NXP Semiconductors and Microsoft combined their strengths to develop a new Anomaly Detection Solution for Azure IoT, presented at Microsoft Build in Seattle. The two companies collaborate on bringing Artificial Intelligence (AI) and Machine Learning (ML) capabilities for anomaly detection to Azure IoT users by putting together NXP’s offline machine learning capability and embedded processing know-how and Microsoft’s cloud expertise.
Detecting anomalies
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 Forest and 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.
“Preventing failures and reducing downtime are key to enhance productivity and system safety,” said Denis Cabrol, executive director and general manager of IoT and Security Solutions at NXP. “We partnered with Microsoft to combine the power of Azure IoT with local intelligence running on NXP’s embedded technology to unlock innovation for the IoT– as part of our continued efforts to bring cognitive services down to the silicon.”
“We are proud to expand our collaboration with NXP to include the new Azure IoT and i.MX RT106C Anomaly Detection Solution,” said Rodney Clark, Vice President, IoT Sales, Microsoft. “Solutions like this from NXP empower developers with products, tools and services to accelerate development of complete edge to cloud solutions.”
Seamless connection to Azure IoT Cloud
NXP’s anomaly detection solution is designed with a robust set of sensors and high-performance i.MX RT106C crossover microcontroller (MCU) running up to 600MHz, capable of collecting and analyzing sensor data in real time locally at the edge. 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/
