基于改进栈式自编码器的风电机组发电机健康评估

计算机工程与科学

基于改进栈式自编码器的风电机组发电机健康评估

林涛，赵成林，刘航鹏，赵参参

（河北工业大学人工智能与数据科学学院，天津 300130）

收稿日期:2019-06-10 修回日期:2019-10-11 出版日期:2020-03-25 发布日期:2020-03-25
基金资助:
河北省科技计划（17214304D）

Health assessment of wind turbine generator

based on improved stacked auto-encoder

LIN Tao，ZHAO Cheng-lin，LIU Hang-peng，ZHAO Shen-shen

(School of Artificial Intelligence,Hebei University of Technology,Tianjin 300130,China)

Received:2019-06-10 Revised:2019-10-11 Online:2020-03-25 Published:2020-03-25

摘要/Abstract

摘要：

风电机组发电机具有结构复杂、维修困难的特点，为对其进行健康评估，结合去噪自编码器与稀疏自编码器的特点，对传统栈式自编码器模型进行改进，利用模型的重构误差监测风电机组发电机的运行状态。将经离线测试得到的重构误差与在线监测得到的重构误差进行分布差异性比对，通过融合3种差异指标得到风电机组发电机的健康度。利用河北某风场实际数据对健康评估模型进行训练测试，通过实例分析证明该模型能够有效跟踪风电机组发电机的状态变化，具有故障早期识别的作用。

关键词: 风电机组发电机, 健康度, 栈式自编码器, 去噪自编码, 稀疏自编码器

Abstract:

Wind turbine generator has the characteristics of complicated structure and difficult maintenance. In order to evaluate its health, this paper combines the characteristics of denoising auto-encoder and sparse auto-encoder to improve the traditional stacked auto-encoder model, and uses the reconstruction error of the model to monitor the running state of the wind turbine generator. The reconstruction error obtained by off-line testing is compared with the reconstruction error obtained by online monitoring, and the health of the wind turbine generator is obtained by combining three different indicators. The health assessment model is trained and tested by using the actual data of a wind farm in Hebei Pro- vince. The example analysis shows that the method can effectively track the state change of the wind turbine generator and has the function of early identification of faults.

Key words: wind turbine generator, health assessment, stacked auto-encoder, denoising auto-encoder, sparse auto-encoder

林涛，赵成林，刘航鹏，赵参参. 基于改进栈式自编码器的风电机组发电机健康评估[J]. 计算机工程与科学.

LIN Tao，ZHAO Cheng-lin，LIU Hang-peng，ZHAO Shen-shen.

Health assessment of wind turbine generator

based on improved stacked auto-encoder

[J]. Computer Engineering & Science.

[1]	范韫. 基于EMD距离的稀疏自编码器[J]. 计算机工程与科学, 2022, 44(05): 894-900.
[2]	谢国民，张婷婷，刘明，屠乃威，刘志邦. 基于SDAE特征表示的协同主题回归推荐模型[J]. 计算机工程与科学, 2019, 41(05): 924-932.
[3]	马永军，李亚军，汪睿，陈海山. 基于Wasserstein GAN的文档表示模型[J]. 计算机工程与科学, 2019, 41(01): 161-165.