双并联前向过程神经网络及其应用研究

为克服多层前向过程神经网络收敛速度慢、精度低的问题,提出了一种双并联前向过程神经网络模型.在输入空间中引入一组合适的函数正交基,将输入函数和网络权函数表示为该组正交基的展开形式,并利用基函数的正交性简化网络聚合运算过程.给出了相应的学习算法,并以飞机发动机状态监控中发动机排气温度的预测为例验证了模型和算法的有效性.

Research on Double Parallel Feedforward Process Neural Networks and Its Application

To solve the problems of slow convergence speed and low accuracy of the multilayer feedforward process neural networks, a double parallel feedforward process neural networks model is proposed. By introducing a set of appropriate orthogonal basis functions into the input space, the input functions and the weight functions are expanded under the orthogonal basis functions, and the time aggregation operation of the process neurons is simplified by using the orthogonality of the basis functions. The corresponding learning algorithm is given and the effectiveness of this method is proved by the prediction of exhaust gas temperature in aircraft engine condition monitoring.