Machine learning can drive productivity improvements
John Hague, senior vice president and general manager of asset performance management at AspenTech, believes that low-touch machine learning is now driving the value of asset performance management.
Today a range of new methodologies and cutting-edge technologies are driving asset performance management (APM) beyond its historical capabilities. However, it is low-touch machine learning, a disruptive technology that deploys precise failure pattern recognition with high accuracies and months of advanced notice on failures, that is helping scale APM’s potential and increasing its bottom-line value.
The widespread integration of machine learning in APM marks a transition from estimated engineering and statistical models towards measuring asset behaviour patterns.
Manufacturing facilities staff can are now extract value from existing design and operations data to optimise asset performance. Deployed coherently, with appropriate automation, this low touch machine learning enables greater agility to incorporate current, historical and projected conditions from process sensors and mechanical and process events. Systems become more agile – flexible models emerge that adapt to real data conditions – and incorporate the nuances of asset behaviour.
It is possible to perform active, accurate management of individual processes and mechanical assets and it can also applied to combinations of assets — plant-wide, system-wide or across multiple locations, ushering in a new era of predictive maintenance.
There are five machine learning best practices that drive state-of-the-art reliability management, across multiple process industries.
Data collection and preparation: Over the last two decades, every attempt at massive data analysis from diverse sources of plant data collected from sensors has run into issues around collection, timeliness, validation, cleansing, normalisation, synchronisation and structure issues. Data preparation can consume up to 80% of the time to execute and repeat data mining and analysis. However, it is an essential process to appropriate and accurate data. Advances in APM have now automated most of the data preparation process which reveals new opportunities with minimal preparation.
Condition-based monitoring: Once data is trustworthy, condition-based monitoring (CBM) can be applied. Plant conditions will vary constantly, according to mechanical performance of assets, feedstock variations in quality, weather conditions and production timeline and demand changes. Static models cannot work under such duress. In addition, focusing CBM on mechanical equipment behaviour reveals only a small fraction of the true issues causing degradation and failure.
APM can now deliver comprehensive monitoring of the mechanical and upstream and downstream process conditions that can lead to failure.
Work management history: The history of work provides the breadcrumb trail of past solutions to failure prevention and/or remediation. Problem identification, coding and a standard approach of problem resolution provide a baseline for the failure point in an asset lifecycle. OEM data can deliver insight into process issues and outliers specific to the configuration and engineering within the plant process.
Predictive and prescriptive analytics: Using engineering and statistical models to estimate the future readings of sensors, and interpret variances from actual readings, can result in errors and false positives. Top performers use inline, real-time analysis of the patterns of normal and failure behaviours of process equipment and machines.
Predictive analytics can accurately portray asset lifecycle and asset reliability and focus on the root cause of degradation. It provides accurate, critical lead times, allowing time for decisions that can eliminate damage and maintenance or provide preparation time to reduce time-to-repair and mitigate the consequences.
Best-in-class APM provides prescriptive advice based on root cause analysis and presents information on the approach that will proactively avoid process conditions that cause damage. As a result, predictive and prescriptive capabilities enable asset lifecycle reliability and facilitate decisions on when and how to maximise production, while proactively avoiding asset and output risks.
Pool and fleet analytics: The next level of analytics allows patterns discovered on one asset in a pool or fleet to be shared, enabling the same safety and shutdown protection for all equipment. Once deployed, companies can rapidly scale solutions from a unit to multiple sites.
Traditional maintenance practices can now be improved, to recognise issues affecting asset degradation. Operational integrity improves when organisations implement strategies to detect root causes early and avoid unplanned downtime.>
Source: Control Engineering Europe - All Articles