Flexciton AI-based software enables upgrade to smart fabs

Industry 4.0 and its intelligent use of data is revolutionising the way many companies manufacture their products more efficiently, Flexciton claim. However, the company points out that chip fabs are the most complex manufacturing environments in the world, yet they’re slow to adopt AI software that has the power to make them smarter by automating decisions and optimising production.

Flexciton CEO and Co-Founder, Jamie Potter, explained, “Fabs commonly use heuristic software where rules have been written by engineers to run the production and are based on historical data. This set of rules is used by the software to dispatch the wafers to the various tool sets across the fab. There is no intelligence built into the software. The intelligence comes from the skilled industrial engineers who use their years of experience to adjust and tweak the scheduling rules to allow for changing conditions and production requirements.”

A truly smart fab uses scheduling software with intelligence built-in that can holistically look at the current state of the production to spot bottlenecks and idle machines to automatically adjust to prevent them. The data that both approaches require is the same and is already automatically gathered by most fabs and stored in their MES. The heuristic approach looks at the current data using on-premise computers and generates the schedules based on the rules.

“We have found that this is not very efficient as it is based on historical data and pre-set rules,” he added. “The rules have to be written by engineers and so they are dependent on people’s knowledge and experience to try and anticipate what will be the right decision in all possible scenarios. Because it is impossible to predict all instances that may happen in the future, the rule set requires constant tweaking and maintenance.  

This is a huge amount of work and requires constant updating with new rules and, if the engineers that wrote them leave - you're in trouble. This is where heuristics are particularly weak. The rules aren't necessarily wrong, but the decisions they give are inconsistent. They also struggle to cope with most complex constraints and are obviously unable to automatically adjust to rapid changes happening in a fab. These decisions aren't usually overridden, they are just allowed to happen in the fab at the expense of factory efficiency that can steadily decrease over time.”

For example, the rules don't take into account a hard-physical constraint in the factory and, as a result, may try to provide an instruction which is physically impossible to implement. Then an operator must step in to override the system. 

In addition, the on-premise computers are limited by their processing power which means that they are limited to only evaluating a very small number of possible scheduling scenarios. By contrast, Flexciton AI scheduling software runs on computer processing power by using Cloud computing.  This means that it can evaluate billions of possible scheduling options every five minutes to select the one that exactly meets the KPIs that have been set. Flexciton optimisation algorithms thus offer intelligence and capabilities that are way beyond what humans are able to offer.

He concluded, “Once implemented, the fab is truly smart. It operates without the constant requirement for engineers to be tied up in time-consuming and costly daily maintenance, adjusting or writing new rules. It uses smart technology to automatically adjust production schedules to changing objectives or new fab conditions such as new tools, recipes, product mixes, etc. without needing human programming. Apart from saving this on-going overhead and freeing the engineers up for other work, the Flexciton software provides a significant improvement in productivity. Unlike the heuristic-based software that can only see a couple of steps ahead at best in individual toolset areas, Flexciton software knows what is happening throughout the fab. It’s like a chess player being able to see many moves ahead and adjusting the scheduling to prevent bottlenecks and idle machines. This results in more wafers being processed by the fab so that going smart quickly pays for itself.”