Navigation

  • Skip to Content
NTNU Home NTNU Home

ntnu.edu

  • Studies
    • Master's programmes in English
    • For exchange students
    • PhD opportunities
    • All programmes of study
    • Courses
    • Financing
    • Language requirements
    • Application process
    • Academic calendar
    • FAQ
  • Research and innovation
    • NTNU research
    • Research excellence
    • Strategic research areas
    • Innovation resources
    • PhD opportunities
  • Life and housing
    • Student in Trondheim
    • Student in Gjøvik
    • Student in Ålesund
    • For researchers
    • Life and housing
  • About NTNU
    • Contact us
    • Faculties and departments
    • Libraries
    • International researcher support
    • Vacancies
    • About NTNU
    • Maps
  1. Employees

Språkvelger

Norsk

Shaoyao Chen

Download press photo
Download press photo
Foto:

Shaoyao Chen

PhD student
Faculty of Engineering

shaoyao.chen@ntnu.no
About Publications

About

Research

With the rapid advancements in artificial intelligence, infrastructure and mechanical systems monitoring and maintenance can now leverage suitable AI algorithms to achieve both economic and labor efficiencies. As part of the larger Metint project, my PhD project aims to continuously monitor railway vehicles and infrastructure by applying the latest data science and machine learning techniques.

The focus of my work is to mine the data which is from the measuring system installed on a regularly operated passenger train and develop algorithms that provide information on the status of railway catenaries and train bogies. The measuring system is designed to work simultaneously with the train's daily run, avoiding interrupting train traffic.

Through my PhD work, I will contribute to the Metint project's goal of determining the trainset and railway infrastructure condition by analyzing data from onboard systems on Norwegian passenger trains. The outcome of my work will assist the railway industry in transitioning from traditional corrective maintenance to predictive maintenance, achieving greater efficiency and reducing costs.

Research areas and interests

Deep Learning, Machine Learning, Artificial Intelligence, Data Mining, Data Science

Publications

  • Chronological
  • By category
  • All publications registered in NVA

2025

  • Chen, Shaoyao; Song, Yang; Nåvik, Petter Juell; Rønnquist, Anders; Frøseth, Gunnstein Thomas. (2025) Defects detection for railway catenary system with encoder-decoder architecture. Railway Engineering Science
    Academic article

2024

  • Chen, Shaoyao; Frøseth, Gunnstein Thomas; Derosa, Stefano; Lau, Albert; Rønnquist, Anders. (2024) Railway Catenary Condition Monitoring: A Systematic Mapping of Recent Research. Sensors
    Academic literature review

Journal publications

  • Chen, Shaoyao; Song, Yang; Nåvik, Petter Juell; Rønnquist, Anders; Frøseth, Gunnstein Thomas. (2025) Defects detection for railway catenary system with encoder-decoder architecture. Railway Engineering Science
    Academic article
  • Chen, Shaoyao; Frøseth, Gunnstein Thomas; Derosa, Stefano; Lau, Albert; Rønnquist, Anders. (2024) Railway Catenary Condition Monitoring: A Systematic Mapping of Recent Research. Sensors
    Academic literature review

NTNU – Norwegian University of Science and Technology

  • For employees
  • |
  • For students
  • |
  • Intranet
  • |
  • Blackboard

Studies

  • Master's programmes in English
  • For exchange students
  • PhD opportunities
  • Courses
  • Career development
  • Continuing education
  • Application process

News

  • NTNU News
  • Vacancies

About NTNU

  • About the university
  • Libraries
  • NTNU's strategy
  • Research excellence
  • Strategic research areas
  • Organizational chart

Contact

  • Contact NTNU
  • Employees
  • Find experts
  • Press contacts
  • Researcher support
  • Maps

NTNU in three cities

  • NTNU in Gjøvik
  • NTNU in Trondheim
  • NTNU in Ålesund

About this website

  • Use of cookies
  • Accessibility statement
  • Privacy policy
  • Editorial responsibility
Facebook Instagram Linkedin Snapchat Tiktok Youtube
Sign In
NTNU logo