Author: Sandmeier, Nino
Publisher: Universitätsverlag der TU Berlin
ISBN: 3798332479
Category : Technology & Engineering
Languages : en
Pages : 236
Book Description
This thesis deals with the development of a model-based adaptive test design strategy with a focus on steady-state combustion engine calibration. The first research topic investigates the question how to handle limits in the input domain during an adaptive test design procedure. The second area of scope aims at identifying the test design method providing the best model quality improvement in terms of overall model prediction error. To consider restricted areas in the input domain, a convex hull-based solution involving a convex cone algorithm is developed, the outcome of which serves as a boundary model for a test point search. A solution is derived to enable the application of the boundary model to high-dimensional problems without calculating the exact convex hull and cones. Furthermore, different data-driven engine modeling methods are compared, resulting in the Gaussian process model as the most suitable one for a model-based calibration. To determine an appropriate test design method for a Gaussian process model application, two new strategies are developed and compared to state-of-the-art methods. A simulation-based study shows the most benefit applying a modified mutual information test design, followed by a newly developed relevance-based test design with less computational effort. The boundary model and the relevance-based test design are integrated into a multicriterial test design strategy that is tailored to match the requirements of combustion engine test bench measurements. A simulation-based study with seven and nine input parameters and four outputs each offered an average model quality improvement of 36 % and an average measured input area volume increase of 65 % compared to a non-adaptive space-filling test design. The multicriterial test design was applied to a test bench measurement with seven inputs for verification. Compared to a space-filling test design measurement, the improvement could be confirmed with an average model quality increase of 17 % over eight outputs and a 34 % larger measured input area. Diese Arbeit befasst sich mit der Entwicklung einer modellbasierten adaptiven Versuchsplanungsstrategie für die Anwendung in der Applikation des Stationärverhaltens von Verbrennungsmotoren. Der erste Forschungsteil untersucht, wie sich Grenzen im Eingangsraum in die Versuchsplanung eines adaptiven Prozesses einbinden lassen. Ein weiterer Fokus liegt auf der Identifikation einer modellbasierten Versuchsplanung, die eine bestmögliche Verbesserung der globalen Modellqualität hinsichtlich des Prädiktionsfehlers ermöglicht. Es wird ein Grenzraummodell auf Basis der konvexen Hülle unter Zuhilfenahme eines Algorithmus zur Bestimmung eines konvexen Konus entwickelt, das als Grundlage für eine Versuchsplanung in beschränkten Eingangsräumen verwendet wird. Um die Anwendbarkeit bei hochdimensionalen Problemstellungen zu gewährleisten, wird ein Verfahren vorgestellt, das eine Berechnung auch ohne die Bestimmung der exakten konvexen Hülle und konvexen Konen ermöglicht. Des Weiteren werden verschiedene Methoden zur datengetriebenen Modellbildung des Verbrennungsmotors verglichen, wobei das Gauß-Prozess Modell als die geeignetste Modellierungsmethode hervorgeht. Um die bestmögliche Versuchsplanungsmethode bei der Anwendung des Gauß-Prozess Modells zu ermitteln, werden zwei neue Strategien entwickelt und mit verfügbaren Methoden aus der Literatur verglichen. Eine simulationsbasierte Studie zeigt, dass eine angepasste Mutual Information Methode die besten Ergebnisse liefert. Ein neu entwickeltes relevanzbasiertes Verfahren erreicht die zweitbesten Ergebnisse, bietet aber einen geringeren Berechnungsaufwand als das Mutual Information Verfahren. Das Grenzmodell und das relevanzbasierte Verfahren werden in einem multikriteriellen Versuchsplanungsverfahren zusammengeführt, das an die Anforderungen von Messungen an einem Verbrennungsmotorenprüfstand angepasst ist. In einer simulationsbasierten Studie mit sieben bzw. neun Eingangsparametern und jeweils vier Ausgängen konnte eine durchschnittliche Modellqualitätsverbesserung von 36 % und eine mittlere Vergrößerung des vermessenen Eingangsraumvolumens von 65 % im Vergleich zu einer nichtadaptiven raumfüllenden Versuchsplanung gezeigt werden. Das multikriterielle Versuchsplanungsverfahren wurde anhand von Prüfstandsmessungen mit sieben Eingangsparametern verifiziert. Im Vergleich zu einer raumfüllenden Versuchsplanung konnte eine mittlere Modellqualitätsverbesserung über alle acht Ausgänge von 17 % und ein um 34 % vergrößertes vermessenes Eingangsraumvolumen erreicht werden, wodurch die Ergebnisse der Simulationen bestätigt werden konnten.
