风电场主设备预警诊断系统设计与开发

Abstract
Figure/Table
References
Related Citation (15)

Download: PDF (1878 KB) HTML (1 KB)
Export: BibTeX | EndNote (RIS)

Abstract Considering the harsh environment of wind farms, the difficulty of early fault monitoring and high unit failure rate, a wind farm main equipment early warning diagnosis method based on multi-parameter modeling and vibration signal spectrum analysis is proposed. First, the structured and unstructured data from the wind farm online monitoring system, point inspection system, monitoring system and other systems are collected, and the multi-source data are pre-processed and effectively fused according to the equipment characteristics and application system requirements. Then an early warning model is established based on multiple parameters, and the trend analysis of the equipment status data is realized based on the output of the early warning model and the vibration signal spectrum analysis. Finally, a system is designed and developed to display equipment warning information and fault diagnosis results with operation and maintenance decision suggestions. The wind farm main equipment early warning diagnosis system provides a new idea for intelligent online monitoring of wind turbines, which will effectively realize early warning of equipment failure, reduce the failure rate of equipment, and improve the efficiency of equipment maintenance personnel.

Key words： wind farm wind power generation multi-parameter modeling early warning diagnosis online monitoring

Received: 28 February 2023

	Service

	E-mail this article
	Add to my bookshelf
	Add to citation manager
	E-mail Alert
	RSS
	Articles by authors
	ZHANG Junjun
	CHEN Guo
	LU Yingqiang
	QIAO Supeng
	HU Zhongzhong

Cite this article:

ZHANG Junjun,CHEN Guo,LU Yingqiang等. Design and development of wind farm main equipment early warning diagnosis system[J]. Electrical Engineering, 2023, 24(5): 52-57.

URL:

http://dqjs.cesmedia.cn/EN/Y2023/V24/I5/52

[1] 彭跃辉. 双碳目标下新能源合理利用率形势分析及政策建议[J]. 华北电力大学学报(社会科学版), 2022(6): 42-50.
[2] 高安娜. “双碳”目标驱动下的中国清洁能源发展优化路径研究[D]. 镇江: 江苏大学, 2021.
[3] 庄甦. 浅析风力发电设备运维存在的问题与改进措施[J]. 中国设备工程, 2021(3): 38-40.
[4] 朱建华, 何卓林, 闫伟军, 等. 风电场自动电压控制中风机和静止无功发生器的无功分配研究[J]. 电气技术, 2022, 23(4): 31-36.
[5] 和萍, 文福拴, 薛禹胜, 等. 风力发电对电力系统小干扰稳定性影响述评[J]. 电力系统及其自动化学报, 2014, 26(1): 1-7, 38.
[6] 缪海飞, 曹翔, 林青, 等. 电力监控系统实时DDoS攻击检测方法[J]. 电气技术, 2022, 23(2): 99-104.
[7] 胡晓彤, 李涛, 薛方勇. 浅析优化风电场运维管理提高经济效益的方法[J]. 电力系统装备, 2021(4): 120-121.
[8] 林京鹏, 胡小林, 索王军. 大数据在促进引战配合智能化发展中的应用[J]. 探测与控制学报, 2022, 44(3): 34-37.
[9] 杨童亮, 胡东, 唐超, 等. 基于SMA-VMD-GRU模型的变压器油中溶解气体含量预测[J]. 电工技术学报, 2023, 38(1): 117-130.
[10] 杨文广, 蒋东翔. 大型风力机组远程智能监测与诊断系统的研究与开发[J]. 中国工程科学, 2015, 17(3): 24-29.
[11] 陈艳艳, 尹少平, 王灵梅. 风电远程监测与诊断系统数据通信研究[J]. 华东电力, 2013, 41(1): 148-151.
[12] 辛卫东, 马志勇, 滕伟, 等. 振动监测技术在风电机组齿轮箱故障诊断中的应用[J]. 中国电力, 2012, 45(5): 77-80.
[13] 章敏. 基于SCADA系统的某风电场MW级风电机组快速故障诊断与控制策略优化[J]. 太阳能, 2021(9): 71-77.
[14] 武鑫. 基于数据驱动的风电机组关键部件监测预警技术研究[D]. 秦皇岛: 燕山大学, 2019.
[15] 朱余启, 陈汝昌, 戈本星, 等. 基于波形统计分析的频率振荡相关联机组快速识别技术[J]. 广东电力, 2021, 34(2): 54-60.
[16] 李娟. 基于Hadoop云平台的空间属性数据挖掘技术研究[J]. 南京理工大学学报, 2022, 46(4): 419-426.
[17] 高经纬, 马超, 苏鸿, 等. 基于改进机器学习算法的步态识别与预测研究[J]. 生物医学工程学杂志, 2022, 39(1): 103-111.
[18] 王宇. 基于非线性状态估计的长时延丢包网络故障检测算法[J]. 微电子学与计算机, 2019, 36(10): 91-95.
[19] 陈宗遥, 卜旭辉, 郭金丽. 基于神经网络的数据驱动互联电力系统负荷频率控制[J]. 电工技术学报, 2022, 37(21): 5451-5461.