Cepsa has become a pioneer in Spain and in the world in using Amazon Lookout for Equipment at its facilities, the new Amazon Web Services (AWS) solution, which facilitates large-scale predictive maintenance in industrial facilities and whose general availability was announced yesterday globally by AWS.
This technology uses machine learning models developed by AWS to facilitate predictive maintenance. Amazon Lookout for Equipment receives data from industrial equipment sensors (for example, pressure, flow, RPM, temperature, and power), and then trains a unique machine learning model to accurately predict early warning signs of machine failure or suboptimal performance through real-time data streams from equipment. With this cloud-based technology, Cepsa can quickly and accurately detect equipment anomalies, quickly diagnose problems, reduce false alerts and avoid costly downtime by taking action before equipment failure occurs.
“At Cepsa, digital transformation focuses on people. In this sense, our professionals are the engine of our transformation. With Amazon Lookout for Equipment, we are bringing machine learning insights to the experts who know equipment best—reliability and maintenance engineers—enabling them to make more informed decisions for superior uptime and lower operating costs.” declared Alberto Gascón, head of advanced analytics at Cepsa. “Solutions like predictive maintenance for equipment traditionally involve complex, manual data science like selecting the right algorithms and parameters, but Amazon Lookout for Equipment automates these processes so engineers can focus on solving the most critical challenges that affect to your business."
A news article on How to Erase and Format a USB Drive on Your Mac by @abhijitharjunan on @TechLilaBlog https://t.co/MutUxbMvfN #TechTips
— TechLilac Mon Sep 11 12:55:54 +0000 2017
The first tests of this technology that Cepsa has carried out have been carried out at its La Rábida (Huelva) and Gibraltar-San Roque (Cádiz) refineries with good results. Specifically, they have focused on the detection and prediction of anomalies in rotating equipment, such as pumps or compressors.
Until now, to analyze data from their equipment, most companies have used simple rule- or model-based approaches to identify problems based on past performance. However, the rudimentary nature of these approaches often leads to identifying problems too late to take action, or receiving false alarms based on misdiagnosed problems that require unnecessary and timely inspection. Today, this AWS technology based on machine learning techniques enables companies like Cepsa to quickly identify anomalies and learn unique relationships between historical data from equipment across a facility or across multiple locations.