Tag Archives: Aspen Mtell

AspenTech Mtell Agents getting ahead of the mine maintenance game

AspenTech is looking to turn condition monitoring procedures in the minerals processing plant on their head by providing prescriptive maintenance tools powered by machine learning that offer the earliest possible issue detection along with the required context to allow operators to act.

“After more than a decade of working on Mtell, we understand how to slot into an operation to make sure our data is clear, prescriptive and acted on,” Mike Brooks, Global Director of APM Solutions at AspenTech told IM recently.

Aspen Mtell® has been a gamechanger for industries such as metals and mining, according to the company, performing prescriptive maintenance by forecasting degradation and equipment failures, alerting staff in advance of when a failure could occur, identifying potential causes and the scope of any failure, and providing advice on the corrective action to avoid or mitigate the impending failure.

This is leading to increased operational efficiency, resulting in improved energy efficiency and reduced emissions, according to the company.

Unlike other mining-related predictive maintenance proponents, AspenTech and Aspen Mtell have been using machine learning for over a decade, using the benefits of this technology to improve on the condition monitoring and firefighting maintenance procedures in place at industrial sites.

“By obtaining sufficient domain knowledge and packaging it into a solution, we have created a product that is able to detect patterns in the data, track any anomalies and contextualise these anomalies on the basis of past performance and previous incidents,” Brooks explained.

This process involves detecting failures, “hidden failures” (spikes or changes in behaviour not associated with an event) and when an asset is offline from past operating data and contextualising this within what is considered ‘normal’ operating conditions. From this, data analysts create “Failure Agents” and “Anomaly Agents” to spot potential failures and watch for changes in normal operating behaviour.

Once these Agents have been trained from historical data, they are deployed to monitor live equipment feeds with all deviations labelled as anomalies and detected by the appropriate Agent.

If an anomaly does not match the signature of a deployed Failure Agent, the anomaly triggers an alert requesting an inspection to determine the cause. The results of the inspection will categorise the anomaly as either a new variation of “normal” or a new never-before-seen failure pattern.

If it is the former, the Anomaly Agent will be updated with this new information to make sure no future false alerts with the same signature occur. If categorised as a new failure, a new Failure Agent will be deployed to allow for earlier detection in the future.

The more operating data the Aspen Mtell platform ingests, the more accurate the alert system becomes and the more context the solution can provide operators. Brooks said around a year’s worth of data often proves enough to know what ‘normal’ looks like while ensuring false alerts are kept to a minimum.

In some instances, Aspen Mtell has managed to get ahead of a potential failure on certain components by 4-6 months, allowing maintenance personnel to strategically schedule maintenance procedures and reduce unplanned downtime, according to Brooks.

“Not only are we able to identify the root cause and failure mode with alerts, but we can also often provide details of exactly what is needed to fix it based on past experience,” he said. Such information is particularly useful in an industry like mining, which has an ageing employee demographic that will, in the future, need to be replaced with a new generation of personnel.

“This is all part of our vision of the ‘Self-Optimizing Plant’,” Brooks said.

The Self-Optimizing Plant, as AspenTech puts it, is a self-adapting, self-learning and self-sustaining set of software technologies that work together to anticipate future conditions and act accordingly, adjusting operations within the context of the enterprise. The plant does this through pervasive real-time access to data and information, combining engineering fundamentals and artificial intelligence, and capturing and using knowledge to optimise across multiple levels, provide recommendations and automate actions securely in a closed feedback loop.

While the mining industry is still some way off adopting such a vision, AspenTech is getting nearer to convincing the sector of its potential future worth.

Brooks provided an example from a mining company with a worldwide presence that was having difficulty with frequent production interruptions caused by unexpected equipment failures as a case in point.

This company decided to deploy Aspen Mtell across a whole site to improve the reliability and availability of equipment, boost production yields and reduce maintenance costs.

On the secondary cone crusher at the operation in question, the Aspen Mtell application gave an extreme early warning and exposed a multi-dimensional pattern showing fast incremental changes, according to AspenTech. This provided the technicians with the required insights to detect the degradation issue and take the appropriate action, avoiding operational complications that can result in production and maintenance costs in the order of $100,000-500,000 per incident.

Similarly, Aspen Mtell was able to deliver a very early lead time and warnings of a bearing issues on the cone crusher, well in advance of the vibration detection system, allowing early action to service a minor issue before a catastrophic failure. This resulted in savings of around $75,000, according to AspenTech.

Equally, monitoring and catching potential bearing problems on conveyors allowed early replacement without the extended shutdowns associated with unplanned maintenance. Such avoidance is generally worth around $1-$1.5 million in operational costs, AspenTech says.

“The net results were that the company was able to better plan and schedule service and repairs on the mobile heavy haul trucks and the static ore processing, improving operators’ safety, extending component lifetimes, and increasing equipment availability besides improving on spare part/resource planning,” it said.

“The positive results encouraged the company to expand the Aspen Mtell application to other mining sites.”

Brooks says this specific company is one of a handful of miners realising the benefits of Aspen Mtell, with the mining sector fast becoming one of AspenTech’s key growth markets behind oil & gas.

And, with AspenTech having just completed the acquisition of Emerson’s OSI Inc and Geological Simulation Software business, there could be many more mining-related opportunities on the horizon.

Aspen Tech and Wood to offer clients predictive, prescriptive maintenance solutions

Aspen Technology and Wood have announced a new partnership that will offer Wood’s clients Aspen Mtell® asset performance management (APM) technology for predictive and prescriptive maintenance.

The partnership will enable global enterprises to improve the performance of their manufacturing and facility assets through a maintenance solution built upon industrial artificial intelligence (AI) and machine learning, the companies said.

Aspen Mtell analyses historical and real-time operational and maintenance data to discover the precise failure signatures that precede asset degradation and breakdowns, predict future failures, and prescribe detailed actions to mitigate problems, they explained.

Wood has decades of experience providing solution-independent asset performance consulting, as well as integrating and deploying specialty engineering services and real-time performance monitoring systems, some of which has been mining-related.

“The combination of this deep domain expertise of asset and operator challenges, with AspenTech’s extensive knowledge of the process manufacturing industry and proven AI-driven predictive and prescriptive maintenance solutions, provides a unique customised asset performance management solution for operators’ needs,” the two companies said.

Prabu Parthasarathy, Vice President of Intelligent Operations at Wood, said: “Wood has an extensive understanding of the performance optimisation needs of our clients and realised a unique opportunity to provide a solution to help enhance asset productivity and identify potential issues well ahead of time.”

Darren Martin, CTO at Wood, added: “We are excited to bring AspenTech into our strategic partnership ecosystem to unlock innovative technology solutions to solve our clients’ challenges. Aspen Mtell is part of our connected operations and maintenance programs that will allow our clients to detect patterns in operating data, allowing them to take prescriptive action and avoid unplanned downtime. Together, our vision is to drive value through digital twins across the full asset lifecycle, working to optimise asset performance, monitoring, and control across any environment.”

Greg Mason, Senior Vice President and General Manager of APM, Aspen Technology, said the value of predictive and prescriptive maintenance represents much more than simply predicting failures on large rotating assets.

“Companies that are truly focused on eliminating safety and environmental incidents tied to machine failure, in addition to avoiding production losses, understand the need to have a comprehensive predictive maintenance culture throughout the entire plant,” he said. “This requires an analytics technology that is scalable, resources needed to deploy to scale, and the expertise to lead change management. I’m pleased to say that the partnership of AspenTech and Wood around the Aspen Mtell solution provide these three unique capabilities needed to bring contextualised AI for the process industries to scale.”