A novel hierarchical hyper-parameter search algorithm based on greedy strategy for wind turbine fault diagnosis

作者：

Highlights：

• Reuseing LeNet5 network and using it for planetary gear fault diagnosis.

• A method on hyperparameter search called HGSHRS is proposed.

• The performance in each stage of the proposed algorithm is verified.

• The stability on specific model is studied under different optimization methods.

摘要

•Reuseing LeNet5 network and using it for planetary gear fault diagnosis.•A method on hyperparameter search called HGSHRS is proposed.•The performance in each stage of the proposed algorithm is verified.•The stability on specific model is studied under different optimization methods.

论文关键词：Fault diagnosis,Wind turbines,Hyper-parameter search,Approximate optimal models,HGSHRS

论文评审过程：Received 7 July 2021, Revised 27 April 2022, Accepted 28 April 2022, Available online 2 May 2022, Version of Record 4 May 2022.

论文官网地址：https://doi.org/10.1016/j.eswa.2022.117473