Artificial intelligence-based multi-objective optimisation for proton exchange membrane fuel cell: A literature review

Feng, Zhiming; Huang, Jian; Jin, Shiwei; Wang, Guanqi; Chen, Leo

doi:10.1016/j.jpowsour.2021.230808

Cited by 40 publications

(17 citation statements)

References 153 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The artificial wolf pack algorithm (AWPA) was embedded in the optimization to obtain the optimum ROMP reaction condition [26,41]. Wolves are gregarious animals and mostly live in packs.…”

Section: The Artificial Wolf Pack Algorithmmentioning

confidence: 99%

“…Over the past decades, computer-aided design in PEMFC field has facilitated the development of PEMFC [23][24][25]. As artificial intelligence (AI) has experienced rapid development in the past decade, it has been gradually employed in different fields to assist the design, and optimization issues [26][27][28][29]. AI-based optimization has gained astonishing achievements in material development research, such as searching for optimal reaction conditions and analyzing the results [30,31].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Artificial intelligence-based optimization for ring-opening metathesis polymerization of proton exchange membrane

Feng¹,

Jin²,

Xiang³

et al. 2023

Preprint

Self Cite

View full text Add to dashboard Cite

The proton exchange membrane (PEM) is one of the significant components in PEM fuel cells. However, conventional synthesis experiments for proton exchange membrane (PEM) require considerable workload and time due to complicated conditions and various influencing factors. Here we initially utilized artificial intelligence (AI) techniques based on the artificial wolf pack algorithm (AWPA) to optimize the synthesis reaction conditions of the ring-opening metathesis polymerization (ROMP) reaction of norbornene derivatives for PEM preparation. An empirical model was established based on four variables, including temperature, reaction time, catalyst amount and ratio of reactants, with two fitness functions, including molecular weight (MW) and molecular weight distribution (MWD). Four trend indices were used, including the mean average precision (mAP), the mean, standard deviation (mSTD), the moving mean of the average precision (mmAP) and the moving mean of standard derivation (mmSD). The theoretical optimum values of operating conditions were obtained successfully, including reactant ratio (0.71), temperature (41.23 oC), catalyst content (0.20) and reaction time (47.94 min). The method in this paper helps optimize PEM preparation conditions and guides a database for AI-aid ROMP reactions.

show abstract

“…The artificial wolf pack algorithm (AWPA) was embedded in the optimization to obtain the optimum ROMP reaction condition [26,41]. Wolves are gregarious animals and mostly live in packs.…”

Section: The Artificial Wolf Pack Algorithmmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Artificial intelligence-based optimization for ring-opening metathesis polymerization of proton exchange membrane

Feng¹,

Jin²,

Xiang³

et al. 2023

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…However, the models have been only verified under a constant current, and the operating conditions have not been fully considered. Inspired by the works of similar electrochemical systems, such as Li-ion batteries and hydrogen fuel cells [21][22][23], this paper presents a health status assessment and RUL prediction approach for µDMFC under different operating conditions, where a single degradation metric, such as the output voltage, no longer provides accurate RUL prediction, even when observed continuously. Although the polarization curves can provide accurate health status, such as the internal impedance of the cell, they are difficult to monitor in real time monitored and can only be measured offline at a low frequency.…”

Section: Introductionmentioning

confidence: 99%

Internal Characterization-Based Prognostics for Micro-Direct-Methanol Fuel Cells under Dynamic Operating Conditions

Zhang

Wang

et al. 2022

Sensors

View full text Add to dashboard Cite

Micro-direct-methanol fuel cells (μDMFCs) use micro-electro mechanical system (MEMS) technology, which offers high energy density, portable use, quick replenishment, and free fuel reforming and purification. However, the μDMFC is limited by a short effective service life due to the membrane electrode’s deterioration in electrochemical reactions. This paper presents a health status assessment and remaining useful life (RUL) prediction approach for μDMFC under dynamic operating conditions. Rather than making external observations, an internal characterization is used to describe the degradation indicator and to overcome intrusive influences in operation. Then, a Markov-process-based usage behavior prediction mechanism is proposed to account for the randomness of real-world operation. The experimental results show that the proposed degradation indicator alleviates the reduction in μDMFC output power degradation behavior caused by the user loading profile. Compared with the predictions of RUL using traditional external observation, the proposed approach achieved superior prognostic performance in both accuracy and precision.

