Journal
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
Volume 26, Issue 4, Pages 851-865Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TNNLS.2015.2399020
Keywords
Actor-critic; approximate dynamic programming (ADP); category; optimal control; shunting inhibitory artificial neural network (SIANN)
Categories
Funding
- National Science Foundation [ECCS-1128050]
- Beijing Natural Science Foundation [4143065, 4132078]
- National Natural Science Foundation of China [61304079, 61433004, 61374105, 61120106011]
- China Post-Doctoral Science Foundation [2013M530527]
- Fundamental Research Funds for the Central Universities [FRF-TP-14-119A2]
- Open Research Project through the State Key Laboratory of Management and Control for Complex Systems [20120106]
- Office of Naval Research, Arlington, VA, USA [N00014-13-1-0562]
- Air Force Office of Scientific Research through the European Office of Aerospace Research and Development [13-3055]
- U.S. Army Research Office [W911NF-11-D-0001]
- Ministry of Education, China, through the 111 Project [B08015]
- Direct For Computer & Info Scie & Enginr
- Div Of Information & Intelligent Systems [1208623] Funding Source: National Science Foundation
- Directorate For Engineering
- Div Of Electrical, Commun & Cyber Sys [1405173, 1128050] Funding Source: National Science Foundation
- Directorate For Engineering
- Div Of Electrical, Commun & Cyber Sys [1101401] Funding Source: National Science Foundation
Ask authors/readers for more resources
In industrial process control, there may be multiple performance objectives, depending on salient features of the input-output data. Aiming at this situation, this paper proposes multiple actor-critic structures to obtain the optimal control via input-output data for unknown nonlinear systems. The shunting inhibitory artificial neural network (SIANN) is used to classify the input-output data into one of several categories. Different performance measure functions may be defined for disparate categories. The approximate dynamic programming algorithm, which contains model module, critic network, and action network, is used to establish the optimal control in each category. A recurrent neural network (RNN) model is used to reconstruct the unknown system dynamics using input-output data. NNs are used to approximate the critic and action networks, respectively. It is proven that the model error and the closed unknown system are uniformly ultimately bounded. Simulation results demonstrate the performance of the proposed optimal control scheme for the unknown nonlinear system.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available