VGTU Journals (Vilnius Gediminas Technical University - Vilnius Tech)
Not a member yet
12536 research outputs found
Sort by
Forecasting mechanical properties of steel structures through dynamic metaheuristic optimization for adaptive machine learning
No full textMachine learning (ML) presents a promising method for predicting mechanical properties in structural engineering, particularly within complex nonlinear structures under extreme conditions. Despite its potential, research has shown a disproportionate focus on concrete structures, leaving steel structures less explored. Furthermore, the prevalent combination of metaheuristic optimization (MO) and ML in existing studies is often subjective, pointing to a significant gap in identifying and leveraging more effective hybrid models. To bridge these gaps, this study introduces a novel system named the Multiple Metaheuristic Optimizers – Multiple Machine Learners (MMOMML) system, designed for predicting mechanical strength in steel structures. The MMOMML system amalgamates 17 MO algorithms with 15 ML techniques, generating 255 hybrid models, including numerous novel configurations not previously examined. With a user-friendly interface, MMOMML enables structural engineers to tackle inference challenges efficiently, regardless of their coding proficiency. This capability is convincingly demonstrated through two practical applications: steel beams’ shear strength and steel cellular beams’ elastic buckling. By offering a versatile and robust tool, the MMOMML system meets construction engineers’ and researchers’ practical and research needs, marking a significant advancement in the field
Multi-objective green design model based on costs, CO2 emissions and serviceability for high-rise buildings with a mega-structure system
No full textIn light of growing environmental concerns, the reduction of CO2 emissions is increasingly vital. Particularly in the construction industry, a major contributor to global carbon emissions, addressing this issue is critical for environmental sustainability and mitigating the accelerating impacts of climate change. This study proposes the Optimal Green Design Model for Mega Structures (OGDMM) to optimise CO2 emissions, cost-effectiveness, and serviceability in highrise buildings with mega structures. The OGDMM examines the impact of each material and structural design of main members on these three critical aspects. Analytical results for high-rise buildings (120–200 m, slenderness ratio: 2.0–8.0) demonstrate that OGDMM can reduce CO2 emissions and costs by an average of 4.67% and 3.97%, respectively, without compromising serviceability. To ensure comprehensive evaluation, this study introduces five new evaluation indicators encompassing environmental, economic, and serviceability performances of high-rise buildings. Based on these criteria, optimised structural designs for high-rise buildings are classified into four categories according to slenderness ratio, leading to the formulation of corresponding design guidelines. The model’s applicability is further validated through its application to a 270-m-tall high-rise building in Korea, showing reductions in CO2 emissions and costs by 8.99% and 18.50%, respectively, while maintaining structural serviceability
An improved random forest model to predict bond strength of FRP-to-concrete
No full textFiber-reinforced polymer (FRP) is an excellent building material for strengthening concrete structures, but it is difficult to accurately evaluate the bond strength of FRP-to-concrete due to the influence of various parameters. In this study, a novel hybrid model which combines particle swarm optimization (PSO) with random forest (RF) was proposed to predict the bond strength of FRP-to-concrete. The PSO algorithm was used to optimize the hyperparameters of the RF model. A total of 749 specimens collected from the literature were used to develop the proposed PSO-RF model. Each sample contains 11 parameters required for the model. These 11 parameters are (1) the compressive strength of concrete, (2) the tensile strength of concrete, (3) the width of concrete specimen, (4) the maximum aggregate size of concrete, (5) the tensile strength of FRP, (6) the thickness of FRP, (7) the elastic modulus of FRP, (8) the tensile strength of adhesive, (9) the bond length of FRP, (10) the bond width of FRP, and (11) the bond strength of FRP-to-concrete. The proposed PSO-RF model was compared with other machine learning models as well as ten empirical equations. Six statistical indices, namely root mean squared error (RMSE), mean absolute error (MAE), coefficient of determination (R2), Nash-Sutcliffe efficiency coefficient (NSE), Willmott’s Index of Agreement (WIA), and Legates-McCabe’s Index (LM) were used to evaluate the prediction performance of the abovementioned models. The results show that the RMSE, MAE, R2, NSE, WIA and LM values of the PSO-RF model are 1.529 kN, 0.942 kN, 0.986, 0.984, 0.996 and 0.892, respectively, for the training datasets and 2.672 kN, 1.967 kN, 0.963, 0.961, 0.989 and 0.761, respectively, for the test datasets. It can be concluded that the proposed PSO-RF model has the best comprehensive performance in predicting the bond strength of FRP-to-concrete. In addition, the sensitivity analysis of the PSO-RF model was also conducted in this study
