Data Driven Science And Engineering

A textbook covering data-science and machine learning methods for modelling and control in engineering and science, with Python and MATLAB®.

Data-driven discovery is revolutionizing the modeling, prediction, and control of complex systems. This textbook brings together machine learning, engineering mathematics, and mathematical physics to integrate modeling and control of dynamical systems with modern methods in data science. It highlights many of the recent advances in scientific computing that enable data-driven methods to be applied to a diverse range of complex systems, such as turbulence, the brain, climate, epidemiology, finance, robotics, and autonomy. Aimed at advanced undergraduate and beginning graduate students in the engineering and physical sciences, the text presents a range of topics and methods from introductory to state of the art.

Combining scientific computing methods and algorithms with modern data analysis techniques, including basic applications of compressive sensing and machine learning, this book develops techniques that allow for the integration of the dynamics of complex systems and big data. MATLAB is used throughout for mathematical solution strategies.

This is the first textbook on a generally applicable control strategy for turbulence and other complex nonlinear systems. The approach of the book employs powerful methods of machine learning for optimal nonlinear control laws. This machine learning control (MLC) is motivated and detailed in Chapters 1 and 2. In Chapter 3, methods of linear control theory are reviewed. In Chapter 4, MLC is shown to reproduce known optimal control laws for linear dynamics (LQR, LQG). In Chapter 5, MLC detects and exploits a strongly nonlinear actuation mechanism of a low-dimensional dynamical system when linear control methods are shown to fail. Experimental control demonstrations from a laminar shear-layer to turbulent boundary-layers are reviewed in Chapter 6, followed by general good practices for experiments in Chapter 7. The book concludes with an outlook on the vast future applications of MLC in Chapter 8. Matlab codes are provided for easy reproducibility of the presented results. The book includes interviews with leading researchers in turbulence control (S. Bagheri, B. Batten, M. Glauser, D. Williams) and machine learning (M. Schoenauer) for a broader perspective. All chapters have exercises and supplemental videos will be available through YouTube.

Data-Driven Traffic Engineering: Understanding of Traffic and Applications Based on Three-Phase Traffic Theory shifts the current focus from using modeling and simulation data for traffic measurements to the use of actual data. The book uses real-world, empirically-derived data from a large fleet of connected vehicles, local observations and aerial observation to shed light on key traffic phenomena. Readers will learn how to develop an understanding of the empirical features of vehicular traffic networks and how to consider these features in emerging, intelligent transport systems. Topics cover congestion patterns, fuel consumption, the influence of weather, and much more. This book offers a unique, data-driven analysis of vehicular traffic in traffic networks, also considering how to apply data-driven insights to the intelligent transport systems of the future. Provides an empirically-driven analysis of traffic measurements/congestion based on real-world data collected from a global fleet of vehicles Applies Kerner’s three-phase traffic theory to empirical data Offers a critical scientific understanding of the underlying concerns of traffic control in automated driving and intelligent transport systems

This book addresses the emerging paradigm of data-driven engineering design. In the big-data era, data is becoming a strategic asset for global manufacturers. This book shows how the power of data can be leveraged to drive the engineering design process, in particular, the early-stage design. Based on novel combinations of standing design methodology and the emerging data science, the book presents a collection of theoretically sound and practically viable design frameworks, which are intended to address a variety of critical design activities including conceptual design, complexity management, smart customization, smart product design, product service integration, and so forth. In addition, it includes a number of detailed case studies to showcase the application of data-driven engineering design. The book concludes with a set of promising research questions that warrant further investigation. Given its scope, the book will appeal to a broad readership, including postgraduate students, researchers, lecturers, and practitioners in the field of engineering design.

This book introduces condition-based maintenance (CBM)/data-driven prognostics and health management (PHM) in detail, first explaining the PHM design approach from a systems engineering perspective, then summarizing and elaborating on the data-driven methodology for feature construction, as well as feature-based fault diagnosis and prognosis. The book includes a wealth of illustrations and tables to help explain the algorithms, as well as practical examples showing how to use this tool to solve situations for which analytic solutions are poorly suited. It equips readers to apply the concepts discussed in order to analyze and solve a variety of problems in PHM system design, feature construction, fault diagnosis and prognosis.

Materials informatics: a ‘hot topic’ area in materials science, aims to combine traditionally bio-led informatics with computational methodologies, supporting more efficient research by identifying strategies for time- and cost-effective analysis. The discovery and maturation of new materials has been outpaced by the thicket of data created by new combinatorial and high throughput analytical techniques. The elaboration of this "quantitative avalanche"—and the resulting complex, multi-factor analyses required to understand it—means that interest, investment, and research are revisiting informatics approaches as a solution. This work, from Krishna Rajan, the leading expert of the informatics approach to materials, seeks to break down the barriers between data management, quality standards, data mining, exchange, and storage and analysis, as a means of accelerating scientific research in materials science. This solutions-based reference synthesizes foundational physical, statistical, and mathematical content with emerging experimental and real-world applications, for interdisciplinary researchers and those new to the field. Identifies and analyzes interdisciplinary strategies (including combinatorial and high throughput approaches) that accelerate materials development cycle times and reduces associated costs Mathematical and computational analysis aids formulation of new structure-property correlations among large, heterogeneous, and distributed data sets Practical examples, computational tools, and software analysis benefits rapid identification of critical data and analysis of theoretical needs for future problems