Fault detection and diagnosis in refrigeration systems using machine learning algorithms

Zahra Soltani*, Kresten Kjær Sørensen, John Leth, Jan Dimon Bendtsen

*Kontaktforfatter

Publikation: Bidrag til tidsskriftTidsskriftartikelForskningpeer review

8 Citationer (Scopus)
124 Downloads (Pure)

Abstract

The functionality of industrial refrigeration systems is important for environment-friendly companies and organizations, since faulty systems can impact human health by lowering food quality, cause pollution, and even lead to increased global warming. Therefore, in this industry, there is a high demand among manufacturers for early and automatic fault diagnosis. In this paper, different machine learning classifiers are tested to find the best solution for diagnosing twenty faults possibly encountered in such systems. All sensor faults and some relevant component faults are simulated in a high fidelity Matlab/Simscape model of the system, which has previously been used for controller development and verification. In this work, Convolutional Neural Networks, Support Vector Machines (SVM), Principal Components Analysis-SVM, Linear Discriminant Analysis-SVM, and Linear Discriminant Analysis classifiers are compared. The results indicate that the fault detection reliability of the algorithms highly depends on how well the training data covers the operation regime. Furthermore, it is found that a well-trained SVM can simultaneously classify twenty types of fault with 95% accuracy when the verification data is taken from different system configurations.

OriginalsprogEngelsk
TidsskriftInternational Journal of Refrigeration
Vol/bind144
Sider (fra-til)34-45
Antal sider12
ISSN0140-7007
DOI
StatusUdgivet - dec. 2022

Bibliografisk note

Funding Information:
This work is funded by Innovation fund Denmark and Bitzer Electronics A/S. [fund number:9065-00010B]

Publisher Copyright:
© 2022 The Authors

Emneord

  • Dimensionality reduction
  • Fault detection
  • Machine learning
  • Refrigeration
  • Sensor

Fingeraftryk

Dyk ned i forskningsemnerne om 'Fault detection and diagnosis in refrigeration systems using machine learning algorithms'. Sammen danner de et unikt fingeraftryk.

Citationsformater