融合数字孪生的风电机组故障检测ASL-CatBoost方法
ASL-CatBoost Method for Wind Turbine Fault Detection Integrated with Digital Twin
梁宏涛 1孔翎超 1刘国柱 1董文轩 1刘香怡1
作者信息
- 1. 青岛科技大学 信息科学技术学院,山东 青岛 266061
- 折叠
摘要
针对当前风电场状态监控可视化程度低、运维实时性不足的问题,基于数字孪生五维模型概念,构建风电场数字孪生五维模型框架;针对传统算法故障检测能力不足、风机故障数据集存在正负样本不平衡的问题,提出使用改进的ASL-CatBoost算法实现风机故障状态的精准检测.以数字孪生平台为基础,结合MATLAB/Simulink建立叶片质量不平衡状态下的双馈风力发电机仿真数学模型,模拟多种风速、温度条件下不同原因导致的风机故障状况数据,辅助故障检测算法进行训练,增强算法的泛化能力;设计实现风电场数字孪生运维管控一体化平台案例,在实时数据的驱动下,实现风电机组运行状态的实时监视与精准管控,验证所提框架和改进算法的可行性.
Abstract
In view of the low visibility of the current wind farm status monitoring and insufficient real-time operation and maintenance,based on the concept of digital twin five-dimensional model,the framework of wind farm digital twin five-dimensional model is constructed.Aiming at the insufficient fault detection capability of traditional algorithms and unbalanced positive and negative samples in fan fault data set,the improved ASL-CatBoost algorithm is proposed to achieve the accurate detection of fan fault status.Based on the digital twinning platform,combined with MATLAB/Simulink,the simulation mathematical model of doubly-fed wind turbine under the condition of blade mass imbalance is established,and the auxiliary fault detection algorithm is used to simulate the data of wind turbine fault conditions caused by different reasons under various wind speeds and temperatures to train and enhance the generalization ability of the algorithm.A case of the integrated platform of wind farm digital twinning operation,maintenance and control is designed.Driven by real-time data,the real-time monitoring and accurate control of wind turbine operation status is realized,and the feasibility of the proposed framework and improved algorithm is verified.
关键词
数字孪生/机器学习/风力发电/故障检测/虚拟仿真Key words
digital twin/machine learning/wind power generation/fault detection/virtual simulation引用本文复制引用
基金项目
国家自然科学基金(61973180)
国家自然科学基金(6217072142)
山东省产教融合研究生联合培养示范基地项目(2020-19)
出版年
2024
NETL
NSTL
万方数据