Wind turbine condition monitoring using multi-sensor data system

Wind turbines are being complex and critical systems. They encompass interacting mechanical and electrical systems subjected to variable aerodynamics and environmental conditions. Therefore, the use of single sensor to monitor and evaluate the performance and working condition of the system will not generate reliable results. To tackle this issue and to enhance the reliability of such system a multi-sensor (i.e. vibrations, torque, voltage and current) fusion system proposed in this paper to monitor the health condition of the wind turbine system. In time domain, both wind turbine vibration and the generated current increased by increasing the blade rotational speed. However, the overall vibration level is reduced by increasing the blade pitch angle. This could relate to the influence of increasing the air resistance, as more area of the blade will be in contact with the air, which plays the role of a damper. The developed air resistance reduce the rotational speed of the blade and consequently the generated current and voltage dropped. In frequency domain, the FFT power spectrum peaks are clearly indicates the influence of the rotational speed of different wind turbine rotating components on the generated frequency peaks. However, the peaks are very clear with less noise in the electrical signals compared with the vibrational signals. This gives a motivation to examine the application of the both vibrational and electrical signals for wind turbine condition monitoring and fault diagnostics. © International Journal Of Renewable Energy Research, 2018.