Shapelet-Based Sensor Fault Detection and Human-Centered Explanations in Industrial Control System

Abstract

With the development of information and communication technology, industrial control systems (ICSs) that operate in closed environments are now operating in smart environments, and external threats are increasing. To predict failure and respond to threats, anomaly detection and fault detection using artificial intelligence (AI) are being introduced, but the issue of the reliability of AI prediction is emerging. For anomaly detection, the operator must check thousands of sensors. In addition, practical operational constraints exist because AI predictions are not always accurate. This study proposes shapelet-based anomaly detection and automatic fault sensor description technology to overcome these limitations. Through intuitive abnormality detection and interpretation based on these representative patterns, when an abnormal situation occurs, operators can immediately intuitively determine which sensor causes the problem and how much the sensor differs from the pattern. This was verified with the HIL-based Augmented ICS Security Dataset (HAI) and Secure Water Treatment (SWaT) dataset, which is widely used in the ICS field. In the case of the HAI Dataset, 95.12% of the failed sensors were analyzed by extracting and inspecting only 4% of the total sensors. In the case of the SWaT Dataset, only 7% of the sensors were extracted and inspected, confirming that 84% of the failed sensors could be analyzed. We expect that intuitive explanations and anomaly detection will enable more effective technological operations in industrial environments.

Keywords

• Anomaly detection
• efficient explanations
• effective operation
• fault sensor
• shapelet