Reliable monitoring for the early fault diagnosis of gearbox faults is of great concern for the wind industry. This paper presents a novel approach for health condition monitoring (CM) and fault diagnosis in wind turbine gearboxes using vibration analysis. This methodology is based on a machine learning algorithm that generates a baseline for the identification of deviations from the normal operation conditions of the turbine and the intrinsic characteristic-scale decomposition (ICD) method for fault type recognition. Outliers picked up during the baseline stage are decomposed by the ICD method to obtain the product components which reveal the fault information. The new methodology proposed for gear and bearing defect identification was validated by laboratory and field trials, comparing well with the methods reviewed in the literature.

No abstract

No abstract

Corrosion is often the cause of pipeline failure potentially resulting in disasters causing damage and fatalities. To maintain the integrity of nonpiggable lines, NACE's external corrosion direct assessment (ECDA) methodology is commonly applied to assess external corrosion that can occur at coating defects on underground pipelines. Work presented here is from a validation exercise carried out on the results of ECDA assessment using subsequent excavation data. The ECDA was carried out over 300 km of crude oil pipelines with excavation carried out at 200 locations. This paper models the relationships between pipeline coating defect area (area with coating breakdown), corrosion depth, direct current-voltage gradient (DCVG) measurements (in terms of %IR values) and factors capturing diverse environmental conditions through novel application of regression models. This paper sheds light on the challenges in drawing conclusions in the assessment of corrosion from DCVG inspection data and other types of data that form key inputs to ECDA. We expect that the analyses shown here using innovative regression models will support more reliable predictions of external corrosion in pipelines.

No abstract