Applications of Artificial Intelligence Techniques in the Petroleum Industry

Description

Applications of Artificial Intelligence Techniques in the Petroleum Industry gives engineers a critical resource to help them understand the machine learning that will solve specific engineering challenges. The reference begins with fundamentals, covering preprocessing of data, types of intelligent models, and training and optimization algorithms. The book moves on to methodically address artificial intelligence technology and applications by the upstream sector, covering exploration, drilling, reservoir and production engineering. Final sections cover current gaps and future challenges. Cover Title-pag_2020_Applications-of-Artificial-Intelligence-Techniques-in-the-Pet Applications of Artificial Intelligence Techniques in the Petroleum Industry Copyrigh_2020_Applications-of-Artificial-Intelligence-Techniques-in-the-Petr Copyright Content_2020_Applications-of-Artificial-Intelligence-Techniques-in-the-Petro Contents About-the-aut_2020_Applications-of-Artificial-Intelligence-Techniques-in-the About the author Chapter-1---Intro_2020_Applications-of-Artificial-Intelligence-Techniques-in 1 Introduction 1.1 Overview 1.2 Preprocessing of data 1.2.1 Data cleaning 1.2.2 Data integration 1.2.3 Data transformation 1.2.4 Data reduction 1.2.5 Data discretization 1.2.6 Data statistics 1.2.6.1 Skewness 1.2.6.2 Kurtosis 1.3 Processing of data 1.3.1 Data training 1.3.2 Data validation and testing 1.4 Postprocessing of data 1.4.1 Statistical analyses for models’ evaluation 1.4.1.1 Average percent relative error (APRE) 1.4.1.2 Average absolute percent relative error (AAPRE) 1.4.1.3 Root mean square error (RMSE) 1.4.1.4 Standard deviation (SD) 1.4.1.5 Coefficient of determination (R2) 1.4.2 Graphical error analysis for models’ evaluation 1.4.2.1 Error distribution curve 1.4.2.2 Crossplots 1.4.2.3 Cumulative frequency plots versus absolute percent relative error 1.4.2.4 Group error 1.4.2.5 3-D plots 1.5 Applicability domain of a model 1.5.1 Identification of experimental data outliers 1.6 Sensitivity analysis on models’ inputs 1.6.1 Relevancy factor analysis 1.7 The areas of intelligent models applications in the petroleum industry References Chapter-2---Intellig_2020_Applications-of-Artificial-Intelligence-Techniques 2 Intelligent models 2.1 Artificial neural networks 2.1.1 Multilayer perceptron neural network 2.1.2 Radial basis function neural network 2.2 Fuzzy logic systems 2.3 Adaptive neuro-fuzzy inference system 2.4 Support vector machine 2.4.1 Ordinary support vector machine 2.4.2 Least-square support vector machine 2.5 Decision tree 2.5.1 Random forest 2.5.2 Extra trees 2.6 Group method of data handling 2.6.1 Hybrid group method of data handling 2.7 Genetic programming 2.7.1 Multigene genetic programming 2.8 Gene expression programming 2.9 Case-based reasoning 2.10 Committee machine intelligent system References Chapter-3---Training-and-opt_2020_Applications-of-Artificial-Intelligence-Te 3 Training and optimization algorithms 3.1 Overview 3.2 Genetic algorithm 3.3 Differential evolution 3.4 Particle swarm optimization 3.5 Ant colony optimization 3.6 Artificial bee colony 3.7 Firefly algorithm 3.8 Imperialist competitive algorithm 3.9 Simulated annealing 3.10 Coupled simulated annealing 3.11 Gravitational search algorithm 3.12 Cuckoo optimization algorithm 3.13 Gray wolf optimization 3.14 Whale optimization algorithm 3.15 Levenberg–Marquardt algorithm 3.16 Bayesian regularization algorithm 3.17 Scaled conjugate gradient algorithm 3.18 Resilient backpropagation algorithm References Chapter-4---Application-of-intelligen_2020_Applications-of-Artificial-Intell 4 Application of intelligent models in reservoir and production engineering 4.1 Reservoir fluid properties 4.1.1 One-phase properties 4.1.2 Two-phase properties 4.2 Rock properties 4.3 Enhanced oil recovery 4.3.1 Enhanced oil recovery processes 4.3.2 Minimum miscibility pressure 4.4 Well test analysis 4.5 Formation damage 4.6 Asphaltene 4.7 Production pipelines 4.8 Wax 4.9 Other applications References Chapter-5---Application-of-intelli_2020_Applications-of-Artificial-Intellige 5 Application of intelligent models in drilling engineering 5.1 Drilling fluids 5.2 Lost circulation problem 5.3 Stuck pipe 5.4 Flow patterns and frictional pressure loss of two-phase fluids 5.5 Rate of penetration 5.6 Other applications References Chapter-6---Application-of-intellig_2020_Applications-of-Artificial-Intellig 6 Application of intelligent models in exploration engineering 6.1 Overview 6.2 Geochemistry 6.3 Geophysics 6.4 Petro-physics 6.5 Geo-mechanical characterization of organic-rich shales 6.6 Brittleness index in shale gas and tight oils 6.7 Total organic carbon determination 6.8 Shear wave velocity 6.9 Flow units 6.10 Facies identification from well log References Chapter-7---Weaknesses-and-strengths_2020_Applications-of-Artificial-Intelli 7 Weaknesses and strengths of intelligent models in petroleum industry 7.1 Overview 7.2 Intelligent models versus theoretical models 7.3 Intelligent models versus empirical correlations 7.4 Effect of the number of actual data 7.5 Validation of the developed models References Index_2020_Applications-of-Artificial-Intelligence-Techniques-in-the-Petrole Index