Author(s)

Amber Himanen

Affiliation(s)

Department of Applied Physics, Aalto University, Finland.

Corresponding Author

Amber Himanen

ABSTRACT

In recent years, traditional energy sources such as coal, oil, and natural gas have been gradually depleted, and the use of large amounts of fossil energy has caused environmental pollution. In order to reduce carbon dioxide emissions, the country actively promotes wind, The development of renewable energy sources such as light, hydropower, and hydrogen energy, and the key to the promotion and application of these energy technologies is the research and development of new materials. At present, the development of new materials mainly relies on researchers to conduct experimental optimization based on the material structure and its expected catalytic activity for a specific system, resulting in a slow development process of new materials. With the further development of computational materials science, researchers have integrated a large number of material databases on material structure and performance characterization, and gradually optimized and screened new materials through comparison. This paper reviews the current design ideas and synthesis methods of material development, focusing on artificial intelligence (AI) and expounding the recent research based on AI Method design, models and algorithms in the process of preparing renewable energy materials, and summarized AI The research significance and development process used in material design, and finally the AI Methods The development of design and preparation of renewable energy materials is prospected, the material optimization model proposed by this research group is introduced, and cases of the model's successful application in material optimization for hydrogen evolution from electrolysis of water and hydrogen production from sodium borohydride are listed. The future, AI The technology has very broad application prospects in theoretical calculations, synthetic design, performance prediction, and material microstructure characterization analysis of new materials.

KEYWORDS

Material preparation; Artificial Intelligence (AI); Renewable energy; Material optimization

CITE THIS PAPER

Amber Himanen. Research progress of artificial intelligence in the field of renewable energy materials research and development. World Journal of Materials Science. 2023, 1(2): 1-12. DOI:10.61784/wjms231268.

REFERENCES

[1] Wu C L, Li Y T, Li Y. Hydrogen Storage and Transpor tation. Beijing: Chemical Industry Press, 2021. 37. 

[2] Gu B L. Material Science Systems Engineering: the key to the establishment of China's new material industry system. Science & Technology Review, 2015, 33 (10): 1.

[3] Zheng L, Li H J, Xu X F. Catalytic decomposition of N2O over Mg-Co composite oxides hydrothermally prepared by using carbon sphere as template. Journal of Fuel Chemistry Technology, 2018, 46(5): 569.

[4] Sun L, Searson P C, Chien C L. Electrochemical deposi tion of nickel nanowire arrays in single-crystal mica films. Applied Physics Letters, 1999, 74(19): 2803.

[5] Adhyapak P V, Karandikar P, Vijayamohanan K, Athawale A A, Chandwadkar A J. Synthesis of silver nanowires inside mesoporous MCM-41 host . Materials letters, 2004, 58 (7-8 ): 1168.

[6] Wei J Q, Jiang B, Li Y H, Wu D H. Preparation and structure of boron carbide nanowires. Acta Physico- Chimica Sinica, 2004, 20(3): 256.

[7] Chen L, Chen J M, Zhou H D. Application and development of microemulsification technology in preparation of inorganic nanomaterials. Journal of Materials Science and Engineering, 2004, 22(1): 4.

[8] Li L, Zhao B S. Multi-objective optimization on head forming process parameters based on artificial neural network and genetic algorithm. Forging & Stamping Technology, 2021, 46(5): 39.

[9] Branowski B, Zablocki M, Sydor M. The material indices method in the sustainable engineering design process: a review. Sustainability, 2019, 11(19): 5465.

[10] Chen C T, Chrzan D C, Gu G X. Nano-topology optimization for materials design with atom-by-atom control. Nature Communications, 2020, 11(1): 1.

[11] Deng H, Cheng L, To A C. Distortion energy-based topology optimization design of hyperelastic materials. Structural Multidisciplinary Optimization, 2019, 59 (6): 1895.

[12] Xiao R J, Li H, Chen L Q. Development of new materials for Lithium batteries based on materials genome approach. Acta Physica Sinica, 2018, 67(12): 9.

[13] Huang Y, Yue L H. Application of uniform design method in the development of power ferrite materials.  Journal of Magnetic Materials and Devices, 2009, 40 (3): 4.

[14] Liu Y Q, Wang C X, Zhang A M, Shan B, Zhao Y K, Peng W. Light-off temperature of precious metal-based three-way catalytic materials on basis of hierarchical clustering by recognition algorithm. Chinese Journal of Rare Metals, 2022, 46(7): 982.

[15] Lee M. An analysis of the effects of artificial intelligence on electric vehicle technology innovation using patent data. World Patent Information, 2020, 63: 102002.

[16] Tian Q C, Wang M L. Research progress of deep learning algorithms. Computer Engineering and Applications, 2019, 55(22): 9.