Optimization of adaptive test design methods for the determination of steady-state data-driven models in terms of combustion engine calibration
Author: Sandmeier, Nino
Publisher: Universitätsverlag der TU Berlin
ISBN: 3798332479
Category : Technology & Engineering
Languages : en
Pages : 236
Book Description
This thesis deals with the development of a model-based adaptive test design strategy with a focus on steady-state combustion engine calibration. The first research topic investigates the question how to handle limits in the input domain during an adaptive test design procedure. The second area of scope aims at identifying the test design method providing the best model quality improvement in terms of overall model prediction error. To consider restricted areas in the input domain, a convex hull-based solution involving a convex cone algorithm is developed, the outcome of which serves as a boundary model for a test point search. A solution is derived to enable the application of the boundary model to high-dimensional problems without calculating the exact convex hull and cones. Furthermore, different data-driven engine modeling methods are compared, resulting in the Gaussian process model as the most suitable one for a model-based calibration. To determine an appropriate test design method for a Gaussian process model application, two new strategies are developed and compared to state-of-the-art methods. A simulation-based study shows the most benefit applying a modified mutual information test design, followed by a newly developed relevance-based test design with less computational effort. The boundary model and the relevance-based test design are integrated into a multicriterial test design strategy that is tailored to match the requirements of combustion engine test bench measurements. A simulation-based study with seven and nine input parameters and four outputs each offered an average model quality improvement of 36 % and an average measured input area volume increase of 65 % compared to a non-adaptive space-filling test design. The multicriterial test design was applied to a test bench measurement with seven inputs for verification. Compared to a space-filling test design measurement, the improvement could be confirmed with an average model quality increase of 17 % over eight outputs and a 34 % larger measured input area. Diese Arbeit befasst sich mit der Entwicklung einer modellbasierten adaptiven Versuchsplanungsstrategie für die Anwendung in der Applikation des Stationärverhaltens von Verbrennungsmotoren. Der erste Forschungsteil untersucht, wie sich Grenzen im Eingangsraum in die Versuchsplanung eines adaptiven Prozesses einbinden lassen. Ein weiterer Fokus liegt auf der Identifikation einer modellbasierten Versuchsplanung, die eine bestmögliche Verbesserung der globalen Modellqualität hinsichtlich des Prädiktionsfehlers ermöglicht. Es wird ein Grenzraummodell auf Basis der konvexen Hülle unter Zuhilfenahme eines Algorithmus zur Bestimmung eines konvexen Konus entwickelt, das als Grundlage für eine Versuchsplanung in beschränkten Eingangsräumen verwendet wird. Um die Anwendbarkeit bei hochdimensionalen Problemstellungen zu gewährleisten, wird ein Verfahren vorgestellt, das eine Berechnung auch ohne die Bestimmung der exakten konvexen Hülle und konvexen Konen ermöglicht. Des Weiteren werden verschiedene Methoden zur datengetriebenen Modellbildung des Verbrennungsmotors verglichen, wobei das Gauß-Prozess Modell als die geeignetste Modellierungsmethode hervorgeht. Um die bestmögliche Versuchsplanungsmethode bei der Anwendung des Gauß-Prozess Modells zu ermitteln, werden zwei neue Strategien entwickelt und mit verfügbaren Methoden aus der Literatur verglichen. Eine simulationsbasierte Studie zeigt, dass eine angepasste Mutual Information Methode die besten Ergebnisse liefert. Ein neu entwickeltes relevanzbasiertes Verfahren erreicht die zweitbesten Ergebnisse, bietet aber einen geringeren Berechnungsaufwand als das Mutual Information Verfahren. Das Grenzmodell und das relevanzbasierte Verfahren werden in einem multikriteriellen Versuchsplanungsverfahren zusammengeführt, das an die Anforderungen von Messungen an einem Verbrennungsmotorenprüfstand angepasst ist. In einer simulationsbasierten Studie mit sieben bzw. neun Eingangsparametern und jeweils vier Ausgängen konnte eine durchschnittliche Modellqualitätsverbesserung von 36 % und eine mittlere Vergrößerung des vermessenen Eingangsraumvolumens von 65 % im Vergleich zu einer nichtadaptiven raumfüllenden Versuchsplanung gezeigt werden. Das multikriterielle Versuchsplanungsverfahren wurde anhand von Prüfstandsmessungen mit sieben Eingangsparametern verifiziert. Im Vergleich zu einer raumfüllenden Versuchsplanung konnte eine mittlere Modellqualitätsverbesserung über alle acht Ausgänge von 17 % und ein um 34 % vergrößertes vermessenes Eingangsraumvolumen erreicht werden, wodurch die Ergebnisse der Simulationen bestätigt werden konnten.
