Designing a computational model to predict petroleum crisis and a practical model to use hydrogen fuel as an alternative

Abstract

newlinePetroleum is being consumed at a rapid pace all over the world, but the amount of newlinepetroleum is constant in earth crust and production to consumption requirement is not up to newlinemark. It is expected that a day may come when this world will witness the crisis of this oil. newlineIn this present work, it predicts that petroleum production over consumption with respect to newlinethe sharp increase of population, leads to a decisive issue in the production of an alternative newlinefuel. Hydrogen fuel has been identified as the highest clean potential energy carrier similar newlineto electricity. Energy carriers are used to move, store and deliver energy in a form that can newlinebe easily used. For this reason hydrogen fuel will be most likely to be an alternate newlinerenewable energy source in the future. Hydrogen fuel can be used in internal combustion newlineengines or fuel cells emitting environmentally beneficial transportation fuel. newlineOne can solve this type of problem to predict accurately based upon a guess by newlinetaking various degrees of information from the past and from the current state. In the newlinetechnical domain, some computational techniques can be used to solve the prediction newlineproblem. The basic criteria for future prediction are based upon either the value or the trend newlineof a variable with a corresponding fitness function. The prediction of petroleum crisis in the newlineworld we are using novel and suitable Artificial Neural Network (ANN) based approach. newlineThe set of observation comprising three features like population, petroleum production and newlinepetroleum consumption of different countries are being considered to design the predictive newlinemodel. In our analysis, we used the data provided by different government sources of the newlineten countries (like USA, Middle East countries, China and India, etc.) over a period of newlinemore than 30 years and then simulated by a nonlinear and multistep ahead prediction newlinemethodology, i.e. nonlinear autoregressive network (NARnet) to predict petroleum crisis in newlinenear future. The NARnet model simulates the current data, i.e. known values and newlinedynamically simulates all these for the multistep ahead prediction. By this dynamic newlinemethod, simulating the present data, we can predict any number of future data as desired. newlineThe normalized mean square error (NMSE) of our prediction method, i.e. NARnet has been newlineverified by different standard predictive methods to handle the data set and found to be newlinebetter in its performance. It has been predicted that by 2050, hydrogen fuel may be a newlinesuitable replacement for petroleum, and will not only reduce pollution, but also enhances newlinethe fuel efficiency at lower cost as compared to that of petroleum. newlineviii newlineThe main challenge is the storage of the hydrogen fuel and to carry the fuel. The newlinemain problem arises to make the practically feasible container addressing the various newlineproblems due to some basic nature of the hydrogen element. By considering the major newlineproblem attempt was taken to design a model to show the suitable material which could be newlineperfect to use as a hydrogen fuel container. For that reason, prior to fabrication and newlineselection of appropriate materials, simulation is extensively required to avoid wastage of newlinetime and expenditure. newlineBased on scientific literature and our oxidation model, it has been observed that, newlineTiO2 nanotubes grown on Ti substrates (Ti-TiO2) by anodization method may considered as newlinepromising materials for hydrogen storage application. The oxidation model is built to show newlinethe effectiveness of Ti plate over other metals as the inner oxidation in wet oxidation newlinemethod is very less as compared to other metals. The thickness of TiO2 thin film grown on newlineTi plate (Ti-TiO2) by anodization method was experimentally verified as oxidation newlinesimulated value.