Ali Al-Shawafi

This study investigates the use of advanced convolutional neural networks (CNNs) to analyze and classify the fracture behavior of U-shaped concrete modified with polyurethane (PU) under repeated drop-weight impact loads. A total of 17 U-shaped specimens were tested under multiple drop-weight impact loads for each PU binder content (0%, 10%, 20%, and 30%) by weight of cement. By integrating digital image correlation (DIC) with dynamic and static mechanical testing, this research evaluates the concrete’s impact resistance and flexural behavior with varying PU binder content. Three CNN architectures, InceptionV3, MobileNet, and DenseNet121, were trained on a dataset comprising 1655 high-resolution crack images to classify the failure stages into no crack, initial crack, and advanced failure. Experimental results revealed that 20% PU content optimally enhances impact resistance and flexural strength, while mechanical properties declined significantly with 30% PU content. The strain localization in DIC analysis indicated reduced matrix cohesion, which was measured by the extent of strain concentration in the material, highlighting the importance of maintaining PU content below 20% to avoid compromising structural integrity. Among the models, InceptionV3 demonstrated superior accuracy (96.67%), precision, and recall, outperforming MobileNet (94.56%) and DenseNet121 (90.03%). The combination of DIC and deep learning offers a robust, automated framework for crack assessment, significantly improving accuracy and efficiency over traditional methods such as visual inspections, which are time-consuming and reliant on expert judgment.

This study investigated the mechanical and impact resistance properties of U-shaped polymer-modified concrete (PMC) incorporated with epoxy (EP) and polyacrylate (PA) binders. The polymer-modified concrete mixtures were prepared with varying binder contents (0 to 30%) at intervals of 10% for each EP and PA binder. Moreover, scanning electron microscopy (SEM) analysis coupled with energy-dispersive X-ray spectroscopy (EDS) was used to study the microstructure of the polymer-modified concrete mixtures. An Artificial Neural Network (ANN) model was developed to predict failure crack strength (N2). The results indicate that EP binders enhance impact resistance but decrease compressive strength, whereas PA binders slightly improve both mechanical and impact properties. Introducing the EP binder into the PCM mixtures reduces the compressive strength by 4.91%, 15.09%, and 33.02% for EP10, EP20, and EP30, respectively, compared to the reference specimen, whereas the impact strength at the initial crack strength was improved by 127.64%, 221.95%, and 17.07% for EP 10, EP 20, and EP 30, respectively. The ANN model demonstrated high accuracy in predicting N₂, achieving R² values of 0.9892 and 0.9664 during training and testing, respectively.

The effectiveness of repair work relies on whether the interface substrate can achieve sufficient bond strength when subjected to numerous stresses. This study investigated the bond properties of repaired normal concrete (NC-to-NC) elements, including cube, beam, and U-shaped specimens, after undergoing natural fracture due to flexural and tensile stresses. The specimens were repaired using a polyurethane (PU) matrix by gluing the two parts and applying compression, splitting, and drop-weight impact (DWI) tests to evaluate the bond strength properties. The results revealed that the PU matrix effectively repairs NC substrate with adequate bond strength, which exceeds the minimum allowable bond strength specified in the ASTM ACI 546-06 to rehabilitate damage concrete structures. The reference beams exhibit a peak applied load capacity of 15.6 kN with less deflection than the repaired samples. The compressive strength of the NC-to-NC repaired specimens loaded along and parallel to the interface plane revealed a decrease in compressive strength of 47.3% and 31.5% compared to the NC-R samples, respectively. The mean number of blows at the cracking stages appeared nearly equal for reference and repaired NC-to-NC specimens. The reference specimens exhibited an average number of 24 and 31 blows at the initial and failure stages, respectively, which were higher by 9.1% and 5.2% than the NC-to-NC repaired specimens. The PU binder showed promising results in achieving adequate interfacial bond strength under static and impact loads.

This study examined the impact properties of ultra-high-performance concrete (UHPC) mixtures with steel fiber (SF) and retrofitted with polyurethane (PU) grouting using repeated drop-weight tests. Micro-steel fiber was added to UHPC mixes from 0 to 3% Vf, and PU grouting overlays of 5 mm, 10 mm, and 15 mm were applied. Digital image correlation (DIC) was used to analyze failure modes. The results showed significant impact durability and energy absorption improvements with increased SF content and thicker PU overlays. UHPC-15PU exhibited 363% and 449% higher first crack and failure strengths than UHPC-5PU. DIC analysis confirmed the failure patterns of the U-shaped UHPC specimen under impact load conditions.

Ultra-high-performance concrete (UHPC) has been used in building joints due to its increased strength, crack resistance, and durability, serving as a repair material. However, efficient repair depends on whether the interfacial substrate can provide adequate bond strength under various loading scenarios. The objective of this study is to investigate the bonding behavior of composite U-shaped normal strength concrete–ultra-high-performance fiber reinforced concrete (NSC-UHPFRC) specimens using multiple drop-weight impact testing techniques. The composite interface was treated using grooving (Gst), natural fracture (Nst), and smoothing (Sst) techniques. Ensemble machine learning (ML) algorithms comprising XGBoost and CatBoost, support vector machine (SVM), and generalized linear machine (GLM) were employed to train and test the simulation dataset to forecast the impact failure strength (N2) composite U-shaped NSC-UHPFRC specimen. The results indicate that the reference NSC samples had the highest impact strength and surface treatment played a substantial role in ensuring the adequate bond strength of NSC-UHPFRC. NSC-UHPFRC-Nst can provide sufficient bond strength at the interface, resulting in a monolithic structure that can resist repeated drop-weight impact loads. NSC-UHPFRC-Sst and NSC-UHPFRC-Gst exhibit significant reductions in impact strength properties. The ensemble ML correctly predicts the failure strength of the NSC-UHPFRC composite. The XGBoost ensemble model gave coefficient of determination (R²) values of approximately 0.99 and 0.9643 at the training and testing stages. The highest predictions were obtained using the GLM model, with an R² value of 0.9805 at the testing stage.

As internal curing self-healing agents in concrete repair, the basic properties of superabsorbent polymers (SAPs), such as water absorption and release properties, are generally affected by several factors, including temperature and humidity solution properties and SAP particle size, which regulate the curing effect and the durability of cementitious composites. This study aimed to investigate the water retention capacities of SAPs in an alkaline environment over extended periods by incorporating liquid sodium silicate (SS) into SAP–water mixtures and examining the influence of temperature. The influence of SAP particle size on mortar’s water absorption capacity and mechanical behavior was investigated. Two mixing techniques for SAPs (dry and pre-wetting) were employed to assess the influence of SAP on cement mortars’ slump, mechanical properties, and cracking resistance. Four types of SAPs (SAP-a, SAP-b, SAP-c, and SAP-d), based on the molecular chains and particle size, were mixed with SS to study their water absorption over 30 days. The results showed that SAPs exhibit rapid water absorption within the first 30 min, exceeding 85% before reaching a saturation point, and the chemical and temperature variations in the water significantly affected water absorption and desorption. The filtration results revealed that SAP-d exhibited the slowest water release rate, retaining water for considerably longer than the other three types of SAPs. The mechanical properties of SAP mortar were reduced due to the addition of an SAP and the improved cracking resistance of the cement mortars.