Publisher: Universitätsverlag der TU Berlin
ISBN: 3798332479
Category : Technology & Engineering
Languages : en
Pages : 236
Book Description
This thesis deals with the development of a model-based adaptive test design strategy with a focus on steady-state combustion engine calibration. The first research topic investigates the question how to handle limits in the input domain during an adaptive test design procedure. The second area of scope aims at identifying the test design method providing the best model quality improvement in terms of overall model prediction error. To consider restricted areas in the input domain, a convex hull-based solution involving a convex cone algorithm is developed, the outcome of which serves as a boundary model for a test point search. A solution is derived to enable the application of the boundary model to high-dimensional problems without calculating the exact convex hull and cones. Furthermore, different data-driven engine modeling methods are compared, resulting in the Gaussian process model as the most suitable one for a model-based calibration. To determine an appropriate test design method for a Gaussian process model application, two new strategies are developed and compared to state-of-the-art methods. A simulation-based study shows the most benefit applying a modified mutual information test design, followed by a newly developed relevance-based test design with less computational effort. The boundary model and the relevance-based test design are integrated into a multicriterial test design strategy that is tailored to match the requirements of combustion engine test bench measurements. A simulation-based study with seven and nine input parameters and four outputs each offered an average model quality improvement of 36 % and an average measured input area volume increase of 65 % compared to a non-adaptive space-filling test design. The multicriterial test design was applied to a test bench measurement with seven inputs for verification. Compared to a space-filling test design measurement, the improvement could be confirmed with an average model quality increase of 17 % over eight outputs and a 34 % larger measured input area. Diese Arbeit befasst sich mit der Entwicklung einer modellbasierten adaptiven Versuchsplanungsstrategie für die Anwendung in der Applikation des Stationärverhaltens von Verbrennungsmotoren. Der erste Forschungsteil untersucht, wie sich Grenzen im Eingangsraum in die Versuchsplanung eines adaptiven Prozesses einbinden lassen. Ein weiterer Fokus liegt auf der Identifikation einer modellbasierten Versuchsplanung, die eine bestmögliche Verbesserung der globalen Modellqualität hinsichtlich des Prädiktionsfehlers ermöglicht. Es wird ein Grenzraummodell auf Basis der konvexen Hülle unter Zuhilfenahme eines Algorithmus zur Bestimmung eines konvexen Konus entwickelt, das als Grundlage für eine Versuchsplanung in beschränkten Eingangsräumen verwendet wird. Um die Anwendbarkeit bei hochdimensionalen Problemstellungen zu gewährleisten, wird ein Verfahren vorgestellt, das eine Berechnung auch ohne die Bestimmung der exakten konvexen Hülle und konvexen Konen ermöglicht. Des Weiteren werden verschiedene Methoden zur datengetriebenen Modellbildung des Verbrennungsmotors verglichen, wobei das Gauß-Prozess Modell als die geeignetste Modellierungsmethode hervorgeht. Um die bestmögliche Versuchsplanungsmethode bei der Anwendung des Gauß-Prozess Modells zu ermitteln, werden zwei neue Strategien entwickelt und mit verfügbaren Methoden aus der Literatur verglichen. Eine simulationsbasierte Studie zeigt, dass eine angepasste Mutual Information Methode die besten Ergebnisse liefert. Ein neu entwickeltes relevanzbasiertes Verfahren erreicht die zweitbesten Ergebnisse, bietet aber einen geringeren Berechnungsaufwand als das Mutual Information Verfahren. Das Grenzmodell und das relevanzbasierte Verfahren werden in einem multikriteriellen Versuchsplanungsverfahren zusammengeführt, das an die Anforderungen von Messungen an einem Verbrennungsmotorenprüfstand angepasst ist. In einer simulationsbasierten Studie mit sieben bzw. neun Eingangsparametern und jeweils vier Ausgängen konnte eine durchschnittliche Modellqualitätsverbesserung von 36 % und eine mittlere Vergrößerung des vermessenen Eingangsraumvolumens von 65 % im Vergleich zu einer nichtadaptiven raumfüllenden Versuchsplanung gezeigt werden. Das multikriterielle Versuchsplanungsverfahren wurde anhand von Prüfstandsmessungen mit sieben Eingangsparametern verifiziert. Im Vergleich zu einer raumfüllenden Versuchsplanung konnte eine mittlere Modellqualitätsverbesserung über alle acht Ausgänge von 17 % und ein um 34 % vergrößertes vermessenes Eingangsraumvolumen erreicht werden, wodurch die Ergebnisse der Simulationen bestätigt werden konnten.
