0%

Book Description

Build a strong and efficient IoT infrastructure at industrial and enterprise level by mastering Industrial IoT network

Key Features

  • Gain hands-on experience working with industrial architecture
  • Explore the potential of cloud-based Industrial IoT platforms, analytics, and protocols
  • Improve business models and transform your workforce with Industry 4.0

Book Description

We live in an era where advanced automation is used to achieve accurate results. To set up an automation environment, you need to first configure a network that can be accessed anywhere and by any device. This book is a practical guide that helps you discover the technologies and use cases for Industrial Internet of Things (IIOT).

Hands-On Industrial Internet of Things takes you through the implementation of industrial processes and specialized control devices and protocols. You'll study the process of identifying and connecting to different industrial data sources gathered from different sensors. Furthermore, you'll be able to connect these sensors to cloud network, such as AWS IoT, Azure IoT, Google IoT, and OEM IoT platforms, and extract data from the cloud to your devices.

As you progress through the chapters, you'll gain hands-on experience in using open source Node-Red, Kafka, Cassandra, and Python. You will also learn how to develop streaming and batch-based Machine Learning algorithms.

By the end of this book, you will have mastered the features of Industry 4.0 and be able to build stronger, faster, and more reliable IoT infrastructure in your Industry.

What you will learn

  • Explore industrial processes, devices, and protocols
  • Design and implement the I-IoT network flow
  • Gather and transfer industrial data in a secure way
  • Get to grips with popular cloud-based platforms
  • Understand diagnostic analytics to answer critical workforce questions
  • Discover the Edge device and understand Edge and Fog computing
  • Implement equipment and process management to achieve business-specific goals

Who this book is for

If you're an IoT architect, developer, or stakeholder working with architectural aspects of Industrial Internet of Things, this book is for you.

