基于神经网络的双燃料发动机活塞最高温度预测

Prediction of maximum temperature of piston in dual fuel engine based on neural network

由硬度塞测法和ANSYS有限元软件建立双燃料发动机活塞的温度场模型,得到不同工况下活塞最高温度。采用Elman神经网络建立活塞最高温度与双燃料发动机转速、扭矩、替代率、喷油提前角以及NOx浓度参数关系模型。结果表明:该模型变量物理意义明确、形式简单便于实现,计算得到的拟合值与实测值的最大相对误差不超过2.17%,对双燃料发动机活塞最高温度的预测效果好,所建模型为保护发动机的活塞提供一个方法。

The temperature field model of the piston of the dual-fuel engine is established by the method of hardness plug test and ANSYS finite element software,and the maximum temperature of the piston under different working conditions is obtained.The Elman neural network is used to establish the model of the relationship between the maximum piston temperature and the rotational speed,torque,substitution rate,injection advance angle and NOx concentration of the dual fuel engine.The results show that the model has clear physical meaning and simple form,and the maximum relative error between the calculated and measured values is less than 2.17%.The prediction of the maximum temperature of the dual-fuel engine piston is good.The model provides a method for protecting the piston of the engine.