Machine Learning in Field-Level Devices Thanks to NVIDIA® Jetson Nano™

Powerful hardware for machine learning at the field level

SYS TEC electronic entwickelt leistungsfähiges, individuelles Edge-Device inklusive Anbindung vielfältiger Sensorik zur Realisierung von Machine Learning on the edge.

Our customer needed a device powerful enough for their machine learning application. The AI was to be trained directly on the edge device. Applying the AI (artificial intelligence) at the field level reduces the ongoing costs of data transmission while providing the AI with a complete data pool of the individual plant.

The plant status data required by the AI, such as acceleration, temperature, brightness or air pressure, are collected by means of sensors. The SYS TEC electronic development team integrated these directly in the device and created the possibility to connect further sensors via CAN bus, Bluetooth or Sub-GHz. Ethernet, WiFi and LTE interfaces are available for communication.

The required high computing power within the edge device is provided by the NVIDIA® Jetson Nano™ module, which is designed for use in embedded IoT applications. It is plugged as a System on Module (SOM) onto the carrier board developed by SYS TEC electronic.

Training of an artificial intelligence, e.g. with neural networks based on tensor flow, is thus directly executable in the field. The resulting intelligent gateway is capable of analyzing the sensor data directly in the field and forwarding it in a preprocessed form. It thus meets the high customer requirements. The data connection of the device to a central cloud instance can be omitted.

SYS TEC combines many years of experience as an electronics service provider

In addition to hardware development, we provide the customer with a complete package on the software side. Thus, the development engineers of SYS TEC electronic realized the adaptation to the Linux operating system by means of Yocto and integrated RAUC for the realization of over-the-air updates (OTA) via the communication interfaces.

Python modules are available to the customer for the connection of the sensor drivers to the application software. On individual request, demo programs have also been developed to serve as a reference for the customer's implementation of the application software.

The extensive experience of the SYS TEC electronic team also enabled the solution of further challenges in the project. For example, it was necessary to ensure operation under load at an ambient temperature of 60°C and to develop a suitable cooling concept for this purpose.

As a full-service electronics provider, we not only take care of hardware and software development for our customer, but also the subsequent series introduction and assembly services.

Overview of our comprehensive services

The power of the NVIDIA® Jetson Nano™ on your device too.

You too can benefit from our many years of expertise in custom electronics development combined with the powerful computing performance of the NVIDIA® Jetson Nano™. Our consultants and experienced developers will be happy to advise you on custom-fit solutions for your specific challenge.

Your contact:

Your SYS TEC electronic sales team

Contact person