Mtell

Founded in 2006 by Paul Rahilly, Mtell was a San Diego-based company that developed software for managing the health of industrial equipment. The firm established itself as a key player in the industrial internet sector by creating machine learning technologies for predictive and prescriptive maintenance. Its core business focused on providing solutions that helped companies in asset-intensive industries—such as energy, chemicals, mining, and pharmaceuticals—to prevent equipment failures, thereby increasing asset use and avoiding unplanned downtime.

Mtell's flagship product, Previse, was an end-to-end machine learning solution that monitored equipment around the clock. It worked by analyzing real-time and historical data to detect the earliest signs of equipment degradation, diagnose the root cause of potential issues, and then prescribe the necessary actions to prevent a breakdown. The software was designed to be low-touch and rapidly deployable, capable of identifying normal and abnormal operational behaviors within weeks. A key feature was its use of autonomous 'Agents' that learned from equipment behavior and could share these findings across a network of similar assets to enhance overall process performance. This system integrated with existing enterprise asset management (EAM) systems to automatically dispatch work orders.

The company's offerings also included Basis, a condition monitoring application for collaboration between operations and maintenance teams, and Reservoir, a scalable big data repository for managing time series, event, and asset data. In October 2016, Aspen Technology acquired Mtelligence Corporation (known as Mtell) for $37 million. This acquisition was a strategic move for AspenTech to integrate Mtell's predictive and prescriptive maintenance capabilities into its aspenONE® suite, strengthening its asset optimization strategy. Paul Rahilly, Mtell's founder and CEO at the time, expressed excitement about combining their machine learning expertise with AspenTech's broader technological and market reach.

Keywords: predictive maintenance, prescriptive maintenance, machine learning, asset performance management, industrial internet, equipment failure prediction, condition monitoring, unplanned downtime, industrial AI, asset optimization, root cause analysis, maintenance software, process manufacturing, energy sector, chemical industry, mining technology, pharmaceutical manufacturing, AspenTech, operational efficiency, big data repository