With the proliferation of electric vehicles (EVs), the supportingfacilities and infrastructure become new components inconjunction with conventional electrical appliances. These novelappliances, e.g., charging piles and energy storage devices, bringnew features as well as challenges to the existing power grid. Toenhance the accuracy of mechanical fault identification for on-loadtap changers (OLTCs) in smart grid with EVs, a feature selectionmethod for OLTC mechanical fault identification is proposed inthis paper. This method relies on the multi-feature fusion and thejoint application of the K-nearest neighbors algorithm (KNN) andthe improved whale optimization algorithm (IWOA). By multi-featurefusion, the high-dimensional set of time-domain and frequencydomaincharacteristics as well as energy and composite multi-scale permutation entropy can be constructed. As a result,the maximum correlation minimum redundancy (mRMR) principle can be used to screen the sensitive feature subsets.Finally, IWOA is used to optimize the sensitive feature subsets, and KNN is used to classify the different types of optimalfeature subsets. The experimental results show that the proposed method is at least 8% more accurate than the existingmethods. The high-accuracy nature of the proposed method can accelerate the promotion of EVs and the establishmentof intelligent transportation environments.
With the proliferation of electric vehicles (EVs), the supporting <br>facilities and infrastructure become new components in <br>conjunction with conventional electrical appliances. These novel <br>appliances, eg, charging piles and energy storage devices, bring <br>new features as well as challenges to the existing power grid . To <br>enhance the accuracy of mechanical fault identification for on-load <br>tap changers (OLTCs) in smart grid with EVs, a feature selection <br>method for OLTC mechanical fault identification is proposed in <br>this paper. This method relies on the multi-feature fusion and the <br>joint application of the K-nearest neighbors algorithm (KNN) and <br>the improved whale optimization algorithm (IWOA). By multi-feature<br>fusion, the high-dimensional set of time-domain and frequencydomain <br>characteristics as well as energy and composite multi-scale permutation entropy can be constructed. As a result, <br>the maximum correlation minimum redundancy (mRMR) principle can be used to screen the sensitive feature subsets. <br>Finally, IWOA is used to optimize the sensitive feature subsets, and KNN is used to classify the different types of optimal <br>feature subsets. The experimental results show that the proposed method is at least 8% more accurate than the existing <br>methods. The high -accuracy nature of the proposed method can accelerate the promotion of EVs and the establishment <br>of intelligent transportation environments.
正在翻译中..
With the thes of the spark of electric vehicles (EVs), the supporting<br>facilities and infrastructure es new components in<br>sane with sie eelectrical appliances. These novel<br>Appliances, e.g., charging piles and energy storage devices, bring<br>New features as well as challenges to the existing power grid. To<br>enhance the accuracy of the mon dy'm fault for on-load<br>Tap changers (OLTCs) in smart with grid EVs, a feature selection<br>method for OLTC mon dydd is proposed in<br>this paper. This method team on the multi-feature-fusion and the the<br>the joint application of the K-nearest neighbors (knN) and<br>The improved whale optimization algorithm (IWOA). By multi-feature<br>Fusion, the high-dimensional set of time-domain and frequencydomain<br>Features as well as energy and composite multi-scale pertati entropy can be sged. As a result,<br>The rheolyse lysau sr.resy (mRMR) principle be be used to screen the sensitive sensitive subsets.<br>Finally, IWOA is used to optimize the sensitive sensitive photos, and KNN is used to do the sic<br>feature subsets. The tha oedd sydd sydd sy'n at es 8% more tha ann an oedd<br>the methods. The high-dy-accuracy nature of the proposed method saccelerate the promotion of eVs and the establishment<br>of the intelligent transportation s.
正在翻译中..