基于PSO-XGBoost的风电叶片缺陷分类算法
DEFECT CLASSIFICATION ALGORITHM OF WIND TURBINE BLADES BASED ON PSO-XGBOOST
郑浩 1贾展飞 1周丽婷 2王晫1
作者信息
- 1. 沈阳工业大学信息科学与工程学院,沈阳 110870
- 2. 信华信技术股份有限公司,大连 116085
- 折叠
摘要
针对风电叶片缺陷回波信号分类效率低的问题,提出粒子群-极限梯度提升(PSO-XGBoost)算法.首先采用变分模态分解(VMD)结合模糊熵的方法对缺陷回波数据进行特征提取,建立XGBoost多分类模型,在此基础上采用PSO算法对XGBoost超参数进行寻优,建立PSO-XGBoost多分类模型.这种PSO、XGBoost相结合的算法可提高风电叶片缺陷的预测精度、减少缺陷分类的误差.通过仿真,对PSO-XGBoost、XGBoost及其他几种机器学习算法进行对比,结果表明PSO-XGBoost算法准确度最高,其缺陷分类准确率可达98%.由此可见,采用PSO-XGBoost算法可有效提高风电叶片缺陷分类的准确率.
Abstract
To tackle the issue of the low classification efficiency of defect echo signals of wind turbine blades,a particle swarm optimization and extreme gradient boosting algorithm(PSO-XGBoost)is proposed in this paper.Primarily,feature extraction of the defect echo data is applied via variation mode decomposition(VMD)combining with fuzzy entropy to establish XGBoost multiclassification model.Subsequently,XGBoost hyperparameters are optimized via PSO algorithm to establish a PSO-XGBoost multiclassification model.The algorithm of combining of PSO with XGBoost improves the prediction accuracy of wind power blade defects,and reduces the error of defect classification.The simulation results show that PSO-XGBoost algorithm has prediction accuracy by compared with XGBoost and other algorithms,the defects classification accuracy rate of PSO-XGBoost algorithm is up to 98%.Consequently,the PSO-XGBoost algorithm effectively enhances the accuracy of wind turbine blade defect classification.
关键词
风电叶片/粒子群/特征提取/缺陷分类Key words
wind turbine blades/particle swarm optimization/feature extraction/defect classification引用本文复制引用
基金项目
辽宁省教育厅项目(LFGD2019007)
辽宁省教育厅项目(LJKMZ20220478)
辽宁省高等学校产业技术研究院重大项目(201844016)
出版年
2024
NETL
NSTL
万方数据