Case Study 2: Waste Recycling Plant

Home > Resources > About Monitoring > Case Study 2: Waste Recycling Plant

Case Study 2:

Condition Monitoring at Recycling Plant

At the waste recycling plant a complete online wireless condition monitoring system with triaxial vibration sensors is installed on critical equipment bearings.  The sensors are battery powered with MAX long life batteries ( up to 8 years life time) and have a magnetic base for easy installation.  At the same time, current signature monitoring (ESA) is performed on the electrical motors of the equipment.  All data is collected in the Edge, on the iQunet server, which is installed locally, on premise.  The iQunet AI service featuring Anomaly Detection, is running on all sensors, providing sensitive alarms on upcoming failures.  The complete set-up and results can be found in this presentation.



  • Plant type: Waste treatment
  • Asset type: ballistic separators, waste conveyors
  • Critical parts being monitored: critical bearings on drive axes of multiple machines
  • Installed iQunet monitoring:

During the last few days the Anomaly Monitor Dashboard shows an upwards trend.  An alarm is raised.

A steep upward trend requires immediate action where a rather flat oriented trendline should require close follow up and inspection of the asset.

Once the anomaly score multiplies in a few days, it is time to maintain the asset and plan for replacement parts and service.



In conclusion, the implementation of triaxial vibration sensors and current signature monitoring (ESA) at the waste recycling plant has significantly enhanced the predictive maintenance capabilities for critical equipment bearings and electrical motors. The use of long-life battery-powered sensors with magnetic bases ensures easy installation and longevity, while the iQunet server and AI service provide real-time data collection and anomaly detection. The system’s ability to monitor trends and detect anomalies allows for timely interventions, thereby reducing the risk of equipment failure and optimizing maintenance schedules. The recent upward trend observed by the Anomaly Monitor underscores the system’s effectiveness in identifying potential issues early, enabling proactive maintenance actions to maintain operational efficiency and minimize downtime. The combination of advanced monitoring technologies and AI-driven analytics ensures that the plant can operate smoothly and sustainably, with minimal interruptions.