Fault Diagnosis Method of Plunger Pump Based on Meta-Learning and Improved Multi-Channel Convolutional Neural Network Under Small Sample Condition

A fault diagnosis method based on meta-learning and an improved multi-channel convolutional neural network (MAML-MCCNN-ISENet) was proposed to solve the problems of insufficient feature extraction and low fault type identification accuracy of vibration signals at small sample sizes. The signal is fi...

Full description

Saved in:
Bibliographic Details
Main Authors: Xiwang Yang, Jiancheng Ma, Hongjun Hu, Jinying Huang, Licheng Jing
Format: Article
Language:English
Published: MDPI AG 2025-07-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/25/15/4587
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849405928269414400
author Xiwang Yang
Jiancheng Ma
Hongjun Hu
Jinying Huang
Licheng Jing
author_facet Xiwang Yang
Jiancheng Ma
Hongjun Hu
Jinying Huang
Licheng Jing
author_sort Xiwang Yang
collection DOAJ
description A fault diagnosis method based on meta-learning and an improved multi-channel convolutional neural network (MAML-MCCNN-ISENet) was proposed to solve the problems of insufficient feature extraction and low fault type identification accuracy of vibration signals at small sample sizes. The signal is first preprocessed using adaptive chirp mode decomposition (ACMD) methods. A multi-channel input structure is then employed to process the multidimensional signal information after preprocessing. The improved squeeze and excitation networks (ISENets) have been enhanced to concurrently enhance the network’s adaptive perception of the significance of each channel feature. On this basis, a meta-learning strategy is introduced, the learning process of model initialization parameters is improved, the network is optimized by a multi-task learning mechanism, and the initial parameters of the diagnosis model are adaptively adjusted, so that the model can quickly adapt to new fault diagnosis tasks on limited datasets. Then, the overfitting problem under small sample conditions is alleviated, and the accuracy and robustness of fault identification are improved. Finally, the performance of the model is verified on the experimental data of the fault diagnosis of the laboratory plunger pump and the vibration dataset of the centrifugal pump of the Saint Longoval Institute of Engineering and Technology. The results show that the diagnostic accuracy of the proposed method for various diagnostic tasks can reach more than 90% on small samples.
format Article
id doaj-art-8cc0e4e5fe6b4a9bbf4618999ee96cab
institution Kabale University
issn 1424-8220
language English
publishDate 2025-07-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj-art-8cc0e4e5fe6b4a9bbf4618999ee96cab2025-08-20T03:36:33ZengMDPI AGSensors1424-82202025-07-012515458710.3390/s25154587Fault Diagnosis Method of Plunger Pump Based on Meta-Learning and Improved Multi-Channel Convolutional Neural Network Under Small Sample ConditionXiwang Yang0Jiancheng Ma1Hongjun Hu2Jinying Huang3Licheng Jing4School of Information and Communication Engineering, Shanxi University of Electronic Science and Technology, Linfen 041000, ChinaSchool of Computer Science and Technology, North University of China, Taiyuan 030051, ChinaSchool of Computer Science and Technology, North University of China, Taiyuan 030051, ChinaSchool of Computer Science and Technology, North University of China, Taiyuan 030051, ChinaSchool of Mechanical Engineering, North University of China, Taiyuan 030051, ChinaA fault diagnosis method based on meta-learning and an improved multi-channel convolutional neural network (MAML-MCCNN-ISENet) was proposed to solve the problems of insufficient feature extraction and low fault type identification accuracy of vibration signals at small sample sizes. The signal is first preprocessed using adaptive chirp mode decomposition (ACMD) methods. A multi-channel input structure is then employed to process the multidimensional signal information after preprocessing. The improved squeeze and excitation networks (ISENets) have been enhanced to concurrently enhance the network’s adaptive perception of the significance of each channel feature. On this basis, a meta-learning strategy is introduced, the learning process of model initialization parameters is improved, the network is optimized by a multi-task learning mechanism, and the initial parameters of the diagnosis model are adaptively adjusted, so that the model can quickly adapt to new fault diagnosis tasks on limited datasets. Then, the overfitting problem under small sample conditions is alleviated, and the accuracy and robustness of fault identification are improved. Finally, the performance of the model is verified on the experimental data of the fault diagnosis of the laboratory plunger pump and the vibration dataset of the centrifugal pump of the Saint Longoval Institute of Engineering and Technology. The results show that the diagnostic accuracy of the proposed method for various diagnostic tasks can reach more than 90% on small samples.https://www.mdpi.com/1424-8220/25/15/4587fault diagnosisplunger pumpsmall samplemeta-learning
spellingShingle Xiwang Yang
Jiancheng Ma
Hongjun Hu
Jinying Huang
Licheng Jing
Fault Diagnosis Method of Plunger Pump Based on Meta-Learning and Improved Multi-Channel Convolutional Neural Network Under Small Sample Condition
Sensors
fault diagnosis
plunger pump
small sample
meta-learning
title Fault Diagnosis Method of Plunger Pump Based on Meta-Learning and Improved Multi-Channel Convolutional Neural Network Under Small Sample Condition
title_full Fault Diagnosis Method of Plunger Pump Based on Meta-Learning and Improved Multi-Channel Convolutional Neural Network Under Small Sample Condition
title_fullStr Fault Diagnosis Method of Plunger Pump Based on Meta-Learning and Improved Multi-Channel Convolutional Neural Network Under Small Sample Condition
title_full_unstemmed Fault Diagnosis Method of Plunger Pump Based on Meta-Learning and Improved Multi-Channel Convolutional Neural Network Under Small Sample Condition
title_short Fault Diagnosis Method of Plunger Pump Based on Meta-Learning and Improved Multi-Channel Convolutional Neural Network Under Small Sample Condition
title_sort fault diagnosis method of plunger pump based on meta learning and improved multi channel convolutional neural network under small sample condition
topic fault diagnosis
plunger pump
small sample
meta-learning
url https://www.mdpi.com/1424-8220/25/15/4587
work_keys_str_mv AT xiwangyang faultdiagnosismethodofplungerpumpbasedonmetalearningandimprovedmultichannelconvolutionalneuralnetworkundersmallsamplecondition
AT jianchengma faultdiagnosismethodofplungerpumpbasedonmetalearningandimprovedmultichannelconvolutionalneuralnetworkundersmallsamplecondition
AT hongjunhu faultdiagnosismethodofplungerpumpbasedonmetalearningandimprovedmultichannelconvolutionalneuralnetworkundersmallsamplecondition
AT jinyinghuang faultdiagnosismethodofplungerpumpbasedonmetalearningandimprovedmultichannelconvolutionalneuralnetworkundersmallsamplecondition
AT lichengjing faultdiagnosismethodofplungerpumpbasedonmetalearningandimprovedmultichannelconvolutionalneuralnetworkundersmallsamplecondition