基于工况识别与多元非线性回归优化的能量管理策略

为给混合动力汽车智能管理策略提供基础，开展了基于学习向量化(LVQ)神经网络的工况模式识别算法研究。选取4种典型微观道路类型工况和3类标准循环工况，提取11个参数为训练特征数据，建立了LVQ神经网络工况模式识别算法；在此基础上，以某款混联式动力系统为例，结合多元非线性回归分析制定相应控制策略；最后，基于Simulink仿真平台建立LVQ神经网络工况模式识别及整车仿真模型，分别采用中国城市典型循环工况以及构建UDDS+NYCC+UDDS的标准行驶工况进行道路工况识别验证。结果表明，所建立的LVQ神经网络工况识别算法可以准确识别工况模式并能有效提高能量管理策略的控制效果。

Energy Management Strategy Based on Type Recognition and Multivariate Nonlinear Regression Optimization

The type recognition algorithm of driving conditions was studied based on LVQ neural network，to provide the basis for the intelligent management strategy of hybrid electric vehicles. First, 11 characteristic parameters were extracted from 4 typical road type conditions and the 3 kinds of standard cycle conditions to train the data. Then, the LVQ neural network type recognition algorithm of driving condition was developed. Based on this, a hybrid power system was as an example, which combined with multiple nonlinear regression analysis to develop the corresponding control strategy. Finally, LVQ neural network type recognition simulation model of driving condition was established based on the Simulink simulation platform, type recognition tests were carried on under the Chinese city typical cycle road conditions, standard condition recognition tests were carried on by constructing UDDS+NYCC+UDDS driving conditions. The results show that the established LVQ neural network may accurately identify the type of driving condition types and the control effectiveness of the energy management strategy is improved effectively.