Computer vision-based path planning can play a crucial role in numerous technologically driven smart applications. Although various path planning methods have been proposed, limitations, such as unreliable three-dimensional (3D) localization of objects in a workspace, time-consuming computational processes, and limited two-dimensional workspaces, remain. Studies to address these problems have achieved some success, but many of these problems persist. Therefore, in this study, which is an extension of our previous paper, a novel path planning approach that combined computer vision, Q-learning, and neural networks was developed to overcome these limitations. The proposed computer vision-neural network algorithm was fed by two images from two views to obtain accurate spatial coordinates of objects in real time. Next, Q-learning was used to determine a sequence of simple actions: up, down, left, right, backward, and forward, from the start point to the target point in a 3D workspace. Finally, a trained neural network was used to determine a sequence of joint angles according to the identified actions. Simulation and experimental test results revealed that the proposed combination of 3D object detection, an agent-environment interaction in the Q-learning phase, and simple joint angle computation by trained neural networks considerably alleviated the limitations of previous studies.

Efforts to increase the power output of wind turbines include Diffuser Augmented Wind Turbines (DAWT) or a shroud for the rotor of a wind turbine. The selected duct has three main components: a nozzle, a diffuser, and a flange. The combined effect of these components results in enriched upstream velocity for the rotor installed in the throat of the duct. To obtain the maximum velocity in the throat of the duct, the optimum angles of the three parts have been analyzed. A code was developed to allow all the numerical steps including changing the geometries, generating the meshes, and setting up the numerical solver simultaneously. Finally, the optimum geometry of the duct has been established that allows a doubling of the flow velocity. The flow characteristics inside the duct have also been analyzed in detail. An H-Darrieus Vertical Axis Wind Turbine (VAWT) has been simulated inside the optimized duct. The results show that the power coefficient of the DAWT can be enhanced up to 2.9 times. Deep dynamic stall phenomena are captured perfectly. The duct advances the leading-edge vortex generation and delays the vortex separation.

Recent development in using wind turbines for urban areas results in inserting turbines inside buildings. As buildings' walls may act as a duct for the turbine, this study focuses on a ducted wind turbine with a fixed duct geometry. A method is organized for achieving the improved generated power and the wind speed augmentation with fixed geometry of duct regardless of the type of the turbine, which is the aim of building designers. Using a porous disc (PD) instead of a wind turbine rotor makes the study cost and time effective. PDs within a duct help estimate any given duct's maximum available power extraction capability. In addition, experimental and numerical tests examine the effect of PDs solidity on the performance of diffuser augmented wind turbines and the corresponding economic analysis. Both experimental and numerical results agree that the power coefficient highly depends on the solidities of the PD. The power coefficient of a ducted PD with a solidity of 0.3 is augmented by up to 30%. Nevertheless, in some cases, employing a duct can contribute to the power reduction if the solidity exceeds a critical value. A smoke visualization technique helps vortex study. Economic assessment of a ducted turbine for three scenarios belonging to Germany and Italy shows a 15.3% decline in cost per electricity production. The payback period decreases by 3.42 years, 7.68 months, and 6.36 months for Scenarios 1, 2, and 3.

The Betz theory expresses that no horizontal axis wind turbine can extract more than 16/27 (59.3%) of the kinetic energy of the wind. The factor 16/27 (0.593) is known as the Betz limit. Horizontal Axis wind turbine designers try to improve the power performance to reach the Betz limit. Modern operational wind turbines achieve at peak 75% to 80% of the Betz limit. In 1919, Albert Betz used an analytical method to derive the Betz limit. He derived momentum equations of an Actuator Disc (AD) in the stream. In this research, an experimental and a numerical setup based on the Actuator Disc (AD) have been designed and tested to reach the Betz limit. A Plexiglass screen with the porosity of 0.5 mimics the wind turbine rotor. For the numerical study, a 2D flow filed is considered. The results of both experimental and numerical methods agree well with the analytical results of the Betz theory. From the experimental and numerical results, the relative errors in comparison with the Betz limit (which is 16/27) are 0.16% and 1.27%, respectively. The small amount of errors shows the possibility of reaching the Betz limit using either experimental or numerical methods. This approach can be used for modeling ideal wind turbines, ideal rotating devices or ideal wind farms either numerically or experimentally and gives the maximum possible power extractions; thus, any improvement to the performance of a system can be made by this method.

The expenses of a wind turbine modeling in particular a wind farm modeling either numerically or experimentally cause to take the advantages of actuator disks (AD). Porous disks (PD) are used to simulate actuator disks in experiments especially for wake studies. A rotor of a wind turbine replaced by a PD can be modeled efficiently with less cost and process time. For a proper PD selection, some semi‐empirical equations are suggested for a range of solidity of 0.2‐0.6. These equations came from a number of tests. The PDs with different dimensions and solidity values were considered for the tests and models. The results of 2D and 3D numerical simulations and the experimental results show that at the solidity of 0.5, the coefficient of performance of a PD reaches approximately 16/27 which is equal to the Betz's limit; the relation between the coefficient of power and the solidity is fitted by a parabolic equation. The average error of the proposed equations for the power coefficient is reported 1.59%. Finally, based on the current results, some semi‐empirical equations are suggested to help the initial PD selection, and then, the cost of further studies may decrease.