Design and Operation of Production Networks for Mass Personalization in the Era of Cloud Technology

__Design and Operation of Production Networks for Mass Personalization in the Era of Cloud Technology__ draws on the latest industry advances to provide everything needed for the effective implementation of this powerful tool. Shorter product lifecycles have increased pressure on manufacturers through the increasing variety and complexity of production, challenging their workforce to remain competitive and profitable. This has led to innovation in production network methodologies, which together with opportunities provided by new digital technologies has fed a rapid evolution of production engineering that has opened new solutions to the challenges of mass personalization and market uncertainty. In addition to the latest developments in cloud technology, reference is made to key enabling technologies, including artificial intelligence, the digital twin, big data analytics, and the internet of things (IoT) to help users integrate the cloud approach with a fully digitalized production system. Front Cover Design and Operation of Production Networks for Mass Personalization in the Era of Cloud Technology Copyright Contents Contributors Preface Acknowledgments Chapter 1 Introduction to cloud technology and Industry 4.0 1.1 Introduction 1.2 Structure of the book 1.2.1 Distinctive features of this book 1.2.2 Expected trends in production networks for mass personalization in the cloud technology era 1.2.3 Latest advances in cloud manufacturing and global production networks enabling the shift to the mass personaliza ... 1.2.4 The mass personalization of global production networks 1.2.5 Production management guided by industrial Internet of things and adaptive scheduling in smart factories 1.2.6 Digital technologies as a solution to complexity caused by mass personalization 1.2.7 Innovative smart scheduling, and predictive maintenance tools and techniques 1.2.8 Review of commercial and open technologies available for industrial Internet of things 1.2.9 The role of big data analytics in the context of modeling design and operation of manufacturing systems 1.2.10 Digital twins in Industry 4.0 1.2.11 Review of machine learning technologies and artificial intelligence in modern manufacturing systems 1.2.12 Blockchain-enabled product lifecycle management References Chapter 2 Expected trends in production networks for mass personalization in the cloud technology era 2.1 Introduction 2.2 Emerging technologies enabling new production paradigms 2.2.1 I4.0 technologies enabling reconfigurable SC (X-network) and intertwined supply network (ISN) 2.2.1.1 Big data analytics in supply chains 2.2.1.2 Digital twin 2.2.1.3 Additive manufacturing 2.2.1.4 Advanced tracing and tracking systems 2.2.2 I4.0 enabling factory production network 2.2.2.1 Cloud manufacturing 2.2.2.2 Big data analytics in production systems 2.2.2.3 Artificial intelligence 2.2.2.4 Smart intralogistics and autonomous mobile robots 2.3 Trends in supply chain: Reconfigurable SC (X-network) and intertwined supply network (ISN) 2.4 Trends in production systems: Factory production networks 2.5 Conclusions References Chapter 3 Latest advances in cloud manufacturing and global production networks enabling the shift to the mass personaliza ... 3.1 Motivation and section structure 3.2 Main characteristics of MPP 3.3 Global production networks (GPNs) and cloud manufacturing (CM) 3.3.1 Framework for designing and operating GPNs 3.3.2 Challenges 3.3.3 Enablers 3.3.4 Cloud manufacturing 3.4 Impact of MPP on the design and operation of GPNs 3.4.1 Implications and challenges of MPP for production strategy 3.4.2 Enabling concepts for production strategy 3.4.3 Implications and challenges for network footprint 3.4.4 Enabling concepts for network footprint 3.4.5 Implications and challenges for network management 3.4.6 Enabling concepts for network management 3.5 Practical examples 3.5.1 Use case 1: Improving product quality at and customer satisfaction with a tier-1-supplier by applying Industry 4 ... 