Péter Tamás Szemes

Operating pressurized water reactor (PWR) nuclear power plants requires effective regulation of the control rod speed to achieve the desired reactor power demand. However, the presence of time delay in the control rod speed due to latency in communication and aging can lead to output power oscillation and instability. This paper proposes a backstepping fractional-order proportional-integral-derivative (PID)-based sliding mode control (SMC) with a finite-time convergence for power control of a PWR with control time delay compensated using an auxiliary signal to mitigate any power oscillation. Due to the simple structure and approximation accuracy of the multi-dimensional Taylor network (MDTN), it is employed to identify the complex dynamics of the reactor. The MDTN approximation error is attenuated using an adaptive law to improve the approximation accuracy. The bended tracking error (BTE) scheme is used to eliminate the SMC reaching phase so that the output power can track the desired level at the initial time in the sliding phase, thereby ensuring robustness and convergence within a preassigned settling time. The finite-time stability of the closed-loop system is demonstrated through Lyapunov-based analysis. Simulation results have shown that the proposed power control achieved a root-mean-square error (RMSE) of 0.002305, which is superior compared to high-order sliding mode control (HOSMC) and radial basis function neural network-based event-triggered fixed time control (RBFNN-ET-FT) that achieved an RMSE of 1.745 and 0.880, respectively.

The automotive suspension must perform competently to support comfort and safety when driving. Traditionally, car suspension control tuning is performed through trial and error or with classical techniques that cannot guarantee optimal performance under varying road conditions. The study aims at designing a Linear Quadratic Regulator-based Bacterial Memetic Algorithm (LQR-BMA) for suspension systems of automobiles. BMA combines the bacterial foraging optimization algorithm (BFOA) and the memetic algorithm (MA) to enhance the effectiveness of its search process. An LQR control system adjusts the suspension’s behavior by determining the optimal feedback gains using BMA. The control objective is to significantly reduce the random vibration and oscillation of both the vehicle and the suspension system while driving, thereby making the ride smoother and enhancing road handling. The BMA adopts control parameters that support biological attraction, reproduction, and elimination-dispersal processes to accelerate the search and enhance the program’s stability. By using an algorithm, it explores several parts of space and improves its value to determine the optimal setting for the control gains. MATLAB 2024b software is used to run simulations with a randomly generated road profile that has a power spectral density (PSD) value obtained using the Fast Fourier Transform (FFT) method. The results of the LQR-BMA are compared with those of the optimized LQR based on the genetic algorithm (LQR-GA) and the Virus Evolutionary Genetic Algorithm (LQR-VEGA) to substantiate the potency of the proposed model. The outcomes reveal that the LQR-BMA effectuates efficient and highly stable control system performance compared to the LQR-GA and LQR-VEGA methods. From the results, the BMA-optimized model achieves reductions of 77.78%, 60.96%, 70.37%, and 73.81% in the sprung mass displacement, unsprung mass displacement, sprung mass velocity, and unsprung mass velocity responses, respectively, compared to the GA-optimized model. Moreover, the BMA-optimized model achieved a −59.57%, 38.76%, 94.67%, and 95.49% reduction in the sprung mass displacement, unsprung mass displacement, sprung mass velocity, and unsprung mass velocity responses, respectively, compared to the VEGA-optimized model.