[17] Chen J H. Application of artificial intelligence technology and computational materials science in materials research. Proceedings of the 8th Youth Science and Technology Forum of China Aeronautical Society. Guangdong, China, 2018. 1326.

[18] Huang J P, Deng X Z. Research and application of key technology of intelligent manufacturing of building ceramics. Foshan Ceramics, 2021, 31(2): 4.

[19] Zhang J M, Yang W D, Li Y. Application of artificial intelligence in composite materials research. Advances in Mechanics, 2021, 51(4): 36.

[20] Sun H Y, Gao X X, Yang H X. A review of full-scale wind-field measurements of the wind-turbine wake effect and a measurement of the wake-interaction effect. Renewable Sustainable Energy Reviews, 2020, 132: 110042.)

[21] Wang X F, Zeng X W, Yang X, Li J L. Feasibility study of offshore wind turbines with hybrid monopile foundation based on centrifuge modeling. Applied Energy, 2018, 209: 127.

[22] Zhang Y, Huang T, Bompard E F. Big data analytics in  smart grids: a review. Energy Informatics, 2018, 1 (1): 1.

[23] Hong Y Y, Rioflorido C L P P. A hybrid deep learning- based neural network for 24h aheadwind power forecasting. Applied Energy, 2019, 250: 530.

[24] Lin Z, Liu X L. Wind power forecasting of an offshore wind turbine based on high-frequency SCADA data and deep learning neural network. Energy, 2020, 201: 117693.

[25] Kumar Y, Ringenberg J, Depuru Soma S, Devabhaktuni V K, Lee Jin W, Nikolaidis E, Andersen B, Afjeh A. Wind energy: trends and enabling technologies. Renewable and Sustainable Energy Reviews, 2016, 53: 209.

[26] Pasquali F, Suk H, Behdad S, Hall J. Method for design life of energy system components based on levelized cost of energy. Journal of Cleaner Production, 2020, 268: 121971.

[27] Li S H. Wind power prediction using recurrent multilayer perceptron neural networks. In: 2003 IEEE Power Engineering Society General Meeting. Toronto, Canada, 2003. 2325.

[28] Barbounis T G, Theocharis J B, Alexiadis M C, Dokopoulos P S. Long-term wind speed and power forecasting using local recurrent neural network models. IEEE Transactions on Energy Conversion, 2006, 21(1): 273.

[29] Qin L, Wei Z. Integrating dynamic Bayesian network and physics-based modeling for risk analysis of a time- dependent power distribution system during hurricanes . Reliability Engineering System Safety, 2022, 220: 108290.

[30] Johansson T B, Kelly H, Reddy A K, Williams R H. Renewable fuels and electricity for a growing world econ omy: defining and achieving the potential. Energy Studies Review, 1992, 4(3): 201.

[31] Salkuti, Reddy S. Multi-objective based optimal scheduling of microgrid considering uncertainties. In: 2019 International Conference on Cutting-edge Technologies in Engineering. Uttar Pradesh, India, 2019. 50.

[32] Berndt E R, Wood D O. Technology, prices, and the derived demand for energy. The Review of Economics Statistics, 1975, 57: 259.

[33] Kojima A, Teshima K, Shirai Y, Miyasaka T. Organometal halide perovskites as visible-light sensitizers for photovoltaic cells. Journal of the American Chemical Society, 2009, 131(17): 6050.

[34] Park N G. Perovskite solar cells: an emerging photovoltaic technology. Materials Today, 2015, 18(2): 65.

[35] Manser J S, Saidaminov M I, Christians J A, Bakr O M, Kamat P V. Making and breaking of lead halide perovskites. Accounts of Chemical Research, 2016, 49(2): 330.

[36] Meng L, You J B, Yang Y. Addressing the stability is sue of perovskite solar cells for commercial applications. Nature Communications, 2018, 9(1): 1.

[37] Jiang S, Wu C C, Li F, Zhang Y Q, Zhang Z H, Zhang Q H, Chen Z J, Qu B, Xiao L X, Jiang M L. Machine learning(ML)-assisted optimization doping of KI in MAPbI3 solar cells. Rare Metals, 2021, 40(7): 1698.

[38] Park N G, Gr?tzel M, Miyasaka T, Zhu K, Emery K. Towards stable and commercially available perovskiteso lar cells. Nature Energy, 2016, 1(11): 1.

[39] Allam O, Holmes C, Greenberg Z, Kim K C, Jang S S. Density functional theory-machine learning approach to analyze the bandgap of elemental halide perovskites and ruddlesden-popper phases. Chem. Phys. Chem., 2018, 19(19): 2559.

[40] Pilania G, Mannodi K A, Uberuaga B, Ramprasad R, Gubernatis J, Lookman T. Machine learning bandgaps of double perovskites. Scientific Reports, 2016, 6(1): 1.