3.5.2 Use case 2: Development of a platform for the configuration and operation of manufacturer-independent production ... 3.6 Summary and future research needs References Further reading Chapter 4 The mass personalization of global networks 4.1 Introduction 4.2 Evolution of manufacturing paradigms 4.3 Manufacturing networks life cycle 4.3.1 Supply chain 4.3.2 Configuration of a production network 4.3.3 Management and planning of production networks 4.3.4 Simulation and ICT support systems for production networks life cycle 4.3.5 Cloud computing in Industry 4.0 4.4 Industrial frameworks and case studies from mass customization (MC) toward mass personalization (MP) 4.5 Discussion and outlook 4.6 Conclusions References Chapter 5 Production management guided by industrial internet of things and adaptive scheduling in smart factories 5.1 Introduction 5.1.1 Level one: Sensors and actuators—Connecting what should be connected 5.1.2 Level two: Systems and internal services—Monitor and manage 5.1.3 Level three: Connectivity—Connect for new applications and capabilities 5.1.4 Level four: New services and ecosystems—Transformation 5.2 State of the art 5.2.1 Adaptive scheduling in cloud manufacturing 5.2.2 Developments in smart scheduling technologies 5.3 Decision-making frameworks in smart factories 5.4 Production networks toward mass personalization 5.5 Discussion and outlook 5.5.1 Digital skills toward Engineer 4.0 5.5.2 Outlook 5.6 Conclusions References Chapter 6 Digital technologies as a solution to complexity caused by mass personalization 6.1 Introduction 6.2 Digital technologies for product development 6.2.1 Product design 6.2.2 Product manufacturing 6.2.3 Manufacturing and product service 6.3 Product data and lifecycle management platforms 6.4 Conclusions and outlook References Chapter 7 Innovative smart scheduling and predictive maintenance techniques 7.1 Background 7.2 Motivation 7.3 CPS and industry 4.0 7.3.1 CPS 7.3.1.1 Smart connection 7.3.1.2 Data-to-information conversion 7.3.1.3 Cyber 7.3.1.4 Cognition 7.3.1.5 Configuration 7.3.2 Industry 4.0 7.4 Smart scheduling 7.4.1 Overview of scheduling methods 7.4.2 Need for smart scheduling 7.4.3 Prevailing techniques for smart scheduling 7.5 Predictive maintenance 7.5.1 Overview of maintenance strategies 7.5.2 Time-based vs condition-based techniques 7.5.2.1 Time-based maintenance 7.5.2.2 Condition-based maintenance Condition monitoring Vibration monitoring Sound or acoustic monitoring Oil analysis or lubricant monitoring Other CM techniques Maintenance decision-making 7.5.3 Predictive maintenance 7.5.3.1 Random forests 7.5.3.2 Artificial neural networks 7.5.3.3 Support vector machine 7.5.3.4 K-means 7.5.4 From predictive to prescriptive maintenance 7.6 Conclusion and future research direction References Chapter 8 Review of commercial and open technologies available for Industrial Internet of Things 8.1 Introduction 8.2 Fundamentals and state of the art 8.2.1 History and definition 8.2.2 Similarities and differences of IoT and IIoT 8.2.3 State of the art: Existing frameworks 8.2.3.1 Industrial internet architecture framework ( Lin et al., 2019) 8.2.3.2 RAMI 4.0 ( Plattform Industrie 4.0, 2018) 8.2.3.3 Internet of production ( Schuh, Prote, et al., 2020) 8.2.4 Data sovereignty 8.2.4.1 International data spaces reference architecture ( Otto & Jarke, 2019) 8.2.4.2 GAIA-X ( Bundesministerium für Wirtschaft und Energie, 2020) 8.3 IIoT framework 8.3.1 Framework description 8.3.1.1 Layer model 8.3.1.2 Framework processes 8.3.1.3 Cross-enterprise data exchange 8.3.2 Use cases in the IIoT framework 8.3.2.1 Material tracking and transportation 8.3.2.2 3D-assembly instructions and automated quality inspection 8.3.2.3 Data-based smart farming platform 8.4 IIoT development 8.4.1 Commercial IIoT platforms 8.4.2 Edge technologies for on-premise IIoT operations 8.5 IIoT impact 8.5.1 Data transparency by Henkel 8.5.2 Emerging data platforms 8.5.3 Subscription by KAESER 8.6 Summary and reflection References Chapter 9 The role of big data analytics in the context of modeling design and