In this paper, Wavelet Transform is applied to improve the on-line prediction of crude oil distillation (COD) qualities. First, the wavelets-based multi-scale analysis method was applied to treat the process data effectively. According to their unique characteristics with multi-scale Wavelet Transform, different variations are detected and modified, such as steps, peaks, noises, abnormal sudden changes, and so on. Using the process data with noises discarded and abnormal sudden changes treated effectively, the COD quality prediction can be sure of safety and high accuracy. Next, for some COD units on-line quality analyzers are available, and a new correcting strategy is taken in this paper to give effective update. The update is accomplished based on process data trends extraction. At last, the data processing and the on-line update strategy are introduced to a prediction system of COD product qualities to improve its prediction accuracy. The improved prediction system has been applied in a real plant, and the results are satisfactory.