欢迎访问《汽车安全与节能学报》，
汽车安全与节能学报

汽车安全与节能学报 ›› 2026, Vol. 17 ›› Issue (3): 351-358.DOI: 10.3969/j.issn.1674-8484.2026.03.007

• 汽车节能与环保 • 上一篇    下一篇

基于神经网络的高压缩比火花点火发动机爆震预测

张伟旋(), 马志寅, 傅锦泓, 李雪松, 许敏()   

  1. 上海交通大学 机械与动力工程学院， 上海 200240， 中国
  • 收稿日期:2025-12-31 修回日期:2026-03-03 出版日期:2026-06-30 发布日期:2026-07-02
  • 通讯作者: *许敏，教授。E-mail：mxu@sjtu.edu.cn。
  • 作者简介:张伟旋（1998—），男（汉），上海，博士研究生。E-mail：zwx13262290591@sjtu.edu.cn。
  • 基金资助:
    国家自然科学基金资助项目(E52276125);国家自然科学基金资助项目(E52006140)

Knock prediction of high-compression-ratio spark-ignition engine based on neural networks

ZHANG Weixuan(), MA Zhiyin, FU Jinhong, LI Xuesong, XU Min()   

  1. School of Mechanical Engineering, Shanghai Jiao Tong University, Shanghai 200240, China
  • Received:2025-12-31 Revised:2026-03-03 Online:2026-06-30 Published:2026-07-02

RichHTML

4

PDF

17

摘要：

为预测压缩比为14 的火花点火发动机的爆震，基于经标定的一维仿真模型与台架实验数据，提出了一种基于神经网络的爆震智能预测方法。构建并对比了2种由多层感知机构成的神经网络架构：端到端式与两阶段管道式。端到端式模型直接输入控制参数进行爆震预测，管道式模型基于“控制参数、燃烧状态、爆震预测”的显式物理推理链。并进行了台架实验验证。结果表明：管道式模型预测准确率98.6%，优于端到端模型的96.1%。对20个实际控制参数组的预测准确率达到100%。从而，本模型能够预测实际发动机的爆震事件，可望为发动机实时控制与性能优化提供解决方案。

关键词: 火花点火发动机, 爆震预测, 控制参数, 燃烧过程参数, 神经网络, 多层感知机

Abstract:

A neural-network-based intelligent knock prediction method was developed based on neural-network, by using a calibrated 1-dimension simulation model and engine test bench data, to predict knock in a spark-ignition (SI) engine with a compression ratio of 14. Two neural network architectures with multilayer perception were constructed and compared, including an end-to-end model and a two-stage pipeline model. The end-to-end model directly used control parameters for knock prediction. The pipeline model followed an explicit physical reasoning chain of “control parameters, combustion state, knock prediction”. Some validation tests were performed on an engine bench. The results show that the pipeline model achieves a prediction accuracy of 98.6%, which is superior to the end-to-end model's accuracy of 96.1%. The model achieves 100% prediction accuracy for 20 actual control parameter sets. Therefore, this model can predict knock events in real engines and will provide a solution for real-time engine control and performance optimization.

Key words: spark ignition (SI) engines, knock prediction, control parameters, combustion process parameters, neural networks, multilayer perceptron

中图分类号: