The invention discloses a vehicle short-time domain working condition prediction method based on an optimized Markov prediction model, and belongs to the technical field of automobile control. According to the method, the training set is constructed by collecting the historical travel working condition data of the vehicle, the vehicle state parameters collected by the training set are used for completing the training of the state transition matrix, and the prediction model is built; an acceleration-impact degree state transition matrix is added into the model to improve the prediction precision of the vehicle speed and the acceleration; structural optimization is carried out on the state transition matrix to improve the solving speed of the algorithm, the storage state of the probability matrix is adjusted, and real-time calculation of the algorithm in the vehicle driving process is ensured.
本发明公开了一种基于优化后的马尔可夫预测模型的车辆短时域工况预测方法,属于汽车控制技术领域。本发明通过采集车辆历史出行工况数据进行训练集的构建,运用训练集采集到的车辆状态参数完成状态转移矩阵的训练并搭建预测模型;通过在模型中加入加速度—冲击度状态转移矩阵以提高车速及加速度的预测精度;通过对状态转移矩阵进行结构性优化以提升算法的求解速度,调整概率矩阵的储存状态、确保车辆行驶过程中算法的实时计算。
Vehicle short-time domain working condition prediction method based on optimized Markov prediction model
一种基于优化后的马尔可夫预测模型的车辆短时域工况预测方法
2024-12-13
Patent
Electronic Resource
Chinese
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 |
Electric bus energy consumption prediction method combined with Markov working condition prediction
European Patent Office | 2024
|European Patent Office | 2020
|Fuel cell vehicle energy management optimization method based on working condition prediction
European Patent Office | 2021
|Vehicle working condition prediction method and system based on Wiener random process
European Patent Office | 2020
|Prediction of Vehicle Motion Based on Markov Model
IEEE | 2017
|