Table of Contents

  1. Title Page
  2. Copyright and Credits
    1. Hands-On Industrial Internet of Things
  3. Dedication
  4. About Packt
    1. Why subscribe?
    2. Packt.com
  5. Contributors
    1. About the authors
    2. About the reviewer
    3. Packt is searching for authors like you
  6. Preface
    1. Who this book is for
    2. What this book covers
    3. To get the most out of this book
      1. Download the example code files
      2. Download the color images
      3. Conventions used
    4. Get in touch
      1. Reviews
  7. Introduction to Industrial IoT
    1. Technical requirements
    2. IoT background
      1. History and definition
      2. IoT enabling factors
      3. IoT use cases
    3. IoT key technologies
    4. What is the I-IoT?
    5. Use cases of the I-IoT 
    6. IoT and I-IoT – similarities and differences
    7. IoT analytics and AI
    8. Industry environments and scenarios covered by I-IoT
    9. Summary
    10. Questions
    11. Further reading
  8. Understanding the Industrial Process and Devices
    1. Technical requirements
    2. The industrial process
      1. Automation in the industrial process
      2. Control and measurement systems
      3. Types of industrial processes
        1. Continuous processes
        2. Batch processes
        3. Semi-continuous processes
        4. Discrete processes
    3. The CIM pyramid
      1. CIM pyramid architecture – devices and networks
        1. Level 1 – sensors, transducers, and actuators
        2. Level 2 – RTU, embedded controllers, CNCs, PLCs, and DCSes
        3. Level 3 – SCADA, Historian
        4. Level 4 – MES
        5. Level 5 – ERP
        6. CIM networks
    4. The I-IoT data flow
      1. The Industrial IoT data flow in a factory
      2. The edge device
      3. The Industrial IoT data flow in the cloud
    5. Summary
    6. Questions
    7. Further reading
  9. Industrial Data Flow and Devices
    1. Technical requirements
    2. The I-IoT data flow in the factory
    3. Measurements and the actuator chain
      1. Sensors
      2. The converters
        1. Digital to analogical
        2. Analog to digital
      3. Actuators
    4. Controllers
      1. Microcontrollers
        1. Embedded microcontrollers
        2. Microcontrollers with external memory
        3. DSPs
      2. PLCs
        1. Processor module
        2. Input and output (I/O) module
        3. Remote I/O module
        4. Network module
        5. Other modules
      3. DCS
    5. Industrial protocols
      1. Automation networks
      2. The fieldbus
    6. Supervisory control and data acquisition (SCADA)
    7. Historian
    8. ERP and MES 
      1. The asset model
        1. ISA-95 equipment entities
        2. SA-88 extensions
    9. Summary
    10. Questions
    11. Further reading
  10. Implementing the Industrial IoT Data Flow
    1. Discovering OPC
      1. OPC Classic
        1. The data model and retrieving data in OPC Classic
      2. OPC UA
        1. The OPC UA information model
        2. OPC UA sessions
        3. The OPC UA security model
        4. The OPC UA data exchange
        5. OPC UA notifications
    2. Understanding the I-IoT edge
      1. Features of the edge
        1. The edge gateway
        2. The edge tools
        3. The edge computing
      2. The IoT edge versus the I-IoT edge
      3. The fog versus the I-IoT edge
      4. The edge architecture
        1. The edge gateway
        2. The edge computing
        3. The edge tools
      5. Edge implementations
        1. Azure IoT Edge
        2. Greengrass
        3. Android IoT
        4. Node-RED
        5. Docker edge
        6. Intel IoT Gateway
      6. Edge internet protocols
    3. Implementing the I-IoT data flow
      1. I-IoT data sources and data gathering
        1. PLC
          1. Advantages of the PLC
          2. Disadvantages of the PLC
        2. DCS
        3. SCADA
          1. Advantages of SCADA systems
          2. Disadvantages of SCADA systems
        4. Historians
          1. Advantages of Historians
          2. Disadvantages of Historians
      2. Edge deployment and data flow scenarios
        1. Edge on fieldbus setup
          1. Strengths of the edge on fieldbus setup
          2. Weaknesses of the fieldbus setup
        2. Edge on OPC DCOM
          1. Strengths of the edge in OPC DCOM
          2. Weaknesses of the edge in OPC DCOM
        3. Edge on OPC Proxy
          1. Strengths of the edge on OPC Proxy
          2. Weaknesses of the edge on OPC Proxy
        4. Edge on OPC UA
          1. Strengths of the edge on the OPC UA
          2. Weaknesses of the edge on OPC UA
        5. OPC UA on the controller
    4. Summary
    5. Questions
    6. Further reading
  11. Applying Cybersecurity
    1. What is a DiD strategy?
      1. People
      2. Technology
      3. Operating modes and procedures
      4. The DiD in Industrial Control System (ICS) environment
    2. Firewalls
    3. Common control-network-segregation architectures
      1. Network separation with a single firewall
      2. A firewall with a DMZ
      3. A paired firewall with a DMZ
      4. A firewall with DMZ and VLAN
    4. Securing the I-IoT data flow
      1. Securing the edge on fieldbus
      2. Securing the edge on OPC DCOM
      3. Securing the edge on OPC Proxy
      4. Securing the edge on OPC UA
      5. Securing OPC UA on a controller
    5. Summary
    6. Questions
    7. Further reading
  12. Performing an Exercise Based on Industrial Protocols and Standards
    1. Technical requirements
    2. The OPC UA Simulation Server
      1. OPC UA Node.js
        1. Starting an OPC UA sample server
      2. Prosys OPC UA Simulator
        1. Installing the Prosys server
        2. Simulating measures
    3. The edge
      1. Node-RED
    4. Summary
    5. Questions
