本文已被：浏览 1215次 下载 420次
投稿时间：2020-09-02
投稿时间：2020-09-02
中文摘要: 齿轮箱是风电机组运行的关键设备。针对风电机组齿轮箱故障发生频繁、运行维护成本高等问题，提出了一种基于数据采集与监控（SCADA）系统异常数据清洗和动态神经网络的建模方法，对风机齿轮箱油池温度进行了建模。随后采用统计过程控制方法分析残差，根据残差分布特征计算阈值上下限，实现了齿轮箱油池温度异常状态预警。最后以双馈式风力发电机组为研究对象进行建模分析并给出实例，验证了该模型对齿轮箱油池温度预警的实用性和有效性。
Abstract:Gearbox is the key equipment for wind turbine operation.Aiming at the frequent occurrence of wind turbine gearbox failures and high operation and maintenance costs,a method based on supervisory control and data acquisition(SCADA) system abnormal data cleaning and dynamic neural network modeling is proposed to measure the temperature of the wind turbine gearbox oil pool.Subsequently,the statistical process control method is used to analyze the residuals,and the upper and lower thresholds are calculated according to the distribution characteristics of the residuals,so as to realize the early warning of the abnormal temperature of the gearbox oil sump.Finally,a modeling analysis of the doubly-fed wind turbine is the research object and an example is given,which verifies the practicality and effectiveness of the model for the gearbox oil sump temperature warning.
keywords: wind turbine gearbox oil temperature supervisory control and data acquisition system data cleaning dynamic neural network statistical process control
文章编号：20206006 中图分类号：TK81 文献标志码：
基金项目:
| 作者 | 单位 | |
| 陈映琼 | 国电浙江北仑第一发电有限公司 | |
| 顾军民 | 国电宁波风电开发有限公司 | |
| 姜胜 | 国网湖北省电力有限公司 | |
| 陈思函 | 华北电力大学 | 874439741@qq.com |
引用文本：
陈映琼,顾军民,姜胜,等.基于数据清洗和动态神经网络的风电机组齿轮箱油温预警方法研究[J].上海电力大学学报,2020,36(6):547-552.
CHEN Yingqiong,GU Junmin,JIANG Sheng,et al.Research on Early Warning Method of Gearbox Oil Temperature of Wind Turbine Based on Data Cleaning and Dynamic Neural Network[J].Journal of Shanghai University of Electric Power,2020,36(6):547-552.
陈映琼,顾军民,姜胜,等.基于数据清洗和动态神经网络的风电机组齿轮箱油温预警方法研究[J].上海电力大学学报,2020,36(6):547-552.
CHEN Yingqiong,GU Junmin,JIANG Sheng,et al.Research on Early Warning Method of Gearbox Oil Temperature of Wind Turbine Based on Data Cleaning and Dynamic Neural Network[J].Journal of Shanghai University of Electric Power,2020,36(6):547-552.