Design of an Auto-associative Neural Network by Using Design of Experiments Approach
| Autor: | Nenad Muškinja, Božidar Bratina, Boris Tovornik |
|---|---|
| Rok vydání: | 2008 |
| Předmět: |
Artificial neural network
business.industry Time delay neural network Computer science Design of experiments Computational intelligence Machine learning computer.software_genre Fault detection and isolation Network simulation Probabilistic neural network Robustness (computer science) Artificial intelligence Data mining business computer |
| Zdroj: | Lecture Notes in Computer Science ISBN: 9783540855620 KES (1) |
| DOI: | 10.1007/978-3-540-85563-7_9 |
| Popis: | Data driven computational intelligence methods have become popular in Fault detection and isolation (FDI) due to relatively quick design and not so difficult implementation on real systems. In this paper a research work on a Taguchi DoE approach for training the auto-associative neural network to extract non-linear principal components of a system, is presented. Design of such network was first proposed by Kramer however for achieving robustness to unspecified parameters such as noise level and disturbances, a design of experiments methodology can be used to optimally define network structure and parameters. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|