基于改进组合核函数高斯过程回归的车速预测  

Vehicle Speed Prediction Based on Gaussian ProcessRegression with Improved Combination Kernel Function

作　　者：赵靖华[1,2] 闻龙 汪守丰 刘倩妤 周宇麒 刘妲 解方喜[2] ZHAO Jinghua;WEN Long;WANG Shoufeng;LIU Qianyu;ZHOU Yuqi;LIU Da;XIE Fangxi(College of Mathematics and Computer,Jilin Normal University,Siping 136000,Jilin Province,China;National Key Laboratory of Automotive,Chassis Integration and Bionics,Jilin University,Changchun 130025,China;Department of Technical Development,Qijing Machinery Co.,Ltd.,Ningbo 315000,Zhejiang Province,China)

机构地区：[1]吉林师范大学数学与计算机学院,吉林四平136000 [2]吉林大学汽车底盘集成与仿生全国重点实验室,长春130025 [3]奇精机械股份有限公司技术开发部,浙江宁波315000

出　　处：《吉林大学学报(理学版)》2025年第2期454-464,共11页Journal of Jilin University:Science Edition

基　　金：国家自然科学基金面上项目(批准号:61773009);吉林省科技发展计划项目(批准号:20240601034RC)。

摘　　要：基于高斯过程回归技术,提出一种新的实时车速预测方法,在准确有效预测前车速度的同时量化了预测的不确定性.该方法通过引入平方指数和Matern的组合核函数SEM,并改进组合核函数为SEM^(*),有效平衡了单一核函数对车速预测的优缺点,并在超参数寻优时采用了粒子群实时求解方法.瞬态工况下2 s时长车速预测的仿真分析表明:相比于单核性能较好的径向基(SE)核函数,SEM方法在车速FTP75工况下平均绝对误差(MAE)和均方根误差(RMSE)标准分别降低了10.09%和7.23%,而SEM^(*)方法在两个误差指标上相比SEM方法分别降低8.02%和8.13%;在城市典型工况下,SEM相比SE方法MAE和RMSE分别降低了3.44%和4.16%,而SEM^(*)在两个误差指标上相比SEM核函数分别降低3.57%和2.17%;同时SEM^(*)方法在FTP75工况单次最大计算时间上相对SE核函数降低0.3 s,城市典型工况付出的代价是相对SE核函数提高了0.015 s的最大计算时间,但计算时间仍在0.1 s采样时刻以内,具有实时性.We proposed a novel real-time vehicle speed prediction method based on Gaussian process regression(GPR)technology,which accurately and effectively predicted the velocity of the preceding vehicle while quantifying the uncertainty of the prediction.This method introduced a combination kernel function SEM of squared exponent(SE)and Matern,and improved the combination kernel function to SEM^(*).This effectively balanced the advantages and disadvantages of a single kernel function for vehicle speed prediction,and a particle swarm optimization method for real-time solution in hyperparameter optimization was adopted.The simulation analysis of 2 s vehicle speed prediction under transient operating conditions shows that under the FTP75 working condition,compared to the radial basis SE kernel function with better single kernel performance,the SEM method reduces the mean absolute error(MAE)and root mean square error(RMSE)standards by 10.09%and 7.23%respectively,while the SEM^(*)method reduces the two error indicators by 8.02%and 8.13%respectively compared to the SEM method.Under typical urban working conditions,the SEM reduces MAE and RMSE standards by 3.44%and 4.16%respectively compared to the SE method,while the SEM^(*)reduces the two error indicators by 3.57%and 2.17%respectively compared to the SEM method.At the same time,the SEM^(*)method reduces the maximum single calculation time relative to the SE method by 0.3 s under the FTP75 working condition,and the cost paid under typical urban conditions is an increase in the maximum single calculation time relative to the SE method by 0.015 s,but the calculation time is still within 0.1 s of the sampling time,which has real-time performance.

关 键 词：组合核函数 高斯过程 车速预测 

分 类 号：TP273[自动化与计算机技术—检测技术与自动化装置]