A Data-Driven Approach for Bearing Fault Prognostics

Jin, Xiaohang; Que, Zijun; Sun, Yi; Guo, Yuanjing; Wang, Qiao

doi:10.1109/ias.2018.8544586

Cited by 45 publications

(3 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Ahmad et al (2017) implemented a hybrid PHM approach by training an adaptive predictive model on the NASA bearing degradation data and then adopting a regression-based approach to predict the RUL. Other researchers such as Jin et al (2018) used a self-organizing map (SOM) to train the degradation model for the bearings data from the FEMTO-ST PRONOSTIA test bed and then adopted an unscented Kalman Filters to estimate RUL using the trained model. In general, the hybrid approach combines the use of degradation data to train an AI algorithm to learn the parameters of a physical model, and then uses the learned model along with statistical or other approaches to make extrapolations or predictions.…”

Section: Hybrid/fusionmentioning

confidence: 99%

Artificial intelligence in prognostics and health management of engineering systems

Ochella

Shafiee

Dinmohammadi

2022

Engineering Applications of Artificial Intelligence

View full text Add to dashboard Cite

Section: Hybrid/fusionmentioning

confidence: 99%

Artificial intelligence in prognostics and health management of engineering systems

Ochella

Shafiee

Dinmohammadi

2022

Engineering Applications of Artificial Intelligence

View full text Add to dashboard Cite

“…Therefore, anomaly detection and fault diagnosis of wind turbines through SCADA data analysis becomes a hot topic. Generally, based on the SCADA data, a normal behavior model (NBM) [9] can be built and quantitative anomaly indicators [10] can be constructed for condition monitoring of wind turbines. For example, a NBM based on principal component analysis and support vector regression was established to detect generator fault based on power, voltages, and currents SCADA data [11].…”

Section: Introductionmentioning

confidence: 99%

Condition Monitoring of Wind Turbine Generators Based on SCADA Data and Feature Transfer Learning

et al. 2023

View full text Add to dashboard Cite

In order to build an effective condition monitoring (CM) model for the target wind turbines (WTs) with few operational data, an approach based on the feature transfer learning and a modified generative adversarial network is proposed. First, a large amount of labelled data from WTs are analyzed to construct a CM model with the aid of an autoencoder. This forms the knowledge of CM for WTs in the source domain. Second, a generative adversarial network is trained to build a mapping relationship between the features of different WTs. Third, the health status of the target WT is determined by analyzing the data collected from it online based on the proposed approach. Two case studies are conducted to verify that the proposed method can transfer the CM knowledge from source WT to target WT and achieve good performance in the CM of target WT.INDEX TERMS Autoencoder, condition monitoring (CM), feature transfer learning, generative adversarial network (GAN), wind turbine (WT).

show abstract

“…Categorizing these methods in classes is quite difficult because of a wide variety of applications. However, Vachtsevanos et al, in [3], classified prognostic methods into three main categories, prognosis based on: (i) experience, (ii) data, and (iii) model [4], [5], [6], [7], [8], [9], [10]. However, it is possible to integrate experience-based prognostic into data-driven prognosis since it handles system data.…”

Section: Introductionmentioning

confidence: 99%