This website uses cookies primarily for visitor analytics. Certain pages will ask you to fill in contact details to receive additional information. On these pages you have the option of having the site log your details for future visits. Indicating you want the site to remember your details will place a cookie on your device. To view our full cookie policy, please click here. You can also view it at any time by going to our Contact Us page.

Close

AI will be part of the future for automation

09 October 2023

Andy MacPherson discusses the impact that AI is expected to have within food and beverage manufacturing

Artificial Intelligence (AI) has leapt into wider public consciousness following the launch of accessible, generative AI models such as ChatGPT. Within the control and automation sector the impact of AI has been less dramatic, but sweeping changes are coming. 

AI is not, however, an isolated trend. It is the culmination of a series of technology developments that have been applied to automate anything from single actuators to robots and complete machines. We have adopted the terms ‘Digitalisation’ and ‘Industry 4.0’ to encapsulate these developments and to help us paint a vision of the future. 

AI both uses and can help us create complex machine models more rapidly and accurately from standardised and structured data models. A good example of this standardisation are Digital Twins which play an intrinsic role by incorporating all the information about components and sub-systems: their physical attributes, performance dynamics and operation. A standardised and structured format enables digital reading and means the user doesn’t need to ‘hard program’ all this data. The system ‘reads’ its constituent parts and ‘understands’ their operation, interpreting anomalies in their performance and supplying valuable information in plain text to improve predictive maintenance, energy consumption, etc. This means the digital system configuration is always up to date and isn’t reliant on updating documentation or programs during the machine lifecycle. 

Today, we can access an enormous amount of data about our machines. However, it has rarely been possible or economical, to analyse this data and convert it into useful intelligence. This is where AI comes in. 

Within food manufacturing, we are often looking to use AI for results that can be expressed in terms of Overall Equipment Effectiveness (OEE) measures such as availability, performance, and quality. AI offers the potential to analyse large amounts of data to look for patterns or anomalies and trigger deployable outcomes. However, there isn’t an all-powerful, off-the-shelf AI package that can be instantly deployed: Instead, there are independent packages that can be used to achieve specific tasks. Inconsistent or poorly structured data can make it difficult to achieve a comprehensive result, so specialist data skills and expertise are needed in the selection of the best software tools and in preparation of the data to enable the required business results.

We need a tool kit of software packages to achieve these tasks – each package performing its specific function and then passing its output to the next package to continue the process of converting the raw data into improved machine availability perhaps through predictive maintenance, or optimised performance or quality. 

The Festo Automation Experience (AX) AI tool was developed initially as a cloud-based solution, for customer facing applications. It enables us to use our application knowledge combined with AI to provide actionable outputs. I see interesting developments ahead in even more localised applications – on edge or embedded within smart products. Machine builders will be able to simply add this into their existing control structure, utilising existing hardware or running in parallel. 

Last word
Machinery in the food sector will become more productive by becoming smarter in a large part due to AI. It will be self-optimising for performance both in terms of output and energy consumption. Machinery availability will become higher as we reduce wear and tear through self-tuning actuators and drives and predictive maintenance. Equipment such as robots will be easier to program and interact with, and hopefully we will achieve this like the mobile phone companies have managed without the need for an instruction manual!

Andrew MacPherson, Head of UK Sales and Industry Sector Manager, Food and Beverage at Festo GB. 


Contact Details and Archive...

Print this page | E-mail this page