Infrastructures, Volume 10, Issue 2 (February 2025) – 9 articles

Visual inspection is a common method for detecting structural damage, but has limitations in terms of subjectivity, time, and access. This research proposes an innovative approach to identify cracks using a 3D model generated from photographs of an unmanned aerial vehicle (UAV) and the use of a convolutional neural network (CNN). These networks are effective in detecting complex patterns, improving the accuracy and efficiency of damage identification based on simple visual inspection. The case study is the old Villena Rey bridge in Lima, Peru. The methodology covers (i) the development of a 3D model of the bridge structure, (ii) the extraction of photographs of the model and its binary segmentation, (iii) the application of deep learning through the training and testing phase of a CNN to achieve crack detection in photographs, and (iv) damage location within the 3D model. An 88.4% accuracy was achieved in crack detection, identifying 18 damage points, of which 3 turned out to be false positives. Additionally, it was determined that the left pillar in the southern area of the bridge presented the highest concentration of damage, which underlines the effectiveness of the method used. Full article

Structural health monitoring (SHM) is critical for ensuring the safety and longevity of structures, yet existing methodologies often face challenges such as high data dimensionality, lack of interpretability, and reliance on extensive label datasets. Current research in SHM has primarily focused on supervised approaches, which require significant manual effort for data labeling and are less adaptable to new environments. Additionally, the large volume of data generated from dynamic structural monitoring campaigns often includes irrelevant or redundant features, further complicating the analysis and reducing computational efficiency. This study addresses these issues by introducing an unsupervised learning approach for SHM, employing an agglomerative clustering model alongside an unsupervised feature selection technique utilizing box-plot statistics. The proposed method is assessed through raw acceleration signals obtained from four dynamic structural monitoring campaigns, including 44 features with temporal, statistical, and spectral information. In addition, these features are also evaluated in terms of their relevance, and the most important ones are selected for a new execution of the computational procedure. The proposed feature selection not only reduces data dimensionality but also enhances model interpretability, improving the clustering performance in terms of homogeneity, completeness, V-measure, and adjusted Rand score. The results obtained for the four analyzed cases provide clear insights into the patterns of behavior and structural anomalies. Full article

Rollover crashes are among the most prevalent types of accidents in developing countries. Various factors may contribute to the occurrence of rollover crashes. However, limited studies have simultaneously investigated both traffic stream and road-related variables. For instance, the effects of T-intersection density, U-turns, roadside parking lots, the entry and exit ramps of side roads, as well as traffic stream characteristics (e.g., standard deviation of vehicle speeds, speed violations, presence or absence of speed cameras, and road surface deterioration) have not been thoroughly explored in previous research. Additionally, the simultaneous modeling of crash frequency and intensity remains underexplored. This study examines single-vehicle rollover crashes in Yazd Province, located in central Iran, as a case study and simultaneously evaluates all the variables. A dataset comprising three years of crash data (2015–2017) was collected and analyzed. A crash index was developed based on the weight of crash intensity, road type, road length (as dependent variables), and road infrastructure and traffic stream properties (as independent variables). Initially, the dataset was refined to determine the significance of explanatory variables on the crash index. Correlation analysis was conducted to assess the linear independence between variable pairs using the variance inflation factor (VIF). Subsequently, various models were compared based on goodness of fit (GOF) indicators and odds ratio (OR) calculations. The results indicated that among ten crash modeling techniques, namely, Poisson, negative binomial (NB), zero-truncated Poisson (ZTP), zero-truncated negative binomial (ZTNB), zero-inflated Poisson (ZIP), zero-inflated negative binomial (ZINB), fixed-effect Poisson (FEP), fixed-effect negative binomial (FENB), random-effect Poisson (REP), and random-effect negative binomial (RENB), the FENB model outperformed the others. The Akaike information criterion (AIC) and Bayesian information criterion (BIC) values for the FENB model were 1305.7 and 1393.6, respectively, demonstrating its superior performance. The findings revealed a declining trend in the frequency and severity of rollover crashes. Full article