[41] Takahashi K, Takahashi L, Miyazato I, Tanaka Y. Searching for hidden perovskite materials for photovoltaic systems by combining data science and first principle calculations. ACS Photonics, 2018, 5(3): 771.

[42] Li Y Y, Stroe D I, Cheng Y H, Sheng H M, Sui X, Teodorescu R. On the feature selection for battery state of health estimation based on charging-discharging profiles. Journal of Energy Storage, 2021, 33: 102122.

[43] Lin C P, Cabrera J, Yang F f, Ling M H, Tsui K L, Bae S J. Battery state of health modeling and remaining useful life prediction through time series model. Applied Energy, 2020, 275: 115338.

[44] Sodeyama K, Igarashi Y, Nakayama T, Tateyama Y, Okada M. Liquid electrolyte informatics using an exhaustive search with linear regression. Physical Chemistry Chemical Physics, 2018, 20(35): 22585.

[45] Aurbach D, Pollak E, Elazari R, Salitra G, Kelley C S, Affinito J. On the surface chemical aspects of very high energy density, rechargeable Li-sulfur batteries. Journal of the Electrochemical Society, 2009, 156 (8): A694.

[46] Okamoto Y, Kubo Y. Ab initio calculations of the redox potentials of additives for lithium-ion batteries and their prediction through machine learning. ACS Omega, 2018, 3(7): 7868.

[47] Jalem R, Aoyama T, Nakayama M, Nogami M. Multivariate method-assisted Ab initio study of olivine-type LiMXO4(Main group M2+ -X5+ and M3+ -X4+)compositions as potential solid electrolytes. Chemistry of Materials, 2012, 24(7): 1357.

[48] Chen C, Lu Z H, Ciucci F. Data mining of molecular dynamics data reveals Li diffusion characteristics in garnet Li7La3Zr2O12. Scientific Reports, 2017, 7(1): 1.

[49] Cunha R P, Lombardo T, Primo E N, Franco A A. Artificial intelligence investigation of NMC cathode manufac turing parameters interdependencies. Batteries Supercaps, 2020, 3(1): 60.

[50] Ma S A, Jiang M D, Tao P, Song C Y, Wu J B, Wang  J, Deng T, Shang W. Temperature effect and thermal   impact in lithium-ion batteries: a review. Progress   in Natural Science: Materials International, 2018, 28 (6): 653.

[51] Str?bel M, Pross B J, Kopp M, Birke K P. Impedance based temperature estimation of lithium ion cells using artificial neural networks. Batteries, 2021, 7 (4): 85.

[52] Zambalov S D, Yakovlev I A, Skripnyak V A. Numerical simulation of hydrogen combustion process in rotary engine with laser ignition system. International Journal of Hydrogen Energy, 2017, 42(27): 17251.

[53] Yu P, Wang F M, Shifa T A, Zhan X Y, Lou X D, Xia F, He J. Earth abundant materials beyond transition metal dichalcogenides: a focus on electrocatalyzing hydrogen evolution reaction. Nano Energy, 2019, 58: 244.

[54] Jiang L, Gonzalez D A, Ling C J, Malik A, Roskilly A P, Smallbone A J. PEF plastic synthesized from industrial carbon dioxide and biowaste. Nature Sustainability, 2020, 3(9): 761.

[55] Whiting K, Carmona L G, Sousa T. A review of the use of exergy to evaluate the sustainability of fossil fuels and non-fuel mineral depletion. Renewable Sustainable Energy Reviews, 2017, 76: 202.

[56] Suermann M, Gimpel T, Bühre L V, Schade W, Bensmann B, Hanke Rauschenbach R. Femtosecond laser-induced surface structuring of the porous transport layers in proton exchange membrane water electrolysis. Journal of Materials Chemistry A, 2020, 8 (9 ) : 4898.

[57] Simari C, Potsi G, Policicchio A, Perrott a I, Nicotera THE.

Clay-carbon nanotubes hybrid materials for nanocompos ite membranes: advantages of branched structure for proton transport under low humidity conditions in PEMFCs. The Journal of Physical Chemistry C, 2016, 120 (5): 2574.

[58] Ding R, Wang R, Ding Y Q, Yin W J, Liu Y D, Li J, Liu J G. Designing AI-aided analysis and prediction models for nonprecious metal electrocatalyst-based proton-exchange membrane fuel cells. AngewandteChemie, 2020, 132(43): 19337.

[59] Ding R, Yin W J, Cheng G, Chen Y W, Wang J K, Wang X B, Han M, Zhang T R, Cao Y L, Zhao H M, Wang S P, Li J, Liu J G. Effectively increasing Pt utilization efficiency of the membrane electrode assembly in proton exchange membrane fuel cells through multiparameter optimization guided by machine learning. ACS Applied Materials Interfaces, 2022, 14(6): 8010.

