Applications of metaheuristic optimization algorithms in model predictive control for chemical engineering processes: A systematic review

Annual Reviews in Control, Год журнала: 2024, Номер 58, С. 100973 - 100973

Опубликована: Янв. 1, 2024

Язык: Английский

---

Development of machine learning model for the prediction of selectivity to light olefins from catalytic cracking of hydrocarbons

Fuel, Год журнала: 2024, Номер 381, С. 133682 - 133682

Опубликована: Ноя. 15, 2024

Язык: Английский

---

Efficient Online Controller Tuning for Omnidirectional Mobile Robots Using a Multivariate-Multitarget Polynomial Prediction Model and Evolutionary Optimization

Biomimetics, Год журнала: 2025, Номер 10(2), С. 114 - 114

Опубликована: Фев. 14, 2025

The growing reliance on mobile robots has resulted in applications where users have limited or no control over operating conditions. These require advanced controllers to ensure the system's performance by dynamically changing its parameters. Nowadays, online bioinspired controller tuning approaches are among most successful and innovative tools for dealing with uncertainties disturbances. Nevertheless, these present a main limitation real-world due extensive computational resources required their exhaustive search when evaluating of complex dynamics. This paper develops an approach leveraging surrogate modeling strategy omnidirectional robot controller. polynomial response surface method is incorporated as identification stage model system predict behavior indirect adaptive approach. comparative analysis concerns state-of-the-art approaches, such online, offline robust, non-robust based optimization. results show that proposal reduces load up 62.85% while maintaining regarding under adverse also increases 93% compared approaches. Then, retains competitiveness systems conditions, other drop it. Furthermore, posterior comparison against another Gaussian process regression corroborates best reducing competitor's 91.37% increasing 63%. Hence, proposed decreases execution time be applied evolution without deteriorating closed-loop performance. To authors' knowledge, this first been tested robot.

Язык: Английский

---

A novel ensemble network based on CNN‐AM‐BiLSTM learner for temperature prediction of distillation columns

The Canadian Journal of Chemical Engineering, Год журнала: 2025, Номер unknown

Опубликована: Март 5, 2025

Abstract In recent years, complexity has significantly increased in chemical processes where a distillation column serves as crucial unit. It is worthwhile to develop an accurate and reliable predictive model maintain the steady operation condition of column. Although data‐driven models that do not rely on any prior knowledge present promising approach, they encounter challenges associated with nonlinearity dynamic behaviour within process data. To tackle these challenges, deep learning‐based combined distilled spatiotemporal attention ensemble network (CDSAEN) proposed. The CDSAEN constructed by sequentially integrating multiple base learners, which are iteratively generated decreasing span lengths through boosting method implemented specially designed extraction evaluation function. learner, convolutional neural (CNN), mechanism (AM), bidirectional long short‐term memory (BiLSTM) utilized adaptively capture intricate features establish robust mapping relationship from inputs output. Real‐world data system plant reconstructed time series dataset subsequently fed into for training forecast temperature apparatus advance. results exhibited effectiveness reliability. Additionally, comparison six other approaches, proposed attained superior performance mean absolute error (MAE) = 0.084, root squared (RMSE) 0.108, R 2 0.974. This study can provide support maintaining stable columns processes.

Язык: Английский

---

LSTM with shallow NNs for indoor temperature long-term predictions in refrigeration systems

Neural Computing and Applications, Год журнала: 2024, Номер unknown

Опубликована: Окт. 16, 2024

Язык: Английский

---

Dynamic modeling and predictive control of boil-off gas generation during LNG loading

Computers & Chemical Engineering, Год журнала: 2022, Номер 160, С. 107698 - 107698

Опубликована: Янв. 30, 2022

Язык: Английский

---

Artificial neural network based identification of process dynamics and neural network controller design for continuous distillation column

Sustainable Energy Technologies and Assessments, Год журнала: 2023, Номер 57, С. 103168 - 103168

Опубликована: Апрель 5, 2023

Язык: Английский

---

A Leap Forward in Chemical Process Design: Introducing an Automated Framework for Integrated AI and CFD Simulations

Computers & Chemical Engineering, Год журнала: 2024, Номер unknown, С. 108906 - 108906

Опубликована: Окт. 1, 2024

Язык: Английский

---

A New Self-Tuning Nonlinear Model Predictive Controller for Autonomous Vehicles

Complexity, Год журнала: 2023, Номер 2023, С. 1 - 9

Опубликована: Янв. 16, 2023

Autonomous driving has recently been in considerable progress, and many algorithms have suggested to control the motions of driverless cars. The model predictive controller (MPC) is one efficient approaches by which speed direction near future an automobile could be predicted controlled. Even though MPC enormous benefit, performance (minimum tracking error) such a strictly depends on appropriate tuning its parameters. This paper applies particle swarm optimization (PSO) algorithm find global minimum error controller’s parameters ultimately calculating front steering angle directed motor force wheels autonomous vehicle (AV). article consists acquiring dynamics, extended control, paradigm. proposed approach compared with previous research literature simulation results show higher performance, also it less computationally expensive. that method only three adjustable overshoot about 8% RMSE 0.72.

Язык: Английский

---

Control of an Industrial Distillation Column Using a Hybrid Model with Adaptation of the Range of Validity and an ANN‐based Soft Sensor

Chemie Ingenieur Technik, Год журнала: 2023, Номер 95(7), С. 1114 - 1124

Опубликована: Май 16, 2023

Abstract Advanced control schemes such as model predictive can be used to minimize the use of resources while guaranteeing specified product quality. In this paper, we consider an industrial mother liquor distillation column varying flow rate and composition feed. There are specifications for all streams. To address challenging problem, employ a nonlinear model‐predictive controller using hybrid model, which consists simple phenomenological augmented by data‐based component compensate plant‐model mismatch. The trustworthiness is addressed domain validity estimated one‐class support vector machine. During operation, it may turn out that also reliable in wider range, therefore, data recently visited operating points recorded extended if sufficiently accurate. improve performance controller, artificial neural network estimate from available measurements.

Язык: Английский

---