SunScreen: Visual Fault Detection for Solar-Thermal Systems

Abstract

Fault detection is essential to ensure the proper operation of solar-thermal plants. Hence, monitoring personnel frequently analyze the data to detect unusual behavior. While visualization approaches may considerably support the monitoring personnel during their work, no existing application can yet deal with the multivariate and time-dependent sensor data, or does not fully support the users' workflow. Thus, this work introduces the visual framework SunScreen. It allows users to explore the sensor data, automatically detected anomalies, and system events (e.g., already detected faults and services). The feedback from the users shows that they appreciate the tool and especially its annotation functionality. However, the SUS results indicate that it does not meet all requirements yet. S olar-thermal plants use solar irradiation to produce heat. With heat accounting for approximately 50% of the global energy demand, 1 this technology could play a crucial role in the transition to renewable energy. However, monitoring is essential to ensure the proper operation of the plants. Thus, monitoring personnel frequently analyze the sensor data to detect unusual behavior.However, the main challenge for this fault detection is the complex behavior of solar-thermal plants and its multidimensional, time-dependent, and non-linear measurement data. As a result, the data is hard to interpret even by experts, while automatic fault detection algorithms are prone to raise false alarms. 2,3 Visual frameworks may considerably support the monitoring personnel by combining domain knowledge and automatic anomaly detection and letting users explore the measurement data.Unfortunately, no designated software for fault detection at solar thermal plants exists yet. Lacking an alternative, operators often use supervisory control and data acquisition (SCADA) applications. However, mainly targeted at industrial processes, they do not support analyzing the multidimensional sensor data and provide little functionality for exploring automatic fault detection results. While applications related to XXXX-XXX © 2023 IEEE Digital Object Identifier 10.1109/XXX.0000.0000000