book

Digital Twins in Action

Name: Digital Twins in Action
Author: Greg Biegel
ISBN: 9781633434653

by Greg Biegel

July 2026

Intermediate

344 pages

10h 11m

English

Manning Publications

Read now

Unlock full access

Digital Twins in Action
copyright
contents
preface
acknowledgments
about this book
about the author
about the cover illustration
1 Bridging the physical and digital worlds
1.1 What is a digital twin?1.2 Technologies enabling digital twins1.2.1 Internet of things1.2.2 Cloud computing1.2.3 Machine learning and artificial intelligence1.2.4 Visualization technologies and game engines1.2.5 Agentic AI and autonomous decision-making1.3 Digital twin capability levels1.3.1 Descriptive digital twin1.3.2 Informative digital twin1.3.3 Predictive digital twin1.3.4 Comprehensive digital twin1.3.5 Autonomous digital twin1.4 What are digital twins used for?1.4.1 Accelerating product development1.4.2 Reducing costs through predictive maintenance1.4.3 Optimizing performance and operational efficiency1.4.4 Training and simulation1.5 Digital twins across industries1.5.1 Mining, energy, and industrial1.5.2 Automotive1.5.3 Agriculture1.5.4 Defense1.5.5 Healthcare1.5.6 Infrastructure1.5.7 Smart buildings, cities, and states1.5.8 What a digital twin is not good for1.6 Building your first digital twin: Key considerations and challenges1.6.1 A clear definition of success1.6.2 Data quality1.6.3 Skills gap1.6.4 Build vs. buy1.6.5 Governance and security
2 Mapping physical systems to digital representations
2.1 Defining your objectives2.1.1 Identify specific challenges and opportunities2.1.2 Establish measurable performance indicators and baselines2.1.3 Map decision-making improvements2.1.4 Define a minimum viable digital representation2.2 A home digital twin to optimize energy and water use2.2.1 Mapping the home to a digital representation2.2.2 Start with what you have2.3 Information sources for digital representation2.3.1 Historical records2.3.2 Photographs2.3.3 Videos2.3.4 Engineering documents2.3.5 External systems2.4 Spatial and geometric representations2.4.1 2D geometric models2.4.2 3D geometric models2.5 Spatial mapping and reference systems2.5.1 Coordinate systems and projections2.5.2 Coordinate transformations and conversions2.6 Deciding what you need

