In this research, the combination of the principal component analysis (PCA) model and the traditional techniques with memory effect is developed for detecting the process influenced by a small or a moderate shift in one or more process variables, The traditional techniques, like the exponentially weighted moving average and the cumulative sum, use additional information from the past history of the process for keeping the memory effect of the process behavior trend. On the other hand, PCA can find a set of combination variables which can describe the key variations and trends for the operating data. This integrated method is particularly important for long-term performance deterioration, such as product quality degradation, because gradual small shifts are more difficult to diagnose than a sudden failure of equipment. The complementarity of these methods not only leads to some cross-fertilization between various techniques but also results in a better model. The comparison between the properties of the different combinational methods and PCA in terms of the mathematical definitions is discussed. Furthermore, the proposed methods are demonstrated through two real industrial case studies: a melting process in the glaze industry and the surface quality in a stainless steel slab.