Learning Based Model Predictive Control of Combustion Timing in Multi-Cylinder Partially Premixed Combustion Engine

Li, Xiufei; Yin, Lianhao; Tunestål, Per; Johansson, Rolf

doi:10.4271/2019-24-0016

Cited by 3 publications

(3 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…More importantly, it has the feature of solving systems with constraints. 22,23 As an advanced process control algorithm, MPC has a wide variety of applications in battery management system optimization, electric vehicles control, energy storage arrangement, and microgrid power quality improvement. [24][25][26][27] Therefore, the aim of this research is, firstly, to develop a detailed thermal management model for a PEFC system.…”

Section: Discussionmentioning

confidence: 99%

“…The main advantage of the MPC is that it allows the current timeslot to be optimized while keeping future timeslots in account, which features its ability to anticipate future events and take control accordingly. More importantly, it has the feature of solving systems with constraints . As an advanced process control algorithm, MPC has a wide variety of applications in battery management system optimization, electric vehicles control, energy storage arrangement, and microgrid power quality improvement .…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Temperature control strategy for polymer electrolyte fuel cells

et al. 2020

Int J Energy Res

Self Cite

View full text Add to dashboard Cite

Summary A polymer electrolyte fuel cell (PEFC) is an electrochemical device that converts chemical energy directly to electrical energy, and its performance greatly depends on its operating temperature. Therefore, in this paper, a novel thermodynamic PEFC model with the airflow cooling method is firstly developed for the PEFC system. Then, a novel model predictive control (MPC) controller is designed to control the stack temperature at an optimal value by adjusting the air flow rate on the basis of the developed thermodynamic PEFC model. The thermodynamic PEFC model and the designed controlling strategies are simulated and analysed in Matlab/Simulink. Three tests are conducted to estimate the reliability of the developed controllers concerning different operating conditions: (a) typical perturbation in the current load, (b) any perturbation in the current load, and (c) variation of the ambient temperature. The simulation results demonstrate that the MPC controller can effectively control the stack temperature at the desired value. Moreover, the MPC controller shows much superior effects compared with the conventional proportional integral derivative (PID) controller. In addition, the developed coolant circuit model can be easily applied to various PEFC systems. The MPC controller shows potential also for other controlling issues of PEFC systems due to its strong robustness and fast response.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Temperature control strategy for polymer electrolyte fuel cells

et al. 2020

Int J Energy Res

Self Cite

View full text Add to dashboard Cite

show abstract

“…29 Previous works 144,145 are based on iterative learning to study the engagement effect of wet clutch. In Li et al, 146 the LBMPC controller uses the main injection timing to manage the combustion timing. In Jin et al, 147 an adaptive predictive level method based on machine learning was proposed to solve the problem of predictive control of the power converter's limited control set model.…”

Section: Other Applicationsmentioning

confidence: 99%

Emerging methodologies in stability and optimization problems of learning‐based nonlinear model predictive control: A survey

Meng

Shen

Karimi

2022

Circuit Theory & Apps

View full text Add to dashboard Cite

Since last 40 years, the theory and technology of model predictive control (MPC) have been developed rapidly. However, nonlinear MPC still faces difficulties such as high online computational complexity and inability to accurately model the system. In order to improve or solve the problems mentioned above of MPC, recent researches have deepened the learning‐based control. The learned method can model unknown or highly uncertain nonlinearities. And the emergence of efficient algorithms has greatly improved the feasibility of computing. Stability is at the heart of control design. Learning‐based nonlinear model predictive control (LB‐NMPC) has achieved systematic research results in the past 10 years. But the stability of LB‐NMPC is still an open question that has not been fully addressed in the literature. This review mainly summarizes the latest research progress of LB‐NMPC. More specifically, the uncertainty and online optimization problems of the considered systems are investigated mainly focusing on the use of learning techniques. At the same time, the research hotspots such as the control stability and constraint satisfaction of LB‐NMPC are briefly discussed. Finally, the application of LB‐NMPC technology in integrated circuits, path tracking control, and other fields is reviewed, which provides a reference for the research and application of LB‐NMPC.

show abstract

Adaptive Model Predictive Control of Combustion in Flex-Fuel Heavy Duty Compression-Ignition Engine

Tunestål

Johansson

2020

IFAC-PapersOnLine

View full text Add to dashboard Cite

Learning Based Model Predictive Control of Combustion Timing in Multi-Cylinder Partially Premixed Combustion Engine

Cited by 3 publications

References 13 publications

Temperature control strategy for polymer electrolyte fuel cells

Temperature control strategy for polymer electrolyte fuel cells

Emerging methodologies in stability and optimization problems of learning‐based nonlinear model predictive control: A survey

Adaptive Model Predictive Control of Combustion in Flex-Fuel Heavy Duty Compression-Ignition Engine

Contact Info

Product

Resources

About