The increasing occurrence of cyberattacks specifically aimed at critical infrastructure has led to the adoption of network intrusion detection techniques for the Internet of Things (IoT). Securing IoT networks is difficult because of the growing number of connected devices and the advanced methods used by attackers. This study investigates the application of machine learning and neural networks in the prevention of prevalent online fraud and assesses their efficacy. The text discusses important ideas related to email filtering, machine learning, artificial neural networks, and network intrusion techniques. The study discusses the difficulties related to e-fraud detection and suggests methods to improve detection systems. Furthermore, it offers a thorough examination of IoT intrusion detection, emphasizing the risks, weaknesses, assaults, and methods of detection. Securing the billions of autonomous nodes in the Internet of Things (IoT), each with distinct characteristics, poses a significant challenge. Conventional techniques like as encryption, access control, and authentication are inadequate when used individually. Thus, this work utilizes deep learning techniques to detect widespread IoT vulnerabilities, such as Distributed Denial of Service (DDoS) assaults. The models are evaluated using different datasets, including NSL-KDD, DS2OS, and IoT Botnet. The evaluation is based on measures such as accuracy, precision, recall, and F1-score. The deep machine learning intrusion detection system has a high accuracy rate of 96.38%, which shows its efficiency in recognizing risks related to the Internet of Things (IoT) Where the data was trained by 80% and the data was tested by 20.

This manuscript introduces a perturbation-free extremum-seeking control strategy specifically designed to enhance the operational performance of wind turbines under optimal conditions. The strategy employed utilizes a perturbation-free extremum-seeking approach to ensure the wind turbine farm operates at maximum power efficiency while also reducing power output fluctuations. By employing this control system, the wind turbine generators are maintained at their optimal power output level, effectively navigating through disturbances such as tower shadow, wind shear, and the erratic nature of wind speeds without introducing external perturbations. The algorithm is adept at managing the blade pitch angles and the turbines’ rotational speed, ensuring a controlled and efficient operation. Furthermore, this paper outlines a perturbation-free method to optimize energy production and decrease fatigue loads, thereby extending the operational lifespan of a wind turbine. The superior operational efficiency of the wind turbine array generators achieved through this approach underscores its effectiveness. The robustness and effectiveness of this perturbation-free control system are validated through comprehensive simulation tests on an array comprising four wind turbine generators. The outcomes of these simulations solidly back the extremum-seeking control system's proficiency in reaching maximum power output without relying on perturbative methods, highlighting its innovative contribution to wind turbine efficiency optimization.

This paper proposes a realistic principal Gaussian Process model for the wind turbine, with a kernel derived. The model is trained and validated on a data-driven practical wind turbine model to predict optimal operational curves for the optimal operating conditions of wind turbine generators. The proposed technique indicates the critical parameters of the wind behaviour from historical wind speed data to keep maximum power. This technique is used to avoid periodic fluctuations in the output power of the wind turbine generators by design an efficient control system. The frequent changes in the power output come from tower shadow, wind shear, gust, and turbulence in the wind speed. The operational curves of the critical parameters included the profiles of power, blades pitch angle, and turbine rotor speed. The power improvement performance of the turbine can use the relationship between critical parameters ahead of time to predict wind behaviour.

The development of control systems to improve efficiency requires accurate mathematical models. This article deals with the modelling of two-mass variable speed wind turbine generators. A model design of a 3.5 MW vertically axial wind generator and a mathematical model of an electromechanical system is considered in this article. Wind turbine generators behave to have the most significant uncertainty, specified the possibility for nonlinear behaviour. The main focus is on structural aerodynamics, including the forcing and motion of the rotating parts of the turbine. The turbine’s critical structural aerodynamics and mechanical components are the blade pitch actuators, drive shaft actuators, and turbine specifications. With an accurate wind turbine model, the control engineers will design control systems to reduce loads, increase the operating lifetime, and increase electrical power. Methods of linearization about operating points have been proposed to enable an efficient control system design. The results show that the model can be used in different strategies evaluation. © 2022 Thaker Nayl et al.

Cerebral Palsy (CP)is a collection of permanent, non-progressive disorders that impact the individual’s motor ability. The rehabilitation of patients with CP is very important to improve their motor abilities and to minimize the need for third parties. In this paper, a low-cost hand rehabilitation glove based on finger bend/pressure analysis is presented. The data glove is used to improve hand functioning for pre-school children with cerebral palsy through virtual reality games. The system consists of two parts: the data glove and several virtual games. The data glove consists of a microcontroller, flex sensors, force sensors and radiofrequency transmission units. The use of the newly developed system will assist the psychotherapist to follow the CP child daily, weekly or monthly. The rehabilitation model and the predicted physiotherapy results can be extracted from the patient’s record after using the data. Experimental results have shown that the regular usage of the data glove improved 75 % of the participants’ fingers bending the angel and the child’s grip ability.

