Computers & Chemical Engineering最新文献

Crude oil procurement and blending are key processes in refinery production. When solving the integrated optimization problem of simple oil procurement and blending, the following issues are mainly considered: how to establish an integrated optimization model of crude oil procurement and blending process under different time scales to minimize the cost of procurement under the premise of ensuring the stability of the properties of blended crude oil. The paper proposes an integrated optimization model, takes cost minimization as the model's objective function, and provides stability through the yield and property constraints of blended crude oil. Then, the paper describes the procurement process by an event-based representation and the blending process by a continuous event representation and proposes a hybrid event-time-based representation to describe the model. Finally, this paper verifies the model's effectiveness in solving real production problems through case simulations.

Fed-batch cultures are the preferred operation mode for industrial bioprocesses requiring high cellular densities. Avoids accumulation of major fermentation by-products due to metabolic overflow, increasing process productivity. Reproducible operation at high cell densities is challenging ($>100$ gDCW/L), which has precluded rigorous model evaluation. Here, we evaluated three phenomenological models and proposed a novel hybrid model including a neural network. For this task, we generated highly reproducible fed-batch datasets of a recombinant yeast growing under oxidative, oxygen-limited, and respiro-fermentative metabolic regimes. The models were reliably calibrated using a systematic workflow based on pre-and post-regression diagnostics. Compared to the best-performing phenomenological model, the hybrid model substantially improved performance by 3.6- and 1.7-fold in the training and test data, respectively. This study illustrates how hybrid modeling approaches can advance our description of complex bioprocesses that could support more efficient operation strategies.

This manuscript proposes a general new framework for mathematical modeling, extended sensitivity analysis and dynamic optimization of tangential flow filtration (TFF) systems for concentration of monoclonal antibody (mAb) products and, potentially, other biologics. This framework is comprised of four major components: (I) a new first-principles-inspired TFF model; (II) dedicated parameter estimation strategies for automated model training; (III) new extended sensitivity analysis techniques for enhancing TFF phenomenological understanding and providing general guidance on TFF process development; and (IV) novel mono-objective and multi-objective dynamic optimization strategies for optimal TFF design and operation. The application of this framework to Bovine immunoglobulin γ (IgG) – a mAb analog in terms of physicochemical properties – shows the potential benefits it may offer in terms of overall TFF performance and rapid TFF development for new mAb candidates, compared to the current state of the art.

Soft sensor plays an important role in improving product quality; however, practical applications may often face with the problem of small sample size, which is challenging for developing data-driven models in terms of feature selection and good generalization. This paper proposes a data enhancement approach for small sample size data-driven problems based on generative adversarial networks integrated with maximum relevance minimum redundancy (MRMR). First, sample expansion is performed on the initial data by using a generative adversarial network. Second, irrelevant variables are eliminated by the MRMR and optimal features are obtained. Finally, neural networks-based soft sensor modeling is performed using the augmented dataset and the selected features. The proposed method is tested on a simulated penicillin case, an actual penicillin production case and an actual erythromycin production case. Experimental results show that the proposed method outperforms state-of-the-art existing methods, which verify the effectiveness and superiority of the proposed method.

Gaussian process (GP) regression has gained significant popularity in machine learning because it has the intrinsic capability to capture uncertainty in function prediction and requires a limited number of hyperparameters to be optimized. In this study, a Gaussian process model predictive control (GPMPC) algorithm is proposed to model the unknown dynamics of the process using Gaussian process regression. The GPMPC incorporates the expected variance of the GP model to account for the model's uncertainty and to achieve prudent control. Meanwhile, the extended state observer (ESO) is introduced for the GPMPC, which can estimate the unmodeled dynamics and unknown disturbance. With the designed feedforward gain, the proposed extended state observer-based GPMPC (GPMPC-ESO) method can achieve offset-free performance. Theoretical analysis is conducted to evaluate the stability and disturbance rejection performance of the control system. Finally, the algorithms are validated by simulation in continuous stirred tank reactor (CSTR) process control.

