Scalable Architecture for Anomaly Detection and Visualization in Power Generating Assets

Power-generating assets (e.g., jet engines, gas turbines) are often instrumented with tens to hundreds of sensors for monitoring physical and performance degradation. Anomaly detection algorithms highlight deviations from predetermined benchmarks with the goal of detecting incipient faults. We are developing an integrated system to address three key challenges within analyzing sensor data from power-generating assets: (1) difficulty in ingesting and analyzing data from large numbers of machines; (2) prevalence of false alarms generated by anomaly detection algorithms resulting in unnecessary downtime and maintenance; and (3) lack of an integrated visualization that helps users understand and explore the flagged anomalies and relevant sensor context in the energy domain. We present preliminary results and our key findings in addressing these challenges. Our system's scalable event ingestion framework, based on OpenTSDB, ingests nearly 400,000 sensor data samples per seconds using a 30 machine cluster. To reduce false alarm rates, we leverage the False Discovery Rate (FDR) algorithm which significantly reduces the number of false alarms. Our visualization tool presents the anomalies and associated content flagged by the FDR algorithm to inform users and practitioners in their decision making process. We believe our integrated platform will help reduce maintenance costs significantly while increasing asset lifespan. We are working to extend our system on multiple fronts, such as scaling to more data and more compute nodes (70 in total).