“…Due to its simplicity and effectiveness, LFFC has been widely applied in many areas, such as robotics [11], linear motors [8,10,13], piezoelectric actuators [14], uninterruptible power supply (UPS) inverters [15], and refrigeration systems [16]. Two different types of neural networks are often used as function approximators, that is, multilayer perceptron (MLP) network and B-spline neural networks (BSN) [1,11,[14][15][16]. It is assumed that in an adaptive or learning control scheme like LFFC, the learning activity always requires a long computation time (mostly in seconds) so that it should not be implemented in the same real-time periodic task, which is employed for feedback control with sampling time typically required in milliseconds.…”