Fuel cost forecast of E-class gas generator set
LEI Tiping
CHEN Xikang
CAO Shuanglu
LIU Wei
ZI Pingyang
FAN Rong
ZHANG Kun
Abstract：Using design parameters,correction curve and historical data,the influence of natural gas calorific value,ambient temperature,ambient humidity and generation load fluctuation on the power generation fuel cost of the unit was analyzed,and the power generation cost prediction model of E-class gas generating unit was established,and the multi-layer neural network algorithm was adopted to make iterative correction by using historical data.The results show that the calorific value and generating load of natural gas are negatively correlated with the fuel cost of generating unit,and the environmental temperature and humidity are positively correlated with the cost of generating unit,and the environmental humidity has the least influence on the fuel cost of generating unit.It is proved that the error of power consumption predicted by the modified model is less than 6%,which meets the application demand.
Keywords：gas generatorfuel costneural networkprediction model
Publication Date：2025-03-25
Online Publishing Date：2025-08-15(First online date of this platform, not the publication date of the document)
Pages：3( 31-33 )