Skip to main content

Mtell receives Frost & Sullivan award for machine learning analytics platform

Published by
Hydrocarbon Engineering,

Based on its recent analysis of the big data and analytics market in the oil and gas industry, Frost & Sullivan has recognised Mtell with the 2015 American Frost & Sullivan Award for Customer Value Leadership. Mtell’s advanced machine learning platform facilitates the precise, timely, and prognostic assessment of a machine's operational condition. The platform boasts leading edge prescriptive analysis capabilities that guarantee early detection of degradation.

Mtell's scalable, machine learning platform uses real time sensor data and combines anomaly detection and precise pattern recognition techniques to deliver accurate alerts on the impending failure of a machine. By focusing on degradation detection rather than failure detection, Mtell's machine learning platform addresses customers' specific pain points, such as environmental damage, personnel safety, loss of productivity due to machine downtime, or any other related compliance issues.

"Mtell has further improved its technology to enable individual machines to learn from their surroundings and transfer knowledge to other machines. The key differentiator here is its ability to detect small faults and minor degradations before they become major catastrophes," said Frost & Sullivan Senior Research AnalystRahul Vijayaraghavan. "This not only significantly boosts the operational efficiency levels of customers' assets, but also saves cost and time by increasing equipment uptime."

The smart machine learning based solution incorporates artificial software agents that are easier to implement and produce the best results among similar products. The customer can create multiple agents on a single asset to extract precise data patterns. The agents detect minute by minute changes in any machine and correlate everything to detect a failure in advance, thus providing customers with ample time (often more than 30 days) to plan their maintenance efforts.

In addition, the solution's seamless integration with other enterprise asset management (EAM) systems to automatically issue work orders is a huge advantage to customers that need a cost effective, centralised asset health decision support platform. Other attractive features of Mtell's advanced machine learning platform include its rapid deployment, ease of use, and limited human involvement post implementation. As the platform is self sufficient, self learning, and self improving, there is limited requirement for expensive maintenance methodologists or data scientists.

"While the platform can analyse and cleanse data as well as provide training for agents through wizards, users can step in and obtain metrics on several perspectives of an asset's condition and even tweak certain values to get a larger percentage of a result, based on their specific requirements," observed Rahul. "Moreover, Mtell's centralised control over asset performance allows customers to easily scale up production."

The platform can be sold to a wide variety of customers, including owner operators in asset intensive businesses, companies that provide remote monitoring and maintenance services, and original equipment manufacturers that supply software and services along with their equipment. These strategic collaborations and partnerships with key value chain participants ensure that end users do not have to rely heavily on Mtell for implementation services, adding value to the overall customer experience.

Adapted from press release by Rosalie Starling

Read the article online at:


Embed article link: (copy the HTML code below):