NEURAL-NETWORK MODELING OF FLUID-POWER CONTROL-SYSTEMS USING INTERNALSTATE VARIABLES

An approach is developed for identifying the behaviour of fluid power control systems using Artificial Neural Networks in conjunction with f requency-rich input excitation. Two different motor speed control syst ems are studied, the first considering the prediction of output torque using a mathematical model to identify the dynamic behaviour followed by predictions of the actual steady-state behaviour, the second consi dering the predictions of the output speed using direct experimental d ata to identify the dynamic behaviour, In both cases comparisons are m ade between the use of multi-sinusoidal and pseudo random binary input signals for network training and validation. A unique feature in both system studies is the use of internal state variables, pressure and f low rate, for network training. The results have implications for on-l ine identification of fluid power dynamic components with potential fo r adaptive control and fault diagnosis applications. Copyright (C) 199 6 Elsevier Science Ltd.