电镀与涂饰

2025, 06, v.44 110-117

机器学习辅助筛选MOFs缓蚀剂载体及其吸附性能预测

黄晓珊¹ 关雅芳¹ 李惠琳¹ 龚凌涛¹ 明忠源² 李和国² 赵越² 吴玉芳¹ 梁红¹ 王雯菲¹ 乔智威¹

基金项目(Foundation): 国家自然科学基金（22478085,21978058）; 珠江人才计划（2019QN01L255）; 广东省自然科学基金（2022A1515011446,2023A1515240076,2021A1515010078）; 新型反应器与绿色化学工艺湖北省重点实验室开放/创新基金（NRG202407）; 西安现代化学研究所氟氮化工国家重点实验室（204-J-2022-1877）; 广州大学国家级大学生创新创业项目（202211078209,202311078015）; 广东大学生科技创新培育专项资金资助项目（pdjh2023a0406）

邮箱(Email):

DOI: 10.19289/j.1004-227x.2025.06.016

43	0	15
下载次数	被引频次	阅读次数

引用本文下载本文

PDF

引用导出

GB/T 7714-2015 MLA APA Refworks EndNote NoteExpress NoteFirst

摘要全文参考文献出版信息相关文章

摘要：

[目的]针对醇类、硫醇类有机缓蚀剂易挥发、表面稳定性差的问题，提出结合高通量计算筛选(HTS)与机器学习(ML)的MOFs(金属-有机框架化合物)材料设计策略，以实现高效缓蚀剂载体的快速开发。[方法]以甲醇、乙醇、甲硫醇和乙硫醇为目标分子，通过巨正则蒙特卡洛(GCMC)模拟计算31 399种假设性MOFs(hMOFs)的吸附性能，并采用8种机器学习算法建立结构-性能关系模型。[结果]在选取的8种机器学习方法中，梯度提升回归(GBR)、随机森林(RF)、极端梯度提升(XGB)和极端随机森林(ET)这4种算法均能很好地预测出MOF-缓蚀剂的表面吸附性能，其中吸附热、密度和孔隙率是影响吸附性能的关键参数。通过调整金属活性中心和有机链接有望获得高性能缓蚀剂。[结论]本研究建立的“HTS+ML”方法具有高效、快速、准确的优点，不仅能够节省大量人力、物力和时间，还能为有机缓蚀剂的性能提升和实际应用提供理论指导。

关键词： 有机缓蚀剂; 金属-有机框架; 机器学习; 高通量计算筛选; 吸附;

Abstract：

[Objective] To address the challenges of volatility and poor interfacial stability in alcohol-and thiol-based organic corrosion inhibitors, a design strategy for metal-organic frameworks(MOFs) integrating high-throughput computational screening(HTS) with machine learning(ML) was developed to enable rapid construction of highperformance inhibitor carriers. [Method] The adsorption performances of 31 399 kinds of hypothetical MOFs(hMOFs)for methanol, ethanol, methanethiol, and ethanethiol were simulated through grand canonical Monte Carlo(GCMC)calculations. The relationship model between structure and property of MOFs were established using eight kinds of ML methods. [Result] Among the eight ML methods selected, four algorithms i.e. gradient boosted regression(GBR), random forest(RF), extreme gradient boosting(XGB), and extreme random forest(ET), were able to predict the surface adsorption properties of MOF-corrosion inhibitor very well, and the adsorption heat, density, and porosity were identified as the key parameters governing adsorption performance. Strategic modification of metal active centers and organic linkers was demonstrated to be an effective approach for developing high-performance corrosion inhibitors. [Conclusion]The “HTS + ML” method established in this study has advantages of high efficiency, speed and accuracy, which not only saves a lot of manpower, material resources and time, but also provides theoretical guidance for the performance enhancement of organic corrosion inhibitors and their practical application.

KeyWords： organic corrosion inhibitor; metal–organic framework; machine learning; high-throughput computational screening; adsorption;

如需获取全文，请访问cnki.net

参考文献

[1]BENTISS F, TRAISNEL M, LAGRENEE M. The substituted 1,3,4-oxadiazoles:a new class of corrosion inhibitors of mild steel in acidic media[J]. Corrosion Science, 2000, 42(1):127-146.

[2]VALCARCE M B, LóPEZ C, VáZQUEZ M. The role of chloride,nitrite and carbonate ions on carbon steel passivity studied in simulating concrete pore solutions[J]. Journal of the Electrochemical Society,2019, 159(5):C244-C251.

