Title :
An evolved recurrent neural network and its application in the state estimation of the CSTR system
Author :
Zhang, Chunkai ; Hu, Hong
Author_Institution :
Dept. of Mech. Eng. & Autom., Harbin Inst. of Technol., China
Abstract :
Continuous stirred tank reactor system (CSTR) is a typical chemical reactor system with a complex nonlinear dynamic characteristics. In this paper, a recurrent neural network (RNN) evolved by a cooperative scheme is proposed to estimate the state of the CSTR system, which combines the architectural evolution with weight learning. In this scheme, particle swarm optimization (PSO) adoptively constructs the network architectures, then evolutionary algorithm (EA) is employed to evolve the network nodes with this architecture, and this process is automatically alternated. It can effectively alleviate the noisy fitness evaluation problem and the moving target problem. In addition of these, a closer behavioral link between the parents and their offspring is maintained, which improves the efficiency of evolving RNN. The results show that the proposed scheme is able to evolve both the architecture and weights of RNN, and the effectiveness and efficiency is better than the algorithms of TDRB, GA, PSO, and HGAPSO applied to the fully connected RNN.
Keywords :
chemical reactors; evolutionary computation; learning (artificial intelligence); nonlinear dynamical systems; particle swarm optimisation; recurrent neural nets; state estimation; chemical reactor system; continuous stirred tank reactor system; evolutionary algorithm; moving target problem; network architectures; noisy fitness evaluation problem; nonlinear dynamic characteristics; particle swarm optimization; recurrent neural network; state estimation; weight learning; Chemical reactors; Continuous-stirred tank reactor; Evolutionary computation; Genetic algorithms; Intelligent networks; Mathematical model; Nonlinear dynamical systems; Particle swarm optimization; Recurrent neural networks; State estimation; CSTR system; recurrent neural network; soft computing;
Conference_Titel :
Systems, Man and Cybernetics, 2005 IEEE International Conference on
Print_ISBN :
0-7803-9298-1
DOI :
10.1109/ICSMC.2005.1571465