Related references
Note: Only part of the references are listed.
Article
Engineering, Civil
Shangjun Ye et al.
Summary: Real-time control of hydroelectric generating units and floodgates is crucial for the economy and safety of hydroelectric production. Existing methods have limitations in accuracy and fluctuation control. Therefore, a data-driven and physics-based coupled real-time model predictive control (MPC) method is proposed to enhance accuracy, reduce decision space, and incorporate feedback correction.
JOURNAL OF HYDROLOGY
(2023)
Article
Automation & Control Systems
Issa Hammoud et al.
Summary: This paper presents a data-driven model predictive control (MPC) approach for the current control of synchronous machines. The motor model is represented using a long-short term memory (LSTM) neural network (NN), which is obtained purely from collected data without any physical knowledge. As online optimization using the obtained data-driven model is not easily implementable in the available sampling time, the neural model is used to solve an MPC problem offline. Finally, the control policy is learned through another computationally implementable neural network that runs in real-time as a current controller. The proposed data-driven MPC controller is experimentally tested and benchmarked against MPC schemes incorporating physically-based models.
EUROPEAN JOURNAL OF CONTROL
(2022)
Article
Computer Science, Information Systems
Krzysztof Zarzycki et al.
Summary: This article deals with Model Predictive Control (MPC) algorithms that utilize Short Term Memory (LSTM) and Gated Recurrent Unit (GRU) neural networks for prediction. The traditional approach of using successively linearized LSTM or GRU models in MPC is found to be unsatisfactory in terms of prediction accuracy and control quality. The presented MPC control schemes employ online advanced trajectory linearization, resulting in simple quadratic optimization programs. The discussed approaches demonstrate excellent prediction accuracy and control quality, similar to those achieved with full nonlinear prediction and online nonlinear optimization in MPC. It is also revealed that the described MPC algorithms are several times faster than the nonlinear optimization-based MPC method. Furthermore, the performance of MPC based on LSTM and GRU networks is compared, with GRU networks being recommended for their simplicity.
INFORMATION SCIENCES
(2022)
Proceedings Paper
Automation & Control Systems
Tinu Vellamattathil Baby et al.
Summary: This study investigates perception and robust model-predictive control (MPC) strategies in realistic traffic environments using data from real-world driving experiments. The research focuses on a heterogeneous traffic environment with human-driven vehicles, optimizing fuel consumption and accounting for prediction errors with a data-driven algorithm and robust MPC strategy.
Article
Green & Sustainable Science & Technology
Byung-Ki Jeon et al.
Summary: There is a growing interest in saving building energy through model predictive control (MPC) studies, with data-driven models favored for their fast computation speed. A method involving data generation through a building energy model and using LSTM network for learning in MPC has been proposed. The MPC model successfully reduced grid energy consumption by 35% compared to a reference case and also reduced computation time by approximately 30%.
Article
Automation & Control Systems
Fabio Bonassi et al.
Summary: This paper provides sufficient conditions for ensuring the input-to-state stability (ISS) and incremental input-to-state stability (delta ISS) of Gated Recurrent Units (GRUs) neural networks. These conditions are applicable to both single-layer and multi-layer architectures, and involve nonlinear inequalities on the network's weights. The resulting training procedure is tested on a Quadruple Tank nonlinear benchmark system, demonstrating remarkable modeling performances.
SYSTEMS & CONTROL LETTERS
(2021)
Article
Automation & Control Systems
Enrico Terzi et al.
Summary: This article analyzes the stability properties of long short-term memory (LSTM) networks in the context of designing model predictive controllers (MPC) for plant models. It derives conditions for Input-to-State stability (ISS) and Incremental Input-to-State stability (delta ISS) of LSTM, designs an observer for state estimation convergence, and implements it in a MPC scheme for solving tracking problems. The closed-loop scheme is proven to be asymptotically stable, and numerical tests on a pH reactor simulator confirm the effectiveness of the proposed approach.
INTERNATIONAL JOURNAL OF ROBUST AND NONLINEAR CONTROL
(2021)
Article
Chemistry, Analytical
Krzysztof Zarzycki et al.
Summary: This study thoroughly compared the efficiency of LSTM and GRU neural networks in MPC, deriving MPC prediction equations and analyzing the performance under different model configurations. It was found that the GRU network performed well in control quality despite having fewer parameters than LSTM.
Proceedings Paper
Automation & Control Systems
Fabio Bonassi et al.
Summary: This paper explores the training and application of stable Gated Recurrent Units (GRUs) in a Nonlinear Model Predictive Control framework for offset-free tracking of constant references with guaranteed closed-loop stability, showing remarkable performance in a pH neutralization process benchmark test.
Article
Biochemical Research Methods
Pauli Virtanen et al.
Article
Engineering, Multidisciplinary
Xiaobo Jie et al.
MATHEMATICAL PROBLEMS IN ENGINEERING
(2020)
Article
Engineering, Chemical
Matthew J. Ellis et al.
CHEMICAL ENGINEERING RESEARCH & DESIGN
(2020)
Proceedings Paper
Automation & Control Systems
Daniele Masti et al.
Proceedings Paper
Automation & Control Systems
Danimir T. Doncevic et al.
Proceedings Paper
Automation & Control Systems
Bernardo B. Schwedersky et al.
Proceedings Paper
Automation & Control Systems
M. Schoukens et al.
Article
Mathematics, Applied
Joshua L. Proctor et al.
SIAM JOURNAL ON APPLIED DYNAMICAL SYSTEMS
(2016)
Article
Computer Science, Software Engineering
A Wachter et al.
MATHEMATICAL PROGRAMMING
(2006)
Article
Automation & Control Systems
KH Johansson
IEEE TRANSACTIONS ON CONTROL SYSTEMS TECHNOLOGY
(2000)
