Many manufacturers today invest in machine health monitoring and predictive analytics tools related to critical assets, and for good reason. As the term suggests, this equipment is essential for core business functions. Broadly speaking, it includes any asset that directly supports safety, regulatory compliance, cost control, or operational throughput.
Machines and tools that are only tangentially linked to these objectives are generally considered supporting assets. Most manufacturers are less concerned with applying predictive maintenance tools to promote machine health for supporting equipment because these assets don’t have the same impact on unplanned downtime or factory safety.
Even so, supporting assets make up about 60% of a typical plant’s rotating assets, and failures associated with this equipment can still disrupt operations and delay production. In the absence of predictive analytics, manufacturers tend to address supporting assets on a preventive maintenance schedule. This approach requires absorbing high labor costs for low-value work and greater spare parts inventory costs because manufacturers have little insight into the actual health of supporting equipment. Recently, labor shortages and persistent supply chain issues have exacerbated these costs and created long lead times for many spares.
Applying Predictive Analytics to SE Diagnostics and Maintenance
By relying on a preventive approach characterized by route- and time-based maintenance, many manufacturing companies spend a significant portion of maintenance and repair (M&R) budgets on supporting assets, often unnecessarily. That’s a considerable problem, as wasteful spending drains essential resources and ultimately reduces a manufacturer’s margin for error in critical asset maintenance. Augury’s Machine Health for Supporting Equipment (MH SE) tool can help manufacturers avoid this scenario.
MH SE includes automated predictive analytics features that use real-time data to alert factory personnel of potential machine health issues. Specific confidence level ratings, which become more accurate over time with machine learning technology, accompany each fault rating. Operators and technicians can use SE diagnostics as a valuable decision-making tool when assessing issues or planning and undertaking maintenance activities.
Machine Health for Supporting Equipment in Action
In the early deployment of MH SE, one client – a leading pet food manufacturer – installed the technology at a large plant that housed the majority of its supporting asset portfolio. Augury’s AI quickly detected vibration anomalies within an oven’s circular fan. The tool’s automated system directly alerted on-site maintenance workers, who acted promptly to address the issue.
MH SE dramatically improves manufacturing maintenance efficiency, empowering manufacturers to prioritize at-risk machines and allocate more resources toward more valuable tasks.
In addition to delivering automated alerts, the platform makes all AI detections visible to on-site teams via an intuitive digital interface where users can provide feedback on detection accuracy and log repairs to create an evolving machine health record for each asset.
In the case of the oven fan, the on-site team saw a trend of increasing vibration metrics and the precise conditions that prompted the cliff detection (which occurs when anomalous data patterns persist past an established time threshold). Ultimately, the team replaced the fan’s bearings in time to avoid a potentially significant loss of product.
MH SE dramatically improves manufacturing maintenance efficiency, empowering manufacturers to prioritize at-risk machines and allocate more resources toward more valuable tasks. Additionally, when deployed in combination with Augury’s Machine Health for Critical Assets solutions, MH SE allows manufacturers to access a robust dataset and gain insights regarding comprehensive cross-plant performance.
Get in touch today to learn more about how Augury can help your team make smarter maintenance and investment decisions and take more decisive action.