Research on X-ray weld seam defect detection and size measurement method based on neural network self-optimization

To effectively solve the problems of low detection accuracy caused by low quality image discriminative features of X-ray weld defects, lack of intuitive representation of the defect size of existing detection algorithms, and the strong subjectivity of the detection model artificial parameter adjustment, an X-ray weld defect detection and size measurement algorithm based on neural network self-optimization is proposed. Firstly, a high-performance detection model for X-ray weld defects is constructed, and the detection accuracy is comprehensively improved through a series of featured module designs with the capabilities of feature information enhancement and multiscale information fusion. Secondly, a model optimization strategy is proposed to obtain the optimal hyperparameter components of the model through adaptive optimization to enhance the model's self-learning capability. Finally, by constructing the mapping relationship between the actual size of defects and the screen resolution, the size measurement algorithm of weld defects is designed, and the integrated technology of defect detection and size measurement is realised. Experimental results show that the proposed algorithm achieves good results even on a small-scale X-ray weld seam defect dataset. Compared to other classical and advanced detection models used in the experiments, mAP@0.5 is improved by an average of 16.1% and mAP@.5:.95 by an average of 10.7%. The image processing speed reaches up to 68 frames per second, and the error between the size calibration and manual actual measurement is less than 0.1 cm, which can meet the real-time detection requirements for weld seam defects in practical industrial production.