Dynamics and Predictive Control of Gas Phase Propylene Polymerization in Fluidized Bed Reactors

A two-phase dynamic model, describing gas phase propylene polymerization in a fluidized bed reactor, was used to explore the dynamic behavior and process control of the polypropylene production rate and reactor temperature. The open loop analysis revealed the nonlinear behavior of the polypropylene fluidized bed reactor, jus- tifying the use of an advanced control algorithm for efficient control of the process variables. In this case, a central- ized model predictive control （MPC） technique was implemented to control the polypropylene production rate and reactor temperature by manipulating the catalyst feed rate and cooling water flow rate respectively. The corre- sponding MPC controller was able to track changes in the setpoint smoothly for the reactor temperature and pro- duction rate while the setpoint tracking of the conventional proportional-integral （PI） controller was oscillatory with overshoots and obvious interaction between the reactor temperature and production rate loops. The MPC was able to produce controller moves which not only were well within the specified input constraints for both control vari- ables, but also non-aggressive and sufficiently smooth for practical implementations. Furthermore, the closed loop dynamic simulations indicated that the speed of rejecting the process disturbances for the MPC controller were also acceotable for both controlled variables.

Mathematical Model and Advanced Control for Gas-phase Olefin Polymerization in Fluidized-bed Catalytic Reactors

In this study, the developments in modeling gas-phase catalyzed olefin polymerization fluidized-bed reactors （FBR） using Ziegler-Natta catalyst is presented. The modified mathematical model to account for mass and heat transfer between the solid particles and the surrounding gas in the emulsion phase is developed in this work to include site activation reaction. This model developed in the present study is subsequently compared with well-known models, namely, the bubble-growth, well-mixed and the constant bubble size models for porous and non porous catalyst. The results we obtained from the model was very close to the constant bubble size model, well-mixed model and bubble growth model at the beginning of the reaction but its overall behavior changed and is closer to the well-mixed model compared with the bubble growth model and constant bubble size model after half an hour of operation. Neural-network based predictive controller are implemented to control the system and compared with the conventional PID controller, giving acceptable results.

Energy efficiency and savings analysis with multirate sampling for petrochemical process using convolutional neural network-based transfer learning

Energy efficiency in the petrochemical industry is crucial in reducing energy consumption and environmental impact.An accurate energy efficiency model will provide valuable insight for supporting operational adjustment decisions.In practice,due to inconsistent sampling intervals in the petrochemical industry,the traditional approach for obtaining energy efficiency may be unreliable and difficult to handle these multirate data char-acteristics.Therefore,in this paper,a multi-channel convolutional neural network model integrating a model parameter-based transfer learning approach is proposed to improve the prediction of energy efficiency under inconsistent sampling intervals.The multi-channel structure aims to recognize a different pattern from the dataset by convolving the information along the time dimension.Concurrently,transfer learning allows the model to learn a new pattern of input after the model is fully trained.Finally,the performance for energy ef-ficiency prediction and saving analysis is validated by applying it to the vinyl chloride monomer production case study.The result shows that the proposed model outperformed traditional models and typical convolutional neural network structures in terms of accuracy and reproducibility,with an r-square of 0.97.The utilization of transfer learning prevents a significant drop in performance and enhances adaptability in model learning on real-time energy tracking.Moreover,the energy gap analysis of the prediction result identified a significant energysaving potential,which would decrease annual energy consumption by 7.25%on average and a 5,709-ton reduction in carbon dioxide emissions.

Explainable deep transfer learning for energy efficiency prediction based on uncertainty detection and identification

Energy efficiency is an important aspect of increasing production capacity, minimizing environmental impact, and reducing energy usage in the petrochemical industries. However, in practice, data quality can be degraded by measurement malfunction throughout the operation, leading to unreliable and inaccurate prediction results. Therefore, this paper presents a transfer learning fault detection and identification-energy efficiency predictor (TFDI-EEP) model formulated using long short-term memory. The model aims to predict the energy efficiency of the petrochemical process under uncertainty by using the knowledge gained from the uncertainty detection task to improve prediction performance. The transfer procedure resolves weight initialization by applying partial layer freezing before fine-tuning the additional part of the model. The performance of the proposed model is verified on a wide range of fault variations to thoroughly examine the maximum contribution of faults that the model can tolerate. The results indicate that the TFDI-EEP achieved the highest r-squared and lowest error in the testing step for both the 10% and 20% fault variation datasets compared to other conventional methods. Furthermore, the revelation of interconnection between domains shows that the proposed model can also identify strong fault-correlated features, enhancing monitoring ability and strengthening the robustness and reliability of the model observed by the number of outliers. The transfer parameter improves the prediction performance by 9.86% based on detection accuracy and achieves an r-squared greater than 0.95 on the 40% testing fault variation.