Many industrial companies have installed physical sensors on equipment with the aim of avoiding unplanned downtime due to equipment failure. Generally speaking, the data from these sensors is underutilised, as it is processed using simple rules or models. The result can be false alarms, or warnings that cannot be actioned before failure occurs.

Amazon Lookout for Equipment makes it easy to apply machine learning models for preventative maintenance.

Users upload their sensor data (e.g. pressure, flow rate, RPMs, temperature, and power) to Amazon S3, and point Amazon Lookout for Equipment to the relevant bucket.

The service automatically analyses the data, identifies normal patterns, and builds a machine learning model for the customer's environment.

Amazon Lookout for Equipment then uses that model to analyse incoming sensor data and identify early warning signs of machine failure or malfunction.

For example, if Amazon Lookout for Equipment detected an issue on a pump with 50 sensors, the service could show which five sensors indicate an issue on a specific motor, and relate that issue to the motor power current and temperature.

This, according to AWS, allows customers to identify the issue, diagnose the problem, prioritise needed actions, and perform precision maintenance before issues happen, saving money and improving productivity.

"Many industrial and manufacturing companies have heavily invested in physical sensors and other technology with the aim of improving the maintenance of their equipment. But even with this gear in place, companies are not in a position to deploy machine learning models on top of the reams of data due to a lack of resources and the scarcity of data scientists. As a result, they miss out on critical insights and actionable findings that would help them better manage their operations," said AWS vice president of machine learning Swami Sivasubramanian.

"Today, we're excited to announce the general availability of Amazon Lookout for Equipment, a new service that enables customers to benefit from custom machine learning models that are built for their specific environment to quickly and easily identify abnormal machine behaviour, so that they can take action to avoid the impact and expense of equipment downtime."

Siemens Energy senior vice president for digital solutions Amogh Bhonde said "Siemens Energy works with our customers to improve performance, reliability, and safety through our existing business lines enhanced with digital service solutions. Digitalization is a key driver for a sustainable energy future.

"With Amazon Lookout for Equipment, we see an opportunity to combine AWS machine learning with Siemens Energy subject matter expertise to give improved visibility into the systems and equipment across the entirety of a customer's operation. Amazon Lookout for Equipment's automated machine learning workflow makes it easy to build and deploy models across a variety of assets types with no data science knowledge required."

Amazon Lookout for Equipment is available immediately in AWS's US East (N. Virginia), EU (Ireland), and Asia Pacific (Seoul) regions, with wider availability expected in the coming months.

Image: Mixabest via Wikimedia Commons (CC BY-SA 3.0)