Fault Diagnosis of Wind Turbine Gearbox Using a Novel Method of Fast Deep Graph Convolutional Networks

Yu, Xiaoxia; Tang, Baoping; Zhang, Kai

doi:10.1109/tim.2020.3048799

Cited by 88 publications

(29 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Each A i,j term represents the weight of the connected edge between i and j. The graph Laplacian is defined as L = D−A, where L is the graph Laplacian and D = diag[ j A i,j ] is the degree matrix of A [40]. Every graph has the option of being directed or undirected.…”

Section: A Graph Convolutional Neural Networkmentioning

confidence: 99%

Spatial Graph Convolutional Neural Network via Structured Subdomain Adaptation and Domain Adversarial Learning for Bearing Fault Diagnosis

Ghorvei¹,

Kavianpour²,

Beheshti³

et al. 2021

Preprint

View full text Add to dashboard Cite

Unsupervised domain adaptation (UDA) has shown remarkable results in bearing fault diagnosis under changing working conditions in recent years. However, most UDA methods do not consider the geometric structure of the data. Furthermore, the global domain adaptation technique is commonly applied, which ignores the relation between subdomains. This paper addresses mentioned challenges by presenting the novel deep subdomain adaptation graph convolution neural network (DSAGCN), which has two key characteristics: First, graph convolution neural network (GCNN) is employed to model the structure of data. Second, adversarial domain adaptation and local maximum mean discrepancy (LMMD) methods are applied concurrently to align the subdomain's distribution and reduce structure discrepancy between relevant subdomains and global domains. CWRU and Paderborn bearing datasets are used to validate the DSAGCN method's efficiency and superiority between comparison models. The experimental results demonstrate the significance of aligning structured subdomains along with domain adaptation methods to obtain an accurate data-driven model in unsupervised fault diagnosis.

show abstract

Section: A Graph Convolutional Neural Networkmentioning

confidence: 99%

Spatial Graph Convolutional Neural Network via Structured Subdomain Adaptation and Domain Adversarial Learning for Bearing Fault Diagnosis

Ghorvei¹,

Kavianpour²,

Beheshti³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…E VERY rotary machine is composed of bearings that ranges from civilian to military applications, such as motors, industrial fans, compressors, automobiles, turbines, and vehicles [1], [2], [3], [4]. A single fault in a bearing can shut down the whole machine it is contained within; therefore, vibration analysis techniques are extensively studied to detect early-stage faults in rotary machines [5], [6].…”

Section: Introductionmentioning

confidence: 99%

Early-Stage Fault Diagnosis for Rotating Element Bearing Using Improved Harmony Search Algorithm With Different Fitness Functions

Ahsan

Bismor

2022

IEEE Trans. Instrum. Meas.

View full text Add to dashboard Cite

“…In recent years, data-driven wind turbine power curves (WTPCs) have become vital for many applications such as condition monitoring, forecasting, see for example [20], [21]. Examples of data-driven techniques for monitoring WTs are also presented in [8] and [22][23][24][25].…”

Section: Introductionmentioning

confidence: 99%

Operational Variables for Improving Industrial Wind Turbine Yaw Misalignment Early Fault Detection Capabilities Using Data-Driven Techniques

Pandit

Infield

Dodwell

2021

IEEE Trans. Instrum. Meas.

View full text Add to dashboard Cite

Offshore wind turbines are complex pieces of engineering and are, generally, exposed to harsh environmental conditions that are making them to susceptible unexpected and potentially catastrophic damage. This results in significant down time, and high maintenance costs. Therefore, early detection of major failures is important to improve availability, boost power production and reduce maintenance costs.This paper proposes a SCADA data based Gaussian Process (GP) (a data-driven, machine learning approach) fault detection algorithm where additional model inputs, called operational variables (pitch angle and rotor speed) are used. Firstly, comparative studies of these operational variables are carried out to establish whether the parameter leads to improved early fault detection capability; it is then used to construct an improved GP fault detection algorithm. The developed model is then validated against existing methods in terms of capability to detect in advance (and by how much) signs of failure with a low false positive rate.Failure due to yaw misalignment results in significant down time and a reduction in power production was found to be a useful case study to demonstrate the effectiveness of the proposed algorithms. Historical SCADA 10-minute data obtained from pitch-regulated turbines were used for models training and validation purposes. Results show that (i) the additional model inputs were able to improve the accuracy of GP power curve models with rotor speed responsible for a significant improvement in performance; (ii) the inclusion of rotor speed enhanced early failure detection without any false positives, in contrast to the other methods investigated.

show abstract

Fault Diagnosis of Wind Turbine Gearbox Using a Novel Method of Fast Deep Graph Convolutional Networks

Cited by 88 publications

References 27 publications

Spatial Graph Convolutional Neural Network via Structured Subdomain Adaptation and Domain Adversarial Learning for Bearing Fault Diagnosis

Spatial Graph Convolutional Neural Network via Structured Subdomain Adaptation and Domain Adversarial Learning for Bearing Fault Diagnosis

Early-Stage Fault Diagnosis for Rotating Element Bearing Using Improved Harmony Search Algorithm With Different Fitness Functions

Operational Variables for Improving Industrial Wind Turbine Yaw Misalignment Early Fault Detection Capabilities Using Data-Driven Techniques

Contact Info

Product

Resources

About