Machine Learning for Wireless Structural Health Monitoring

ABSTRACT

The course provides fundamental knowledge about Machine Learning (ML) and its application to wireless Structural Health Monitoring (SHM). While being based on rigorous theoretical content, the course is oriented towards the most relevant applications for civil engineers. To complete the didactic offer, various numerical exercises (exploiting SW programs) will follow the theoretical lessons.  

COURSE CONTENT

Part 1: THE "THREE-STEPS LEARNING-BY-EXAMPLES (LBE)" FRAMEWORK

  • Overview, general concepts, and taxonomy of Machine Learning (ML) methodologies
  • Interpolation techniques
  • Dimensionality reduction methodologies
  • Space exploration/sampling methodologies
  • Classification and regression methodologies
     

Part 2: APPLICATIONS TO WIRELESS STRUCTURAL HEALTH MONITORING (SHM)

  • Overview of ML methodologies applied to wireless SHM
  • Model‐driven approaches vs. data‐driven approaches
  • Damage definition and identification
  • Data acquisition and processing
  • Damage prognosis
  • Modes/technologies for wireless SHM and their integration with ML
 

TEACHING ACTIVITIES

  • Theoretical Lessons
  • e-Xam Self Assessment (each teaching class or periodically)
  • MATLAB Hands-On
  • e-Xam Final Assessment
 

FURTHER READINGS

  1. J.‐A. Goulet, Probabilistic Machine Learning for Civil Engineers. Cambridge, MA: The MIT Press, 2020.
  2. A. Cury, Structural Health Monitoring Based on Data Science Techniques. Cham, Switzerland: Springer, 2022.
  3. A. I. J. Forrester, A. Sobester, and A. J. Keane, Engineering Design via Surrogate Modelling: A Practical Guide. Hoboken, N.J.: John Wiley & Sons, 2008.
  4. T. Hastie, J. Friedman, and R. Tisbshirani, The Elements of Statistical Learning: Data Mining, Inference, and Prediction. New York: Springer, 2017.
  5. V. N. Vapnik, The Nature of Statistical Learning Theory. New York: Springer, 2000.