We demonstrate a novel multiscale nonlinear process monitoring and fault detection method, called the scale-sifting multiscale algorithm(SMA). The key innovative feature of SMA is essential scale data reconstruction without prior knowledge of signals monitored compared with state-of-the-art multiscale monitoring methods. The SMA includes a scale-sifting benchmark, data decomposition and data reconstruction, and dynamic kernel partial least squares. The scale-sifting benchmark is developed to sift out special scales with the essential features of abnormal situations. Then, the data are reconstructed corresponding to selected scales. Finally, dynamic KPLS is applied to analyze data reconstructed for online quality process monitoring and fault detection. The application results illustrate the effectiveness of the proposed method