The invention discloses a vehicle load value estimation method based on a BP neural network, and the method comprises the steps: calculating the load value of a vehicle according to the characteristic parameters of the whole vehicle, correcting the related weight according to the estimated error, and finally accurately calculating the load of the vehicle through the corresponding weight and characteristic parameter data, the selection of the vehicle characteristic parameters and the structural design of the neural network are obtained through multiple times of training and testing results. The vehicle load is accurately calculated in real time, and a proper gear shifting strategy can be selected, so that the vehicle power is improved, the vehicle oil consumption is reduced, and the driving feeling of the whole vehicle can be effectively improved. According to the method, the defect of load calculation based on vehicle dynamics is overcome through the neural network algorithm, the BP network can learn and store a large number of input and output mode mapping relations, mathematical expressions of the mapping relations do not need to be revealed and described in advance, actual measurement verifies that the scheme is higher in calculation accuracy and small in influence of vehicle driving working conditions, and the method is suitable for large-scale popularization and application. And meanwhile, the estimation speed is also remarkably improved.
本发明公开了一种基于BP神经网络的车辆负载值估算方法,根据整车特征参数计算车辆的负载值,再根据估算的误差修正相关权值,最终通过相应的权值和特征参数数据可准确地计算出车辆负载,其中,车辆特征参数的选择和神经网络的结构设计是通过多次训练和测试结果得出的。对车辆负载的实时准确计算,能够选择合适的换挡策略,以此提升车辆动力,并降低车辆油耗,还能够有效提升整车驾乘感受。本发明通过神经网络算法弥补基于车辆动力学计算负载的不足,BP网络能学习和存贮大量的输入输出模式映射关系,而无需事前揭示描述这种映射关系的数学表达,经实测验证,本发明方案计算准确度更高,且受车辆行驶工况影响小,同时估算速度也有显著提升。
Vehicle load value estimation method based on BP neural network
基于BP神经网络的车辆负载值估算方法
2023-10-03
Patent
Elektronische Ressource
Chinesisch
IPC: | B60W CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION , Gemeinsame Steuerung oder Regelung von Fahrzeug-Unteraggregaten verschiedenen Typs oder verschiedener Funktion / G06N COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS , Rechnersysteme, basierend auf spezifischen Rechenmodellen |
Estimation of Extreme Value Vehicle Load Based on the Extended Burr XII Distribution
Online Contents | 2018
|Estimation of Extreme Value Vehicle Load Based on the Extended Burr XII Distribution
Springer Verlag | 2017
|Pure electric vehicle mass estimation method based on neural network
Europäisches Patentamt | 2022
|Estimation of Vehicle Centroid Side Angle Based on Neural Network
Springer Verlag | 2022
|