Analytical models to predict distresses and service conditions of road pavements can greatly contribute to the development of an effective pavement management system. These models allow the transportation agencies to monitor and track the deterioration of pavements and consequently determine the needed maintenance operations to preserve the performance of the network. In this research, the pavement distresses and service conditions of the Indus Highway N-55 located in Karak district, Pakistan were examined. Distresses were identified by visual observation, and then their severity and extent were measured individually by using a Vernier caliper and a measuring scale. For each distress type, the corresponding PCR was calculated. The compaction densities of the base and wearing courses were considered as input parameters to develop an ordinal logistic regression model for two dominant distresses, namely rutting and potholes. Rutting severity and extent were divided into three levels, while pothole severity was divided into four levels. Bulk and maximum specific gravity were found to have a significant impact on the models of both distresses. The model can be used to predict their development in terms of severity and extent. The proposed formulation provides valuable insights into monitoring and predicting pavement distresses by assessing the densities of road construction materials. Full article

The use of precast concrete pipes for water and sewage transportation systems is a very important element of a country’s infrastructure. The main aim of this study was to investigate the effects of concrete’s compressive strength and reinforcement levels on the mechanical performance of spun-cast full-scale precast concrete pipes in the local construction industries of developing countries. A test matrix was adopted using a full 3² factorial design. The studied concrete’s compressive strength was 20, 30, and 40 MPa, and reinforcement levels were 60%, 80%, and 100%, representing low, medium, and high levels, respectively. The medium level of reinforcement represented the reinforcement requirement of ASTM C76 in concrete pipes. A total of eighteen full-scale pipes of 450 mm diameter were cast in an industrial precast pipe unit using a spin-casting technique and were tested under a three-edge bearing load. The experimental results showed that the crack load and ultimate load of the tested pipes increased with higher levels of concrete strength and reinforcement levels. For example, an approximately 35% increase in the 0.30 mm crack load was observed when the concrete strength increased from 20 MPa to 30 MPa for all tested levels of reinforcement. Similarly, around a 19% increase in ultimate load was observed for pipes with 80% reinforcement compared to identical pipes with 60% reinforcement. It was found that the pipe class, as per ASTM C76, is highly dependent on the concrete strength and reinforcement levels. All of the pipes exhibited the development of flexural cracks at critical locations (crown, invert, and springlines). Moreover, concrete pipes cast with low-level strength and reinforcement also showed signs of crushing at the crown location near to the pipe failure. The analysis of variance (ANOVA) results showed that the main factors (compressive strength and reinforcement levels) were significantly affected by the cracking loads of precast pipes. No significant effect of the interaction of factors was observed on the crack load response. However, interaction factors, along with main factors, have significant effects on the ultimate load capacity of the concrete pipes, as indicated by the F-value, p-value, and Pareto charts. This study made an effort to illustrate and optimize the mechanical performance of pipes cast with various concrete strengths and reinforcement levels to facilitate the efficient use of materials for more resilient pipe infrastructure. Moreover, the exact optimization of concrete strength and reinforcement level for the desired pipe class will make the pipe design economical, leading to an increased profit margin for local spin-cast pipe fabricators without compromising the pipe’s quality. Full article

The widespread adoption of wood in construction is driven by its sustainability, cost-effectiveness, and esthetic appeal. The construction of wood buildings often requires minimal specialized equipment, contributing to affordability and higher demand for wood-frame structures. Wood is considered more sustainable than other building materials, such as steel or concrete, for several reasons, including its renewable nature, low embodied energy, carbon sequestration, energy efficiency, and biodegradability, among others. In the United States, wood is the most common material used in building construction. While many of the structures are single-family homes, wood framing is also prevalent in larger apartment complexes, as well as commercial and industrial buildings. Timber has also been traditionally used for bridge construction, and recently, it has been considered again for the construction of new bridges. Over time, wood-frame construction has developed from a basic method for primitive shelters into a sophisticated field of structural design. As an eco-friendly resource, wood is crucial for promoting sustainable building practices. However, ensuring the long-term performance and safety of timber structures is essential. Regular inspections and testing of wooden structures are important to identify signs of wear, damage, or decay. One type of testing which is gaining popularity is nondestructive testing (NDT). NDT techniques have become invaluable for assessing the condition of timber components because such techniques are non-invasive in nature and do not cause damage, ensuring that structures remain functional with minimal disruptions. These methods provide critical insights into the structural integrity and operational efficiency of wood under sustained loads and in inclement environments. This article examines various NDT techniques used to evaluate timber structures, highlighting their capabilities, as well as advantages and limitations. It also discusses the importance of wood in advancing sustainability within the construction industry and emphasizes the need for accurate and reliable assessment methods to enhance the use of timber as an environmentally friendly building material. By incorporating NDT practices into regular inspection and maintenance protocols for buildings, bridges, and other structures, various stakeholders can ensure the durability, longevity, and safety of timber structures, thereby contributing to the progress and advancement of sustainable construction practices worldwide. Full article

