Limestone calcined clay cement (LC3) is a sustainable alternative to ordinary Portland cement, capable of reducing the binder’s carbon footprint by 40% while satisfying all key performance metrics. The inherent compositional heterogeneity in select components of LC3, combined with their convoluted chemical interactions, poses challenges to conventional analytical models when predicting mechanical properties. Although some studies have employed machine learning (ML) to predict the mechanical properties of LC3, many have overlooked the pivotal role of feature selection. Proper feature selection not only refines and simplifies the structure of ML models but also enhances these models’ prediction performance and interpretability. This research harnesses the power of the random forest (RF) model to predict the compressive strength of LC3. Three feature reduction methods—Pearson correlation, SHapley Additive exPlanations, and variable importance—are employed to analyze the influence of LC3 components and mixture design on compressive strength. Practical guidelines for utilizing these methods on cementitious materials are elucidated. Through the rigorous screening of insignificant variables from the database, the RF model conserves computational resources while also producing high-fidelity predictions. Additionally, a feature enhancement method is utilized, consolidating numerous input variables into a singular feature while feeding the RF model with richer information, resulting in a substantial improvement in prediction accuracy. Overall, this study provides a novel pathway to apply ML to LC3, emphasizing the need to tailor ML models to cement chemistry rather than employing them generically.
Ultrahigh temperature ceramics (UHTCs) have melting points above 3000°C and outstanding strength at high temperatures, thus making them apposite structural materials for high‐temperature applications. Di‐borides, nitride, and carbide compounds—processed via various techniques—have been extensively studied and used in the manufacture of UHTCs. Current analytical models, based on our current but incomplete understanding of the theory, are unable to produce a priori predictions of mechanical properties of UHTCs based on their mixture designs and processing parameters. As a result, researchers have to rely on experiments—which are often costly and time‐consuming—to understand composition–structure–performance links in UHTCs. This study employs machine learning (ML) models (i.e., random forest and artificial neural network models) to predict Young's modulus, flexural strength, and fracture toughness of UHTCs in relation to a wide range of mixture designs, processing parameters, and testing conditions. Outcomes demonstrate that adequately trained ML models can yield reliable predictions, a priori, of the three aforesaid mechanical properties. The prediction performance on Young's modulus is superior to flexural strength and fracture toughness. Next, the ML model with the best prediction performance is utilized to evaluate and rank the impacts of input variables on Young's modulus. Finally, on the basis of such classification of consequential and inconsequential input variables, this study develops an easy‐to‐use, closed‐form analytical model to predict Young's modulus of UHTCs. Overall, this study highlights the ability of data‐driven numerical models to complement, or even replace, time‐consuming experiments, thereby accelerating the development of UHTCs.
more » « less- PAR ID:
- 10370372
- Publisher / Repository:
- Wiley-Blackwell
- Date Published:
- Journal Name:
- Journal of the American Ceramic Society
- Volume:
- 105
- Issue:
- 11
- ISSN:
- 0002-7820
- Format(s):
- Medium: X Size: p. 6851-6863
- Size(s):
- p. 6851-6863
- Sponsoring Org:
- National Science Foundation
More Like this
-
more » « less
-
more » « less
Abstract Zirconium carbide (ZrC) powder, batched to a ratio of 0.98 C/Zr, was prepared by carbothermal reduction of ZrO2with carbon black. Nominally phase‐pure ZrC powder had a mean particle size of 2.4 μm. The synthesized powder was hot‐pressed at 2150°C to a relative density of > 95%. The mean grain size was 2.7 ± 1.4 μm with a maximum observed grain size of 17.5 μm. The final hot‐pressed billets had a C/Zr ratio of 0.92, and oxygen content of 0.5 wt%, as determined by gas fusion analysis. The mechanical properties of ZrC0.92O0.03were measured at room temperature. Vickers’ hardness decreased from 19.5 GPa at a load of 0.5 kgf to 17.0 GPa at a load of 1 kgf. Flexural strength was 362.3 ± 46 MPa, Young's modulus was 397 ± 13 MPa, and fracture toughness was 2.9 ± 0.1 MPa•m1/2. Analysis of mechanical behavior revealed that the largest ZrC grains were the strength‐limiting flaw in these ceramics.
