高温構造機器の寿命評価への知的アプローチ(<小特集>劣化・老化とライフサイクル)

概要

論文の詳細を見る
This paper describes some intelligent approaches to the life assessment of high-temperature components of power generation plants. First one of knowledge-based systems (KBSs) for component life assessment (CLA) technologies being developed in Europe is introduced. Next, some analyses of case studies on failure of structural components in power plants using the multilayer neural networks are described. Using selected test data about case studies stored in the structural failure database of the KBS the network is trained : for example, to predict possible failure mechanisms like creep-, overheating-or overstressing-induced failure. The results clearly show that the well-trained neural network predicts possible failure mechanism in unknown case studies very accurately.
日本シミュレーション学会の論文
1996-03-15