Clustering- and statistic-based approach for detection and impact evaluation of faults in end-user substations of thermal energy systems
2024

Detecting and Evaluating Faults in Heating Systems

Sample size: 486 publication 10 minutes Evidence: moderate

Author Information

Author(s): Samanta A. Weber, Michael Fischlschweiger, Dirk Volta, Ulf Rieck-Blankenburg

Primary Institution: University of Applied Sciences Flensburg

Hypothesis

Can a clustering and statistical approach effectively identify and evaluate faults in user substations of thermal energy systems?

Conclusion

The study successfully developed a workflow that automates fault detection and quantifies the impact of faults on heating system efficiency.

Supporting Evidence

  • The study identified common fault indicators such as exceeded return temperature and very low cooling.
  • Statistical methods confirmed the successful detection of faulty substations.
  • The workflow allows for prioritization of fault elimination measures based on the quantified impact.

Takeaway

This study helps find problems in heating systems so they can work better and save energy.

Methodology

The study used a three-step workflow involving k-means clustering to identify fault indicators, followed by statistical methods to detect faulty substations and quantify their impact.

Potential Biases

Potential bias in expert labeling of fault indicators could affect the results.

Limitations

The study relies on data from a specific model region, which may not be generalizable to other areas.

Participant Demographics

The study focused on substations in a district heating network in northern Germany.

Digital Object Identifier (DOI)

10.1038/s41598-024-82103-5

Want to read the original?

Access the complete publication on the publisher's website

View Original Publication