Meta-Analysis and Machine Learning Models to Optimize the Efficiency of Self-Healing Capacity of Cementitious Material

Abstract

Concrete and cement-based materials inherently possess an autogenous self-healing capacity. Despite the huge amount of literature on the topic, self-healing concepts still fail to consistently enter design strategies able to effectively quantify their benefits on structural performance. This study aims to develop quantitative relationships through statistical models and artificial neural network (ANN) by establishing a correlation between the mix proportions, exposure type and time, and width of the initial crack against suitably defined self-healing indices (SHI), quantifying the recovery of material performance. Furthermore, it is intended to pave the way towards consistent incorporation of self-healing concepts into durability-based design approaches for reinforced concrete structures, aimed at quantifying, with reliable confidence, the benefits in terms of slower degradation of the structural performance and extension of the service lifespan. It has been observed that the exposure type, crack width and presence of healing stimulators such as crystalline admixtures has the most significant effect on enhancing SHI and hence self-healing efficiency. However, other parameters, such as the amount of fibers and Supplementary Cementitious Materials have less impact on the autogenous self-healing. The study proposes, through suitably built design charts and ANN analysis, a straightforward input–output model to quickly predict and evaluate, and hence “design”, the self-healing efficiency of cement-based materials.

An Overview of AI-Assisted Design-on-Simulation Technology for Reliability Life Prediction of Advanced Packaging

“…In recent years, AI theory has been widely used in various research domains. Machine learning involves the use of AI theory combined with big data to guide computers for training and learning; eventually, a simple AI model with input and output relationships will be developed to help researchers make design decisions [ 21 , 22 , 23 , 24 ]. Machine learning [ 25 , 26 , 27 , 28 ] can be applied for regression or classification models using either supervised or unsupervised learning.…”

An Advanced Deep Attention Collaborative Mechanism for Secure Educational Email Services

“…The purpose of the NMF is to calculate the elements of W and H so that their product is as “close” as possible to A , with proximity being measured by some distance function. More strictly, nonnegative table factorization is the following combination optimization problem (which in this case is described as a minimization problem) [ 28 , 29 ]: where D (· || ·) is a distance function of arrays A and WH . In general, the problem of minimizing the function D is NP-hard, for which additionally no convex formulations are known that would lead to finding the total minimum of D concerning both tables W and H at the same time.…”

Effects of Autogenous and Stimulated Self-Healing on Durability and Mechanical Performance of UHPFRC: Validation of Tailored Test Method through Multi-Performance Healing-Induced Recovery Indices

“…Because of its high matrix compactness, which prevents and delays the ingress and transport of aggressive substances, UHPC/UHPFRC has an intrinsic high durability in the un-cracked state [27]. On the other hand, it is usually designed in order to have a strain-hardening behavior in bending and/or even in direct tension, this behavior allowing the formation of several small cracks which may be favorable for a faster and higher effectiveness of self-healing processes [26,37].…”

“…Its morphological and chemical characteristics have been already described in [34][35][36]. High-speed mixing [16][17][18][19][20][21][22][23][24][25][26] This was calibrated to obtain a self-leveling consistency and guarantee a proper dispersion of the steel fibers (l f = 20 mm; d f = 0.22 mm), which were added at a volume fraction equal to 1.5% in order to obtain a strain-hardening tensile response at the required level of strength and deformation capacity [31]. The objective of the whole experimental program was to characterize, through a tailored experimental methodology, the self-healing capacity in HPFRCC with and without crystalline admixtures.…”

“…Effectiveness of crack self-sealing, however produced, in delaying the chloride penetration was reliably assessed and confirmed [25], though a quantitative approach able to provide, e.g., a crack width-exposure time scenario dependent on the rate of recovery of chloride imperviousness, is far from being reached. This can be ascribed to the sparsity and variety of the database, to which even data mining strategies would hardly be applicable [26].…”