CNN-Transformer-BiGRU: A Pump Fault Detection Model for Industrialized Recirculating Aquaculture Systems

Background: Modern aquaculture is increasingly adopting industrialized recirculating aquaculture systems, in which the stable operation of its circulating water pump is essential. Yet, given the complex working conditions, this pump is prone to malfunctioning, so its timely fault prediction and accu...

Full description

Saved in:
Bibliographic Details
Main Authors: Wei Shao, Chengquan Zhou, Dawei Sun, Chen Li, Hongbao Ye
Format: Article
Language:English
Published: MDPI AG 2025-05-01
Series:Applied Sciences
Subjects:
Online Access:https://www.mdpi.com/2076-3417/15/11/6114
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849330605542604800
author Wei Shao
Chengquan Zhou
Dawei Sun
Chen Li
Hongbao Ye
author_facet Wei Shao
Chengquan Zhou
Dawei Sun
Chen Li
Hongbao Ye
author_sort Wei Shao
collection DOAJ
description Background: Modern aquaculture is increasingly adopting industrialized recirculating aquaculture systems, in which the stable operation of its circulating water pump is essential. Yet, given the complex working conditions, this pump is prone to malfunctioning, so its timely fault prediction and accurate diagnosis are imperative. Traditional fault detection methods rely on manual feature extraction, limiting their ability to identify complex faults, and deep learning methods suffer from unstable recognition accuracy. To address these issues, a three-class fault detection method for water pumps based on a convolutional neural network, transformer, and bidirectional gated recurrent unit (CNN-transformer-BiGRU) is proposed here. Methods: It first uses the continuous wavelet transform to convert one-dimensional vibration signals into time–frequency images for input into a CNN to extract the time-domain and frequency-domain features. Next, the transformer enhances the model’s hierarchical learning ability. Finally, the BiGRU captures the forward/backward feature information in the signal sequence. Results: The experimental results show that this method’s accuracy in fault detection is 91.43%, significantly outperforming traditional machine learning models. Using it improved the accuracy, precision, and recall by 1.86%, 1.97%, and 1.86%, respectively, relative to the convolutional neural network and long short-term memory (CNN-LSTM) model. Conclusions: Hence, the proposed model has superior performance indicators. Applying it to aquaculture systems can effectively ensure their stable operation.
format Article
id doaj-art-c4d0cd05e7f44637a2b69caf11472ebb
institution Kabale University
issn 2076-3417
language English
publishDate 2025-05-01
publisher MDPI AG
record_format Article
series Applied Sciences
spelling doaj-art-c4d0cd05e7f44637a2b69caf11472ebb2025-08-20T03:46:52ZengMDPI AGApplied Sciences2076-34172025-05-011511611410.3390/app15116114CNN-Transformer-BiGRU: A Pump Fault Detection Model for Industrialized Recirculating Aquaculture SystemsWei Shao0Chengquan Zhou1Dawei Sun2Chen Li3Hongbao Ye4College of Mathematics and Computer Science, Zhejiang A&F University, 666 Wusu Street, Hangzhou 311300, ChinaAgricultural Equipment Research Institute, Zhejiang Academy of Agricultural Sciences, 298 Desheng Middle Road, Hangzhou 310021, ChinaAgricultural Equipment Research Institute, Zhejiang Academy of Agricultural Sciences, 298 Desheng Middle Road, Hangzhou 310021, ChinaAgricultural Equipment Research Institute, Zhejiang Academy of Agricultural Sciences, 298 Desheng Middle Road, Hangzhou 310021, ChinaAgricultural Equipment Research Institute, Zhejiang Academy of Agricultural Sciences, 298 Desheng Middle Road, Hangzhou 310021, ChinaBackground: Modern aquaculture is increasingly adopting industrialized recirculating aquaculture systems, in which the stable operation of its circulating water pump is essential. Yet, given the complex working conditions, this pump is prone to malfunctioning, so its timely fault prediction and accurate diagnosis are imperative. Traditional fault detection methods rely on manual feature extraction, limiting their ability to identify complex faults, and deep learning methods suffer from unstable recognition accuracy. To address these issues, a three-class fault detection method for water pumps based on a convolutional neural network, transformer, and bidirectional gated recurrent unit (CNN-transformer-BiGRU) is proposed here. Methods: It first uses the continuous wavelet transform to convert one-dimensional vibration signals into time–frequency images for input into a CNN to extract the time-domain and frequency-domain features. Next, the transformer enhances the model’s hierarchical learning ability. Finally, the BiGRU captures the forward/backward feature information in the signal sequence. Results: The experimental results show that this method’s accuracy in fault detection is 91.43%, significantly outperforming traditional machine learning models. Using it improved the accuracy, precision, and recall by 1.86%, 1.97%, and 1.86%, respectively, relative to the convolutional neural network and long short-term memory (CNN-LSTM) model. Conclusions: Hence, the proposed model has superior performance indicators. Applying it to aquaculture systems can effectively ensure their stable operation.https://www.mdpi.com/2076-3417/15/11/6114aquacultureBiGRUconvolutional neural network (CNN)fault detectiontransformer
spellingShingle Wei Shao
Chengquan Zhou
Dawei Sun
Chen Li
Hongbao Ye
CNN-Transformer-BiGRU: A Pump Fault Detection Model for Industrialized Recirculating Aquaculture Systems
Applied Sciences
aquaculture
BiGRU
convolutional neural network (CNN)
fault detection
transformer
title CNN-Transformer-BiGRU: A Pump Fault Detection Model for Industrialized Recirculating Aquaculture Systems
title_full CNN-Transformer-BiGRU: A Pump Fault Detection Model for Industrialized Recirculating Aquaculture Systems
title_fullStr CNN-Transformer-BiGRU: A Pump Fault Detection Model for Industrialized Recirculating Aquaculture Systems
title_full_unstemmed CNN-Transformer-BiGRU: A Pump Fault Detection Model for Industrialized Recirculating Aquaculture Systems
title_short CNN-Transformer-BiGRU: A Pump Fault Detection Model for Industrialized Recirculating Aquaculture Systems
title_sort cnn transformer bigru a pump fault detection model for industrialized recirculating aquaculture systems
topic aquaculture
BiGRU
convolutional neural network (CNN)
fault detection
transformer
url https://www.mdpi.com/2076-3417/15/11/6114
work_keys_str_mv AT weishao cnntransformerbigruapumpfaultdetectionmodelforindustrializedrecirculatingaquaculturesystems
AT chengquanzhou cnntransformerbigruapumpfaultdetectionmodelforindustrializedrecirculatingaquaculturesystems
AT daweisun cnntransformerbigruapumpfaultdetectionmodelforindustrializedrecirculatingaquaculturesystems
AT chenli cnntransformerbigruapumpfaultdetectionmodelforindustrializedrecirculatingaquaculturesystems
AT hongbaoye cnntransformerbigruapumpfaultdetectionmodelforindustrializedrecirculatingaquaculturesystems