Artificial intelligence (AI) offers significant benefits for machine builders and end users but this usually involves large volumes of data and cloud computing. However, as this article explains, multicore processing means that machines can have AI onboard, so data can be collected and actions taken in real time.
With an increasing price pressure trend in the market and a more stringent regulatory compliance framework, manufacturers - particularly in the pharmaceutical industry - are re-thinking their processes to be more flexible and adaptive to change. To cope with that, the packaging industry serving them and other industries has experienced a continuous increase in the automation content and in the amount of data taken from the machine, referred to as 'sensorisation'. The result is an abundance of data to process, with more processing capability needed.
Thanks to this increased processing power and the availability of increasing volumes of data, the discussion about Artificial Intelligence (AI) in manufacturing industries is gaining momentum. In the case of the advances required for Industry 4.0 - such as predictive maintenance, networking and efficient production - the use of adaptive algorithms offers enormous potential. Many packaging companies are realising that AI presents an opportunity to increase not only the Overall Equipment Effectiveness (OEE) - and therefore combine reduced costs with increased productivity - but also to improve the analysis of data to contribute to continuous improvement programmes such as reducing waste or process operations variability at their customers end.
However, there is still something of a chasm between the desired status and the reality of the situation: many of the AI solutions advertised on the market, which are often cloud-based, have significant requirements in terms of infrastructure and IT; these solutions also work with an overwhelming amount of data that is laborious and time-consuming to prepare and process. The question of added value often remains somewhat murky for providers, who cannot determine whether and how the investment in AI will provide a return. The fact that system designs for manufacturing industry are generally both complex and unique is another contributing factor.
Given these conditions, how do we go about designing and integrating AI that creates tangible added value in the production process? Instead of laboriously searching a huge volume of data for patterns, in addition to the processes that are running, Omron tackles things from the other direction: the required AI algorithms are integrated in the machine control system, thereby creating the framework for real-time optimisation truly on the edge - at the machine, for the machine. In contrast to cloud computing, where individual manufacturing lines or sites are analysed using limited processing power at a high level, the AI controller used by Omron, which features adaptive intelligence, is closer to the action and learns to distinguish normal patterns from abnormal ones for the individual machine.
The AI controller integrated in Omron's Sysmac platform - a complete solution for factory automation featuring modules for control, motion and robotics, image processing and machine safety - is primarily used in the packaging process at the points where the customer is experiencing the greatest efficiency problems (the bottlenecks). The processes gain intelligence based on previous findings and improvements that have been made and subsequently drive holistic optimisation of the entire packaging line.
By utilising the benefits of multicore processing, the Sysmac controller uses two processor cores for general Sysmac machine control functions, another core is dedicated to motion control functions and the fourth core is used solely for AI.
With world-class OEE values said to be 85 per cent and above, an average OEE in a typical pharmaceutical packaging line around 30 per cent seems a big challenging to improve. However, other industries where packaging lines have benefited from implementing traditional automation have achieved values ranging from 65 to 75 per cent. But, what if you go beyond that and use artificial intelligence for automation? If quality is improved and predictive maintenance is used to prevent machine downtime, it is possible to make much more significant efficiency gains.
In any case, regardless of the number, what really matters about getting OEE information is what you do with it and how you tackle the identified pain points. An AI controller provides optimisation in exactly this area: what needs to be done to improve; it is driven by practical requirements and aims to noticeably improve operations in real-time, the closer to the action the better. It is important to note that an improvement of just a few percentage points can result in significant efficiency gains and cost reductions. With its new AI solution, Omron hopes to drive added value and practical improvements, thereby helping to create a smarter industry.