AbstractThe effect of decaying catalyst efficacy in a commercial‐scale, semi‐continuous petrochemical process was investigated. The objective was to gain a better understanding of process behaviour and its effect on production rate. The process includes a three‐stage reaction performed in fixed bed reactors. Each of the three reaction stages consists of a number of catalyst beds that are changed periodically to regenerate the catalyst. Product separation and reactant recycling are then performed in a series of distillation columns. In the absence of specific measurements of the catalyst properties, process operational data are used to assess catalyst decay. A number of statistical techniques were used to model production rate as a function of process operation, including information on short‐ and long‐term catalyst decay. It was found that ridge regression, partial least squares and stepwise selection multiple linear regression yielded similar predictive models. No additional benefit was found from the application of non‐linear partial least squares or Curds and Whey. Finally, through time series profiles of total daily production volume, corresponding to individual in‐service cycles of the different reaction stages, short‐term catalyst degradation was assessed. It was shown that by successively modelling the process as a sequence of batches corresponding to cycles of each reaction stage, considerable economic benefit could be realized by reducing the maximum cycle length in the third reaction stage. Copyright © 2001 John Wiley & Sons, Ltd.