摘要
准确地评估电厂设备健康状态,对电厂安全稳定生产、提高设备运行安全性具有十分重要的意义;针对当前电厂设备健康评估方法存在预测精度不高的问题,提出了一种基于集成深度随机森林算法的智能电厂设备健康评估方法;详细介绍电厂设备健康评估系统结构,且分析了健康评估数据结构与影响因素;将设备评估分为6类不同的层级,使得设备健康状态分析更方便;结合深度学习与集成学习技术,提出了集成深度随机森林算法;通过仿真实验分析验证了提出方法的有效性;结果表明,所提方法对电厂设备健康评估准确度达到97%,与其他评估方法相比,文章提出的算法具有最高的健康评估准确度。
To accurately assess the health status of power plant equipment,it is of great significance to ensure the safe and stable production of power plants and improve the safety of equipment operation.Aimed at low prediction accuracy in current power plant equipment health assessment methods,an intelligent power plant equipment health assessment method based on the integrated deep random forest algorithm is proposed.Firstly,the power plant equipment health assessment system structure is introduced in detail,and the health assessment data structure and influencing factors are analyzed.Secondly,the equipment evaluation is divided into six different levels,which makes the equipment health analysis more convenient.Then,combined with deep learning and integrated learning technology,an integrated deep random forest algorithm is proposed.Finally,simulation experiments verify the effectiveness of the proposed method.The results show that the evaluation model accuracy of the proposed method can reach up to 97%,and the proposed algorithm has the highest accuracy in health assessment compared with other evaluation methods.
作者
庄保乾
韩路
李晓虎
高社民
刘少阳
ZHUANG Baoqian;HAN Lu;LI Xiaohu;GAO Shemin;LIU Shaoyang(Xinjiang Zhundong TBEA TBEA Energy Co.,Ltd.,Changji 831700,China)
出处
《计算机测量与控制》
2024年第8期322-328,共7页
Computer Measurement &Control
基金
新疆准东特变能源有限责任公司北一智慧电厂项目(TBEA-TCNY-ZTJG(2021)-GCFW-2021-003-01)。
关键词
设备健康评估
深度随机森林
集成学习
集成深度森林
equipment health assessment
deep random forest
integrated learning
integrated deep forest
