Hybrid model for optimization of crude oil distillation units

Abstract

in Wiley Online Library (wileyonlinelibrary.com)Planning, scheduling, and real time optimization are currently implemented using different types of models, which causes discrepancies between their results. This work presents a single model of a crude distillation unit (preflash, atmospheric, and vacuum towers) suitable for all of these applications, thereby eliminating discrepancies between models used in these decision processes. Product true boiling point (TBP) curves are predicted via partial least squares model from the feed TBP curve and operating conditions (flows, pumparound heat duties, furnace coil outlet temperatures). Combined with volumetric and energy balances, this enables prediction of crude distillation on par with a rigorous distillation model, with 0.5% root mean square error (RMSE) over a wide range of conditions. Associated properties (e.g., gravity, sulfur) are computed for each product based on its distillation curve and corresponding property distribution in the feed. Model structure makes it particularly amenable for development from plant data.

Hybrid Semi‐parametric Modeling in Separation Processes: A Review

“…Later, they optimized the resulting hybrid model showing that it converged to a better optimum than the rigorous mechanistic model (possibly due to the reduction of the nonlinearities in the model). This work was later extended by applying additional simplifications, which made the hybrid model independent from the tray temperatures (conserving the high accuracy) which made it suitable for RTO, planning and scheduling applications . This last example reveals that hybrid models can be used to unify different scales (which traditionally are treated with independent models) within a single model.…”

Recent progress and challenges in process optimization: Review of recent work at ECUST

“…The development of a hybrid model is a reliable approach, which provides a high degree of freedom for balancing complexity and prediction precision. For example, the work by Fu et al proposed a hybrid modelling method for a crude oil distillation unit, which can be used in planning, scheduling, and RTO. Delicate strategies, such as decomposition methods, should also be explored further.…”

Impact of crude distillation unit model accuracy on refinery production planning

“…3. Fu et al (2016) showed that the straight line through the middle section of the TBP curve depends only on how the tower feed is cut into different products (i.e., cumulative volumetric percentage corresponding to the front and back of each product) and the corresponding temperatures on the feed TBP curve. In other words, for a given tower configuration, the middle section is determined by the properties of the feed and by the amounts of the feed allocated to each product.…”

“…Nonlinearities occur via certain ratios (e.g., reflux/distillate, stripping steam/product flow, and pumparound heat duty/feed flow). In Fu et al (2016) showed that the hybrid CDU model predicts 95% points on the product TBP curves of most products with errors of 0.3% or less. An exception is vacuum pipestill products, for which their model achieves relative errors of 0.1% to 0.9%.…”

“…We compare the swing cut + bias CDU model with a recently developed hybrid CDU model (Fu et al, 2016). The hybrid CDU model computes material and energy balances, as well as product true boiling point (TBP) curves and bulk properties (e.g., sulfur % and cetane index, and other properties).…”