Complex Model Identification Based on RBF Neural Network

Song, Yibin; Wang, Peijin; Kai-li, LI

doi:10.1007/978-3-540-28648-6_35

Cited by 1 publication

(1 citation statement)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, it is difficult to measure the volume of air goes into the cooling tower, and it can be difficult to obtain satisfactory results. In resent years , RBF(Radial Basis Function) provide a new method for the fitting of non-linearity [1] .Compared with BP neural network, RBF neural network could insure the structure of network topology under the specific questions,conclude the ability of self-learning,self-organizing,adaptive function.The excellent features of the RBF shows more vitality than the BP neural network, it will replace the BP neural network in more and more areas.…”

Section: Introductionmentioning

confidence: 99%

Research on RBF Neural Network of Wet Cooling Tower Under Cross-Wind Conditions

Gong

Wang

et al. 2012

AMM

View full text Add to dashboard Cite

Brief description is given of existing appraising methods for the performance of cooling tower and their shortcoming firstly. Then the mathematics model of cooling tower operation performance is given by means of relative perfect RBF neural network. Comparing with the usual linearity and non-linearity cooling tower mathematics model, the RBF neural networks mathematics can more truly reflect cooling tower operation performance. This conclusion is valuable for giving a more true and simple method for appraising the operation performance of cooling tower. In this text, we consider that cross-wind effect operation efficiency, the complex process of heat and mass transfer between gas and water is easily effected by the air temperature of surroundings,humidity and the influence of cross-wind.

show abstract

Section: Introductionmentioning

confidence: 99%