Slipping Trend Prediction Based on Improved Informer

During locomotive operation, large amounts of operation data are recorded by the TCU (Traction Control Unit). The prediction and detection of slipping through the analysis of large amounts of data are of great significance for energy saving and locomotive operation safety. The TCU records time serie...

Full description

Saved in:
Bibliographic Details
Main Authors: Jingchun Huang, Sheng He, Haoxiang Feng, Yongjiang Yu
Format: Article
Language:English
Published: MDPI AG 2025-04-01
Series:Applied Sciences
Subjects:
Online Access:https://www.mdpi.com/2076-3417/15/8/4112
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850144726041231360
author Jingchun Huang
Sheng He
Haoxiang Feng
Yongjiang Yu
author_facet Jingchun Huang
Sheng He
Haoxiang Feng
Yongjiang Yu
author_sort Jingchun Huang
collection DOAJ
description During locomotive operation, large amounts of operation data are recorded by the TCU (Traction Control Unit). The prediction and detection of slipping through the analysis of large amounts of data are of great significance for energy saving and locomotive operation safety. The TCU records time series data with a step length of 1 s. The transformer-based Informer algorithm performs well in time series prediction and analysis. Based on the improved Informer algorithm, this paper proposes a slip trend prediction method, which can predict the slipping state of n time steps according to the data of the previous seconds. By adding the improved prediction model of Informer to the classification model, this study, rather than adding a classification branch to the prediction model, directly improves the output structure, so as to realize long-sequence prediction with a multi-classification model. The model can effectively extract the important features in the data, and can realize multi-axle synchronous prediction and output the slipping state in parallel over the next few seconds. The comprehensive accuracy of this model in multi-axle synchronous prediction tasks can reach 94.75%. Finally, the model is analyzed according to the predicted results, and the effects of different models are compared. The attention mechanism and experimental data are analyzed by visualization.
format Article
id doaj-art-a3afb2f8e14748abba5368aec97de188
institution OA Journals
issn 2076-3417
language English
publishDate 2025-04-01
publisher MDPI AG
record_format Article
series Applied Sciences
spelling doaj-art-a3afb2f8e14748abba5368aec97de1882025-08-20T02:28:16ZengMDPI AGApplied Sciences2076-34172025-04-01158411210.3390/app15084112Slipping Trend Prediction Based on Improved InformerJingchun Huang0Sheng He1Haoxiang Feng2Yongjiang Yu3School of Electrical Engineering, Southwest Jiaotong University, Chengdu 610097, ChinaSchool of Electrical Engineering, Southwest Jiaotong University, Chengdu 610097, ChinaSchool of Electrical Engineering, Southwest Jiaotong University, Chengdu 610097, ChinaSchool of Electrical Engineering, Southwest Jiaotong University, Chengdu 610097, ChinaDuring locomotive operation, large amounts of operation data are recorded by the TCU (Traction Control Unit). The prediction and detection of slipping through the analysis of large amounts of data are of great significance for energy saving and locomotive operation safety. The TCU records time series data with a step length of 1 s. The transformer-based Informer algorithm performs well in time series prediction and analysis. Based on the improved Informer algorithm, this paper proposes a slip trend prediction method, which can predict the slipping state of n time steps according to the data of the previous seconds. By adding the improved prediction model of Informer to the classification model, this study, rather than adding a classification branch to the prediction model, directly improves the output structure, so as to realize long-sequence prediction with a multi-classification model. The model can effectively extract the important features in the data, and can realize multi-axle synchronous prediction and output the slipping state in parallel over the next few seconds. The comprehensive accuracy of this model in multi-axle synchronous prediction tasks can reach 94.75%. Finally, the model is analyzed according to the predicted results, and the effects of different models are compared. The attention mechanism and experimental data are analyzed by visualization.https://www.mdpi.com/2076-3417/15/8/4112informertransformerdata analysistime series predictionmulti-axle parallel prediction
spellingShingle Jingchun Huang
Sheng He
Haoxiang Feng
Yongjiang Yu
Slipping Trend Prediction Based on Improved Informer
Applied Sciences
informer
transformer
data analysis
time series prediction
multi-axle parallel prediction
title Slipping Trend Prediction Based on Improved Informer
title_full Slipping Trend Prediction Based on Improved Informer
title_fullStr Slipping Trend Prediction Based on Improved Informer
title_full_unstemmed Slipping Trend Prediction Based on Improved Informer
title_short Slipping Trend Prediction Based on Improved Informer
title_sort slipping trend prediction based on improved informer
topic informer
transformer
data analysis
time series prediction
multi-axle parallel prediction
url https://www.mdpi.com/2076-3417/15/8/4112
work_keys_str_mv AT jingchunhuang slippingtrendpredictionbasedonimprovedinformer
AT shenghe slippingtrendpredictionbasedonimprovedinformer
AT haoxiangfeng slippingtrendpredictionbasedonimprovedinformer
AT yongjiangyu slippingtrendpredictionbasedonimprovedinformer