Applying the Computing Power of AI to Demanding Industrial Environments

发布日期:
June 6, 2023



Rugged platforms for demanding applications including defense, mining, agriculture, forestry, and construction have historically been constrained by the limited operational temperature ranges of high-performance processors and other key system components.  These applications typically require operational temperatures in the range of -40°C to 70°C ambient (and, thus, even higher junction temperatures), and the highest-performance, most desirable processors simply weren’t generally offered with these operational temperature ranges.

Elma's JetSys-5330 AI Computing System based on the NVIDIA® Orin® SOM

The new NVIDIA Jetson AGX Orin industrial system-on-module (SOM) opens the door to address new rugged deployable deep learning and streaming I/O platforms.
While the high-end of temperature ranges tends to get the most attention, due to the need to shift heat out of the components, ironically it is the low-end -40°C requirement that often poses the biggest challenges.  Electrical components begin to act unpredictably when they are started after a long cold soak at -40°C, often disrupting designed-for power sequencing and simply not starting correctly.  This can be addressed by introducing pre-heating mechanisms, but that requires time, power, and extra components that drive costs.  It’s much better to design for a reliable cold start at these low temperatures.

The new Jetson AGX Orin Industrial SOM provides impressive control over the power it consumes (and thus the heat it generates) by providing settings for three power budgets – 15W, 35W, 60W, up to a max of 75W. If an application does not require 100% duty cycle from the processor to meet its processing needs, the developer can set the industrial-grade module to a lower power budget to reduce the overall heat load of a deployable system.  This can mean the difference between needing an active cooling kit (i.e. fans) and being able to rely on passive fanless convection cooling.

Of the applications mentioned above, defense applications have traditionally led the way in rugged system design.  Various standards such as MIL-STD-810 define both the environmental requirements that electronic components must reliably operate in, as well as the test methodologies needed to validate that the components do, in fact, meet the requirements.

In addition to the temperature ranges, rugged systems need to deal with extremes of vibration and shock, humidity, rain and icing, blowing sand and dust, electro-static discharge (ESD), and exposure to liquid contaminants such as fuel, hydraulic fluid, and even something as mundane (but surprisingly damaging) as coffee or soda pop.  With the rise of AI-driven automation in non-defense rugged applications, it is natural to turn to deployable defense platforms for guidance on how to ruggedize for these similarly demanding, non-defense applications.

Elma Electronic has taken this approach with our latest rugged integrated system, the JetSys-5330.  We leveraged years of experience in designing rugged deployable AI/embedded computing systems to ensure that the rugged platform will reliably operate even under the most demanding situations.  Let’s take a look at some examples of where this can be important:


- Operational temperatures:  Clearly applications like mining, agriculture, construction, and forestry (referred to herein as MACF for this article) require operation across a wide range of temperatures.  Mid-winter in northern Canada can expose MACF vehicles to the -40°C range, while electronic systems in mining vehicles in Australia or central Africa must contend with 45°C ambient plus additional heat generated by the vehicle. The Jetson AGX Orin Industrial supports from -40C to 85C at the TTP surface.

- Shock and vibration:  MACF platforms generally live their operational lives under constant barrage of vibrations and shock.

- Humidity, rain, icing, blowing sand and dust, and other liquid contaminants: The Ingress Protection code (or IP code) is the generally accepted approach for defining (and verifying) what sort of contaminant intrusion an electronic system can reliably withstand.  MACF systems generally operate in environments that require up to IP67-levels of ingress protection (no ingress of dust, and total immersion into 1m of water for 30 minutes).  Additional testing for liquid contaminants is often an operational requirement.  While it is possible to protect sensitive computing systems by placing them in environmentally controlled cabinets, the freedom to place a system wherever it is needed without concern for exposure to environmental contaminants is an important feature.

- ESD:  MACF systems operate in dusty environments and around human operators which often expose sensitive electronic systems to ESD events.  Thus advanced AI/streaming video systems must be tolerant of ESD events.

To reliably leverage the unprecedented, embedded AI and streaming vision processing capabilities of the AGX Orin for environmentally demanding MACF applications, system integrators and vehicle OEMs should consider suppliers with deployable defense computing system experience.  Elma’s JetSys-5330, with its NVIDIA Jetson AGX Orin Industrial SOM, introduces a compelling AI and vision processing solution for many MACF autonomous vehicles or operational automation applications.

You'll find more details on the JetSys-5330 on the product page.

NVIDIA, Jetson and Orin are all trademarks of NVIDIA Corporation

Downloads

No items found.

阅读更多博客文章

Partners Corner: What is Edge AI Enabling in Industrial Computing Applications?

Partners Corner: What is Edge AI Enabling in Industrial Computing Applications?

Similar to how cloud computing evolved over the last decade to the de facto way of storing and managing data, Edge AI is taking off. Edge AI is one of the most notable trends in artificial intelligence, as it allows people to run AI processes without having to be concerned about security or slowdowns due to data transmission. And its impact is notable in industrial embedded computing, since it allows platforms to react quickly to inputs without access to the cloud. We asked some Edge AI partners: If analytics can be performed in the cloud, what is the benefit of an Edge AI approach, especially as it’s related to industrial embedded computing?

Membership in the NVIDIA® Partner Network

Membership in the NVIDIA® Partner Network

We are taking AI Computing to the next level! Find out how our membership in the NVIDIA® Partner Network complements the designs of our rugged computing systems to deliver enhanced deployable systems specifically designed to operate in harsh environments.