Tomas Bata University in Zlín
Institutional repository of Tomas Bata University LibraryNot a member yet
10673 research outputs found
Sort by
The implementation of neural networks for polymer mold surface evaluation
Get PDFThis paper presents the measurement and evaluation of the surfaces of molds produced using additive technologies. This is an emerging trend in mold production. The surfaces of such molds must be treated, usually using laser-based alternative machining methods. Regular evaluation is necessary because of the gradually deteriorating quality of the mold surface. However, owing to the difficulty in scanning the original surface of the injection mold, it is necessary to perform surface replication. Therefore, this study aims to describe the production of surface replicas for in-house developed polymer molds together with the determination of suitable descriptive parameters, the method of comparing variances, and the mean values for the surface evaluation. Overall, this study presents a new summary of the evaluation process of replicas of the surfaces of polymer molds. The nonlinear regression methodology provides the corresponding functional dependencies between the relevant parameters. The statistical significance of a neural network with two hidden layers based on the principle of Rosenblatt’s perceptron has been proposed and verified. Additionally, machine learning was utilized to better compare the original surface and its replica.Tomas Bata University in Zlín, TBU, (IGA/FT/2024/002
Initial coin offering prediction comparison using Ridge regression, artificial neural network, random forest regression, and hybrid ANN-Ridge
Get PDFCan machine learning take a prediction to win an investment in ICO (Initial Coin Offering)? In this research work, our objective is to answer this question. Four popular and lower computational demanding approaches including Ridge regression (RR), Artificial neural network (ANN), Random forest regression (RFR), and a hybrid ANN-Ridge regression are compared in terms of accuracy metrics to predict ICO value after six months. We use a dataset collected from 109 ICOs that were obtained from the cryptocurrency websites after data preprocessing. The dataset consists of 12 fields covering the main factors that affect the value of an ICO. One-hot encoding technique is applied to convert the alphanumeric form into a binary format to perform better predictions; thus, the dataset has been expanded to 128 columns and 109 rows. Input data (variables) and ICO value are non-linear dependent. The Artificial neural network algorithm offers a bio-inspired mathematical model to solve the complex non-linear relationship between input variables and ICO value. The linear regression model has problems with overfitting and multicollinearity that make the ICO prediction inaccurate. On the contrary, the Ridge regression algorithm overcomes the correlation problem that independent variables are highly correlated to the output value when dealing with ICO data. Random forest regression does avoid overfitting by growing a large decision tree to minimize the prediction error. Hybrid ANN-Ridge regression leverages the strengths of both algorithms to improve prediction accuracy. By combining ANN’s ability to capture complex non-linear relationships with the regularization capabilities of Ridge regression, the hybrid can potentially provide better predictive performance compared to using either algorithm individually. After the training process with the cross-validation technique and the parameter fitting process, we obtained several models but selected three of the best in each algorithm based on metrics of RMSE (Root Mean Square Error), R2 (R-squared), and MAE (Mean Absolute Error). The validation results show that the presented Ridge regression approach has an accuracy of at most 99% of the actual value. The Artificial neural network predicts the ICO value with an accuracy of up to 98% of the actual value after six months. Additionally, the Random forest regression and the hybrid ANN-Ridge regression improve the predictive accuracy to 98% actual value
Assessing the risk of a terrorist attack against a soft target: The use of expert opinion in threat assessment
No full textThe article reviewed the methods for assessing the risks of a terrorist attack against a soft target. Considering the number of factors affecting the choice of a target by a terrorist group or individual terrorists and the limited usability of historical data on previous terrorist attacks, the article further focuses on the possibility of using expert opinion on the importance of criteria for identifying soft targets. For this purpose, a questionnaire survey was conducted at the regional police directorates of the Police of the Czech Republic. Based on the survey results, the level of security, the number of persons, and its symbolic significance were identified as the most important criteria for selecting a soft target as a target of a terrorist attack
The modification of useful injection-molded parts' properties induced using high-energy radiation
