融合联合范数和主成分分析的焊缝缺陷识别研究

Research on weld defect recognition by integrating joint norm and principal component analysis

摘要:

焊缝表面缺陷识别在焊接过程和质量控制中起着至关重要的作用。经典的二维主成分分析(two-dimensional principal component analysis,2DPCA)算法在焊缝缺陷识别中采用F范数度量存在对异常偏差值和噪声敏感、鲁棒性差、投影距离最大的同时不能有效减小重构误差等问题。针对上述问题,本文使用了联合范数度量方式,将L1和R1范数添加到函数模型中,提出了一种名为L1-2DPCA-R1的二维主成分分析算法,列出了该算法的迭代求解方法。该算法降低了图像的重构误差,有着较好的重构性能,抑制了异常偏差值和噪声的影响,提高了鲁棒性,保持了分类率的优势。实验结果表明,该算法能够准确检测各种焊缝缺陷类型,比其他主成分分析 (principal compoent analysis,PCA) 算法抗大噪声的能力更强、鲁棒性更优、重构误差更小。

Abstract:

Weld surface defect recognition plays a vital role in the welding process and quality control.The classical two-dimensional principal component analysis (2DPCA) algorithm using the Fnorm metric in weld defect recognition suffers from the problems of being sensitive to abnormal deviation values and noise,poor robustness,and not being able to effectively reduce the reconstruction error while the projection distance is maximum.Aiming at the above problems,this paper uses a joint-norm metric,a two-dimensional principal component analysis algorithm called L1-2DPCA-R1 is proposed by adding L1 and R1 norm to the function model,and the iterative solution method of the algorithm is listed.This algorithm reduces the reconstruction error of the image,has better reconstruction performance,suppresses the influence of abnormal deviation values and noise,improves the robustness,and maintains the advantage of classification rate.Experiments show that the algorithm can accurately detect various weld defect types,with better resistance to large noise,better robustness,and smaller reconstruction error than other principal component analysis (PCA) algorithms.