Title :
Unknown order process emulation
Author :
Volovici, Daniel ; Breazu, Macarie ; Mihalache, Adrian
Author_Institution :
Dept. of Comput. Sci., Univ. Lucian Blaga of Sibiu, Romania
Abstract :
Approaches the emulation problem using feedforward neural networks of single input single output (SISO) processes, applying a backpropagation method with a higher convergence rate. In this kind of application, difficult problems appear when the system´s order is a priori unknown. A search through the SISO processes space is proposed, aiming to find a favorable neural emulator over the training examples set
Keywords :
backpropagation; linear systems; neurocontrollers; nonlinear control systems; SISO processes; backpropagation method; feedforward neural networks; neural emulator; search method; single input single output processes; unknown order process emulation; Backpropagation; Computer science; Control systems; Emulation; Equations; Feedforward neural networks; Industrial training; Multi-layer neural network; Neural networks; Process control;
Conference_Titel :
Neural Networks, 2001. Proceedings. IJCNN '01. International Joint Conference on
Conference_Location :
Washington, DC
Print_ISBN :
0-7803-7044-9
DOI :
10.1109/IJCNN.2001.939552
