Industrial application of Wavelet Transform to the on-line prediction of side draw qualities of crude unit

In this paper, Wavelet Transform is applied to improve the on-line predicti on of crude oil distillation (COD) qualities. First, the wavelets-based mul ti-scale analysis method was applied to treat the process data effectively. According to their unique characteristics with multi-scale Wavelet Transfo rm, different variations are detected and modified, such as steps, peaks, n oises, abnormal sudden changes, and so on. Using the process data with nois es discarded and abnormal sudden changes treated effectively, the COD quali ty prediction can be sure of safety and high accuracy. Next, for some COD u nits on-line quality analyzers are available, and a new correcting strategy is taken in this paper to give effective update. The update is accomplishe d based on process data trends extraction. At last, the data processing: an d the on-line update strategy are introduced to a prediction system of COD product qualities to improve its prediction accuracy. The improved predicti on system has been applied in a real plant, and the results are satisfactor y. (C) 2000 Elsevier Science Ltd. All rights reserved.