machinery
Not a member yet
8395 research outputs found
Sort by
Neuro-fuzzy control of commercial vehicles braking
No full textIncreasing dynamic performance and the general level of automation of commercial vehicles emphasize the issue of safety. Modern braking systems focus on sustaining vehicle stability, often degrading the brake performance. The major downgrades of the braking performance are nearly impossible to model using a classical mathematical approach, making them not feasible to use in real braking system controllers. In this paper, the use of combined Neural Networks and Fuzzy logic for the control of the braking system of a commercial vehicle while maximizing performance and sustaining stability is proposed. The control system comprises adhesion estimation, an inverse brake model, and a fuzzy logic controller to keep the system giving optimal control signals in various brake conditions while sustaining vehicle stability and steerability. The results based on a semi-trailer system reveal the success of the proposed AI-based braking system algorithm while braking under varying conditions.No. 451-03-65/2024-03/200105, February 5, 2024
Extension of the Throughflow Solver for Predicting the Aerodynamic Performance of Fans with Inlet Distortion
No full textNext-generation aircraft with boundary layer ingesting (BLI) engines can reduce fuel consumption but pose challenges for fan and compressor operation due to inlet distortion. To optimize the design of such engines, it is essential to assess the impact of non-uniform inlet flow on stability and performance, with the final result of a distortion-tolerant machine. One of the first steps in this process is estimating the aerodynamic performance using fast but reliable mathematical models. This paper presents an extension of the existing throughflow solver that predicts the effects of the upstream distortion. The proposed method, based on the parallel compressor theory, introduces multiple planes to accurately define and track the circumferential distribution of parameters as they advance through the machine. It applies to all types of distortion: total pressure, total temperature, and swirl. The model is demonstrated for a high-pressure, low hub-to-tip diameter ratio fan with nonuniform total pressure at the inlet. Flow physics associated with distortion is analyzed using results from full annulus unsteady RANS simulations for three operating points: near stall, design, and near choke. The flow field results are compared with the CFD data at the design point. The overall performance is evaluated against a clean inlet case
EXPERIMENTAL AND NUMERICAL INVESTIGATION OF THE TURBULENT SWIRLING FLOW IN PIPE BEHIND THE AXIAL FAN IMPELLER
No full textExperimental and numerical research of the turbulent swirling flow in pipe behind the axial fan impeller, which generates solid body profile of the circumferential velocity, is presented in this paper. This is a phenomenon relevant to numerous industrial applications, where axial fans are still inbuilt without the guide vanes. The experimental investigation was carried out using stereo PIV, LDA, and original classical probes. However, in this research are discussed three velocity components measured subsequently by use of the one-component LDA system.
The applied numerical approach involved solving the Navier-Stokes equations under appropriate turbulence modeling conditions, ensuring a high level of accuracy in predicting the swirl intensity and velocity distribution in the pipe. The combination of the unstructured mesh in the inlet and the runner section and structured mesh in the outlet section with the application of the SST and k-ε turbulence models led to the final results. Average velocity profiles, determined in this numerical simulation, are compared with the experimentally obtained data and differences are quantified. These experimentally validated numerical results enable good physical interpretation of the development of the average velocity profiles of the generated turbulent swirling flow in the entire domain.no. 451-03-65/2024-03/20010
Numerical Simulation of Five-Hole Probe Used for Small UAV
No full textThe multi-hole probe (MHP) is extensively employed in turbomachinery, although its application in the aviation industry is relatively limited. With the recent expansion of the aviation field, especially small unmanned aerial vehicles (UAVs) and drones, there is now a variety of unmanned aircraft, each with its own specific features. The MHP provides a compact, easy-to-manufacture, and accurate way to measure flight angles while gathering real-time external data. This study presents a numerical simulation of a five-hole probe, which is compared with experimental data obtained from wind tunnel testing. The objective is to assess the feasibility of utilizing numerical simulation for the calibration of the five-hole probe, thereby reducing reliance on traditional wind tunnel testing methods
Fuzzy Lyapunov Approach for Adaptive System Control
No full textFor the efficient speed control of DC motors, this paper combines
Model Reference Adaptive Control (MRAC) and Fuzzy Logic (FL).
The proposed approach ensures stability and good system performance
for various desired speeds and undesired disturbances
2D Truss optimization using FEM-PSO and Generative AI
No full textThis paper presents the theoretical foundations and
implementation of a web-based application for the Particle
swarm optimization of 2D truss structures. The framework
achieves its objective through the integration of three powerful
computational tools: the Finite Element Method (FEM) for
deterministic structural analysis, Particle Swarm
Optimization (PSO) for heuristic, population-based design
exploration, and Large Language Model (LLM), Google's
Gemini, for automated interpretation of results.
