Surface stabilization treatment serves as a primary method to promote stable rust layer formation on weathering steel (WS). However, due to the complex and multicomponent chemical formulations of stabilization treatment agents (STA), the precise control over STA component ratios to achieve the best stabilization treatment effect remains highly challenging. This study combines high-throughput experiment and machine learning method to establish an optimization framework for designing rust layer STA formulation. By employing high-throughput droplet dispensing experiments and wire beam electrode electrochemical testing, a predictive model is constructed using the AdaBoost algorithm. Interpretability analysis is further integrated to guide Bayesian optimization for iterative formulation refinement. After two optimization cycles, the optimal STA formulation (0.70 g/L CuSO₄, 0.20 g/L MgSO₄, 0.60 g/L Na₂HPO₄, and 0.20 g/L tannic acid) is identified from over 2.8 million candidate formulations. The optimized STA promotes the generation of stable rust layer on Q420 WS, which effectively reduces rust layer defects, inhibits corrosive medium penetration, and significantly enhances the corrosion resistance of WS.

The discovery of synergistic strategies effectively improves the corrosion inhibition capability of amino acids. However, the wide variety of amino acid formulations and the time-consuming nature of corrosion tests make combinatorial discovery challenging to achieve. Herein, a library of 70 amino acids was created and tested in a high-throughput manner. Benefiting from a vast amount of labeled data of amino acid formulations, an interpretable machine learning approach was used to reveal the contribution of molecular features to inhibition performance of amino acids and the synergisms in the optimal formulation. The synergism was verified by electrochemical tests and quantum chemical calculations.

Machine learning is a powerful means for the rapid development of high-performance functional materials. In this study, we presented a machine learning workflow for predicting the corrosion resistance of a self-healing epoxy coating containing ZIF-8@Ca microfillers. The orthogonal Latin square method was used to investigate the effects of the molecular weight of the polyetheramine curing agent, molar ratio of polyetheramine to epoxy, molar content of the hydrogen bond unit (UPy-D400), and mass content of the solid microfillers (ZIF-8@Ca microfillers) on the low impedance modulus (lg|Z|_0.01Hz) values of the scratched coatings, generating 32 initial datasets. The machine learning workflow was divided into two stages: In stage I, five models were compared and the random forest (RF) model was selected for the active learning. After 5 cycles of active learning, the RF model achieved good prediction accuracy: coefficient of determination (R ²) = 0.709, mean absolute percentage error (MAPE) = 0.081, root mean square error (RMSE) = 0.685 (lg(Ω·cm²)). In stage II, the best coating formulation was identified by Bayesian optimization. Finally, the electrochemical impedance spectroscopy (EIS) results showed that compared with the intact coating ((4.63 ± 2.08) × 10¹¹ Ω·cm²), the |Z|_0.01Hz value of the repaired coating was as high as (4.40 ± 2.04) × 10¹¹ Ω·cm². Besides, the repaired coating showed minimal corrosion and 3.3% of adhesion loss after 60 days of neutral salt spray testing.

In this work, an active protective epoxy coating with weathering resistant, corrosion-warning, and self-healing properties was developed by incorporating tannic acid (TA) loaded mesoporous silica (MSN-TA) nanocontainers. The introduction of MSN-TA nanocontainers could alleviate the coating degradation via scavenging the radicals generated during UV irradiation. Compared with the blank coating, the coating containing 5 wt.% MSN-TA nanocontainers exhibited much less degradation in surface morphology, wettability and glossiness, and maintained a good barrier property after 384 h of accelerated weathering. Once the coating was damaged, the released TA could react with the Fe³⁺ ions to form a chelate that endowed the coating scratch with a visible black coloration, i.e. triggering a self-warning capability to indicate the initial onset of corrosion. In addition, the generated chelate could inhibit extensive corrosion propagation, offering a significant self-healing effect demonstrated by the stabilized impedance modulus values during 28 days of immersion in NaCl solution.

Following the construction of a dataset of cross-category corrosion inhibitors at different concentrations based on 1241 data from 184 research papers, a performance prediction model incorporating 2D–3D molecular graph representation and corrosion inhibitor concentration information was established. This model was shown to effectively predict the inhibition efficiency (IE) of different categories of corrosion inhibitors for carbon steel in 1 mol/L HCl solution. The model was also able to predict IEs of corrosion inhibitors at different concentrations. The results demonstrated that 3D features of corrosion inhibitors, especially those of large molecules, had a significant impact on the prediction precision of IEs.

