No abstract

No abstract

We present a generic methodology for machinery fault diagnosis through pattern recognition techniques. The proposed method has the advantage of dealing with complicated signatures, such as those present in the vibration signals of rolling element bearings with and without defects. The signature varies with the location and severity of bearing defects, load and speed of the shaft, and different bearing housing structures. More specifically, the proposed technique contains effective feature extraction, good learning ability, reliable feature fusion, and a simple classification algorithm. Examples with experimental testing data were used to illustrate the idea and effectiveness of the proposed method.

The failure of wind turbine blades is a major concern in the wind power industry due to the resulting high cost. It is, therefore, crucial to develop methods to monitor the integrity of wind turbine blades. Different methods are available to detect subsurface damage but most require close proximity between the sensor and the blade. Thermography, as a non-contact method, may avoid this problem. Both passive and active pulsed and step heating and cooling thermography techniques were investigated for different purposes. A section of a severely damaged blade and a small "plate" cut from the undamaged laminate section of the blade with holes of varying diameter and depth drilled from the rear to provide "known" defects were monitored. The raw thermal images captured by both active and passive thermography demonstrated that image processing was required to improve the quality of the thermal data. Different image processing algorithms were used to increase the thermal contrasts of subsurface defects in thermal images obtained by active thermography. A method called "Step Phase and Amplitude Thermography", which applies a transform-based algorithm to step heating and cooling data was used. This method was also applied, for the first time, to the passive thermography results. The outcomes of the image processing on both active and passive thermography indicated that the techniques employed could considerably increase the quality of the images and the visibility of internal defects. The signal-to-noise ratio of raw and processed images was calculated to quantitatively show that image processing methods considerably improve the ratios. the blade [10]. Since access to a blade is difficult and requires an industrial climber or crane, which can be dangerous and/or time-consuming, the practical implementation of conventional methods sometimes requires blade removal. Developing new NDT techniques that are capable of detecting faults in the blades from larger distances is essential.Infrared (IR) thermography is a non-contact, long-distance NDT technique that can inspect extensive areas quickly by capturing thermal images of the object's surface. In general, defective areas alter the temperature distributions on the surface that are measured by IR cameras. Thermographic inspection is typically divided into two categories: active and passive. In active thermography, different heating sources such as flash and halogen lamps are employed for heating the object making the technique less usual for operating wind turbines. It is used here largely to allow comparison with passive thermography which utilizes solar radiation [2] to heat a blade (usually around sunrise) or to cool it at sunset. This method has been widely used to detect subsurface defects of different materials including metals [11], composites [12,13], and concrete [14].Different studies have used thermography to detect faults in wind turbine blades. Meinlischmidt and Aderhold [2] employed passive thermography to detect internal structural features and subsurface defects s...

Abstract:The idea of indicative fault diagnosis based on measuring the wind turbine tower sound and vibration is presented. It had been reported by a wind farm operator that a major fault on the generator bearing causes shock and noise to be heard from the bottom of the wind turbine tower. The work in this paper was conceived to test whether tower top faults could be identified by taking simple measurements at the tower base. Two accelerometers were attached inside the wind turbine tower, and vibration data was collected while the wind turbine was in operation. Tower vibration signals were analyzed using Empirical Mode Decomposition and the outcomes were correlated with the vibration signals acquired directly from the generator bearings. It is shown that the generator bearing fault signatures were present in the vibrations from the tower. The results suggest that useful condition monitoring of nacelle components can be done even when there is no condition monitoring system installed on the generator bearings, as is often the case for older wind turbines. In the second part of the paper, acoustic measurements from a healthy and a faulty wind turbine are shown. The preliminary analysis suggests that the generator bearing fault increases the overall sound pressure level at the bottom of the tower, and is not buried in the background noise.