The additive manufacturing of concrete, also known as 3D-printed concrete, is produced layer by layer using a 3D printer. The three-dimensional printing of concrete offers several benefits compared to conventional concrete construction, such as reduced labor costs and wastage of materials. It can also be used to build complex structures with high precision and accuracy. However, optimizing the mix design of 3D-printed concrete is challenging, involving numerous factors and extensive hit-and-trail experimentation. This study addresses this issue by developing predictive models, such as the Gaussian Process Regression model, Decision Tree Regression model, Support Vector Machine model, and XGBoost Regression models. The input parameters were water (Kg/m³), cement (Kg/m³), silica fume (Kg/m³), fly ash (Kg/m³), coarse aggregate (Kg/m³ & mm for diameter), fine aggregate (Kg/m³ & mm for diameter), viscosity modifying agent (Kg/m³), fibers (Kg/m³), fiber properties (mm for diameter and MPa for strength), print speed (mm/sec), and nozzle area (mm²), while target properties were the flexural and tensile strength of concrete (MPa data from 25 literature studies were collected. The water/binder ratio used in the dataset ranged from 0.27 to 0.67. Different types of sands and fibers have been used, with fibers having a maximum length of 23 mm. Based upon the Coefficient of Determination (R²), Root Mean Square Error (RMSE), Mean Square Error (MSE), and Mean Absolute Error (MAE) for casted and printed concrete, the SVM model performed better than other models. All models’ cast and printed flexural strength values were also correlated. The model’s performance has also been checked on six different mix proportions from the dataset to show its accuracy. It is worth noting that the lack of ML-based predictive models for the flexural and tensile properties of 3D-printed concrete in the literature makes this study a novel innovation in the field. This model could reduce the computational and experimental effort required to formulate the mixed design of printed concrete.

Formulating a mix design for 3D concrete printing (3DCP) is challenging, as it involves an iterative approach, wasting a lot of resources, time, and effort to optimize the mix for strength and printability. A potential solution is mix formulation through artificial intelligence (AI); however, being a new and emerging field, the open-source availability of datasets is limited. Limited datasets significantly restrict the predictive performance of machine learning (ML) models. This research explores data augmentation techniques like deep generative adversarial network (DGAN) and bootstrap resampling (BR) to increase the available data to train three ML models, namely support vector machine (SVM), artificial neural network (ANN), and extreme gradient boosting regression (XGBoost). Their performance was evaluated using R², MSE, RMSE, and MAE metrics. Models trained on BR-augmented data showed higher accuracy than those trained on the DGAN-augmented data. The BR-trained XGBoost exhibited the highest R² scores of 0.982, 0.970, 0.972, 0.971, and 0.980 for cast compressive strength, printed compressive strength direction 1, 2, 3, and slump flow respectively. The proposed method of predicting the slump flow (mm), cast, and anisotropic compressive strength (MPa) can effectively predict the mix design for printable concrete, unlocking its full potential for application in the construction industry.

After the catastrophic destruction of the October 2005 Kashmir earthquake, the first building code of Pakistan was developed in 2007. The sole purpose of the building code of Pakistan (BCP) was to incorporate advancements in earthquake-resistant design to fortify structures and ensure the safety of citizens against future seismic events. After 2007, the BCP was not revised till 2021 to include the changes over time. However, the recently updated version of BCP 2021 highlights that the seismicity of many regions in Pakistan is high, which is not truly reflected in the BCP 2007. Therefore, the advancements in earthquake-resistant design due to the growing concerns about the potential risks of seismicity in the region have been incorporated into the updated version of the BCP. However, there are concerns among researchers that many structures designed on the 2007 code may need seismic fortification. Therefore, the current study focuses on the seismic fortification of existing systems that were developed using previous codes. Non-linear viscous fluid dampers are used to improve the seismic resilience of existing structures. This study compares the seismic performance of an existing reinforced concrete building with and without non-linear viscous dampers and subjected to a non-linear dynamic analysis. The performance of the building is evaluated in terms of story displacement, story drift, story acceleration, and energy dissipation mechanisms. Adding the non-linear fluid viscous dampers in the structure caused a decrease in the inter-story drift by around 31.16% and the roof displacement was reduced by around 36.58%. In addition to that, in a controlled structure, more than 70% of energy was dissipated by the fluid viscous dampers. These results indicate that adding the non-linear fluid viscous dampers to the existing structure significantly improved the vibration performance of the system against undesirous vibrations. The outcomes of this study also provide a very detailed insight into the usage of non-linear viscous dampers for improving the seismic performance of existing buildings and can be used to develop effective strategies to mitigate the impact of seismic events on already built structures.