| Autor: |
Chamay, Mónica, Oh, Se-do, Kim, Young-Jin |
| Předmět: |
|
| Zdroj: |
Journal of Mechanical Science & Technology; Sep2014, Vol. 28 Issue 9, p3529-3536, 8p |
| Abstrakt: |
Diverse techniques have been developed for dimension reduction, especially to facilitate the implementation of artificial neural networks (ANNs). For ANNs, the training process can become very complex and demand a great deal of hardware resources, making prior dimension reduction very important; accordingly, this research proposes a new algorithm to increase the degree of dimension reduction. A new procedure is applied to extract important and meaningful non-parametric characteristics from the data. The data in this research was obtained from accelerometers installed in a wind power machine and processed using a linear predictive coefficient/cepstrum coefficients procedure. The procedure consists of the extraction of linear predictive coefficients from the signal data, and subsequent extraction of six features from those coefficients, thereby reducing the amount of data to process and enabling the processing of that information using neural networks. The features employed were selected carefully based on the error obtained from a neural network implementation. The results of this implementation reveal to reduce the data shown to reduce the data to only six input variables for the ANN, thereby enabling the ANN to achieve a very low rate of classification error and training time consuming. [ABSTRACT FROM AUTHOR] |
| Databáze: |
Complementary Index |
| Externí odkaz: |
|
Full text from SpringerLink