A quality monitoring method by means of support vector machines (SVM) for robotized gasmetal arc welding (GMAW) is introduced. Through the feature extraction of the welding process signal,a SVM classifier is constructed to establish the relationship between the feature of process parametersand the quality of weld penertration. Under the samples obtained from auto parts welding productionline, the learning machine with a radial basis function kernel shows good performance. And thismethod can be feasible to identify defect online in welding production. A quality monitoring method by means of support vector machines (SVM) for robotized gasmetal arc welding (GMAW) is introduced. Through the feature extraction of the welding process signal, a SVM classifier is constructed to establish the relationship between the feature of process parameters and the quality of weld penertration. Under the samples obtained from auto parts welding productionline, the learning machine with a radial basis function kernel shows good performance. And this method can be feasible to identify defect online in welding production.