The presence of toxic gas emissions from conventional vehicles is worrisome globally. Over the past few years, there has been a broad adoption of electric vehicles (EVs) to reduce energy usage and mitigate environmental emissions. The EVs are characterized by limited range, cost, and short range. This prompts the need for hybrid electric vehicles (HEVs). This study describes the conversion of a 2022 Volkswagen Crafter (VW) 35 TDI 340 delivery van from a conventional diesel powertrain into a hybrid electric vehicle (HEV) augmented with synchronous electrical machines (motor and generator) and a BMW i3 60 Ah battery pack. A downsized 1.5 L diesel engine and an electric motor–generator unit are integrated via a planetary power split device supported by a high-voltage lithium-ion battery. A MATLAB (R2024b) Simulink model of the hybrid system is developed, and its speed tracking PID controller is optimized using genetic algorithm (GA) and particle swarm optimization (PSO) methods. The simulation results show significant efficiency gains: for example, average fuel consumption falls from 9.952 to 7.014 L/100 km (a 29.5% saving) and CO₂ emissions drop from 260.8 to 186.0 g/km (a 74.8 g reduction), while the vehicle range on a 75 L tank grows by ~40.7% (from 785.7 to 1105.5 km). The optimized series–parallel powertrain design significantly improves urban driving economy and reduces emissions without compromising performance.

This study evaluates deep learning models for vehicle detection in urban environments, focusing on the integration of regional data and standardized evaluation protocols. A central contribution is the creation of DebStreet, a novel dataset that captures images from a specific urban setting under varying weather conditions, providing regionally representative information for model development and evaluation. Using DebStreet, four state-of-the-art architectures were assessed: Faster R-CNN, YOLOv8, DETR, and Side-Aware Boundary Localization (SABL). Notably, SABL and YOLOv8 demonstrated superior precision and robustness across diverse scenarios, while DETR showed significant improvements with extended training and increased data volume. Faster R-CNN also proved competitive when carefully optimized. These findings underscore how the combination of regionally representative datasets with consistent evaluation methodologies enables the development of more effective, adaptable, and context-aware vehicle detection systems, contributing valuable insights for advancing intelligent urban mobility solutions.

This study, aimed at professionals in research and development in the fields of computer vision, artificial intelligence, and intelligent transportation, presents a systematic literature review on recent machine learning methodologies applied to the detection and tracking of vehicles, pedestrians, and traffic flow. The analysis of articles published between 2022 and 2025 (early access) in the post-COVID era explored the integration of machine learning and deep learning to address traffic challenges, allowing for the comparison of different approaches and the formulation of hypotheses based on the 46 articles that comprised the review corpus. Furthermore, the evaluation of the reported metrics revealed inconsistencies in the methodologies employed, attributed to the lack of standardization across the studies. In light of this, this work proposes alternatives for future experiments, emphasizing the emerging potential of the field through the adoption of new standardization systems and the exploration of experimental combinations.

Modeling of various phenomena in engineering work is always a kind of simplification of real processes, aiming at a model where a certain level of mathematical theory and computational procedures is sufficient. If the complexity of the required theory corresponds to the general mathematical competence of engineers, then technical problems can be treated separately in engineering (or physical) models without regard to the mathematical background. However, in some advanced engineering fields, the harmonized development of engineering and mathematical models and toolboxes is necessary to find efficient solutions. For example, modeling variable structure systems in ideal sliding mode requires a mathematical toolbox that goes far beyond general engineering competence through the theory of discontinuous right-hand-side differential equations. Although sliding mode control is popular in practice and the concept of sliding mode allows a significant reduction of model complexity, its exact mathematical description is rarely encountered. The problem of friction compensation of a micro-telemanipulator using sliding mode control demonstrates a harmonized application of the mathematical and engineering approaches. Based on Filippov’s theory, the ideal sliding mode can be discussed. Although an ideal system cannot be implemented in reality, the real systems can be kept close enough to it; therefore, the discussion of the solution of the ideal model is important for practical applications. Although several elements of the topic are available in the literature, in this paper a unique complex approach is given for users of sliding mode control with experimental considerations, different engineering models, and codes. The paper concludes that sliding mode control is a case where engineering and mathematical modeling are inseparable and requires the competence of both fields.

