This paper presents a hardware implementation upon a Field Programmable Gate Array (FPGA) of improved Vector Control Strategies (VCSs) based on a Fuzzy Logic System (FLS) of a grid-connected wind energy conversion system. Usually, the classical VCS is based on fixed-gain Proportional Integral Derivative (PID) controllers, which are known to exhibit limited performance against the nonlinear behavior of wind systems, such as rapid fluctuations of the wind speed and uncertainties of the system parameters. In order to overcome this limitation, an improved VCS based on Fuzzy Gain Scheduling PID controllers (VCS-FGS-PID) is suggested in this work to guarantee good tracking, high accuracy and good robustness under system parameter variations. Indeed, the PID controller gains are tuned, in real-time, by the FLS. In addition, the proposed VCS-FGS-PID methods are implemented on the FPGA in order to reduce the delays and the period of the system of the control loop, thanks to its parallel processing. In fact, the performance of the suggested VCS-FGS-PID approaches are proved by digital simulation with the Xilinx system generator tool under Matlab/Simulink, in addition to an experimental hardware-in-the-loop implementation using the FPGA. The obtained results demonstrate that the proposed VCS-FGS-PID techniques offer better performance as regards good tracking and high accuracy and good robustness against stator resistance variability compared to VCS-PI.

This paper proposes a novel method using a machine learning-based Adaptive Neuro-Fuzzy Inference System (ANFIS) to optimize Maximum Power Point Tracking (MPPT) in variable-speed Wind Turbines (WT). The ANFIS algorithm, blending artificial neural networks and fuzzy logic, addresses issues with traditional wind speed sensors, such as cost, imprecision, and susceptibility to adverse weather conditions. An initial offline-trained ANFIS is suggested to understand turbine power characteristics, and subsequently estimate varying wind speed, addressing strong nonlinearity due to WT aerodynamics and wind speed fluctuations. A second ANFIS efficiently tracks the maximum power point, overcoming limitations of linear controllers. Implemented in Matlab/Simulink for a 3.5 kW WT, the approach demonstrates effectiveness, precision, and faster response time in wind speed estimation and accurate MPPT compared to alternatives. A notable advantage is its independence from instantaneous wind speed measurement, providing a cost-effective solution for wind energy systems.

This paper proposes a Xilinx Zynq-FPGA (Field Programmable Gate Array) for real time hardware implementation of a vector control strategy for a grid-connected variable-speed wind energy conversion system. In order to overcome the problem of important computation time and the control loop delay due to the sequential processing of the control algorithm for wind generator, a Xilinx Zynq-FPGA is proposed as an alternative solution, thanks to its parallel processing. In fact, the Xilinx Zynq-FPGA is characterized by a hardware architecture with parallel computation. Indeed, the FPGA technology has great advantages like the programmable wired function, the fast computing capability, the shorter design cycle, the integrated processor, the low power consumption and the higher density. The studied system is composed of a wind turbine, a permanent magnet synchronous generator, and two converters (a rectifier and an inverter) linked by a DC bus. The system is connected to the grid through a resistor–inductor filter. The proposed control strategy performances are evaluated by digital simulation utilizing an Xilinx System Generator (XSG) toolbox that guaranties rapid and efficient prototyping of the implemented architecture on the FPGA device. In fact, the hardware architectures of the rectifier vector control and the inverter vector control are designed using the XSG tool. The obtained results demonstrate that the XSG simulation offers better results in terms of tracking and accuracy.

In this work, a comprehensive study of various wind energy conversion system control methodologies is proposed more precisely a comparative study of an intelligent vector control technique of a three-phase rectifier for a wind turbine linked to the grid. Its goal is to ensure a stable control technique that performs well in the face of external perturbations. The system under consideration consists of two converters connected by the DC bus, a permanent magnet synchronous generator, and a wind turbine. A resistor–inductor filter connects the system to the grid. In our system, we use a vector control strategy which is generally based on a proportional–integral controller. However, because of the control sensitivity to external disturbances and parameter modifications, a control method based on a Fuzzy Logic-Control (FLC) mode has been developed. Such a technique provides high performances, like the insensitivity to system non-linearity. Indeed, this study emphasizes the significance of implementing the proposed FLC utilizing the Field-Programmable Gate Array (FPGA). Because of obvious parallelism provided by the FPGA, the fundamental advantage of the FPGA implementation is the growth of the control loop latency. This suggested control algorithm’s performance is investigated utilizing digital simulation through the use of a Xilinx System Generator (XSG) tool, in addition to the implementation with a Zynq-FPGA. In reality, the XSG tool is used to design the hardware structures of the rectifier vector control. The collected results demonstrate that FLC simulation provides superior tracking and precision.

Traffic sign detection is a fundamental component of intelligent transportation systems, yet remains challenging due to the small size of signs, visual occlusions, and complex environmental conditions. In this paper, we propose a novel YOLO-based architecture enhanced with multi-scale attention and Transformer modules to address these limitations. Specifically, a Convolutional Block Attention Module (CBAM) is employed to refine spatial and channel-wise features, while a C3 Transformer (C3TR) module introduces multi-head self-attention to capture global contextual information. The proposed enhancements significantly improve the model's ability to detect small and visually degraded traffic signs. Evaluated on the German Traffic Sign Detection Benchmark (GTSDB), our model achieves a mAP@0.5 of 96.75%, mAP@0.5:0.95 of 81.18%, precision of 97.05%, and recall of 95.07%. Compared to YOLOv5 s, this reflects relative gains of +11.2% in mAP@0.5, + 26.6% in mAP@0.5:0.95, + 1.6% in precision, and +20.0% in recall, with a 41.9% reduction in model size. It also outperforms YOLOv8, YOLOv7-tiny, and Faster R-CNN, particularly for degraded signs. For real-time deployment on embedded systems, the model is optimized using NVIDIA TensorRT. This optimization significantly reduces inference latency and computational load while preserving high detection accuracy, making the model well-suited for ADAS and autonomous driving applications.