对基于人工神经网络的柴油机气缸压力识别方法应注意的问题进行了研究，指出利用人工神经网络进行气缸压力识别时振动信号与压力信号在相位上要一致，同时指出在对网络的训练时，输入层神经元个数与隐含层神经元个数选择适当与否，对网络训练和识别影响很大，笔者认为取第六缸上止点前后１４０°范围内数据和ｒ＝ ５～１０ 比较好。 The problems that should be paid attention to in diesel cylinder pressure identification based on artificial neural network are researched. It is pointed out that the vibration signal and pressure signal should be consistent in phase when using artificial neural network to identify cylinder pressure, meanwhile, it is pointed out that in the training of network, The number of neurons in the layer and the number of neurons in the hidden layer of the appropriate choice or not, the network training and identification of a great influence, I think the sixth cylinder before and after the top dead center 140 ° range of data and r = 5 to 10 is better .