The general trend towards more-intelligent energy-aware ac drives is driving the development of new motor topologies and advanced model-based control techniques. Among the candidates, pure reluctance and anisotropic permanent magnet motors are gaining popularity, despite their complex structure. The availability of accurate mathematical models that describe these motors is essential to the design of any model-based advanced control. This paper focuses on the relations between currents and flux linkages, which are obtained through innovative radial-basis function neural networks. These special drive-oriented neural networks take as inputs the motor voltages and currents, returning as output the motor flux linkages, inclusive of any nonlinearity and cross-coupling effect. The theoretical foundations of the radial basis function networks, the design hints and a commented series of experimental results on a real laboratory prototype are included in the paper. The simple structure of the neural network fits for implementation on standard drives. The online training and tracking will be the next steps in FPGAbased control systems.Index Terms-Permanent magnet motors, reluctance motor, artificial neural networks, magnetic flux linkages.
NOMENCLATURE
Variables names convention:• variable with accent : estimated quantities • bold lowercase variable: vectorial quantities Symbols used:flux linkages τ (t) Electromagnetic torque d,q Voltage estimation errors N g K Number of Gaussian functions b k Proportional coefficient of the first layer d max Diameter of the quadratic training region n k , x k , a k Input, centre in (d, q) reference frame and output of the k th Gaussian functions w d,q k Proportional coefficients of the second layer M Number of steady state training points L. Ortombina, F. Tinazzi and M. Zigliotto are with