Wind Turbine Gearbox Condition Monitoring with AAKR and Moving Window Statistic Methods

Abstract

Condition Monitoring (CM) of wind turbines can greatly reduce the maintenance costs for wind farms, especially for offshore wind farms. A new condition monitoring method for a wind turbine gearbox using temperature trend analysis is proposed. Autoassociative Kernel Regression (AAKR) is used to construct the normal behavior model of the gearbox temperature. With a proper construction of the memory matrix, the AAKR model can cover the normal working space for the gearbox. When the gearbox has an incipient failure, the residuals between AAKR model estimates and the measurement temperature will become significant. A moving window statistical method is used to detect the changes of the residual mean value and standard deviation in a timely manner. When one of these parameters exceeds predefined thresholds, an incipient failure is flagged. In order to simulate the gearbox fault, manual temperature drift is added to the initial Supervisory Control and Data Acquisitions (SCADA) data. Analysis of simulated gearbox failures shows that the new condition monitoring method is effective.

Modelling Wind Turbine Failures based on Weather Conditions

“…[11] and/or the transition periods between seasons, see e.g. [22]. Figures 3 to 7 show the standardised coefficient magnitudes.…”

Failure Mode Identification and End of Life Scenarios of Offshore Wind Turbines: A Review

“…The same study points out that "among all bearings in a planetary gearbox, the planet bearings, the intermediate shaft-locating bearings and high-speed locating bearings tend to fail at a higher rate, while the planet carrier bearings, hollow shaft bearings and non-locating bearings are most unlikely to fail". Another important failure is the shaft-gearbox decoupling, which is considered to be catastrophic [21], while pitting, cracking, scratching and other faults are ranked with lower criticality [38], as they can be detected early enough through gearbox diagnosis and Condition Monitoring (CM) methods such as Acoustic Emission (AE) [50] or Auto-associative Kernel Regression (AAKR) [51]. Reference [29] presented a study related to WT drive-train diagnosis, where the electrical analysis was assessed for mechanical defects and the diagnosis of gear eccentricity was investigated.…”

Monitoring gearbox using a wireless temperature node powered by thermal energy harvesting module

“…The temperature is easily measured and important indicators for the health of many machine components such as gearbox and is often recorded automatically using data acquisition system [5,6]. An unexpected increase in component temperature may indicate an overload, poor lubrication or possibly ineffective passive or active cooling.…”

“…An unexpected increase in component temperature may indicate an overload, poor lubrication or possibly ineffective passive or active cooling. Reference [5] used temperature trend analysis to monitor the gearbox's operating conditions. The Auto Associative Kernel Regression (AAKR) method is used to model the normal behaviour of gearbox temperature and give temperature estimates.…”