The increasing cost of landfills, and lack of natural large aggregates observing interests for using wastes to produce concrete and mortar materials. Utilizing plastic waste and crushed ceramic waste ...not only save the landfills cost but also reduce the cost of using natural aggregates. Secondly, tea is the second most consumed beverage at world level and resulted huge amount of waste. Thus, this article attempts to develop the appropriate characteristics of self-compacting concrete (SCC) by adding plastic waste, tea waste, and crushed ceramics. The fresh and hardened properties of the SCC were investigated to examine the addition of waste plastic, whereas the content of tea waste and crushed ceramic was kept constant. The results revealed that the addition of plastic waste caused to reduce SFD, L-Box, segregation, and fresh density, and obtained maximum values as 765 mm, 0.94, 19, and 2382 kg/m
3
for PP5 and RP5, respectively, whereas T500 and V-funnel flow gradually increased with increasing waste plastic, and the maximum values were obtained as 3.44 and 16 for RP25 and PP+RP25, respectively. Further, compressive and flexural strengths were decreased with increasing content of waste plastic, and the maximum values were obtained as 55 MPa and 6.5 MPa for PP5 and PP+RP5 at 28 days, respectively. The results proved the possibility of using plastic waste, tea waste, and crushed ceramics in SCC.
Graphical abstract
This paper gives a comprehensive overview of the state-of-the-art machine learning methods that can be used for estimating self-compacting rubberized concrete (SCRC) compressive strength, including ...multilayered perceptron artificial neural network (MLP-ANN), ensembles of MLP-ANNs, regression tree ensembles (random forests, boosted and bagged regression trees), support vector regression (SVR) and Gaussian process regression (GPR). As a basis for the development of the forecast model, a database was obtained from an experimental study containing a total of 166 samples of SCRC. Ensembles of MLP-ANNs showed the best performance in forecasting with a mean absolute error (MAE) of 2.81 MPa and Pearson’s linear correlation coefficient (R) of 0.96. The significantly simpler GPR model had almost the same accuracy criterion values as the most accurate model; furthermore, feature reduction is easy to combine with GPR using automatic relevance determination (ARD), leading to models with better performance and lower complexity.
Assessment of seismic vulnerability in urban areas is a challenging task that requires a meticulous and systematic approach. Sarajevo and Banja Luka, together with Tuzla, are the most urbanized and ...densely populated cities in Bosnia and Herzegovina. Sarajevo and Banja Luka experienced devastating earthquakes in 1962 and 1969, respectively. This is why it is of the utmost importance to conduct seismic vulnerability evaluation of the existing building stock in Bosnia and Herzegovina. Until today no systematic database regarding structures and their typology has been compiled for the territory of Bosnia and Herzegovina in connection with their vulnerability to seismic actions. The choice of an appropriate vulnerability method plays a key role in the process of assessment of seismic risk and highly depends on the available information, characteristics of the buildings, organization of data collection and decision-makers. Among various methods, it was decided to use the macroseismic method derived from the EMS-98 scale for the vulnerability assessment of the existing buildings in Bosnia and Herzegovina. The database was obtained from the “typology of residential buildings in the BiH” project, a comprehensive survey of 13,044 existing residential buildings in BIH, which was conducted for energy performance assessment of the national building stock. For the purpose of this research, the database was reduced to a sample of 2933 buildings, as it included a selection of only unreinforced and confined masonry buildings built from 1918 to 2014 and located in Sarajevo and Banja Luka. The aim of this paper is to provide an overture in assessing the seismic risk in Sarajevo and Banja Luka by applying the method based on the vulnerability index. The vulnerability index is calculated by the macroseismic method which is in the function of the type of building, regional vulnerability factor and behavior modifier factors. The application of this method confirms the notable seismic risk in the cities of Sarajevo and Banja Luka due to the high vulnerability of the buildings. It may be argued that the behavior modifiers which had the largest impact on the change of the vulnerability class were the number of floors and type of roof structure. This research intends to contribute to the prevention of an earthquake disaster, in the form of a theoretical forecast of the aftermath: structural damage and/or socio-economic losses that may occur after an earthquake.
Tuzla is the third most populated city in Bosnia and Herzegovina. In the last 50 years, Tuzla has experienced several minor and moderate earthquakes. On August 30th, 2019, an earthquake of magnitude ...m
b
= 4.7 and the intensity from V to VI according to the MCS scale hit an area located 6 km from Mramor a village located 10 km from Tuzla. The city of Tuzla is known for salt and coal exploitation, which has caused the settlement of the city of Tuzla. Assessment of the seismic risk depends on various features, from the availability of data, knowledge regarding the buildings to the selection of vulnerability method that is going to be applied. The outcome risk assessment due to ground motion represents the first step to support the decisions and actions to mitigate potential losses. From the available database, all the structures located in Tuzla were elaborated, leading to a sample of 203 buildings, including reinforced concrete buildings, unreinforced masonry with flexible and rigid floors, and confined masonry buildings. The RISK-UE Building Category Matrix was used for structural and typological characterization of the elaborated buildings. The range of the construction period for the selected sample is from 1961 to 2014. The elaborated structures were residential buildings either for individual or collective housing. This paper aims to provide preliminary information regarding seismic risk in the Tuzla region taking into account the specific site effects on the vulnerability by applying the macroseismic model. The vulnerability index is calculated by applying the macroseismic method being a function of the type of building, behavior modifier factors, and regional vulnerability factors. The seismic risk in the town of Tuzla is in the range from medium to high. Site characteristics have been incorporated in the calculation, leading to amplification of damage and higher vulnerability of structures.
