Title :
Improved robust minmax estimation algorithm with moving time window
Author :
Xue, Yun-can ; Yang, Qi-Wen ; Qian, Ji-Xin
Author_Institution :
Coll. of Comput. & Inf. Eng., Hohai Univ., Jiangsu, China
Abstract :
The shortcoming of the standard robust minmax estimation algorithm, which cannot track abrupt parameter changes, is discussed. Based on this, an improved robust minmax estimation algorithm with moving time window is presented. Selection criteria are given to select the length of time window. The modified algorithm has good trackability and holds good performance of standard robust minmax estimation. Simulation experiments carried out on the fed-batch process verify its good properties.
Keywords :
batch processing (industrial); chemical industry; fermentation; minimax techniques; parameter estimation; abrupt parameter changes; fed-batch process; fermentation; identification; moving time window; parameter estimation; robust minmax estimation algorithm; simulation experiments; Cybernetics; Linear programming; Machine learning; Minimax techniques; Noise robustness; Parameter estimation; Polynomials; Projection algorithms; State estimation;
Conference_Titel :
Machine Learning and Cybernetics, 2002. Proceedings. 2002 International Conference on
Print_ISBN :
0-7803-7508-4
DOI :
10.1109/ICMLC.2002.1167465
