Enhancing Fault Diagnosis in Imbalanced Data Using Weighted GRU Architecture

Authors

  • Jarukamol Dawkrajai Chulalongkorn University
  • Weerawun Weerachapichasgul Naresuan University
  • Wachira Daosud Burapha University
  • Paisan Kittisupakorn Chulalongkorn University

DOI:

https://doi.org/10.4186/ej.2025.29.7.35

Keywords:

LSTM, GRU, SMOTE, imbalanced data, multi-stage flash desalination plant, accuracy

Abstract

The class imbalance, characterized by an unequal distribution between normal and abnormal classes, is predominantly observed in the field of fault diagnosis. Abnormal classes typically represent a minority, leading to a biased learning process favoring the majority class. Therefore, class balancing techniques are essential when applying deep learning approaches to ensure accurate classification of minority fault classes. In this study, we investigate and propose weighted approach for the gated recurrent unit (GRU) algorithm. The proposed weighted approach adjusts all three weights-input, recurrent, and bias inside the GRU architecture. Additionally, the synthetic minority over-sampling (SMOTE) technique with vanilla GRU and long short-term memory (LSTM) as well as the combination of SMOTE and the proposed weighting technique for GRU and LSTM, are compared to the proposed weighting architecture with GRU. We evaluate the effectiveness of this technique using operational data from a real multi-stage flash desalination plant, synthesizing datasets with varying imbalance ratios (4, 9, and 14) for evaluation. Performance metrics such as accuracy is employed for evaluation. Among the models tested, the weighted GRU (WGRU), the proposed model, consistently outperforms others across all variables and imbalance ratios.

Downloads

Download data is not yet available.

Author Biographies

Jarukamol Dawkrajai

Control and System Engineering Research Laboratory, Department of Chemical Engineering, Faculty of Engineering, Chulalongkorn University, Bangkok 10330, Thailand

Weerawun Weerachapichasgul

Department of Industrial Engineering, Faculty of Engineering, Naresuan University, Phitsanulok 65000, Thailand

Wachira Daosud

Department of Chemical Engineering, Faculty of Engineering, Burapha University, Chonburi 20131, Thailand

Paisan Kittisupakorn

Control and System Engineering Research Laboratory, Department of Chemical Engineering, Faculty of Engineering, Chulalongkorn University, Bangkok 10330, Thailand

Downloads

Published In
Vol 29 No 7, Jul 31, 2025
How to Cite
[1]
J. Dawkrajai, W. Weerachapichasgul, W. Daosud, and P. Kittisupakorn, “Enhancing Fault Diagnosis in Imbalanced Data Using Weighted GRU Architecture”, Eng. J., vol. 29, no. 7, pp. 35-44, Jul. 2025.