基于胶囊网络的TIG熔透预测  

TIG penetration prediction based on capsule network

作　　者：王颖[1] 高胜[1] 吴立明[2] Wang Ying;Gao Sheng;Wu Liming(Northeast Petroleum University,Daqing 163318,Heilongjiang,China;Petro China Daqing Oilfield Company,Daqing 163000,Heilongjiang,China)

机构地区：[1]东北石油大学,黑龙江大庆163318 [2]大庆油田有限责任公司,黑龙江大庆163000

出　　处：《焊接》2023年第4期15-20,28,共7页Welding & Joining

摘　　要：以钨极气体保护焊(tungsten inert gas welding,TIG)熔透预测作为研究对象,文中提出了一种基于胶囊网络(capsule network,CapsNet)的熔透预测模型,并在模型中引入压缩奖惩网络模块(squeeze-excitation,SE模块)来提高模型的精度及训练速度。模型以焊接区的熔池正面图像作为输入,利用卷积层提取浅层特征,并通过压缩奖惩网络模块自适应提取不同特征的重要程度,依据重要程度调节特征图,再传递至胶囊层,采用动态路由算法迭代更新胶囊层间的耦合系数,最终获得3种熔透状态(未熔透、熔透、过熔透)的预测结果。迭代次数为70、激活函数选线性整流函数(linear rectification function,ReLU)、卷积层数为2层、胶囊层数为2层时模型在预测准确率和训练时间上表现最佳。为了进一步验证所提模型的性能,分别与传统胶囊网络,AlexNet和VGG19进行了对比分析。结果表明,改进后的胶囊神经网络能够有效地预测焊缝的熔透状态,在小样本数据集上表现较稳定,精度较高。Taking the penetration prediction of TIG welding as the research object,this paper proposes a penetration prediction model based on capsule network,and introduces the Squeeze-Excitation module into the model to improve the accuracy and training speed of the model.The model takes the front image of the weld pool in the welding area as the input,extracts the shallow features by using the convolution layer,adaptively extracts the importance of different features by Squeeze-Excitation module,adjusts the feature map according to the importance,and then transmits it to the capsule layer.The dynamic routing algorithm is used to update the coupling coefficient between the capsule layers,and the model finally obtains the prediction results of three penetration states(incomplete penetration,penetration and over penetration).When the number of iterations is 70,the activation function is ReLU,the number of convolution layers is 2,and the number of capsule layers is 2,the model performs best in prediction accuracy and training time.In order to further verify the performance of the proposed model,it is compared with traditional capsule network,AlexNet and VGG19.The results show that the improved capsule neural network can effectively predict the penetration state of weld,which is stable and accurate on small sample data sets.

关 键 词：熔透预测 胶囊网络 压缩奖惩网络模块 图像处理 

分 类 号：TG409[金属学及工艺—焊接]