• • • SUPPLEMENT • • •
applications. But, is it going to be possible to achieve more efficient thermal solutions and better systems overall with OSM modules or SMARC modules? That can often be a hard nut to crack in the concept stage of design. Advantech can meet both low-TDP and small
form factor requirements with its next-generation edge AI modules, a number of which will be available shortly. Key among the new releases will be solutions based on Qualcomm and NXP CPU platforms.
Roadmap to the future Advantech maintains a comprehensive roadmap of new AI-on-Module introductions as innovations progress from concept, through development and validation testing, to mass production. Among the latest solutions to enter production
is Advantech’s AOM-2721, which offers a compact OSM (Open Standard Module) size L form factor of just 45 x 45 mm and is based on the ultra-high performance Qualcomm QCS6490 platform. This chipset delivers powerful edge AI thanks to AI-accelerator architecture with up to 13 TOPS potential peak AI inferencing performance at low TDP. On-device machine learning facilitates the
proliferation of edge computing use cases at an exponential scale. The Qualcomm QCS6490 System-on-Computer is purpose-built for high- performance edge computing, combining up to 8-core Qualcomm CPUs, an integrated Qualcomm Adreno GPU and a powerful AI engine (NPU + digital signal processor). Featuring AI-powered triple ISPs, scalable compute performance, premium multi- gigabit connectivity choices and expanded I/O, the QCS6490 is an ideal choice. Advantech’s AOM-2721 OSM 1.1 AI-on-Module
and sending only anonymised data back to the server is contributing to the compliance of these solutions.
Knowledge is power Thermal Design Power (TDP) represents the maximum amount of heat a component is expected to generate under typical usage conditions. In semiconductors, low TDP indicates a processor that consumes less power and generates lower heat than a higher TDP counterpart. As a result, system design engineers can offer their customers a solution with reduced energy consumption for longer battery life in portable devices, less heat output to avoid the need for extensive cooling systems, lower environmental impact and potentially quieter operation. Design engineers also need to focus on form
factor. Edge AI devices often work on the edge of what’s possible in terms of thermal solution. Small form factor is crucial due to the need for compact, power-efficient, and rugged devices that are deployable in diverse environments and
electricalengineeringmagazine.co.uk
with Qualcomm QCS6490 provides PCIe, USB 3.2, Giga Ethernet, MIPI-CSI camera serial interface, I2C serial communication protocol, serial peripheral interface, general purpose I/O, PWM (Pulse Width Modulation) and embedded DisplayPort interfaces and DisplayPort and MIPI-D serial interface displays for embedded applications. Another new AI-on-Module, Advantech’s
AOM-5521, is also now in mass production. It is based on the NXP
i.MX 95 System-on-Computer platform and offers a compact SMARC form factor of 82 x 50mm. The
i.MX 95 delivers safe, secure, power-efficient edge computing, combining AI-accelerated vision processing with high-performance compute and immersive Arm Mali-powered 3D graphics. Stand-out features include its innovative NXP Neutron NPU accelerator for machine learning, high-speed connectivity and safety and security features, as well as its integrated EdgeLock secure enclave. The Advantech AOM-5521 with NXP
i.MX95 and
its integrated AI NPU offers reliable and secure operations. It provides extensive connectivity options, including USB 2.0, USB 3.2 Gen1By1, 10 Gigabit Ethernet, MIPI-C serial interface, PCIe, as well as both a dual-channel LVDS signal interface and a 4-lane MIPI-D serial display interface. These features position the AOM-5521 as an excellent choice for a wide variety of embedded applications.
Elite performers Beyond the Qualcomm QCS6490 and NXP
i.MX95, Advantech is also planning AI-on-Module solutions featuring the Qualcomm Elite/X Plus and Qualcomm QCS9100. This is great news for design engineer sectors
such as defense because it extends choices in key applications that include loitering drones. The availability of AI-on-Modules with small form factors and low TDP, just 6.5 watts in some cases, supports critical tasks such as autonomous object detection. In fact, any applications demanding characteristics such as compliance, cybersecurity and resilience are set to benefit. Options include both solder-down OSM modules and SMARC modules, providing greater freedom in mechanical designs.
Innovative options are also upcoming for
commercial applications like intercom facial recognition. For example, a forthcoming development is the Advantech AOM-3841 AI-on- Module featuring the low-TDP Rock Chip RK3576 System-on-Computer. During a period when design engineers are
looking to create the optimal solutions by balancing many attributes; performance, reliability, resilience, form factor and low TDP, Advantech’s next-generation AI-on-Modules provide a convenient and effective way forward. In Eastern Europe, where rising demand for AI-enabled solutions is being driven by rising venture capital investment, strong government support, and a growing pool of skilled tech talent, designers must give greater credence to the availability of edge AI platforms for use in a region that continues to make notable progress on the global stage.
www.advantech.com ELECTRICAL ENGINEERING • JULY/AUGUST 2026 35
Page 1 |
Page 2 |
Page 3 |
Page 4 |
Page 5 |
Page 6 |
Page 7 |
Page 8 |
Page 9 |
Page 10 |
Page 11 |
Page 12 |
Page 13 |
Page 14 |
Page 15 |
Page 16 |
Page 17 |
Page 18 |
Page 19 |
Page 20 |
Page 21 |
Page 22 |
Page 23 |
Page 24 |
Page 25 |
Page 26 |
Page 27 |
Page 28 |
Page 29 |
Page 30 |
Page 31 |
Page 32 |
Page 33 |
Page 34 |
Page 35 |
Page 36 |
Page 37 |
Page 38 |
Page 39 |
Page 40 |
Page 41 |
Page 42 |
Page 43 |
Page 44 |
Page 45 |
Page 46 |
Page 47 |
Page 48
