There has been considerable interest and activity in the area of application of the artificial neural network (ANN) to hydraulic systems. The pattern recognition capabilities of the ANN has led to an early investigation in areas where the neural networks could be trained using signals that were at least statistically similar to those signals which the trained ANN would be exposed during operation. The dynamic and encompassing nature of hydraulic system signals poses more of a challenge to ANN training and implementation than one of only pattern recognition. However, in the past decade, there has been considerable activity and progress in the application of ANN techniques for hydraulic systems control, identification and condition monitoring.This paper provides an overview of work in this area. The ANN has proven to be a valuable addition to the current existing techniques. The learned behavior capability is a definite asset in the control of the nonlinear, complex systems encountered in the fluid power area. Training is a fundamental requirement for the ANN and this is very often accomplished using a simulation model of the system. ANN based controllers have demonstrated superior performance when compared to conventional PID controllers although these controllers are often an integral part of the training regime or in system operation with the ANN playing a supervisory role. In adaptive control, the ANN can be used to replace the plant model where the ability to emulate or mimic a nonlinear system plays a crucial role. As well, the control algorithm can utilize ANN capability. Fuzzy based controllers also have an approximate reasoning or intelligence capability based on a qualitative description of their dependencies. ANN techniques have been successfully employed in a form of parameter adjustment to enhance the performance of these controllers. Condition monitoring is perhaps a more natural application of the ANN where the pattern recognition capability can be fully utilized in a “stand alone” fashion. Simulation models have been successfully used to train the ANN for fault detection in physical systems.