In this work, a new strategy to control the pitch angle of wind turbine generator is proposed. The strategy is based on designing an intelligent control system capable of maintaining a stable minimum fluctuating power generation. This can be achieved by providing the wind speed information to the controller in advance and hence allowing the controller to take the optimum action in controlling the blade pitch angle. A model based optimizer uses Model Predictive Control (MPC) technique to predict the wind turbine generator future behaviour and select the optimal control actions assisted by the wind speed information while satisfying the power generation constraints. The simulation results show that a significant improvement can be made using the proposed control method.

This article presents the design and experimental evaluation of a novel sliding mode control scheme, being applied to the case of an articulated vehicle. The proposed sliding mode controller is based on a novel continuous sliding surface, being introduced for reducing the chattering phenomenon, while achieving a better tracking performance and a fast minimization of the corresponding tracking error. The derivation of the sliding mode controller relies on the fully nonlinear kinematic model of the articulated vehicle, while the overall stability of the control scheme is proven based on the Lyapunov's stability condition. The performance of the established control scheme is being experimentally evaluated through multiple path tracking scenarios on a small scale and fully realistic articulated vehicle

In this article, a complete analysis towards the development of a switching modeling and control framework for an articulated vehicle, under the effect of varying slip angles will be presented. The established nonlinear kinematic model, of the nonholonomic articulated vehicle, will be transformed into an error dynamics model, which in the sequel will be linearized around multiple nominal slip angle cases. The proposed control architecture will consist of a switching control scheme, based on multiple model predictive controllers, for the articulated vehicle under varying slip angles. The controllers will be developed in order to improve the performance of the articulated vehicle's path tracking, while compensating the varying slippage effect. The current measured slip angle is being considered as the switching rule and a corresponding switching control scheme is being defined, being able to apply constraints on the states, the control signal and the output variables. Both the non-slip and slip models will be derived to highlight the significance of accounting for slips in path following control and their significant effect on deteriorating the performance of the overall control scheme when not considered. Multiple simulation results will be presented to prove the efficacy of the overall suggested scheme.

The aim of this article is to analyze the effect of kinematic parameters on a novel proposed on-line motion planning algorithm for an articulated vehicle based on Model Predictive Control. The kinematic parameters that are going to be investigated are the vehicle's velocity, the maximum allowable change in the articulated steering angle, the safety distance from the obstacles and the total number of obstacles in the operating arena. The proposed modified path planning algorithm for the articulated vehicle belongs to the family of Bug-Like algorithms and is able to take under consideration, the mechanical and physical constraints of the articulated vehicle, as well as its full kinematic model. During the on-line motion planning algorithm, the MPC controller controls the lateral motion of the vehicle, through the rate of the articulation angle, while driving it accurately and safely over the on-line formulated desired path. The efficiency of the proposed combined path planning and control scheme is being evaluated under numerous simulated test cases, while exhaustive simulations have been made for analyzing the dependency of the proposed framework on the kinematic parameters.

The objective of this thesis is to address the problems of modeling, path planning and path following for an articulated vehicle in a realistic environment and in the presence of multiple obstacles.In greater detail, the problem of the kinematic modeling of an articulated vehicle is revisited through the proposal of a proper model in which the dimensions and properties of the vehicle can be fully described, rather than considering it as a unit point. Based on this approach, nonlinear and linear error kinematics models are proposed that are also able to account for the effect of the slip angles, a factor that can cause dramatic deterioration in the overall performance of the vehicle.Subsequently, two different concepts for addressing the problem of path following for articulated vehicles are proposed. The first concept is based on a switching model predictive control architecture, which relies on multiple switching linear error dynamics models of the articulated vehicle to account for the effect of varying the slip angles and cruising speed as well as the mechanical and physical constraints of the vehicle.The second proposed control concept is a novel nonlinear sliding mode controller that introduces continuous sliding surfaces to reduce chattering effects while tracking a reference trajectory.The sliding mode controller is utilized based on the extracted nonlinear error coordinates of the articulated vehicle. The feasibility of this approach has been demonstrated through multiple experimental tests on a small scale using a fully realistic articulated vehicle.Finally, in the path planning part of the thesis, artificial potential field and bug algorithms are addressed. More specifically, the potential field path planning algorithm is modified by considering the nonlinear kinematic model of the articulated vehicle and correspondingly adapting the repulsive and attractive coefficients.In the case of the well-known bug algorithm, a suitable navigation method for an articulated vehicle for local path planning based on a minimum set of sensors and with decreased complexity for online implementation is also proposed.Furthermore, the performance of the modified potential field method has been experimentally evaluated in multiple path planning scenarios using the previously mentioned small-scale realistic articulated vehicle.