Prediction of Truck Fuel Consumption Based on Crossformer-LSTM Characteristic Distillation
With the increasing number of heavy-duty trucks and their high fuel consumption characteristics, reducing fuel costs has become a primary challenge for the freight industry. Consequently, accurately predicting fuel consumption for heavy-duty trucks is crucial. However, existing fuel consumption pred...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-12-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/15/1/283 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841549406959042560 |
|---|---|
| author | Kai Du Qingqing Shi Jingni Song Dan Chen Weiyu Liu |
| author_facet | Kai Du Qingqing Shi Jingni Song Dan Chen Weiyu Liu |
| author_sort | Kai Du |
| collection | DOAJ |
| description | With the increasing number of heavy-duty trucks and their high fuel consumption characteristics, reducing fuel costs has become a primary challenge for the freight industry. Consequently, accurately predicting fuel consumption for heavy-duty trucks is crucial. However, existing fuel consumption prediction models still face challenges in terms of prediction accuracy. To address this issue, a model named Cross-LSTM Multi-Feature Distillation (CLMFD) is proposed. The CLMFD model employs the Crossformer model and the LSTM model as teacher and student models, respectively, utilizing multi-layer intermediate features for distillation. Fuel consumption data from a vehicular networking system was used in this study. Initially, the raw data were preprocessed by segmenting it into two-kilometer intervals, calculating sample features, and handling outliers using box plots. Feature selection was then performed using XGBoost. Subsequently, the CLMFD model was applied to predict fuel consumption. Experimental results demonstrate that the CLMFD model significantly outperforms baseline models in prediction performance. Ablation studies further indicate that the CLMFD model effectively integrates the strengths of both the Crossformer and LSTM, exhibiting superior predictive performance. Finally, predictions on data with varying masking rates show that the CLMFD model demonstrates robust performance. These findings validate the reliability and practicality of the CLMFD model, providing strong support for future research in fuel consumption prediction. |
| format | Article |
| id | doaj-art-5fb77fbcb91b43b9a2076b31acf70318 |
| institution | Kabale University |
| issn | 2076-3417 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj-art-5fb77fbcb91b43b9a2076b31acf703182025-01-10T13:15:01ZengMDPI AGApplied Sciences2076-34172024-12-0115128310.3390/app15010283Prediction of Truck Fuel Consumption Based on Crossformer-LSTM Characteristic DistillationKai Du0Qingqing Shi1Jingni Song2Dan Chen3Weiyu Liu4Electronic and Control Engineering, Chang’an University, Xi’an 710064, ChinaCollege of Transportation Engineering, Chang’an University, Xi’an 710064, ChinaCollege of Transportation Engineering, Chang’an University, Xi’an 710064, ChinaElectronic and Control Engineering, Chang’an University, Xi’an 710064, ChinaElectronic and Control Engineering, Chang’an University, Xi’an 710064, ChinaWith the increasing number of heavy-duty trucks and their high fuel consumption characteristics, reducing fuel costs has become a primary challenge for the freight industry. Consequently, accurately predicting fuel consumption for heavy-duty trucks is crucial. However, existing fuel consumption prediction models still face challenges in terms of prediction accuracy. To address this issue, a model named Cross-LSTM Multi-Feature Distillation (CLMFD) is proposed. The CLMFD model employs the Crossformer model and the LSTM model as teacher and student models, respectively, utilizing multi-layer intermediate features for distillation. Fuel consumption data from a vehicular networking system was used in this study. Initially, the raw data were preprocessed by segmenting it into two-kilometer intervals, calculating sample features, and handling outliers using box plots. Feature selection was then performed using XGBoost. Subsequently, the CLMFD model was applied to predict fuel consumption. Experimental results demonstrate that the CLMFD model significantly outperforms baseline models in prediction performance. Ablation studies further indicate that the CLMFD model effectively integrates the strengths of both the Crossformer and LSTM, exhibiting superior predictive performance. Finally, predictions on data with varying masking rates show that the CLMFD model demonstrates robust performance. These findings validate the reliability and practicality of the CLMFD model, providing strong support for future research in fuel consumption prediction.https://www.mdpi.com/2076-3417/15/1/283fuel consumption forecastvehicle networking datafeature selectioncross-LSTM multi-feature distillation |
| spellingShingle | Kai Du Qingqing Shi Jingni Song Dan Chen Weiyu Liu Prediction of Truck Fuel Consumption Based on Crossformer-LSTM Characteristic Distillation Applied Sciences fuel consumption forecast vehicle networking data feature selection cross-LSTM multi-feature distillation |
| title | Prediction of Truck Fuel Consumption Based on Crossformer-LSTM Characteristic Distillation |
| title_full | Prediction of Truck Fuel Consumption Based on Crossformer-LSTM Characteristic Distillation |
| title_fullStr | Prediction of Truck Fuel Consumption Based on Crossformer-LSTM Characteristic Distillation |
| title_full_unstemmed | Prediction of Truck Fuel Consumption Based on Crossformer-LSTM Characteristic Distillation |
| title_short | Prediction of Truck Fuel Consumption Based on Crossformer-LSTM Characteristic Distillation |
| title_sort | prediction of truck fuel consumption based on crossformer lstm characteristic distillation |
| topic | fuel consumption forecast vehicle networking data feature selection cross-LSTM multi-feature distillation |
| url | https://www.mdpi.com/2076-3417/15/1/283 |
| work_keys_str_mv | AT kaidu predictionoftruckfuelconsumptionbasedoncrossformerlstmcharacteristicdistillation AT qingqingshi predictionoftruckfuelconsumptionbasedoncrossformerlstmcharacteristicdistillation AT jingnisong predictionoftruckfuelconsumptionbasedoncrossformerlstmcharacteristicdistillation AT danchen predictionoftruckfuelconsumptionbasedoncrossformerlstmcharacteristicdistillation AT weiyuliu predictionoftruckfuelconsumptionbasedoncrossformerlstmcharacteristicdistillation |