Bio

Jingxiao Liu is a Ph.D. candidate in the Department of Civil & Environmental Engineering at Stanford University. He received his M.S. in Civil Engineering from Carnegie Mellon University in 2017. His research focuses on structural health monitoring, smart infrastructure systems, and smart city applications using signal processing, data mining, physics-guided machine learning, mobile sensing, and fiber-optic sensing techniques.

The main objective of his Ph.D. research is to develop physics-guided data-driven approaches for drive-by structural health monitoring that are scalable to a large stock of structures without requiring training data from every structure. His prior works on this topic have the following accomplishments: 1) Based on the physical understandings of vehicle-structure interaction systems, he has developed damage localization and quantification algorithms for drive-by SHM of bridges and an anomaly detection algorithm for railroad track geometry monitoring. He has published his works in top-tier conferences and journals in both civil and electrical engineering. 2) Collaborating with the Port Authority of Allegheny County, he has conducted real-world deployments and multiple field experiments on a light rail system, including a 42.2-km railroad track and multiple bridges, to validate the robustness of his approaches with complex and realistic infrastructure. He has published a comprehensive dataset collected from vehicles in this light rail system, which is the first open-access dataset for drive-by SHM.

Honors & Awards

  • Leavell Fellowship on Sustainable Built Environment, Civil and Environmental Engineering, Stanford University (2020)
  • Dean’s Fellowship, College of Engineering, Carnegie Mellon University (2018)

Education & Certifications

  • M.S., Carnegie Mellon University, Civil Engineering (2017)

Contact

  • Academic
    liujx@stanford.edu
    University - Student Department: Civil and Environmental Engineering Position: Graduate
    University - Student Department: Electrical Engineering Position: Graduate

Additional Info

Links

All Publications

  • HierMUD: Hierarchical multi-task unsupervised domain adaptation between bridges for drive-by damage diagnosis STRUCTURAL HEALTH MONITORING-AN INTERNATIONAL JOURNAL Liu, J., Xu, S., Berges, M., Noh, H. 2022

    View details for DOI 10.1177/14759217221081159

    View details for Web of Science ID 000840350900001

  • Predicting peak stresses in microstructured materials using convolutional encoder-decoder learning MATHEMATICS AND MECHANICS OF SOLIDS Shrivastava, A., Liu, J., Dayal, K., Noh, H. 2022

    View details for DOI 10.1177/10812865211055504

    View details for Web of Science ID 000739405600001

  • Diagnosis algorithms for indirect structural health monitoring of a bridge model via dimensionality reduction MECHANICAL SYSTEMS AND SIGNAL PROCESSING Liu, J., Chen, S., Berges, M., Bielak, J., Garrett, J. H., Kovacevic, J., Noh, H. 2020; 136

    View details for DOI 10.1016/j.ymssp.2019.106454

    View details for Web of Science ID 000529083600015

  • DAMAGE-SENSITIVE AND DOMAIN-INVARIANT FEATURE EXTRACTION FOR VEHICLE-VIBRATION-BASED BRIDGE HEALTH MONITORING Liu, J., Chen, B., Chen, S., Berges, M., Bielak, J., Noh, H., IEEE IEEE. 2020: 3007–11

    View details for Web of Science ID 000615970403051

  • Dynamic responses, GPS positions and environmental conditions of two light rail vehicles in Pittsburgh SCIENTIFIC DATA Liu, J., Chen, S., Lederman, G., Kramer, D. B., Noh, H., Bielak, J., Garrett, J. H., Kovacevic, J., Berges, M. 2019; 6: 146

    Abstract

    We present DR-Train, the first long-term open-access dataset recording dynamic responses from in-service light rail vehicles. Specifically, the dataset contains measurements from multiple sensor channels mounted on two in-service light rail vehicles that run on a 42.2-km light rail network in the city of Pittsburgh, Pennsylvania. This dataset provides dynamic responses of in-service trains via vibration data collected by accelerometers, which enables a low-cost way of monitoring rail tracks more frequently. Such an approach will result in more reliable and economical ways to monitor rail infrastructure. The dataset also includes corresponding GPS positions of the trains, environmental conditions (including temperature, wind, weather, and precipitation), and track maintenance logs. The data, which is stored in a MAT-file format, can be conveniently loaded for various potential uses, such as validating anomaly detection and data fusion as well as investigating environmental influences on train responses.

    View details for DOI 10.1038/s41597-019-0148-9

    View details for Web of Science ID 000481667300002

    View details for PubMedID 31406119

    View details for PubMedCentralID PMC6690915

  • A Damage Localization and Quantification Algorithm for Indirect Structural Health Monitoring of Bridges Using Multi-Task Learning Liu, J., Berges, M., Bielak, J., Garrett, J. H., Kovacevic, J., Noh, H., Bond, L. J., Holland, S., Laflamme, S. AMER INST PHYSICS. 2019

    View details for DOI 10.1063/1.5099821

    View details for Web of Science ID 000479309100117

  • Detecting Anomalies in Longitudinal Elevation of Track Geometry Using Train Dynamic Responses via a Variational Autoencoder Liu, J., Wei, Y., Berges, M., Bielak, J., Garrett, J. H., Noh, H., Lynch, J. P., Huang, H., Sohn, H., Wang, K. W. SPIE-INT SOC OPTICAL ENGINEERING. 2019

    View details for DOI 10.1117/12.2513711

    View details for Web of Science ID 000483016400039

https://orcid.org/0000-0001-5559-1627