Hands-On Industrial Internet of Things, 2nd Edition

Cover
Title Page
Copyright and Credits
Dedication
Contributors
Table of Contents
Preface
Part 1:Industrial IoT
Chapter 1: Introduction to Industrial IoT
	Technical requirements
	IoT background
		History and definition
		IoT enabling factors
	IoT use cases
	IoT key technologies
	What is the IIoT?
		Use cases of the IIoT
		IoT and IIoT – similarities and differences
		IoT analytics, AI, and AIoT
		Industry environments and scenarios covered by IIoT
	Summary
Chapter 2: Understanding the Industrial Process and Devices
	Technical requirements
	The industrial process
		Automation in the industrial process
		Control and measurement systems
		Types of industrial processes
	The CIM pyramid
		CIM pyramid architecture – devices and networks
		CIM networks
	The IIoT data flow
		The Industrial IoT data flow in a factory
		The edge device
		The Industrial IoT data flow in the cloud
	Summary
Chapter 3: Industrial Data Flow and Devices
	Technical requirements
	The IIoT data flow in the factory
	Measurements and the actuator chain
		Sensors
		Converters
		Actuators
	Controllers
		Microcontrollers
		PLCs
		Advanced Control
		DCS
	Industrial protocols
		The OSI/ISO model
		Automation networks
		The fieldbus
	Supervisory control and data acquisition (SCADA)
	Historian
	ERP and MES
		The asset model
		ISA-95 equipment entities
		SA-88 extensions
	Summary
Chapter 4: Implementing the Industrial IoT Data Flow
	Discovering OPC
		OPC Classic
		OPC UA
		The OPC UA information model
		OPC UA sessions
		The OPC UA security model
		The OPC UA data exchange
		OPC UA notifications
	Understanding the IIoT edge
		The IoT edge versus the IIoT edge
		The fog versus the IIoT edge
	The edge architecture
		The edge gateway
		The edge computing
		The edge tools
	Edge implementations
		Azure IoT Edge
		AWS IOT Edge
		Node-RED
	Edge internet protocols
	Implementing the IIoT data flow
		IIoT data sources and data gathering
		PLC
		DCS
		SCADA
		Historians
	Edge deployment and data flow scenarios
		The edge on a fieldbus setup
		The edge on OPC DCOM
		The edge on OPC-Proxy
		The edge on OPC UA
		OPC UA on the controller
	Summary
Chapter 5: Applying Cybersecurity
	What is a DiD strategy?
		Making people aware
		Understanding technology
		Operating modes and procedures
		The DiD in an industrial control system environment
		Firewalls
	Common control-network-segregation architectures
		Network separation with a single firewall
		A firewall with a DMZ
		A paired firewall with a DMZ
		A firewall with DMZ and VLAN
	Securing the IIoT data flow
		Securing the edge on a fieldbus
		Securing the edge on OPC DCOM
		Securing the edge on OPC Proxy
		Securing the edge on OPC UA
		Securing OPC UA on a controller
	Summary
Chapter 6: Performing an Exercise Based on Industrial Protocols and Standards
	Technical requirements
	The OPC UA Simulation Server
		OPC UA Server Node.js
		Prosys OPC UA Simulator – optional step
	The edge
		Installing a simple edge client
		The Node-RED edge
		Node-RED
	Summary
Part 2:Industrial IoT Architecture
Chapter 7: Developing Industrial IoT and Architecture
	Technical requirements
	Introduction to the IIoT platform and architectures
	Microservice, containers, and serverless computing
		Docker
		Microservice-oriented technologies
		Software as a service
	The standard IIoT flow
	Understanding the time-series technologies
		Not only sensors
	Asset registry
	Data processing and the analytics platform
		Excursion monitoring analytics
		Advanced analytics
		Big data analytics
	Hands-on with InfluxDB, Node-RED, and OPC UA
	Using Docker Compose and Docker Build
	Summary
Chapter 8: Implementing a Custom Industrial IoT Platform
	Technical requirements
	An open source platform in practice
		Mosquitto as a data gateway
		Storing time-series data on InfluxDB
		Connecting InfluxDb and MQTT Data Broker
		Starting and testing the data flow
		Visualizing data using Grafana
		Developing our batch analytics with Airflow
		Developing our online analytics with Airflow
		What’s still missing here?
