Dynamic System Identification by Neural Network : A New Fast Learning Method Based on Error Back Propagation
スポンサーリンク
概要
- 論文の詳細を見る
A theoretical formulation of a new fast learning method based on back propagation is presented in this paper. In contrast to the existing back propagation algorithm which is based solely on the modification of connecting weights in between units (i.e., neurons) of different layers of the neural network, the present method calculates the optimum slope of the sigmoid function for each unit together with the variation of the connecting weights. The effectiveness and versatility of the present method is verified by the system identification of (a) linear and (b) nonlinear (Duffing and fluid-type) single degree of freedom mass-spring dynamic models. In all of the three cases, the present method excels in speed and accuracy compared to that of the existing method using a fixed slope sigmoid function.
- 一般社団法人日本機械学会の論文
- 1995-12-15
著者
-
Pal Chinmoy
Nissan Motor Corporation Research Center
-
Kayaba Naoki
Yokohama National University, Dept. of Mechanical Engineering
-
Morishita Shin
Yokohama National University, Dept. of Mechanical Engineering
-
Hagiwara Ichiro
Nissan Motor Corporation, Research Center
-
Kayaba Naoki
Yokohama National University Dept. Of Mechanical Engineering
-
Morishita Shin
Yokohama National University
-
Morishita Shin
Yokohama National University Dept. Of Mechanical Engineering
-
Hagiwara Ichiro
Nissan Motor Co. Ltd.
関連論文
- Dynamic System Identification by Neural Network : A New Fast Learning Method Based on Error Back Propagation
- Dynamic Analysis of Thin-Walled Box Columns Subjected to Axial Crushing Using the Finite-Element Method
- 236 Development of An Overall Mechanical Model For Osteoblast Bone Cells
- Mechanical properties of a cultured osteoblast
- A friction-controllable engine mount using an MR fluid
- Technical Development of Radiated Noise Reduction Using Sensitivity Analysis : Series C : Vibration, Control Engineering, Engineering for Industry
- Development of New Mode-Superposition Technique for Truncating Lower- and/or Higher-Frequency Modes : Application of Eigenmode Sensitivity Analysis for Systems with Repeated Eigenvalues
- A Substructure Method Incorporating Homogenization for Finding Optimum Vehicle Body Panel Topologies
- 420 発電用新型炉に適用する3次元免装置の開発 : 油圧ロッキング抑制装置の高圧力下の作動性と健全性評価(耐震I,OS-2 耐震・免震・制震,総合テーマ「伝統を,未来へ!」)
- Development of Eigenmode and Frequency Response Sensitivity Analysis Methods for Coupled Acoustic-Structural Systems
- Study of Structure Identification Method Using Sensitivity Analysis
- Optimum Analysis for Structural Vibration Character : First Report Proposition of a New Eigen Mode Sensitive Analysis and Comparison between Some Different Methods : Series C : Vibration, Control Engineering, Engineering for Industry
- Development of New Mode-Superposition Technique for Truncating Lower- and/or Higher-Frequency Modes : Application to Eigenmode Sensitivity Analysis
- Eigenfrequency Maximization of Plates by Optimization of Topology Using Homogenization and Mathematical Programming
- Sensitivity Calculation Methods for Conducting Modal Frequency Response Analysis of Coupled Acoustic-Structural Systems