Genetic Algorithm for Observer Parameters Tuning in Sensorless Induction Motor Drive

The paper presents an example of genetic algorithm applied to speed adaptive flux observer parameters tuning in sensorless induction motor drive. The algorithm concerns an optimal gain matrix and PI controller gain coefficients tuning. The gain matrix is implemented in a neural network. Two methods of weights obtaining in the network is proposed. Presented approach selects an optimal operating point of the observer in the presence of measurement noise and inaccurate knowledge of mathematical model parameters.