Neural network based explicit MPC for chemical reactor control

Kiš, Karol; Klaučo, Martin

doi:10.2478/acs-2019-0030

Cited by 16 publications

(5 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Karol and Martin [72] applied ANN to a fixed univariate MPC system. The model predictive controller uses an algorithm called receding horizon policy proposed by Mayne et al [73].…”

Section: Neural Network-based Model Predictive Controlmentioning

confidence: 99%

Application of Artificial Neural Networks in Chemical Process Control

Wang

Chen

2022

AJRCoS

View full text Add to dashboard Cite

An important data-driven model is the artificial neural network. Artificial neural networks have been widely used in many domains of chemical processes due to its robustness, fault tolerance, self-adaptive capability, and self-learning ability. For the chemical process with nonlinearity and strong coupling, artificial neural networks can model and control the process well and make up for the lack of traditional PID control technology. As a result, ANN has emerged as a significant positive trend for chemical process control. In this paper, the principle, development history, and common structure of artificial neural networks are first outlined. Then the role of artificial neural networks in chemical process control is introduced in three aspects: improved PID control, improved model predictive control, and for hybrid models. The important effect of artificial neural networks in chemical process control is reflected by comparison. Finally, it is proposed that chemical process control can be more developed by applying more deep learning algorithms and developing multiple neural networks and hybrid models in chemical process control.

show abstract

“…Karol and Martin [72] applied ANN to a fixed univariate MPC system. The model predictive controller uses an algorithm called receding horizon policy proposed by Mayne et al [73].…”

Section: Neural Network-based Model Predictive Controlmentioning

confidence: 99%

Application of Artificial Neural Networks in Chemical Process Control

Wang

Chen

2022

AJRCoS

View full text Add to dashboard Cite

show abstract

“…Such controllers have already been used in other applications, such as diesel airpath control 26 or the control of chemical reactors. 27…”

Section: Design Of Multiple Inputs Multiple Outputs (Mimo) Controller...mentioning

confidence: 99%

Dynamic measurement with in-cycle process excitation of HCCI combustion: The key to handle complexity of data-driven control?

Bedei

Oberlies

Schaber

et al. 2022

International Journal of Engine Research

View full text Add to dashboard Cite

Homogeneous Charge Compression Ignition (HCCI) is a low temperature combustion technique with a high potential for reducing emissions while simultaneously improving fuel consumption. However, the high sensitivity to changing boundary conditions and low combustion stability at the edges of the operating range has lead to implementation challenges. Additionally, cyclic coupling through internal exhaust gas recirculation causes cyclic variations of the process, resulting in incomplete combustion, or even misfiring. Thus, consecutive cycles must be decoupled to increase the process stability. To achieve an accurate description of the coupling effects on a cycle-to-cycle and an inner-cyclic timescale, a novel measurement methodology is presented to generate data with a high variance. For this purpose, an active process excitation is performed to capture all relevant interactions between operating and feedback variables to enable modeling of the coupling effects on both timescales. To demonstrate the potential of the methodology, the generated data is used to design multiple input, multiple output (MIMO) models for both cyclic and inner-cyclic timescales. Artificial neural networks are then utilized to address the highly nonlinear process by taking advantage of the large amount of training data. Inverse process models are then used to implement a pure cycle-to-cycle and a multiscale MIMO closed-loop controller. Compared to state-of-the-art rule-based control approaches, the process stability and its thermodynamic efficiency are significantly improved. For the multiscale MIMO controller, a reduction of the standard deviation of the indicated mean effective pressure and the combustion phasing of more than 65% is achieved. In particular, the additional inner-cyclic feedback loop achieves a remarkable reduction of the standard deviation of approximately 35% and a 1.2% higher indicated efficiency compared to the cycle-to-cycle MIMO controller. The dynamic measurement with active in-cycle process excitation has proven to be an enabler for data-driven MIMO control of HCCI on multiple timescales.

show abstract

“…[ 260,261 ] Coupled with MPC schemes, deep neural networks registered highly improved control of chemical reactors. [ 262,263 ] Prosthesis and clinical systems successfully deployed deep neural network‐based predictors or classifiers in controller development. [ 264,265 ] An important type of deep neural network is convolutional neural network, in which neurons in a layer respond to selected inputs, some of which are aggregates of multiple neural outputs from the previous layer.…”

Section: Miscellaneous Ai‐based Process Control Technologiesmentioning

confidence: 99%

Artificial intelligence‐based process control in chemical, biochemical, and biomedical engineering

Dutta

Upreti

2021

Can J Chem Eng

View full text Add to dashboard Cite

In the last three decades, artificial intelligence (AI) has been increasingly and vigorously utilized for process control in chemical, biochemical, and biomedical engineering. These disciplines frequently involve fairly sophisticated processes under risks of operational upsets, and thus have an ever increasing demand of superior control strategies. As the deployment of AI in process control pushes the limits in this regard, the research advances, which are multitudinous and varied, need to be assimilated and organized to help promote further utilization and progress in the field. To that end, we examine more than 280 relevant research publications, and systematically collate the information. The AI‐based technologies are classified, and their over‐arching control paradigm is presented. Common AI‐based control technologies are then presented, which are based on expert systems, fuzzy logic, artificial neural networks, nature‐inspired algorithms, and hybrid approaches. Their working principles, types, and implementations are summarized along with advantages, limitations, and comparisons, if available. Important applications in the above disciplines are included with the help of tables that capture important details. A discussion is also provided on advanced and newly emerging AI‐based control technologies with pertinent applications. Overall trends are analyzed, and future prospects are identified based on the survey.

show abstract

Neural network based explicit MPC for chemical reactor control

Cited by 16 publications

References 17 publications

Application of Artificial Neural Networks in Chemical Process Control

Application of Artificial Neural Networks in Chemical Process Control

Dynamic measurement with in-cycle process excitation of HCCI combustion: The key to handle complexity of data-driven control?

Artificial intelligence‐based process control in chemical, biochemical, and biomedical engineering

Contact Info

Product

Resources

About