Amazon Web Services is rolling out a series of new tools within its industrial Internet of things lineup that aim to improve machine performance and uptime.
First up the company announced Amazon Monitron, a condition monitoring service for customers that currently lack an existing sensor network. The system and its array of sensors can detect potential failures on critical equipment, allowing for the implementation of a predictive maintenance program.
For those customers that do have an existing sensor network, AWS introduced an API-based machine learning (ML) service called Amazon Lookout for Equipment that functions as a pathway to send sensor data to AWS for predictive modeling. Like Monitron, Lookout for Equipment analyzes sensor data to detect abnormal behavior on industrial machines.
The service pulls together historical time series data and past maintenance events on industrial equipment, automatically tests possible combinations, and builds an optimal machine learning model to learn the normal behavior of the equipment. From there, customers can perform ML inference to detect abnormal behavior of the equipment, and the results can be integrated into existing monitoring software for visualization or alerts.
Additional IIoT products from AWS include AWS Panorama, a new hardware appliance that lets companies add computer vision to existing on-premises cameras and extend AWS computer vision to the edge. Once connected to a network, the AWS Panorama appliance automatically identifies camera streams and runs computer vision models on them.
Meantime, the AWS Panorama SDK is meant to help hardware vendors build cameras that are capable of running computer vision models at the edge.
Amazon also introduced Amazon Lookout for Vision, new detection software that uses machine learning to process thousands of images an hour to spot defects and anomalies.
"Industrial and manufacturing customers are constantly under pressure from their shareholders, customers, governments, and competitors to reduce costs, improve quality, and maintain compliance," said Swami Sivasubramanian, VP of Amazon Machine Learning for AWS. "We're excited to bring customers five new machine learning services purpose-built for industrial use that are easy to install, deploy, and get up and running quickly and that connect the cloud to the edge to help deliver the smart factories of the future for our industrial customers."