Skip to content
DraconiticResearch
Search Sources API
203,234 studies31 sourcesUpdated 58 min ago
Peer-reviewedCC BY 4.0Molecules

Interpretable Prediction of Interfacial Resistance for an Imidazoline–Sodium Molybdate–Tween 80 Corrosion Inhibitor Using Bayesian-Optimized Stacking

  • Changfeng Fan1,2
  • Xue Wang1,3
  • Xinfu Che4
  • Xianghua Zhan1,2
  • Xiaoli Yin1,2
  • Debao Gao5
  • Binchao Gao5
  • Qihao Zhao1
  • Yancong Liu1,2,6
6 affiliations
  1. 1Shandong Institute of Petrochemical and Chemical Technology, Dongying 257061, China
  2. 2Shandong Engineering Research Center for Green Manufacturing and Intelligent Control, Dongying 257061, China
  3. 3College of Chemical Engineering, China University of Petroleum, Qingdao 266580, China
  4. 4Jack Artificial Lift Machinery Co., Ltd., Dongying 257061, China
  5. 5School of Mechanical and Automotive Engineering, Qingdao University of Technology, Qingdao 266580, China
  6. 6College of Mechanical and Electronic Engineering, China University of Petroleum, Qingdao 266580, China
Open at sourceDOICite

Abstract

Predicting the performance of multicomponent corrosion inhibitors requires models that relate composition to electrochemical response and provide interpretable formulation guidance. This study combined Latin hypercube sampling and Bayesian-optimized stacking to investigate an imidazoline–sodium molybdate–Tween 80 inhibitor for mild steel in 3.5 wt.% NaCl. A dataset of 90 formulations linked component concentrations to total interfacial resistance, Rtotal, obtained from electrochemical impedance spectroscopy. The response comprised pore resistance and charge-transfer resistance. The stacking ensemble combined K-nearest neighbors, support vector regression and LightGBM with a ridge regression meta-learner. In ten-fold evaluation following dataset-level hyperparameter selection, stacking achieved R2 = 0.9036, a mean squared error of 969.46 (Ω·cm2)2 and a mean absolute percentage error of 2.22%. SHapley Additive exPlanations (SHAP) assigned normalized mean absolute attributions of 49.7%, 48.0% and 2.3% to Tween 80, imidazoline and sodium molybdate, respectively. These values identify influential predictors within the sampled domain rather than independent chemical contributions. Complementary polarization and surface observations supported adsorption-mediated protection with possible molybdate-associated interfacial reinforcement. By connecting formulation composition, electrochemical response and model attribution, this framework supports the prioritization of inhibitor mixtures under the investigated conditions.

Related

  1. Catch-and-Release of Molybdate [MoO4] 2– by a Synthetic “Molybdophore” Host.
    Shannon M. Leahy, Ethan T. Kang, Hemant P. Yennawar +1
    ChemRxivPreprintLicence not statedGeneral chemistryChemRxiv
  2. Strain-induced suppression of thermochromism in divalent cobalt molybdate thin films
    Kiri van Koughnet, Joey Williamson, Kane Hill +10
    Chemical SciencePeer-reviewedCC BYFull textMaterials & polymersHALEurope PMC
  3. DISSOLVR: An Interpretable and Fast Framework for Aqueous and Organic Solubility Prediction
    Vansh Ramani, Har Ashish Arora, Dhairya Kuchhal +2
    arXivPreprintCC BY 4.0Full textPhysical chemistryarXiv
  4. Cation-Directed Host–Guest Assembly and Reversible Wheel to Cluster Interconversion in a 20-Molybdate System
    Arun Pal, Alisher Kuanysh, Vinaya Siby +10
    Chemistry - A European JournalPeer-reviewedCC BY 4.0Full textInorganic & organometallic chemistryMaterials & polymersHAL
  5. Synthesis and structure of (NH₄)₁₂[Mo₃₆O₁₁₂(OH)₄(H₂O)₁₀], the first example of the [Mo₃₆O₁₁₂]⁸⁻ molybdate anion cluster to bear a charge of 12.
    Rajpal S Gaur, Stephanie L Brock, Cassandra L Ward
    Acta crystallographica. Section E, Crystallographic communicationsPeer-reviewedCC BYFull textMaterials & polymersEurope PMC

Cite

BibTeXRIS
BibTeX
@article{fan2026interpretable,
  title = {{Interpretable Prediction of Interfacial Resistance for an Imidazoline–Sodium Molybdate–Tween 80 Corrosion Inhibitor Using Bayesian-Optimized Stacking}},
  author = {Changfeng Fan and Xue Wang and Xinfu Che and Xianghua Zhan and Xiaoli Yin and Debao Gao and Binchao Gao and Qihao Zhao and Yancong Liu},
  journal = {Molecules},
  year = {2026},
  month = nov,
  doi = {10.3390/molecules31213978},
  url = {https://www.mdpi.com/1420-3049/31/21/3978},
  note = {CC BY 4.0},
}
RIS
TY  - JOUR
TI  - Interpretable Prediction of Interfacial Resistance for an Imidazoline–Sodium Molybdate–Tween 80 Corrosion Inhibitor Using Bayesian-Optimized Stacking
AU  - Changfeng Fan
AU  - Xue Wang
AU  - Xinfu Che
AU  - Xianghua Zhan
AU  - Xiaoli Yin
AU  - Debao Gao
AU  - Binchao Gao
AU  - Qihao Zhao
AU  - Yancong Liu
PY  - 2026
DA  - 2026/11/04
JO  - Molecules
DO  - 10.3390/molecules31213978
UR  - https://www.mdpi.com/1420-3049/31/21/3978
AB  - Predicting the performance of multicomponent corrosion inhibitors requires models that relate composition to electrochemical response and provide interpretable formulation guidance. This study combined Latin hypercube sampling and Bayesian-optimized stacking to investigate an imidazoline–sodium molybdate–Tween 80 inhibitor for mild steel in 3.5 wt.% NaCl. A dataset of 90 formulations linked component concentrations to total interfacial resistance, Rtotal, obtained from electrochemical impedance spectroscopy. The response comprised pore resistance and charge-transfer resistance. The stacking ensemble combined K-nearest neighbors, support vector regression and LightGBM with a ridge regression meta-learner. In ten-fold evaluation following dataset-level hyperparameter selection, stacking achieved R2 = 0.9036, a mean squared error of 969.46 (Ω·cm2)2 and a mean absolute percentage error of 2.22%. SHapley Additive exPlanations (SHAP) assigned normalized mean absolute attributions of 49.7%, 48.0% and 2.3% to Tween 80, imidazoline and sodium molybdate, respectively. These values identify influential predictors within the sampled domain rather than independent chemical contributions. Complementary polarization and surface observations supported adsorption-mediated protection with possible molybdate-associated interfacial reinforcement. By connecting formulation composition, electrochemical response and model attribution, this framework supports the prioritization of inhibitor mixtures under the investigated conditions.
SN  - 1420-3049
ER  -