{"id":383,"date":"2022-08-16T12:00:59","date_gmt":"2022-08-16T12:00:59","guid":{"rendered":"https:\/\/globalgoodplay.com\/?p=383"},"modified":"2022-11-07T10:51:43","modified_gmt":"2022-11-07T10:51:43","slug":"smart-devices-smart-manufacturing-pegatron-taps-ai-digital-twins","status":"publish","type":"post","link":"https:\/\/globalgoodplay.com\/?p=383","title":{"rendered":"Smart Devices, Smart Manufacturing: Pegatron Taps AI, Digital Twins"},"content":{"rendered":"
\n

In the fast-paced field of making the world\u2019s tech devices, Pegatron Corp. initially harnessed AI to gain an edge. Now, it\u2019s on the cusp of creating digital twins to further streamline its efficiency.<\/p>\n

Whether or not they\u2019re familiar with the name, most people have probably used smartphones, tablets, Wi-Fi routers or other products that Taiwan-based Pegatron makes in nearly a dozen factories across seven countries. Last year, it made more than 10 million notebook computers.<\/p>\n

Andrew Hsiao, associate vice president of Pegatron\u2019s software R&D division, is leading the company\u2019s move into machine learning and the 3D internet known as the metaverse.<\/p>\n

Building an AI Platform<\/b><\/h2>\n

\u201cWe\u2019ve been collecting factory data since 2012 to find patterns and insights that enhance operations,\u201d said Hsiao, a veteran tech manager who\u2019s been with the company for 14 years, since it spun out of ASUS, one of the world\u2019s largest PC makers.<\/p>\n

In 2016, Pegatron\u2019s COO, Denese Yao, launched a task force to apply new technology to improve operations. Hsiao\u2019s team of AI experts collaborated with factory workers to find use cases for AI. One of their first pilot projects used deep learning to detect anomalies in products as they came down the line.<\/p>\n

It got solid results using modified versions of neural network models like ResNet, so they stepped on the gas.<\/p>\n

Today, Pegatron uses Cambrian, an AI platform it built for automated inspection, deployed in most of its factories. It maintains hundreds of AI models, trained and running in production on NVIDIA GPUs.<\/p>\n

Fewer Defects, More Consistency<\/b><\/h2>\n

The new platform catches up to 60% more defects with 30% fewer variations than human inspectors, and factory employees appreciate it.<\/p>\n

\u201cManual inspection is a boring, repetitive job, so it\u2019s not surprising employees don\u2019t like it,\u201d he said. \u201cNow, we\u2019re seeing employees motivated to learn about the new technology, so it\u2019s empowering people to do more value-added work.\u201d<\/p>\n

The system may also improve throughput as factories adjust workflows on assembly and packing stations to account for faster inspection lines.<\/p>\n

Models Deployed 50x Faster<\/b><\/h2>\n

Pegatron\u2019s system uses NVIDIA A100 Tensor Core GPUs to deploy AI models up to 50x faster than when it trained them on workstations, cutting weeks of work down to a few hours.<\/p>\n

\u201cWith our unified platform based on DGX, we have our data lake, datasets and training all in one place, so we can deploy a model in one click,\u201d Hsiao said.<\/p>\n

Using the Multi-Instance GPU capability in A100 GPUs, Pegatron cut developers\u2019 wait time for access to an accelerator from nearly an hour to 30 seconds. \u201cThat lets us dynamically schedule jobs like AI inference and lightweight model training,\u201d he said.<\/p>\n

As part of its AI inference work, the system analyzes more than 10 million images a day using NVIDIA A40 and other GPUs.<\/p>\n

Triton, NGC Simplify AI Jobs<\/b><\/h2>\n

Pegatron uses NVIDIA Triton Inference Server, open-source software that helps deploy, run and scale AI models across all types of processors, and frameworks. It works hand-in-hand with NVIDIA TensorRT, software that simplifies neural networks to reduce latency.<\/p>\n

\u201cTriton and TensorRT make it easy to serve multiple clients and convert jobs to the most cost-effective precision levels,\u201d he said.<\/p>\n

Hsiao\u2019s team optimizes pretrained AI models it downloads in integrated Kubernetes containers from the NVIDIA NGC hub for GPU-optimized software.<\/p>\n

\u201cNGC is very helpful because we get with one click the deep learning frameworks and all the other software components we need, stuff that used to take us a lot of time to pull together,\u201d he said.<\/p>\n

Next Step: Digital Twins<\/b><\/h2>\n

Taking another step in smarter manufacturing, Pegatron is piloting NVIDIA Omniverse, a platform for developing digital twins<\/p>\n

It has two use cases so far. First, testing Omniverse Replicator to generate synthetic data of what products coming down the inspection line might look like under different lighting conditions or orientations. This information will make its perception models smarter.<\/p>\n

Second, it\u2019s creating digital twins of inspection machines. That lets remote workers manage them remotely, have better insight into predictive maintenance and simulate software updates before deploying them to a physical machine.<\/p>\n

\u201cToday, when a system goes down, we can only check logs that might be incomplete, but with Omniverse, we can replay what happened to understand how to fix it, or, run simulations to predict how it will behave in the future,\u201d he said.<\/p>\n

What\u2019s more, industrial engineers who care about throughput, automation engineers responsible for downtime, and equipment engineers who handle maintenance can work together on the same virtual system at the same time, even when logging in from different countries.<\/p>\n

Vision of a Virtual Factory<\/b><\/h2>\n

If all goes well, Pegatron could have Omniverse available on its inspection machines before the end of the year.<\/p>\n

Meanwhile, Hsiao is looking for partners who can help build virtual versions of a whole production line in Omniverse. Longer term, his vision is to create a digital twin of an entire factory.<\/p>\n

\u201cIn my opinion, the greatest impact will come from building a full virtual factory so we can try out things like new ways to route products through the plant,\u201d he said. \u201cWhen you just build it out without a simulation first, your mistakes are very costly.\u201d<\/p>\n<\/div>\n","protected":false},"excerpt":{"rendered":"

In the fast-paced field of making the world\u2019s tech devices, Pegatron Corp. initially harnessed AI to gain an edge. Now, it\u2019s on the cusp of creating digital twins to further streamline its efficiency. Whether or not they\u2019re familiar with the name, most people have probably used smartphones, tablets, Wi-Fi routers or other products that Taiwan-based<\/p>\n","protected":false},"author":1,"featured_media":384,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[6],"tags":[],"class_list":["post-383","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-blog"],"_links":{"self":[{"href":"https:\/\/globalgoodplay.com\/index.php?rest_route=\/wp\/v2\/posts\/383"}],"collection":[{"href":"https:\/\/globalgoodplay.com\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/globalgoodplay.com\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/globalgoodplay.com\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/globalgoodplay.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=383"}],"version-history":[{"count":2,"href":"https:\/\/globalgoodplay.com\/index.php?rest_route=\/wp\/v2\/posts\/383\/revisions"}],"predecessor-version":[{"id":655,"href":"https:\/\/globalgoodplay.com\/index.php?rest_route=\/wp\/v2\/posts\/383\/revisions\/655"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/globalgoodplay.com\/index.php?rest_route=\/wp\/v2\/media\/384"}],"wp:attachment":[{"href":"https:\/\/globalgoodplay.com\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=383"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/globalgoodplay.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=383"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/globalgoodplay.com\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=383"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}