A Silicon Valley chip manufacturer was looking for a new way to identify and remove cracked silicon dies (small blocks of semiconductor material) from the manufacturing line in real time, without disrupting the manufacturing process.
Historically, these cracks were easy to spot using low grade vision systems. But as the requirement for smaller chips have increased, die manufacturers have to reduce wafer thickness via backgrinding. Backgrinding produces lines (a.k.a. scars) on the dies that make cracks harder to identify.
The manufacturer asked for our help in creating a new solution that could meet three business acceptance criteria:
Using Intelligent Process Automation, we created an A.I. image recognition solution. Trained on existing images, this solution is capable of accurately classifying dies as “GOOD” or “CRACKED” and appropriately instructing the manufacturing line to continue or remove a questionable die.
Thanks to the use of machine learning, the solution is fully retrainable, meaning its accuracy can be continuously and remotely improved. This also means it can be retrained for multiple different product types.
There were three challenges facing quality assurance.
The first challenge was a lack of data available to train the A.I. with, which is a common issue for anomaly detection projects. In this case, there were very few numbers of “CRACKED” die images to work with. We used two data augmentation approaches to solve this. The first was to split each cracked image into smaller windows, and then flip and rotate them to provide 10x the amount of examples. We also used data synthesization techniques to create hugely realistic replicas of cracked dies using real-world examples as a base. It was crucial in this stage to ensure that the A.I. model was able to detect real-world cracks by using information from the synthesised cracks – in other words, they needed to be realistic enough to give an accurate reading. Once we had verified that the models were accurate enough, we were able to combine these two methods to give us a representative amount of information to train the machine learning model, meaning we could accurately classify a wider variance of images.
Once we had verified that the models were accurate enough, we were able to combine these two methods to give us an infinite amount of information to train the machine learning model, meaning we could accurately classify a wider variance of images.
Our second challenge was to enable the A.I. solution to differentiate cracks from backgrinding scars. Unlike cracks, the scars occur in uniformed patterns due to the backgrinding process. Through careful research and experimentation, our experienced Data Scientists were able to identify the best scientific approach of using Fourier Transforms as the optimal solution to identify backgrinding stripe masks. We then applied these masks to the images and then reversed the Fourier Transforms to provide cleaned images. Since cracks are never uniform, this process ensured cracks would not be removed from images by mistake.
OF FAULTY DIES ARE MISLABELED AS GOOD. QUALITY STANDARD MAINTAINED.
OF GOOD DIES ARE MISLABELED AS “CRACKED” (11% IMPROVEMENT OVER EXISTING PROCESS – LESS WASTE)
We’ve also significantly reduced the false positive error rate that was originally above 12% to below <1%, meaning very few non-faulty dies are classified as “CRACKED”.
Current speed tests indicate images can be processed in less than 0.7 seconds, which we are able to improve by fine tuning and removing complexities from the A.I. model. Once we achieve the business acceptance criteria of less than 0.4 seconds while maintaining the same false negative and false positive error rate, the solution will be placed into full production.
Though we built this image recognition software for a specific product, its A.I. model is continuously trainable. This means as more “GOOD” and “CRACKED” dies are identified, the A.I. can continually learn from the data and improve its accuracy over time. It also means the model can be applied to any new products in the future, allowing the client to achieve the same benefits of automation in manufacturing for other production lines.
This solution can be applied to the quality assurance processes across many industry verticals, as these same techniques can be trained to spot imperfections in products on productions lines throughout all stages of the manufacturing process.
At Intelygenz, we analyze our Process Automation projects using a 3-wins pattern.
To provide a real benefit to the organization, it must generate benefits for customer, employee and company: