The operations management team of an International Oil Company (IOC) was troubled by recent asset performance and equipment failure rates. Management had limited success in extracting and analyzing rig data due to the sheer number of legacy data systems that came from post-merger integration. Each asset's operational data was stored across multiple, disparate systems and the information models varied by system. Benchmarking asset performance across geographies or against industry averages proved highly time-consuming and difficult.
Using Arundo's software, the company was able to aggregate all asset data into a common store, correlate and map the data relationships into an information model based on industry standards, and continuously update the model using real-time sensor data collection from the various systems. Arundo leveraged the latest in machine learning to automatically cleanse the inbound data in prep for analysis, then autonomously map the asset hierarchy from identified relationships. With the analysis-ready data available in a central store, the Arundo suite provided fleet-wide benchmarking comparisons and asset-to-asset performance KPIs with visibility down to the equipment level. The real-time, operational dashboards are running 24x7 in a cloud-based web portal for the company's operations center.