Siemens Digital Industries Software’s SynthAI service is delivering the power of machine learning (ML) and artificial intelligence (AI) to solve the challenge of training machine vision systems.
“We were looking for a quick and easy solution that will enable us to detect wire terminals in a robotic electric cabinet assembly station. With SynthAI, our control engineers were able to achieve great results within just a few hours,” said Omer Einav, CEO of Siemens’ client, Polygon Technologies. “The tedious task of annotating a large set of training images to train the model was shortened significantly. The results show great promise for many additional use-cases we plan to handle with SynthAI.”
Machine learning is used for a variety of vision-based automation use-cases such as robotic bin picking, sorting, palletising, quality inspection and more. While usage of machine learning for vision-based automation is growing, many industries face challenges and struggle to implement it within their computer vision applications. This is due to the need to collect many images of the parts in question and the challenges associated with accurately annotating the different products within those images – particularly before production or manufacturing begins.
To solve this challenge, synthetic data is used to speed up the data collection and training process. However, utilising synthetic data for vision use-cases requires expertise in synthetic image generation and can be complex, time consuming and expensive. This is where Siemens’ SynthAI changes the game.
Rather than waiting for pre-production parts to be ready or using complex processes to generate synthetic data, machine vision specialists only need to provide 3D CAD data of the parts. SynthAI will then automatically generate thousands of randomised annotated synthetic images within minutes, without the specialist knowledge typically required.
SynthAI will also automatically train a machine learning model that could be used to detect a product in real life. Once the training is done, the trained model can be downloaded, tested and deployed offline, using no more than a little Python coding. If organisations prefer to handle training of their own systems, complete synthetic image datasets together with the annotations are also available.
Five data centre trends to watch in 2025
IT in Manufacturing
Any innovation that comes out in 2025 – whether it’s flying cars, highly advanced AI or a breakthrough medical treatment – will be built on the back of an equally innovative IT foundation driven by data. Data that needs to be stored, managed and made accessible in the data centre, in the cloud or at the edge. Is it too much of a stretch to say the future of humankind is dependent on data storage? We don’t think so.
Read more...Recovering from a cyberattack
IT in Manufacturing
While many organisations have invested heavily in frontline defence tools to try to keep out bad actors, they have spent far less time and money preparing for what happens when the criminals eventually get in. And they will get in.
Read more...The value of proactive maintenance management Schneider Electric South Africa
IT in Manufacturing
Maintenance has come a long way from the days when we waited for things to break, and thanks to the ever-increasing capabilities of technology, predictive maintenance has become a viable solution for keeping equipment running smoothly and efficiently around the world.
Read more...Pinpointing pipeline occurrences in seconds, not hours Schneider Electric South Africa
IT in Manufacturing
At any given moment, thousands of kilometres of critical assets flow through pipelines that cross veld, mountainous areas, dense forests, and even busy streets. Surprisingly, many of these pipelines operate either unmonitored or with scant oversight, leading to missed opportunities for operational continuity and efficiency.
Read more...Next-generation AI-enhanced electronic systems design software Siemens South Africa
IT in Manufacturing
Siemens Digital Industries Software has launched the latest advancement in its electronic systems design portfolio. The next-generation release takes an integrated and multidisciplinary approach, bringing a unified user experience that delivers cloud connectivity and AI capabilities to push the boundaries of innovation in electronic systems design.
Read more...Spatial computing and AI – where no man has sustainably gone before Schneider Electric South Africa
IT in Manufacturing
Some will argue that we now live in a sci-fi world where we dream of electric sheep, and today’s technology – unlike HAL – can provide us with the answers we seek. To the realist it might seem a bit implausible, but when you start using terms like ‘spatial computing realises sustainable AI’ it doesn’t seem that far-fetched.
Read more...Safeguarding DCS today and tomorrow Schneider Electric South Africa
IT in Manufacturing
Today’s distributed control systems (DCS) are highly intelligent, converging OT and IT in a centralised manner that allows for simplified management and coordination of operations. It is technology evolution at its finest, but with a caveat, cybersecurity challenges.
Read more...Quantum computing is not as futuristic as it sounds
IT in Manufacturing
The first quantum computer was created almost three decades ago. While its applications are still unknown to many, this advanced field combines computer science, physics and mathematics to deliver solutions the world has been trying to find for aeons – and those it doesn’t yet know it needs.
Read more...Transform field data into actionable business data
IT in Manufacturing
As part of its ongoing commitment to enhancing industry connectivity, Teledyne Gas & Flame Detection is making its new and proprietary Teledyne GDCloud available with the company´s GS700, GS500 and Shipsurveyor portable gas leak detectors, and also its PS200 portable four-gas monitor for personal safety and confined-space applications.
printer friendly version