Electricity + Control September 2019

CONTROL SYSTEMS + AUTOMATION + SYSTEMS ENGINEERING

Omron Industrial Automation offers some pointers to manufacturers considering using artificial intelligence, the cloud or edge computing, all technologies that can contribute to increasing overall equipment effectiveness in manufacturing plant and, in turn, business profitability. Artificial intelligence in industrial manufacturing

Take Note!

1. In moving towards using AI in manufacturing, an essential first step is to start collecting and cleaning data. 2. Companies also need to think about what and how much data is needed, before deciding on the best way forward. 1 2

I n themanufacturing arena, people andmachines tend to have a symbiotic relationship – they depend on each other for their performance and for future improvements. People are increasingly making better machines – most recently through the use of affordable and innovative automation solutions based on more powerful hardware and software. These enhanced machines then help people to be more productive, bringing advantages to the wider society by providing more value higher up the value chain. AI and the cloud versus the edge Two technological advances that are playing significant roles in the improvement of machines are cloud and edge computing. Cloud computing, which relates to the storage, management and analysis of data that is stored remotely on a server, either locally or on the internet, has become commonplace in a relatively short time. Although it has proven invaluable in many circumstances, it’s important to ask if it is the best solution for any business, or, in particular, for the production line. Edge computing has emerged more recently as an alternative. It enables data storage, applications and analysis to be carried out at the edge of a machine or plant. While there are various interpretations about what the edge entails, in broad terms it is about lines and devices being monitored with real-time sensors and data at the machine level being processed in microseconds. This means that a machine’s condition can be monitored in real time, enabling an immediate response to any performance anomalies. The volume of data available, however, is relatively limited.

In considering which of these options will be most effective for their operations, industrial manufacturers also need to take into account new solutions involving artificial intelligence (AI) and machine learning (ML). Omron has demonstrated how AI can be incorporated intomachines by developing Forpheus, the world’s first robot that can play and train people in table tennis. Forpheus embodies Omron’s three-fold philosophy for innovative automation: integration, interaction and intelligence (specifically, AI). The robot uses its cameras and sensors to observe and assess the mood and skill level of the opposing player. With integrated AI it analyses the data and modifies its own play accordingly. Forpheus presents an example of how smart machines could be used to train and assist people in the manufacturing sector, making the most of their potential. However, although AI offers some great potential benefits for industrial applications, all too often, companies may be eager to start using it without being fully aware of the challenges they could face. So, what are the key issues involved in deploying AI and in determining how AI can improve a production line or a process, and if cloud or edge computing should be implemented? 1. Identifying the problem One of the biggest challenges companies face is that they often don’t knowwhat problem they want to solve. Some aren’t yet measuring any data, so although they might be keen to implement AI, this will prove difficult without the necessary data. The solution is to start collecting and cleaning data first, before even thinking about introducing

30 Electricity + Control

SEPTEMBER 2019