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®.

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 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.

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 dynamical systems is a burgeoning field?it connects how measurements of nonlinear dynamical systems and/or complex systems can be used with well-established methods in dynamical systems theory. This is a critically important new direction because the governing equations of many problems under consideration by practitioners in various scientific fields are not typically known. Thus, using data alone to help derive, in an optimal sense, the best dynamical system representation of a given application allows for important new insights. The recently developed dynamic mode decomposition (DMD) is an innovative tool for integrating data with dynamical systems theory. The DMD has deep connections with traditional dynamical systems theory and many recent innovations in compressed sensing and machine learning. Dynamic Mode Decomposition: Data-Driven Modeling of Complex Systems, the first book to address the DMD algorithm, presents a pedagogical and comprehensive approach to all aspects of DMD currently developed or under development; blends theoretical development, example codes, and applications to showcase the theory and its many innovations and uses; highlights the numerous innovations around the DMD algorithm and demonstrates its efficacy using example problems from engineering and the physical and biological sciences; and provides extensive MATLAB code, data for intuitive examples of key methods, and graphical presentations.

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

Discover solutions to common obstacles faced by project managers. Written as a business novel, the book is highly interactive, allowing readers to participate and consider options at each stage of a project. The book is based on years of experience, both through the author's research projects as well as his teaching lectures at business schools. The book tells the story of Emily Reed and her colleagues who are in charge of the management of a new tennis stadium project. The CEO of the company, Jacob Mitchell, is planning to install a new data-driven project management methodology as a decision support tool for all upcoming projects. He challenges Emily and her team to start a journey in exploring project data to fight against unexpected project obstacles. Data-driven project management is known in the academic literature as “dynamic scheduling” or “integrated project management and control.” It is a project management methodology to plan, monitor, and control projects in progress in order to deliver them on time and within budget to the client. Its main focus is on the integration of three crucial aspects, as follows: Baseline Scheduling: Plan the project activities to create a project timetable with time and budget restrictions. Determine start and finish times of each project activity within the activity network and resource constraints. Know the expected timing of the work to be done as well as an expected impact on the project’s time and budget objectives. Schedule Risk Analysis: Analyze the risk of the baseline schedule and its impact on the project’s time and budget. Use Monte Carlo simulations to assess the risk of the baseline schedule and to forecast the impact of time and budget deviations on the project objectives. Project Control: Measure and analyze the project’s performance data and take actions to bring the project on track. Monitor deviations from the expected project progress and control performance in order to facilitate the decision-making process in case corrective actions are needed to bring projects back on track. Both traditional Earned Value Management (EVM) and the novel Earned Schedule (ES) methods are used. What You'll Learn Implement a data-driven project management methodology (also known as "dynamic scheduling") which allows project managers to plan, monitor, and control projects while delivering them on time and within budget Study different project management tools and techniques, such as PERT/CPM, schedule risk analysis (SRA), resource buffering, and earned value management (EVM) Understand the three aspects of dynamic scheduling: baseline scheduling, schedule risk analysis, and project control Who This Book Is For Project managers looking to learn data-driven project management (or "dynamic scheduling") via a novel, demonstrating real-time simulations of how project managers can solve common project obstacles