Hybrid BO-XGBoost and BO-RF Models for the Strength Prediction of Self-Compacting Mortars with Parametric Analysis

Self-compacting mortar (SCM) has superior workability and long-term durable performance compared to traditional mortar. The strength of SCM, including both its compressive and flexural strengths, is a crucial property that is determined by appropriate curing conditions and mix design parameters. In the context of materials science, predicting the strength of SCM is challenging because of multiple influencing factors. This study employed machine learning techniques to establish SCM strength prediction models. Based on ten different input parameters, the strength of SCM specimens were predicted using two different types of hybrid machine learning (HML) models, namely Extreme Gradient Boosting (XGBoost) and the Random Forest (RF) algorithm. HML models were trained and tested by experimental data from 320 test specimens. In addition, the Bayesian optimization method was utilized to fine tune the hyperparameters of the employed algorithms, and cross-validation was employed to partition the database into multiple folds for a more thorough exploration of the hyperparameter space while providing a more accurate assessment of the model's predictive power. The results show that both HML models can successfully predict the SCM strength values with high accuracy, and the Bo-XGB model demonstrated higher accuracy (R² = 0.96 for training and R² = 0.91 for testing phases) for predicting flexural strength with low error. In terms of compressive strength prediction, the employed BO-RF model performed very well, with R² = 0.96 for train and R² = 0.88 testing stages with minor errors. Moreover, the SHAP algorithm, permutation importance and leave-one-out importance score were used for sensitivity analysis to explain the prediction process and interpret the governing input variable parameters of the proposed HML models. Finally, the outcomes of this study might be applied to guide the future mix design of SCM specimens.

The Effect of Acanthocardia tuberculata Shell Powder as Filler on the Performance of Self-Compacting Mortar

In this research, the feasibility of using Acanthocardia tuberculata shell waste from the canning industry in the manufacturing of self-compacting mortar (SCM) was tested. The seashells were finely ground to be used as filler instead of the limestone filler normally used in this type of SCM. First, a physicochemical and microstructural characterisation of all raw materials was carried out, including the particle size distribution of both fillers. Subsequently, the self-compactability properties in the fresh state of SCM were evaluated using a total substitution by volume of limestone filler for seashell powder, using different self-compactiblity parameters. The mineralogical phases of all the SCM tested were identified once hardened by means of X-ray diffraction technique, thermogravimetric and differential thermal analysis. In addition, the mechanical properties, water absorption capacity, dry bulk density and accessible porosity of water of hardened mortars at 28 days of curing were analysed. The effect of replacing limestone filler by Acanthocardia tuberculata filler resulted in a decrease in compressive strength of 29.43, 16.84 and 2.29%, respectively. The results indicate that it is possible to completely replace natural limestone filler with Acanthocardia tuberculata shell filler without significantly affecting the mechanical properties of SCM.

Fresh, Mechanical, and Durability Properties of Self-Compacting Mortar Incorporating Alumina Nanoparticles and Rice Husk Ash

This paper presents a comprehensive evaluation on self-compacting (SC) mortars incorporating 0, 1, 3, and 5% alumina nanoparticles (NA) as well as 0% and 30% rice husk ash (RHA) used as Portland cement replacement. To evaluate the workability, mechanical, and durability performance of SC mortars incorporating NA and RHA, the fresh properties (slump flow diameter and V-funnel flow time), hardened properties (compressive strength, flexural strength, and ultrasonic pulse velocity), and durability properties (water absorption, rapid chloride permeability, and electrical resistivity) were determined. The results indicated that the addition of NA and RHA has negligible effect on the workability and water absorption rate of the SC mortars. However, significant compressive and flexural strength development was observed in the SC mortars treated with NA or the combination of NA and RHA. The introduction of RHA and NA also reduced the rapid chloride permeability and enhanced the electrical resistivity of the SC mortars significantly. It is concluded that the coexistence of 30% RHA and 3% NA as cement replacement in SC mortars can provide the best mechanical and durability performance.

Utilization of Palm Oil Clinker as Cement Replacement Material

The utilization of waste materials from the palm oil industry provides immense benefit to various sectors of the construction industry. Palm oil clinker is a by-product from the processing stages of palm oil goods. Channelling this waste material into the building industry helps to promote sustainability besides overcoming waste disposal problems. Environmental pollution due to inappropriate waste management system can also be drastically reduced. In this study, cement was substituted with palm oil clinker powder as a binder material in self-compacting mortar. The fresh, hardened and microstructure properties were evaluated throughout this study. In addition, sustainability component analysis was also carried out to assess the environmental impact of introducing palm oil clinker powder as a replacement material for cement. It can be inferred that approximately 3.3% of cement production can be saved by substituting palm oil clinker powder with cement. Reducing the utilization of cement through a high substitution level of this waste material will also help to reduce carbon emissions by 52%. A cleaner environment free from pollutants can be created to ensure healthier living. Certain industries may benefit through the inclusion of this waste material as the cost and energy consumption of the product can be minimized.

Feasibility Studies of Palm Oil Mill Waste Aggregates for the Construction Industry

The agricultural industry in Malaysia has grown rapidly over the years. Palm oil clinker (POC) is a byproduct obtained from the palm oil industry. Its lightweight properties allows for its utilization as an aggregate, while in powder form as a filler material in concrete. POC specimens obtained throughout each state in Malaysia were investigated to evaluate the physical, chemical, and microstructure characteristics. Variations between each state were determined and their possible contributory factors were assessed. POC were incorporated as a replacement material for aggregates and their engineering characteristics were ascertained. Almost 7% of density was reduced with the introduction of POC as aggregates. A sustainability assessment was made through greenhouse gas emission (GHG) and cost factor analyses to determine the contribution of the addition of POC to the construction industry. Addition of POC helps to lower the GHG emission by 9.6% compared to control specimens. By channeling this waste into the construction industry, an efficient waste-management system can be promoted; thus, creating a cleaner environment. This study is also expected to offer some guides and directions for upcoming research works on the incorporation of POC.