An Intelligent Approach to Detecting Novel Fault Classes for Centrifugal Pumps Based on Deep CNNs and Unsupervised Methods

Mahdi Abdollah Chalaki, Daniyal Maroufi, Mahdi Robati, Mohammad Javad Karimi, Ali Sadighi
9/22/2023
cs.LG

Official code: mahdichalaki/AI-fault-detection-pumps (4 stars, last commit 2025-01-26).

Abstract

Despite the recent success in data-driven fault diagnosis of rotating machines, there are still remaining challenges in this field. Among the issues to be addressed, is the lack of information about variety of faults the system may encounter in the field. In this paper, we assume a partial knowledge of the system faults and use the corresponding data to train a convolutional neural network. A combination of t-SNE method and clustering techniques is then employed to detect novel faults. Upon detection, the network is augmented using the new data. Finally, a test setup is used to validate this two-stage methodology on a centrifugal pump and experimental results show high accuracy in detecting novel faults.

View on arXivView PDF

Code Implementations(1)

mahdichalaki/AI-fault-detection-pumpsOfficial
40Jupyter NotebookJan 24, 20251 years ago

Similar Papers

ECNN: A Low-complex, Adjustable CNN for Industrial Pump Monitoring Using Vibration Data

84% match2025

Advancing machine fault diagnosis: A detailed examination of convolutional neural networks

84% match2025

AI-Powered Machine Learning Approaches for Fault Diagnosis in Industrial Pumps

82% match2025

Application of a Dense Fusion Attention Network in Fault Diagnosis of Centrifugal Fan

82% match2023

Machine Fault Classification using Hamiltonian Neural Networks

80% match2023

A new transformation for embedded convolutional neural network approach toward real-time servo motor overload fault-detection

80% match2023

Cite this paper

@article{chalaki2023intelligent,
  title  = {An Intelligent Approach to Detecting Novel Fault Classes for Centrifugal Pumps Based on Deep CNNs and Unsupervised Methods},
  author = {Mahdi Abdollah Chalaki and Daniyal Maroufi and Mahdi Robati and Mohammad Javad Karimi and Ali Sadighi},
  year   = {2023},
  eprint = {2309.12765},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2309.12765v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2309.12765.svg)](https://codeofpaper.com/paper/2309.12765)

Discussion