Planning municipal drainage infrastructure maintenance operations with finite available crews: pragmatic optimization approach
No full textThis paper proposes a streamlined approach to addressing the problem of allocating finite crew resources to concurrent jobs in the context of municipal drainage infrastructure maintenance. The problem was defined from the perspective of a project manager involved in planning such operations on a day-by-day basis. The problem statement was then transformed into a simplified Integer Linear Programming optimization model. Performance metrics were devised to evaluate the optimization model’s effectiveness. A heuristic algorithm representing the decision-making process by a seasoned planner in the partner company was also developed. Both methods were applied to a case study and contrasted based on the same performance metrics. The findings underscored substantial optimization benefits in rendering decision support in resource-constrained drainage construction operations planning. In conclusion, this research presents an alternative strategy for navigating the complexities inherent in finite crew resource allocation on multiple concurrent drainage projects; lends a cost-effective optimization solution to improving the utilization of finite available crews while satisfying service demands from multiple clients to the largest extent possible
Municipal solid waste collection and transportation routing optimization based on IAC-SFLA
No full textIn order to realize the efficient collection and low-carbon transport of municipal garbage and accelerate the realize the “dual-carbon” goal for urban transport system, based on the modeling and solving method of vehicle routing problem, the municipal solid waste (MSW) collection and transport routing optimization of an Improved Ant Colony-Shuffled Frog Leaping Algorithm (IAC-SFLA) is proposed. In this study, IAC-SFLA routing Optimization model with the goal of optimization collection distance, average loading rate, number of collections, and average number of stations is constructed. Based on the example data of garbage collection and transport in southern Baohe District, the comparative analysis with single-vehicle models, multiple-vehicle models, and basic ant colony algorithms. The multi-vehicle model of collection and transportation is superior to the single-vehicle model and the improved ant colony algorithm yields a total collection distance that is 19.76 km shorter and an average loading rate that rises by 4.15% from 93.95% to 98.1%. Finally, the improved ant colony algorithm solves for the domestic waste collection and transportation path planning problem in the north district of Baohe. Thus, the effectiveness and application of the proposed algorithm is verified. The research result can provide reference for vehicle routing in the actual collection and transport process, improve collection and transport efficiency, and achieve the goal of energy conservation and emission reduction
Mapping the salinity status of agricultural soils between Kırıkhan-Kumlu in the Eastern Mediterranean region of Turkey with Geographic Information Systems (GIS)
No full textIn this study, it was aimed to determine the salinity status of agricultural soils between Kırıkhan-Kumlu in the Eastern Mediterranean region of Turkey by mapping with Geographic Information Systems (GIS). For this purpose, a total of 60 soil samples were taken from 0–20 and 20–40 cm depths and from 30 different points to represent the agricultural soils of Kırıkhan-Kumlu region in the Eastern Mediterranean region of Turkey. In the soil samples, pH, cation exchange capacity (CEC) and exchangeable cation (ECC) values were determined to determine some soil properties. Total salt, salinity class, sodium adsorption rate (SAR), exchangeable sodium percentage (ESP) and soluble cations (Na, Ca and Mg) were determined to determine the salinity status of the soils.According to the results of the research; as a result of the analysis carried out to determine the salinity status of the soils; pH values were determined between 6.91–7.98; total salt content between 0.02–0.13%; SAR values between 0.023–0.044 me/100 gr; ESP values between 0.35–2.96%; soluble Na content between 0.019–0.034 me/100 gr; soluble Ca content between 0.018–0.245 me/100 gr and soluble Mg content between 0.037–0.113 me/100 gr. In addition, by applying the ESP-SAR regression relationship of the soils, it was revealed that the soils tended to alkalize towards the lower layers. The salinity values obtained as a result of the study were transferred to the Geographic Information Systems (GIS) environment and interpolated by Kriging method and a salinity map of the study area was created. In conclusion, as a result of the research conducted in the soils of the study area in the Eastern Mediterranean region, it was determined that all of the agricultural soils of Kırıkhan-Kumlu region were classified as non-saline and that the soils did not have any problems in terms of salinity
