基于过程神经元网络的动态预测模型及其应用

〗针对动态系统过程预测预报问题，提出了一种基于过程神经元网络的动态预测方法．过程神经元网络的输入/输出均可以是时变函数，其时空聚合运算和激励可同时反映时变输入信号的空间聚合作用和输入过程中的阶段时间累积效应．基于过程神经元网络的动态预测模型能同时满足对系统的非线性辨识和过程预测，在机制上对动态预测预报问题有较好的适应性．文中给出了基于函数基展开和梯度下降法的学习算法，以电力负荷预报为例验证了模型和算法的有效性．

Dynamic Prediction Model Based on Process Neural Networks and Its Application

A dynamic prediction method based on process neural networks is proposed for the process forecasting and prediction problem of dynamic system. Both the inputs and outputs of the process neural networks can be timevarying functions and their spatial-temporal aggregation operation and activation can reflect the space aggregation function of the time-varying input signals and the stage time cumulation effect in the input process at the same time. Dynamic prediction model based on process neural networks can meet nonlinear recognition and process predition of the dynamic system, and has better adaptability to dynamic forecasting and prediction problem in mechanism. The paper gives a learning algorithm based on function basis expansion integrated with gradient descent, and proves the effectiveness of the model and algorithm with the example of power load forecasting.