Fuzzy Adaptive Control for Pure-feedback System via Time Scale Separation

Daoxiang Gao,Zengqi Sun,Bin Xu 제어·로봇·시스템학회 2013 International Journal of Control, Automation, and Vol.11 No.1

A fuzzy adaptive control method is proposed for a class of completely non-affine pure-feedback nonlinear systems. By the combination of back-stepping control method and time scale separation, the virtual/actual control inputs are derived from the solutions of a series of fast dynamical equations. This strategy avoids the drawback of “explosion of complexity’’ inherently existing in the conventional back-stepping design for the pure-feedback system as the dynamic surface control (DSC) method does for the strict-feedback nonlinear system. By using mean value theorem, error system dynamic is obtained for each subsystem. Thus, Lyapunov theory can be employed for the stability analysis. It shows that the developed fuzzy adaptive control scheme achieves semi-global uniform ultimate boundedness of all the signals in the closed loop. Simulation results are presented to show the effectiveness of the approach.

Intelligent Scheduling Control of Networked Control Systems with Networked-induced Delay and Packet Dropout

Hongbo Li,Zengqi Sun,Badong Chen,Huaping Liu,Fuchun Sun 대한전기학회 2008 International Journal of Control, Automation, and Vol.6 No.6

Networked control systems (NCSs) have gained increasing attention in recent years due to their advantages and potential applications. The network Quality-of-Service (QoS) in NCSs always fluctuates due to changes of the traffic load and available network resources. To handle the network QoS variations problem, this paper presents an intelligent scheduling control method for NCSs, where the sampling period and the control parameters are simultaneously scheduled to compensate the effect of QoS variation on NCSs performance. For NCSs with network-induced delays and packet dropouts, a discrete-time switch model is proposed. By defining a sampling-period-dependent Lyapunov function and a common quadratic Lyapunov function, the stability conditions are derived for NCSs in terms of linear matrix inequalities (LMIs). Based on the obtained stability conditions, the corresponding controller design problem is solved and the performance optimization problem is also investigated. Simulation results are given to demonstrate the effectiveness of the proposed approaches.

Appearance-based Robot Visual Servo via a Wavelet Neural Network

Qingjie Zhao,Zengqi Sun,Fuchun Sun,Jihong Zhu 대한전기학회 2008 International Journal of Control, Automation, and Vol.6 No.4

This paper proposes a robot visual servo approach based on image appearance and a wavelet function neural network. The inputs of the wavelet neural network are changes of image features or the elements of image appearance vector, and the outputs are changes of robot joint angles. Image appearance vector is calculated by using eigen subspace transform algorithm. The proposed approach does not need a priori knowledge of the robot kinematics, hand-eye geometry and camera models. The experiment results on a real robot system show that the proposed method is practical and simple.

A New Approach to Fuzzy Modeling and Control for Nonlinear Dynamic Systems: Neuro-Fuzzy Dynamic Characteristic Modeling and Adaptive Control Mechanism

Xiong Luo,Zengqi Sun,Fuchun Sun 제어·로봇·시스템학회 2009 International Journal of Control, Automation, and Vol.7 No.1

The study on nonlinear control system has received great interest from the international research field of automatic engineering. There are currently some alternative and complementary methods used to predict the behavior of nonlinear systems and design nonlinear control systems. Among them, characteristic modeling (CM) and fuzzy dynamic modeling are two effective methods. However, there are also some deficiencies in dealing with complex nonlinear system. In order to overcome the deficiencies, a novel intelligent modeling method is proposed by combining fuzzy dynamic modeling and characteristic modeling methods. Meanwhile, the proposed method also introduces the low-level learning power of neural network into the fuzzy logic system to implement parameters identification. This novel method is called neuro-fuzzy dynamic characteristic modeling (NFDCM). The neuro-fuzzy dynamic characteristic model based overall fuzzy control law is also discussed. Meanwhile the local adaptive controller is designed through the golden section adaptive control law and feedforward control law. In addition, the stability condition for the proposed closed-loop control system is briefly analyzed. The proposed approach has been shown to be effective via an example.

Flow Based Clustering Algorithm for Tourism Search Engine

Liu Jie,Du Junping,Sun Zengqi,Jia Yingming 제어로봇시스템학회 2010 제어로봇시스템학회 국제학술대회 논문집 Vol.2010 No.10

This paper introduces a flow based clustering algorithm for tourism search engine. Unlike the general tourism search engines such as www.tripadvisor.com, www.qunar.com and www.kayak.com etc. to return the users’" queries huge amount of web page links, this algorithm helps the tourism search engine create a list of words which serve as suggestions to expand and update the users’" queries. It is much different from the previous clustering algorithms which cluster the results by the similar subjects. This algorithm clusters the search results by the inside vector distance representing each relationship between the web pages. In this manner, these representatives belong to different clusters merging into something like different flows. The experimental results indicate that the algorithm performs an unexpected usefulness for the users’" queries. Meanwhile, through the comparison with some often used algorithms and an online survey, it shows this algorithm has an accepted performance.

