摘要
为实现火电厂发电设备的智能故障诊断与预测,提出了一种基于LSTM和CNN相结合的深度学习方法。该模型通过LSTM模块建模时间序列,并使用CNN模块提取空间局部特征,实现了故障模式的识别。结果表明,所设计的模型可以提高故障诊断的平均精度,并且提供了充足的预警时间,大大提高了火电厂发电装备的运行效率和安全性。
A deep learning method based on the combination of LSTM and CNN is proposed to achieve intelligent fault diagnosis and prediction of power generation equipment in thermal power plants.This model models time series using LSTM modules and extracts spatial local features using CNN modules,achieving fault pattern recognition.The results show that the designed model can improve the average accuracy of fault diagnosis and provide sufficient warning time,greatly improving the operational efficiency and safety of power generation equipment in thermal power plants.
作者
曾阳
张莉
李国朋
ZENG Yang;ZHANG Li;LI Guopeng(Zhaolou Comprehensive Utilization Power Plant,Yancoal Heze Energy Chemical Co.,Ltd.,Heze,Shandong 274700,China;Shandong Huaju Energy Co.,Ltd.,Jining,Shandong 273500,China)
出处
《自动化应用》
2024年第6期102-104,共3页
Automation Application
关键词
深度学习
故障诊断
发电设备
deep learning
fault diagnosis
power generation equipment