Case Study: Radiator Core Degradation Detected by DataMind AI in Komatsu 930E

Cooling system failures in large haul trucks can lead to severe engine damage, costly repairs, and extended unplanned downtime. To mitigate these risks, DataMind AI continuously monitors engine coolant temperatures, oil temperatures, coolant analysis results, and maintenance records, enabling early detection of thermal degradation before it escalates into failure.

In this case, DataMind AI identified abnormal cooling performance in a Komatsu 930E, where engine coolant temperature repeatedly exceeded the high alert threshold at 90.56°C and engine oil temperature trended near the alert limit of 104.4°C over a period of several weeks. Despite these thermal warning signs, coolant analysis returned normal results, ruling out fluid degradation or contamination. Maintenance records showed no related jobs or events registered during this period, making the issue invisible to periodic inspection routines.

By correlating rising temperature telemetry with normal coolant analysis and the absence of maintenance activity, DataMind AI pinpointed the root cause as saturated or failing radiator cores, with possible restriction in the engine oil cooler circuits. A recently completed 5000-hour service milestone further supported that radiator replacement was due.

Based on the early diagnosis, the site team inspected and cleaned radiator and oil cooler cores and verified replacement requirements before the issue escalated. The operation avoided approximately $85,000 in repair costs and prevented 3 days of unplanned downtime, demonstrating the value of continuous AI-driven thermal monitoring.