Artificial neural networks for real-time estimation of basic waveforms of voltages and currents

New parallel algorithms for estimation of parameters of sinewaves contaminated by noise are proposed. The problem of estimation is formulated as an optimization problem and solved by using the gradient descent method. Algorithms based on the least absolute value, the least-squares and the minimax (Chebyshev) criteria are developed and compared. The implementation of the algorithms by an appropriate neural network is also given. Illustrative computer simulation results confirm validity and high performance of the proposed solution