Fundamentals of Design of Experiments for Automotive Engineering Volume I
Author: Young J. Chiang
Publisher: SAE International
ISBN: 1468606026
Category : Computers
Languages : en
Pages : 358
Book Description
In a world where innovation and sustainability are paramount, Fundamentals of Design of Experiments for Automotive Engineering: Volume I serves as a definitive guide to harnessing the power of statistical thinking in product development. As first of four volumes in SAE International’s DOE for Product Reliability Growth series, this book presents a practical, application-focused approach by emphasizing DOE as a dynamic tool for automotive engineers. It showcases real-world examples, demonstrating how process improvements and system optimizations can significantly enhance product reliability. The author, Yung Chiang, leverages extensive product development expertise to present a comprehensive process that ensures product performance and reliability throughout its entire lifecycle. Whether individuals are involved in research, design, testing, manufacturing, or marketing, this essential reference equips them with the skills needed to excel in their respective roles. This book explores the potential of Reliability and Sustainability with DOE, featuring the following topics: - Fundamental prerequisites for deploying DOE: Product reliability processes, measurement uncertainty, failure analysis, and design for reliability. - Full factorial design 2K: A system identification tool for relating objectives to factors and understanding main and interactive effects. - Fractional factorial design 2RK-P: Ideal for identifying main effects and 2-factor interactions. - General fractional factorial design LK-P: Systematically identification of significant inputs and analysis of nonlinear behaviors. - Composite designs as response surface methods: Resolving interactions and optimizing decisions with limited factors. - Adapting to practical challenges with “short” DOE: Leveraging optimization schemes like D-optimality, and A-optimality for optimal results. Readers are encouraged not to allow product failures to hinder progress but to embrace the "statistical thinking" embedded in DOE. This book can illuminate the path to designing products that stand the test of time, resulting in satisfied customers and thriving businesses. (ISBN 9781468606027, ISBN 9781468606034, ISBN 9781468606041, DOI 10.4271/9781468606034)
Publisher: SAE International
ISBN: 1468606026
Category : Computers
Languages : en
Pages : 358
Book Description
In a world where innovation and sustainability are paramount, Fundamentals of Design of Experiments for Automotive Engineering: Volume I serves as a definitive guide to harnessing the power of statistical thinking in product development. As first of four volumes in SAE International’s DOE for Product Reliability Growth series, this book presents a practical, application-focused approach by emphasizing DOE as a dynamic tool for automotive engineers. It showcases real-world examples, demonstrating how process improvements and system optimizations can significantly enhance product reliability. The author, Yung Chiang, leverages extensive product development expertise to present a comprehensive process that ensures product performance and reliability throughout its entire lifecycle. Whether individuals are involved in research, design, testing, manufacturing, or marketing, this essential reference equips them with the skills needed to excel in their respective roles. This book explores the potential of Reliability and Sustainability with DOE, featuring the following topics: - Fundamental prerequisites for deploying DOE: Product reliability processes, measurement uncertainty, failure analysis, and design for reliability. - Full factorial design 2K: A system identification tool for relating objectives to factors and understanding main and interactive effects. - Fractional factorial design 2RK-P: Ideal for identifying main effects and 2-factor interactions. - General fractional factorial design LK-P: Systematically identification of significant inputs and analysis of nonlinear behaviors. - Composite designs as response surface methods: Resolving interactions and optimizing decisions with limited factors. - Adapting to practical challenges with “short” DOE: Leveraging optimization schemes like D-optimality, and A-optimality for optimal results. Readers are encouraged not to allow product failures to hinder progress but to embrace the "statistical thinking" embedded in DOE. This book can illuminate the path to designing products that stand the test of time, resulting in satisfied customers and thriving businesses. (ISBN 9781468606027, ISBN 9781468606034, ISBN 9781468606041, DOI 10.4271/9781468606034)
Nonlinear System Identification
Author: Oliver Nelles
Publisher: Springer Nature
ISBN: 3030474399
Category : Science
Languages : en
Pages : 1235
Book Description
This book provides engineers and scientists in academia and industry with a thorough understanding of the underlying principles of nonlinear system identification. It equips them to apply the models and methods discussed to real problems with confidence, while also making them aware of potential difficulties that may arise in practice. Moreover, the book is self-contained, requiring only a basic grasp of matrix algebra, signals and systems, and statistics. Accordingly, it can also serve as an introduction to linear system identification, and provides a practical overview of the major optimization methods used in engineering. The focus is on gaining an intuitive understanding of the subject and the practical application of the techniques discussed. The book is not written in a theorem/proof style; instead, the mathematics is kept to a minimum, and the ideas covered are illustrated with numerous figures, examples, and real-world applications. In the past, nonlinear system identification was a field characterized by a variety of ad-hoc approaches, each applicable only to a very limited class of systems. With the advent of neural networks, fuzzy models, Gaussian process models, and modern structure optimization techniques, a much broader class of systems can now be handled. Although one major aspect of nonlinear systems is that virtually every one is unique, tools have since been developed that allow each approach to be applied to a wide variety of systems.
