Synthesis of optimal control using neural network with mixed structure |
| |
| Affiliation: | 1. Department of Civil and Environmental Engineering, University of California Irvine, 4130 Engineering Gateway, Irvine, CA, 92697-2175, USA;2. Department of Earth System Science, University of California Irvine, Irvine, CA, USA;3. Institute for Biodiversity and Ecosystem Dynamics, University of Amsterdam, Amsterdam, The Netherlands;1. Key Laboratory for Green Chemical Process of Ministry of Education, Hubei Key Laboratory of Novel Reactor and Green Chemical Technology, School of Chemical Engineering and Pharmacy, Wuhan Institute of Technology, Wuhan, 430205, Hubei, PR China;2. School of Health Science and Engineering, Hubei University, Wuhan, 430062, Hubei, PR China;3. Department of Urology, Renmin Hospital of Wuhan University, Wuhan, 430060, Hubei, PR China;4. Hubei Jiangxia Laboratory, Wuhan, 430200, Hubei, PR China;1. MOE Key Laboratory of Marine Genetics and Breeding (Qingdao 266003), and Key Laboratory of Tropical Aquatic Germplasm of Hainan Province of Sanya Oceanographic Institution (Sanya 572024), Ocean University of China, China;2. Laboratory for Marine Fisheries Science and Food Production Processes, and Center for Marine Molecular Biotechnology, Qingdao National Laboratory for Marine Science and Technology, Qingdao, 266237, China;3. Hainan Yazhou Bay Seed Laboratory, Sanya, 572024, China;1. Germplasm Bank of Wild Species, Kunming Institute of Botany, Chinese Academy of Sciences, Kunming, Yunnan, 650201, China;2. Kunming College of Life Science, University of Chinese Academy of Sciences, Kunming, Yunnan, 650201, China;3. Gongshan Bureau of the Gaoligongshan National Nature Reserve, Gongshan, Yunnan, 673500, China |
| |
| Abstract: | This paper proposes firstly to use a neural network with a mixed structure for learning the system dynamics of a nonlinear plant, which consists of multilayer and recurrent structure. Since a neural network with a mixed structure can learn time series, it can learn the dynamics of a plant without knowing the plant order. Secondly, a novel method of synthesizing the optimal control is developed using the proposed neural network. Procedures are as follows: (1) Let a neural network with a mixed structure learn the unknown dynamics of a nonlinear plant with arbitrary order, (2) after the learning is completed, the network is expanded into an equivalent feedforward multilayer network, (3) it is shown that the gradient of a criterion functional to be optimized can be easily obtained from this multilayer network, and then (4) the optimal control is generated by applying any of the existing non-linear programming algorithm based on this gradient information. The proposed method is successfully applied to the optimal control synthesis problem of a nonlinear coupled vibratory plant with a linear quadratic criterion functional. |
| |
| Keywords: | |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
