IDMs

Jay Vleeschhouwer, managing director of Griffin Securities, has followed the EDA industry as a leading financial analyst for 25 years and is a popular speaker at the annual Design Automation Conference. Vleeschhouwer discusses his DAC presentation The State of EDA: A View from Wall Street.

Traditionally, defect classification is done manually by operators or using Automated Optical Inspection (AOI) machines, often leading to classification inconsistencies. Also, rules-based AOIs may at times be unable to fully satisfy project requirements due to the rigidity of inspection recipes. SixSense – Breaking the Status Quo with Artificial Intelligence Enter SixSense, an AI-powered defect classification software platform that has been making breakthroughs in defect detection and classification for semiconductors to make manufacturing smarter and more efficient. Founded in 2018, SixSense has already amassed a wealth of experience and chalked up a number of successes such as automating the manual image classification process, reducing manufacturing false rejects, and capturing escapees. Infineon Technologies and GlobalFoundries were amongst the early adopters of SixSense’s platform: classifAI. With Infineon, classifAI has allowed over-rejection rates to be precisely quantified. classifAI – Simple UI, Easy Usage, Powerful Models As a UI-based assistive software platform, classifAI, SixSense’s automated defect classification platform is built with the defect and yield engineer in mind. SixSense takes care of all the back-end complexities – such as coding, algorithm modelling and deployment – to enable end users to get started and use the platform with a simple GUI. The simplified end-to-end AI pipeline offered on the platform includes data labelling to make data AI-ready, model training, and model testing. Ultimately, models are deployed on the production floor for 24/7 inferencing of hundreds of millions of images every year, at scale, across processes, tools and sites. Machine learning models built by the SixSense team have seen strong results, with model accuracy of up to 98% in certain use cases. Track Record of delighting IDMs, Foundries and OSAT Customers SixSense has consistently solved visual inspection problems and enabled the success of IDMs, foundries and OSATs since its inception. The AI technology has helped a range of customers across 100mm-300mm wafer standards, both pure silicon and compound wafers, and caters to specific end-use market requirements such as RF and automotive. Partnerships between startups and established manufacturers are key to actualizing the value of AI in manufacturing. “Our collaboration with AI startup SixSense has enabled us to explore opportunities in yield gain, improving cycle time, and real-time monitoring of process shifts,” said Dato’ Tan Soo Hee, Executive Vice President, Global Backend Operations at Infineon Technologies Asia Pacific. “SixSense has been very attentive to the needs of our engineering team, addressing project requirements using a customer-first approach evident in the design of the intuitive software platform,” said Melvyn Peh, Principal Engineer, Automation-Scan-Pack, Infineon Technologies Asia Pacific. The intelligent annotation module is one of many offered by SixSense, which uses AI to train AI and accelerate the data annotation process by focusing on the semiconductor-specific requirements. Another valuable module in classifAI is advanced analytics that capture the heatmap for defect distribution on the images. Images are stacked on top of each other, with the location of defects aggregated to provide the defect heatmap. Through this, systematic failure patterns were identified that allowed defect engineers to zero in on key sources of failure and assist in root-cause analysis. Infrastructure – Scale Fast, Adapt Quickly, Accelerate Value Creation In the dynamic world of technology, machine learning and AI projects must meet changing infrastructure demands. A cloud-first approach is often favored for the plethora of benefits it offers. “We’re looking forward to a great partnership with SixSense, treading together hand in hand exploring fresh ideas and possibilities,” said Manju Jalali, Vice President of digital manufacturing at GlobalFoundries, who oversees the company-wide roll out of classifAI. For use cases where on-premise deployments are preferred, SixSense offers such options for infrastructure integration, satisfying all possible infrastructure requirements in the market. Contributing to a vibrant innovation ecosystem SixSense was mentioned by Singapore’s Deputy Prime Minister Heng Swee Keat during an event that marked Infineon’s 50th anniversary in Singapore: “I am heartened that Infineon will be investing more than $27 million over three years on an AI initiative in Singapore. Under this initiative, Infineon Singapore will be partnering academia, industry, and local startup SixSense AI to develop new AI solutions and courses.” Explosive Growth of AI in Chip Manufacturing According to a McKinsey Company report, AI contribution to semiconductor company earnings is projected to rise to between $85 billion and $95 billion per year in the coming years. SixSense has been taking great strides in creating value for their semiconductor customers. “SixSense offers tremendous value in a high-growth vertical in the semiconductor industry, marrying the latest deep learning algorithm with the compute power of the cloud,” said Rajan Rajgopal, CEO of DenseLight Semiconductor. “This leads to faster root-cause analysis that helps reduce the cost of non-conformance and improve quality.” Dominic Teo is Enterprise Business Development Representative at SixSense. He can be reached at [email protected].

