Prediction Optimization Study of Strapping Parameters for In-Vehicle Hydrogen Storage Cylinders under Random Vibration based on GA-XGBoost

In recent years, fuel cell vehicles have garnered increasing attention due to their zero emissions and zero pollution characteristics, and the application of in-vehicle hydrogen storage cylinders has become more and more common. During vehicle operation, factors such as uneven road surfaces and internal vibrations inevitably subject the in-vehicle hydrogen storage cylinders to vibrations. Consequently, it becomes imperative to conduct a mechanical analysis to assess their response to random vibration loads and subsequently optimize their structure. This article presents an approach to optimize the strapping parameters for in-vehicle hydrogen storage cylinders, utilizing the GA-XGBoost model. Ansys Workbench is employed to perform power spectral density-based random vibration analysis on in-vehicle high-pressure hydrogen storage cylinders (Type III) affixed with straps. A hundred sets of different strapping parameters (spacing, thickness, and width) were randomly generated The stress analysis of hydrogen storage cylinders under various strapping parameters was conducted, and an XGBoost model was established to predict the strapping parameters. The model achieved an R<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> of 0.945. Additionally, Genetic Algorithm was utilized to predict the optimal strapping parameters, aiming to minimize the stress of hydrogen storage cylinders. The findings reveal that for the Type III hydrogen storage cylinder examined, the optimal strapping parameters are as follows: spacing of 625 mm, thickness of 17 mm, and width of 58 mm, resulting in a stress value of 1920.49 Pa. Validation analysis of the model demonstrates a stress value of 1921.5 Pa, with a prediction error of 0.52%. This study offers theoretical underpinning for the PSD random vibration analysis and aids in the selection of strapping parameters for in-vehicle high-pressure hydrogen storage cylinders.

Authors

Institutions

Publication Details

Published
2024-08-23
DOI
https://doi.org/10.1109/ictle62418.2024.10703920
Citations
1
Primary Topic
Mechanical stress and fatigue analysis
Type
article
Field-Weighted Citation Impact
0.27

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Prediction Optimization Study of Strapping Parameters for In-Vehicle Hydrogen Storage Cylinders under Random Vibration based on GA-XGBoost

Junqi Yao, Yan Yin, Ting Guo, Zhikun Qin et al.
1 citations
Mechanical stress and fatigue analysis
0.27
article

Prediction Optimization Study of Strapping Parameters for In-Vehicle Hydrogen Storage Cylinders under Random Vibration based on GA-XGBoost

Junqi Yao, Yan Yin, Ting Guo, Zhikun Qin, Fan Zhang
article en
1 citations

Abstract

In recent years, fuel cell vehicles have garnered increasing attention due to their zero emissions and zero pollution characteristics, and the application of in-vehicle hydrogen storage cylinders has become more and more common. During vehicle operation, factors such as uneven road surfaces and internal vibrations inevitably subject the in-vehicle hydrogen storage cylinders to vibrations. Consequently, it becomes imperative to conduct a mechanical analysis to assess their response to random vibration loads and subsequently optimize their structure. This article presents an approach to optimize the strapping parameters for in-vehicle hydrogen storage cylinders, utilizing the GA-XGBoost model. Ansys Workbench is employed to perform power spectral density-based random vibration analysis on in-vehicle high-pressure hydrogen storage cylinders (Type III) affixed with straps. A hundred sets of different strapping parameters (spacing, thickness, and width) were randomly generated The stress analysis of hydrogen storage cylinders under various strapping parameters was conducted, and an XGBoost model was established to predict the strapping parameters. The model achieved an R<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> of 0.945. Additionally, Genetic Algorithm was utilized to predict the optimal strapping parameters, aiming to minimize the stress of hydrogen storage cylinders. The findings reveal that for the Type III hydrogen storage cylinder examined, the optimal strapping parameters are as follows: spacing of 625 mm, thickness of 17 mm, and width of 58 mm, resulting in a stress value of 1920.49 Pa. Validation analysis of the model demonstrates a stress value of 1921.5 Pa, with a prediction error of 0.52%. This study offers theoretical underpinning for the PSD random vibration analysis and aids in the selection of strapping parameters for in-vehicle high-pressure hydrogen storage cylinders.

Tianjin University (CN), China Automotive Technology and Research Center (CN)
Research and Development
Affordable and clean energy
Openalex Percentile: Top 50%
Mechanical stress and fatigue analysis
0.27
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.