Data driven hybrid model identification for control and optimisation of petrochemical and refining plants

点击翻译按钮获取中文摘要

Excellence in operation of process plants is attained by determining the best operating conditions (optimisationof operation) and controlling their real-time operation to maintain these best conditions. Such control andoptimisation require accurate process models.Since 1970s there have been two separate streams of model development: (i) rigorous models derived fromthe first principles, and (ii) empirical models identified from plant data via methods developed in theautomatic control community. The former usually require a large effort in deriving the first principlesequations and construction of efficient algorithms for solving them. The latter have proceeded along the pathof identifying empirical models from the plant operating data. Even though significant advances have beenmade, and there are many instances of very successful use of both types of models for optimisation and control,respectively, there are still many opportunities for improvement. For instance, identification of models forprocesses with large time delaysDuring the last decade there have been significant advances in artificial intelligence methods for speechrecognition, image recognition and classification, handwriting recognition etc. Foundation for these advancesare deep neural networks comprised on many layers. It has been found that specific neural network structuresare best at creating models for specific types of applications. This research proposes to identify very accuratemodels from operating data by developing specific model structures for specific types of processes. It willcombine some first principles equations (e.g. mass and energy balances) with deep neural networks or withmodels developed via identification methods from the automatic control field. Models predicting bothsteady-state and dynamic behaviour will be developed, with particular attention devoted to models with largetime delays (e.g. ethane/ethylene splitter). Having developed a "standard form" of the model for specificequipment will enable such models to be readily adjusted to represent specific equipment and be re-used.