-
more » « less
This experimental study investigates the effects of dispersion techniques on the mechanical properties of POSS‐epoxy nanocomposites. The POSS is dispersed into the epoxy resin by stoichiometrically varying the weight fraction from 0.5 to 10 wt% and materials are prepared using three different dispersion techniques. Various mechanical properties are reported as functions of processing parameters and weight fractions. It is found that the nanocomposites with highly dispersed POSS show higher modulus and toughness values. For example, nanocomposites prepared by ultrasonication show increases in elastic and flexural modulus values by average amounts of 23% and 15%, respectively. Also, it is found that fracture toughness values increased for all three processing techniques, with the highest increase by an average of 50% at 8 wt% of POSS inclusion for nanocomposites prepared by ultrasonication. TEM images of the nanocomposites demonstrate that the properties are also affected by the formation of soft domains at higher loading levels of POSS. Further evidence on the soft domains is found in the variations of
T g. FTIR spectroscopy shows evidence of SiOSi stretching, again suggesting the formation of compliant domains due to POSS‐POSS agglomeration. POLYM. COMPOS., 39:E2445–E2453, 2018. © 2018 Society of Plastics Engineers -
Thermoplastic elastomers based on ABA triblock copolymers are typically limited in modulus and strength due to crack propagation within the brittle regions when the hard end-block composition favors morphologies that exhibit connected domains. Increasing the threshold end-block composition to achieve enhanced mechanical performance is possible by increasing the number of junctions or bridging points per chain, but these copolymer characteristics also tend to increase the complexity of the synthesis. Here, we report an in situ polymerization method to successfully increase the number of effective junctions per chain through grafting of poly(styrene) (PS) to a commercial thermoplastic elastomer, poly(styrene)–poly(butadiene)–poly(styrene) (SBS). The strategy described here transforms a linear SBS triblock copolymer–styrene mixture into a linear-comb-linear architecture in which poly(styrene) (PS) grafts from the mid-poly(butadiene) (PBD) block during the polymerization of styrene. Through systematic variation in the initial SBS/styrene content, nanostructural transitions from disordered spheres to lamellar through reaction-induced phase transitions (RIPT) were identified as the styrene content increased. Surprisingly, maximum mechanical performance (Young's modulus, tensile strength, and elongation at break) was obtained with samples exhibiting lamellar nanostructures, corresponding to overall PS contents of 61–77 wt% PS (including the original PS in SBS). The PS grafting from the PBD block increases the modulus and the strength of the thermoplastic elastomer while preventing brittle fracture due to the greater number of junctions afforded by the PS grafts. The work presented here demonstrates the use of RIPT to transform standard SBS materials into polymer systems with enhanced mechanical properties.more » « less
-
more » « less
Abstract Dynamic hydrogel crosslinking captures network reorganization and self‐healing of natural materials, yet is often accompanied by reduced mechanical properties compared to covalent analogs. Toughening is possible in certain materials with processing by directional freeze‐casting and salting‐out, producing hierarchically organized networks with directionally enhanced mechanical properties. The implications of including dynamic supramolecular crosslinking alongside such processes are unclear. Here, a supramolecular hydrogel prepared from homoternary crosslinking by pendant guests with a free macrocycle is subsequently processed by directional freeze‐casting and salting‐out. The resulting hydrogels tolerate multiple cycles of compression. Excitingly, supramolecular affinity dictates the mechanical properties of the bulk hydrogels, with higher affinity interactions producing materials with higher Young's modulus and enhanced toughness under compression. The importance of supramolecular crosslinking is emphasized with a supramolecular complex that is converted in situ into a covalent crosslink. While supramolecular hydrogels do not fracture and spontaneously self‐heal when cut, their covalent analogs fracture under moderate strain and do not self‐heal. This work shows a molecular‐scale origin of bulk hydrogel toughening attributed to affinity and dynamics of supramolecular crosslinking, offering synergy in combination with bulk post‐processing techniques to yield materials with enhanced mechanical properties tunable at the molecular scale for the needs of specific applications.