[3]ASHASSI-SORKHABI H, GHALEBSAZ-JEDDI N, HSAHEMADEH F, et al. Corrosion inhibition of carbon steel in hydrochloric acid by some polyethylene glycols[J]. Electrochimica Acta, 2006, 51(18):3848-3854.

[4]FINSGAR M, JACKSON J. Application of corrosion inhibitors for steels in acidic media for the oil and gas industry:a review[J].Corrosion Science, 2014, 86:17-41.

[5]WU Y D, GUO L, TAN B C, et al. 5-mercapto-1-phenyltetrazole as a high-efficiency corrosion inhibitor for Q235 steel in acidic environment[J]. Journal of Molecular Liquids, 2021, 325:115132.

[6]MERIMI I, ASLAM R, HAMMOUTI B, et al. Adsorption and inhibition mechanism of(Z)-4-((4-methoxybenzylidene)amino)-5-methyl-2,4-dihydro-3H-1,2,4-triazole-3-thione on carbon steel corrosion in HCl:experimental and theoretical insights[J]. Journal of Molecular Structure, 2021, 1231:129901.

[7]DEYAB M A. Hydroxyethyl cellulose as efficient organic inhibitor of zinc-carbon battery corrosion in ammonium chloride solution:electrochemical and surface morphology studies[J]. Journal of Power Sources, 2015, 280:190-194.

[8]GHAZOUI A, BENCHAT N, EL-HAJJAJI F, et al. The study of the effect of ethyl(6-methyl-3-oxopyridazin-2-yl)acetate on mild steel corrosion in 1M HCl[J]. Journal of Alloys and Compounds, 2017, 693:510-517.

[9]ZHANG H B, CUI J L, SUN J C, et al. Corrosion inhibition of methanol towards stainless steel bipolar plate for direct formic acid fuel cell[J].International Journal of Hydrogen Energy, 2020, 45(55):30924-30931.

[10]BELARBI Z, VU TN, FARELAS F, et al. Thiols as volatile corrosion inhibitors for top of the line corrosion[J]. Corrosion, 2017, 73(7):892-899.

[11]POPOOLA L T. Organic green corrosion inhibitors(OGCIs):a critical review[J]. Corrosion Review, 2019, 37(2):71-102.

[12]CHEN K J, MADDEN D G, MUKHERJEE S, et al. Synergistic sorbent separation for one-step ethylene purification from a four-component mixture[J]. Science, 2019, 366(6462):241-246.

[13]李耀辉,廖宏儿,耿铁,等.镁合金表面Mg–MOF-74/硅烷复合涂层的制备及耐蚀性[J].电镀与涂饰, 2022, 41(4):245-250.LI Y H, LIAO H E, GENG T, et al. Preparation and corrosion resistance of Mg–MOF-74/silane composite coating on magnesium alloy surface[J].Electroplating&Finishing, 2022, 41(4):245-250.

[14]肖天铸,刘伟,纪茜. AZ31B镁合金表面Mg–Cu–MOF涂层的制备及性能[J].电镀与涂饰, 2023, 42(3):80-84.XIAO T Z, LIU W, JI Q. Preparation and properties of Mg–Cu–MOF coating on AZ31B magnesium alloy[J]. Electroplating&Finishing,2023, 42(3):80-84.

[15]杨强,王仁娟,黄博文,等.金属有机框架材料对水体中重金属离子去除性能及机理的研究进展[J].材料研究与应用, 2024, 18(2):309-328.YANG Q, WANG R J, HUANG B W, et al. Research progress on the removal performance and mechanism of metal–organic frameworks for heavy metal ions in water[J]. Materials Research and Application, 2024,18(2):309-328.

[16]LU Y Z H, ZHANG H C, CHAN J Y, et al. Homochiral MOF–polymer mixed matrix membranes for efficient separation of chiral molecules[J].Angewandte Chemie International Edition, 2019, 58(47):16699-17080.

[17]LIU Z W, ZHANG K, WU Y, XI H X. Effective enhancement on methanol adsorption in Cu-BTC by combination of lithium-doping and nitrogen-doping functionalization[J]. Journal of Materials Science,2018, 53(8):6080-6093.

[18]LIU Z W, ZHANG K, WU Y, XI H X. New functionalized IRMOF-10with strong affinity for methanol:a simulation study[J]. Applied Surface Science, 2018, 440:351-358.

