基于Apriori算法和卷积神经网络的风电机组故障诊断模型

Fault Diagnosis Model of Wind Turbine Based on Apriori and Convolutional Neural Network

随着风能设备的规模在各国不断增大,风电机组的运行与维护成为研究热点.针对风电机组的故障诊断问题,本文提出了一种基于Apriori算法和卷积神经网络(convolutional neural networks,CNN)的故障诊断模型.该模型将k均值聚类(k-means)与Apriori算法结合进行特征选取并进行验证,以降低对专家经验的依赖性;以卷积神经网络构建故障诊断模型.以真实风电场SCADA(supervisory control and data acquisition)数据进行实验,通过准确率、精准率等指标将本文模型与其他模型进行对比.结果表明,与其他模型相比,本文模型的准确率更高,整体效果更好.

With the increasing scale of wind energy equipment in various countries,the operation and maintenance of wind turbine has become a research hotspot.In this article,we propose a fault diagnosis model based on Apriori algorithm and convolutional neural network(CNN)to address the problem of fault diagnosis of wind turbine.This model combines k-means and Apriori algorithm for feature selection and verification so as to reduce the dependence on expert experience;the fault diagnosis model is constructed by CNN.The experiment was conducted with supervisory control and data acquisition(SCADA)data of real wind farm,and our proposed model was compared with other models including accuracy,accuracy and other indicators.The results show that compared with other models,the accuracy of this model is higher and the overall effect is better.