Two-ANN approach to frequency and harmonic evaluation

L. L. Lai, Wai Lok Chan, A. T.P. So

Research output: Journal article publicationConference articleAcademic researchpeer-review

8 Citations (Scopus)


In power electronics study, there are frequently occasions that the frequency of the signal under monitoring is varying significantly during the measurement period. That creates a hugh 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. In this paper, a solution using two Hopfield type Artificial Neural Networks (N-N) is being proposed. 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.
Original languageEnglish
Pages (from-to)245-250
Number of pages6
JournalIEE Conference Publication
Issue number440
Publication statusPublished - 1 Jan 1997
Externally publishedYes
EventProceedings of the 1997 5th International Conference on Artificial Neural Networks - Cambridge, United Kingdom
Duration: 7 Jul 19979 Jul 1997

ASJC Scopus subject areas

  • Electrical and Electronic Engineering


Dive into the research topics of 'Two-ANN approach to frequency and harmonic evaluation'. Together they form a unique fingerprint.

Cite this