Publisher: Springer Nature
ISBN: 3030474399
Category : Science
Languages : en
Pages : 1235
Book Description
This book provides engineers and scientists in academia and industry with a thorough understanding of the underlying principles of nonlinear system identification. It equips them to apply the models and methods discussed to real problems with confidence, while also making them aware of potential difficulties that may arise in practice. Moreover, the book is self-contained, requiring only a basic grasp of matrix algebra, signals and systems, and statistics. Accordingly, it can also serve as an introduction to linear system identification, and provides a practical overview of the major optimization methods used in engineering. The focus is on gaining an intuitive understanding of the subject and the practical application of the techniques discussed. The book is not written in a theorem/proof style; instead, the mathematics is kept to a minimum, and the ideas covered are illustrated with numerous figures, examples, and real-world applications. In the past, nonlinear system identification was a field characterized by a variety of ad-hoc approaches, each applicable only to a very limited class of systems. With the advent of neural networks, fuzzy models, Gaussian process models, and modern structure optimization techniques, a much broader class of systems can now be handled. Although one major aspect of nonlinear systems is that virtually every one is unique, tools have since been developed that allow each approach to be applied to a wide variety of systems.
Data Analytics for Intelligent Transportation Systems
Author: Mashrur Chowdhury
Publisher: Elsevier
ISBN: 0443138796
Category : Computers
Languages : en
Pages : 572
Book Description
Data Analytics for Intelligent Transportation Systems provides in-depth coverage of data-enabled methods for analyzing intelligent transportation systems (ITS), including the tools needed to implement these methods using big data analytics and other computing techniques. The book examines the major characteristics of connected transportation systems, along with the fundamental concepts of how to analyze the data they produce. It explores collecting, archiving, processing, and distributing the data, designing data infrastructures, data management and delivery systems, and the required hardware and software technologies. It presents extensive coverage of existing and forthcoming intelligent transportation systems and data analytics technologies. All fundamentals/concepts presented in this book are explained in the context of ITS. Users will learn everything from the basics of different ITS data types and characteristics to how to evaluate alternative data analytics for different ITS applications. They will discover how to design effective data visualizations, tactics on the planning process, and how to evaluate alternative data analytics for different connected transportation applications, along with key safety and environmental applications for both commercial and passenger vehicles, data privacy and security issues, and the role of social media data in traffic planning. Data Analytics for Intelligent Transportation Systems will prepare an educated ITS workforce and tool builders to make the vision for safe, reliable, and environmentally sustainable intelligent transportation systems a reality. It serves as a primary or supplemental textbook for upper-level undergraduate and graduate ITS courses and a valuable reference for ITS practitioners. - Utilizes real ITS examples to facilitate a quicker grasp of materials presented - Contains contributors from both leading academic and commercial domains - Explains how to design effective data visualizations, tactics on the planning process, and how to evaluate alternative data analytics for different connected transportation applications - Includes exercise problems in each chapter to help readers apply and master the learned fundamentals, concepts, and techniques - New to the second edition: Two new chapters on Quantum Computing in Data Analytics and Society and Environment in ITS Data Analytics
Publisher: Elsevier
ISBN: 0443138796
Category : Computers
Languages : en
Pages : 572
Book Description
Data Analytics for Intelligent Transportation Systems provides in-depth coverage of data-enabled methods for analyzing intelligent transportation systems (ITS), including the tools needed to implement these methods using big data analytics and other computing techniques. The book examines the major characteristics of connected transportation systems, along with the fundamental concepts of how to analyze the data they produce. It explores collecting, archiving, processing, and distributing the data, designing data infrastructures, data management and delivery systems, and the required hardware and software technologies. It presents extensive coverage of existing and forthcoming intelligent transportation systems and data analytics technologies. All fundamentals/concepts presented in this book are explained in the context of ITS. Users will learn everything from the basics of different ITS data types and characteristics to how to evaluate alternative data analytics for different ITS applications. They will discover how to design effective data visualizations, tactics on the planning process, and how to evaluate alternative data analytics for different connected transportation applications, along with key safety and environmental applications for both commercial and passenger vehicles, data privacy and security issues, and the role of social media data in traffic planning. Data Analytics for Intelligent Transportation Systems will prepare an educated ITS workforce and tool builders to make the vision for safe, reliable, and environmentally sustainable intelligent transportation systems a reality. It serves as a primary or supplemental textbook for upper-level undergraduate and graduate ITS courses and a valuable reference for ITS practitioners. - Utilizes real ITS examples to facilitate a quicker grasp of materials presented - Contains contributors from both leading academic and commercial domains - Explains how to design effective data visualizations, tactics on the planning process, and how to evaluate alternative data analytics for different connected transportation applications - Includes exercise problems in each chapter to help readers apply and master the learned fundamentals, concepts, and techniques - New to the second edition: Two new chapters on Quantum Computing in Data Analytics and Society and Environment in ITS Data Analytics
Data Analysis and Applications 1
Author: Christos H. Skiadas
Publisher: John Wiley & Sons
ISBN: 1786303825
Category : Mathematics
Languages : en
Pages : 286
Book Description
This series of books collects a diverse array of work that provides the reader with theoretical and applied information on data analysis methods, models, and techniques, along with appropriate applications. Volume 1 begins with an introductory chapter by Gilbert Saporta, a leading expert in the field, who summarizes the developments in data analysis over the last 50 years. The book is then divided into three parts: Part 1 presents clustering and regression cases; Part 2 examines grouping and decomposition, GARCH and threshold models, structural equations, and SME modeling; and Part 3 presents symbolic data analysis, time series and multiple choice models, modeling in demography, and data mining.
