Wind turbine fault sampling algorithm based on improved BSMOTE and sequential characteristics

doi:10.11772/j.issn.1001-9081.2020091384

Journal of Computer Applications ›› 2021, Vol. 41 ›› Issue (6): 1673-1678.DOI: 10.11772/j.issn.1001-9081.2020091384

Special Issue: 人工智能

• Artificial intelligence • Previous Articles Next Articles

Wind turbine fault sampling algorithm based on improved BSMOTE and sequential characteristics

YANG Xian¹, ZHAO Jisheng², QIANG Baohua¹, MI Luzhong², PENG Bo³, TANG Chenghua¹, LI Baolian³

1. Guangxi Key Laboratory of Image and Graphic Intelligent Processing(Guilin University of Electronic Technology), Guilin Guangxi 541004, China;
2. Beijing Huadian Tianren Electric Power Control Technology Company Limited, Beijing 100039, China;
3. The 54 th Research Institute of China Electronics Technology Group Corporation, Shijiazhuang Hebei 050081, China

Received:2020-09-07 Revised:2020-12-16 Online:2021-06-10 Published:2021-01-26
Supported by:
This work is partially supported by the National Natural Science Foundation of China (61762025, 62062028), the Guangxi Key Research and Development Program (AB18126053, AB18126063, AD18281002), the Program of CHN Energy Technology and Environment Group Corporation Limited (IKY.2019.0002), the Natural Science Foundation of Guangxi (2017GXNSFAA198226, 2019GXNSFDA185007, 2019GXNSFDA185006, 2018GXNSFAA294058), the Guangxi Key Science and Technology Program (AA18118031, AA18242028), the Development Foundation of CETC54 (SXX18138X017), the Innovation Project of GUET Graduate Education (2019YCXS051, 2020YCXS052), the Fund of Guangxi Key Laboratory of Image and Graphic Intelligent Processing (GIIP201603, GIIP1806).

基于改进的BSMOTE和时序特征的风机故障采样算法

杨鲜¹, 赵计生², 强保华¹, 米路中², 彭博³, 唐成华¹, 李宝莲³

1. 广西图像图形与智能处理重点实验室(桂林电子科技大学), 广西桂林 541004;
2. 北京华电天仁电力控制技术有限公司, 北京 100039;
3. 中国电子科技集团公司第54研究所, 石家庄 050081

通讯作者: 强保华
作者简介:杨鲜(1994-),男,四川成都人,硕士研究生,主要研究方向:风电大数据、机器学习;赵计生(1980-),男,山西忻州人,高级工程师,硕士,主要研究方向:电气自动化、新能源智慧发电、风电远程监控;强保华(1972-),男,河南南阳人,教授,博士,CCF会员,主要研究方向:大数据分析、图像处理;米路中(1980-),男,江西金溪人,高级工程师,主要研究方向:风电大数据、人工智能;彭博(1990-),男,河北沙河人,工程师,主要研究方向:开源情报、大数据应用;唐成华(1974-),男,湖北黄冈人,教授,博士,主要研究方向:网络与信息安全、大数据处理与挖掘;李宝莲(1972-),女,河北石家庄人,高级工程师,硕士,主要研究方向:软件可靠性设计、大数据分析。
基金资助:
国家自然科学基金资助项目（61762025，62062028）；广西重点研发计划项目（AB18126053，AB18126063，AD18281002）；国家能源科技环保集团股份有限公司资助项目（IKY.2019.0002）；广西自然科学基金资助项目（2017GXNSFAA198226，2019GXNSFDA185007，2019GXNSFDA185006，2018GXNSFAA294058）；广西科技重大专项（AA18118031，AA18242028）；中电科54所发展基金资助项目（SXX18138X017）；桂林电子科技大学研究生教育创新项目（2019YCXS051，2020YCXS052）；广西图像图形与智能处理重点实验室基金资助项目（GIIP201603，GIIP1806）。

