Review on model predictive control: an engineering perspective

The International Journal of Advanced Manufacturing Technology, Journal Year: 2021, Volume and Issue: 117(5-6), P. 1327 - 1349

Published: Aug. 11, 2021

Abstract Model-based predictive control (MPC) describes a set of advanced methods, which make use process model to predict the future behavior controlled system. By solving a—potentially constrained—optimization problem, MPC determines law implicitly. This shifts effort for design controller towards modeling to-be-controlled process. Since such models are available in many fields engineering, initial hurdle applying is deceased with MPC. Its implicit formulation maintains physical understanding system parameters facilitating tuning controller. can even systems, cannot be by conventional feedback controllers. With most theory laid out, it time concise summary and an application-driven survey. review article should serve as such. While beginnings MPC, several widely noticed paper have been published, comprehensive overview on latest developments, applications, missing today. reviews current state art including theory, historic evolution, practical considerations create intuitive understanding. We lay special attention applications order demonstrate what already possible Furthermore, we provide detailed discussion implantation details general strategies cope computational burden—still major factor Besides key methods development this points trends emphasizing why they next logical steps

Language: Английский

---

Development and application of machine learning‐based prediction model for distillation column

International Journal of Intelligent Systems, Journal Year: 2021, Volume and Issue: 36(5), P. 1970 - 1997

Published: Jan. 14, 2021

Distillation is an energy-consuming process in the chemical industry. Optimizing operating conditions can reduce amount of energy consumed and improve efficiency processes. Herein, we developed a machine learning-based prediction model for distillation applied to optimization. The mainly used control temperature column. We that predicted according following procedure: (1) data collection; (2) characteristic extraction from collected learning time; (3) min–max normalization performance; (4) case study conducted select artificial neural network algorithm, optimization method, batch size, which are most appropriate elements predicting production stage temperature. result revealed was observed with root mean squared error 0.0791 coefficient determination 0.924 when long short-term memory Adam size 128 were applied. calculated steam consumption required consistently maintain by utilizing model. calculation indicated expected be reduced approximately 14%, average flow rate 2763–2374 kg/h. This proposed method applying confirmed operation could through efficient operation.

Language: Английский

---

Classification and recycling of recyclable garbage based on deep learning

Journal of Cleaner Production, Journal Year: 2023, Volume and Issue: 414, P. 137558 - 137558

Published: May 24, 2023

Language: Английский

---

Energy utilization assessment of a semi-closed greenhouse using data-driven model predictive control

Journal of Cleaner Production, Journal Year: 2021, Volume and Issue: 324, P. 129172 - 129172

Published: Sept. 30, 2021

With the global increase in food demand, closed and controlled greenhouses are an essential source for year-round crop production. Maintaining optimum conditions inside greenhouse throughout year is critical to improving quality yield. However, consume more resources than other commercial buildings due their inefficient operation structure. Therefore, a data-driven model predictive control approach semi-closed proposed temperature reducing energy consumption this study. The method consists of multilayer perceptron representing system integrated with objective function optimization algorithm. trained using historical data from solar radiation, outside temperature, humidity difference, fan speed, HVAC as input parameters predict temperature. model's performance evaluated under varying scenarios, such increasing prediction time step changing number samples training set. Results illustrated that MPC had better adaptive winter summer RMSE value 0.33 °C 0.36 °C, respectively. Similarly, resulted reduction 7.70% 16.57% season. framework flexible can be applied systems by tuning on new

Language: Английский

---

Artificial neural networks for bio-based chemical production or biorefining: A review

Renewable and Sustainable Energy Reviews, Journal Year: 2021, Volume and Issue: 153, P. 111748 - 111748

Published: Oct. 22, 2021

Language: Английский

---

Process knowledge-based random forest regression for model predictive control on a nonlinear production process with multiple working conditions

Advanced Engineering Informatics, Journal Year: 2022, Volume and Issue: 52, P. 101561 - 101561

Published: March 9, 2022

Language: Английский

---

Effective MPC strategies using deep learning methods for control of nonlinear system

International Journal of Dynamics and Control, Journal Year: 2024, Volume and Issue: 12(10), P. 3694 - 3707

Published: May 23, 2024

Language: Английский

---

Artificial neural network-based model predictive control for optimal operating conditions in proton exchange membrane fuel cells

Journal of Cleaner Production, Journal Year: 2022, Volume and Issue: 380, P. 135049 - 135049

Published: Nov. 3, 2022

Language: Английский

---

Machine learning-based predictive control using on-line model linearization: Application to an experimental electrochemical reactor

Process Safety and Environmental Protection, Journal Year: 2023, Volume and Issue: 197, P. 721 - 737

Published: Aug. 14, 2023

Language: Английский

---

Dynamic real-time energy saving control of pressure-swing distillation based on artificial neural networks

Chemical Engineering Science, Journal Year: 2023, Volume and Issue: 282, P. 119271 - 119271

Published: Sept. 15, 2023

Language: Английский

---