Multimodal bearing fault classification under variable conditions: A 1D CNN with transfer learning

Bearings play an integral role in ensuring the reliability and efficiency of rotating machinery — reducing friction and handling critical loads. Bearing failures that constitute up to 90% of mechanical faults highlight the imperative need for reliable condition monitoring and fault detection. This s...

Full description

Saved in:
Bibliographic Details
Main Authors: Tasfiq E. Alam, Md Manjurul Ahsan, Shivakumar Raman
Format: Article
Language:English
Published: Elsevier 2025-09-01
Series:Machine Learning with Applications
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2666827025000659
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849422260134215680
author Tasfiq E. Alam
Md Manjurul Ahsan
Shivakumar Raman
author_facet Tasfiq E. Alam
Md Manjurul Ahsan
Shivakumar Raman
author_sort Tasfiq E. Alam
collection DOAJ
description Bearings play an integral role in ensuring the reliability and efficiency of rotating machinery — reducing friction and handling critical loads. Bearing failures that constitute up to 90% of mechanical faults highlight the imperative need for reliable condition monitoring and fault detection. This study proposes a multimodal bearing fault classification approach that relies on vibration and motor phase current signals within a one-dimensional convolutional neural network (1D CNN) framework. The method fuses features from multiple signals to enhance the accuracy of fault detection. Under the baseline condition (1500 rpm, 0.7 Nm load torque, and 1000 N radial force), the model reaches an accuracy of 96% with addition of L2 regularization. In addition, the model demonstrates robust performance across three distinct operating conditions by employing transfer learning (TL) strategies. Among the tested TL variants, the approach that preserves parameters up to the first max-pool layer and then adjusts subsequent layers achieves the highest performance. While this approach attains excellent accuracy across varied conditions, it requires more computational time due to its greater number of trainable parameters. To address resource constraints, less computationally intensive models offer feasible trade-offs, albeit at a slight accuracy cost. Overall, this multimodal 1D CNN framework with late fusion and TL strategies lays a foundation for more accurate, adaptable, and efficient bearing fault classification in industrial environments with variable operating conditions.
format Article
id doaj-art-6aada61b85f341ccaefca1bedeb0eaa5
institution Kabale University
issn 2666-8270
language English
publishDate 2025-09-01
publisher Elsevier
record_format Article
series Machine Learning with Applications
spelling doaj-art-6aada61b85f341ccaefca1bedeb0eaa52025-08-20T03:31:10ZengElsevierMachine Learning with Applications2666-82702025-09-012110068210.1016/j.mlwa.2025.100682Multimodal bearing fault classification under variable conditions: A 1D CNN with transfer learningTasfiq E. Alam0Md Manjurul Ahsan1Shivakumar Raman2Department of Industrial and Systems Engineering, University of Oklahoma, Norman, OK 73019, USA 11 https://www.ou.edu.Corresponding author.; Department of Industrial and Systems Engineering, University of Oklahoma, Norman, OK 73019, USA 11 https://www.ou.edu.Department of Industrial and Systems Engineering, University of Oklahoma, Norman, OK 73019, USA 11 https://www.ou.edu.Bearings play an integral role in ensuring the reliability and efficiency of rotating machinery — reducing friction and handling critical loads. Bearing failures that constitute up to 90% of mechanical faults highlight the imperative need for reliable condition monitoring and fault detection. This study proposes a multimodal bearing fault classification approach that relies on vibration and motor phase current signals within a one-dimensional convolutional neural network (1D CNN) framework. The method fuses features from multiple signals to enhance the accuracy of fault detection. Under the baseline condition (1500 rpm, 0.7 Nm load torque, and 1000 N radial force), the model reaches an accuracy of 96% with addition of L2 regularization. In addition, the model demonstrates robust performance across three distinct operating conditions by employing transfer learning (TL) strategies. Among the tested TL variants, the approach that preserves parameters up to the first max-pool layer and then adjusts subsequent layers achieves the highest performance. While this approach attains excellent accuracy across varied conditions, it requires more computational time due to its greater number of trainable parameters. To address resource constraints, less computationally intensive models offer feasible trade-offs, albeit at a slight accuracy cost. Overall, this multimodal 1D CNN framework with late fusion and TL strategies lays a foundation for more accurate, adaptable, and efficient bearing fault classification in industrial environments with variable operating conditions.http://www.sciencedirect.com/science/article/pii/S2666827025000659Bearing fault detection1D CNNTransfer learningMultimodal fusionL2 regularization
spellingShingle Tasfiq E. Alam
Md Manjurul Ahsan
Shivakumar Raman
Multimodal bearing fault classification under variable conditions: A 1D CNN with transfer learning
Machine Learning with Applications
Bearing fault detection
1D CNN
Transfer learning
Multimodal fusion
L2 regularization
title Multimodal bearing fault classification under variable conditions: A 1D CNN with transfer learning
title_full Multimodal bearing fault classification under variable conditions: A 1D CNN with transfer learning
title_fullStr Multimodal bearing fault classification under variable conditions: A 1D CNN with transfer learning
title_full_unstemmed Multimodal bearing fault classification under variable conditions: A 1D CNN with transfer learning
title_short Multimodal bearing fault classification under variable conditions: A 1D CNN with transfer learning
title_sort multimodal bearing fault classification under variable conditions a 1d cnn with transfer learning
topic Bearing fault detection
1D CNN
Transfer learning
Multimodal fusion
L2 regularization
url http://www.sciencedirect.com/science/article/pii/S2666827025000659
work_keys_str_mv AT tasfiqealam multimodalbearingfaultclassificationundervariableconditionsa1dcnnwithtransferlearning
AT mdmanjurulahsan multimodalbearingfaultclassificationundervariableconditionsa1dcnnwithtransferlearning
AT shivakumarraman multimodalbearingfaultclassificationundervariableconditionsa1dcnnwithtransferlearning