Abstract

Abstract: To solve the imbalance problem of wind turbine dataset, a Borderline Synthetic Minority Oversampling Technique-Sequence (BSMOTE-Sequence) sampling algorithm was proposed. In the algorithm, when synthesizing new samples, the space and time characteristics were considered comprehensively, and the new samples were cleaned, so as to effectively reduce the generation of noise points. Firstly, the minority class samples were divided into security class samples, boundary class samples and noise class samples according to the class proportion of the nearest neighbor samples of each minority class sample. Secondly, for each boundary class sample, the minority class sample set with the closest spatial distance and time span was selected, the new samples were synthesized by linear interpolation method, and the noise class samples and the overlapping samples between classes were filtered out. Finally, Support Vector Machine (SVM), Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) were used as the fault detection models of wind turbine gear box, and F1-Score, Area Under Curve (AUC) and G-mean were used as performance evaluation indices of the models, and the proposed algorithm was compared with other sampling algorithms on real wind turbine datasets. Experimental results show that, compared with those of the existing algorithms, the classification effect of the samples generated by BSMOTE-Sequence algorithm is better with an average increase of 3% in F1-Score, AUC and G-mean of the detection models. The proposed algorithm can be effectively applicable to the field of wind turbine fault detection where the data with sequential rule is imbalanced.

Key words: wind turbine fault detection, imbalanced data, sequential characteristic, sampling algorithm, overlapping sample between classes

摘要： 针对风机数据集的不平衡问题，提出了一种BSMOTE-Sequence采样算法，在合成新样本时综合考虑空间和时间特征，并对新样本进行清洗，从而有效减少噪声点的生成。首先，根据每个少数类样本的近邻样本的类别比例，将少数类样本划分为安全类样本、边界类样本和噪声类样本。然后，对每个边界类样本都遴选出空间距离、时间跨度最接近的少数类样本集，利用线性插值法合成新样本，并过滤掉噪声类样本以及类间重叠样本。最后，以支持向量机（SVM）、卷积神经网络（CNN）、长短期记忆（LSTM）人工神经网络作为风机齿轮箱故障检测模型，F1-Score、曲线下面积（AUC）和G-mean作为模型性能评价指标，在真实风机数据集上把所提算法与常用的多种采样算法进行对比，实验结果表明：相比已有算法，BSMOTE-Sequence算法所生成样本的分类效果更好，使得检测模型的F1-Score、AUC和G-mean平均提高了3%，该算法能有效地适用于数据具有时序规律且不平衡的风机故障检测领域。

关键词: 风机故障检测, 不均衡数据, 时序特征, 采样算法, 类间重叠样本

CLC Number:

TP183

YANG Xian, ZHAO Jisheng, QIANG Baohua, MI Luzhong, PENG Bo, TANG Chenghua, LI Baolian. Wind turbine fault sampling algorithm based on improved BSMOTE and sequential characteristics[J]. Journal of Computer Applications, 2021, 41(6): 1673-1678.

杨鲜, 赵计生, 强保华, 米路中, 彭博, 唐成华, 李宝莲. 基于改进的BSMOTE和时序特征的风机故障采样算法[J]. 计算机应用, 2021, 41(6): 1673-1678.

