摘要
文章提出了一种基于混合模型的水力发电机组(HGU)振动趋势预测系统,以提高预测的准确性和稳定性。模型集成了自适应经验小波变换(AEWT)、样本熵(SE)、萤火虫优化(GSO)、核极限学习机(KELM)和多目标萤火虫算法(MOSSA)。通过对二滩水电站的实际数据进行验证,结果表明所提出的模型在准确性和效率上均优于传统方法。此研究为水电站的状态趋势预测提供了一种新的有效方法。
The article proposes a hybrid model-based vibration trend prediction system for hydroelectric generating units(HGUs)to improve the accuracy and stability of predictions.The model integrates Adaptive Empirical Wavelet Transform(AEWT),Sample Entropy(SE),Glowworm Swarm Optimization(GSO),Kernel Extreme Learning Machine(KELM),and Multi Objective Firefly Algorithm(MOSSA).By verifying the actual data of Ertan Hydropower Station,the results show that the proposed model is superior to traditional methods in terms of accuracy and efficiency.This study provides a new and effective method for predicting the state trend of hydropower stations.
作者
许细忠
XU Xizhong(Guangdong Hydropower Planning&Design Institute Co.,Ltd.,Guangzhou 510000,China)
出处
《云南水力发电》
2025年第3期195-198,206,共5页
Yunnan Water Power
关键词
水电站
水力发电机组
数据平台
状态趋势预测系统
hydropower station
hydropower generation units
data platform
state trend prediction system