Mathematical foundation of the FEM, the bio-inspired
algorithmic behavior of PSO [1], and the transformer-based
architecture that enables the reasoning capabilities of LLMs
[2] are shown. The result is a tool that not only solves
engineering problem but also serves as a case study in the
powerful emerging synthesis of classical numerical methods
and advanced artificial intelligence.No. 451-03-137/2025-03/200105, dated February 4, 202
Novel Design of an Optimized Morphing EDF Duct
No full textElectric Ducted Fans (EDF) provide several advantages over conventional propellers. In hover they can provide additional thrust for the same power
and rotor diameter meaning smaller footprint of the aircraft on the take-off/landing
area. In axial flight the shroud reduces the tip losses of the rotor especially in higher
flight speeds. Unfortunately, due to the difference in velocity streamlines in both
flight regimes, a shroud optimized for hover will have negative effects on the
propulsion efficiency in axial flight. This means that a compromise must be made
in the design of a propulsion system intended for fixed wing Vertical Take-off
Landing (VTOL) aircraft with efficient axial flight capabilities for example, using
separate systems for hover and for axial flight. Here, an optimization methodology is proposed for a novel design of a morphing ducted fan. Firstly, the optimal
geometry for hover was obtained by genetic algorithm (GA) optimization. After
that, GA optimization was used to obtain the optimal geometry for cruise with the
introduction of constraints as to be able to create a geometry capable of morphing.
In the end, the internal structure of the duct which can provide accurate control of
the inlet and outlet was defined by utilizing techniques similar to the ones used in
morphing wing designs
The Impact of Top and Middle Management Commitment to Occupational Safety and Health on Corporate Social Responsibility in Mining Industry
No full textCorporate social responsibility (CSR) is centered on the idea that organizational leaders have an obligation to make decisions and take actions that are desirable according to the values of society. Nonetheless, a growing corpus of research increasingly focuses on comprehending how individual-level elements, such as managerial engagement and attitudes, influence CSR initiatives within businesses. In that aim, this study examines the impact of managerial commitment to occupational safety and health (OSH) on different dimensions of CSR. Using a quantitative approach, data were collected on the sample sized 33 and analyzed through reliability, factor and regression analysis. The model proved statistically significant relationship between managerial OSH commitment and CSR performance. This paper findings underscore the crucial role that managerial engagement in workplace safety plays important role in CSR plans by showing that higher managerial commitment to OSH improves CSR outcomes. Future research should focus to sample enlargement and structural equations modeling application.contract no. 451-03-65/2024-03/200105 from 05.02.202
COGNITIVE MOBILE ROBOTICS BASED ON INTELLIGENT MECHANISMS OF LEARNING
No full textThe purpose of this contribution is the deployment of digital manufacturing through new cognitive
intelligence mechanisms. With the implementation of Industry 4.0 principles, mobile intelligent robots utilized as transportation vehicles in the manufacturing system need a higher degree of autonomy to fulfill all the requirements of the contemporary market. Although industrial robots are common in manufacturing systems, mobile robotics requires the expertise of specialists in cognitive robotics issues to gain international competitiveness, particularly for small and medium-sized enterprises. The industrial mobile robots’ autonomous subsystems based on deep machine learning provide significantly more flexibility as well as more accurate and robust real-time decisions compared to common deterministic sensor-based algorithms. The main goal of this paper is to create artificial intelligence-based solutions for cognitive mobile robotics within Industry 4.0 using a Machine Learning (ML) based approach, particularly deep learning (convolutional neural networks, recurrent neural networks, etc.). The focus of the paper is the generation of new ML-based cognitive intelligence mechanisms for obstacle avoidance, decision-making, and visual control of intelligent mobile robots, whereas the main goal of the paper is to demonstrate the possibility of integrating intelligent ML-based algorithms into a high-level cognitive architecture by enabling better understanding of the environment in real-time through the processing of higher-quality and more complex sensory data, thereby enhancing the overall flexibility of mobile robotic systems within intelligent manufacturing systems.40th International Conference of Production Engineering (ICPES 2025) - Serbia 2025, Nis, Serbia, 18th - 19th
September 2025,
Editors:
Prof. dr Miodrag T. Manić, University of Niš, Faculty of Mechanical Engineering,
Prof. dr Saša S. Ranđelović, University of Niš, Faculty of Mechanical Engineering
EFFICIENCY OF SOLAR CELLS IN THE CONDITIONS OF ELECTROMAGNETIC OR NEUTRON RADIATION
No full textThe paper discusses the influence of the dose of gamma or neutron radiation on commercial silicon photovoltaic cell under operating conditions. Before the measurement, the cells were irradiated with electromagnetic gamma radiation or neutron radiation. The examination was carried out experimentally and theoretically. The experiments were performed under well-controlled laboratory condidtions. Only licenced instruments were used. The measurement uncertanty of the experimental procedure was less than 5%.MNTR 451-03-137/2025-03/20010