A comprehensive overview of the ADALINE method applied to rapid voltage sags detection in multi-motors drive systems

Mounir Bensaid, Abdellfattah Ba-Razzouk, Mustapha Elharoussi


Several strategies have been developed for identifying power quality issues, monitoring them, and compensating for relevant disturbances. In this field, online estimate of amplitudes and phase angles of network voltages and currents is commonly used. The adaptive linear neuron (ADALINE)-based voltage sag detection algorithm with least mean square (LMS) adaptation allows for rapid convergence of estimate techniques based on artificial neural networks (ANN). This approach has the advantage of being straightforward to implement on hardware and based on simple calculations (essentially multiply and accumulate "MAC"). This paper gives a comparison of the performance of two ADALINE approaches ("with" and "without" error supervision) for detecting and estimating voltage dips. The described techniques and models of a two-coupled motor system were implemented in MATLAB/Simulink/SimPowerSystems to run simulations under various fault scenarios in order to create the three-phase voltage sag alarm signal. The simulation outcomes are presented and debated.


ADALINE; Artificial neural networks; Least mean square; MATLAB; Voltage sags

Full Text:


DOI: https://doi.org/10.11591/eei.v11i6.4141


  • There are currently no refbacks.

Creative Commons License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

Bulletin of EEI Stats