Risk-Based Thresholding for Reliable Anomaly Detection in Concentrated Solar Power Plants

2025-03-24

AI Summary

Operational risks—including freezing, deformation, and corrosion—pose critical challenges to high-temperature solar receivers in concentrating solar power (CSP) plants; conventional threshold-based anomaly detection methods lack statistical coverage guarantees under limited-sample conditions. This paper proposes a risk-controllable anomaly detection framework: (1) a novel anomaly scoring method integrating temporal density forecasting to enhance modeling of infrared image sequences; (2) a risk-aware threshold generation mechanism with finite-sample coverage guarantees, enabling reliable decision-making under arbitrary risk functions; and (3) the first open-source, multi-scenario synthetic thermographic dataset, augmented with an expert-in-the-loop deferral mechanism. Evaluated over several months across two operational CSP plants, the framework significantly improves detection reliability and supports data-driven maintenance optimization. All code and the dataset are publicly released.

Technology Category

• Data Mining & Knowledge Management: Anomaly/Outlier Detection
• Machine Learning: Calibration & Uncertainty Quantification
• Constraint Satisfaction and Optimization: Distributed CSP/Optimization

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Security and Privacy: Large-scale security measurements
• Graph Algorithms and Modeling for the Web: Algorithms and analysis for heterogeneous, signed, attributed, multi-relational, temporal, higher-order, and annotated Web-related graphs

Abstract

Efficient and reliable operation of Concentrated Solar Power (CSP) plants is essential for meeting the growing demand for sustainable energy. However, high-temperature solar receivers face severe operational risks, such as freezing, deformation, and corrosion, resulting in costly downtime and maintenance. To monitor CSP plants, cameras mounted on solar receivers record infrared images at irregular intervals ranging from one to five minutes throughout the day. Anomalous images can be detected by thresholding an anomaly score, where the threshold is chosen to optimize metrics such as the F1-score on a validation set. This work proposes a framework for generating more reliable decision thresholds with finite-sample coverage guarantees on any chosen risk function. Our framework also incorporates an abstention mechanism, allowing high-risk predictions to be deferred to domain experts. Second, we propose a density forecasting method to estimate the likelihood of an observed image given a sequence of previously observed images, using this likelihood as its anomaly score. Third, we analyze the deployment results of our framework across multiple training scenarios over several months for two CSP plants. This analysis provides valuable insights to our industry partner for optimizing maintenance operations. Finally, given the confidential nature of our dataset, we provide an extended simulated dataset, leveraging recent advancements in generative modeling to create diverse thermal images that simulate multiple CSP plants. Our code is publicly available.

Problem

• Develops risk-based thresholding for CSP anomaly detection
• Proposes density forecasting for image likelihood scoring
• Provides simulated dataset for confidential CSP thermal images

Innovation

• Risk-based thresholding with finite-sample guarantees
• Density forecasting for anomaly score estimation
• Simulated dataset using generative modeling techniques