Get PDFThe modification of polymer materials' useful properties can be applicable in many industrial areas due to the ability to make commodity and technical plastics (plastics that offer many benefits, such as processability, by injection molding) useful in more demanding applications. In the case of injection-molded parts, one of the most suitable methods for modification appears to be high-energy irradiation, which is currently used primarily for the modification of mechanical and thermal properties. However, well-chosen doses can effectively modify the properties of the surface layer as well. The purpose of this study is to provide a complex description of high-energy radiation's (β radiation) influence on the useful properties of injection-molded parts made from common polymers. The results indicate that β radiation initiates the cross-linking process in material and leads to improved mechanical properties. Besides the cross-linking process, the material also experiences oxidation, which influences the properties of the surface layer. Based on the measured results, the main outputs of this study are appropriately designed regression models that determine the optimal dose of radiation.Internal Grant Agency of Tomas Bata University in Zlin, (IGA/CebiaTech/2024/002, IGA/FT/2024/003)Internal Grant Agency of Tomas Bata University in Zli
Regenerable chitosan-embedded magnetic iron oxide beads for nitrate removal from industrial wastewater
No full textIndustrial sites worldwide significantly contribute to water pollution. Nitrates are a common effluent pollutant from such sites. Effective means to remove nitrate ions (NO3-) from polluted waters are needed. Chitosan beads, which are a non-toxic, biocompatible, and biodegradable polymer, are used for this purpose in this research. Iron-oxide nanoparticles are synthesized via the co-precipitation route and embedded into chitosan by chemical co-precipitation to form ion exchange chitosan beads (IECBs) for NO3- removal. The performance of the IECBs in a batch system was studied against NO3- adsorption from industrial water. Morphological, structural, and chemical characterization was performed by SEM, EDX mapping, BET, XRD, and FTIR, while the extent of NO3- adsorption was quantified using UV-vis spectroscopy. Different factors influencing the adsorption of NO3- on the IECBs were investigated, including the adsorbent dosage, pH of the solution, initial concentration, and interaction time. It is demonstrated that pseudo-second-order isothermal and kinetic models were best fits to the experimental data. It was found that the IECBs had a maximum adsorption capacity of 47.07 mg g-1 and could load up to similar to 93% of the NO3- from the batch system. The regeneration efficiency for the IECBs over 5 cycles remained high in the range of 93% to 79%, indicating their potential for industrial water treatment use. Synthesis of regenerable chitosan-embedded magnetic iron oxide beads.Higher Education Commission, Pakistan; National University of Sciences and Technology (NUST) Research Directorate, HEC [6020]; NRPU [RP/CPS/2022/002]; Ministry of Education, Youth, and Sports of the Czech Republic DKRVOMinistry of Education, Youth, and Sports of the Czech Republic DKRVO, (RP/CPS/2022/002); NRPU, (6020); Healthcare Excellence Canada, HEC; National University of Sciences and Technology, NUS
Investigating the potential of AI-driven innovations for enhancing differential evolution in optimization tasks
No full textIn recent years, artificial intelligence (AI) and machine learning have demonstrated remarkable potential in various application domains, including optimization. This study investigates the process of leveraging AI, particularly large language models (LLMs), to enhance the performance of metaheuristics, with a focus on the well-established Differential Evolution (DE) algorithm. We employ GPT, a state-of-the-art LLM, to propose an improved mutation strategy based on a dynamic switching mechanism, which is then integrated into the DE algorithm. Throughout the investigation, we also observe and analyze any errors or limitations the LLM might exhibit. We conduct extensive experiments on a comprehensive set of 30 benchmark functions, comparing the performance of the proposed AI-inspired strategy with the standard DE algorithm. The results suggest that the AI-driven dynamic switching mutation strategy provides a competitive edge in terms of solution quality, showcasing the potential of using AI to guide the development of improved optimization algorithms. This work not only highlights the effectiveness of the proposed strategy but also contributes to the understanding of the process of using LLMs for enhancing metaheuristics and the challenges involved therein.Faculty of Applied Informatics, Tomas Bata University in Zlin; Tomas Bata University in Zlín, TBU, (IGA/CebiaTech/2023/004
The influence of building orientation of additively produced samples on their mechanical properties
No full textDirect metal laser sintering (DMLS) produces parts from metal powders using the energy of the laser beam to promote sintering in an inert and thermally controlled chamber environment. Many factors influence the resulting mechanical properties of each part. One of these parameters is the direction in which the part is built. The paper addresses the behavior of 3D-printed maraging steel MS1 in uniaxial tensile tests, where the effect of specimen orientation on the modulus of elasticity as well as other mechanical properties was investigated. The morphology of the fracture surfaces was also evaluated using scanning electron microscopy. Standard specimens were fabricated using DMLS technology in five different orientations, with ten specimen pieces produced in each direction. After 3D printing, the specimens were heat treated to remove residual stresses and machined to final dimensions