Modelling Intelligent Driving Behaviour Using Machine Learning

In vehicular systems, driving is considered to be the most complex task, involving many aspects of external sensory skills as well as cognitive intelligence. External skills include the estimation of distance and speed, time perception, visual and auditory perception, attention, the capability to drive safely and action-reaction time. Cognitive intelligence works as an internal mechanism that manages and holds the overall driver’s intelligent system.These cognitive capacities constitute the frontiers for generating adaptive behaviour for dynamic environments. The parameters for understanding intelligent behaviour are knowledge, reasoning, decision making, habit and cognitive skill. Modelling intelligent behaviour reveals that many of these parameters operate simultaneously to enable drivers to react to current situations. Environmental changes prompt the parameter values to change, a process which continues unless and until all processes are completed. This paper model intelligent behaviour by using a ‘driver behaviour model’ to obtain accurate intelligent driving behaviour patterns. This model works on layering patterns in which hierarchy and coherence are maintained to transfer the data with accuracy from one module to another. These patterns constitute the outcome of different modules that collaborate to generate appropriate values. In this case, accurate patterns were acquired using ANN static and dynamic non-linear autoregressive approach was used and for further accuracy validation, time-series dynamic backpropagation artificial neural network, multilayer perceptron and random sub-space on real-world data were also applied.     

Split internal-loop photobioreactor for Scenedesmus sp. microalgae:Culturing and hydrodynamics

In this study, the evaluation of the performance of the split internal loop photobioreactor for culturing a species of green microalgae, Scenedesmus sp. under different operating superficial gas velocity and during a different time of growth (i.e., starting for the first day until end day of the culturing process) was addressed. The evaluation of the performance of the split internal loop photobioreactor was included assessing the density, pH, temperature, vis-cosity, surface tension, the optical density, cell population, dry biomass, and chlorophyll of the culture medium of the microalgae culturing. Additionally, the hydrodynamics of a Split Internal-Loop Photobioreactor with microalgae culturing was comprehensively quantified. Radioactive particle tracking (RPT) and gamma-ray com-puted tomography (CT) techniques were applied for the first time to quantify and address the influence of microalgae culture on the hydrodynamic parameters. The hydrodynamics parameters such as local liquid veloc-ity field, shear stresses, turbulent kinetic energy, and local gas holdup profiles were measured at different super-ficial gas velocities as well as under different times of algae growth. The obtained results indicate that the flow distribution may significantly affect the performance of the photobioreactor, which may have substantial effects on the cultivation process. The obtained experimental data can serve as benchmark data for the evaluation and validation of computational fluid dynamics (CFD) codes and their closures. This, in turn, allows us to develop ef-ficient reactors and consequently improving the productivity and selectivity of these photobioreactors.     

Torque redistribution and time regulation methods for actuator of fault-tolerant parallel robots

In this article, we investigate and employ torque redistribution and time regulation approaches to track a preplanned trajectory while avoiding actuator saturation for redundantly actuated, fault-tolerant parallel robots encountering actuator failure. The torque redistribution method utilizes actuation redundancies (if available) after joint failure and/or saturation to alter the torque requirements of the joints so as to avoid saturation. The time regulation method is based upon the alteration of the time to completion of the defined joint-space trajectory. By searching for a suitable time scaling factor to change (reduce) the inertia load requirements, the robot attempts to slow down or speed up as it moves along the defined trajectory to avoid saturation. The preferred implementation strategy is to use the torque redistribution approach when redundancy is available and actuation capacity is sufficient, otherwise the time regulation approach is employed. For both methods, the computed torque technique, consisting of a model reference algorithm in the feedforward process, and a proportional plus integral plus derivative (PID) controller, to deal with modeling errors and disturbances in the feedback process, are utilized.     

Analysis of gross error rates in operation of commercial nuclear power stations

Experience in operation of US commercial nuclear power plants is reviewed over a 25-moth period. The reports accumulated in that period on events of human error and component failure are examined to evaluate gross operator error rates. The impact of such errors on plant operation and safety is examined through the use of proper taxonomies of error, tasks and failures. Four categories of human errors are considered; namely, operator, maintenance, installation and administrative. The computed error rates are used to examine appropriate operator models for evaluation of operator reliability. Human error rates are found to be significant to a varying degree in both BWR and PWR. This emphasizes the import of considering human factors in safety and reliability analysis of nuclear systems. The results also indicate that human errors, and especially operator errors, do indeed follow the exponential reliability model.     

Analysis of coherence,strain, thermal vibration and preferred orientation in carbons by X-Ray diffraction

In ideal graphitic layers the inter-atomic (or inter-unit cell) distances l and the number of atoms (or unit cells) n(l) at a distance from any atom (or unit cell) chosen as origin may be represented by sets l and n(l) which define the structure. In the defective lattice theory presented here the structure of diffusely scattering (the so-called amorphous) carbons are likewise defined by the two sets, however n(l)'s are modified by a probability (coherence probability) function g(l) and l's are modified for dispersion (strain effects). It is shown that the coherence probability function can be determined from the atomic radial distribution curves without a priori knowledge of distortion and temperature diffuse scattering. Analytical expressions have been developed that permit analysis of distortion and temperature diffuse scattering from the observed profiles of the diffuse peaks and from the atomic radial distribution functions. In analyzing the distortion, Gauss', Gauchy's and Laplace's distributions are considered. It is demonstrated that distortion could be responsible for the diffuseness of the diffraction profiles of carbons to a greater extent than the coherence probability, the so-called domain or particle size effect. It is also shown that the integrated intensities, I(φ), of the (00l) reflections of anisotropic, e.g. pyrolytic, carbons are related to the angle φ that the diffraction vector makes with the pole of the sample by I(φ) = K exp (?p²sin²φ) in which K is the proportionality constant and p is the characteristic parameter of the sample. The equation has a reasonably sound physical basis and has been found to be applicable to samples having a wide range of preferred orientations.     

Design of a small single-purpose nuclear desalination plant compatible with the local resources in the middle east

Present plans in the Middle East involve the construction of several nuclear power plants with desalination capabilities to provide power and water to meet the requirements of the anticipated growth in the industrial sector and development of new settlements to improve the socio-economical aspects of population distribution. This effort has been matched by a program initiated by the Development Consultants Association (DCA) to provide the necessary training, manpower and expertise necessary for adequate involvement in siting, design, construction and operation of both nuclear and desalination plants.

In this paper results of the preliminary stages of the design of a 2.6 million gallons per day (1000 cubic meters/day) single-purpose 40 MW thermal MSF-heavy water nuclear plant are reported. Design objectives and philosophy are reviewed. A descriprion is given of the neutronic, thermal, control and mechanical design parameters of the plant. The design is based on utilization of available local material, technology and manpower. The feasibility of production of heavy water in the fertilizer production plants and the extraction of natural uranium from the phospahate mines on the Red Sea coast are considered pointing out further stages of development and future plans.