Gini index-based methods and indexes

External resources

Gini index (GI) is an outstanding sparsity index which has been widely applied in machinery fault diagnosis. It has been verified that GI has the most stable gradient property and has the best ability to distinguish impulsiveness and repetitive transients compared with the most-used sparsity indexes, such as kurtosis, Lp/Lq norm, etc. To guide the application of GI in this field, some Matlab codes are provided. There are the codes of GI, GI-based indexes, improved methods based on GI and the deconvolution methods based on GI.

The matlab codes of GI and GI-based indexes permit to reproduce some results in the papers:

[1] Y. Miao, et al., Practical framework of Gini index in the application of machinery fault feature extraction, Mechanical Systems and Signal Processing, 165 (2022) 108333.

[2] Y. Miao, et al., Application of an improved MCKDA for fault detection of wind turbine gear based on encoder signal, Renewable Energy, 151 (2020) 192-203.

[3] Y. Miao, et al., Research on sparsity indexes for fault diagnosis of rotating machinery, Measurement, 158 (2020) 107733.

The matlab codes of improved methods based on GI and the deconvolution methods based on GI permit to reproduce some results in the papers:

[1] Y. Miao, et al., Practical framework of Gini index in the application of machinery fault feature extraction, Mechanical Systems and Signal Processing, 165 (2022) 108333.

[2] Y. Miao, et al., Improvement of kurtosis-guided-grams via Gini index for bearing fault feature identification, Measurement Science and Technology, 28 (2017) 125001.

Copyright (c) belongs to the authors of the papers. An acknowledgment for the codes and the citations about all the papers above must be included in the publications as long as the codes are used.

Our works and full texts can refer

https://www.researchgate.net/profile/Yonghao-Miao

https://scholar.google.com.hk/citations?user=gRZ_iZsAAAAJ&hl=zh-CN&oi=ao