Nine-lumped kinetic model for VGO catalytic cracking; using catalyst deactivation

This work proposes an ensemble learning-based catalytic cracking coke yield prediction model called the harmonic-ensembled extreme learning machine (HEELM). The model integrates extreme learning machine (ELM) base learners with different activation functions to improve the overall prediction effect. An overfitting index is proposed, and the optimal number of hidden layer nodes of ELM-base learners is determined with it. By examining the influence of different activation functions on the prediction results, the best activation function structure of the ELM-base learner has been determined. Besides, a harmonic layer is established to determine the weight of each base learner in real-time. The proposed model is validated using 1.5 years of historical data from China’s commercial fluidized catalytic cracking (FCC) plant. The results show that the proposed model has outperformed most other ELM-base learners. The relative prediction error is further reduced by 10.97% after introducing the harmonic layer. The proposed model exhibits stable performance with good generalization in three segments of industrial data, and it has guiding significance for stable operation and CO2 emission reduction of the FCC plant.

Section: Introductionsupporting

confidence: 80%

An Ensemble-Learning Approach To Predict the Coke Yield of Commercial FCC Unit

Zhang

Cao

Lan

et al. 2022

“…It combines reaction rules and reaction rate constants and simulates the petroleum refining process through the variation of a large matrix to predict the product composition. Compared with traditional lumping methods, − the SOL method can track petroleum molecules during the reaction process and provide more accurate product molecular composition, and make it possible to calculate physical properties of enormous petroleum molecules by group contribution with corresponding mixing rules by programming. In the past 20 years, SOL method has been successfully applied in the delayed coking and catalytic cracking process. − Recently, Qin et al built an FCC model and showed that a diameter expanding reactor could enhance the hydrogen transfer and isomerization reactions to reduce the olefin content .…”

Section: Introductionmentioning

confidence: 99%

Reaction Behaviors of Polycyclic Aromatic Hydrocarbon Molecules in a Diesel Hydro-Upgrading Process Based on the Molecular-Level Reaction Kinetic Model

Qin

et al. 2022

A molecular-level reaction kinetic model for the diesel hydro-upgrading (DHU) process was established on the basis of the structure-oriented lumping (SOL) method to describe the hydro-upgrading reaction network and investigate the reaction behaviors of polycyclic aromatic hydrocarbon (PAH) molecules. Twenty-two structural increments were selected to construct an 835 row × 23 column feed oil molecular matrix based on the composition analysis. Twenty-eight reaction rules were formulated to deduce molecular reactions according to the hydro-upgrading reaction mechanism. One-hundred ninety-seven structural vectors were used to represent the PAH molecules and 299 structural vectors were used to represent the monocyclic aromatic hydrocarbon (MAH) molecules. The reaction network containing about 24 600 reactions was generated and calculated by MATLAB programming. The reliability of the model was verified by industrial data. The molecular matrix transformation could clearly track the reaction path of the petroleum molecules and reveal the influence of the temperature and the hydrogen partial pressure on PAH molecules in the reaction network. The hydro-upgrading process containing the reactions of aromatic hydrogenation and ring opening reduced the PAH content and increased the cetane number (CN). At a hydrogen partial pressure of 10.0 MPa, the optimal reactor operating temperature range was 304.1−324.1 °C when the diesel yield was required to be larger than 88.0 wt % and the PAH content was less than 5.5 wt % in the refinery.

“…The current modeling strategies for the chemical process are mainly composed of knowledge-based and data-driven approaches, among which knowledge-based approaches have made significant progress in polymerization reactions, − fluid catalytic cracking, − and other industrial applications. Tools such as ensemble models and molecular dynamics simulations can help reveal complex reaction mechanisms and nonlinear dynamic relationships between the variables, providing valuable guidance for practical design and operation.…”

Section: Introductionmentioning

confidence: 99%

Adaptive Data Dimensionality Reduction for Chemical Process Modeling Based on the Information Criterion Related to Data Association and Redundancy

Luo

Chen

et al. 2022

Chemical process modeling is the basis for research and applications in related fields. With the development of industrial informatization, data-driven process modeling techniques are increasingly applied in chemical processes, helping to obtain more accurate results with less model development costs. However, due to the high-dimensional nonlinear characteristics of most chemical processes, problems such as the "curse of dimensionality" and information redundancy will render the models more prone to overfitting with reduced accuracies and weaker generalization abilities. Many data dimensionality reduction methods are adopted to mitigate the above problems, but most are limited by inaccurate association measurements and weak redundancy exclusion. In this paper, the extensive existence of data associations and information redundancies is first revealed through the analysis from an information-theoretic perspective. Then, a feature selection method based on conditional refined maximal information coefficient maximization (CRMICM) is proposed to improve the consistency of association measurement and the accuracy of redundancy estimation with limited samples. The final prediction modeling test for an actual fluidized catalytic cracking (FCC) process proves the extensive association between the variables and targets. Only a few variables are essential for the modeling, while the rest are redundant. Compared with other methods, CRMICM achieves the best dimensionality reduction effects on the FCC process data regarding the number of features and model prediction accuracy, showing its good applicability for chemical processes.