Electricity + Control September 2019

CONTROL SYSTEMS + AUTOMATION + SYSTEMS ENGINEERING

Omron has focused on developing tools to help people understand the complexities of what is happening in machines.

AI. Companies can then start to obtain information from the data and begin visualising it in a smart way. This is basic data science and will help companies start realising a range of benefits. It’s important to note that a lot of existing data isn’t suitable for analysis: it may be contaminated, duplicated or scattered, or there may be key information missing. There is huge potential for the use of new technology, but it can only be used if the data gathered is sufficient and correct (which involves ensuring a lot of attributes are right). Companies considering the use of AI also need to think in a broader sense about data science and what and how much data is needed before deciding on the best way forward. Even then, a substantial amount of data is needed to inform the best decisions. AI can be applied at various levels, depending on the problem to be solved. For instance, in order to compare the performance of two factories, data must be gathered from both and put into the cloud (inside or outside the enterprise), and then compared and analysed to draw a comparison. At the other end of the spectrum, the requirement may be to analyse the performance of a machine that isn’t fully meeting production specifications. This can be difficult in a mass production scenario. For example, a manufacturer providing parts for the automotive industry might need to generate 100 000 items per day, to be delivered ‘just in time’ to the customer, so that they can be built into cars the next day. If it takes two weeks to analyse the quality data to discover that the product isn’t meeting the specifications, this could delay the identification of an issue that could then lead to an extensive product recall.

This, therefore, is a completely different problem that needs solving. It can’t be solved in the cloud, as it can take hours or days to collect the data there and analyse it. Instead, a solution that will run in the machine is needed to identify a low-quality pattern before the 100 000 items are shipped, or even before they are produced, to avoid scrap. This is where edge computing is very useful. The main challenge remains: what is the problem to be solved? A company with strong top- level management will know the key challenges it faces and will want to use the most effective tools to optimise its performance. The problems faced will determine what needs to be done. For instance, is there a need to look wide, at a lot of data?To compare a large amount of data, say from 20 factories, AI in the cloud can play a key role. However, if the need is for an immediate response to avoid downtime on a bottling line, for example, a solution with AI at the edge should be considered. 2. Accessing and making best use of data The machines in a factory are potentially a source of valuable data. How can users access and analyse such data and how can it be used most effectively in a manufacturing plant, especially when introducing AI to enhance its capabilities? The key questions to be addressed here are: - Data - Do I have enough data and, if so, which data is most relevant and how will it be used? - Infrastructure - Howmuchwill the infrastructure cost? - Outcomes - What problem do I really need to solve and what increase in efficiency can be achieved by using cloud or edge computing?

Electricity + Control

SEPTEMBER 2019

31