This article studies the transformation and assembly process of the Volkswagen (VW) Crafter from conventional to hybrid vehicle of the department of vehicles engineering, University of Debrecen, and uses a computer-aided simulation (CAS) to design the vehicle based on the real measurement data (hardware-in-the-loop, HIL method) obtained from an online CAN bus data measurement platform using MATLAB/Simulink/Simscape and LabVIEW software. The conventional vehicle powered by a 6-speed manual transmission and a 4-stroke, 2.0 Turbocharged Direct Injection Common Rail (TDI CR) Diesel engine and the transformed hybrid electrified powertrain are designed to compare performance. A novel methodology is introduced using Netcan plus 110 devices for the CAN bus analysis of the vehicle’s hybrid version. The acquired raw CAN data is analyzed using LabVIEW and decoded with the help of the database (DBC) file into physical values. A classical proportional integral derivative (PID) controller is utilized in the hybrid powertrain system to manage the vehicle consumption and CO₂ emissions. However, the intricate nonlinearities and other external environments could make its performance unsatisfactory. This study develops the energy management strategies (EMSs) on the basis of enhanced proportional integral derivative-based genetic algorithm (GA-PID), and compares with proportional integral-based particle swarm optimization (PSO-PI) and fractional order proportional integral derivative (FOPID) controllers, regulating the vehicle speed, allocating optimal torque and speed to the motor and engine and reducing the fuel and energy consumption and the CO₂ emissions. The integral time absolute error (ITAE) is proposed as a fitness function for the optimization. The GA-PID demonstrates superior performance, achieving energy efficiency of 90%, extending the battery pack range from 128.75 km to 185.3281 km and reducing the emissions to 74.79 gCO₂/km. It outperforms the PSO-PI and FOPID strategies by consuming less battery and motor energy and achieving higher system efficiency.

Hybrid electric vehicles (HEVs) have emerged as a trendy technology for reducing over-dependence on fossil fuels and a global concern of gas emissions across transportation networks. This research aims to design the hybridized drivetrain of a Volkswagen (VW) Jetta MK5 vehicle on the basis of its mathematical background description and a computer-aided simulation (MATLAB/Simulink/Simscape, MATLAB R2023b). The conventional car operates through a five-speed manual gearbox, and a 2.0 TDI internal combustion engine (ICE) is first assessed. A comparative study evaluates the optimal fuel economy between the conventional and the hybrid versions based on a proportional-integral-derivative (PID) controller, whose optimal set-point is predicted and computed by a genetic algorithm (GA). For realistic hybridization, this research integrated a Parker electric motor and the diesel engine of a VW Crafter hybrid vehicle from the faculty of engineering to reduce fuel consumption and optimize the system performance of the proposed car. Moreover, a VCDS measurement unit is developed to collect vehicle data based on real-world driving scenarios. The simulation results are compared with experimental data to validate the model’s accuracy. The simulation results prove the effectiveness of the proposed energy management strategy (EMS), with an approximately 89.46% reduction in fuel consumption for the hybrid powertrain compared to the gas-powered traditional vehicle, and 90.05% energy efficiency is achieved.

The main contribution of this article is creating synergy between subjects; this means that students use the same graphical tool in several subjects. So far, the bond graph has not been used in control theory, but it is the “native language” of mechatronics engineers, so we would like to introduce it into the teaching of control theory. The bond graph method is proposed as a novel teaching method to teach mechatronics subjects in the paper. The bond graph is a graphical alternative to ordinary differential equations from a mathematical standpoint. Traditionally, control theory employs ordinary differential equations, as they are familiar to control theorists. However, mathematically, both approaches are equivalent but require a slightly different approach in their application. This article highlights the mathematical similarities between the two approaches while emphasizing the distinctions in graphical representation. Another contribution is that the PID and sliding mode controller are represented using the bond graph method. In the meantime, through the use of practical examples, we effectively illustrate how the same problem can be solved using either approach. In the training materials, the PID controller and an adaptive robust sliding mode controller (ARSMC) with the bond graph are utilized as examples to demonstrate synergy in mechatronics. Finally, we present proof that mechatronic engineers achieve superior outcomes when utilizing the bond graph approach, based on test results from undergraduate students.