COMMENT u FESTO IRELAND


AI can deliver big benefits for Irish manufacturers


Stephen McGovern, head of customer applications & technical services at Festo Ireland, says that Artificial Intelligence (AI) is getting a bad press, which is bad news for Irish manufacturing


T


here have been many more negative press stories about AI’s potential misuse than its potential power for good. The Irish engineering community needs to understand and communicate the true benefits of AI technology by championing the practical industrial applications that are already massively improving productivity, reducing energy consumption, and increasing competitiveness.


AI PRODUCTIVITY BENEFITS At Festo Ireland, we use AI internally and within customer facing products and services, such as the Festo Automation Experience [AX] artificial intelligence tool. Festo AX enables engineers to use machine learning algorithms to achieve high added value from the data produced by their systems. It was initially designed to support preventative maintenance, energy efficiency and quality optimisation, enabling customers to increase productivity and reduce costs. Today’s developments are focused on more localised applications on Edge or embedded within Smart products and include new Festo AX applications such as Grip AI, a robot vision aid and Cylinder AI, a stand-alone actuator package. Artificial Intelligence is a form of Machine Learning, where the system improves and develops through use. Festo AX keeps humans “in the loop” by integrating the users’ valuable application knowledge alongside our algorithms within Reinforcement Learning software. User inputs help Festo AX to ‘learn’ more about the state of the assets, providing continuous learning and thereby improving the algorithm


12 February 2024 Irish Manufacturing


predictions. This means anomalies are more reliably defined, with finer classifications and alerts raised more appropriately. Human feedback on data anomalies trains the


software, establishes patterns for systemised models, and allows causes and solutions to be correctly categorised and communicated. Having learned what is important or not, notifications and alerts are raised to the appropriate people at the best time and in the preferred way. This can be via high level reports, maintenance interventions, text messages or direct input to smart maintenance tools.


SIMPLIFYING MACHINE DESIGN Beyond the machine control environment there are applications for AI in machine design and operation. We will soon see more powerful software tools that support designers and programmers with AI optimised machine designs. These will be programmed more intuitively than today using plain speech or text, making them much easier to use.


AI will also enable us to create complex machine models more rapidly and accurately. Digital Twins will play an intrinsic role by incorporating all the information about components and sub-systems: their physical attributes, performance dynamics and operation. 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. In time, Digital Twins will allow complete plant operations to be mapped, monitored and optimised using AI. Another great example of AI in action is in the maintenance and repair stage of machines’ lifecycles. Our technical support specialists have a reoccurring task to identify photographs sent to them of Festo components on their machines. These sometimes include the labels or sometimes just the product. Now an AI supported service helps customers identify their product images – whether it is of the data matrix, the product label, or the product image. The system’s recognition capability is constantly improving, and its scope is being expanded from a few product families to encompass the whole Festo range. Once a product is identified the specific Spare Parts catalogue information and complete product data is immediately accessible.


REALISING AI’S POTENTIAL There are clearly wider risks and challenges as we move towards an AI-enabled future. Factors like IP ownership and in-built bias need to be monitored and carefully addressed and, as AI solutions become ever more convincing, we need to be careful that logic errors aren’t built-in, reinforced, or repeated. The responsibility remains with humans to verify and check automated outputs. Staying up to date with the latest AI


developments is essential if we are to realise its full potential and enable society to increase confidence in the technology. We are positively embracing the new era of AI at Festo Ireland and look forward to our customers reaping the rewards.


www.irish-manufacturing.com


Page 1  |  Page 2  |  Page 3  |  Page 4  |  Page 5  |  Page 6  |  Page 7  |  Page 8  |  Page 9  |  Page 10  |  Page 11  |  Page 12  |  Page 13  |  Page 14  |  Page 15  |  Page 16  |  Page 17  |  Page 18  |  Page 19  |  Page 20  |  Page 21  |  Page 22  |  Page 23  |  Page 24  |  Page 25  |  Page 26  |  Page 27  |  Page 28  |  Page 29  |  Page 30  |  Page 31  |  Page 32  |  Page 33  |  Page 34  |  Page 35  |  Page 36  |  Page 37  |  Page 38  |  Page 39  |  Page 40  |  Page 41  |  Page 42  |  Page 43  |  Page 44