A New Incremental Learning Method Based on Rainbow Memory for Fault Diagnosis of AUV

Autonomous Underwater Vehicles (AUVs) are gradually becoming some of the most important equipment in deep-sea exploration. However, in the dynamic nature of the deep-sea environment, any unplanned fault of AUVs would cause serious accidents. Traditional fault diagnosis models are trained in static a...

Full description

Saved in:
Bibliographic Details
Main Authors: Ying Li, Yuxing Ye, Zhiwei Zhang, Long Wen
Format: Article
Language:English
Published: MDPI AG 2025-07-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/25/15/4539
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849406478888206336
author Ying Li
Yuxing Ye
Zhiwei Zhang
Long Wen
author_facet Ying Li
Yuxing Ye
Zhiwei Zhang
Long Wen
author_sort Ying Li
collection DOAJ
description Autonomous Underwater Vehicles (AUVs) are gradually becoming some of the most important equipment in deep-sea exploration. However, in the dynamic nature of the deep-sea environment, any unplanned fault of AUVs would cause serious accidents. Traditional fault diagnosis models are trained in static and fixed datasets, making them difficult to adopt in new and unknown deep-sea environments. To address these issues, this study explores incremental learning to enable AUVs to continuously adapt to new fault scenarios while preserving previously learned diagnostic knowledge, named the RM-MFKAN model. First, the approach begins by employing the Rainbow Memory (RM) framework to analyze data characteristics and temporal sequences, thereby delineating boundaries between old and new tasks. Second, the model evaluates data importance to select and store key samples encapsulating critical information from prior tasks. Third, the RM is combined with the enhanced KAN network, and the stored samples are then combined with new task training data and fed into a multi-branch feature fusion neural network. The proposed RM-MFKAN model was conducted on the “Haizhe” dataset, and the experimental results have demonstrated that the proposed model achieves superior performance in fault diagnosis for AUVs.
format Article
id doaj-art-4153a8c603414b2390dfa9ed0db1d06c
institution Kabale University
issn 1424-8220
language English
publishDate 2025-07-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj-art-4153a8c603414b2390dfa9ed0db1d06c2025-08-20T03:36:22ZengMDPI AGSensors1424-82202025-07-012515453910.3390/s25154539A New Incremental Learning Method Based on Rainbow Memory for Fault Diagnosis of AUVYing Li0Yuxing Ye1Zhiwei Zhang2Long Wen3College of Power Engineering, Naval University of Engineering, No.177 Jiefang Road, Wuhan 430033, ChinaSchool of Mechanical Engineering and Electronic Information, China University of Geosciences, No. 388 Lumo Road, Wuhan 430074, ChinaSchool of Mechanical Engineering and Electronic Information, China University of Geosciences, No. 388 Lumo Road, Wuhan 430074, ChinaCollege of Power Engineering, Naval University of Engineering, No.177 Jiefang Road, Wuhan 430033, ChinaAutonomous Underwater Vehicles (AUVs) are gradually becoming some of the most important equipment in deep-sea exploration. However, in the dynamic nature of the deep-sea environment, any unplanned fault of AUVs would cause serious accidents. Traditional fault diagnosis models are trained in static and fixed datasets, making them difficult to adopt in new and unknown deep-sea environments. To address these issues, this study explores incremental learning to enable AUVs to continuously adapt to new fault scenarios while preserving previously learned diagnostic knowledge, named the RM-MFKAN model. First, the approach begins by employing the Rainbow Memory (RM) framework to analyze data characteristics and temporal sequences, thereby delineating boundaries between old and new tasks. Second, the model evaluates data importance to select and store key samples encapsulating critical information from prior tasks. Third, the RM is combined with the enhanced KAN network, and the stored samples are then combined with new task training data and fed into a multi-branch feature fusion neural network. The proposed RM-MFKAN model was conducted on the “Haizhe” dataset, and the experimental results have demonstrated that the proposed model achieves superior performance in fault diagnosis for AUVs.https://www.mdpi.com/1424-8220/25/15/4539intelligent fault diagnosisincremental learningrainbow memorydeep learning
spellingShingle Ying Li
Yuxing Ye
Zhiwei Zhang
Long Wen
A New Incremental Learning Method Based on Rainbow Memory for Fault Diagnosis of AUV
Sensors
intelligent fault diagnosis
incremental learning
rainbow memory
deep learning
title A New Incremental Learning Method Based on Rainbow Memory for Fault Diagnosis of AUV
title_full A New Incremental Learning Method Based on Rainbow Memory for Fault Diagnosis of AUV
title_fullStr A New Incremental Learning Method Based on Rainbow Memory for Fault Diagnosis of AUV
title_full_unstemmed A New Incremental Learning Method Based on Rainbow Memory for Fault Diagnosis of AUV
title_short A New Incremental Learning Method Based on Rainbow Memory for Fault Diagnosis of AUV
title_sort new incremental learning method based on rainbow memory for fault diagnosis of auv
topic intelligent fault diagnosis
incremental learning
rainbow memory
deep learning
url https://www.mdpi.com/1424-8220/25/15/4539
work_keys_str_mv AT yingli anewincrementallearningmethodbasedonrainbowmemoryforfaultdiagnosisofauv
AT yuxingye anewincrementallearningmethodbasedonrainbowmemoryforfaultdiagnosisofauv
AT zhiweizhang anewincrementallearningmethodbasedonrainbowmemoryforfaultdiagnosisofauv
AT longwen anewincrementallearningmethodbasedonrainbowmemoryforfaultdiagnosisofauv
AT yingli newincrementallearningmethodbasedonrainbowmemoryforfaultdiagnosisofauv
AT yuxingye newincrementallearningmethodbasedonrainbowmemoryforfaultdiagnosisofauv
AT zhiweizhang newincrementallearningmethodbasedonrainbowmemoryforfaultdiagnosisofauv
AT longwen newincrementallearningmethodbasedonrainbowmemoryforfaultdiagnosisofauv