PEMFC RUL Prediction for Non-Stationary Time Series Based on Crossformer Model

Proton-Exchange Membrane Fuel Cells (PEMFCs), as efficient and environmentally friendly energy conversion devices, have wide application potential in areas such as transportation, mobile power, and distributed energy. However, the remaining useful life (RUL) issue of PEMFCs has been one of the main...

Full description

Saved in:
Bibliographic Details
Main Authors: Ning Zhou, He Zeng, Zefei Zheng, Ke Wang, Jianxin Zhou
Format: Article
Language:English
Published: MDPI AG 2025-02-01
Series:Applied Sciences
Subjects:
Online Access:https://www.mdpi.com/2076-3417/15/5/2515
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850050828156534784
author Ning Zhou
He Zeng
Zefei Zheng
Ke Wang
Jianxin Zhou
author_facet Ning Zhou
He Zeng
Zefei Zheng
Ke Wang
Jianxin Zhou
author_sort Ning Zhou
collection DOAJ
description Proton-Exchange Membrane Fuel Cells (PEMFCs), as efficient and environmentally friendly energy conversion devices, have wide application potential in areas such as transportation, mobile power, and distributed energy. However, the remaining useful life (RUL) issue of PEMFCs has been one of the main challenges limiting their commercialization. The RUL prediction problem of PEMFCs exhibits characteristics of time series forecasting, but its data possess multidimensional features and non-stationarity, which limits the applicability of classical time series forecasting models like the Transformer in solving the RUL prediction problem. In this paper, we propose a PEMFC RUL prediction model based on the Crossformer for non-stationary time series (De-stationary-Crossformer). Firstly, the overall architecture adopts the Crossformer model to extract dependencies between different features and temporal dependencies. Secondly, adaptive normalization is applied to the data to mitigate the non-stationarity in the original data, thereby increasing their predictability. Subsequently, a non-stationary attention mechanism is introduced in the model to simultaneously utilize the non-stationarity in the original data when extracting deep information. Additionally, manual features are introduced through mathematical statistics to enhance the predictive performance of the model. During the training process, the TILDE-Q loss function is used to focus on the similarity between the predicted sequence and the true sequence. The model proposed in this paper improves the MSE by 31% compared to the Transformer and 23% compared to the Crossformer in the experimental prediction of the RUL of PEMFCs in actual vehicles.
format Article
id doaj-art-a6dbc907194d4c819fb9d91c69175a97
institution DOAJ
issn 2076-3417
language English
publishDate 2025-02-01
publisher MDPI AG
record_format Article
series Applied Sciences
spelling doaj-art-a6dbc907194d4c819fb9d91c69175a972025-08-20T02:53:19ZengMDPI AGApplied Sciences2076-34172025-02-01155251510.3390/app15052515PEMFC RUL Prediction for Non-Stationary Time Series Based on Crossformer ModelNing Zhou0He Zeng1Zefei Zheng2Ke Wang3Jianxin Zhou4School of Information Engineering, Wuhan University of Technology, Wuhan 430070, ChinaSchool of Information Engineering, Wuhan University of Technology, Wuhan 430070, ChinaSchool of Information Engineering, Wuhan University of Technology, Wuhan 430070, ChinaSchool of Information Engineering, Wuhan Huaxia Institute of Technology, Wuhan 430223, ChinaSchool of Information Engineering, Wuhan University of Technology, Wuhan 430070, ChinaProton-Exchange Membrane Fuel Cells (PEMFCs), as efficient and environmentally friendly energy conversion devices, have wide application potential in areas such as transportation, mobile power, and distributed energy. However, the remaining useful life (RUL) issue of PEMFCs has been one of the main challenges limiting their commercialization. The RUL prediction problem of PEMFCs exhibits characteristics of time series forecasting, but its data possess multidimensional features and non-stationarity, which limits the applicability of classical time series forecasting models like the Transformer in solving the RUL prediction problem. In this paper, we propose a PEMFC RUL prediction model based on the Crossformer for non-stationary time series (De-stationary-Crossformer). Firstly, the overall architecture adopts the Crossformer model to extract dependencies between different features and temporal dependencies. Secondly, adaptive normalization is applied to the data to mitigate the non-stationarity in the original data, thereby increasing their predictability. Subsequently, a non-stationary attention mechanism is introduced in the model to simultaneously utilize the non-stationarity in the original data when extracting deep information. Additionally, manual features are introduced through mathematical statistics to enhance the predictive performance of the model. During the training process, the TILDE-Q loss function is used to focus on the similarity between the predicted sequence and the true sequence. The model proposed in this paper improves the MSE by 31% compared to the Transformer and 23% compared to the Crossformer in the experimental prediction of the RUL of PEMFCs in actual vehicles.https://www.mdpi.com/2076-3417/15/5/2515PEMFCRUL predictiontime series forecastingmultidimensional featuresnon-stationary
spellingShingle Ning Zhou
He Zeng
Zefei Zheng
Ke Wang
Jianxin Zhou
PEMFC RUL Prediction for Non-Stationary Time Series Based on Crossformer Model
Applied Sciences
PEMFC
RUL prediction
time series forecasting
multidimensional features
non-stationary
title PEMFC RUL Prediction for Non-Stationary Time Series Based on Crossformer Model
title_full PEMFC RUL Prediction for Non-Stationary Time Series Based on Crossformer Model
title_fullStr PEMFC RUL Prediction for Non-Stationary Time Series Based on Crossformer Model
title_full_unstemmed PEMFC RUL Prediction for Non-Stationary Time Series Based on Crossformer Model
title_short PEMFC RUL Prediction for Non-Stationary Time Series Based on Crossformer Model
title_sort pemfc rul prediction for non stationary time series based on crossformer model
topic PEMFC
RUL prediction
time series forecasting
multidimensional features
non-stationary
url https://www.mdpi.com/2076-3417/15/5/2515
work_keys_str_mv AT ningzhou pemfcrulpredictionfornonstationarytimeseriesbasedoncrossformermodel
AT hezeng pemfcrulpredictionfornonstationarytimeseriesbasedoncrossformermodel
AT zefeizheng pemfcrulpredictionfornonstationarytimeseriesbasedoncrossformermodel
AT kewang pemfcrulpredictionfornonstationarytimeseriesbasedoncrossformermodel
AT jianxinzhou pemfcrulpredictionfornonstationarytimeseriesbasedoncrossformermodel