“It takes a courageous fool to say things that have not been said and to do things that have not been done.” ― Criss Jami, Venus in Arms

The core of the Mtell solution is machine learning-based condition monitoring; the fastest and most accurate available today. Mtell makes machines smart so they use knowledge of previous conditions, combined with actual internal and external measurements, to determine their health and predict failures. The predictive monitoring part of the Mtell Suite sits under Condition Based Monitoring (CBM), which is just beneath Asset Health Monitoring (AHM).

AHM is the superset of all activities used to monitor, manage, inspect, maintain, and renew physical assets. These maintenance functions determine operational performance and profitability of industries where operating assets are fundamental to the core of the business. The main goal of AHM is to achieve optimal availability at minimum cost, while assuring lifetime asset integrity. However, how many of those maintenance products in the acronym soup can actually do it?

In addition to providing superior condition monitoring and failure predictions, Mtell also performs Predictive-Scheduling (PS), where smart machines order maintenance directly with your existing EAM system. Our machine learning is then able to detect anomalies and patterns in operations that have gone unrecognized. The user simply indicates if the anomaly is a new operating condition, or an impending failure. Machine learning has the ability to retrain itself, so that whenever either condition reoccurs, it will be acknowledged and dealt with by alerting users and ordering preemptive maintenance automatically.

When an Mtell smart machine detects an early failure pattern, it has the ability to predict the time-to-failure (TTF), and it knows the full work-scope necessary for maintenance. This process is determined by learned failure codes from that particular EAM system. Mtell smart machines recognize when the process is degrading, and identify specific failures well before equipment damage occurs. In fact, the Mtell Predictive Scheduling enables our customers to move from random disruptive failures with costly emergency maintenance and repairs, to well understood failure patterns with early warnings in precise alerts. The Predictive Scheduling also provides detailed maintenance requests and TTF information.

Consequently, Mtell smart machines can actually avoid failure by requesting maintenance at the first onset of an issue, even when the corrective action is very simple, such as changing the lube oil or a filter. These maintenance requests are not derived from assertions, they are based on real data updating continuously in real-time.

Based on intelligently processing all data contained within the EAM system, the Mtell Suite provides full optimization of all maintenance processes leading to the best performing assets. Combined with your existing EAM system, the Mtell Suite provides a complete Asset Health Management solution.