NXP, Microsoft demo edge-to-cloud ML predictive maintenance solution

May 10, 2019 //By Wisse Hettinga
NXP, Microsoft demo edge-to-cloud ML solution for predictive maintenance
New machine learning-based anomaly detection solution powered by NXP’s Anomaly Detection Toolbox, NXP i.MX RT Crossover Processors and Microsoft’s Azure IoT

NXP Semiconductors announced collaboration with Microsoft to bring Artificial Intelligence (AI) and Machine Learning (ML) capabilities for anomaly detection to Azure IoT users.

By combining complementary strengths, NXP’s offline machine learning capability and embedded processing with Microsoft’s cloud expertise, the two companies jointly demonstrate a new Anomaly Detection Solution for Azure IoT at Microsoft Build.

The solution consists of a small form factor, low power System-on-Module (SOM) powered by NXP’s i.MX RT106C Crossover Processors, a full suite of sensors, and an associated Anomaly Detection Toolbox. The toolbox utilizes various ML algorithms such as Random Forestand Simple Vector Machine (SVM), to model normal behavior of devices, detect anomalous behavior through a combined local and cloud mechanisms.

This allows much lower cloud bandwidth requirements while maintaining full online logging and processing capabilities at a fraction of the cost. Applications include predictive maintenance for rotating components, presence detection and intrusion detection.  

The solution seamlessly connects to the Azure IoT Cloud, providing customers an easy way to transfer data to the cloud, where they can visualize the data and utilize powerful data analytical tools to train behavior prediction models for deploying on edge devices.

For more information visit, https://iotedge.nxp.com/anomaly-detection/.

 


Vous êtes certain ?

Si vous désactivez les cookies, vous ne pouvez plus naviguer sur le site.

Vous allez être rediriger vers Google.