How to Use IIoT-Enabled Asset Tracking to Optimize Maintenance

Editor's Note: Eric Whitley is the director of smart manufacturing for L2L.

Those in the food safety industry are no strangers to the daily risks and serious implications of food contamination, cold chain interruptions and waste. While hazard prevention comes with many variables, equipment maintenance must be a top priority, with considerable effort and investment put into implementing preventive maintenance strategies to ensure equipment integrity and reliability.

The Industrial Internet of Things (IIoT) is revolutionizing manufacturing and maintenance by enabling remote monitoring, data collection and automated control. The technology has implications for lowering risk and improving quality in food processing. The two applications of IIoT discussed in this article promise optimized maintenance practices, reduced operating costs and greater product control.

REAL-TIME ASSET MONITORING. Connecting miniature, rugged and smart sensors to operating equipment provides real-time operating characteristics, location and movement. These sensors report data through a wireless network, and the benefits are threefold. 

Financially, enterprise asset management systems can use this data to enhance financial performance by tracking asset location, frequency of use and condition. This insight enables businesses to optimize their balance sheets by removing, repairing or relocating their lazy assets.

Operationally, continuous asset monitoring ensures key operating parameters remain within critical process requirements. When data trends show abnormalities, automated alerts warn maintenance personnel or operators to act and prevent procedural exceedances.

A common operational example in agribusiness logistics is an IIoT device placed in critical shipments to monitor temperature and humidity, light exposure (from an opened carton), movement and exposure to excessive G-forces from handling. The device allows global inquiry into the status and location and sends automated alerts when exceedances are felt by one or multiple sensor thresholds.

Commercially, real-time asset monitoring optimizes maintenance and asset management. Sensors monitor the key parameters on critical equipment, measuring specific characteristics like flow, temperature, pressure differential, fluid levels and ultrasonic vibration. The continuous data stream picks up when bearings become noisy, when energy use increases or pressures and flows alter — all signs of underlying maintenance issues. Actions like lubricating a dry bearing can be automated as well. Maintenance professionals can also schedule an early intervention during planned downtime, preventing sub-optimal operation or equipment failure.

The Swedish company Tetra Pak has invested heavily in IIoT technology for its milk packaging plant, which processes and packs aseptic products. One critical component is an expensive carton-sealing servo motor with a life expectancy between 2,000 and 7,000 hours of operation. Replacing it at 2,000 hours would be hugely expensive when it might run for another two years, but its failure could impose a four-day unplanned stoppage to the entire line. By implementing IIoT monitoring on 11 packaging lines, Tetra Pak managed to fit five servo motor replacements into routine planned stops of four hours, avoiding an estimated loss of $30,000 and preventing premature part replacement.

PREDICTIVE MAINTENANCE. Predictive maintenance takes asset management to the next level by using artificial intelligence (AI) and machine learning (ML). AI and ML are used to monitor IIoT data streams for changes in operating characteristics that are undetectable by human senses. 

The machine learning algorithms use advanced analytics to process historical maintenance data and operational information, enabling the identification of progressive decline in operating parameters. Once trained, the system can predict equipment failure weeks or months ahead, allowing maintenance personnel sufficient time to organize resources and schedule maintenance interventions and minimizing or negating production stoppages.

PepsiCo Inc. has implemented predictive maintenance technology at four of its Frito-Lay plants. Sensors transmit sound data to a cloud-based AI platform trained to identify over 80,000 sounds of industrial machinery operating at various stages of their lifecycle, from new to failing. By overlaying pattern identification over the data from the Frito-Lay equipment, the AI system predicts imminent component failure, informing the maintenance team on what needs replacing and when.

The general manager of PepsiCo Labs claims the technology has optimized maintenance to such a degree that Frito-Lay has obtained a further 4,000 hours of annual manufacturing capacity. The company plans to roll the technology out to all its beverage and bottling facilities across the U.S.

FINAL THOUGHTS. The momentum to apply IIoT technology for competitive advantage is growing across industries. With organizations increasingly scrutinized for sustainability, safety and quality credentials, IIoT asset tracking promises less waste, improved asset longevity, optimized maintenance practices and safer, more efficient production.

With the time and safety imperatives being implicit in food processing, using asset tracking to optimize maintenance, monitor processes and track equipment in real-time offers businesses an attractive return on investment.