A comparison of neural networks and model-based methods applied for fault diagnosis of electro-hydraulic control systems

The paper aims to investigate two advanced methods used in fault diagnosis of electro-hydraulic (EH) control systems. The theoretical background of the neural network method and model-based approach are presented and the implementation of these methods is summarised with procedures in easy steps to follow for application. The pros and cons of these methods are also analysed based on fault detection capability. It is concluded that a combination of the neural network method and the model-based approach will be beneficial.