References

[1] 王桂兰, 赵洪山, 米增强. XGBoost算法在风机主轴承故障预测中的应用[J]. 电力自动化设备, 2019, 39(1):73-77, 83.(WANG G L,ZHAO H S,MI Z Q. Application of XGBoost algorithm in prediction of wind motor main bearing fault[J]. Electric Automation Equipment,2019,39(1):73-77,83.)
[2] SOH W W,YUSUF R M. Predicting credit card fraud on a imbalanced data[J]. International Journal of Data Science and Advanced Analytics,2019,1(1):12-17.
[3] 林泳昌, 朱晓姝. 一种基于SMOTE的不均衡样本KNN分类方法[J]. 广西科学, 2020, 27(3):276-283.(LIN Y C,ZHU X S. A SMOTE based KNN classification method for unbalanced samples[J]. Guangxi Sciences,2020,27(3):276-283.)
[4] CHAWLA N V,BOWYER K W,HALL L O,et al. SMOTE:synthetic minority over-sampling technique[J]. Journal of Artificial Intelligence Research,2002,16:321-357.
[5] HAN H,WANG W,MAO B. Borderline-SMOTE:a new oversampling method in imbalanced data sets learning[C]//Proceedings of the 2005 International Conference on Intelligent Computing,LNCS 3644. Berlin:Springer,2005:878-887.
[6] BUNKHUMPORNPAT C, SINAPIROMSARAN K, LURSINSAP C. Safe-level-SMOTE:safe-level-synthetic minority over-sampling technique for handling the class imbalanced problem[C]//Proceedings of the 2009 Pacific-Asia Conference on Knowledge Discovery and Data Mining,LNCS 5476. Berlin:Springer,2009:475-482.
[7] 刘余霞, 刘三民, 刘涛, 等. 一种新的过采样算法DB_SMOTE[J]. 计算机工程与应用, 2014, 50(6):92-95.(LIU Y X,LIU S M, LIU T,et al. A new oversampling algorithm DB_SMOTE[J]. Computer Engineering and Applications,2014,50(6):92-95.)
[8] 陈睿, 张亮, 杨静, 等. 基于BSMOTE和逆转欠抽样的不均衡数据分类算法[J]. 计算机应用研究, 2014, 31(11):3299-3303. (CHEN R,ZHANG L,YANG J,et al. Classification algorithm for imbalanced data sets based on combination of BSMOTE and inverse under sampling[J]. Application Research of Computers,2014,31(11):3299-3303.)
[9] DEVI D,BISWAS S K,PURKAYASTHA B. Redundancy-driven modified Tomek-link based undersampling:a solution to class imbalance[J]. Pattern Recognition Letters,2017,93:3-12.
[10] GEORGIOS D,FERNANDO B,FELIX L. Improving imbalanced learning through a heuristic oversampling method based on k-means and SMOTE[J]. Information Sciences, 2018, 465:1-20.
[11] 夏英, 李刘杰, 张旭, 等. 基于层次聚类的不平衡数据加权过采样方法[J]. 计算机科学, 2019, 46(4):22-27.(XIA Y,LI L J, ZHANG X, et al. Weighted oversampling method based on hierarchical clustering for unbalanced data[J]. Computer Science,2019,46(4):22-27.)
[12] 李克文,林亚林,杨耀忠. 一种改进的基于欧氏距离的SDRSMOTE算法[J]. 计算机工程与科学, 2019, 41(11):2063-2070.(LI K W,LIN Y L,YANG Y Z. An improved SDRSMOTE algorithm based on Euclidean distance[J]. Computer Engineering and Science,2019,41(11):2063-2070.)
[13] 魏力, 张育平. 一种改进型的不平衡数据欠采样算法[J]. 小型微型计算机系统, 2019, 40(5):1094-1098.(WEI L,ZHANG Y P. Improved under-sampling algorithm for imbalanced data[J]. Journal of Chinese Computer Systems,2019,40(5):1094-1098.)
[14] 曹渝昆, 巢俊乙, 王晓飞. 基于LSTM神经网络的风机齿轮带断裂故障预测[J]. 电气自动化, 2019, 41(4):92-95.(CAO Y K, CHAO J Y,WANG X F. Prediction of wind turbine gear belt breakage based on the LSTM neural network[J]. Electrical Automation,2019,41(4):92-95.)
[15] 李铭璐. 基于深度学习的风机叶片覆冰故障检测方法研究[D]. 武汉:华中科技大学, 2019:41-45.(LI M L. Study on failure detection methods of wind turbine icing event based on deep learning[D]. Wuhan:Huazhong University of Technology, 2019:41-45.)
[16] 余达. 基于深度学习的风力发电系统故障在线诊断研究[D]. 广州:华南理工大学, 2018:39-43.(YU D. Online fault diagnosis of wind power systems using deep learning algorithms[D]. Guangzhou:South China University of Technology, 2018:39-43.)
[17] 葛阳鸣. 基于集成学习的短期风力发电功率预测研究[D]. 南京:南京邮电大学, 2019:26-34.(GE Y M. Research on power prediction of short-term wind power generation based on integrated learning[D]. Nanjing:Nanjing University of Posts and Telecommunications,2019:26-34.)
[18] FOTOUHI S,ASADI S,KATTAN M W. A comprehensive data level analysis for cancer diagnosis on imbalanced data[J]. Journal of Biomedical Informatics,2019,90:Article No. 103089.
[19] 张永清, 卢荣钊, 乔少杰, 等. 一种基于样本空间的类别不平衡数据采样方法[J/OL]. 自动化学报.[2020-07-22]. https://doi.org/10.16383/j.aas.c200034.(ZHANG Y Q, LU R Z,QIAO S J, et al. A class-imbalanced data sampling method based on sample space[J/OL]. Journal of Automation.[2020-07-22]. https://doi.org/10.16383/j.aas.c200034.)
[20] 宋玲玲, 王时绘, 杨超, 等. 改进的XGBoost在不平衡数据处理中的应用研究[J]. 计算机科学, 2020, 47(6):98-103.(SONG L L,WANG S H,YANG C,et al. Application research of improved XGBoost in unbalanced data processing[J]. Computer Science, 2020,47(6):98-103.)