The quest for real-time dynamic optimization solutions in the process industry represents a formidable computational challenge, particularly within the realm of applications like model-predictive control, where rapid and reliable computations are critical. Conventional methods can struggle to surmount the complexities of such tasks. Quantum computing and quantum annealing emerge as avant-garde contenders to transcend conventional computational constraints. We convert a dynamic optimization problem, characterized by an optimization problem with a system of differential–algebraic equations embedded, into a Quadratic Unconstrained Binary Optimization problem, enabling quantum computational approaches. The empirical findings synthesized from classical methods, simulated annealing, quantum annealing via D-Wave’s quantum annealer, and hybrid solver methodologies, illuminate the intricate landscape of computational prowess essential for tackling complex and high-dimensional dynamic optimization problems. Our findings suggest that while quantum annealing is a maturing technology that currently does not outperform state-of-the-art classical solvers, continuous improvements could eventually aid in increasing efficiency within the chemical process industry.

Semicontinuous distillation is a separation technique used to purify multicomponent mixtures with low to medium throughput. This research addresses the problem of designing a Data-driven Model Predictive Control (MPC) approach that enables minimizing the Total Annualized Cost (TAC) of the semicontinuous process per tonne of feed processed while maintaining the required product purity. In lieu of typically unavailable first principles models, the manuscript demonstrates the implementation of data-driven technique using data collected from an Aspen Plus Dynamics simulation as a test bed. A subspace model identification technique is adapted to develop a multi-model framework to capture the dynamic behavior of the process and then utilized within a Shrinking Horizon MPC (SHMPC) scheme, to achieve the required objective. The simulation results demonstrate a lowering of the TAC/tonne of feed by 11.4% compared to the traditional PI setup used in the previous studies.

Fault detection and diagnosis (FDD) is crucial for ensuring process safety and product quality in the chemical industry. Despite the large amounts of process data recorded and stored in chemical plants, most of them are not well-labeled, and their conditions are not adequately specified. In this study, an optimized data-driven FDD model was developed for a chemical process based on automatic clustering algorithms. Due to data preprocessing importance, feature selection was performed by a non-dominated sorting genetic algorithm (NSGAII) based on k-means clustering. The optimal subset of features is selected by comparing clustering results for each subset. The performance of the proposed feature selection method was compared with the Fisher discriminant ratio (FDR), and XGBoost methods. The t-distributed stochastic neighbor embedding (t-SNE), Isomap, and KPCA dimension reduction methods were also employed for feature extraction. Finally, automatic clustering was performed based on metaheuristic algorithms for fault detection and diagnosis. Results were compared with non-automatic clustering methods. The performance of the proposed method was evaluated by examining the Tennessee Eastman and four water tank processes as case studies. The results showed that the proposed method is reliable and capable of online and offline chemical process fault detection and diagnosis. As a result, the findings of this study can be used to stabilize the operation of chemical processes.

CO₂ capture plants can help reduce the cost of deploying capture systems across the globe. However, the CO₂ variability and model uncertainty represent operational challenges to capture CO₂ from different sources. This work proposes a framework for analyzing the optimal plant design considering different flue gas sources. We show a methodology to generate large data sets from optimization runs using rigorous models in Aspen Plus®. The efficiency of the approach allows its application to large-scale optimization problems, with an average CPU time per run of 176 s.

We additionally build surrogate models (SMs) for the capital and operating costs of the capture plants, employing an iterative procedure to generate SMs using ALAMO. We systematically reject SMs with high uncertainty in the estimated parameters. This approach results in SMs with favorable bias-variance tradeoffs, enabling their effective application to optimization problems under uncertainty, as demonstrated with a pooling problem of CO₂ streams.

In offshore wells, severe slugs are frequent problems that can limit oil production. It has already been proven that active pressure control can mitigate this effect, but defining the setpoint is still a manual task that requires constant human intervention. This study proposes a novel approach utilizing machine learning to aid the search for optimal production levels while preventing severe slugging. Two unsupervised machine learning methods, namely Self-Organizing Maps (SOM) and Generative Topographic Mapping (GTM), were evaluated for the early detection of slugging patterns in offshore oil wells. This study utilizes simulated FOWM model data to construct the necessary database. Additionally, real-world well data underwent SOM and GTM analysis, providing valuable insights from practical contexts. Both SOM and GTM showed promising results. However, GTM outperformed SOM in terms of mapping orientation and prediction scores. In addition, the GTM was easier to optimize in terms of hyperparameters for map tuning.