On December 1, 2020, AWS launched a predictive maintenance service for the industrial sector: Amazon Monitron. Predictive maintenance aims to intervene before an error occurs. The advantage therefore lies in the reduction of downtime due to maintenance work.
Amazon Monitron uses machine learning to analyze the data collected by sensors. Machine learning is a branch of artificial intelligence that allows a program to autonomously improve its performance through data analysis. Specifically, the Amazon Monitron service processes data with the aim of detecting abnormal elements in order to avoid possible errors.
In the same category
Sidewalk: Amazon’s new network will be launched before the end of the year
In detail, the Monitron range includes sensors that control the vibrations and temperature of the devices. They work wirelessly and can be installed on motors, gearboxes, fans or even pumps. The data recorded by the sensors is transmitted to the Amazon cloud using Monitron gateways: Amazon Web Services (AWS). These gateways connect to sensors via Bluetooth Low Energy (BLE) and to AWS via WLAN. Once the data has been transferred, machine learning and the visualization of the results follow in the Monitron application, which also sends alerts as soon as an anomaly is detected.
The industrial sector is relatively isolated from innovations coming from the cloud, particularly due to the specific characteristics of each unit of production that require a personalized approach. In addition, factories, power plants, wells, etc. have equipment that requires high investments and is often outdated or unsuitable for cloud technologies. Because of this, the Amazon Monitron installation takes different forms, particularly depending on the equipment present in the structure. To get the service, it is not necessary to equip everything with the sensors offered by AWS. As long as these are interoperable, it is possible to use sensors of another brand.
Andy Jassy, CEO of AWS, also announced the launch of Amazon Lookout for Equipment, a dedicated solution for industrial equipment. He also introduced the AWS Panorama Appliance, which “enables companies to add computer vision to smart cameras,” said Andy Jassy. Finally, he announced the launch of the Panorama SDK, a device for camera manufacturers to use the Panorama model to develop their products.
In short, Amazon is democratizing machine learning technologies for the industrial sector. That offering comes at the right time with the advent of private 5G, which should mark the rise of the Internet of Things in Industry (IIoT).