Concept: US-based semiconductor equipment manufacturer Applied Materials launched optical semiconductor wafer inspection machines using AI and big data technology. These machines are used in chip factories to automatically inspect chips and detect killer defects that can ruin chips. These chips are formed through hundreds of manufacturing steps before they are finished and sliced into individual chips that are used in electronic products.

Nature of Disruption: Applied Materials leverages AI and big data in the inspection machine to examine more chips and also to detect advanced defects that can damage the chips. For a chip maker, these techs will help in the timely detection of the quality of chips thereby earning more revenue and profits over the life of a manufacturing process. The company provides three solutions that work together in real-time to find and classify defects faster, better and cost-effectively. The solutions include Enlight optical wafer inspection system that combines industry-leading speed with high resolution and advanced optics to collect more yield-critical data per scan; ExtractAI technology that solves wafer inspection problem by accurately distinguishing yield-killing defects from the millions of noise signals generated by high-end optical scanners; and SEMVision eBeam review system trains the Enlight system with ExtractAI technology to classify and distinguish defects from noise. This optical inspector claims to be three times faster and has the sensitivity to find yield-critical defects.

Outlook: Semiconductor technology is becoming increasingly complex and expensive. Reducing the time needed to develop and ramp advanced manufacturing process nodes can worth billions of dollars to chip makers around the world. For instance, when it comes to memory chips, a week’s downtime can knock down annual output by 2%. On top of that, the price of the chips drops rapidly over time, and falling behind schedule can severely damage revenue. Applied materials with AI and big data technologies address the pain points for the semiconductor industry in terms of quickly fixing the errors thereby reducing time and loss of revenue.

This article was originally published in