我的订单 | 我的收藏 | 加入收藏 | 返回首页
暖通空调杂志社>期刊目次>2018年>第10期

基于ReliefF与mRMR耦合特征选择的多联机制冷剂充注量故障诊断

Refrigerant charge fault diagnosis for variable refrigerant flow system based on ReliefF and mRMR coupling feature selection

李正飞[1] 谭泽汉[2] 陈焕新[1] 刘江岩[1] 黄荣庚[1] 刘佳慧[1]
[1]华中科技大学 [2]空调设备及系统运行节能国家重点实验室

摘要:

针对制冷剂充注量故障,提出了一种结合ReliefFmRMR特征选择算法的故障诊断方法。首先,利用ReliefF算法计算出每个特征变量的权重系数W(A),剔除权重系数低于阈值的特征;然后,利用集成的mRMR算法选出与目标类别具有最大相关性且相互之间具有最小冗余性的特征子集;最后,利用特征提取后的变量建立BP神经网络模型进行故障诊断,并和单一特征选择算法的结果进行对比。结果表明:该方法较好地提高了多联机制冷剂充注量故障诊断模型的诊断精度和效率。

关键词:多联机空调系统,制冷剂充注量,故障诊断,ReliefF,最大相关最小冗余,神经网络

Abstract:

For the refrigerant charge fault, presents a fault detection and diagnosis method combined with ReliefF and mRMR feature selection algorithm. Firstly, calculates the weight coefficient W(A) of each feature variable by the ReliefF algorithm, and removes the features with weight coefficient lower than the threshold. Then, selects the features which have the max-relevance with the target class and min-redundancy with each other by the ensemble mRMR algorithm. Finally, develops a BP neural network model based on the newly selected variables to achieve fault detection and diagnosis, and compares the results with that of single feature selection algorithm. The result indicates that the new method can improve the accuracy and efficiency of the diagnostic model.

Keywords:variablerefrigerantflowairconditioningsystem,refrigerantcharge,faultdiagnosis,ReliefF,maximumrelevanceandminimumredundancy,neuralnetwork

    你还没注册?或者没有登录?这篇期刊要求至少是本站的注册会员才能阅读!

    如果你还没注册,请赶紧点此注册吧!

    如果你已经注册但还没登录,请赶紧点此登录吧!