Robust Power Designing of Supplementary Damping Controller in VSC HVDC System to Improve Energy Conversion Efficiency of Wind Turbine and Power System Stability

Because of low losses and voltage drop, fast control of power, limitless connection distance, and isolation issues, using high-voltage direct-current (HVDC) transmission system is recommended to transfer power in the power systems, including wind farms. This paper aims to propose a supplementary damping controller (SDC) based on the HVDC to improve not only power system dynamic stability but also energy conversion efficiency and torsional vibration damping in the wind power plants (WPPs). When the WPPs are working in power control mode, the active power is set to its reference value, which is extracted from power-speed curve. This paper shows that torsional oscillations associated with the poorly torsional modes can be affected by different operating regions of the power-speed curve of WPP. Therefore, it is essential to employ an SDC to have the optimum energy conversion efficiency in the wind turbine and the most dynamic stability margin in the power system. The SDC is designed using a fractional-order PID controller (FOPID) based on the multiobjective bat-genetic algorithm (MOBGA). The simulation results show that the proposed control strategy effectively works in minimizing the torsional and electromechanical oscillations in power system and optimizing the energy conversion efficiency in the wind turbine.

A New Multiface Target Detection Algorithm for Students in Class Based on Bayesian Optimized YOLOv3 Model

Deep learning theory is widely used in face recognition. Combined with the needs of classroom attendance and students’ learning status monitoring, this article analyzes the YOLO (You Only Look Once) face recognition algorithms based on regression method. Aiming at the problem of small target missing detection in the YOLOv3 network structure, an improved YOLOv3 algorithm based on Bayesian optimization is proposed. The algorithm uses deep separable convolution instead of conventional convolution to improve the Darknet-53 basic network, and it reduces the amount of calculation and parameters of the network. A multiscale feature pyramid is built, and an attention guidance module is designed to strengthen multiscale fusion, detecting different sizes of targets. The loss function is improved to solve the imbalance of positive and negative sample distribution and the imbalance between simple samples and difficult samples. The Bayesian function is adopted to optimize the classifier and improve the classification efficiency and accuracy, ensuring the accuracy of small target detection. Five groups of comparative experiments are carried out on public COCO and VOC2012 datasets and self-built datasets. The experimental results show that the proposed improved YOLOv3 model can effectively improve the detection accuracy of multiple faces and small targets. Compared with the traditional YOLOv3 model, the mean mAP of the target is improved by more than 1.2%.

Based on Knowledge Recognition and Using Binomial Distribution Function to Establish a Mathematical Model of Random Selection of Test Questions in the Test Bank

With the in-depth development of social reforms, the scientificization of enterprise online examinations has become more and more urgent and important. The key to realizing scientific examinations is the automation and rationalization of propositions. Therefore, the construction and realization of the test question bank is also more important. In the realization of the entire test question database, how to select satisfactory test questions randomly from a large number of test questions through the selection of test questions so that the average difficulty, discriminability, and reliability of the test are satisfactory? These requirements are also more important. Among them, random selection of questions is an important difficulty in the realization of the test question bank. In order to solve the difficulties of random selection of these test questions, the author combines the experience of constructing the test question bank and uses the discrete binomial distribution to draw conclusions. Random variables established the first mathematical model for topic selection. By determining the form of the test questions and the distribution of the difficulty of the test questions and then making it use a random function to select questions, this will achieve better results.

Regularized Multiframe Super-Resolution Image Reconstruction Using Linear and Nonlinear Filters

The primary goal of the multiframe super-resolution image reconstruction is to produce an image with a higher resolution by integrating information extracted from a set of corresponding images with low resolution, which is used in various fields. However, super-resolution image reconstruction approaches are typically affected by annoying restorative artifacts, including blurring, noise, and staircasing effect. Accordingly, it is always difficult to balance between smoothness and edge preservation. In this paper, we intend to enhance the efficiency of multiframe super-resolution image reconstruction in order to optimize both analysis and human interpretation processes by improving the pictorial information and enhancing the automatic machine perception. As a result, we propose new approaches that firstly rely on estimating the initial high-resolution image through preprocessing of the reference low-resolution image based on median, mean, Lucy-Richardson, and Wiener filters. This preprocessing stage is used to overcome the degradation present in the reference low-resolution image, which is a suitable kernel for producing the initial high-resolution image to be used in the reconstruction phase of the final image. Then, L2 norm is employed for the data-fidelity term to minimize the residual among the predicted high-resolution image and the observed low-resolution images. Finally, bilateral total variation prior model is utilized to restrict the minimization function to a stable state of the generated HR image. The experimental results of the synthetic data indicate that the proposed approaches have enhanced efficiency visually and quantitatively compared to other existing approaches.

Improvement of the Voltage Profile and Loss Reduction in Distribution Network Using Moth Flame Algorithm: Wolaita Sodo, Ethiopia

Voltage stability and line losses are inevitable issues even in modern power systems. There are several techniques that emerged to solve problems in the power system to provide quality and uninterrupted supply to customers. The algorithms used in this paper to determine the appropriate location and size of the Static Var Compensator (SVC) in the Distribution Network (DN) are Moth Flame Optimization (MFO) and Particle Swarm Optimization (PSO). The objective function is defined to minimize voltage deviation and power loss. The burning problem of voltage stability improvement current scenario is because of a rise in electricity demands in all sectors. Paramount duties of power engineers are to keep the system stable and maintain voltage magnitude constant even during peak hours. The results were checked with the aid of MATLAB on Wolaita Sodo radial distribution of 34 bus data networks. The potential use of SVC is key to solve distribution system power quality issues and estimating the advantage of the installation. The results obtained from the test system were compared with PSO results. This comparison was done to know the computational time of proposed techniques. The performance of the MFA based SVC was superior in distribution system and highlighted the importance of device.

