Search

The magnet-less switched reluctance motor (SRM) speed-torque characteristics are ideally suited for traction motor drive characteristics and its advantage to minimize the overall cost of on-road EVs. The main drawbacks are torque and flux ripple, which have produced high in low-speed operation. However, the emerging direct torque control (DTC) operated magnitude flux and torque estimation with voltage vectors (VVs) gives high torque ripples due to the selection of effective switching states and sector partition accuracy. On the other hand, the existing model predictive control (MPC) with multiple objective and optimization weighting factors produces high torque ripples due to the system dynamics and constraints. Therefore, existing DTC and MPC can result in high torque ripples. This paper proposed a finite set (FS)-MPC with a single cost function objective without weighting factor: the predicted torque considered to evaluate VVs to minimize the ripples further. The selected optimal VV minimizes the SRM drive torque and flux ripples in steady and dynamic state behaviour. The classical DTC and proposed model were developed, and simulation results were verified using MATLAB/Simulink. The proposed model operated in SRM drives experimental results to prove the effective minimization of torque and flux ripples compared to the existing DTC. [ABSTRACT FROM AUTHOR]

Subset feature selection for microarray data is intended to reduce the number of irrelevant features in order to extract significant features from the dataset. Simultaneously, choosing the appropriate features from the high-dimensional dataset may enhance the learning algorithm's classification precision. Relief algorithms and their variants are successful attribute estimators. MultiSURF is the latest descendant of relief-based approaches; it estimates the feature by preserving target instance-centric neighborhood determination. However, the large number of redundant features can lead to the degraded performance of MultiSURF's ability to select relevant features from the datasets. In order to select an informative feature from extremely redundant data, we suggest an innovative feature weighting algorithm called boundary margin relief (BMR). BMR's main concept is to predict the feature weights through the measurement of the local hyperplane, which is typically used in I-Relief techniques. The weights of the features in the proposed methods are very robust in terms of removing redundant features. To show the efficiency of the method, comprehensive studies involving classification tests were conducted on benchmark microarray datasets by combining the suggested technique with conventional classifiers, including support vector machine, k-nearest neighbor, and Naive Bayes. Extensive studies have shown that the proposed method has three notable features: (1) elevated classification accuracy, (2) outstanding redundant robustness, and (3) good stability about different classification algorithms. [ABSTRACT FROM AUTHOR]