What this book covers
Chapter 1, Introduction to Industrial IOT, provides some background to industrial IoT, the story, use cases, and the contrast with the home internet of things. It helps you understand the Industrial IoT Process
Chapter 2, Understanding the Industrial Process and Devices, helps you understand the industrial process and devices and defines the factory processes. This chapter describes the concept of a distributed control system (DCS), programmable logic controllers (PLCs), supervisory control and data acquisition (SCADA), Historian, manufacturing execution system (MES), enterprise resource planning (ERP), and fieldbus. It introduces the International Electrotechnical Commission (IEC)-61131 and the CIM pyramid. Finally, it designs a big picture, from equipment through to the cloud.
Chapter 3, Industrial Data Flow and Devices, details which equipment, devices, network protocols, and software layers manage the industrial IoT data flow along its path, from the sensors on the factory floor to the edge that is the external boundary of the industrial IoT data flow inside the factory.
Chapter 4, Implementing the Industrial IoT Data Flow, explains how to implement the industrial IoT data flow in a complex industrial plant. This journey starts with an understanding of how to select the industrial data source to connect to for the purpose of gathering the data and ends by providing five network scenarios for edge deployment in industrial plants.
Chapter 5, Applying Cybersecurity, explores the industrial IoT data flow from the cybersecurity perspective, outlining the goals of the DiD strategy, and the most common network architecture to secure industrial control systems, including the five network scenarios for edge deployment discussed in the previous chapter.
Chapter 6, Performing an Exercise Based on Industrial Protocols and Standards, explores how to implement a basic data flow from the edge to the cloud by means of OPC UA and Node-RED.
Chapter 7, Developing Industrial IoT and Architecture, outlines the basic concepts regarding industrial IoT data processing, providing the key principles for storing time series data, handling the asset data model, processing the data with analytics, and building digital twins.
Chapter 8, Implementing a Custom Industrial IoT Platform, shows how to implement a custom platform leveraging the most popular open source technologies: Node.js, Docker, InfluxDB, Neo4J, Apache Airflow, Mosquitto, and Docker.
Chapter 9, Building an AWS Industrial IOT Solution, explores the solutions proposed by Amazon Web Services (AWS) and the capabilities of the AWS IoT platform. This chapter introduces the Edge IoT of AWS (Greengrass), the IoT Core, and AWS SiteWise and builds the first part of the proposed architecture. We will learn about these technologies by performing a practical exercise.
Chapter 10, Implementing an Industrial IOT Data Flow with AWS, concludes the proposed architecture by implementing a data flow using DynamoDB, AWS analytics, and Grafana to display data. We will gain practical experience with these technologies through hands-on exercise.
Chapter 11, Performing a Practical Industrial IoT Solution with Azure, develops a wing-to-wing industrial IoT solution leveraging Azure, Azure Edge, and the Azure IoT platform. We will learn about these technologies by performing a practical exercise.
Chapter 12, Implementing an Industrial IoT Data Flow with Azure, finalizes the proposed architecture, implementing the data flow with Azure Cosmos DB, Stream Analytics, and Synapse. We will learn about these technologies by performing a practical exercise.
Chapter 13, Performing Diagnostic, Maintenance, and Predictive Analytics, introduces the basic concepts of analytics and data consumption. It also develops basic analytics for anomaly detection and prediction. The chapter also introduces new concepts of generative AI.
Chapter 14, Implementing a Digital Twin – Advanced Analytics, develops a physics-based and data-driven digital equipment model to monitor assets and systems.
Chapter 15, Deploying an Analytics Model, shows how to develop analytics on Azure ML and AWS SageMaker. Finally, the chapter explores other common technologies.
