Beyond immediate oper - ational gains, the system also contributed to a cultural shift within the maintenance organisation. Teams began to rely more heavily on data- driven insights rather than reactive troubleshooting, fostering a proactive mindset and improving collaboration between field technicians and reliability engineers. The visibility provided by real-time dashboards and historical trend analysis empowered stakeholders to make informed decisions and prioritise maintenance activ - ities based on actual equip - ment conditions rather than
P1 V Overall velocity waveform RMS
20 mm/s
15 mm/s
10 mm/s
5 mm/s
0 mm/s
Jun 28
Jul 1
Jul 4
Jul 7
Jul 10
Jul 13
Jul 16
2025
Figure 2 This chart illustrates a fault condition where the overall waveform root mean square (RMS) value increases due to the malfunction. Once corrective action is taken, the RMS value begins to decline, indicating system recovery
thresholds (normal, warning, and critical) enabled precise classification of anomalies and ensured that alerts were contextually relevant. The automated email notifications provided timely communication, allowing maintenance teams to act swiftly and decisively. Moreover, the field implementation highlighted the oper - ational advantages of wireless monitoring. The elimination of manual data collection reduced technician workload and improved safety by minimising exposure to hazard - ous areas. The wireless sensors’ ease of installation and battery-powered design facilitated rapid deployment without the need for extensive cabling or infrastructure modifications. Additionally, the flexibility of sensor place - ment allowed coverage of previously inaccessible or high-risk zones, further enhancing the system’s reach and effectiveness across the refinery. Results and future outlook Over the course of the deployment, the wireless vibration monitoring system proved to be a transformative tool in the refinery’s maintenance strategy. By enabling continu - ous condition monitoring and integrating intelligent alert - ing mechanisms, the system facilitated early detection of mechanical anomalies and supported timely interventions that prevented equipment failures. This proactive approach not only minimised the risk of unexpected breakdowns but also allowed maintenance teams to plan interventions dur - ing scheduled downtimes, thereby improving overall oper - ational efficiency. The three documented cases of bearing degradation, mechanical misalignment, and shaft deflection serve as compelling evidence of the system’s value. In each instance, the ability to act before a failure occurred resulted in tangi - ble benefits: reduced repair costs, avoidance of unplanned downtime, and enhanced operational safety. These out - comes underscore the strategic importance of predictive maintenance in high-risk industrial environments, where even minor disruptions can have significant financial and safety implications.
fixed schedules. This shift also encouraged cross-functional engagement, as operations, engineering, and IT teams began to align more closely around shared performance goals. Looking ahead, the next phase of this initiative involves scaling the system to other rotating assets across the refin - ery, including pumps, compressors, and fans. These assets share similar failure modes and operational criticality, mak - ing them ideal candidates for wireless vibration monitoring. The modular architecture of the current system supports easy expansion, and the existing infrastructure can accom - modate additional sensors and gateways with minimal con - figuration effort. This scalability ensures that the benefits realised in the initial deployment can be replicated across the broader asset base. Furthermore, there are plans to integrate the monitoring system with advanced analytics platforms and machine learning models. By leveraging historical vibration data and failure records, predictive algorithms can be trained to fore - cast equipment degradation patterns with greater accu - racy. This will enable even earlier interventions and support long-term asset health management. Over time, such inte - gration could evolve into a fully autonomous maintenance ecosystem, where AI-driven insights continuously optimise performance, reduce human error, and extend the lifecycle of critical equipment. Murat Barış Türkoğlu is the Head of Information Technologies, with full responsibility for IT, OT, and digital transformation processes. He leads strategic efforts to unify these three domains, ensuring seamless technology integration and innovation across the organisation. Barış graduated from Dicle University in Diyarbakır, Turkey, with a degree in electrical and electronics engineering. Mert Uztemur is a Senior Operational Technologies Engineer, responsible for industrial systems projects and IoT implementations. He holds a BSc in electronics and communication engineering from İzmir Institute of Technology İzmir, Turkey, and an MSc in manage - ment information systems from Dokuz Eylül University, İzmir, Turkey. His work supports operational efficiency and digital transformation in industrial environments.
66
PTQ Q1 2026
www.digitalrefining.com
Powered by FlippingBook