Study on Food Safety Emergencies Knowledge Acquisition and Representation on Ontology

Yang Yuehua,Du Junping,Sun Zengqi,Jia Yingmin 제어로봇시스템학회 2011 제어로봇시스템학회 국제학술대회 논문집 Vol.2011 No.10

Study knowledge acquisition of food safety emergencies based on ontology, and use this method to acquire classes, properties, relations and axioms of food safety emergencies field; Study knowledge representation based on ontology, and on this basis construct a shared, reusable, extensible food safety emergencies domain ontology, and describe it in OWL form, hence form a set of relatively complete food safety emergencies knowledge acquisition and knowledge representation system, as is applied to the establishment of a food safety emergency knowledge base ,it can greatly improve the efficiency of knowledge search and knowledge reasoning.

Adaptive Filtering under Minimum Information Divergence Criterion

Badong Chen,Yu Zhu,Jinchun Hu,Zengqi Sun 제어·로봇·시스템학회 2009 International Journal of Control, Automation, and Vol.7 No.2

Traditional filtering theory is always based on optimization of the expected value of a suitably chosen function of error, such as the minimum mean-square error (MMSE) criterion, the minimum error entropy (MEE) criterion, and so on. None of those criteria could capture all the probabilistic in-formation about the error distribution. In this work, we propose a novel approach to shape the probabil-ity density function (PDF) of the errors in adaptive filtering. As the PDF contains all the probabilistic information, the proposed approach can be used to obtain the desired variance or entropy, and is ex-pected to be useful in the complex signal processing and learning systems. In our method, the informa-tion divergence between the actual errors and the desired errors is chosen as the cost function, which is estimated by kernel approach. Some important properties of the estimated divergence are presented. Also, for the finite impulse response (FIR) filter, a stochastic gradient algorithm is derived. Finally, simulation examples illustrate the effectiveness of this algorithm in adaptive system training.

Study on Feature Dimension Reduction Method of Emergency Topic Model Based on Improved CHI and LSA

Liang Meiyu,Du Junping,Jia Yingmin,Sun Zengqi 제어로봇시스템학회 2011 제어로봇시스템학회 국제학술대회 논문집 Vol.2011 No.10

According to some flaws in the existing feature dimension reduction methods, a new method of two-step combined feature dimension reduction based on improved CHI algorithm and LSA algorithm is proposed in this paper. First, apply the improved CHI algorithm to realize the initial feature selection, resolve the problem of high dimension and sparseness in the feature space to a certain extent, and then use the LSA algorithm to extract the semantic structures in the initial feature space, and map it into the semantic feature space and realize the second dimension reduction. Experimental results indicate that this method of feature dimension reduction has a better performance, further improving the effect of topic tracking.

Study on SNS Graph Generation and Prediction

Yang Yuehua,Du Junping,Jia Yingmin,Sun Zengqi 제어로봇시스템학회 2010 제어로봇시스템학회 국제학술대회 논문집 Vol.2010 No.10

As the users of social network sites increases, the types of applications service social network sites provide are becoming more and more. This paper establishes an SNS graph generation model based on social services provided by kaixin.com, which describes the intrinsic relationship of entities (users, groups, applications, posts, and albums) in the site; extracts some rules according to the relationship of entities and applies these rules to the SNS graph generation, so the SNS graph can be updated dynamically with the selected social network site;Finally proposes an algorithm used to predict which applications may obtain more users in the future roughly based on SNS graph and according to the prediction results the social network site can adjust its website structure thereby absorbing more users.

Image Semantic Description and Automatic Semantic Annotation

Liang Meiyu,Du Junping,Jia Yingmin,Sun Zengqi 제어로봇시스템학회 2010 제어로봇시스템학회 국제학술대회 논문집 Vol.2010 No.10

Making the semantic description and automatic semantic annotation of the image which contains rich contents and intuitive expression is a research subject that is challenging. It is a key technology of realizing fast and effective image retrieval and a research focusing on cross media mining. Also it has great application value in various kinds of fields. This paper studies and discusses image media semantic description and automatic semantic annotation. By extracting SIFT visual features, we make the description of the image semantic, then establish the association between local image visual features and semantic keywords, and finally realize the image to the text feature mapping and the automatic semantic annotation. The simulation experiment result shows that this method can accomplish the image automatic semantic annotation efficiently, and also it can reach a higher accuracy.