论文部分内容阅读
本文将神经网络应用于发动机试验数据的拟合，为改善神经网络性能引入了函数连接。研究表明：神经网络能够避免数据的分析和建模工作，能够识别有噪声的输入模式，数据拟合精度高，可减少分析人员的介入。
In this paper, the neural network is applied to the fitting of engine test data, and the function connection is introduced to improve the performance of neural network. The research shows that neural network can avoid the data analysis and modeling work, identify the noisy input mode, and the data fitting accuracy is high, which can reduce the intervention of analysts.