基于非线性自回归神经网络的喷油器瞬态油量预测方法研究  

Based on Nonlinear Auto-regression Neural Network Prediction Method of Injector Transient Quantity

作　　者：冯源[1] 秦琳琳 陆娟[1] 

机构地区：[1]中国一汽无锡油泵油嘴研究所,江苏无锡214063

出　　处：《现代车用动力》2017年第4期15-18,31,共5页Modern Vehicle Power

摘　　要：为了预测喷油器在瞬态工况下的喷油量,结合ETC试验特点,提出了一种带外部输入的非线性自回归神经网络,该模型由于引入了多步输入输出时延,因而可反映系统的历史状态信息,可以很好的响应动态时变系统特性,从而能够更有效地实现复杂动态系统建模。本文将轨道压力、喷射脉宽作为模型外部输入,且对喷油器喷射油量进行时延反馈,并针对延迟阶数和隐层节点数进行了优选对比,根据专家经验和对比结果,选择合适的模型参数值,进而建立喷油器瞬态油量的预测模型。最后预测结果表明,该方法可以较好的预测瞬态油量,为今后研究发动机油量预测控制,改善发动机各缸均匀性提供可靠的应用基础。In order to predict the injector fuel quantity under transient operating conditions,considering the characteristics of engine transient test,a nonlinear autoregressive with external input of neural network is introduced. Due to the introduction of multistep inputs and outputs delay,the model can reflect the history of system state information. It can respond to the dynamictime-varying system,so as to realize the modeling of complex dynamic system more effectively. This paper takes the rail pressure and injection pulse width as external input of the model which combined with time delay feedback of injector quantity. According to the experience of experts and the results of comparison,the appropriate parameters of the model are selected. Then the prediction model of injector transient quantity is established. Finally,the result shows that the method can well predict the injection quantity. It provides a reliable basis for the study of engine fuel quantity feedback control and the improvement of the cylinder homogeneity.

关 键 词：柴油机 喷油器 非线性自回归 瞬态油量 预测方法 

分 类 号：TK423.8[动力工程及工程热物理—动力机械及工程]