基于改进深层神经网络的织物配方智能预测算法

Intelligent prediction algorithm for fabric formula based on improved deep neural network

针对织物三刺激配色精度不高,无法克服配色过程中出现的同色异谱等问题,提出了基于改进深层神经网络的织物配方智能预测算法。采用高光谱成像系统测量织物的光谱反射率信息,利用改进的深层神经网络来建立织物的光谱反射率--染色配方关系模型。实验结果显示,改进深层神经网络的配方预测值与真实值的平均误差在0.02以内,表明改进深层神经网络能有效的解决织物配方预测问题,具有很好的应用价值。

The prediction accuracy of fabric tristimulus color matching is not high,and the problem of homochromolysis appearing in the color matching process cannot be overcome.An intelligent prediction algorithm for fabric formula based on improved deep neural network is proposed.The hyperspectral imaging system was used to measure the spectral reflectance information of the fabric,and the improved deep neural network was used to establish the relationship between the spectral reflectance of the fabric and the corresponding dyeing formulation.The experimental results show that the average error between the predicted value with the dyeing formulation of the improved deep neural network and the real value is less than 0.02,proving that the improved deep neural network has a good predictive effect on the fabric formulation and has good application value.