Quality monitoring can effectively improve product quality and production efficiency. In the production process of complex products, the interaction of multiple quality characteristics affects the quality of production jointly. The large number of quality characteristics and coupled relationship of some characteristics enhance the difficulty of accurate diagnosis of abnormal variables. In order to diagnose the abnormal variables accurately and improve product quality and production efficiency, this paper proposes a model of monitoring the mean shift based on the improved grid optimization principal component analysis(PCA)-support vector machines(SVM). Before training the model, principal component analysis(PCA) algorithm is used to process the data to reduce data dimension and extract data feature information. Then, this paper uses the modified grid algorithm to optimize the parameters of support vector machine (SVM). Finally, the optimized SVM model is attained. The simulation results show that the proposed method has better performance than the traditional methods.