| |
AN ADAPTIVE HOPFIELD NEURAL NETWORK FOR FREQUENCY AND HARMONIC DETERMINATION
| [View]
[Download]
|
| Author(s) |
L. L. Lai; W. L. Chan; A.T.P. So |
| Abstract |
In real life, there are frequently occasions that the frequency of the signal under monitoring is varying significantly during the measurement period. That creates a large problem to the conventional approach of spectrum analysis using Fast Fourier Transform. An obvious example is the measurement of the output of a Variable Voltage and Variable Frequency Converter during the motor
acceleration/deceleration stages. Many iterations are required in solving the frequency and harmonic determination using Hopfield neural network. In this paper, a solution using two adaptive Hopfield Artificial Neural Networks (NN) is being proposed. The adaptive feature comes from the slope adjustment which speeds up the convergence of the neural network. One NN is used to calculate the frequency of the signal whereas the other. is used to estimate the magnitudes and phase angles of the spectra. The deceleration profile of Danfoss Variable Speed Drive (VSD) is used as an example to illustrate the usefulness and effectiveness of this approach. |
| Download |
| Filename: | Unnamed file |
| Filesize: | 503.3 KB |
|
| Type |
Members Only |
| Date |
Last modified 2016-02-19 by System |
| |
 |