Riahi - Iran University of Science and Technology Narmak, Tehran, Iran
Gholizadeh - Iran University of Science and Technology Narmak, Tehran, Iran

Maintenance reliability and efficiency in industrial hydraulic systems operation has become a point of concern for the professionals in maintenance engineering. One practical approach in this regard is the realization of symptoms of early stage malfunctioning in fluid power systems after which maintenance planning and preventive means would follow upon a reasonably accurate and subsequently acceptable determination. Among the highly reliable sources providing such convenience, Artificial Neural Network (ANN) stands a high chance of success. Neural network method has been used to detect faults occurring in most hydraulic systems. These faults could be related to supply pressure, effective bulk modulus and total leakage. The simulated system in this study consists of hydraulic servo valve, double acting cylinder and a spring that resists piston movement. Two main reasons causing this system to have a nonlinear behavior are hydraulic servo valve and compressibility effect of hydraulic fluid. The neural network approach in this investigation comprises of an efficient use in nonlinear systems and requires advance knowledge about the system behavior under faulty conditions and assumptions about the type and severity of faults likely to occur. Neural networks trained with different training algorithms are investigated. After training the network, the system was examined for different inputs and obtained results were compared.

Fault Detection; ANN (Artificial Neural Network); Hydraulic Servo Valve