D-SIMLAB Technologies, a Singapore-based provider of simulation-based business analytics and optimisation software solutions, recently joined SEMI. I spoke with Peter Lendermann, the company’s co-founder and Chief Business Development Officer, about the company’s role in the smart manufacturing movement, how customers are benefiting from D-SIMLAB solutions, and what the future holds for smart manufacturing. Ng: What is D-SIMLAB’s mission?Lendermann: Our mission is to develop, market, and deliver high-performance simulation-based decision support solutions that enable corporations to enhance their performance in a sustainable manner leading to significant cost savings. In particular, we focus on semiconductor manufacturing material flow planning and optimisation but also do business in aviation where we help customers optimise their spare parts support operations. What these two domains have in common are three important attributes: They are capital intensive, their underlying operations are complex, and operations are also heavily affected by random, i.e. unpredictable events, which makes both planning and execution of manufacturing operations very challenging. D-SIMLAB is a spin-off from the Singapore Institute of Manufacturing Technology (SIMTech) under the Agency for Science Technology and Research (A*STAR). Our head office is in Silicon Island Singapore. We also have representations in Germany and the U.S. Most of our staff are industrial and computer engineers with up to 20 years of operations experience in their respective industry domain, as well as vast data analytics and software development capability.Ng: What solutions does D-SIMLAB offer to optimise semiconductor manufacturing?Lendermann: In the three-pillar smart manufacturing framework of Connect, Sense and Predict advocated by SEMI, our focus is on Predict though we emphasise the equal importance of the subsequent Act: Our solutions can Predict, for example, WIP waves or usage-based preventive maintenance due dates. But much more value-add can be realised once some decisions with regard to how to Act can be derived from such a prediction. The ability to pro-actively adjust action plans in a timely manner is essential to overcoming challenges arising from changing customer due dates, mix profile changes, untimely production line issues, and production capacity to be shared with R D lots effectively, so that ultimately our customers can enhance capacity, reduce cycle times and improve the due-date performance of their factories.To that end, our D-SIMCON solution suite spans the full spectrum of decision-support tools required to forecast, manage and optimise material flow – from operational scheduling and dispatching, WIP forecasting and dynamic and static capacity planning all the way to specific applications for fab load mix optimisation or for the enhancement of the product/layer dedication and resist allocation in the lithography area. Our solutions are implemented in numerous 6-, 8- and 12-inch wafer fabs operated by both IDMs and foundries worldwide with capacity ranging from 40,000 to 200,000 wafers per month.Ng: What are the key enablers of D-SIMLAB’s success?Lendermann: Our success lies in deploying production-ready solutions for our customers, allowing them to extract immediate value. Our solutions enable the portrayal of many domain-specific characteristics such as queue time constraints or specific equipment behaviour, which is absolutely essential to generating operationally feasible plans or schedules in order to be able to Act in the best possible manner according to what has been Predicted. Moreover, we have modules for automatic generation, calibration and maintenance of the underlying capacity model, including resolution of data inconsistencies as well as verification and validation of the model, to allow near real-time responses to continuously changing operations. And the associated optimisation approaches focus on creating maximum possible value with as few iterations as possible and within minimum time through smart heuristics and parallel computing infrastructure – a paradigm that is as powerful as it is cost-effective.Ng: What are a few of your more notable customer successes?Lendermann: As a result of the first implementation of our novel, multi-objective based Scheduler cum Dispatcher, a tool capacity gain of 8%, a transportation capacity gain of 10%, and an operator workload reduction of 25% were concurrently realised at one of the critical equipment groups in our customer’s fab. At another set of equipment groups in the same fab, a 7% increase of lots within the critical queue time limiting area was achieved.Another use case we successfully realised is fine-tuning of Preventive Maintenance plans: Based on a seven-day lot arrival forecast at each equipment generated with our WIP Forecaster, a recommendation is made when PM would be best possible without causing too much disruption in the WIP flow. The effect of this synchronisation of the PM plan with material flow enabled a dramatic reduction of the average queue lengths at critical equipment groups and the associated cycle times without incurring any capacity loss. Reduction of average queue length as a result of synchronising preventive maintenance with material flow. Ng: What challenges has D-SIMLAB been facing in the COVID-19 world?Lendermann: Obviously, software delivery projects have become more challenging for the time being since our engineers cannot be on-site frequently. But it also turned out that more and more services can be delivered remotely, which has the nice side effect of making the services more cost-effective for customers. Overall, we are confident that our solid customer base will enable us to sail steadily through these challenging times.Ng: Where does D-SIMLAB see the technological development heading?Lendermann: In the future, enriching decision support and manufacturing execution solutions with machine learning and other AI techniques will be critical in reducing dependency on human experience. This path is essential to making manufacturing operations fully Industry 4.0-compliant. D-SIMLAB will certainly be at the forefront of this development. Bee Bee Ng is president of SEMI Southeast Asia.