Wind turbine fault sampling algorithm based on improved BSMOTE and sequential characteristics

基于改进的BSMOTE和时序特征的风机故障采样算法

PDF

Knowledge

Abstract

Cite this article

share this article

References

Related Articles 15

Recommended Articles

Metrics

[1]	XIAO Zhenyuan, WANG Yihan, LUO Jianqiao, XIONG Ying, LI Bailin. RefineDet based on subsection weighted loss function [J]. Journal of Computer Applications, 2021, 41(7): 1928-1932.
[2]	CUI Xin, XU Hua, SU Chen. Over-sampling algorithm for imbalanced datasets [J]. Journal of Computer Applications, 2020, 40(6): 1662-1667.
[3]	SU Junning, YE Dongyi. Under-sampling method based on sample density peaks for imbalanced data [J]. Journal of Computer Applications, 2020, 40(1): 83-89.
[4]	ZHANG Zongtang, CHEN Zhe, DAI Weiguo. Over sampling ensemble algorithm based on margin theory [J]. Journal of Computer Applications, 2019, 39(5): 1364-1367.
[5]	WANG Wei, XIE Yaobin, YIN Qing. Decision tree improvement method for imbalanced data [J]. Journal of Computer Applications, 2019, 39(3): 623-628.
[6]	WANG Li, CHEN Hongmei, WANG Shengwu. NIBoost: new imbalanced dataset classification method based on cost sensitive ensemble learning [J]. Journal of Computer Applications, 2019, 39(3): 629-633.
[7]	FU Zhongwang, XIAO Rong, YU Xiao, GU Yi. Impact of regression algorithms on performance of defect number prediction model [J]. Journal of Computer Applications, 2018, 38(3): 824-828.
[8]	YAN Binghao, HAN Guodong, HUANG Yajing, WANG Xiaolong. New traffic classification method for imbalanced network data [J]. Journal of Computer Applications, 2018, 38(1): 20-25.
[9]	WANG Lin, GUO Nana. Imbalanced telecom customer data classification method based on dissimilarity [J]. Journal of Computer Applications, 2017, 37(4): 1032-1037.
[10]	CHENG Lingfang, YANG Tianpeng, CHEN Lifei. Soft subspace clustering algorithm for imbalanced data [J]. Journal of Computer Applications, 2017, 37(10): 2952-2957.
[11]	MAO Wentao, WANG Jinwan, HE Ling, YUAN Peiyan. Hybrid sampling extreme learning machine for sequential imbalanced data [J]. Journal of Computer Applications, 2015, 35(8): 2221-2226.
[12]	ZHAO Yu, SHAO Bilin, BIAN Genqing, SONG Dan. Prediction of retweeting behavior for imbalanced dataset in microblogs [J]. Journal of Computer Applications, 2015, 35(7): 1959-1964.
[13]	WANG Jinwan, MAO Wentao, HE Ling, WANG Liyun. Weighted online sequential extreme learning machine based on imbalanced sample-reconstruction [J]. Journal of Computer Applications, 2015, 35(6): 1605-1610.
[14]	ZENG Xiaohui SHI Yibing LIAN Yi. Improved partial hierarchical resampling algorithm for particle filtering [J]. Journal of Computer Applications, 2014, 34(12): 3656-3659.
[15]	YANG Ting MENG Xiangru WEN Xiangxi WU Wen. Optimal hyperplane modification of support vector machine based on Fisher within-class scatter [J]. Journal of Computer Applications, 2013, 33(09): 2553-2556.