基于改进BP神经网络的航空液压油软测量

BP 神经网络越来越多地被应用于软测量建模中，与传统方法相比，BP神经网络进行信息处理可以减少数据的分析和建模工作，但也存在易于陷入局部最小值和初始权值随机选取的缺陷问题。为了解决传统BP神经网络存在的缺陷，论文中在数据预处理过程中引入主成分分析法（PCA），在BP网络输入权值时引入遗传算法（GA），最终达到弥补BP神经网络缺陷的目的；详细介绍了改进算法的流程与步骤，将改进的BP神经网络应用于航空液压油的软测量，先是对航空液压油软测量参数进行分析，包括辅助变量的选择和数据预处理，然后进行基于改进型BP神经网络的建模与仿真实验。实验结果表明，基于改进BP神经网络的航空液压油软测量效果优于传统神经网络，具有更强的泛化能力,因此可进行更广泛的应用。

Aircraft Hydraulic Fluids Soft Measurement Based on Improved BP Neural Network

To solve the problem of Back Propagation (BP) neural network easy to get in local least value and the initial weight is chosen randomly, Principal Component Analysis (PCA) and Genetic Algorithms (GA) are introduced to the BP Neural Network. Soft measurement based on the BP neural Network improved was built and practically applied on aircraft hydraulic fluids detection. The simulation results show that, the improved network could improve the Generalization ability of the model and the ability to predict dynamic measurement data, which make the BP neural Network can be used even more widely.