Online dual updating with recursive PLS model and its application in predicting crystal size of purified terephthalic acid (PTA) process

Abstract To improve the performance of online prediction of existing soft sensor models, we propose a dual updating strategy, i.e., integrating the methods of recursive partial least square (RPLS) model updating and the model output offset updating. In online applications, each update is activated rotationally. In this strategy, a new recursive PLS method is developed and implemented by updating the mean and variance of the training samples using the data acquired from the process, while the offset updating method takes into account both the old overall offset and the new bias between the actual measurement and the model prediction. Since the dual updating strategy takes the advantages of the two updating methods, it is more effective than any individual updating method in adapting process changes. The high performance of the strategy is demonstrated by the application of an industrial purified terephthalic acid (PTA) purification process in which prediction of average crystal particle size was within 2.5% with regard to the relative root mean square error (RMSE). In addition, the dynamic PLS method was found inferior to any of the three methods mentioned above, at least for this particular industrial application. The present dual updating method may also be extended to other industrial applications using process models outside PLS.