January 2021

NEWS n 5 Amazon wants to use machine learning to monitor your plant AMAZONHAS ANNOUNCED five machine-learning technologies and services that will help manufacturers to embed intelligence into their production processes to improve efficiency, quality control, security and safety. The services combine machine learning, sensor analysis, and computer vision, and are claimed to be the most comprehensive suite of cloud-to-edge industrial machine-learning services available. The five services are: n AmazonMonitron , which provides end-to-end machine monitoring using sensors, gateways and machine learning to detect abnormal equipment conditions; n Amazon Lookout for Equipment , which uses machine- learning models combined with existing sensors to detect abnormal behaviour and to enable predictive maintenance; n Amazon Lookout for Vision , which applies AWS-trained computer vision models to images and video streams to find anomalies and flaws in products or processes; n the AWS Panorama Appliance , which allows industrial users with existing cameras to implement computer vision functions to improve quality control and safety; and n the AWS Panorama Software Development Kit (SDK) , which allows industrial camera manufacturers to embed computer vision capabilities into new cameras “Industrial and manufacturing customers are constantly under pressure from their shareholders, customers, governments, and competitors to reduce costs, improve quality, and maintain compliance,”says Swami Sivasubramanian, vice- president of Amazon Machine Learning.“These organisations would like to use the cloud and machine learning to help them automate processes and augment human capabilities across their operations, but building these systems can be error-prone, complex, time-consuming, and expensive. “We’re excited to bring customers five newmachine-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,”he adds. The Monitron monitoring device detects anomalies and predicts when equipment will need maintenance at sites with no existing sensor networks. It allows users to cut costs when building machine-learning-driven predictive maintenance systems, and to focus on their manufacturing, supply chain, and operations functions. The device detects when machines are not operating normally, based on variations in vibration or temperature, and tells users when to examine machinery to determine if maintenance is needed. It combines IoT sensors, a gateway to aggregate and transfer data to AWS, and a machine-learning cloud service that can detect abnormal equipment patterns and deliver results“in minutes” with no machine learning or cloud experience required. Maintenance technicians can start to track machine health“within hours”, without needing any development work or specialised training, says AWS. The Monitron devices can be used on a rotating equipment such as motors, pumps, as well as on conveyor belts. They can monitor a few critical machines such as cooling fans or water pumps, or large-scale industrial installations. The service also includes a mobile app for maintenance technicians to monitor equipment behaviour in real time. They receive alerts of any abnormal equipment conditions from each machine, check up on the health of the machines, and decide if they need to schedule maintenance. The system accepts feedback to improve over time. For users that have existing sensors but don’t want to build machine- learning models, Amazon Lookout for Equipment sends their data to AWS to build models for them and return predictions of abnormal equipment behaviour. The service analyses the sensor data, assesses normal or healthy patterns, and then builds a model customised for each application. It uses the machine- learning model to analyse incoming sensor data and identify early signs of possible machine failures. Amazon Lookout for Vision offers an accurate, low-cost way of using machine learning to process thousands of images an hour to spot defects and anomalies. Users send images to the service in batches or in real time, and it identifies anomalies, such as cracks in machine parts, irregular shapes or incorrect colours. The service is already available and, starting this year, users will be able to run it on AWS Panorama appliances in locations where Internet connections are limited or non-existent. The Panorama devices allow users to add computer vision functions to existing cameras. They connect the device to the network which interacts with the cameras automatically. The appliance is integrated with AWS machine-learning and IoT services that can build custommachine-learning models or analyse video streams. Each appliance can run computer vision models on multiple camera streams in parallel for applications such as quality control, part identification and safety. Finally, the AWS Panorama Software Development Kit (SDK) allows hardware vendors to build cameras that run computer vision models at the edge. For example, the cameras can detect damaged parts on conveyor belts or spot if machinery is outside of a designated zone. Among the first organisations planning to use or offer the AWS industrial services are BP, Fender Musical Instruments, OSIsoft, GE Healthcare and Siemens Mobility. The Taiwanese industrial computing and vision specialist Adlink is planning to add AWS Panorama to its industrial vision systems to offer “truly plug-and-play computer vision at the edge”. RS Components is planning to sell the Monitron devices and to use them to deliver condition-based monitoring via its RS Monition reliability services business. This will be the company’s first end-to-end wireless vibration and temperature condition-monitoring system. “With the emergence of IoT, we have seen our customers looking to bring real-time condition monitoring capabilities into the factory environment to reduce reactive maintenance and improve asset reliability,”says RS technical director, Richard Jeffers. He adds that Amazon Monitron will allow users to deploy cost-effective, easy-to-use, continuously improving condition monitoring and to enable predictive maintenance across a wider range of equipment. https://aws.amazon.com/industrial www.drivesncontrols.com January 2021 Amazon will be offering starter kits containing several of its Monitron machine-monitoring devices