Publisher: John Wiley & Sons
ISBN: 1786303825
Category : Mathematics
Languages : en
Pages : 286
Book Description
This series of books collects a diverse array of work that provides the reader with theoretical and applied information on data analysis methods, models, and techniques, along with appropriate applications. Volume 1 begins with an introductory chapter by Gilbert Saporta, a leading expert in the field, who summarizes the developments in data analysis over the last 50 years. The book is then divided into three parts: Part 1 presents clustering and regression cases; Part 2 examines grouping and decomposition, GARCH and threshold models, structural equations, and SME modeling; and Part 3 presents symbolic data analysis, time series and multiple choice models, modeling in demography, and data mining.
Logic-Driven Traffic Big Data Analytics
Author: Shaopeng Zhong
Publisher: Springer Nature
ISBN: 9811680167
Category : Business & Economics
Languages : en
Pages : 296
Book Description
This book starts from the relationship between urban built environment and travel behavior and focuses on analyzing the origin of traffic phenomena behind the data through multi-source traffic big data, which makes the book unique and different from the previous data-driven traffic big data analysis literature. This book focuses on understanding, estimating, predicting, and optimizing mobility patterns. Readers can find multi-source traffic big data processing methods, related statistical analysis models, and practical case applications from this book. This book bridges the gap between traffic big data, statistical analysis models, and mobility pattern analysis with a systematic investigation of traffic big data’s impact on mobility patterns and urban planning.
Publisher: Springer Nature
ISBN: 9811680167
Category : Business & Economics
Languages : en
Pages : 296
Book Description
This book starts from the relationship between urban built environment and travel behavior and focuses on analyzing the origin of traffic phenomena behind the data through multi-source traffic big data, which makes the book unique and different from the previous data-driven traffic big data analysis literature. This book focuses on understanding, estimating, predicting, and optimizing mobility patterns. Readers can find multi-source traffic big data processing methods, related statistical analysis models, and practical case applications from this book. This book bridges the gap between traffic big data, statistical analysis models, and mobility pattern analysis with a systematic investigation of traffic big data’s impact on mobility patterns and urban planning.
Artificial Intelligence and Data Analytics for Energy Exploration and Production
Author: Fred Aminzadeh
Publisher: John Wiley & Sons
ISBN: 1119879876
Category : Science
Languages : en
Pages : 613
Book Description
ARTIFICAL INTELLIGENCE AND DATA ANALYTICS FOR ENERGY EXPLORATION AND PRODUCTION This groundbreaking new book is written by some of the foremost authorities on the application of data science and artificial intelligence techniques in exploration and production in the energy industry, covering the most comprehensive and updated new processes, concepts, and practical applications in the field. The book provides an in-depth treatment of the foundations of Artificial Intelligence (AI) Machine Learning, and Data Analytics (DA). It also includes many of AI-DA applications in oil and gas reservoirs exploration, development, and production. The book covers the basic technical details on many tools used in “smart oil fields”. This includes topics such as pattern recognition, neural networks, fuzzy logic, evolutionary computing, expert systems, artificial intelligence machine learning, human-computer interface, natural language processing, data analytics and next-generation visualization. While theoretical details will be kept to the minimum, these topics are introduced from oil and gas applications viewpoints. In this volume, many case histories from the recent applications of intelligent data to a number of different oil and gas problems are highlighted. The applications cover a wide spectrum of practical problems from exploration to drilling and field development to production optimization, artificial lift, and secondary recovery. Also, the authors demonstrate the effectiveness of intelligent data analysis methods in dealing with many oil and gas problems requiring combining machine and human intelligence as well as dealing with linguistic and imprecise data and rules.
