基于小波变换的双并联神经网络在混合气体浓度预测中的应用

Concentration Estimation of Gas Mixture Using a Wavelet-Based DPFNN

BP神经网络在混合气体浓度预测中得到广泛应用。针对BP神经网络收敛速度慢的特点,提出了一种新的基于小波变换的并列隐层双并联神经网络结构,这种网络首先对输入数据进行二维离散小波变换,然后用双并联神经网络对变换后两组数据进行训练,确定神经网络的权值和阈值。实验结果证明,相对传统的BP及双并联神经网络,基于小波变换的双并联神经网络的收敛速度加快2～3倍;对混合气体浓度的预测精度也有明显提高。

BP Neural Networks have been widely used in gas mixture concentration estimation.The major drawbacks of the BP algorithm are the problems of local minima and slow convergence.In order to overcome local minima and speedup the convergence of BP,a novel wavelet-based DPFNN（double parallel feedforward neural network）is proposed in this paper.Experimental results showed that,compared to the traditional BP and DPFNN Neural Network,wavelet-based DPFNN neural network can speed up the convergence rate of 2~3 times,and the concentration estimation accuracy of gas mixture can be improved significantly.