A Deep Learning Model for Striae Identification in End Images of Float Glass

Abstract

For float glass, there is a correlation between the striae in end image and the manufacturing process. If clearly understood, the correlation helps to optimize and fine-tune the manufacturing process of float glass. This paper attempts to extract the striae from the end image of float glass with deep learning (DL) neural network (NN). For this purpose, an image segmentation model was established based on improved U-Net, a fully convolutional network (FCN), and used to accurately divide the glass liquid on the end image into different layers. Firstly, the improved U-Net model was constructed to extract the striae from each liquid layer on the end image. Next, the activation function and convolutional mode of the improved U-Net model were optimized to enhance the segmentation accuracy and shorten the training/prediction time. Finally, the proposed model was tested on the float glass production line of Hebei CSG Glass Co., Ltd. The test results show that our model achieved an accuracy of 94%. The research findings lay a solid basis for striae identification on end image of float glass, and provide guidance for optimization and fine-tuning of float glass manufacturing process.

Big Data Mining Optimization Algorithm Based on Machine Learning Model

“…In order to improve the over-fitting problem, Karaç ali and Krim [10] proposed a structural risk minimization strategy, under which, over-fitting can be improved to some extent although it cannot be avoided completely. In view of the shortcomings of the empirical risk minimization strategy and the structural risk minimization strategy, several other methods have been proposed successively to improve overfitting, but they still cannot solve this problem well [11][12][13][14]. Brownfield et al [15] compared seven different nonparametric classifiers -radial basis function neural network, multilayer perceptron neural network, support vector machine, classification and regression tree, Chi-square automatic interaction detection, quick, unbiased and efficient statistical tree algorithm and random forest.…”