    6. Further reading
  13. Developing Industrial IoT and Architecture
    1. Technical requirements
    2. Introduction to the I-IoT platform and architectures
    3. OSGi, microservice, containers, and serverless computing
      1. Docker
    4. The standard I-IoT flow
      1. Understanding the time-series technologies
        1. OSIsoft PI
        2. Proficy Historian
        3. Uniformance Process History Database (PHD)
        4. KairosDB
        5. Riak TS (RTS)
        6. Netflix Atlas
        7. InfluxDB
        8. Elasticsearch
        9. Cloud-based TSDBs
        10. OpenTSDB
      2. Asset registry
      3. Data-processing and the analytics platform
        1. EMAs
        2. Advanced analytics
        3. Big data analytics
        4. Cold path and hot path
    5. Summary
    6. Questions
    7. Further reading
  14. Implementing a Custom Industrial IoT Platform
    1. Technical requirements
    2. An open source platform in practice
      1. Data gateway
    3. Mosquitto as MQTT connector
    4. Apache Kafka as a data dispatcher
      1. Kafka Streams as a Rule Engine
    5. Storing time-series data on Apache Cassandra
      1. Apache Cassandra
        1. KairosDB
          1. Installing Apache Cassandra
          2. Installing KairosDB
          3. Installing the Kafka KairosDB plugin
        2. Graphite
      2. Developing our batch analytics with Airflow
        1. Installing Airflow
        2. Developing a KairosDB operator
        3. Implementing our analytics
      3. Other open source technologies for analytics
    6. Building an asset registry to store asset information
      1. Building an asset model with Neo4j
    7. Pro and cons of the proposed platform
      1. Other technologies
        1. RabbitMQ
        2. Redis
        3. Elasticsearch and Kibana
        4. Grafana
        5. Kaa IoT
        6. Eclipse IoT
        7. Other I-IoT data beyond the time-series
          1. Apache HDFS and Hadoop
          2. Apache Presto
          3. Apache Spark
    8. Summary
    9. Questions
    10. Further reading
  15. Understanding Industrial OEM Platforms
    1. Technical requirements
    2. I-IoT OEM platforms
      1. Why do we use I-IoT commercial platforms?
    3. The Predix Platform
      1. Registering to the Predix Platform
      2. Installing prerequisites
      3. Configuring the user authentication and authorization services
      4. Configuring the time-series database
        1. Configuring security
      5. Ingesting our first bit of data
      6. Getting our data
      7. Deploying our first application
      8. Predix Machine
        1. Configuring the Predix developer kit
        2. Predix Edge OS
      9. Predix Asset
      10. The other Predix services
    4. The MindSphere platform
      1. Registering to MindSphere
      2. Working with MindSphere
    5. Other platforms
    6. Summary
    7. Questions
    8. Further reading
  16. Implementing a Cloud Industrial IoT Solution with AWS
    1. Technical requirements
    2. AWS architecture
      1. AWS IoT
    3. Registering for AWS
      1. Installing the AWS client
    4. IoT Core
      1. Setting the policies
      2. Registering a thing
        1. Working with an MQTT client
    5. Storing data
      1. DynamoDB
      2. Using acts in IoT Core
      3. AWS Kinesis
    6. AWS analytics
      1. Lambda analytics
      2. Greengrass
        1. Working with Greengrass
          1. Step 1 – building Greengrass edge
          2. Step 2 – configuring Greengrass
          3. Step 3 – building the OPC UA Connector
          4. Step 4 – deploying the OPC UA Connector
      3. AWS ML, SageMaker, and Athena
      4. IoT Analytics
        1. Building a channel
        2. Building the pipeline and the data store
        3. Preparing the dataset
    7. QuickSight
    8. Summary
    9. Questions
    10. Further reading
  17. Implementing a Cloud Industrial IoT Solution with Google Cloud
    1. Technical requirements
    2. Google Cloud IoT
      1. Starting with Google Cloud
      2. Installing the GCP SDK
    3. Starting with IoT Core
      1. Building the device registry
      2. Registering a new device
        1. Sending data through MQTT
    4. Bigtable
    5. Cloud Functions
      1. Running the example
    6. GCP for analytics
      1. GCP functions for analytics
      2. Dataflow
      3. BigQuery
      4. Google Cloud Storage
    7. Summary
    8. Questions
    9. Further reading
  18. Performing a Practical Industrial IoT Solution with Azure
    1. Technical requirements
    2. Azure IoT
      1. Registering for Azure IoT
      2. IoT Hub
        1. Registering a new device
        2. Sending data through MQTT
      3. Setting up Data Lake Storage
    3. Azure analytics
      1. Stream Analytics
        1. Testing Stream Analytics
        2. Advanced Stream Analytics
      2. Data Lake Analytics
      3. Custom formatter and reducer with Python, R, and C#
        1. Scheduling the job
      4. ML Analytics
    4. Building visualizations with Power BI
    5. Time Series Insights (TSI)
    6. Connecting a device with IoT Edge
      1. Azure IoT Edge applied to the industrial sector
        1. Building Azure IoT Edge with OPC UA support
    7. Comparing the platforms
    8. Summary
    9. Questions
    10. Further reading
  19. Understanding Diagnostics, Maintenance, and Predictive Analytics
    1. Technical requirements
      1. Jupyter
    2. I-IoT analytics
      1. Use cases
    3. The different classes of analytics
      1. Descriptive analytics
        1. KPI monitoring and health monitoring
        2. Condition monitoring
        3. Anomaly detection
        4. Diagnostic analytics
      2. Predictive analytics
        1. Prognostic analytics
      3. Prescriptive analytics
        1. CBM
        2. Production optimization analytics
