首页> 外文期刊>Electric Power Components and Systems >Normal Behavior Models for the Condition Assessment of Wind Turbine Generator Systems
【24h】

Normal Behavior Models for the Condition Assessment of Wind Turbine Generator Systems

机译:风力发电机系统状态评估的正常行为模型

获取原文
获取原文并翻译 | 示例
           

摘要

This article uses normal behavior models to present an integrated approach for condition assessment of wind turbine generator systems. Monitoring parameters selected from the supervisory control and data acquisition systems of wind farms are used to establish an assessment index system. Health degree is defined to quantify indices. A neural network is used to establish normal behavior models for the parameters closely related to the natural environment. Estimation errors of the neural network models follow a normal distribution. Thus, health degrees can be calculated based on the probability density function of normal distribution. For other monitoring parameters, normal behavior models are developed based on the Parzen estimation, a common non-parametric estimation method. Health degrees are calculated based on the fitted probability density functions. Fuzzy synthetic evaluation is employed, and an assessment process is designed. Finally, the proposed method is performed on actual 1.5-MW wind turbine generator system. The results of condition assessment of two cases are compared with those obtained using the traditional method. Results show that the proposed method is more effective in assessing wind turbine generator systems than the traditional method.
机译:本文使用正常行为模型来提出用于风力发电机系统状态评估的集成方法。从风电场的监督控制和数据采集系统中选择监测参数,以建立评估指标体系。定义健康度以量化指标。神经网络用于建立与自然环境密切相关的参数的正常行为模型。神经网络模型的估计误差服从正态分布。因此,可以基于正态分布的概率密度函数来计算健康度。对于其他监视参数,将基于Parzen估计(一种常见的非参数估计方法)开发正常行为模型。健康度是根据拟合的概率密度函数计算的。采用模糊综合评价,设计了评价过程。最后,所提出的方法是在实际的1.5兆瓦风力发电机系统上执行的。将两种情况的状况评估结果与传统方法得出的结果进行比较。结果表明,该方法在评估风力发电机系统方面比传统方法更为有效。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号