A brief review on offshore wind turbine fault detection and recent development in condition monitoring based maintenance system

Kabir, Mohammed J.; Oo, Amanullah M. T.; Rabbani, Mahbub

doi:10.1109/aupec.2015.7324871

Cited by 38 publications

(27 citation statements)

References 56 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The Fourier transform can therefore be adapted for a sliding time window by using the short‐time Fourier transform, where a spectrotemporal representation of the signal is obtained. This is used for order analysis and allows the spectral values to be tracked in time . Order analysis is a resampling technique that can be effective when analysing nonstationary signals.…”

Section: Methodsmentioning

confidence: 99%

“…This is used for order analysis and allows the spectral values to be tracked in time. 17,18 Order analysis is a resampling technique that can be effective when analysing nonstationary signals. When a signal is resampled using this technique, it moves from a variable shaft speed and constant sampling rate, to constant shaft speed and variable sample rate.…”

Section: Fourier and Order Analysismentioning

confidence: 99%

See 1 more Smart Citation

Prediction of wind turbine generator failure using two‐stage cluster‐classification methodology

et al. 2019

View full text Add to dashboard Cite

Reducing wind turbine downtime through innovations surrounding asset management has the potential to greatly influence the levelised cost of energy (LCoE) for large wind farm developments. Focusing on generator bearing failure and vibration data, this paper presents a two‐stage methodology to predict failure within 1 to 2 months of occurrence. Results are obtained by building up a database of failures and training machine learning algorithms to classify the bearing as healthy or unhealthy. This is achieved by first using clustering techniques to produce subpopulations of data based on operating conditions, which this paper demonstrates can greatly influence the ability to diagnose a fault. Secondly, this work classifies individual clusters as healthy or unhealthy from vibration‐based condition monitoring systems by applying order analysis techniques to extract features. Using the methodology explained in the report, an accuracy of up to 81.6% correct failure prediction was achieved.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Fourier and Order Analysismentioning

confidence: 99%

Prediction of wind turbine generator failure using two‐stage cluster‐classification methodology

et al. 2019

View full text Add to dashboard Cite

show abstract

“…Many CM and fault diagnosis reviews have been published in the last 15 years that include the latest CM methods [34,35]. These can be classified per WT subsystem [36,37] and differentiated between structural [38], mechanical [39], power electronics and control systems [40] or electrical parts [41][42][43].…”

Section: Condition Monitoringmentioning

confidence: 99%

The Use of Electrical Measurements of Wind Turbine Generators for Drive Train Condition Monitoring

Artigao¹,

Honrubia-Escribano²,

Martín-Martínez³

et al. 2020

Design Optimization of Wind Energy Conversion Systems With Applications

View full text Add to dashboard Cite

More modern and larger wind turbine (WT) generators are under continuous development. These exhibit more faults than smaller ones, which becomes critical offshore. Under this framework, operation and maintenance (O&M) is the key to improve reliability and availability of WTs, where condition-based maintenance (CBM) is currently seen as the preferred approach by the early detection and diagnosis of critical faults for WTs. The induction generator is one of the biggest contributors to failure rates and downtime of WTs, together with the gearbox and the drive train. In the present chapter, current signature analysis (CSA) will be introduced as a means for fault detection of WTs. CSA is a cost-effective and nonintrusive technique that can monitor both mechanical and electrical faults within the induction generator, as well as bearing-and gearbox-related faults. Different test cases of in-service wind turbine generators will be used to illustrate its usefulness.

show abstract

“…The information gathered from structural monitoring can be used in a condition-based maintenance schedule to better plan the inspection intervals, minimise the unnecessary replacements and offer practical guidance for future design. A number of non-destructive testing (NDT) techniques have been employed [7,8], such as, conventional strain gauges, ultrasonic testing, acoustic emission, thermography, optical fibre sensors and X-ray imaging. However, most of the existing condition monitoring systems are not suitable for long-term and continuous examination in the field [9].…”

Section: Introductionmentioning

confidence: 99%

Microwaves Sensor for Wind Turbine Blade Inspection

Haigh

Soutis

et al. 2016

Appl Compos Mater

View full text Add to dashboard Cite

The structural integrity of wind turbine blades can be adversely affected by their structural dynamics, temperature extremes, lightning strikes, ultraviolet radiation from sunlight and airborne particulate matter such as hailstones and sand. If subsurface delamination occurs and is undetected then this can lead to fibre breakage and catastrophic failures in composite blades. In this paper we introduce a microwave scanning technique that detects such delamination in practical blade assemblies. Using an open-ended waveguide sensor, the electromagnetic signal reflected from the composite is found to have a phase profile that can detect changes in the composite cross section. Glass fibre T-joints are scanned and the results used to detect thickness variations (e.g., the presence of the web) and delamination. Results are compared across the 18-20 GHz frequency band. The dielectric permittivity of the composite system is measured and is used to estimate the stand-off distance and operating frequency of the sensor. This is critical to the system's ability to detect damage. When the sensor is close to the surface of the structure (standoff distance ≈ 5 mm), delamination down to 0.2 mm in width could be detected.

show abstract

A brief review on offshore wind turbine fault detection and recent development in condition monitoring based maintenance system

Cited by 38 publications

References 56 publications

Prediction of wind turbine generator failure using two‐stage cluster‐classification methodology

Prediction of wind turbine generator failure using two‐stage cluster‐classification methodology

The Use of Electrical Measurements of Wind Turbine Generators for Drive Train Condition Monitoring

Microwaves Sensor for Wind Turbine Blade Inspection

Contact Info

Product

Resources

About