[19]QIAO Z W, XU Q S, CHEETHAM A K, JIANG J W. High-throughput computational screening of metal–organic frameworks for thiol capture[J]. Journal of Physical Chemistry C, 2017, 121(40):22208-22215.

[20]BORBOUDAKIS G, STERGIANNAKOS T, FRYSALI M, et al.Chemically intuited, large-scale screening of MOFs by machine learning techniques[J]. npj Computational Materials, 2017, 3:1-6.

[21]YIN M, ZHANG L, WEI X X, et al. Detection of antibiotics by electrochemical sensors based on metal–organic frameworks and their derived materials[J]. Microchemical Journal, 2022, 183:107946.

[22]ANDERSON G, SCHWEITZER B, ANDERSON R, et al. Attainable volumetric targets for adsorption-based hydrogen storage in porous crystals:molecular simulation and machine learning[J]. Journal of Physical Chemistry C, 2019, 123(1):120-130.

[23]WEI X, PENG D, SHEN L, AI Y J, LU Z H et al. Analyzing of metal organic frameworks performance in CH4 adsorption using machine learning techniques:a GBRT model based on small training dataset[J].Journal of Environmental Chemical Engineering, 2023, 11(3):110086.

[24]WILMER C E, LEAF M, LEE C Y, FARHA O K, HAUSER B G,HUPP J T, SNURR R Q. Large-scale screening of hypothetical metal–organic frameworks[J]. Nature Chemistry, 2012, 4(2):83-89.

[25]CHUNG Y G, CAMP J, HARANCZYK M, et al. Computation-ready,experimental metal–organic frameworks:a tool to enable highthroughput screening of nanoporous crystals[J]. Chemistry of Materials, 2014, 26(21):6185-6192.

[26]WILLEMS T F, RYCROFT C, KAZI M, et al. Algorithms and tools for high-throughput geometry-based analysis of crystalline porous materials[J]. Microporous and mesoporous materials, 2012, 149(1):134-141.

[27]BUCIOR B J, ROSEN A S, HARANCZYK M, et al. Identification schemes for metal–organic frameworks to enable rapid search and cheminformatics analysis[J]. Crystal Growth&Design, 2019, 19(11):6682-6697.

[28]MA X C, LI L Q, ZENG Z, et al. Synthesis of nitrogen-rich nanoporous carbon materials with C3N-type from ZIF-8 for methanol adsorption[J].Chemical Engineering Journal, 2019, 363:49-56.

[29]XUE W D, ZHOU Q X, CUI X, et al. Metal–organic frameworksderived heteroatom-doped carbon electrocatalysts for oxygen reduction reaction[J]. Nano Energy, 2021, 86:106073.

[30]ZHANG L L, HUANG Q H, LI L F, et al. Automatic machine learning combined with high-throughput computational screening of hydrophobic metal–organic frameworks for capture of methanol and ethanol from the air[J]. ACS ES&T Engineering, 2024, 4(1):115-127.

[31]YAN Y L, SHI Z N, LI H L, et al. Machine learning and in-silico screening of metal–organic frameworks for O2/N2 dynamic adsorption and separation[J]. Chemical Engineering Journal, 2022, 427:131604.

[32]TANG H J, JIANG J W. In silico screening and design strategies of ethane-selective metal–organic frameworks for ethane/ethylene separation[J]. AIChE Journal, 2021, 67(3):e17025.

基本信息:

DOI：10.19289/j.1004-227x.2025.06.016

中图分类号:TP181;TG174.42

引用信息:

[1]黄晓珊,关雅芳,李惠琳等.机器学习辅助筛选MOFs缓蚀剂载体及其吸附性能预测[J].电镀与涂饰,2025,44(06):110-117.DOI:10.19289/j.1004-227x.2025.06.016.

基金信息:

国家自然科学基金（22478085,21978058）; 珠江人才计划（2019QN01L255）; 广东省自然科学基金（2022A1515011446,2023A1515240076,2021A1515010078）; 新型反应器与绿色化学工艺湖北省重点实验室开放/创新基金（NRG202407）; 西安现代化学研究所氟氮化工国家重点实验室（204-J-2022-1877）; 广州大学国家级大学生创新创业项目（202211078209,202311078015）; 广东大学生科技创新培育专项资金资助项目（pdjh2023a0406）

请选择需要下载的pdf数据

Summary