Pattern Implementation in the Manufacturing Domain

One of the domains where IoT has contributed (and is expected to contribute further) significantly to digitalization efforts is the manufacturing domain. The prime reason is that this domain stands to gain the most from obtaining real-time visibility into manufacturing operations, identifying optimization opportunities, and automating the existing manual processes (e.g., automating the inspection of goods by analyzing the video feed as it moves over the assembly), resulting in increased operational efficiency.

Most manufacturing plants already deploy automation to a certain extent (e.g., Computer Numerical Control or CNC). Machines are used to perform repetitive tasks such as welding, milling, cutting, and so on by programming a series of predefined instructions. However, there is still huge potential that can be tapped into by deploying IoT technologies end to end (aggregating/analyzing data from all plants and the complete supply...

An overview of smart manufacturing

IoT plays a foundational role in enabling smart manufacturing; however, there are a few additional or complementary technologies (which we will discuss later in this chapter) that play an equally significant role, as shown in the following figure:

Figure 7.1 – IoT and related technologies that are smart-manufacturing enablers

Readers must be aware of certain terms that are used frequently in traditional and smart manufacturing. Let’s discuss these in detail.

Key terms/definitions

In this section, we’ll discuss some of the key concepts in the smart manufacturing domain:

• Digital threads: Digital threads connect disparate manufacturing processes or systems and provide an integrated view as they traverse through the different stages of their life cycles (conceptualization, production, usage, service, repair, and decommission). A digital thread is enabled by installing sensors across the...

Exploring the evolution of the manufacturing domain

The evolution of manufacturing to smart manufacturing and beyond is categorized into five industrial revolutions, as shown in the following figure:

Figure 7.5 – Evolution of smart manufacturing

These revolutions represent significant leaps in terms of productivity and working conditions and are also characterized by the usage of different core technologies. The different stages of evolution are detailed as follows:

• Industry 1.0: The first industrial revolution ushered in an era of mechanization and steam engines whereby activities that were earlier performed using human labor started to be performed using machines.
• Industry 2.0: The second revolution involved the usage of electricity to power industrial machines.
• Industry 3.0: The third industrial revolution relied on using electronics and computers for the automation of production tasks.
• Industry 4.0: Currently, we are in the Industry...

Automatic inspection of finished goods or parts

One interesting use case in the discrete manufacturing space is the automated inspection of finished goods or parts. Finished goods are inspected by analyzing video feeds from digital cameras; by deploying the required machine learning (visual inspection) models on the Device Gateway (DG), these models output a binary value indicating whether a part is defective or not.

Important note

The term sensing device is not limited to video feeds from digital cameras; alternate sensing technologies (such as infrared cameras and x-ray cameras) may very well be used to support specific operating conditions and use case requirements.

If a defective part is detected, a robotic arm will take that part from the conveyor belt and put it in a waste bin. These models are trained at a central server and refined models are pushed to a gateway from the central server. If the model is not able to identify the part with the required level of confidence...

Summary

This chapter detailed the reasons why IoT is expected to play a vital role in making the manufacturing industry smarter. We started by defining a few concepts that are required for understanding the domain; outlined the key characteristics of five industrial revolutions; discussed the benefits expected from smart manufacturing; and, finally, covered how IoT patterns can be used to realize automatic inspection.

In this chapter, we highlighted the fact that in the future, manufacturing companies will act more like software companies by following agile manufacturing methodologies and data-driven decision-making. All this entails more collaboration and necessitates a big cultural change. Therefore, unless manufacturing companies actively invest in training employees, as well as address the expected cultural nuances, the aspiration of being a truly smart manufacturing enterprise will fail. An example of cultural change is to move from experience-based decisions to decisions based...