Publisher: John Wiley & Sons
ISBN: 1119879876
Category : Science
Languages : en
Pages : 613
Book Description
ARTIFICAL INTELLIGENCE AND DATA ANALYTICS FOR ENERGY EXPLORATION AND PRODUCTION This groundbreaking new book is written by some of the foremost authorities on the application of data science and artificial intelligence techniques in exploration and production in the energy industry, covering the most comprehensive and updated new processes, concepts, and practical applications in the field. The book provides an in-depth treatment of the foundations of Artificial Intelligence (AI) Machine Learning, and Data Analytics (DA). It also includes many of AI-DA applications in oil and gas reservoirs exploration, development, and production. The book covers the basic technical details on many tools used in “smart oil fields”. This includes topics such as pattern recognition, neural networks, fuzzy logic, evolutionary computing, expert systems, artificial intelligence machine learning, human-computer interface, natural language processing, data analytics and next-generation visualization. While theoretical details will be kept to the minimum, these topics are introduced from oil and gas applications viewpoints. In this volume, many case histories from the recent applications of intelligent data to a number of different oil and gas problems are highlighted. The applications cover a wide spectrum of practical problems from exploration to drilling and field development to production optimization, artificial lift, and secondary recovery. Also, the authors demonstrate the effectiveness of intelligent data analysis methods in dealing with many oil and gas problems requiring combining machine and human intelligence as well as dealing with linguistic and imprecise data and rules.
ADAS and Automated Driving
Author: Plato Pathrose
Publisher: SAE International
ISBN: 1468604120
Category : Transportation
Languages : en
Pages : 279
Book Description
The day will soon come when you will be able to verbally communicate with a vehicle and instruct it to drive to a location. The car will navigate through street traffic and take you to your destination without additional instruction or effort on your part. Today, this scenario is still in the future, but the automotive industry is racing to toward the finish line to have automated driving vehicles deployed on our roads. ADAS and Automated Driving: A Practical Approach to Verification and Validation focuses on how automated driving systems (ADS) can be developed from concept to a product on the market for widescale public use. It covers practically viable approaches, methods, and techniques with examples from multiple production programs across different organizations. The author provides an overview of the various Advanced Driver Assistance Systems (ADAS) and ADS currently being developed and installed in vehicles. The technology needed for large-scale production and public use of fully autonomous vehicles is still under development, and the creation of such technology is a highly innovative area of the automotive industry. This text is a comprehensive reference for anyone interested in a career focused on the verification and validation of ADAS and ADS. The examples included in the volume provide the reader foundational knowledge and follow best and proven practices from the industry. Using the information in ADAS and Automated Driving, you can kick start your career in the field of ADAS and ADS.
Publisher: SAE International
ISBN: 1468604120
Category : Transportation
Languages : en
Pages : 279
Book Description
The day will soon come when you will be able to verbally communicate with a vehicle and instruct it to drive to a location. The car will navigate through street traffic and take you to your destination without additional instruction or effort on your part. Today, this scenario is still in the future, but the automotive industry is racing to toward the finish line to have automated driving vehicles deployed on our roads. ADAS and Automated Driving: A Practical Approach to Verification and Validation focuses on how automated driving systems (ADS) can be developed from concept to a product on the market for widescale public use. It covers practically viable approaches, methods, and techniques with examples from multiple production programs across different organizations. The author provides an overview of the various Advanced Driver Assistance Systems (ADAS) and ADS currently being developed and installed in vehicles. The technology needed for large-scale production and public use of fully autonomous vehicles is still under development, and the creation of such technology is a highly innovative area of the automotive industry. This text is a comprehensive reference for anyone interested in a career focused on the verification and validation of ADAS and ADS. The examples included in the volume provide the reader foundational knowledge and follow best and proven practices from the industry. Using the information in ADAS and Automated Driving, you can kick start your career in the field of ADAS and ADS.
