Abstract
Convolutional neural network (CNN) is an efficient and robust method which can accurately detect the Tailor Rolled Blank laser welding pool penetration status. To select proper hyperparameters and optimization of CNN model are black box problem. In this paper, an innovative method based on CNN to identify the penetration status of the weld pool during laser welding was introduced. A coaxial monitoring platform is set up, as well as two-class, three-class and four-class datasets are created for training and validating the CNN. The Bayesian Optimization (BO) method is used to optimize hyper-parameters which are adopted for training CNN model, determine the best parameters of depth, initial learning rate, momentum and L2 regularization. The results show that using BO method leads to accuracy improvement compared with the CNN model trained from scratch with default hyper-parameters, hence it can effectively solve the problem that the hyper-parameters of CNN are difficult to adjust. Under various laser welding parameters, high-accuracy detection of penetration status can be acquired with the test accuracy of four-class reaching 95.2%, which slightly lower than the test accuracy of the three-class and two-class.