[60] Mai Y L, Xie X S, Wang Z D, Yan C F, Liu G H. Effect of heat treatment temperature on the Pt3Co binary metal catalysts for oxygen reduced reaction and DFT calculations. Journal of Fuel Chemistry Technology, 2022, 50(1): 114.

[61] Zhu X R, Yan J X, Gu M, Liu T Y, Dai Y F, Gu Y H, Li Y F. Activity origin and design principles for oxygen  reduction on dual-metal-site catalysts: a combined density functional theory and machine learning study. The Journal of Physical Chemistry Letters, 2019, 10 (24): 7760.

[62] Mao L, Jackson L. Comparative study on prediction of fuel cell performance using machine learning approaches. In: Proceedings of the International MultiConference of Engineers and Computer Scientists. Hong Kong, China: Newswood, 2016. 52

[63] Ma R, Yang T, Breaz E, Li Z l, Briois P, Gao F. Data-driven proton exchange membrane fuel cell degradation predication through deep learning method. Applied Energy, 2018, 231: 102.

[64] Chen K, Laghrouche S, Djerdir A. Degradation predic tion of proton exchange membrane fuel cell based on grey neural network model and particle swarm optimization. Energy Conversion Management, 2019, 195: 810.

[65] Yang Z J, Wang B W, Sheng X, Wang Y P, Ren Q, He S Q, Xuan J, Jiao K. An artificial intelligence solution for predicting short-term degradation behaviors of proton exchange membrane fuel cell. Applied Sciences, 2021, 11(14): 6348.

[66] Tritt T M. Holey and unholey semiconductors. Science, 1999, 283(5403): 804.

[67] Bell L E. Cooling, heating, generating power, and recovering waste heat with thermoelectric systems. Science, 2008, 321(5895): 1457.

[68] Sundarraj P, Maity D, Roy S S, Taylor R A. Recent advances in thermoelectric materials and solar thermoelec tric generators-a critical review. RSC Advances, 2014, 4(87): 46860.

[69] Kirihara A, Uchida K I, Kajiwara Y, Ishida M, Nakamura Y, Manako T, Saitoh E, Yorozu S. Spin-current driven thermoelectric coating and J Nature Materials, 2012, 11 (8) :

[70] Uchida K i, Adachi H, Kikkawa T, Kirihara A, Ishida M, Yorozu S, Maekawa S, Saitoh E. Thermo electric generation based on spin Seebec k effects . Proceedings of the IEEE, 2016, 104 (10): 1946.

[71] Butler K T, Davies D W, Cartwright H, Isayev O, Walsh A. Machine learning for molecular and materials science. Nature, 2018, 559(7715): 547.

[72] Lu W H, Ruan H D, Zeng X F, Shu J Q. Research on non-singular terminal sliding mode control of pmsm for  large flotation machine optimized by AEPSO algorithm. Copper Engineering, 2022, (4): 81.

[73] Iwasaki Y, Takeuchi I, Stanev V, Kusne A G, Ishida M, Kirihara A, Ihara K, Sawada R, Terashima K, Someya H. Machine-learning guided discovery of a new  thermoelectric material. Scientific Reports, 2019, 9 (1): 1.

[74] Zhang Y F, Zhang J X, Lu Q M, Zhang X, Liu X. Prog ress in preparation and properties of thermoelectric oxides. Chinese Journal of Rare Metals, 2004, 28 (5): 907.

[75] Li X Y, Song G H, Li G P, Liu Y, Hu F. Advances in Mg3X2(X=Sb, Bi)-based thermoelectric materials. Chinese Journal of Rare Metals, 2022, 46(12): 1621.

[76] Abdellahi M, Ghayour H, Bahmanpour M. Effect of process parameters and synthesis method on the performance of thermoelectric ceramics: a novel simulation. Ceramics International, 2015, 41(5): 6991.

[77] Wang M S, Fu W Y, Du L, Wei Y S, Rao P, Wei L, Zhao X S, Wang Y, Sun S H. Surface engineering by doping manganese into cobalt phosphide towards highly efficient bifunctional HER and OER electrocatalysis . Applied Surface Science, 2020, 515: 146059.

[78] Wei Y S, Zou P C, Yue Y C, Wang M S, Fu W Y, Si S, Wei L, Zhao X S, Hu G Z, Xin H L. One-pot synthesis of B/P-codoped Co-Mo dual-nanowafer electrocatalysts for overall water splitting. ACS Applied Materials Interfaces, 2021, 13(17): 20024.

[79] Wei Y S, Wang M S, Fu W Y, Si S, Wei L, Zhao X S, Wang Y. Mn doped CoP/Ni foam catalyst for hydrogen generation from hydrolysis of sodium borohydride. Materials Letters, 2022, 308: 131166.