A Novel Combined Model for Condition Monitoring of Steam Turbine-generator Sets
ID:16 Submission ID:16 View Protection:ATTENDEE Updated Time:2024-10-23 10:39:39 Hits:36 Oral Presentation

Start Time:2024-11-01 14:00 (Asia/Shanghai)

Duration:20min

Session:[P4] Parallel Session 4 » [P4-1] Parallel Session 4(November 1 PM)

No files

Abstract
状态监测是火力发电中不可或缺的一部分,对潜在故障提供预警,预防重大事故的发生,从而保证生产安全和经济效益。分布式控制系统(DCS)在火电厂中起着举足轻重的作用,充当连接各种设备和系统的中枢神经系统,实现从数据采集、监测到控制的全面集成,保障电厂的高效安全运行。汽轮发电机是火力发电中的关键部件,监测其运行状态是一项至关重要的任务。本研究提出了一种BiGRU-ViT模型,该模型结合了双向门控循环单元(BiGRU)和视觉转换器(ViT)。BiGRU从时间序列的角度提取局部特征,由于其双向结构,捕获双向上下文信息。另一方面,ViT提取空间特征,利用自注意力机制来捕获全局信息。这两个模型的集成使得预测目标参数有了更广阔的视角。利用DCS实际数据进行的测试表明,BiGRU-ViT模型能够提供潜在故障的早期预警,验证了模型的有效性,并表明其在火电厂汽轮发电机状态监测中的适用性。
 
Keywords
Distributed Control System(DCS); Condition monitoring; Steam turbine generator set ; Bidirectional Gated Recurrent Unit (BiGRU); Vision Transformer (ViT).
Speaker
ChenBohua
Master North China Electric Power University

Submission Author
ChenBohua North China Electric Power University
BingHankun North China Electric Power University
YaoQingtao North China Electric Power University
XiangLing North China Electric Power University
HuAijun North China Electric Power University
Comment submit
Verification code Change another
All comments

Important Dates

15th August 2024   31st August 2024- Manuscript Submission

15th September 2024 - Acceptance Notification

1st October 2024 - Camera Ready Submission

1st October 2024  – Early Bird Registration

 

Contact Us

Website:

https://icsmd2024.aconf.org/

Email:
icsmd2024@163.com