Organic coatings are one of the most used and versatile technologies to mitigate corrosion of metals. However, organic coatings are susceptible to defects and damages that may not be easily detected. If not repaired timely, these defects may develop into major coating failures due to corrosion occurring in the damaged region, thereby limiting the lifetime of the to be protected structure. Thus, the development of smart coatings that can accurately identify corrosion location and reliably recover the damage autonomously is of particular interest. Herein, we reported a robust, corrosion-sensing and self-healing coating which incorporated pH-sensitive ZIF-8-capped CaCO₃ microcontainers containing the healing agent tung oil (TO) and the corrosion indicator/inhibitor 1,10-phenanthrolin-5-amine (APhen). The spontaneous leakage of incorporated TO and APhen was restrained, and the release initiated when local pH variation occurred. The corrosion protection performance of the coatings implanted with different contents of smart microcontainers were evaluated. The intact epoxy coating containing 7.5 wt% of the microcontainers exhibited the best protection performance with low water absorption (0.65 wt%), low O₂ permeability (0.21 × 10^–15 cm³ cm cm⁻² s⁻¹ Pa⁻¹), and a high storage modulus (3.0 GPa). Electrochemical impedance spectroscopy (EIS) measurements in 3.5 wt% NaCl solution demonstrated superior durability of the composite coating after self-healing. The immersion test and neutral salt spray test confirmed the coating can accurately report corrosion sites via coloration.

Current experimental verification, computational modeling, and machine learning methods for predicting corrosion inhibition efficiency (IE) are limited to specific inhibitor categories with high cost and poor generalization. In this study, a cross-category corrosion inhibitor dataset is constructed and a three-level direct message passing neural network (3 L–DMPNN) model using molecular structure information that integrates atomic-level, chemical bond-level, and molecular-level features to predict the IEs of compounds in a specific environment is established. This work demonstrates that the 3 L–DMPNN model can predict IEs of cross-category corrosion inhibitors from other independent literature and experimental dataset effectively and quickly.

Herein, we report the development of a self-sensing and active corrosion protection coating which incorporates pH-sensitive multilayer chitosan/alginate-covered CaCO₃ microcontainers containing 1,10-phenanthrolin-5-amine (APhen). The microcontainers can respond to pH variation to release APhen which serves not only as a corrosion indicator but also as an inhibitor. An epoxy coating doped with 5 wt% microcontainers exhibited improved corrosion performance and was capable of inhibiting corrosion spreading from the damaged area in a 3.5 wt% NaCl solution. The salt spray test showed that corrosion damage can be quickly detected by the appearance of a red color within 2 min.

This study investigated the deterioration of a lubricant-infused anodic aluminium oxide surface in a 1 M NaCl solution for ∼200 days. Direct observation by cryo-SEM and quantitative analyses by UV spectroscopy and EIS revealed that the long-term deterioration of the lubricant-infused surface was divided into two stages: the surface-adhered lubricant layer gradually dissolved at a constant rate until the substrate was exposed; afterwards the lubricant infused in the nanochannels began to diffuse and was depleted after ∼200 days. The EIS results also revealed that the defects reduced the corrosion resistance of the lubricant-infused surface considerably.

This work introduces a novel nanocomposite coating with dual-action self-healing corrosion protection activated by the photothermal response of plasmonic titanium nitride nanoparticles (TiN NPs). TiN@mesoporous SiO₂ core–shell nanocontainers were developed as reservoirs for benzotriazole (BTA) corrosion inhibitors and incorporated into the shape memory epoxy coating matrix. Under near-infrared (NIR) light irradiation, the thermogenesis effect of TiN could not only promote the release of corrosion inhibitors from nanocontainers into the crevice, but also trigger the shape memory effect of damaged epoxy to merge the coating scratch. As such, the dual-action self-healing mechanisms combining the formation of an inhibitor-based protective layer and the scratch closure efficiently suppressed the corrosion process at the exposed metal surface. Surface characterization and electrochemical measurement results proved that the nanocomposite coating incorporated with 2 wt% of TiN-BTA@SiO₂ exhibited the optimal corrosion protection as well as an excellent self-healing performance that can be initiated within 30 s of NIR illumination. This photo-controlled self-healing approach is potentially useful in designing next-generation self-healing coatings with ultrafast response time and high healing efficiency.

Recently, lubricant-infused surfaces (LIS) have emerged as a prominent class of surface technology for antifouling, anti-icing and anticorrosion applications. However, long-term corrosion exposure and mechanical damages may deteriorate the practical performance of LIS during application. In this study, a robust LIS was fabricated by the vacuum impregnation of mineral oil into anodized aluminum oxide (AAO) nanochannels with a depth of 50 μm. The impregnation of the lubricant through the entire depth of the high-aspect-ratio nanochannels was visualized under cryo-scanning electron microscopy (cryo-SEM) and also confirmed by weight gain measurements. Electrochemical impedance spectroscopy (EIS) and potentiodynamic polarization (PDP) tests showed that the lubricant stored in the deep nanochannels of LIS can provide excellent corrosion protection during long-term immersion. Furthermore, the as-prepared LIS demonstrated superior resistance to mechanical damage due to a self-healing effect by the lubricant. As shown by cryo-SEM observation and PDP tests, the micro-cracks formed on the LIS can be instantaneously repaired by the in-flow of the oil from the surrounding surface. In the tribological tests, the LIS also presented high wear resistance and superior mechanical durability.