ABSTRACT
Deployment of large-scale wind turbines requires sophisticated operation and maintenance strategies to ensure the devices are safe, profitable and cost-effective. Prognostics aims to predict the remaining useful life (RUL) of physical systems based on condition measurements. Analyzing condition monitoring data, implementing diagnostic techniques and using machinery prognostic algorithms will bring about accurate estimation of the remaining life and possible failures that may occur. This paper proposes to combine two supervised machine learning techniques, namely, regression model and multilayer artificial neural network model, to predict the RUL of an operational wind turbine gearbox using vibration measurements. Root Mean Square (RMS), Kurtosis (KU) and Energy Index (EI) were analysed to define the bearing failure stages. The proposed methodology was evaluated through a case study involving vibration measurements of a high-speed shaft bearing used in a wind turbine gearbox.
ABSTRACT
Acoustic emission (AE) monitoring is a technique of growing interest in the field of nondestructive testing (NDT). The use of AE devices to monitor the health of structural components is currently limited by the cost of AE equipment, which prohibits the permanent placement of AE devices on structures for the purposes of continuous monitoring and the monitoring of areas with limited access. Micro electromechanical systems (MEMS) can provide solutions to these problems. We present the manufacture of a 4.4-µm-thick lead zirconate titanate (PZT) film on a 110-µm-thick titanium foil substrate for use as an AE sensor. The thick-film sensor is benchmarked against commercially available AE sensors in static and dynamic monitoring applications. The thick-film AE device is found to perform well in the detection of AE in static applications. A low signal-to-noise ratio is found to prohibit the detection of AE in a dynamic application.
Subject(s)
Acoustics/instrumentation , Equipment Safety/instrumentation , Equipment Safety/methods , Lead/chemistry , Titanium/chemistry , Zirconium/chemistry , Electric Impedance , Equipment Design , Signal-To-Noise RatioABSTRACT
Monitoring the condition of complex engineering structures is an important aspect of modern engineering, eliminating unnecessary work and enabling planned maintenance, preventing failure. Acoustic emissions (AE) testing is one method of implementing continuous nondestructive structural health monitoring. A novel thick-film (17.6 µm) AE sensor is presented. Lead zirconate titanate thick films were fabricated using a powder/sol composite ink deposition technique and mechanically patterned to form a discrete thick-film piezoelectric AE sensor. The thick-film sensor was benchmarked against a commercial AE device and was found to exhibit comparable responses to simulated acoustic emissions.
