A semi-supervised interpretable machine learning framework for Sensor Fault detection

Panagiotis Martakis*, Artur Movsessian, Yves Reuland, Sai G. S. Pai, Said Quqa, David Garcia Cava, Dmitri Tcherniak, Eleni Chatzi

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

Abstract

Structural Health Monitoring (SHM) of critical infrastructure comprises a major
pillar of maintenance management, shielding public safety and economic sustainability. Although SHM is usually associated with data-driven metrics and thresholds, expert judgement is essential, especially in cases where erroneous predictions can bear casualties or substantial economic loss. Given that inspections are time consuming and potentially subjective, articial-intelligence tools may be leveraged in order to minimize the inspection effort and provide objective outcomes. In this context, timely detection of sensor malfunctioning is crucial in preventing inaccurate assessment and false alarms. The present work introduces a sensor-fault detection and interpretation framework, based on the well-established supportvector machine scheme for anomaly detection, combined with a coalitional game-theory approach. The proposed framework is implemented in two datasets, provided along the 1st International Project Competition for Structural Health Monitoring (IPC-SHM, 2020), comprising acceleration and cable-load measurements from two real cable-stayed bridges. The results demonstrate good predictive performance and highlight the potential for seamless adaption of the algorithm to intrinsically different data domains. For the rst time, the term "decision trajectories", originating from the eld of cognitive sciences, is introduced and applied in the context of SHM. This provides an intuitive and comprehensive illustration of the impact of individual features, along with an elaboration on feature dependencies, that drive individual model predictions. Overall, the proposed framework provides an easy to-train, application-agnostic and interpretable anomaly detector, which can be integrated into the preprocessing part of diverse SHM and condition-monitoring applications, offering a rst screening of the sensor health prior to further analysis.
Original languageEnglish
Pages (from-to)251-266
JournalSmart Structures and Systems, An International Journal
Volume29
Issue number1
Early online date4 Jan 2022
DOIs
Publication statusE-pub ahead of print - 4 Jan 2022

Keywords

  • SHM
  • Sensor fault detection
  • Interpretable AI
  • SHAP
  • One class classifiers
  • Decision trajectories
  • Decision Trajectory Assurance Criterion
  • DTAC

Fingerprint

Dive into the research topics of 'A semi-supervised interpretable machine learning framework for Sensor Fault detection'. Together they form a unique fingerprint.

Cite this