Intelligent Fault Diagnosis Method of Wind Turbines Planetary Gearboxes Based on a Multi-Scale Dense Fusion Network

Huang, Xinghua; Li, Yuanyuan; Chai, Yi

doi:10.3389/fenrg.2021.747622

Cited by 6 publications

(3 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The condition evaluation of a single component of a wind turbine is mainly focused on the fault diagnosis or life prediction of the component. Du et al (2015) and Huang et al (2021) proposed fault diagnosis methods for wind turbine gearbox based on sparse feature recognition and convolutional neural network respectively. To address the bearing fault diagnosis, the methods based on current-demodulated signals and SCADA data respectively were proposed in Gong et al (2013) and Encalada-Dávila et al (2021).…”

Section: Introductionmentioning

confidence: 99%

An evaluation method of health condition for wind turbine based on asymmetric proximity

et al. 2023

View full text Add to dashboard Cite

The accurate condition assessment of wind turbines greatly influences the refined asset management and maintenance scheduling of wind farms. To address the challenges of existing assessment methods in selecting the reliability value and determining wind turbine status levels of being in transition, this study proposes a wind turbine condition evaluation method based on asymmetric proximity. Firstly, the state evaluation index system consisting of the wind turbine performance and output state indices is constructed, and the weighting factors are calculated comprehensively by integrating the subjective and objective weights. Then, the membership function of the index layer is established based on the set pair analysis, and the membership of the target layer is deduced by the weighted average operator. Finally, the proximity degrees between status levels and target membership degrees are calculated, and the wind turbine state is determined based on the proximity principle. Case studies demonstrate that the accuracy rate of the proposed method is up to 97%, which is 6% and 8% higher than the maximum membership principle and the reliability criterion, respectively.

show abstract

Section: Introductionmentioning

confidence: 99%

An evaluation method of health condition for wind turbine based on asymmetric proximity

et al. 2023

View full text Add to dashboard Cite

show abstract

“…To extract multiscale features and improve the performance of classifiers, multiscale CNN methods have been extensively used in fault diagnosis. Huang et al [31] proposed a CNN with a multiscale dense fusion network to combine the multiscale features of each network layer to enhance the fault features for the fault diagnosis of wind turbine planetary gearboxes. To simultaneously perform multiscale feature extraction and classification, Jiang et al [32] proposed a new multiscale CNN for the fault diagnosis of a wind turbine gearbox.…”

Section: Introductionmentioning

confidence: 99%

Bearing fault diagnosis under various operation conditions using synchrosqueezing transform and improved two-dimensional convolutional neural network

Zhuan¹,

Lv²,

Huang³

et al. 2022

Meas. Sci. Technol.

View full text Add to dashboard Cite

In real-world industrial applications, bearings are typically operated under variable speeds and loads depending on the production condition, which results in nonstationary vibration signals from the bearings. Synchrosqueezing transform (SST) is a method that can effectively reflect the change in frequency with time, which is suitable for processing nonstationary bearing signals. However, significant classification features are difficult to extract from time–frequency information when operation conditions such as speed and load change frequently. Hence, an improved two-dimensional convolutional neural network (CNN) named the two-dimensional multiscale cascade CNN (2D MC-CNN) is proposed for performing bearing fault diagnosis under various operating conditions. In a 2D MC-CNN, a multiscale information fusion layer is added prior to the convolutional layer of a conventional CNN to form multiscale cascade images such that sensitive bands can be acquired for fault recognition. Experiments are conducted on bearings by considering various sets of fault categories and fault severity levels under six operating conditions. The experimental results show that the proposed method effectively extracts fault-related features and demonstrates excellent diagnostic accuracy and robustness. Comparisons with the original CNN and other typically used fault diagnosis methods based on the same dataset demonstrate the effectiveness of the proposed 2D MC-CNN and bearing fault diagnosis method.

show abstract

“…CNN solves the dilemma that other algorithms need to artificially extract features. Also, it finds the optimal weight parameters matrix by error back propagation along with local connections and weight sharing based on correlation between data (Zhang et al, 2019), which can automatically extract abstract and valuable features from the data to complete specific tasks (Hao et al, 2022;Huang et al, 2021). Applying CNN to powerformer protection has the potential to achieve good results.…”

Section: Introductionmentioning

confidence: 99%

Stator single-line-to-ground fault protection for powerformers based on HSGC and CNN

et al. 2022

View full text Add to dashboard Cite

It is necessary for powerformers running in parallel to identify which powerformer occurs at the stator single-line-to-ground (SLG) fault. Some state-of-the-art fusion discriminations are used to identify stator SLG fault, but these methods extract fault features artificially, and application conditions are limited. Convolutional neural network (CNN) has shown superior automatic feature extraction ability in various fields, but it cannot directly extract features from one-dimensional time series vectors collected by powerformers. Therefore, this article proposed a novel SLG fault protection scheme based on the hub-and-spoke grid data converting algorithm (HSGC) and CNN. First, Pearson product-moment correlation coefficients (PCCs) are used to calculate the correlations of one-dimensional time series vectors, establish a correspondence between them and the distance of two-dimensional grid cells, and then convert one-dimensional time series vectors to two-dimensional grid-structured data by HSGC. Second, the trained CNN automatically extracts the features of two-dimensional grid-structured data. Finally, the faulty powerformer can be identified based on the output of CNN. The proposed protection scheme is verified through the simulation of ATP-EMTP and Python. The results show that the scheme can accurately detect a faulty Powerformer under different conditions where neutral point is high-resistance or reactance grounding, even if fault resistance is 8,000 Ω.

show abstract

Intelligent Fault Diagnosis Method of Wind Turbines Planetary Gearboxes Based on a Multi-Scale Dense Fusion Network

Cited by 6 publications

References 47 publications

An evaluation method of health condition for wind turbine based on asymmetric proximity

An evaluation method of health condition for wind turbine based on asymmetric proximity

Bearing fault diagnosis under various operation conditions using synchrosqueezing transform and improved two-dimensional convolutional neural network

Stator single-line-to-ground fault protection for powerformers based on HSGC and CNN

Contact Info

Product

Resources

About