Monitoring of solenoid parameters based on neural networks and optical fiber squeezer for solenoid valves diagnosis

As crucial parts of various engineering systems, solenoid valves (SVs) operated by electromagnetic (EMS) are great importance and their failure may lead to cause unexpected casualties. This failure, characterized a degradation the performances SVs, could be due fluctuations in EMS parameters. These essentially attributed changes spring constant, coefficient friction, inductance, resistance coil. Preventive maintenance controlling monitoring these parameters is necessary avoid eventual actuators. The authors propose new methodology for functional diagnosis solenoids used hydraulic systems. proposed method monitors online electrical mechanical varying over time using artificial neural networks algorithm coupled with an optical fiber polarization squeezer based on scrambling. First, MATLAB/Simulink model analyze effect dynamic model. result this simulation training network, then net fitting toolbox determine (Resistance coil R, stiffness K friction B spring) from coefficients transfer function, established step response. Future work will include not only diagnosing modes, but also predicting remaining life results monitoring.