operation of manufacturing systems 9.1 Introduction 9.2 Generic framework for data utilization in industrial environments 9.3 Sources of data in an industrial environment 9.4 Data modeling, semantics, and knowledge extraction 9.5 Process modeling, key feature for the optimization of design and operation of manufacturing systems 9.6 Data contribution to design phase 9.7 Data contribution to the operation of manufacturing systems 9.8 Modeling, design and operation of manufacturing systems for achieving zero defect manufacturing 9.9 Conclusions References Chapter 10 Digital twins in industry 4.0 10.1 Introduction 10.2 Value of digital twins 10.2.1 Advantages of digital twins 10.2.2 Data role in DTs 10.2.3 Product improvement and creation 10.2.4 Product value for life 10.3 Definition of DTs and levels 10.3.1 Definition 10.3.2 Digital model 10.3.3 Digital shadow 10.3.4 Digital twin 10.4 Enabling technologies 10.4.1 Data acquisition technologies 10.4.2 High-fidelity modeling 10.4.3 Simulation-based modeling 10.5 DT architecture 10.5.1 Physical asset 10.5.2 Virtual asset 10.5.3 Services 10.5.4 Data 10.5.5 Connections 10.6 Applications in industry 4.0 10.6.1 DT in low-level manufacturing processes 10.6.2 DT in mid-level robotics-machines 10.6.3 DT in high-level manufacturing systems 10.7 Socio-economic impact 10.8 Future challenges 10.9 Conclusions References Chapter 11 Review of machine learning technologies and artificial intelligence in modern manufacturing systems 11.1 Introduction 11.2 Definition of artificial intelligence 11.3 Definition of machine learning 11.4 Applications of AI in manufacturing 11.4.1 Genetic algorithms 11.4.2 Supervised learning 11.4.3 Unsupervised learning 11.4.4 Reinforcement learning 11.4.5 Deep learning 11.5 Discussion and outlook 11.5.1 Importance of AI in manufacturing 11.5.2 Challenges of AI in manufacturing 11.5.2.1 Data processing and collection 11.5.2.2 Real-time response 11.5.2.3 Flexibility in application 11.5.3 Opportunities of AI in manufacturing 11.6 Future developments and roadmap References Chapter 12 Blockchain-enabled product lifecycle management 12.1 Introduction 12.2 PLM: Concepts, framework, and key phases 12.3 Challenges of PLM in I4.0 12.4 Blockchain for PLM: Opportunities 12.4.1 Blockchain-based framework for PLM 12.4.2 Blockchain-enabled assessment 12.4.3 Blockchain-enabled Cocreation 12.4.4 Blockchain-enabled quick inquiry of tracking and tracing 12.4.5 Blockchain-enabled maintenance 12.4.6 Blockchain-enabled recycling 12.5 Blockchain-enabled PLM: Case studies 12.5.1 Implications from aerospace and aviation industry 12.5.2 Under the Covid-19 pandemic 12.6 Conclusions References Index Back Cover Design and Operation of Production Networks for Mass Personalization in the Era of Cloud Technology draws on the latest industry advances to provide everything needed for the effective implementation of this powerful tool. Shorter product lifecycles have increased pressure on manufacturers through the increasing variety and complexity of production, challenging their workforce to remain competitive and profitable. This has led to innovation in production network methodologies, which together with opportunities provided by new digital technologies has fed a rapid evolution of production engineering that has opened new solutions to the challenges of mass personalization and market uncertainty. In addition to the latest developments in cloud technology, reference is made to key enabling technologies, including artificial intelligence, the digital twin, big data analytics, and the internet of things (IoT) to help users integrate the cloud approach with a fully digitalized production system. Presents diverse cases that show how cloud-based technologies can be used in different ways as part of the standard operation of global production networks Provides detailed reviews of new technologies like the digital twin, big data analytics, and blockchain to provide context on the role of cloud technologies in a fully digitalized system Explores future trends for cloud technology and production engineering