Prediction model for oil seal performance parameters based on PSO-MLP-KAN

Oil seals are critical sealing components in mechanical systems, and their sealing performance directly impacts the operational reliability of the entire system. To accurately, efficiently, and stably predict the sealing performance of oil seals, this study proposes a prediction method based on a co...

Full description

Saved in:
Bibliographic Details
Main Authors: Weixing Yan, Mingshuo Shi, Pengbo Xiao, Kui Zhang, Xin Wu
Format: Article
Language:English
Published: AIP Publishing LLC 2025-05-01
Series:AIP Advances
Online Access:http://dx.doi.org/10.1063/5.0255178
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850209034925244416
author Weixing Yan
Mingshuo Shi
Pengbo Xiao
Kui Zhang
Xin Wu
author_facet Weixing Yan
Mingshuo Shi
Pengbo Xiao
Kui Zhang
Xin Wu
author_sort Weixing Yan
collection DOAJ
description Oil seals are critical sealing components in mechanical systems, and their sealing performance directly impacts the operational reliability of the entire system. To accurately, efficiently, and stably predict the sealing performance of oil seals, this study proposes a prediction method based on a combination of the Kolmogorov–Arnold network (KAN) and multi-layer perceptron (MLP) optimized by particle swarm optimization (PSO) algorithm. First, an oil seal performance prediction model is developed, taking into account macroscopic contact forces and contact curve parameters. To address the challenges posed by incomplete experimental data and limited data quantity, a hybrid approach integrating simulation data and experimental data is employed, complemented by the use of the Latin hypercube sampling method to construct an oil seal performance dataset. To further enhance model prediction accuracy, a PSO-MPL-KAN multi-output prediction model is established. Comparative analysis with existing prediction models demonstrates that the proposed PSO-MPL-KAN model achieves significantly higher accuracy in predicting oil seal sealing performance.
format Article
id doaj-art-8a0ece6479a144e98fb6589d4e415a3a
institution OA Journals
issn 2158-3226
language English
publishDate 2025-05-01
publisher AIP Publishing LLC
record_format Article
series AIP Advances
spelling doaj-art-8a0ece6479a144e98fb6589d4e415a3a2025-08-20T02:10:07ZengAIP Publishing LLCAIP Advances2158-32262025-05-01155055102055102-1210.1063/5.0255178Prediction model for oil seal performance parameters based on PSO-MLP-KANWeixing Yan0Mingshuo Shi1Pengbo Xiao2Kui Zhang3Xin Wu4School of Mechanical Engineering, Hangzhou Dianzi University, Hangzhou 310018, ChinaZhejiang Gunai Rubber and Plastic Science and Technology Co., Ltd., Huzhou 313000, ChinaSchool of Mechanical Engineering, Hangzhou Dianzi University, Hangzhou 310018, ChinaSchool of Mechanical Engineering, Hangzhou Dianzi University, Hangzhou 310018, ChinaSchool of Mechanical Engineering, Hangzhou Dianzi University, Hangzhou 310018, ChinaOil seals are critical sealing components in mechanical systems, and their sealing performance directly impacts the operational reliability of the entire system. To accurately, efficiently, and stably predict the sealing performance of oil seals, this study proposes a prediction method based on a combination of the Kolmogorov–Arnold network (KAN) and multi-layer perceptron (MLP) optimized by particle swarm optimization (PSO) algorithm. First, an oil seal performance prediction model is developed, taking into account macroscopic contact forces and contact curve parameters. To address the challenges posed by incomplete experimental data and limited data quantity, a hybrid approach integrating simulation data and experimental data is employed, complemented by the use of the Latin hypercube sampling method to construct an oil seal performance dataset. To further enhance model prediction accuracy, a PSO-MPL-KAN multi-output prediction model is established. Comparative analysis with existing prediction models demonstrates that the proposed PSO-MPL-KAN model achieves significantly higher accuracy in predicting oil seal sealing performance.http://dx.doi.org/10.1063/5.0255178
spellingShingle Weixing Yan
Mingshuo Shi
Pengbo Xiao
Kui Zhang
Xin Wu
Prediction model for oil seal performance parameters based on PSO-MLP-KAN
AIP Advances
title Prediction model for oil seal performance parameters based on PSO-MLP-KAN
title_full Prediction model for oil seal performance parameters based on PSO-MLP-KAN
title_fullStr Prediction model for oil seal performance parameters based on PSO-MLP-KAN
title_full_unstemmed Prediction model for oil seal performance parameters based on PSO-MLP-KAN
title_short Prediction model for oil seal performance parameters based on PSO-MLP-KAN
title_sort prediction model for oil seal performance parameters based on pso mlp kan
url http://dx.doi.org/10.1063/5.0255178
work_keys_str_mv AT weixingyan predictionmodelforoilsealperformanceparametersbasedonpsomlpkan
AT mingshuoshi predictionmodelforoilsealperformanceparametersbasedonpsomlpkan
AT pengboxiao predictionmodelforoilsealperformanceparametersbasedonpsomlpkan
AT kuizhang predictionmodelforoilsealperformanceparametersbasedonpsomlpkan
AT xinwu predictionmodelforoilsealperformanceparametersbasedonpsomlpkan