Wind turbine drivetrain health assessment using discrete wavelet transforms and an artificial neural network

Murray, C.; Asher, Matthew; Lieven, Nicholas A J; Mulroy, Michael; Ng, C; Morrish, Peter

doi:10.1049/cp.2014.0931

Cited by 7 publications

(6 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Deteriorations or defects of these parts likely lead to changes in the electric currents and/or vibrations emitted by the parts (cf. [46,94,95]).…”

Section: Discussionmentioning

confidence: 99%

“…He provides a taxonomy for fault diagnosis systems and related areas, describes the advantages which can be obtained by fault diagnosis, discusses the relevant approaches, and illustrates a number of applications in this field [4,43]. Other applications contain condition monitoring of rotating electrical machines [44,45], electrical power supplies [46,47], intelligent transportation systems [48,49], or communication networks [50,51]. …”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Information Fusion of Conflicting Input Data

Mönks

Dörksen

Lohweg

et al. 2016

Sensors

View full text Add to dashboard Cite

Sensors, and also actuators or external sources such as databases, serve as data sources in order to realise condition monitoring of industrial applications or the acquisition of characteristic parameters like production speed or reject rate. Modern facilities create such a large amount of complex data that a machine operator is unable to comprehend and process the information contained in the data. Thus, information fusion mechanisms gain increasing importance. Besides the management of large amounts of data, further challenges towards the fusion algorithms arise from epistemic uncertainties (incomplete knowledge) in the input signals as well as conflicts between them. These aspects must be considered during information processing to obtain reliable results, which are in accordance with the real world. The analysis of the scientific state of the art shows that current solutions fulfil said requirements at most only partly. This article proposes the multilayered information fusion system MACRO (multilayer attribute-based conflict-reducing observation) employing the μBalTLCS (fuzzified balanced two-layer conflict solving) fusion algorithm to reduce the impact of conflicts on the fusion result. The performance of the contribution is shown by its evaluation in the scope of a machine condition monitoring application under laboratory conditions. Here, the MACRO system yields the best results compared to state-of-the-art fusion mechanisms. The utilised data is published and freely accessible.

show abstract

“…Deteriorations or defects of these parts likely lead to changes in the electric currents and/or vibrations emitted by the parts (cf. [46,94,95]).…”

Section: Discussionmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Information Fusion of Conflicting Input Data

Mönks

Dörksen

Lohweg

et al. 2016

Sensors

View full text Add to dashboard Cite

show abstract

“…For the Symlet wavelets, however, the computational effort has a logarithmic increase up to a maximum of 13.45 * 10 6 times the computational effort of the haar wavelet, rendering all but a few of the lowest order ineffective.…”

Section: Computational Effortmentioning

confidence: 99%

“…The signal breakdown is performed by a series of convolution operations between the signal and a predefined waveform, called base or mother wavelet, to find their similarity and is expressed as wavelet coefficients. The use of wavelet transforms has been shown to be able to identify bearing failures and has lately been used as a preprocessing tool to machine learning algorithms for automatic detection and classification …”

Section: Introductionmentioning

confidence: 99%

“…9,10 The signal breakdown is performed by a series of convolution operations between the signal and a predefined waveform, called base or mother wavelet, to find their similarity and is expressed as wavelet coefficients. The use of wavelet transforms has been shown to be able to identify bearing failures [11][12][13][14] and has lately been used as a preprocessing tool to machine learning algorithms for automatic detection and classification. 15 A minimization criterion of the Shannon entropy has been used in wavelet analysis of bearing failures to find both the optimal decomposition of the signal which should be used, and which mother wavelet who can best separate the faulty bearing vibrations from the overall noise.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Mother wavelet selection in the discrete wavelet transform for condition monitoring of wind turbine drivetrain bearings

et al. 2019

View full text Add to dashboard Cite

Although the discrete wavelet transform has been used for diagnosing bearing faults for two decades, most work in this field has been done with test rig data. Since field data starts to be made more available, there is a need to shift into application studies. The choice of mother wavelet, ie, the predefined shape used to analyse the signal, has previously been investigated with simulated and test rig data without consensus of optimal choice in literature. Common between these investigations is the use of the wavelet coefficients' Shannon entropy to find which mother wavelet can yield the most useful features for condition monitoring. This study attempts to find the optimal mother wavelet selection using the discrete wavelet transform. Datasets from wind turbine gearbox accelerometers, consisting of enveloped vibration measurements monitoring both healthy and faulty bearings, have been analysed. The bearing fault frequencies' excitation level has been analysed with 130 different mother wavelets, yielding a definitive measure on their performance. Also, the applicability of Shannon entropy as a ranking method of mother wavelets has been investigated. The results show the discrete wavelet transforms ability to identify faults regardless of mother wavelet used, with the excitation level varying no more than 4%. By analysing the Shannon entropy, broad predictions to the excitation level could be drawn within the mother wavelet families but no direct correlation to the main results. Also, the high computational effort of high order Symlet wavelets, without increased performance, makes them unsuitable.

show abstract

A Comprehensive Review of Artificial Intelligence and Wind Energy

Márquez

Gonzalo

2021

Arch Computat Methods Eng

View full text Add to dashboard Cite

Support of artificial intelligence, renewable energy and sustainability is currently increasing through the main policies of developed countries, e.g., the White Paper of the European Union. Wind energy is one of the most important renewable sources, growing in both onshore and offshore types. This paper studies the most remarkable artificial intelligence techniques employed in wind turbines monitoring systems. The principal techniques are analysed individually and together: Artificial Neural Networks; Fuzzy Logic; Genetic Algorithms; Particle Swarm Optimization; Decision Making Techniques; and Statistical Methods. The main applications for wind turbines maintenance management are also analysed, e.g., economic, farm location, non-destructive testing, environmental conditions, schedules, operator decisions, power production, remaining useful life, etc. Finally, the paper discusses the main findings of the literature in the conclusions.

show abstract

Wind turbine drivetrain health assessment using discrete wavelet transforms and an artificial neural network

Cited by 7 publications

References 0 publications

Information Fusion of Conflicting Input Data

Information Fusion of Conflicting Input Data

Mother wavelet selection in the discrete wavelet transform for condition monitoring of wind turbine drivetrain bearings

A Comprehensive Review of Artificial Intelligence and Wind Energy

Contact Info

Product

Resources

About