Font Size: a A A

Intelligent Decentralized Control Algorithms Of Nonlinear Interconnected Systems Based On Neural Networks

Posted on:2022-03-02Degree:MasterType:Thesis
Country:ChinaCandidate:J D LiuFull Text:PDF
GTID:2518306335971969Subject:Computer application technology
Abstract/Summary:PDF Full Text Request
As we all know,interconnected systems widely exist in practical engineering,and with the progress of society and the development of science and technology,the complexity and interconnection degree of engineering application systems will be increasingly enhanced.Therefore,how to effectively control the increasingly complex interconnected systems has become a very challenging and practical research topic.Furthermore,due to the industrial demand for actual systems,it is often required that the interconnected systems in the actual engineering can achieve asymptotic tracking or finite-time stability.Based on the above considerations,this paper presents the asymptotic tracking intelligent decentralized control algorithm and finite-time tracking intelligent decentralized control algorithm for several kinds of large-scale nonlinear interconnected systems respectively by using neural network(NN)technology on the basis of backstepping method.The main contents are as follows:(1)An intelligent decentralized control algorithm with adaptive asymptotic tracking is developed for a class of large-scale nonlinear systems with unknown strong interconnections,unknown time-varying parameters and disturbances.First,by employing the intrinsic properties of Gaussian functions for the interconnection terms for the first time,all extra signals in the framework of decentralized control are filtered out,thereby removing all additional assumptions imposed on the interconnections,such as having upper bounding functions and satisfying matching conditions.Second,by introducing two integral bounded functions,asymptotic tracking control is realized.Moreover,the nonlinear filters with the compensation terms are introduced to circumvent the issue of “explosion of complexity”.It is shown that all the closed-loop signals are bounded and the tracking errors converge to zero asymptotically.In the end,two simulation example are carried out to demonstrate the effectiveness of the intelligent algorithm.(2)An intelligent decentralized control algorithm with adaptive finite-time tracking is proposed for a class of non-strictly feedback large-scale nonlinear interconnected systems with disturbances.First,a practical almost fast finite-time stability framework is established for a general nonlinear system,which is then applied to the design of the large-scale system under consideration.By fusing command filter technique and adaptive neural control and introducing two smooth functions,the “singular” and “explosion of complex” problems in the backstepping procedure are circumvented,while the design obstacles caused by unknown interconnections are overcome.Moreover,according to the framework of practical almost fast finite-time stability,it is shown that all the closed-loop signals of the large-scale system are almost fast finite-time bounded,and the tracking errors can converge to predefined arbitrarily small residual sets in an almost fast finite time.Finally,a simulation example is presented to demonstrate the effectiveness of the proposed finite-time intelligent decentralized control scheme.The research on intelligent control algorithms of large-scale nonlinear interconnected systems is still in the preliminary exploration stage.In this thesis,only the asymptotic tracking intelligent decentralized control algorithm and the finite-time tracking intelligent decentralized control algorithm for this kind of systems have been studied in depth.At present,there are still many control algorithms that need to be designed for this type of systems,such as the design of event-triggered intelligent decentralized control algorithms for large-scale nonlinear interconnected systems,the design of fast finite-time intelligent decentralized control algorithms for large-scale nonlinear interconnected systems,and the design of predefined finite-time intelligent decentralized control algorithm for large-scale nonlinear interconnected systems,etc.
Keywords/Search Tags:Adaptive intelligent decentralized control algorithms, neural networks (NNs), large-scale nonlinear interconnected systems, finite-time control, asymptotic tracking control
PDF Full Text Request
Related items