Effects of evergreen trees on mental restorative quality of winter landscapes
No full textCompared with other seasons, winter usually has low mental restorative quality due to the lack of greenness. Reasonably adding evergreen trees to winter landscapes can improve the quality. However, what proportion, species and planting site of evergreen trees are better for mental restoration? To address this question, two original pictures (describing two landscape types) and 24 manipulated pictures (including three categories and four grades of proportion of evergreen trees) were collected, and 381 respondents were employed to score the mental restorative quality of each picture. The results revealed that planting evergreen trees in the landscape with water was more efficient in promoting mental restoration than planting them in the landscape without water. Adding broad-leaved evergreen trees was much better than adding coniferous trees and the mixture of the two. And, for the landscape with water, moderate proportion of evergreen trees possessed significantly higher mental restoration than low or high proportion
Risk-based regulation and supervision of second-tier banks: experience of EU countries
No full textThe aim of the study was to determine the impact of increased capital adequacy standards of second-tier banks on their performance. The study is based on second-tier banks of EU member states, as these countries are the first to implement the Basel Committee recommendations, so their experience should be studied and taken into account when building risk-based regulation of second-tier banks of Ukraine and Kazakhstan. The study covers the period of 2009–2022, as the Basel III regulations were adopted after 2008, and they began to operate for the second-tier banks of EU member states in 2013. The study was conducted using econometric modelling with an analysis of the dependence of banking indicators on the capital structure established by Basel III. Functional interrelationships of the dependence of Net Interest Income, Profit, Return on Assets, Return on Equity, Risk Costs to Operating Income were tested. The impact of capital adequacy requirements on the performance of second-tier banks was determined: capital adequacy requirements have a positive impact on net interest income and profit of second-tier banks. The obtained results can be used to substantiate increasing capital adequacy requirements to increase the reliability of the banking system as an element in the system of factors of economic growth of the national economy
Methodical approach to the choice of a business management strategy within the framework of a change in commercial activities
No full textThe main purpose of the article is the formation of new strategies in business management with changes in commercial activities. The object of the study is the system of commercial activity and possible changes in it. The scientific task is the definition of a new methodological approach to the formation of new strategies in business management with changes in commercial activity. The research methodology involves the use of a modern method for modeling strategies in business management with changes in business activities. As a result, we presented a methodical approach to the formation of business management strategies in the face of changes in commercial activities. The author’s vision of how the stages of forming the main business management strategy through block-object-oriented modeling should look graphically and schematically was presented. Each of its blocks involves many processions and actions aimed at changes in commercial activity. The innovative novelty of our study lies in the presented methodological approach to the formation of a business management strategy within the framework of changes in commercial activity
Strengthening innovative behavior: the role of supportive climate and absorptive capacity
No full textThis study explores how to achieve innovative behavior in Indonesian SMEs in the culinary and craft sectors. We conducted a literature review and collected data from 372 SME owners. Using SEM analysis, we found that a supportive climate positively impacts both potential and realized absorptive capacity, which in turn positively impacts innovative behavior. The study’s findings contribute to social exchange theory and have implications for SME sector organizations. Limitations include the data collection method, sample size and selection, research objective, cross-sectional design, and self-reported data. Future research could address these limitations and investigate other organizational factors that may influence innovative behavior in SMEs