after removal from the building platform. The measured values were statistically processed and the mechanical properties were evaluated. The tests showed that the orientation of the sample during its production has an effect on the mechanical properties. The comparison of the results with the tensile properties stated by the manufacturer of the steel powder in the data sheet confirmed the values in the declared range. Numerical analysis realized based on measured data implemented to the ANSYS software confirmed experimentally obtained value for ultimate tensile stress. It could be also stated that the morphology of fracture surfaces in most samples was characterized by ductile damage with a pitting effect.Ministerstvo školstva, vedy, výskumu a športu Slovenskej republiky, (032TUKE-4/2022, APVV-19-0550, APVV-19-0550 KEGA 005TUKE-4/2021); Kultúrna a Edukacná Grantová Agentúra MŠVVaŠ SR, KEGA, (005TUKE-4/2021
From fruit waste to hydrogels for agricultural applications
Get PDFHere, we describe and assess a method for reusing specific food waste to make hydrogels, which can be employed to improve the efficacy of agrochemicals and water. It represents an approach for tackling current challenges, such as food waste, water management, and pesticide optimization. Depending on the formulation, the hydrogels were created by crosslinking pectin and starch with CaCl2 or sodium trimetaphosphate. FTIR and SEM were employed to investigate the methylation degree of the extracted pectin, as well as the surface morphology and interior structure of the hydrogels. The swelling behavior and water retention in sandy soil have been investigated. In addition to the hydrogels’ potential to control and reduce pesticide loss, the herbicide Picloram is a model compound. The results show that the hydrogels have important swelling, up to 300%, and a capacity to retain water, preserve, and increase the water content in sandy soil up to 12 days. Picloram experiments show that hydrogels can limit herbicide mobility for up to 30 days under controlled conditions. The conversion of food wastes to highly valuable materials is a promising approach to optimize the water consumption and the loss of agrochemicals regarding sustainable agriculture.Ministry of Science and Higher Education of Russian Federatio
Interlinking dynamics of natural resources, financial development, industrialization, and energy intensity: Implications for natural resources policy in emerging seven countries
No full textThe study examines the intricate relationship between energy poverty, natural resources rents, energy intensity, financial development, and industrialization, with CO2 emissions in the E−7 countries from 1996 to 2021. This study utilizes a nonparametric econometric approach known as the method of moments quantile regression. The findings highlight significant associations among these variables. Higher energy poverty levels are linked to increased CO2 emissions, indicating a correlation between energy poverty and carbon emissions. Likewise, higher energy intensity, reflecting lower energy efficiency, contributes to greater carbon emissions. Furthermore, reliance on natural resources for economic development is positively associated with CO2 emissions, suggesting potential environmental deterioration. The financial development shows a positive association with CO2 emissions, suggesting that increased financial resources may lead to higher carbon emissions. However, this relationship diminishes at higher levels of financial development, indicating a potential decoupling of financial progress from carbon emissions. Industrialization and natural resources display a positive relationship with CO2 emissions, highlighting the contribution of industrialization to carbon emissions. Policymakers are urged to prioritize energy efficiency promotion, facilitate the transition to renewable energy sources, and encourage sustainable industrial practices. Integrating innovation activities that prioritize green technologies and sustainable development can effectively reduce CO2 emissions while supporting economic growth. These findings hold crucial implications for policymakers in the E−7 countries, emphasizing the need for sustainable development and environmental stewardship. Striking a balance between economic growth and environmental preservation is essential for a sustainable future in the E−7 countries
Heat treatment of steel 100CrMn6: Influence of temperature and austenitization time
Get PDFThis study deals with influence of temperature and time of austenitization on final mechanical properties, especially Rockwell hardness (HRC), obtained after heat treatment of steel 100CrMn6 (1.3520). Following process parameters of heat treatment were varied: time of austenitization and type of cooling medium, which has a significant effect on final strucutre, thus mechanical properties. These parameters were varied according to reccomended range given in material sheet. As can be seen from results, different temperature and time of austenitization influenced final hardness after hardening and tempering. Lower temperature and shorter time of austenitization led to insufficient homogenization of austenite and incomplete transformation to martensite and bainite, which resulted in lower hardness. On the other hand, higher temperature and longer time of austenitization can lead to coarser austenite grain, which can also result in lower hardness.Internal Grant Agency of TBU in Zlin [IGA/FT/2024/003