Smart, data-enabled operations are now a reality for the world's leading metals and mining firms.
Senseye analysis shows that most of the sector's leading firms are trialing AI-driven decisioning systems (80%) and predictive maintenance processes (58%) to reduce downtime, drive down maintenance costs and boost overall equipment effectiveness (OEE).
The research found that 32% of the world’s 50 largest metals and mining companies (and six of the top 10) are currently rolling out automated predictive maintenance technologies, at scale. An ever greater number, 46%, are deploying AI systems to multiple areas of their operations.
Why are the world’s metals and mining companies investing in these capabilities at scale?
- Improved operational efficiency. Collectively, the top 50 firms spent an estimated $62.5 billion on plant and equipment maintenance in their last reported financial years. These costs typically reflect up to 3% of a business's total avenue revenue. Collecting and analyzing critical asset condition data leads to more successful early interventions and ensures fewer assets run to fail - saving on equipment costs and boosting OEE.
- Reduced asset downtime. Research shows heavy industrial companies lose $225 billion collectively per year due to unplanned downtime. A predictive approach to maintenance automates the analysis of machine health, identifies early warning signs of deterioration and directs engineers to where they're needed most.
These are just two examples showing the value of reaching the top of Senseye's three-tiered 'Digitisation Pyramid', a structure it built to demonstrate Industry 4.0 progress.
Senseye also found that the top 50 metals and mining firms spent $62.5 billion on plant and equipment maintenance in the last year, with these costs typically representing up to three per cent of annual revenues. Senseye’s analysis indicates the opportunity to save up to $25 billion a year through maintenance efficiencies enabled by predictive maintenance practices.
Level 1: Laying the foundation
Businesses at this level are concentrating on collecting, managing, and storing plant and asset data from their daily operations.
A key trend is an increase in the sensor-based collection condition monitoring data. Cost-effective solutions that allow condition data collection make it easier to acquire operational information from even legacy assets.
Connecting these assets affordably and at scale has created a path for advanced analytics, process control systems and automated predictive maintenance practices to achieve mainstream adoption.
Level 2: Trialling innovative technologies
Businesses at this level are putting their data to use in trials of innovative IoT technologies. By analyzing condition monitoring data, 58% of firms are testing smart PdM systems to reduce downtime, cut maintenance costs and boost OEE.
PdM systems are crucial for enabling widespread preventative maintenance strategies. It provides analysis of condition data at massive scale, detects subtle trends in data, and allows engineering teams more time to proactively address asset faults.
Level 3: Transformation at scale
Firms at the top level have seen the benefits of their trials and are now rolling out these technologies to more business areas.
Scalability means expanding the coverage of an organization's assets while reducing the risk across the monitored equipment. The premise of scalability is that it's possible to monitor much more than just top-priority and critical assets using the staff already in place.[Text Wrapping Break]
By automating a majority of the analytical tasks that engineers perform, companies can address changes in the levels of critical assets within their organization without increasing their labor costs.
Senseye: Connecting assets at scale
With smart PdM reaching mainstream adoption, many metals and mining organizations are introducing these advanced technologies at scale. Senseye’s analysis shows that more than half (58%) of firms that introduced pilot PdM projects have already deployed this capability to other business areas.
The critical factor in successful scalability is ensuring that any solution is generic enough to be scaled across different types of machines and smart enough to then learn each monitored asset's unique characteristics. Automating the analytical tasks that engineers perform daily allows organizations to monitor many more assets and focus on the proactive maintenance of equipment.
To download a copy of Senseye’s Connecting Asset Data at Scale report, please click on the image below.