    4. I-IoT analytics technologies
      1. Rule-based
      2. Model-based
        1. Physics-based
        2. Data-driven
    5. Building I-IoT analytics
      1. Step 0 – problem statement
      2. Step 1 – dataset acquisition
      3. Step 2 – exploratory data analysis (EDA)
      4. Step 3 – building the model
        1. Data-driven versus physics-based model
      5. Step 4 – packaging and deploying
      6. Step 5 – monitoring
    6. Understanding the role of the infrastructure
    7. Deploying analytics
      1. Streaming versus batch analytics
      2. Condition-based analytics
      3. Interactive analytics
      4. Analytics on the cloud
      5. Analytics on the edge
        1. Greengrass and FreeRTOS
        2. Azure functions on the edge
        3. Analytics on the controller
      6. Advanced analytics
    8. Open System Architecture (OSA)
    9. Analytics in practice
      1. Anomaly detection
        1. Steps 0 and 1 – problem statement and the dataset
          1. Problem statement
          2. Preparing the environment
        2. Step 2 – EDA
        3. Step 3 – building the model
          1. Extracting the features
          2. Selecting features
          3. Defining the training set against the validation set
          4. Building the algorithm
        4. Step 4 – packaging and deploying
        5. Step 5 – monitoring
      2. Anomaly detection with ML
        1. Step 3 – building the model
      3. Predictive production
        1. Steps 0 and 1 – problem statement and dataset
        2. Step 2 – EDA
        3. Step 3 – building the model
        4. Steps 4 and 5 – packaging, deploying, and monitoring
    10. Summary
    11. Questions
    12. Further reading
  20. Implementing a Digital Twin – Advanced Analytics
    1. Technical requirements
    2. Advanced analytics and digital twins
      1. Data-driven and physics-based approaches
      2. Advanced technologies
        1. ML
          1. Supervised learning
          2. Unsupervised learning
          3. Reinforcement learning (RL)
        2. DL
          1. TensorFlow
    3. Advanced analytics in practice
      1. Evaluating the RUL of 100 engines
        1. Steps 0 and 1 – problem statement and dataset
          1. Problem statement
          2. Preparing the environment
        2. Step 2 – exploratory data analysis (EDA)
        3. Step 3 – building the model
          1. Extracting the features
          2. Selecting variables
          3. Identifying the training set and the validation set
          4. Defining the model
        4. Step 4 – packaging and deploying
        5. Step 5 – monitoring
      2. Monitoring a wind turbine
        1. Steps 0, 1, and 2 – problem statement, dataset, and exploratory data analysis
        2. Step 3 – building the model
        3. Steps 4 and 5 – packaging and deploying, monitoring
    4. Platforms for digital twins
      1. AWS
      2. Predix
      3. GCP
      4. Other platforms
      5. Advanced modeling
    5. Other kinds of I-IoT data
    6. Summary
    7. Questions
    8. Further reading
  21. Deploying Analytics on an IoT Platform
    1. Technical requirements
    2. Working with the Azure ML service
      1. Starting with the Azure ML service
      2. Developing wind turbine digital twins with Azure ML
        1. Developing the model
        2. Building the image of the model
        3. Registering the model
        4. Deploying the model
        5. Testing the model
          1. Cleaning up the resources
      3. Understanding the ML capabilities of the Azure ML service
        1. Building the surrogate model with logistic regression and Scikit-Learn
        2. Building the training model
        3. Preparing the cluster to deploy the training model
        4. Submitting the model to the cluster
      4. IoT Hub integration
    3. Implementing analytics on AWS SageMaker
      1. Evaluating the remaining useful life (RUL) of an engine with SageMaker
        1. Downloading a dataset on S3
        2. Starting the notebook
        3. Working with the dataset
        4. Understanding the implementation of a SageMaker container
        5. Building the container
        6. Training the model locally
        7. Testing the model locally
        8. Publishing the image on AWS cloud
        9. Training the model in AWS SageMaker
        10. Testing the model on AWS SageMaker notebook
      2. Understanding the advanced features of SageMaker
      3. Consuming the model from AWS IoT Core
    4. Understanding the advanced analytics capabilities of GCP 
      1. ML Engine
    5. Discovering multi-cloud solutions
      1. PyTorch
      2. Chainer
      3. MXNet
      4. Apache Spark
    6. Summary
    7. Questions
    8. Further reading
  22. Assessment
    1. Chapter 1: Introduction to Industrial IoT
    2. Chapter 2: Understanding the Industrial Process and Devices
    3. Chapter 3: Industrial Data Flow and Devices
    4. Chapter 4: Implementing the Industrial IoT Data Flow
    5. Chapter 5: Applying Cybersecurity
    6. Chapter 6: Performing an Exercise Based on Industrial Protocols and Standards
    7. Chapter 7: Developing Industrial IoT and Architecture
    8. Chapter 8: Implementing a Custom Industrial IoT Platform
    9. Chapter 9: Understanding Industrial OEM Platforms
    10. Chapter 10: Implementing a Cloud Industrial IoT Solution with AWS
    11. Chapter 11: Implementing a Cloud Industrial IoT Solution with Google Cloud
    12. Chapter 12: Performing a Practical Industrial IoT Solution with Azure
    13. Chapter 13: Understanding Diagnostics, Maintenance, and Predictive Analytics
    14. Chapter 14: Implementing a Digital Twin - Advanced Analytics
    15. Chapter 15: Deploying Analytics on an IoT Platform
  23. Other Books You May Enjoy
    1. Leave a review - let other readers know what you think
35.173.181.0