Analysis Techniques for Racecar Data Acquisition
Author: Jorge Sergers
Publisher: SAE International
ISBN: 0768064597
Category : Computers
Languages : en
Pages : 537
Book Description
Racecar data acquisition used to be limited to well-funded teams in high-profile championships. Today, the cost of electronics has decreased dramatically, making them available to everyone. But the cost of any data acquisition system is a waste of money if the recorded data is not interpreted correctly. This book, updated from the best-selling 2008 edition, contains techniques for analyzing data recorded by any vehicle's data acquisition system. It details how to measure the performance of the vehicle and driver, what can be learned from it, and how this information can be used to advantage next time the vehicle hits the track. Such information is invaluable to racing engineers and managers, race teams, and racing data analysts in all motorsports. Whether measuring the performance of a Formula One racecar or that of a road-legal street car on the local drag strip, the dynamics of vehicles and their drivers remain the same. Identical analysis techniques apply. Some race series have restricted data logging to decrease the team’s running budgets. In these cases it is extremely important that a maximum of information is extracted and interpreted from the hardware at hand. A team that uses data more efficiently will have an edge over the competition. However, the ever-decreasing cost of electronics makes advanced sensors and logging capabilities more accessible for everybody. With this comes the risk of information overload. Techniques are needed to help draw the right conclusions quickly from very large data sets. In addition to updates throughout, this new edition contains three new chapters: one on techniques for analyzing tire performance, one that provides an introduction to metric-driven analysis, a technique that is used throughout the book, and another that explains what kind of information the data contains about the track.
Publisher: SAE International
ISBN: 0768064597
Category : Computers
Languages : en
Pages : 537
Book Description
Racecar data acquisition used to be limited to well-funded teams in high-profile championships. Today, the cost of electronics has decreased dramatically, making them available to everyone. But the cost of any data acquisition system is a waste of money if the recorded data is not interpreted correctly. This book, updated from the best-selling 2008 edition, contains techniques for analyzing data recorded by any vehicle's data acquisition system. It details how to measure the performance of the vehicle and driver, what can be learned from it, and how this information can be used to advantage next time the vehicle hits the track. Such information is invaluable to racing engineers and managers, race teams, and racing data analysts in all motorsports. Whether measuring the performance of a Formula One racecar or that of a road-legal street car on the local drag strip, the dynamics of vehicles and their drivers remain the same. Identical analysis techniques apply. Some race series have restricted data logging to decrease the team’s running budgets. In these cases it is extremely important that a maximum of information is extracted and interpreted from the hardware at hand. A team that uses data more efficiently will have an edge over the competition. However, the ever-decreasing cost of electronics makes advanced sensors and logging capabilities more accessible for everybody. With this comes the risk of information overload. Techniques are needed to help draw the right conclusions quickly from very large data sets. In addition to updates throughout, this new edition contains three new chapters: one on techniques for analyzing tire performance, one that provides an introduction to metric-driven analysis, a technique that is used throughout the book, and another that explains what kind of information the data contains about the track.
Big Data Analytics Methods
Author: Peter Ghavami
Publisher: Walter de Gruyter GmbH & Co KG
ISBN: 1547401567
Category : Business & Economics
Languages : en
Pages : 254
Book Description
Big Data Analytics Methods unveils secrets to advanced analytics techniques ranging from machine learning, random forest classifiers, predictive modeling, cluster analysis, natural language processing (NLP), Kalman filtering and ensembles of models for optimal accuracy of analysis and prediction. More than 100 analytics techniques and methods provide big data professionals, business intelligence professionals and citizen data scientists insight on how to overcome challenges and avoid common pitfalls and traps in data analytics. The book offers solutions and tips on handling missing data, noisy and dirty data, error reduction and boosting signal to reduce noise. It discusses data visualization, prediction, optimization, artificial intelligence, regression analysis, the Cox hazard model and many analytics using case examples with applications in the healthcare, transportation, retail, telecommunication, consulting, manufacturing, energy and financial services industries. This book's state of the art treatment of advanced data analytics methods and important best practices will help readers succeed in data analytics.
Publisher: Walter de Gruyter GmbH & Co KG
ISBN: 1547401567
Category : Business & Economics
Languages : en
Pages : 254
Book Description
Big Data Analytics Methods unveils secrets to advanced analytics techniques ranging from machine learning, random forest classifiers, predictive modeling, cluster analysis, natural language processing (NLP), Kalman filtering and ensembles of models for optimal accuracy of analysis and prediction. More than 100 analytics techniques and methods provide big data professionals, business intelligence professionals and citizen data scientists insight on how to overcome challenges and avoid common pitfalls and traps in data analytics. The book offers solutions and tips on handling missing data, noisy and dirty data, error reduction and boosting signal to reduce noise. It discusses data visualization, prediction, optimization, artificial intelligence, regression analysis, the Cox hazard model and many analytics using case examples with applications in the healthcare, transportation, retail, telecommunication, consulting, manufacturing, energy and financial services industries. This book's state of the art treatment of advanced data analytics methods and important best practices will help readers succeed in data analytics.