Combined power management/design optimization for a fuel cell/battery plug-in hybrid electric vehicle using multi-objective particle swarm optimization

Geng, Bo; Mills, James K.; Sun, Dong

doi:10.1007/s12239-014-0067-x

Cited by 40 publications

(12 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…PSO can be utilized for the hyper-parameters tuning of the ML algorithm [Kennedy and Eberhart (1995)]. Compared with other metaheuristic algorithms [Montazeri-Gh, Poursamad and Ghalichi (2006); Ma, Xu, Wang et al 2015; Long and Nhan (2012); Castaings, Lhomme, Trigui et al (2016)], PSO requires fewer parameters to be tuned and less computational efforts for multi-objective optimization [Yang (2014); Geng, Mills and Sun (2014)]. Inspired by the social behavior of bird flocking, PSO is an evolutionary optimization algorithm in which a population of individuals changes with time.…”

Section: Pso Algorithmmentioning

confidence: 99%

The Prediction of Self-Healing Capacity of Bacteria-Based Concrete Using Machine Learning Approaches

Zhuang¹,

Zhou²

2019

Computers, Materials &Amp; Continua

View full text Add to dashboard Cite

Advances in machine learning (ML) methods are important in industrial engineering and attract great attention in recent years. However, a comprehensive comparative study of the most advanced ML algorithms is lacking. Six integrated ML approaches for the crack repairing capacity of the bacteria-based self-healing concrete are proposed and compared. Six ML algorithms, including the Support Vector Regression (SVR), Decision Tree Regression (DTR), Gradient Boosting Regression (GBR), Artificial Neural Network (ANN), Bayesian Ridge Regression (BRR) and Kernel Ridge Regression (KRR), are adopted for the relationship modeling to predict crack closure percentage (CCP). Particle Swarm Optimization (PSO) is used for the hyper-parameters tuning. The importance of parameters is analyzed. It is demonstrated that integrated ML approaches have great potential to predict the CCP, and PSO is efficient in the hyperparameter tuning. This research provides useful information for the design of the bacteria-based self-healing concrete and can contribute to the design in the rest of industrial engineering.

show abstract

Section: Pso Algorithmmentioning

confidence: 99%

The Prediction of Self-Healing Capacity of Bacteria-Based Concrete Using Machine Learning Approaches

Zhuang¹,

Zhou²

2019

Computers, Materials &Amp; Continua

View full text Add to dashboard Cite

show abstract

“…In transportation, PEMFC is preferred over the other FC technologies, since PEMFC has the advantages of low operating temperature, higher power density, high efficiency etc. The research on the PEMFC-based HES is of multidirectional [10][11][12][13][14][15][16][17][18][19][20][21][22]. These are classified based on the following attributes:…”

Section: Introductionmentioning

confidence: 99%

“…• DO and EMO for PEMFC-based HES: The formulation of DO and EMO approaches is carried out in [13][14][15][16][17][18][19], respectively. The combined DO and EMO approach is reported in [20][21][22]. The objective functions formulated in these DO and EMO approaches are minimisation of the HES cost [13][14][15]21], minimisation of the mass/volume of HES [14], minimisation of fuel consumption [18][19][20][21][22], maximisation of the HES efficiency [11,14] etc.…”

Section: Introductionmentioning

confidence: 99%

“…The combined DO and EMO approach is reported in [20][21][22]. The objective functions formulated in these DO and EMO approaches are minimisation of the HES cost [13][14][15]21], minimisation of the mass/volume of HES [14], minimisation of fuel consumption [18][19][20][21][22], maximisation of the HES efficiency [11,14] etc. The constraints of the DO and EMO approaches include the vehicle performance constraints in terms of acceleration time, gradability [14,[16][17][18][19]22] etc., the constraint of the dynamic behaviour of the energy sources [14,[17][18][19][20][21], and the maximum size limitation of the HES components [22].…”

Section: Introductionmentioning

confidence: 99%

“…This includes hybrid electric vehicle [14,[18][19][20]22], plug-in hybrid electric vehicle [13,21], locomotive [15,16], transit bus [17], tramway [12] etc. • Solution approach for the DO and EMO problems: The solution strategies used can be categorised into: (i) mathematical and enumerative approaches such as non-linear programming [16], branch and bound algorithm [18], dynamic programming [6] etc.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Design optimisation for component sizing using multi‐objective particle swarm optimisation and control of PEM fuel cell‐battery hybrid energy system for locomotive application

Sarma

Ganguly

2020

IET Electrical Systems in Transportation

View full text Add to dashboard Cite

This study presents a design optimisation (DO) approach for optimal component sizing of the proton exchange membrane fuel cell (PEMFC)-battery hybrid energy system (HES) and a controller design approach for DC-bus voltage regulation and load sharing control for the HES so that the proposed HES is capable of replacing the diesel locomotive WDM-3D used to haul intercity passenger trains in India. The DO approach is formulated as a multi-objective optimisation problem with objective functions of simultaneous minimisation of the total cost of HES and total fuel consumption under the operational constraints of battery state-of-charge limit and instantaneous power balance. Two energy management strategies (EMSs) are proposed for instantaneous power balance between the HES and locomotive power demand. The DO problem is solved for a chosen drive cycle using strength Pareto evolutionary algorithm-2-based particle swarm optimisation, in which an EMS is used as a subroutine. The Pareto front obtained with the multi-objective DO problem consists of a set of solutions with different sizes of PEMFC and battery. A MATLAB-Simulink model is developed with the proposed control strategy. The simulation results show that the designed controllers satisfactorily work under the dynamically varying load similar to a locomotive.

show abstract

PHEV powertrain co-design with vehicle performance considerations using MDSDO

Azad

Behtash

Houshmand

et al. 2019

Struct Multidisc Optim

View full text Add to dashboard Cite

Combined power management/design optimization for a fuel cell/battery plug-in hybrid electric vehicle using multi-objective particle swarm optimization

Cited by 40 publications

References 17 publications

The Prediction of Self-Healing Capacity of Bacteria-Based Concrete Using Machine Learning Approaches

The Prediction of Self-Healing Capacity of Bacteria-Based Concrete Using Machine Learning Approaches

Design optimisation for component sizing using multi‐objective particle swarm optimisation and control of PEM fuel cell‐battery hybrid energy system for locomotive application

PHEV powertrain co-design with vehicle performance considerations using MDSDO

Contact Info

Product

Resources

About