A new energy automobile braking energy recovery optimization method comprises the following steps: 1) collecting continuous road driving data to form a corresponding driving data set; 2) dividing the driving data set into a plurality of working condition data sets; 3) extracting characteristic parameters of each working condition data set, and respectively calculating a proportion value of actual recovery energy and theoretical recovery energy in each working condition data set; 4) clustering each working condition data set by adopting a K-Means clustering algorithm; 5) classifying the clustered working condition data sets to obtain classified driving data sets; 6) dividing the classified driving data set into a training set and a test set; 7) training the SVM identifier by using the training set, and performing performance test on the trained SVM identifier by using the test set until the performance of the trained SVM identifier is the highest; and (8) the trained SVM recognizer serves as an energy recovery working condition classification model, the type of the current working condition is judged according to the real-time driving data, and energy recovery strategy optimization is achieved.
一种新能源汽车制动能量回收优化方法,包括以下步骤:1)采集连续道路行驶数据,形成对应的行驶数据集;2)将行驶数据集划分为若干个工况数据集;3)提取各工况数据集的特征参数,并分别计算各工况数据集中实际回收能量与理论回收能量的比例值;4)采用K‑Means聚类算法对每个工况数据集进行聚类;5)将聚类后的各工况数据集分类,得到分类后的行驶数据集;6)将分类后的行驶数据集划分为训练集、测试集;7)利用训练集对SVM识别器进行训练,并利用测试集对训练后的SVM识别器进行性能测试,直到训练后的SVM识别器性能最高;8)将训练后的SVM识别器作为能量回收工况分类模型,根据实时行驶数据对当前工况的类型进行判断,并实现能量回收策略优化。
New energy automobile braking energy recovery optimization method
一种新能源汽车制动能量回收优化方法
2024-05-28
Patent
Elektronische Ressource
Chinesisch
Electrically driven automobile braking energy recovery system
Europäisches Patentamt | 2015
|Automobile braking energy recovery power generation device
Europäisches Patentamt | 2023
|