Belite calcium sulfoaluminate cement (CSAB), an alternative to Portland cement, exhibits excellent strength at both early and later ages. However, due to its high belite content, the carbon reduction from this type of cement is not sufficient when compared to other alternative cements. To further enhance CSAB’s sustainability, this study investigates the performance of CSAB when partially replaced by low-carbon mineral additives (i.e., limestone and gypsum). The primary objective is to identify the optimal mixture design by incorporating gypsum and limestone to formulate a sustainable binder that maintains high compressive strength. The CSAB is replaced (with both additives) by up to 51% at two different liquid-to-solid ratios of 0.4 and 0.5. gypsum replacements ranging from 0% to 27%, resulting in three unique gypsum-to-ye’elimite molar ratios (M). Limestone replacements range from 0% to 30% in 10% increments. The investigation focuses on the development of hydrates, hydration kinetics, and compressive strength of the sustainable binders after 3 days. The results indicate that a higher replacement level of limestone provides more free water to react with ye’elimite and belite, thereby enhancing the hydration kinetics, but decreasing the compressive strength. It also shows that the addition of gypsum enhances the formation of ettringite, enabling the maintenance of great compressive strength within the binder even at high limestone replacement levels. The binder containing 12% gypsum and 20% limestone was identified as the optimal mixture, yielding a compressive strength of 39 MPa. This performance, when compared to the plain CSAB (compressive strength of 49 MPa), demonstrates that the optimized binder achieves adequate sustainability while maintaining mechanical properties without significant compromise. Full article

Accurate estimation of concrete compressive strength is very important for the improvement of mix design, quality assurance, and compliance with engineering specifications. Most empirical traditional models have failed to capture the complex relationships inherent within varied constituents of concrete mixes. This paper develops a machine learning model for compressive strength prediction using mix design variables and curing age from a “Concrete Compressive Strength Dataset” obtained from the UCI Machine Learning Repository. After comprehensive data preprocessing and feature engineering, various regression and classification models were trained and evaluated, including gradient boosting, random forest, AdaBoost, k-nearest neighbors, linear regression, and neural networks. The gradient boosting regressor (GBR) achieved the highest predictive accuracy with an R² value of 0.94. Feature importance analysis showed that the water–cement ratio and age are the most crucial factors affecting compressive strength. Advanced methods such as SHapley Additive exPlanations (SHAP) values and partial dependence plots were used to attain deep insights about feature interaction with a view to enhancing interpretability and fostering trust in models. Results highlight the potential of machine learning models to improve concrete mix design with the aim of sustainable construction through the optimization of material usage and waste reduction. It is recommended that future research be undertaken with expanding datasets, more features, and richer feature engineering to enhance predictive power. Full article

The increasing global emphasis on sustainable construction practices has spurred significant international research into developing durable and eco-friendly concrete materials. This study investigates the potential of metakaolin and glass powder as supplementary aluminosilicate materials in slag- based geopolymer mortars, aiming to enhance their mechanical properties and durability. To further improve the performance, polypropylene fibers were incorporated at various dosages. Therefore, 13 mixtures of geopolymer mortar based on blast furnace slag have been developed. The control mix does not contain fibers or slag replacement materials, whereas in the other formulations, glass powder and metakaolin have been employed as substitutes for slag at weight percentages (relative to the weight of slag) of 5% and 10%, separately and in combination. Additionally, the fiber-containing samples are divided into two groups based on the volume percentage of polypropylene fibers, comprising 0.2% and 0.4%. The results of the investigation show that the use of glass powder, particularly at a replacement percentage of 10%, leads to an improvement in the 28-day compressive strength. Furthermore, the mixes containing glass powder demonstrated higher flexural strength compared to those containing metakaolin, irrespective of the volume percentage of fibers. The best performance in the rapid chloride permeability test is associated with the mix containing a combination of glass powder and metakaolin at a replacement percentage of 10%. Satisfactory results have been obtained when using fibers at volume percentages of 0.2% and 0.4%. Additionally, this study utilized a fuzzy inference system to predict compressive strength. The results indicate that, by considering uncertainties, the compressive strength of the mortar can be predicted with an error of less than 1% without the need for complex mathematical calculations. Full article