show abstract

“…The employment of optimization algorithms and artificial intelligence constitutes a noticeable number of studies related to PEMFCs [5,32,[34][35][36][37][38][39][40][41][42][43][44]. To introduce the optimum operating conditions of an enhanced parallel flow field PEMFC, Ghasabehi et al [5] studied the impact of operating conditions on performance.…”

mentioning

confidence: 99%

“…They showed the application of the Black Widow Optimization Algorithm to catch the constants of an equation describing the cell's output voltage. There are different algorithms used to predict the output voltage of PEMFCs, such as Adaptive Sparrow Search Algorithm [41], Salp Swarm Algorithm [42], Sine-Cosine Crow Search Algorithm [45], Particle Swarm Optimization [45], Whale Optimization Algorithm [45], Hybrid Adaptive Differential Evolution Procedure [46], Grasshopper Optimization Algorithm [46], Particle Swarm Algorithm [38], Swarm Dolphin Algorithm [47], Grey Wolf Optimization Algorithm [48], Crow Search Algorithm [38], Teacher Learning Algorithm [38]. The accuracy and runtime ratio of different optimization methods can be different.…”

mentioning

confidence: 99%

Cathode Side Transport Phenomena Investigation and Multi-Objective Optimization of a Tapered Parallel Flow Field PEMFC

Jabbary

Ghasabehi

Shams

2022

Preprint

View full text Add to dashboard Cite

A Proton Exchange Membrane Fuel Cell (PEMFC) provides stable, emission-free, high-efficiency power. Water management and durability of PEMFCs are directly affected by transport phenomena at the cathode side. In the present study, transport phenomena are investigated and optimized in a tapered parallel flow field. Main channels in the flow field are tapered, which increases limiting current density by 41%. Two objectives, i.e. water saturation and transport resistance, are considered metrics for transport phenomena in a tapered parallel flow field PEMFC. Operating pressure, temperature, stoichiometries at both sides, and the porosity of gas diffusion layers are selected as parameters to be optimized. Two functions are generated for objectives by integrating 3D multiphase-flow computational fluid dynamics and Response Surface Methodology. Multi-Objective Optimization (MOO) is carried out with two different methods. Multi-Objective Particle Swarm Optimization (MOPSO) and Non-dominated Sorting Genetic Algorithm II (NSGA-II) are employed to produce two challenging Pareto fronts. The results demonstrate that MOPSO performs better than NSGA-II. MOPSO recognized quite the same Pareto front with lower runtime. In the last step, the Technique of Order Preference Similarity to the Ideal Solution (TOPSIS) is used to select an optimum point from the Pareto front. The results are compared against experimental data, and good correspondence is observed. The optimum features are temperature 323, pressure 1 atm, anode stoichiometry 3, cathode stoichiometry 2.62, and porosity 0.68. The porosity and pressure played the most significant roles in determining water saturation and resistance.

show abstract

Artificial intelligence-based multi-objective optimisation for proton exchange membrane fuel cell: A literature review

Cited by 40 publications

References 153 publications

Artificial intelligence-based optimization for ring-opening metathesis polymerization of proton exchange membrane

Artificial intelligence-based optimization for ring-opening metathesis polymerization of proton exchange membrane

Internal Characterization-Based Prognostics for Micro-Direct-Methanol Fuel Cells under Dynamic Operating Conditions

Cathode Side Transport Phenomena Investigation and Multi-Objective Optimization of a Tapered Parallel Flow Field PEMFC

Contact Info

Product

Resources

About