基于RLS和BO算法的重型车载重估算研究  

Research on Heavy-duty Vehicle Mass Estimation Based on Recursive Least Square and Bayesian Optimization Algorithm

作　　者：白晓鑫 吴春玲 景晓军 杨永真 BAI Xiaoxin;WU Chunling;JING Xiaojun;YANG Yongzhen(CATARC Automotive Test Center(Tianjin)Company Limited,Tianjin 300300,China;School of Mechanical Engineering,Tianjin University,Tianjin 300072,China)

机构地区：[1]中汽研汽车检验中心(天津)有限公司,天津300300 [2]天津大学机械工程学院,天津300072

出　　处：《汽车实用技术》2023年第5期56-63,共8页Automobile Applied Technology

基　　金：国家重点研发计划(2022YFC3703600)。

摘　　要：针对重型车实际使用过程中载重估算精度低、成本高等问题,提出基于递归最小二乘法(RLS)和贝叶斯优化(BO)算法的内燃机重型车辆载重估算方法。该方法提出了基于数据滤波的车辆加速度和道路坡度计算方法,使用控制器局域网络(CAN)总线和全球定位系统(GPS)高程数据,基于车辆纵向动力学和RLS进行重型车载重估算。采用BO算法对12组训练数据建模,对车辆载重估算模型中的多变量滤波参数进行寻优配置,并利用测试数据进行模型估算性能评价。结果表明,该方法具有良好的载重估算精度,估算误差在6%以内。In order to solve the problems of low accuracy and high cost of mass estimation in the actual use of heavy vehicles, a method of load estimation of heavy-duty vehicles with internal combustion engine based on recursive least squares(RLS) and bayesian optimization(BO)algorithm is proposed. In this method, a method for calculating vehicle acceleration and road slope based on data filtering is proposed. Controller area network(CAN) bus and global positioning system(GPS) elevation data are used to estimate heavy vehicle load based on vehicle longitudinal dynamics and RLS. The BO algorithm is used to model the 12 groups of training data, and the multivariable filtering parameters in the vehicle mass estimation model are optimized, and the test data are used to evaluate the model estimation performance. The results show that the method has good accuracy of load estimation, and the estimation error is less than 6%.

关 键 词：重型车 载重 估算 递归最小二乘法 贝叶斯优化算法 

分 类 号：U463.2[机械工程—车辆工程]