cs.LGOct 2, 2026

Smart Sensing for Safer Bridges: From Sensor Signals to AI-Driven Anomaly Detection

Authors: Rahul Jaiswal, Joakim Hellum, Halvor Heiberg

Organizations: Smart Sensor Systems AS Oslo, Norway

Read PDF
Ask AI
Cite

Copy citation

DOINot available for this paper

Abstract

Bridges contribute significantly to transportation connectivity and urban development. Therefore, reliable bridge monitoring is crucial for protecting public safety and detecting anomalous behavior in bridge sensor data that may provide early indications of abnormal structural conditions. This paper investigates anomaly detection in real-world bridge sensor data using two different complementary approaches, namely signal processing and the data-driven machine learning model Isolation Forest. The real-time bridge sensor data is collected from an iBridge sensor device installed on a bridge in Norway. The methods are evaluated using anomaly counts, anomaly detection time, processing rate, anomaly rates, visualization, and temporal agreement. Moreover, a controlled anomaly-injection analysis is performed to evaluate the sensitivity of each method. Numerical results demonstrate distinct detection characteristics and computational requirements, highlighting the potential of machine learning, particularly the data-driven Isolation Forest, alongside signal processing for identifying anomalies in bridge sensor measurements.

Figures & tables

Fig. 1: Example of anomaly detection in sensor data.
Fig. 2: A simple illustration of the signal processing technique.
Fig. 3: Illustration of a typical Isolation Tree (iTree) structure.
Fig. 4: Overview of the proposed bridge anomaly detection model.
Fig. 5: Illustration of the iBridge sensor device.
Fig. 6: ADC1 signal in bridge sensor data.
Fig. 7: ADC2 signal in bridge sensor data.
Fig. 8: ADC3 signal in bridge sensor data.
Method with parameters
SignalSignal Processing (SP)Isolation Forest (IF)
ADC1prominence=80, distance=20n_estimators 1 1 1 In Isolation Forest, n_estimators denotes the number of isolation trees, contamination specifies the expected proportion of anomalous samples, and n_jobs determines the number of CPU cores used for computation, where n_jobs=−1\text{n\_jobs}=-1 utilizes all available cores. =300,
  contamination=0.001, n_jobs=-1
ADC2For positive peak: height=-5,n_estimators =300,
 prominence=5, distance=20contamination=0.00001, n_jobs=-1
 For negative peak: height=15, 
TABLE I: Parameter settings for each method.
SignalTotalAnomaly detectionProcessing rateAnomaly rate
 anomaliestime (in seconds)(in samples/second)(in %)
Signal Processing
ADC13490.192619,593,631.540.009247
ADC2140.135527,854,655.240.000371
ADC310.054669,085,072.700.000026
Isolation Forest
TABLE II: Performance of each method.
Fig. 9: ADC1 anomalies detected using signal processing.
Fig. 10: ADC2 anomalies detected using signal processing.
Fig. 11: ADC3 anomalies detected using signal processing.
Fig. 12: ADC1 anomalies detected using Isolation Forest.
Fig. 13: ADC2 anomalies detected using Isolation Forest.
Fig. 14: ADC3 anomalies detected using Isolation Forest.
SignalSPIFMatchedSP agreementIF agreement
 anomaliesanomaliesanomalies(%)(%)
ADC1349357910028.652.79
ADC21429214.296.90
ADC31111100.009.09
TABLE III: Temporal agreement between each method using a ±5\pm 5 samples ( ±1\pm 1 second) matching tolerance.
SignalInjectedSP detectedSP Recall (%)IF detectedIF Recall (%)
ADC11800.0000.00
ADC218633.3318100.00
ADC31815.561372.22
TABLE IV: Anomaly detection under controlled injections.
More in this topic

Online Anomaly Detection

Online anomaly detection identifies unusual events in data streams as they arrive, adapting to changing conditions while balancing detection speed, accuracy, and false alarms.

See all 57 papers

Explore similar work

CardsList

  1. Detecting the Unexpected: AI-Driven Anomaly Detection in Smart Bridge Monitoring

    Mar 30, 2026Rahul Jaiswal, Joakim Hellum, Halvor HeibergAnomaly DetectionStructural Health Monitoring

    Smart Sensor Systems AS, Oslo, Norway

  2. A Vehicle-Integrated Approach to Digital Twin Deployment for Bridges Through Drive-By Sensing

    Sep 25, 2026Zihao Liu, Daigo Kawabe, Jiaji Wang +2Structural Health MonitoringDigital Twins

    School of Civil and Environmental Engineering, University of New South Wales, Sydney, Australia · KyoCenseo Inc., Kyoto, Japan · Department of Civil Engineering, The University of Hong Kong, Hong Kong, China +1

  3. Evaluation of AI-based Visual Crack Detection in Steel Bridges Using Probability of Detection

    Aug 18, 2026Andrii Kompanets, Finn Michael Sherry, Remco Duits +2Fault DetectionStructural Health Monitoring

    Eindhoven University of Technology, Department of the Built Environment, Eindhoven, The Netherlands · Eindhoven Artificial Intelligence Systems Institute, Eindhoven University of Technology, Eindhoven, The Netherlands · Eindhoven University of Technology, Department of Mathematics and Computer Science, Eindhoven, The Netherlands