In this study, a direct torque and flux control is described for a six-phase asymmetrical speed and voltage sensorless induction machine (IM) drive, based on non-linear backstepping control approach. First, the decoupled torque and flux controllers are developed based on Lyapunov theory, using the machine two axis equations in the stationary reference frame. In this control scheme, the actual stator voltages are determined from dc-link voltage using the switching pattern of the space vector pulse-width modulation inverter. Then, for a given motor load torque and rotor speed, a so-called fast search method is used to maximise the motor efficiency. According to this method, the rotor reference flux is decreased in the small steps, until the average of real input power to the motor reaches to a minimum value. In addition, a model reference adaptive system-based observer is employed for online estimating of the rotor speed. Finally, the feasibility of the proposed control scheme is verified by simulation and experimental results.

This article proposes a swarm intelligence ensemble deep transfer learning (named SI-EDTL) for multiple vehicle detection in unmanned aerial vehicle (UAV) images.This method is based on Faster regional-based convolutional neural networks (Faster R-CNN), in which, a set of region proposals are extracted using region proposal network (RPN), and then, CNN is used to mine highly descriptive features of these windows to classify regions. We use three Faster R-CNNs as feature extractors (InceptionV3, ResNet50, and GoogLeNet) that have already pre-trained on Ima-geNet data, combined with five transfer classifiers (KNN, SVM, MLP, C4.5 Decision Tree, and Naïve Bayes). As a result, 15 different base learners are trained through deep transfer learning on a UAV dataset to classify the region proposals into multiple vehicles (car, van, truck, and bus). We combine these 15 base learners through a weighted averaging aggregation into four vehicle classes or no vehicle (background). Hyperparameters of the ensemble model are tuned using whale optimization algorithm, to achieve the best trade-off between total accuracy, precision, and recall. The proposed SI-EDTL model has been successfully developed using parallel processing in MATLAB R2020b. Experimental results on AU-AIR dataset of UAV images demonstrate the superiority of the SI-EDTL model against existing techniques.

No abstract

Summary Benefits of device to device (D2D) underlying massive multi‐input multi‐output (MIMO) cellular networks are noticeable in the fifth generation (5G) of mobile broadband networks. However, the interference of such coexistence from massive MIMO and D2D, due to resource sharing between cellular users and D2D users, should be decreased. Because of this issue, the spectral efficiency of such networks will be reduced. The challenges of such networks are to control the transmit power of their users and to mitigate cellular‐to‐D2D and D2D‐to‐cellular interferences. In this paper, we introduce two techniques to enhance the performance of these systems. Since, we propose a linear receiver filter with a special structure in such coexistence network to increase intended signal and then to increase spectral efficiency. Also, in this research, to decrease the whole interference, by explaining power sets for cellular and D2D transmitter for various distance intervals, we apply an open loop power control approach in the uplink as a suboptimal solution. This solution is a closed‐form solution and is often more useful and take lower time than the optimal solution. Also, we analyze spectral efficiency for the cellular uplink of such networks with the proposed frameworks. Numerical results approve that the two proposed techniques decrease the interferences. Simulation results demonstrate an enhancement in the cellular spectral efficiency.

No abstract

This paper proposes a robust second order sliding mode controller as maximum power point tracking (MPPT) technique in a photovoltaic (PV) boost dc-dc converter with applications to stand-alone systems. The proposed method is independent respect to load type, robust against parametric uncertainties and disturbances. By Lyapunov theorem the asymptotic stability of the closed loop control system is proven. The proposed second order sliding mode controller is simulated with Matlab software and experimental set up in presence of sinusoidal disturbances on output voltage.

No abstract

No abstract