With the incorporation of Industry 4.0 technologies such as predictive and prescriptive analytics, asset performance management can revolutionize machinery lifecycle management.

As industry 4.0 brings new technologies and a transformative approach to industrial productivity, the global asset performance management (APM) market is set to grow from US$2.5bn in 2021 to US$4bn by 2026.

APM has been evolving along with industry, but APM 4.0 is a step change in the way a firm conducts maintenance. Using cyber-physical systems to fundamentally change the way a firm works, APM 4.0 enables proactive asset performance management through predictive alerts and prescriptive analytics that make the most of AI, machine learning (ML) and big data analytics technologies.

Traditional APM focused on reliability engineering methods, but APM 4.0 integrates IT with operational technology (OT) and connects the asset to the person in the different stages of the asset lifecycle through various layers of technology.

Digital transformation of APM

The approach of APM has been transformed from being asset-orientated approach to being a system that holistically connects engineering, operations and performance, creating a single integrated digital thread across the whole asset lifecycle, and laying the groundwork for predictive alerts and prescriptive analytics.

Firms will be able to implement strategies to avoid unplanned downtime while also deciding what preventative or corrective strategy is best for less vital machinery. This will lower costs, reduce unplanned downtime, and optimize labor and equipment usage.

An essential part of APM 4.0 is data-driven decision making, which creates performance indicators that are truly leading in that they can be used to guide adjustments and improve performance in real time, and in certain situations prevent a fault from ever occurring.

This is because a variety of sensors and mobile devices can be used to provide decision makers with real-time data on the condition, performance, and safety of assets. In stark contrast to the widely used, and typically lagging indicators that report failures onlyafter they occur, AI and ML algorithms use sensor data to predict—with more than 95% accuracy—performance degradation and component failure before it happens.

This information is used to set alerts with specific, predefined prescriptive actions that enable maintenance engineers to prevent malfunctions and minimize potential damage.

Prescriptive analytics and actions

In addition to telling asset operators what is likely to happen, APM 4.0 solutions also analyze the best response using big data analytics and ML.

Each triggered alert is linked to prescriptive actions that consist of four attributes: criticality, urgency, action and spare parts management, and provide guidance as to what actions should be taken to ensure asset reliability.

This rule-based logic can also be used to help optimize maintenance and performance via the access to, and analysis of, real-time data.

APM 4.0 business benefits

This latest incarnation of asset performance management has seen early adopters achieve a 25% reduction in unplanned downtime, a 20% increase in asset availability and up to a 30% improvement in asset utilization.

For example, APM 4.0 helped US-based Duke Energy to avoid catastrophic failures that would have cost over US$10m in damages. In another instance, one of the USA’s largest coal, gas and nuclear power utilities deployed more than 10,000 predictive models to monitor its critical equipment: just a single early warning catch of a hairline fracture in a turbine blade was estimated to save the organization US$7.5m.

Over in the petrochemicals sector, Thailand’s SCG Chemicals used APM 4.0 to raise plant reliability from 98% to 100% for significant cost-savings.

Elsewhere, a firm that wanted to transform its 1950s-era plant into a modern manufacturing facility capable of leveraging industrial data to help prevent shutdowns, used APM 4.0 to eliminate manual input of data and visualize the overall manufacturing process across teams.

This helped to improve communication and knowledge sharing and achieve potential savings of over US$2m in averting plant closures.