Back To Top
Aspen Mtell Aspen Mtell

Enhance asset reliability and performance with early warnings and real-time actionable insights, paving the way to operational excellence.

Using predictive maintenance technology, Aspen Mtell delivers the earliest, most accurate warning of equipment failures. It also uses machine learning to recognize precise patterns in operating data that indicate degradation and impending failure—well before it happens. Aspen Mtell is proven across many industries, including energy, chemicals, mining, pharmaceuticals, pulp & paper, power and others.

Aspentech's software offerings provide a streamlined, cost-effective, and customizable way to get started, with gradual implementation options tailored to meet specific business needs. These solutions are system-agnostic, integrating easily through industry standards, ensuring connectivity across Emerson platforms and other systems in diverse industrial environments.

Unlock the Full Potential of Your Assets

  • Use convenient dashboards to gain insights into plant and business performance, empowering informed decision-making.
  • Benefits from a consolidated alert management dashboard, offering prioritization, context, and recommended actions for effective response.
  • Leverage templated with embedded KPIs tailored to common asset categories or employ AI for agent creation and deployment.
  • Access a ready-to-use FMEA library to seamlessly associate alerts with prescriptive actions.

Monitor Asset Performance and Enhance Reliability

Ensure safe operations by deploying agents that monitor asset health and performance and predict potential failures using rules and conditions, advanced first principles or AI/ML models, and custom codes created by data scientists.

Reduce Maintenance and Operational Costs

Boost operational efficiency by implementing recommended actions to mitigate alerts, reducing unplanned maintenance, optimizing spare parts management and increasing productivity. 

Improve Efficiency, Meet Sustainability Metrics

Maximize asset performance, achieve waste reduction, enhance worker safety and align with ESG goals by harnessing operational visibility and actionable insights.

Integrate Seamlessly with AspenTech Solutions

Elevate user experience and lower total cost of ownership by readily integrating with AspenTech Inmation™, Aspen Fidelis™, Aspen HYSYS® and more.

Challenge: Scalability and Limited Foresight of Most Solutions

In its infancy, predictive maintenance suppliers focused on proving their technology’s ability to accurately predict asset failures. Now, in the next stage of technology maturity, prediction accuracy has become table stakes. The conversation today is focused on scalability.


With some approaches taking weeks to months to develop the predictive models for a single asset, scalability becomes critical. Assuming that prediction accuracy and lead times are base requirements, the financial success of predictive maintenance becomes a matter of how to roll out across hundreds or thousands of assets and potentially dozens of plants.

Aspen Mtell is unique in its scalability, as it can be deployed costeffectively on primary and secondary assets. By focusing beyond the most important assets, small problems can be identified and mitigated before they become large problems—and near misses can be avoided. With Aspen Mtell’s broader coverage across the base of assets comes better protection against the events that drive most plant accidents and emissions exceedances—shutdowns and startups.

Solution: Aspen Maestro for Mtell

Aspen Maestro is a breakthrough collection of features within Aspen Mtell, which can assist users in building prediction Agents. Aspen Maestro tackles the three biggest barriers in successful model building: data selection, data cleaning and creating context by incorporating domain expertise.

Build Better Agents Faster

Data analysis can get bogged down in identifying, selecting and preparing data. Typically, these tasks can consume 50% or more of the time spent doing analysis. Aspen Maestro for Mtell streamlines and automates much of that data preparation. Through automated workflows, time and effort is minimized while reducing the skills and experience required
by the end users. Aspen Maestro also tackles the selection of the hyperparameters that control the machine learning algorithm.

Aspen Mtell uses analysis to determine the most important sensors and identify a minimal set of inputs that result in a good Agent. In training Agents, the historical data must be segmented and Aspen Maestro automates that workflow.

Automate Feature Selection

Aspen Maestro also automates feature selection. In data modeling it often helps to use the data to enforce or identify key engineering principles and relationships. For example, if the difference in pressure between two points in the process is a key concept, you can create a pseudo variable for ΔP and use that in lieu of the two individual pressure readings. Aspen Maestro automatically identifies significant features.
 

Leverage Domain Expertise

Aspen Maestro allows users to incorporate domain knowledge. If there are key engineering equations pertinent to the analysis, they can be incorporated into the Agent. This is also a key capability that enables you to leverage your know-how and, importantly, leverage the know-how of other experts.

How it works

Because it is both equipment- and process-agnostic, Aspen Mtell can integrate and interoperate with almost all equipment and systems found in manufacturing including programmable logic controllers, distributed control systems, instrument systems, plant historians, management information systems, EAM systems, business systems and more to correlate patterns of failure that occurred in the past, before Aspen Mtell was installed. 

The Aspen Mtell application collects equipment metadata from the EAM system to build the appropriate equipment hierarchy for monitoring, including mapping the sensor tag names to the correct equipment. Once set up, the system analyzes equipment work orders from the EAM system to correlate patterns of failure that occurred in the past, before Aspen Mtell was installed. Software Agents use the work order information to develop signatures of normal and failure modes, which are deployed immediately to monitor for the recurrence of those patterns, protecting against similar failures and detecting new anomalies that are readily categorized as either new normal conditions or new failure signatures. Unlike other systems, Aspen Mtell uses low-touch machine learning and adapts to new operating modes, enabling it to easily recognize new failure conditions.

Aspen Mtell’s Failure Agents initiate alerts to users, sending failure work orders with the exact failure code into the EAM system using machine-to-machine (M2M/Industrial IoT) technology. In this prescriptive maintenance process, the Agent prescribes appropriate maintenance activity based on the machine’s behavior. The operations and maintenance departments have an extended warning of the potential for failure and can work together with the other affected departments to make better decisions to remediate the failure in the most cost-effective way or adjust production. An Aspen Mtell notification allows small problems to be fixed before they become big ones.

Key Features

 

Aspen Mtell recognizes leading indicators of potential asset failure and alerts plant staff weeks (or even months) prior to breakdown. Advance warning gives staff time to plan maintenance and reschedule production to minimize unplanned downtime and financial impact.

With Aspen Mtell you can accurately predict precisely when a known failure will occur, how the failure will occur and what to do about it. Aspen Mtell is derived from prescriptive advice such as the exact Failure Code directly linked from the EAM system.

Two additional features: Aspen Mtell does not require detailed models of the assets and the solution can be configured by your team, without a cadre of data scientists. 

A Wider Window of Warning 
Unplanned downtime prevention and mitigation requires organizational alignment. The early warning provided by Aspen Mtell’s predictive maintenance technology gives users time to alert and align stakeholders to the issue. With a wider window of warning, it’s possible to
plan any needed maintenance in a way that considers Operations, Maintenance, Technical and Planning/Scheduling Departments and HS&E. The additional time and information enable effective collaboration for better remediation and timing decisions.

Case Studies & Resources

About AspenTech

Aspen Technology, Inc. (NASDAQ: AZPN) is a global software leader helping industries at the forefront of the world’s dual challenge meet the increasing demand for resources from a rapidly growing population in a profitable and sustainable manner. AspenTech solutions address complex environments where it is critical to optimize the asset design, operation and maintenance lifecycle. Through our unique combination of deep domain expertise and innovation, customers in capital-intensive industries can run their assets safer, greener, longer and faster to improve their operational excellence.

LEARN MORE : aspentech.com
Get in touch with an expert, find your nearest office location, or send us a note about your next project!!
TALK TO ONE OF OUR EXPERTS IN THIS FIELD
1-800-265-1005
+
Talk to an expert