3 Sensing the real world
3.1 How sensors work3.1.1 The sensor signal chain3.1.2 Key sensor characteristics3.2 Selecting the right sensors for your digital twin3.2.1 Defining what you’re measuring3.2.2 Matching sensor capabilities to real-world constraints3.2.3 Verifying integration before purchasing3.2.4 Choosing sensors for a home digital twin3.3 Connecting sensors: Communication technologies3.3.1 Short-range technologies (<100 m)3.3.2 Long-range technologies (>100 m)3.3.3 Choosing the right technology3.3.4 Universal data transport architecture3.4 Real-world data collection strategies3.4.1 Edge processing3.4.2 When electronic sensing isn’t enough3.4.3 Manual sensing strategies3.5 Data processing3.5.1 Understanding IoT data characteristics3.5.2 Message decoding3.5.3 Sensor fusion3.6 Scalability and device management3.7 Bringing it all together3.7.1 Data flow walkthrough3.7.2 Architectural principles
4 Data integration and management
4.1 Types of data4.1.1 Reference data4.1.2 Time-series data4.1.3 Unstructured and semi-structured data4.1.4 Spatial data4.1.5 Derived data4.2 Data sources4.2.1 OT data sources4.2.2 IT data sources4.2.3 The convergence of IT and OT4.2.4 External data sources4.3 Data structures and storage4.3.1 Relational and transactional data4.3.2 Columnar and analytical storage4.3.3 Time-series data storage4.3.4 Semi-structured and document data4.3.5 Object storage, data lakes, and lakehouses4.3.6 Specialized storage systems4.3.7 Data life cycle management4.4 Data ingestion4.4.1 Batch data ingestion4.4.2 Streaming data ingestion4.4.3 API integration4.4.4 ETL and data transformation4.5 Data governance and compliance4.5.1 Data classification and sensitivity4.5.2 Regulatory compliance4.5.3 Access control and authentication4.5.4 Data quality4.6 Selecting the right combination4.7 Data store for a home digital twin4.7.1 Storing time-series data4.7.2 Storing object data4.7.3 Storing relationship data
5 Modeling reality
5.1 Making sense of data5.1.1 From measurements to decisions5.1.2 The knowledge engineering challenge5.2 Understanding context in digital twins5.2.1 Types of context5.2.2 How to contextualize data5.2.3 The importance of context in generative AI5.3 Ontologies as a blueprint for understanding5.3.1 Core components of an ontology for a digital twin5.3.2 Defining ontologies for digital twins5.3.3 Choosing an ontology for your model5.4 Knowledge graphs5.4.1 Graph theory5.4.2 Building a knowledge graph as a labeled property graph5.4.3 Graph traversals5.4.4 Building a knowledge graph of my home5.4.5 Choosing a knowledge graph service5.5 Standards and interoperability5.5.1 A framework for implementing standards in your digital twin5.5.2 Practical standards assessment5.5.3 A practical assessment framework5.5.4 Real-world example: The Asset Administration Shell5.6 Serving the model of reality5.6.1 Context-aware data retrieval5.6.2 Building an API layer for my home digital twin5.6.3 The power of a GraphQL schema
6 2D Visualization and insight
6.1 Why graphical visualization matters in digital twins6.1.1 Data-to-visual mapping principles6.1.2 User experience considerations6.2 2D visualization techniques6.2.1 Charts, graphs, and data visualization6.2.2 Dashboards and control panels6.2.3 Schematic diagrams6.2.4 Spatial 2D visualization6.2.5 Heatmaps6.3 2D visualization performance considerations6.3.1 Choosing the right rendering technology6.3.2 Data decimation and aggregation for time-series data6.4 Building effective visualizations with Grafana6.4.1 Why Grafana works well for digital twins6.4.2 Choosing a visualization platform
7 Spatial context and 3D insight
7.1 3D visualization fundamentals for digital twins7.1.1 More complex models7.1.2 Texturing the mesh7.1.3 Web-based 3D visualization7.2 Creating a mesh-based 3D geometric model7.2.1 Serving the model via the web7.2.2 Spatially locating the model7.3 Data integration7.3.1 The importance of spatially locating data in 3D7.3.2 Annotation and markup7.3.3 3D visualization performance considerations7.4 Capturing reality in 3D7.4.1 360-degree photography7.4.2 Photogrammetry7.4.3 Neural Radiance Fields7.4.4 Gaussian splatting7.4.5 Light detection and ranging7.4.6 Simultaneous localization and mapping7.4.7 Universal Scene Description and the NVIDIA Omniverse7.5 Extended reality7.5.1 Virtual reality: Full immersion7.5.2 Augmented reality: Contextual overlay7.5.3 Mixed reality: Blending worlds7.6 Building effective visualizations7.6.1 Security and access control7.6.2 Usability and user experience7.6.3 Data-to-visualization pipeline and scalability
8 Integrating inference and intelligence
8.1 A practical data pipeline8.1.1 Cleaning and normalization8.1.2 Time alignment and resampling8.1.3 Feature extraction8.1.4 Storage8.2 Anomaly and fault detection8.2.1 Rule-based detection and its limitations8.2.2 Statistical approaches8.2.3 Unsupervised learning8.3 Predictive modeling and machine learning8.3.1 Training a forecasting model8.3.2 Applying AutoML8.3.3 Supervised learning8.4 Generative AI8.4.1 Retrieval-augmented generation8.4.2 Agentic AI8.4.3 Building an agent for the home digital twin8.4.4 When agents complement or replace control strategies8.4.5 Multi-agent systems8.5 Choosing the right approach8.5.1 Operational viability8.5.2 Safety and human in the loop8.5.3 Cost
9 Predicting outcomes with simulation
9.1 Modeling and simulating physical systems9.1.1 The digital twin advantage9.1.2 From static models to dynamic simulation9.1.3 Continuous versus discrete event simulation9.2 Continuous systems9.2.1 Simulating a continuous system9.2.2 The initial value problem9.3 Acausal modeling for digital twins9.3.1 How it works9.3.2 Modeling tank drainage in OpenModelica9.3.3 Executing simulations9.3.4 Integrating sensor data with continuous simulation9.4 Simulating processes with discrete event simulation9.4.1 Why DES matters for digital twins9.4.2 DES with Python using SimPy9.4.3 Example application of DES in digital twins9.5 Finite element and field simulation9.5.1 Using FEM for virtual sensing in a digital twin9.5.2 Example application of FEA in digital twins9.6 Computational fluid dynamics9.6.1 CFD with Python for lightweight simulation9.6.2 Example application of CFD in digital twins9.7 Reduced-order models9.7.1 ROMs for virtual sensing9.7.2 An example ROM
10 Digital twins in production
10.1 Selecting the right deployment platform10.1.1 Public cloud providers10.1.2 Digital twin development platforms and engines10.1.3 Fully managed digital twin platforms10.2 Security as a cross-cutting concern10.2.1 Expanding the threat model10.2.2 Identity everywhere10.2.3 Policy as code10.3 Digital twin operations10.3.1 Observability10.3.2 Model lifecycle management10.3.3 Change management10.3.4 Cost management10.3.5 Software dependency management10.4 Aligning to strategy and measuring value10.4.1 Operational impact10.4.2 User adoption and trust10.4.3 Financial value10.5 Governance, ethics, and responsibility10.5.1 Decision authority10.5.2 Accountability and ownership10.5.3 Ethical use10.5.4 Auditability and traceability10.6 A production readiness checklist
appendix A Building a LoRaWAN network
A.1 What you’ll needA.1.1 LoRaWAN gatewayA.1.2 LoRaWAN network serverA.1.3 LoRaWAN sensorsA.2 Step 1: Configuring AWS IoT Core for LoRaWANA.3 Step 2: Configuring your gatewayA.4 Step 3: Configuring device and service profilesA.4.1 Creating the device profileA.4.2 Creating the service profileA.5 Step 4: Adding a destination for your sensor dataA.6 Step 5: Adding a sensor
appendix B Building a custom IoT sensor
B.1 HardwareB.2 Cloud configurationB.2.1 Step 1: Create a thingB.2.2 Step 2: Generate certificatesB.2.3 Step 3: Attach an access policyB.2.4 Step 4: Download certificatesB.3 Device softwareB.4 Verifying the connection
appendix C Capturing a 3D model using photogrammetry
C.1 What you’ll needC.2 Image captureC.2.1 Preparing your cameraC.2.2 Manual photo captureC.2.3 Automated photo captureC.3 Processing the dataC.4 Creating 3D tiles and georeferencing them