	Building an asset registry to store asset information
		Building an asset model with Neo4j
	Pros and cons of the proposed platform
	Other technologies
		Other open source technologies for analytics
		Other open source platforms
		Other IIoT data beyond the time series
	Summary
Chapter 9: Building an AWS Industrial IoT Solution
	Technical requirements
	Why do we use commercial IIoT platforms?
		AWS architecture
		AWS IoT
		Registering with AWS
		Installing the AWS command-line interface client
	IoT Core
		Identifying the AWS MQTT endpoint
		Connecting Node-RED
		Using the AWS SDK
		Greengrass V2
		SiteWise
	Summary
Chapter 10: Implementing an Industrial IOT Data Flow with AWS
	Technical requirements
	Architecture of the exercise
	AWS IoT Analytics
		SageMaker and Athena
		IoT Analytics
	Storing data
	Visualization
		Workforce users
		Grafana
		About visualization
	Summary
Chapter 11: Performing a Practical Industrial IoT Solution with Azure
	Technical requirements
	Azure IoT ecosystem
	Registering for Azure IoT
	Azure IoT Hub
		Registering a new device
		Building a custom edge
		Azure IoT Edge
		Device twins
		Monitoring messages sent through IoT Hub Metrics
	Showing messages sent through Service Bus
	Summary
Chapter 12: Implementing an Industrial IoT Data Flow with Azure
	Technical requirements
	Architecture of the proposed exercise
	Setting the data flow
		Data storage
		Data processing
		Azure Synapse
		Machine Learning analytics
	Building visualizations
		Azure Data Explorer
		Grafana
		Power BI
		IoT Central
		More on Azure Data Explorer
	Comparing the platforms
	Summary
Part 3:Industrial Artificial Intelligence of Thingse
Chapter 13: Performing Diagnostic, Maintenance, and Predictive Analytics
	Technical requirements
		Jupyter
	IIoT analytics
	The different classes of analytics
		Descriptive analytics
		Diagnostic analytics
		Predictive analytics
		Prescriptive analytics
	IIoT analytics technologies
		Rule-based analytics
		Model-based analytics
	Building IIoT analytics
		Step 0 – problem statement
		Step 1 – dataset acquisition
		Step 2 – EDA
		Step 3 – building the model
		Step 4 – packaging and deploying (MLOps)
		Step 5 – monitoring
	Understanding the role of the infrastructure
	Deploying analytics
		Streaming versus batch analytics
		Condition-based analytics
		Interactive analytics
		Analytics on the cloud
		Analytics on the edge
		Analytics on the controller
		Advanced analytics
	OSA
	Analytics in practice
		Anomaly detection in practice
		Anomaly detection with unsupervised ML
		Anomaly detection with supervised ML
		Predictive production analytics in practice
		Prescription using language models
	Summary
Chapter 14: Implementing a Digital Twin – Advanced Analytics
	Technical requirements
	Digital twins
		Digital twins in practice
		Implementing a digital twin in IIoT
	AI and IoT
		ML
		DL
		GenAI
		AGI
	Developing a digital twin
		Preparing the development environment
		Evaluating the RUL of 100 engines
		Monitoring a wind turbine
	Platforms for digital twins
		Digital twins platforms
		Advanced modeling
	Other kinds of IIoT data
	Summary
Chapter 15: Deploying an Analytics Model
	Technical requirements
	Understanding model-as-a-service
	Developing our first MaaS with MLflow
		Starting MLflow
		Developing our ML model
		Understanding Airflow integration
	Working with the Azure ML service
		Starting with the Azure ML service
		Understanding the Azure ML workspace
		Developing wind turbine digital twins with Azure ML
		Cleaning the resources
		IoT Hub integration
		Azure IoT Edge
	Implementing analytics on Amazon SageMaker
		Accessing SageMaker Studio
		Preparing an S3 bucket to store data
		Developing a digital twin with SageMaker
		Consuming the model from AWS IoT Core
		Understanding the advanced features of SageMaker
	Understanding GCP and multi-cloud solutions
	Summary
Index
About Packt
Other Books You May Enjoy