemented in real time for a two degree of freedom (DOF) planar robot.     

Dynamic analysis of memristive neural system with unbounded time-varying delays

Memristive models are currently the dominant technique for neuromorphic VLSI design. Critical dynamics research of memristive systems is very meaningful in both theoretical importance and practical significance. In this paper, by using nonsmooth analysis and control theory, nonlinear dynamics on global asymptotic stability and global exponential stability of memristive neural system with unbounded time-varying delays are explored. The theoretical analysis may yield a deep insight into the electric characteristics of memristor devices.     

A practical propagation path identification scheme for quality-related faults based on nonlinear dynamic latent variable model and partitioned Bayesian network

In this paper, a practical technology or solution of quality-related fault diagnosis is provided for nonlinear and dynamic process. Unlike traditional data-based fault diagnosis methods, the alternative approach is focused more on identifying the propagation path that combines diagnostic information and process knowledge. The new method addresses the quality-related fault detection issue with developed nonlinear dynamic latent variable model for extracting nonlinear latent variables that exhibit dynamic correlations, then the advantage of relative reconstruction based contribution approach is followed to analyze the potential root-cause variables. Meanwhile, a new partitioned Bayesian network methodology is proposed for propagation path identification of quality-related faults. Finally, the whole proposed framework is applied to a real hot strip mill process, where the effectiveness is further demonstrated from real industrial data.     

Distributed control of time-delay interconnected nonlinear systems

This paper addresses the distributed control of delayed interconnected nonlinear systems with time-varying delays in both the local subsystems’ dynamics and the physical interconnections among the subsystems. The Takagi–Sugeno fuzzy model with nonlinear consequent parts (N-TS), which is capable to provide less complex representations than standard T–S fuzzy models, is considered to efficiently deal with this class of complex systems. Then, based on Lyapunov–Krasovskii stability arguments, a synthesis condition is proposed to design a distributed control law such that the origin of the closed-loop interconnected system is locally asymptotically stable together with a guaranteed set of admissible initial conditions for which the validity of the N-TS fuzzy model is ensured. Moreover, a quasi-convex optimization procedure is formulated to enlarge the set of admissible initial conditions. The effectiveness of the proposed synthesis condition is validated in two numerical examples, including an interconnected power network with seven generators.     

Iterative dynamic linearization and identification of a nonlinear learning controller: A data-driven approach

In this article, a nonlinear iterative learning controller (NILC) is developed using an iterative dynamic linearization (IDL) and a parameter iterative learning identification technique. First, the ideal NILC is transformed into a linear parameterized form by using a controller-oriented compact form IDL (controller-CFIDL) technique. Then an iterative learning identification approach is presented for tuning the parameters of the proposed controller using real-time I/O data. For the sake of analysis, a linear data model of the nonlinear plant is obtained by using the system-oriented IDL technology and a corresponding system parameter identification algorithm is developed in iteration domain. The convergence analysis is provided for the dynamically linearized nonlinear and nonaffine discrete-time system. The results are further extended by using a controller-oriented partial form iterative dynamic linearization (controller-PFIDL) method to gain a higher-order NILC utilizing additional control information from previous iterations. Simulations of two examples show the effectiveness of the proposed methods.     

A robust distributed observer design for Lipschitz nonlinear systems with time-varying switching topology

This paper deals with state estimation for a class of Lipschitz nonlinear systems under a time-varying disconnected communication network. A distributed observer consists of some local observers that are connected to each other through a communication network. We consider a situation where a communication network does not remain connected all the time, and the network may be caused by intermittent communication link failure. Moreover, each local observer has access to a local measurement, which may be insufficient to ensure the system’s observability, but the collection of all measurements in the network ensures observability. In this condition, the purpose is to design a distributed observer where the estimated state vectors of all local observers converge to the state vector of the system asymptotically, while local observers exchange estimated state vectors through a communication network and use their local measurements. According to theoretical analysis, a nonlinear and a robust nonlinear distributed observer exist when in addition to the union of all communication topologies being strongly connected during a time interval, the component of each communication graph is also strongly connected during each subinterval. The existence conditions of the distributed observers are derived in terms of a set of linear matrix inequalities (LMIs). Finally, the effectiveness of the presented method is numerically verified using some simulation examples.     

Wavelets transform for nonlinear control of multibody systems

The paper solves using wavelet transform a nonlinear control problem of multibody systems. After, we present a wavelet collocation method to solve a nonlinear time-evolution problem, discrete wavelet transform and the algorithm for interpolation functions and the derivative matrix. We consider a nonlinear quadratic control for an inverted pendulum as a numerical example. The results, using Haar wavelets in algebrization of problem, are accurate compared with those from the literature. The method can be extended for any nonlinear control problem obtaining better results than other procedure for localized phenomena.     

