International Scientific Journals
of Scientific Technical Union of Mechanical Engineering "Industry 4.0"

Explosively welded materials exhibit heterogeneous microstructures and variable mechanical properties, making local analysis crucial for the evaluation of joint integrity. Nanoindentation effectively assesses interface properties but typically relies on a series of analytical calculations. This paper proposes a machine learning approach to predict hardness directly from measured load-displacement curves. A neural network model captures nonlinear relationships in indentation data, demonstrating high accuracy against reference measurements across heterogeneous microstructure. This data-driven method offers a scalable solution for rapid, reliable property assessment in complex engineering materials.

This paper investigates the inverse problem for thermal bridges – determining design parameters (such as material, geometry, thermal resistance R of the components) of the bridge at a known Psi-factor. By using artificial neural networks, a thermal bridge type IF (wall-floor connection) has been considered to evaluate the effectiveness of the methodology. The results show that the approach provides a fast and accurate way to predict the optimal parameters that meet specific energy efficiency requirements. In the future, this approach could help to determine the parameters of thermal bridges using thermographic images non-invasively.

The publication examines the use of artificial neural networks to calculate the linear thermal conductivity (Psi-factor) of thermal bridges given various parameters, such as geometrical data and the thermal resistance R of the thermal bridge components. The neural network is trained on examples of IF, IW, and B thermal bridges, considering the straightforward task of determining Psi using given parameters. The neural network training results show high accuracy in calculations – RMSE is 1.132% on training data and 1.1423% on test data, and the correlation coefficient (R²) is around 0.9997 for both data sets. The applicability of the approach to seismic conditions in the Balkans is assessed.

This paper examines an innovative approach for modeling the influence of climate parameters on transport infrastructure using artificial neural networks. Through them, detailed climatic data are generated by geographical positions and monthly and annual maps are created for Bulgaria’s territory using the following parameters: surface temperature, diffuse fraction, horizontal solar irradiation, and average albedo of the terrain. Average ground temperature and monthly solar irradiation are essential for maintenance planning and developing strategies to adapt to extreme weather conditions, such as heat waves or frost, which can affect the condition and performance of the road surface. Average monthly temperatures can be used to design effective systems to prevent icing of road surfaces and improve drainage systems. By demonstrating the capabilities of accurate modeling and analysis, this paper highlights the importance of applying artificial neural networks in planning and improving the resilience of transport infrastructure against climate change.

The Industry 4.0 revolution has significantly influenced the control of non-linear Multiple Input Multiple Output (MIMO) systems, particularly through the application of artificial neural networks (ANNs). This paper explores current trends in the control of non-linear MIMO objects, emphasizing the role of ANNs in enhancing performance and efficiency. Key developments, methodologies, and case studies are reviewed to illustrate the impact of ANNs on non-linear MIMO control

This paper examines an approach using artificial neural networks for innovative modeling of solar data that is needed to realize solar applications for transport infrastructure purposes. Through this modeling, detailed solar data are generated by geographical positions, and monthly and annual maps are created for the territory of Bulgaria for horizontal solar irradiation with its diffuse and direct components and for inclined and reflected solar irradiation, according to Norio Igawa’s model. Diffuse fraction and horizontal and inclined solar irradiation can be helpful in designing solar applications in road infrastructure, such as power signaling systems and street lighting. By demonstrating the capabilities of accurate modeling and analysis of solar data, this paper highlights the importance of applying artificial neural networks in planning and improving the resilience of transport infrastructure against climate change. Using solar energy in transport infrastructure reduces carbon emissions and strengthens environmental sustainability.

We are witnessing the massive and impressive penetration of artificial intelligence (AI) into many areas of human activity. This process is expected to intensify in the next few decades. In most technical fields, there will be a preponderance of the so-called narrow artificial intelligence with clearly defined tasks and functions. It is usually a coherent set of neural networks trained to solve specific problems. The advantage of narrow AI is that it is entirely controllable and, at the same time, has excellent capabilities. This publication aims to outline guidelines for applying narrow artificial intelligence in investigating the impact of climate change on transport infrastructure. After a brief introduction to narrow artificial intelligence and climate change, various possible areas suitable for AI modeling are explored. Directions and preparatory tasks for collecting climate-sensitive local data on the condition and changes in the transport infrastructure in Bulgaria necessary for AI training are identified.

Previous work has determined the ability of using the Multilayer Perceptron (MLP) type of Artificial Neural Network (ANN) to estimate the power output of a Combined Cycle Power Plant (CCPP) in which optimization did not focus on the solver parameter optimization. In previous work, the solvers used the default parameters. Possibility exists that optimizing solver parameters will net better results. Two solver algorithm’s parameters are optimized: Stochastic Gradient Descent (SGD) and Adam, with 140 and 720 parameter combinations respectively. Solutions are estimated through the use of Root Mean Square Error (RMSE). Lowest RMSE achieved is 4.275 [MW] for SGD and 4.259 [MW] for Adam, achieved with parameters: = 0.05, = 0.02, and nesterov=True for SGD and with parameters = 0.001, 1 = 0.95, 2 = 0.99, and amsgrad=False for Adam. Only a slight improvement is shown in comparison to previous results (RMSE=4.305 [MW]) which points towards the fact that solver parameter optimization with the goal of improving results does not justify the extra time taken for training.

Large amounts of liquidity flow into several precious metals every day. Investment decisions are mainly based on predicting the future movements of the instrument(s) in question. However, high frequency financial data are somewhat hard to model or predict as stochastic processes and many other random factors are involved. It would be valuable information for the investor if he or she knew which precious metals were quantitatively more predictable, that would also be a good basis for more robust trading decisions. The objective in this study is to build predictive models on high frequency precious metal data and compare predictabilities of different metals using only past price and volume values which should be a basis for robust trading decisions. The data used consist of various frequencies from 1-minute to 4-hour covering a period of almost 20 years for each instrument and frequency. Artificial Neural Network (ANN) and Gradient Boosted Decision Tree (XGB) methods are applied. Comparable results are achieved.

Large amounts of liquidity flow into several precious metals every day. Investment decisions are mainly based on predicting the future movements of the instrument(s) in question. However, high frequency financial data are somewhat hard to model or predict as stochastic processes and many other random factors are involved. It would be valuable information for the investor if he or she knew which precious metals were quantitatively more predictable, that would also be a good basis for more robust trading decisions. The objective in this study is to build predictive models on high frequency precious metal data and compare predictabilities of different metals using only past price and volume values which should be a basis for robust trading decisions. The data used consist of various frequencies from 1-minute to 4-hour covering a period of almost 20 years for each instrument and frequency. Artificial Neural Network (ANN) and Gradient Boosted Decision Tree (XGB) methods are applied. Comparable results are achieved

Nowadays all companies and corporations have their own external and internal servers with information that require specialized software for their support and configuration. Sometimes when data is exchanged with other external or internal sources for unwanted reasons data traffic may be different than expected. In this case, artificial neural networks may be used to monitor the traction. Thanks to their ability to learn the artificial neural networks can detect an anomaly in communication traffic.

In this paper, we present an object detection system and its application to plasma sprayed coatings implants with the classifier based on the Principal Component Analysis (PCA). In order to improve performance of the classifier, we used combinations of halftone images and gradient images generated by the Sobel operator. To improve the quality of plasma coatings we apply intelligent control methods based on artificial neural networks and Bayesian network for optimization the weights