摘要
提出一种高效率和高精度的铝箔封口完整密封性检测方法。首先,通过红外线热像仪获取铝箔封口处的热像图,然后利用MATLAB软件批量获取热像图的信息,再对其进行图像预处理。随后用遗传算法对BP神经网络进行优化,进行图像特征提取与分类识别。实验结果证明,此密封性检测方法识别率高、训练时间短,为后续的铝箔封口生产线中的密封不良产品自动筛选和剔除提供了保证。
A high efficiency and high precision testing method for tightness detection method of aluminum foil seal is proposed.First of all,the thermal images of aluminum foil seal are obtained by a thermal imager.Then we use MATLAB software for getting the information of thermal image in batches,and then the image preprocessing.Then BP neural network was optimized by genetic algorithm to extract and classify image features.The experimental results show that this sealing test method has high recognition rate and short training time,which provides a guarantee for automatic screening and elimination of bad sealing products in the subsequent aluminum foil sealing production line.
作者
赵士龙
李维军
石成江
Zhao Shilong;Li Weijun;Shi Chengjiang(School of Mechanical Engineering, Liaoning Shihua University, Fushun Liaoning 113001,China)
出处
《辽宁石油化工大学学报》
CAS
2019年第1期97-100,共4页
Journal of Liaoning Petrochemical University
关键词
铝箔密封性检测
图像预处理
遗传算法
BP神经网络
Aluminum foil sealing test
Image preprocessingr
Genetic algorithm
BP neural network