LS-SVM和BP算法在逆模型控制中的对比研究

最小二乘支持向量机（least squares support vector machine,LS—SVM）具有很好的非线形逼近能力和泛化能力,通过研究逆模型存在的条件,提出了基于LS—SVM的逆模型辨识方法。仿真结果表明基于LS—SVM的逆模型辨识方法在处理非线性对象时,辨识精度、辨识速度、泛化能力都要强于BP算法。     

Gain-scheduled PI tracking control on stochastic nonlinear systems with partially known transition probabilities

This paper studies the problem of continuous gain-scheduled PI tracking control on a class of stochastic nonlinear systems subject to partially known jump probabilities and time-varying delays. First, gradient linearization procedure is used to construct model-based linear stochastic systems in the vicinity of selected operating states. Next, based on stochastic Lyapunov stabilization analysis, sufficient conditions for the existence of a PI tracking control are established for each linear model in terms of linear matrix inequalities. Finally, continuous gain-scheduled approach is employed to design continuous nonlinear PI tracking controllers on the entire nonlinear jump system. Simulation example is given to illustrate the effectiveness of the developed design techniques.     

Reliable control for event-triggered singular Markov jump systems with partly unknown transition probabilities and actuator faults

In this paper, the problem of reliable controller design for event-triggered singular Markov jump systems with partly known transition probabilities, nonlinear perturbations and actuator faults is studied. To mitigate the burden of data transmissions over network, two event-triggered schemes with different triggering conditions are introduced. The switch law between the two event-triggered schemes is governed by a random variable with Bernoulli distribution. Taking nonlinear perturbations and actuator faults into account, the resulting closed-loop system is converted into a time-delay singular Markov jump system with partly known transition probabilities. Sufficient conditions of stochastically admissible for the resulting closed-loop system are obtained in terms of a group of linear matrix inequalities. The co-design of desirable reliable controller and weighting matrices of event-triggered schemes is presented. Finally, two numerical examples are given to show the effectiveness of the developed results.     

中国科技创新能力评价与比较

本文利用"欧洲创新记分牌"指标,提出了一种基于BP神经网络的国家创新能力评价方法,对中国的科技创新能力进行了评价与比较。首先建立国家科技创新指数指标体系,然后根据指标体系,设计BP神经网络模型,并给出可行的评价程序。计算结果表明,在总体上,中国科技创新指数远落后于世界发达国家,与参加"欧洲创新记分牌"比较的33个国家相比,排名第22位,仅强于大多数东欧国家。     

基于神经网络的非线性学术评价方法选择研究

针对学术评价中多属性评价方法和组合评价方法众多,从而导致学术评价结果众多,评价公信力下降问题,优选多属性评价方法成为解决问题的较好途径。线性多属性评价相对成熟,非线性多属性评价的选取是首要问题,基于BP人工神经网络,以非线性多属性评价值作为输出,评价指标作为输入,通过训练人工神经网络,可以得到评价指标权重,进而和评价值评价指标的相关系数进行比较,通过检验非线性多属性评价方法的逻辑一致性来进行评价方法的选取。以JCR2017数学期刊为例,分别采用主成分分析、因子分析、TOPSIS进行评价,然后再基于BP人工神经网络模型进行选取。研究结果表明:非线性多属性评价方法的选择问题是学术评价的基础问题;BP人工神经网络可以用来辅助进行非线性评价方法的选取;采用BP人工神经网络辅助选取非线性评价方法必须具备一定的适用条件。     

Command filter-based finite-time adaptive fuzzy control for nonlinear systems with uncertain disturbance

In this paper, a command filter-based adaptive fuzzy controller is constructed for a class of nonlinear systems with uncertain disturbance. By using the error compensation signals and fuzzy logic system, a command filter-based control strategy is presented to make that the tracking error converge to an any small neighborhood of zero and all closed-loop signals are bounded. In the design procedure, fuzzy logic system is employed to estimate unknown package nonlinear functions, which avoids excessive and burdensome computations. The control scheme not only resolves the explosion of complexity problem but also eliminates the filtering error in finite-time. An example has evaluated the validity of the control method.     

Output feedback exponential stabilization of uncertain chained systems

This paper deals with chained form systems with strongly nonlinear disturbances and drift terms. The objective is to design robust nonlinear output feedback laws such that the closed-loop systems are globally exponentially stable. The systematic strategy combines the input-state-scaling technique with the so-called backstepping procedure. A dynamic output feedback controller for general case of uncertain chained system is developed with a filter of observer gain. Furthermore, two special cases are considered which do not use the observer gain filter. In particular, a switching control strategy is employed to get around the smooth stabilization issue (difficulty) associated with nonholonomic systems when the initial state of system is known.