Content preview from Digital Twins in Action

4 Data integration and management

This chapter covers

The types of data typically used by digital twins
Sources of data and how they are integrated into a digital twin
Data storage solutions
Managing data governance and compliance

Data is the lifeblood of a digital twin. Sensors, enterprise systems, external APIs, and human inputs all generate information that must be combined to form a coherent view of the physical world. If this data is fragmented or inconsistent, the digital twin quickly loses credibility as a decision-support tool.

Building a reliable digital twin therefore depends on effective data integration and management. Data must be collected, validated, transformed, and stored in ways that preserve accuracy while making ...

Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.

Read now

Unlock full access

More than 5,000 organizations count on O’Reilly

O’Reilly covers everything we've got, with content to help us build a world-class technology community, upgrade the capabilities and competencies of our teams, and improve overall team performance as well as their engagement.

Julian F.

Head of Cybersecurity

I wanted to learn C and C++, but it didn't click for me until I picked up an O'Reilly book. When I went on the O’Reilly platform, I was astonished to find all the books there, plus live events and sandboxes so you could play around with the technology.

Addison B.

Field Engineer

I’ve been on the O’Reilly platform for more than eight years. I use a couple of learning platforms, but I'm on O'Reilly more than anybody else. When you're there, you start learning. I'm never disappointed.

Amir M.

Data Platform Tech Lead

I'm always learning. So when I got on to O'Reilly, I was like a kid in a candy store. There are playlists. There are answers. There's on-demand training. It's worth its weight in gold, in terms of what it allows me to do.

Mark W.

Embedded Software Engineer

Designing Distributed Systems, 2nd Edition

Publisher Resources

ISBN: 9781633434653Publisher Support Other Publisher Website Purchase Link

Cloud Computing

Data Engineering

Data Science

AI & ML

Programming Languages

Software Architecture

IT/Ops

Security

Design

Business

Soft Skills

Digital Twins in Action

by Greg Biegel