C206 A METHOD EVALUATING SERVICE LIFE OF STEAM TURBINE ROTOR BASED ON ARTIFICIAL NEURAL NETWORK

概要

論文の詳細を見る
Because of incomplete historical records for the transient operation of steam turbine in power plant, data such as temperature of the steam, inner metal of HP, power output and time interval of a transient process, were not enough to accurately calculate the stress and life-loss of a turbine unit. The general way to evaluate the life-loss of an old turbine unit was to count transient process times under cool and warm as well as hot state to get accumulative total life-loss. Such general evaluation way was rough because of the neglects of the transient details in starting up or shutting down process. It was possible to use online life management system for more accurate evaluation of life loss of a turbine. The paper proposed a new method combining statistics and artificial neural evaluation of life loss of a turbine. The paper proposed a new method combining statistics and artificial neural network based on online lifetime management system, to evaluate past life-loss of the thermal turbine parts. First, the statistics of all previous typical transient operation and the concerned parameters for a year were made to be an operating sample. Second, an artificial neural network was applied to deal with these data, which need not set up accurate math model and carry out mapping between input and output. The life-loss could be output after historical data inputting and artificial neural network training. The new method overcame the constant life-loss caused by transient operation. This method was applied in a 125MW unit and basically satisfied results were achieved.
一般社団法人日本機械学会の論文

C206 A METHOD EVALUATING SERVICE LIFE OF STEAM TURBINE ROTOR BASED ON ARTIFICIAL NEURAL NETWORK

スポンサーリンク

概要

著者

関連論文

スポンサーリンク