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.

For decades, one of the most critical considerations of civil engineers has been the construction of structures that can sufficiently resist earthquakes. However, in many parts of the globe, ancient and contemporary buildings were constructed without regard for engineering; thus, there is a rising necessity to adapt existing structures to avoid accidents and preserve historical artefacts. There are various techniques for retrofitting a masonry structure, including foundation isolations, the use of Fibre-Reinforced Plastics (FRPs), shotcrete, etc. One innovative technique is the use of Shape Memory Alloys (SMAs), which improve structures by exhibiting high strength, good re-centring capabilities, self-repair, etc. One recent disastrous earthquake that happened in the city of Bam, Iran, (with a large proportion of masonry buildings) in 2003, with over 45,000 casualties, is analysed to discover the primary causes of the structural failure of buildings and its ancient citadel. It is followed by introducing the basic properties of SMAs and their applications in retrofitting masonry buildings. The outcomes of preceding implementations of SMAs in retrofitting of masonry buildings are then employed to present two comprehensive schemes as well as an implementation algorithm for strengthening masonry structures using SMA-based devices.

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.

Sažetak: Utjecajne funkcije i njihov grafički prikaz -utjecajne linije, koriste se kod proračuna konstrukcija izloženih djelovanju pokretnih opterećenja. Njima se određuje položaj pokretnog opterećenja koji će dati najnepovoljnije utjecaje na konstrukciju (maksimalne unutarnje sile i pomake) ili njezine dijelove. Cilj ovog rada je analizirati utjecajne linije statički određenih i neodređenih sustava dobivenih programskim paketom Autodesk Robot Structural Analysis, te ih usporediti s jednakima, dobivenima analitičkim putem. U novije vrijeme računala su postala nezamjenjivi alat svakom inženjeru u praksi, no ipak je potrebno dobivene numeričke rezultate raznim programskim paketima prihvatiti uz oprez, te proučiti ograničenja svakog programa. Na nekoliko jednostavnih primjera statički određenih i neodređenih sustava proučene su utjecajne linije dobivene programskim paketom Autodesk Robot Structural Analysis, te uočena dobra podudarnost rješenja s analitičkim rezultatima. Sve dobivene pogreške tijekom rada mogu se generalizirati i korigirati ulaznim parametrima programa, a rezultate dobivene ovim putem možemo koristiti u statičkim proračunima konstrukcija. INFLUENCE LINES CONSTRUCTED USING AUTODESK ROBOTAbstract: Influence functions and their graphical representation -influence lines are used in calculation of structures exposed to moving loads. They are used to determine the position of the moving load that will give the most adverse impacts of construction or its components (maximum internal forces, deflections and displacements), and to determine the values of these quantities. The aim of this work is to analyse influence lines of statically determined and indetermined systems obtained by software, and compare them with the same obtained by analytic methods. In recent years, computers have become an indispensable tool to every engineer in practice, and it is necessary to accepted numerical results obtained by various applications with exceptional caution, and also study the possible limitations of some software. A few examples of statically determined and indetermined systems are studied influence lines obtained software package Autodesk Robot Structural Analysis and observed a good correlation with the analytical results. The resulting operating errors can be generalized and corrected by the input parameters of the program, so the results can be used for static analysis of structures.

No abstract