A study on crack fault diagnosis of wind turbine simulation system

Bae, Keun-Ho; Choi, Byung-Oh; Park, Jong-Won; Kim, Bong-Ki

doi:10.1109/icrms.2014.7107135

Cited by 3 publications

(2 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…(c) The proposed method has strong adaptability to the data of different working conditions, has relatively good fault characterization ability, and can also obtain relatively high recognition accuracy in the case of small samples. For vibration signals, some statistical characteristic parameters are often used to measure the operation status, whether there is a fault, and the degree of fault of the gearbox, and their effectiveness has been verified by many scholars [5,22,23]. The time-domain characteristics and their expressions used in this paper are shown…”

Section: Introductionmentioning

confidence: 90%

“…Lei and Zuo [4] extracted the statistical parameters of the signal in the time domain and frequency domain, screened the features through the Euclidean distance evaluation technique, and finally identified the gear crack fault by using the weighted k-nearest neighbor (KNN) technology, and obtained a good diagnosis effect. Bae et al [5] took the time-domain statistical characteristics as the input, used the adaptive network fuzzy inference system and three directed acyclic graph-support vector machine (DAG-SVM) models to identify the gear crack fault, and compared the identification effects of different models. Wang and Shao [6] screened the statistical time-domain and frequency-domain characteristics of the signal and used the k-means algorithm to identify and classify the crack fault of the planetary gearbox.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Intelligent fault diagnosis of gear crack based on side frequency feature under different working conditions

Xiao

Chen

et al. 2023

Meas. Sci. Technol.

View full text Add to dashboard Cite

Aiming at the problem of gear crack fault diagnosis, an intelligent diagnosis method based on side frequency feature is proposed. It enhances the fault information representation ability of the extracted features and the fault identification ability of the model. Firstly, according to the side frequency distribution characteristics of gear crack fault, the side frequency energy features are quantified, and a relatively complete feature set is constructed by combining the time domain features; Secondly, an evaluation method of feature effectiveness is designed to obtain the optimal feature subset; Finally, a three-stage training network is constructed to achieve an increase in fault diagnosis rate. The test results under different working conditions show that the proposed method can more completely represent the fault information and effectively improve the fault diagnosis rate when compared with the machine learning model of a general two-layer network and feature extraction methods based on entropy features.

show abstract

Section: Introductionmentioning

confidence: 90%