Improving Fault Detection Accuracy_

Harnessing A.I. Image recognition for microchip quality control

Find out how

The ask

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.

 

BUSINESS ACCEPTANCE CRITERIA_

 

The manufacturer asked for our help in creating a new solution that could meet three business acceptance criteria:

 

Cracked stats

What we did

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.

What we did Broadcom

WE WERE ABLE TO MAINTAIN THE SPEED OF IMAGE HANDLING WHILE MAINTAINING THE CLIENT’S STRICT QUALITY STANDARDS.


The process

There were three challenges facing quality assurance.

 

CHALLENGE 01

PROVIDING ACCURATE A.I. TRAINING DATA_

 

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.

01 process

01

Original

02 process

02

Window Creation

03 process

03

10x Augmentation

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.


CHALLENGE 02

DIFFERENTIATING CRACKS FROM SCARS_

 

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.

01 original scars

01

Original

02 masking scars

02

Masking
scars

03 visible cracks

03

Cracks become visible


CHALLENGE 03

MEETING COMMERCIAL DEMANDS_

 

The final challenge was to meet the production line requirements, allowing the solution to work not just from a theoretical point of view, but to be applicable in the real world where it can meet the commercial demands of the business. To achieve this, we needed to take A.I. out of the lab and into production by using our 20 years’ engineering and integration experience and understanding of technical capabilities gained from Intelygenz Labs. In this case, we needed to utilise the customer’s centrally-controlled Edge computing abilities in order to meet the operational needs and ensure commercial viability. To achieve this, we used a cloud environment to simulate and fine tune the solution, with the intention of porting it to local hardware once ready. This approach allows us to flexibly make adjustments and ensures the final solution will meet the speed requirements when applied in the real-world environment.

Results

0%

OF FAULTY DIES ARE MISLABELED AS GOOD. QUALITY STANDARD MAINTAINED.

<1%

OF GOOD DIES ARE MISLABELED AS “CRACKED” (11% IMPROVEMENT OVER EXISTING PROCESS – LESS WASTE)

In the current simulated environment, this computer vision A.I. solution automates the identification and diversion of faulty dies with an extremely high level of accuracy. The solution has a false negative error rate of 0%, meaning no faulty dies are classified as “GOOD”.

Microchip manufacturing

A.I. SOLUTION AUTOMATES THE IDENTIFICATION WITH AN EXTREMELY HIGH LEVEL OF ACCURACY.

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.


Further improvements

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.

The benefits of automation

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:

Customer Value

CUSTOMER VALUE:

  • Improved service quality
  • Round the clock service delivery • Improved service consistency
  • Faster service resolution
  • Round the clock availability
Employee Value

Employee Value:

  • More engaging work
  • Increased employee satisfaction
  • More time for human contact with customers
Shareholder Value

Shareholder Value:

  • Higher ROI within the first year
  • Operational efficiencies
  • Increased accuracy
  • Increased speed
  • Workforce flexibility
  • Competitive advantage
  • Increased scalability
  • Brand enhancing
Share on: Facebook Twitter LinkedIn

BOOK A CONSULTATION

For a free assessment, answers to your questions, or to discover how software and AI can be integrated into your business, don’t hesitate to get in touch.

Let's Talk