The bio-chemical and physical characteristics of a river are directly affected by water temperature, which thereby affects the overall health of aquatic ecosystems. It is a complex problem to ...accurately estimate water temperature. Modelling of river water temperature is usually based on a suitable mathematical model and field measurements of various atmospheric factors. In this article, the air-water temperature relationship of the Missouri River is investigated by developing three different machine learning models (Artificial Neural Network (ANN), Gaussian Process Regression (GPR), and Bootstrap Aggregated Decision Trees (BA-DT)). Standard models (linear regression, non-linear regression, and stochastic models) are also developed and compared to machine learning models. Analyzing the three standard models, the stochastic model clearly outperforms the standard linear model and nonlinear model. All the three machine learning models have comparable results and outperform the stochastic model, with GPR having slightly better results for stations No. 2 and 3, while BA-DT has slightly better results for station No. 1. The machine learning models are very effective tools which can be used for the prediction of daily river temperature.
Given that a significant fraction of buildings and architectural heritage in Europe's historical centers are masonry structures, the selection of proper diagnosis, technological surveys, ...non-destructive testing, and interpretations of crack and decay patterns is paramount for a risk assessment of possible damage. Identifying the possible crack patterns, discontinuities, and associated brittle failure mechanisms within unreinforced masonry under seismic and gravity actions allows for reliable retrofitting interventions. Traditional and modern materials and strengthening techniques create a wide range of compatible, removable, and sustainable conservation strategies. Steel/timber tie-rods are mainly used to support the horizontal thrust of arches, vaults, and roofs and are particularly suitable for better connecting structural elements, e.g., masonry walls and floors. Composite reinforcing systems using carbon, glass fibers, and thin mortar layers can improve tensile resistance, ultimate strength, and displacement capacity to avoid brittle shear failures. This study overviews masonry structural diagnostics and compares traditional and advanced strengthening techniques of masonry walls, arches, vaults, and columns. Several research results in automatic surface crack detection for unreinforced masonry (URM) walls are presented considering crack detection based on machine learning and deep learning algorithms. In addition, the kinematic and static principles of Limit Analysis within the rigid no-tension model framework are presented. The manuscript sets a practical perspective, providing an inclusive list of papers describing the essential latest research in this field; thus, this paper is useful for researchers and practitioners in masonry structures.
One of the major causes of ecological and environmental problems comes from the enormous number of discarded waste tires, which is directly connected to the exponential growth of the world's ...population. In this paper, previous works carried out on the effects of partial or full replacement of aggregate in concrete with waste rubber on some properties of concrete were investigated. A database containing 457 mixtures with partial or full replacement of natural aggregate with waste rubber in concrete provided by different researchers was formed. This database served as the basis for investigating the influence of partial or full replacement of natural aggregate with waste rubber in concrete on compressive strength. With the aid of the database, the possibility of achieving reliable prediction of the compressive strength of concrete with tire rubber is explored using neural network modelling.
Bosnia and Herzegovina is located in South-Eastern Europe which is characterized by one of the most complex tectonic scenarios in Europe. Until now no seismic risk assessment has been conducted for ...Bosnia and Herzegovina. In this study evaluation and improvement of the RAPID methodology was conducted, considering building construction age, construction material and number of storeys. This new methodology is named iRAPID, where
i
stands for improvement. Results from this analysis showed that vulnerable areas are the ones with a higher population, which need not have the highest PGA value, but certainly PGA values above 0.20 g. Prediction models for threatened buildings and the population for Bosnia and Herzegovina are proposed. Taking into account the multidimensional risk protocol the cities with the highest vulnerability are Zenica, Tuzla, City of Mostar, Trebinje, and Travnik.
Abstract
In this study, a machine learning model for the precise manufacturing of green cementitious composites modified with granite powder sourced from quarry waste was designed. For this purpose, ...decision tree, random forest and AdaBoost ensemble models were used and compared. A database was created containing 216 sets of data based on an experimental study. The database consists of parameters such as the percentage of cement substituted with granite powder, time of testing and curing conditions. It was shown that this method for designing green cementitious composite mixes, in terms of predicting compressive strength using ensemble models and only three input parameters, can be more accurate and much more precise than the conventional approach. Moreover, to the best of the authors' knowledge, artificial intelligence has been one of the most effective and precise methods used in the design and manufacturing industry in recent decades. The simplicity of this method makes it more suitable for construction practice due to the ease of evaluating the input variables. As the push towards decreasing carbon emissions increases, a method for designing green cementitious composites without producing waste that is more precise than traditional tests performed in a laboratory is essential.
Replacing a specified quantity of cement with Class F fly ash contributes to sustainable development and reducing the greenhouse effect. In order to use Class F fly ash in self-compacting concrete ...(SCC), a prediction model that will give a satisfactory accuracy value for the compressive strength of such concrete is required. This paper considers a number of machine learning models created on a dataset of 327 experimentally tested samples in order to create an optimal predictive model. The set of input variables for all models consists of seven input variables, among which six are constituent components of SCC, and the seventh model variable represents the age of the sample. Models based on regression trees (RTs), Gaussian process regression (GPR), support vector regression (SVR) and artificial neural networks (ANNs) are considered. The accuracy of individual models and ensemble models are analyzed. The research shows that the model with the highest accuracy is an ensemble of ANNs. This accuracy expressed through the mean absolute error (MAE) and correlation coefficient (R) criteria is 4.37 MPa and 0.96, respectively. This paper also compares the accuracy of individual prediction models and determines their accuracy. Compared to theindividual ANN model, the more transparent multi-gene genetic programming (MGPP) model and the individual regression tree (RT) model have comparable or better prediction accuracy. The accuracy of the MGGP and RT models expressed through the MAE and R criteria is 5.70 MPa and 0.93, and 6.64 MPa and 0.89, respectively.