Page 68 - 《摩擦学学报》2021年第1期

第 41 卷 第 1 期 摩 擦 学 学 报 Vol 41 No 1
2021 年 1 月 Tribology Jan, 2021

DOI: 10.16078/j.tribology.2020027

基于SQPSO优化DELM的踏面磨耗测量模型

1,2*
1,2
1,2
1,2
1,2
王美琪 , 贾思贤 , 陈恩利 , 杨绍普 , 刘鹏飞 , 戚 壮 1,2
(1. 石家庄铁道大学 省部共建交通工程结构力学行为与系统安全国家重点实验室，河北 石家庄 050043;
2. 石家庄铁道大学 机械工程学院，河北 石家庄 050043)
摘 要: 针对难以建立轮轨磨耗的单一模型和无法对各种工况下车轮踏面磨耗进行定量计算的问题，提出一种基于
SQPSO优化DELM的踏面磨耗测量方法(SQPSO-DELM). 首先将衍生特性引入到极限学习机中，提出一种衍生极限
学习机模型(DELM). 然后引入序列二次规划(SQP)方法和量子粒子群优化(QPSO)算法，对DELM的参数进行优化.
通过SQPSO-DELM预测模型，对车辆动力学模型模拟不同试验参数下的车轮踏面最大磨耗量以及对现场列车踏面
磨耗程度的实际测量值进行训练和预测. 结果表明：SQPSO-DELM预测模型的性能参数指标均优于LSSVM、ELM、
PSO-ELM和QPSO-ELM，能较好地反映不同参数对车轮踏面磨耗值的影响规律.
关键词: 极限学习机; 量子粒子群优化算法; 车轮踏面磨耗; 模型辨识; 车辆动力学
中图分类号: TH117.1 文献标志码: A 文章编号: 1004-0595(2021)01–0065–11

Measurement Model of Tread Wear Based on SQPSO

Optimized DELM

1,2*
1,2
1,2
1,2
1,2
WANG Meiqi , JIA Sixian , CHEN Enli , YANG Shaopu , LIU Pengfei , QI Zhuang 1,2
(1. State Key Laboratory of Structural Mechanics Behavior and System Safety of Traffic Engineering Jointly
Established by the Ministry of Transport, Shijiazhuang Tiedao University, Hebei Shijiazhuang 050043, China
2. School of Mechanical Engineering, Shijiazhuang Tiedao University, Hebei Shijiazhuang 050043, China)
Abstract: In view of the difficulty in establishing accurate mathematical model of wheel rail wear and in evaluating,
predicting and quantitatively calculating wheel rail wear under various working conditions, this paper proposed a tread
wear prediction method based on SQPSO optimized DELM model(SQPSO-DELM). First of all, the derivative
characteristics were introduced into the learning machine, and a derivative learning machine model (DELM) was
proposed. Then, the sequential quadratic programming (SQP) and quantum particle swarm optimization (QPSO)
algorithm were introduced to optimize the parameters of DELM. Through SQPSO-DELM prediction model, the
maximum wear of wheel tread under different test parameters of vehicle dynamics model simulation and the actual
measured value of wear degree of on-site train tread were trained and predicted. The results showed that the performance
parameters of SQPSO-DELM prediction model were better than LSSVM, ELM, PSO-ELM and QPSO-ELM, which can
better reflect the influence of different parameters on wheel tread wear value.
Key words: extreme learning machine; quantum particle swarm optimization algorithm; wheel tread wear; model
identification; vehicle dynamics

Received 17 February 2020, revised 29 May 2020, accepted 9 June 2020, available online 28 January 2021.
*Corresponding author. E-mail: chenenl@stdu.edu.cn, Tel: +86-13223435755.
This project was supported by the National Natural Science Foundation of China (11790282,11702179), Young Top-Notch Talents
Program of Higher School in Hebei Province (BJ2019035), Natural Science Foundation of Hebei Province(E2018210052) and
Postgraduate innovation funding project of Shijiazhuang Tiedao University(YC2020030).
国家自然科学基金项目(11790282,11702179)，河北省高等学校科学技术研究青年拔尖人才项目(BJ2019035)，河北省自然科学
基金(E2018210052)和石家庄铁道大学研究生创新项目(YC2020030) 资助.