Nonintrusive Industrial Load Identification Combined with Random Forests and Steady-State Waveform

Nonintrusive industrial load identification can accurately acquire the operation data of each load in the plant, which is the benefit of intelligent power management. The identification method of the industrial load is complicated and difficult to be realized due to the difficulty in collecting transient data for modeling, and high-precision measuring equipment is required. Aiming at this situation, the article proposes a nonintrusive industrial load identification method using a random forest algorithm and steady-state waveform. Firstly, by monitoring the change of the industrial load power state, when the load changes and becomes stable, the steady-state waveform is extracted. Due to different electrical characteristics of industrial loads, the current waveform of loads is different to some extent. We can construct characteristic data for each industrial load to construct its own current steady-state waveform. Then, using the high-dimensional data of the steady-state waveform as the sample data, the bootstrap sampling method and the CART algorithm in the random forest algorithm are used to generate multiple decision trees. Finally, the industrial load types are identified by voting multiple decision trees. The actual operating load data of a factory are used as the sample data in the simulation, and the effectiveness and rapidity of the proposed identification algorithm are verified by the combined load method simulation comparison. The simulation results show that the accuracy of the proposed identification algorithm is more than 99%, the identification time is 3.36 s, which is much higher than that of other methods, and the operation time is less than that of other methods. Therefore, the proposed identification algorithm can effectively realize the nonintrusive industrial load identification.

Comparison of Machine Learning Algorithms for the Prediction of Mechanical Stress in Three-Phase Power Transformer Winding Conductors

This research compares four machine learning techniques: linear regression, support vector regression, random forests, and artificial neural networks, with regard to the determination of mechanical stress in power transformer winding conductors due to three-phase electrical faults. The accuracy compared with finite element results was evaluated for each model. The input data were the transient electrical fault currents of power system equivalents with impedances from low to high values. The output data were the mechanical stress in the conductors located in the middle of the winding. To simplify the design, only one hyperparameter was varied on each machine learning technique. The random forests technique had the most accurate results. The highest errors were found for low-stress values, mainly due to the high difference between maximum and minimum stresses, which made the training of the machine learning models difficult. In the end, an accurate model that could be used in the continuous monitoring of mechanical stress was obtained.

A Maximum Transfer Efficiency Tracking Method for Dynamic Wireless Charging Systems of Electric Vehicles

This paper proposes a new control method to improve transfer efficiency for dynamic wireless charging systems of electric vehicles (EVs). In the charging process, the equivalent impedance in the receiving side varies according to the state of charge of the battery system that reduces the transfer efficiency. An impedance control circuit is constructed on the receiving side to track the optimization impedance that transfer efficiency is maximized. However, the optimization impedance depends on the coupling coefficient. Therefore, in this paper, the coupling coefficient, which varies according to the EVs position, is online estimated only from the receiving side. A 1.5 kW dynamic wireless charging system prototype is built in the laboratory environment. In experiment results, the greatest transfer efficiency obtains 94.14% when the EVs move in aligned on the charging lane. Furthermore, the proposed control method improves by 6% on the transfer efficiency in the case of 30% misalignment when the transfer efficiency obtains 91%.

Some Properties for Adjustable Entropy Function Method and Its Application to Power Systems Dynamic Economic Dispatch with Wind Integrated

With the continuous development of the world economy, the development and utilization of environmentally friendly and renewable energy have become the trend in many countries. In this paper, we study the dynamic economic dispatch with wind integrated. Firstly, we take advantage of the positive and negative spinning reserve to deal with wind power output prediction errors in order to establish a dynamic economic dispatch model of wind integrated. The existence of a min function makes the dynamic economic dispatch model nondifferentiable, which results in the inability to directly use the traditional mathematical methods based on gradient information to solve the model. Inspired by the aggregate function, we can easily transform the nondifferentiable model into a smooth model when parameter p tends to infinity. However, the aggregate function will cause data overflow when p tends to infinity. Then, for solving this problem, we take advantage of the adjustable entropy function method to replace of aggregate function method. In addition, we further discuss the adjustable entropy function method and point out that the solution generated by the adjustable entropy function method can effectively approximate the solution of the original problem without parameter p tending to infinity. Finally, simulation experiments are given, and the simulation results prove the effectiveness and correctness of the adjustable entropy function method.

Research and Implementation of Fast-LPRNet Algorithm for License Plate Recognition

The license plate recognition is an important part of the intelligent traffic management system, and the application of deep learning to the license plate recognition system can effectively improve the speed and accuracy of recognition. Aiming at the problems of traditional license plate recognition algorithms such as the low accuracy, slow speed, and the recognition rate being easily affected by the environment, a Convolutional Neural Network- (CNN-) based license plate recognition algorithm-Fast-LPRNet is proposed. This algorithm uses the nonsegment recognition method, removes the fully connected layer, and reduces the number of parameters. The algorithm—which has strong generalization ability, scalability, and robustness—performs license plate recognition on the FPGA hardware. Increaseing the depth of network on the basis of the Fast-LPRNet structure, the dataset of Chinese City Parking Dataset (CCPD) can be recognized with an accuracy beyond 90%. The experimental results show that the license plate recognition algorithm has high recognition accuracy, strong generalization ability, and good robustness.