Drives & Controls May 2022

n TECHNOLOGY TECHNOLOGY n May 2022 www.drivesncontrols.com 18 SIEMENS HAS LAUNCHED a service that uses AI (artificial intelligence) to generate synthetic images of objects from CAD files. These images can then simplify the training of machine vision systems to identify the objects. Although the use of machine learning for vision-based automation is growing for applications such as robotic bin-picking, sorting, palletising and quality inspections, it can be difficult to implement because of the need to collect many images of the parts being handled and the challenges of annotating the items in those images accurately – especially before production starts. To solve this challenge, synthetic data – computer-generated simulations – is being used increasingly to speed up data collection and training. However, using synthetic data for vision applications requires expertise in generating synthetic images and can be complex, time- consuming and costly. Siemens Digital Industries Software claims that its SynthAI service changes this. Rather than waiting for pre-production parts to be ready or using complex processes to generate synthetic data, users provide 3D CAD data of their parts. The software then generates thousands of randomised, annotated synthetic images of the parts within minutes, without requiring any specialist knowledge. The tool also trains a machine-learning model automatically to detect products in real-life situations. Once the training is done, the trained model can be downloaded, tested and deployed offline – using a few lines of Python coding. For users who prefer to train their own systems, complete sets of synthetic images are available. “The market for AI for machine vision is expected to reach $25bn by 2023, but there are many challenges facing those looking to take advantage of its benefits,” points out Zvi Feuer, senior vice-president and general manager of digital manufacturing at Siemens Digital Industries Software. “SynthAI demonstrates how Siemens is taking its depth of knowledge in both product engineering systems, as well as production preparation and planning, and finding room for innovations that allow our customers to take advantage of tomorrow’s technology, today.” An early adopter of the SynthAI technology has been the Israeli robotics developer, Polygon Technologies. “We were looking for a quick and easy solution that will enable us to detect wire terminals in a robotic electric cabinet assembly station,” recalls CEO, Omer Einav. “With SynthAI our control engineers were able to achieve great results within just a few hours. 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.” https://synth.ai.sws.siemens.com Synthetic images ‘revolutionise’ the training of vision systems A CONSORTIUMOF industrial PC specialists is developing a specification for a standardised modular box PC that will guarantee interoperability of PCs from different suppliers, while offering cost- sensitive integrated designs. The PICMG (PCI Industrial Computer Manufacturers Group) consortium – which has more than 15 members, including Adlink, Eltec, General Micro Systems, Hirose, Intel, Kontron, nVent and Schroff – is hoping to transform the multi-billion dollar box PC industry by introducing an open standard to what is currently a proprietary market. The existing lack of interoperability limits the ability of end-users to achieve cost-effective and sustainable systems, the group says. The new standard, called ModBlox7, will specify a compact, modular box PC that is configurable, supports passive conductive cooling, and can be wall-mounted, snapped onto a DIN rail, or integrated into a 19”rack. The height and depth will be fixed, while the width will be variable in multiples of 7HP. The robust modular designs will be suitable for demanding applications. A PICMG committee is drawing up a specification describing the housing mechanics, function modules and electrical interconnections. The aim is to ratify this specification by the end of 2022. The specification is expected to include: n a cost-effective design that avoids the need for additional backplanes or heatsinks, thus minimising mechanical work; n co-planar board-to-board connectors that couple each PCB to its neighbour and route I/O interfaces (PCIe and USB) to the next board; n encapsulated plug-in modules in multiples of 7HP widths for functional assemblies such as power supplies, CPUs, switches and I/O; and n the ability for each module to host a stack of up to three PCBs. “For industrial end-users, the advantages of a box PC open standard lie in the cost- effective design of the dedicated systems and the flexible interchangeability of components to tailor the platform for dedicated tasks,” says Mathias Beer, chief product officer at PICMG member, Ci4Rail. “Manufacturers also benefit, as the interoperability between the units strengthens their core competence, and they do not have to develop each unit and its embedded components such as cables and mechanics themselves. For VARs and system integrators, the new ecosystem will provide faster configuration options with components from multiple vendors.” The global IPC market is predicted to grow from $4.6bn in 2021 to $6.1bn by 2026 – a CAGR of 5.8%. This expansion is being driven by a growing demand for industrial IoT, the shift towards digitalised manufacturing, stringent regulations, and a desire to optimise resources. www.picmg.org/modblox7 n Standardised box PCs will end proprietary design limitations Siemens’ SynthAI service can generate thousands of synthetic images of parts from CAD files and use them to train machine vision systems to recognise the parts