Deep Learning Control for Autonomous Robot

Several applications of machine learning and artificial intelligence, have acquired importance and come to the fore as a result of recent advances and improvements in these approaches. Autonomous cars are one such application. This is expected to have a significant and revolutionary influence on society. Integration with smart cities, new infrastructure and urban planning with sophisticated cyber-security are some of the current ramifications of self-driving automobiles. The autonomous automobile, often known as self-driving systems or driverless vehicles, is a vehicle that can perceive its surroundings and navigate predetermined routes without human involvement. Cars are on the verge of evolving into autonomous robots, thanks to significant breakthroughs in artificial intelligence and related technologies, and this will have a wide range of socio-economic implications. However, in order for these automobiles to become a reality, they must be endowed with the perception and cognition necessary to deal with high-pressure real-life events and make proper judgments and take appropriate action. The majority of self-driving car technologies are based on computer systems that automate vehicle control parts. From forward-collision warning and antilock brakes to lane-keeping and adaptive drive control, to fully automated driving, these technological components have a wide range of capabilities. A self-driving car combines a wide range of sensors, actuators, and cameras. Recent researches on computer vision and deep learning are used to control autonomous driving systems. For self-driving automobiles, lane-keeping is crucial. This study presents a deep learning approach to obtain the proper steering angle to maintain the robot in the lane. We propose an advanced control for a self-driving robot by using two controllers simultaneously. Convolutional neural networks (CNNs) are employed, to predict the car’ and a proportional-integral-derivative (PID) controller is designed for speed and steering control. This study uses a Raspberry PI based camera to control the robot car.     

Wind Turbine Efficiency Under Altitude Consideration Using an Improved Particle Swarm Framework

In this work, the concepts of particle swarm optimization-based method, named non-Gaussian improved particle swarm optimization for minimizing the cost of energy (COE) of wind turbines (WTs) on high-altitude sites are introduced. Since the COE depends on site specification constants and initialized parameters of wind turbine, the focus was on the design optimization of rotor radius, hub height and rated power. Based on literature, the COE is converted to the Saudi Arabia context. Thus, the constrained wind turbine optimization problem is developed. Then, non-Gaussian improved particle swarm optimization is provided and compared with the conventional particle swarm optimization for solving the optimization design in wind turbine efficiency under different altitudes ranging from 2500 to 4000 m. The results show that as altitude rises, the optimal rotor radius grows, but the optimal hub height and rated power drop, resulting in an increase in COE. Further, the non-Gaussian method display a faster convergence compared to the classical particle swarm optimization. These findings will be useful as a reference for wind turbine design at high altitudes. Thus, it could be employed to optimize the initialized parameter of wind turbine for the planned and largest wind farm in Saudi Arabia in Dumat Al-Jandal selected site.

     

A New Tuning Method for Stabilization Time Delay Systems Using PIλDμ Controllers

This paper presents a new design procedure to tune the fractional order PI^λD^μ controller that stabilizes a first order plant with time delay. The procedure is based on a suitable version of the Hermite–Biehler Theorem and the Pontryagin Theorem. A Theorem and a Lemma are developed to compute the global stability region of the PI^λD^μ controller in the (k_p,k_i,k_d) space. Hence, this Theorem and Lemma allow us to develop an algorithm for solving the PI^λD^μ stabilization problem of the closed loop plant. The proposed approach has been verified by numerical simulation that confirms the effectiveness of the procedure.     

Optimal Robust Control for Unstable Delay System

Proportional-Integral-Derivative control system has been widely used in industrial applications. For uncertain and unstable systems, tuning controller parameters to satisfy the process requirements is very challenging. In general, the whole system’s performance strongly depends on the controller’s efficiency and hence the tuning process plays a key role in the system’s response. This paper presents a robust optimal Proportional-Integral-Derivative controller design methodology for the control of unstable delay system with parametric uncertainty using a combination of Kharitonov theorem and genetic algorithm optimization based approaches. In this study, the Generalized Kharitonov Theorem (GKT) for quasi-polynomials is employed for the purpose of designing a robust controller that can simultaneously stabilize a given unstable second-order interval plant family with time delay. Using a constructive procedure based on the Hermite-Biehler theorem, we obtain all the Proportional-Integral-Derivative gains that stabilize the uncertain and unstable second-order delay system. Genetic Algorithms (GAs) are utilized to optimize the three parameters of the PID controllers and the three parameters of the system which provide the best control that makes the system robust stable under uncertainties. Specifically, the method uses genetic algorithms to determine the optimum parameters by minimizing the integral of time-weighted absolute error ITAE, the Integral-Square-Error ISE, the integral of absolute error IAE and the integral of time-weighted Square-Error ITSE. The validity and relatively effortless application of presented theoretical concepts are demonstrated through a computation and simulation example.     

A new experimental setup designed for the investigation of irradiation of nanosystems in the gas phase: a high intensity mass-and-energy selected cluster beam

DIAM (Dispositif d'Irradiation d'Agre?gats Mole?culaires) is a new experimental setup devoted to investigate processes induced by irradiation at the nanoscale. The DIAM apparatus is based on a combination of techniques including a particle beam from high-energy physics, a cluster source from molecular and cluster physics, and mass spectrometry form analytical sciences. In this paper, we will describe the first part of the DIAM apparatus that consists of an ExB double spectrometer connected to a cluster ion source based on a continuous supersonic expansion in the presence of ionizing electrons. This setup produces high intensities of energy-and-mass selected molecular cluster ion beams (1000 s of counts s(-1)). The performance of the instrument will be shown through measurements of 6-8 keV beams of protonated water clusters, (H(2)O)(n)H(+) (n = 0-21) and mixed protonated (or deprotonated) water-pyridine cluster ions: PyrH(+)(H(2)O)(n) (n = 0-15), Pyr(2)H(+) (H(2)O)(n) (n = 0-9), and (Pyr-H)(+) (H(2)O).     

Stabilizing sets of PI/PID controllers for unstable second order delay system

In this paper, the problem of stabilizing an unstable second order delay system using classical proportional-integralderivative(PID) controller is considered. An extension of the Hermite-Biehler theorem, which is applicable to quasi-polynomials, is used to seek the set of complete stabilizing proportional-integral/proportional-integral-derivative(PI/PID) parameters. The range of admissible proportional gains is determined in closed form. For each proportional gain, the stabilizing set in the space of the integral and derivative gains is shown to be a triangle.