Abstract: Transmission error (TE) is one of the most important sources of gear noise and vibration. Manufacturing tolerances and assembly shifts introduce deviations in tooth geometry that produce periodic mesh disturbances; these disturbances excite the drivetrain and radiate as airborne sound. While many studies have modelled individual tolerance effects in deterministic simulations, few have evaluated the combined influence of realistic tolerance distributions using open Monte–Carlo data. This work analyses the public Gear Statistical tolerance analysis dataset (≈40 k samples) to answer the following questions: (Q1) How accurately can the kinematic transmission error be predicted from measured tolerance and process‑shift data? (Q2) Which individual tolerances and their interactions have the greatest impact on TE? (Q3) Can a TE‑derived proxy quantify noise‑critical excitation without an acoustic model? (Q4) What tolerance combinations minimise TE and noise while respecting manufacturing cost? (Q5) Is there a quantifiable trade‑off between tolerance tightening cost and noise reduction? To address these questions we formulate hypotheses: H1 Non‑linear machine‑learning models achieve high predictive accuracy for TE (R² > 0.85) compared with linear baselines. H2 A small subset of tolerances—profile and lead errors—dominate the TE variance and interact non‑linearly. H3 A relative noise proxy (RNP) derived from TE faithfully ranks noise‑critical excitation across tolerance combinations. H4 A Pareto front exists in the cost–noise plane, enabling cost‑effective tolerance optimisation. H5 Targeted adjustment of the top two tolerances yields larger noise‑reduction per cost than uniform tightening. The following sections describe the data, the modelling framework and the results that support these hypotheses.

Abstract: Improving the ride comfort of commercial vehicles is crucial for driver health and operational safety.This study focuses on optimizing the parameters of a cab suspension system to improve its vibration isolation performance. Initially, nonlinear fitting was applied to experimental data characterizing air spring stiffness and damping, which informed the development of a multi-body rigid-flexible coupled dynamic model of the suspension system; its dynamic characteristics were subsequently validated through modal analysis. Road excitation data, filtered through the chassis suspension, were collected during vehicle testing, and displacement excitations for ride comfort simulation were reconstructed using virtual iteration technology. Thereafter, an integrated ISIGHT platform, combining ADAMS and MATLAB, was employed to systematically optimize suspension parameters and key bushing stiffness via a multi-island genetic algorithm. The optimization results demonstrated significant performance improvements: on General roads, the overall weighted root-mean-square acceleration was markedly reduced with enhanced isolation efficiency; on Belgian pave roads, resonance in the cab's X-axis direction was effectively suppressed; and on Cobblestone roads, the pitch angle was successfully constrained within the design limit. This research provides an effective parameter matching methodology for performance optimization of cab suspension systems.

Abstract: Radiated noise from gearbox housings is a significant contributor to the noise, vibration, and harshness (NVH) performance of automotive drivetrains. Small deviations in wall thickness caused by standard manufacturing tolerances can influence structural stiffness, shift modal frequencies, and alter acoustic radiation levels, particularly near resonance. This study numerically examines the effect of ±10% wall thickness variation using a simplified multi-mode structural–acoustic model. Modal frequencies were scaled proportionally to thickness changes, and frequency response functions were calculated for nominal and tolerance-limit geometries. Statistical variability was assessed through Monte Carlo simulations with wall thickness values sampled from a truncated normal distribution within the tolerance range. Results show that a ±10% variation can produce modal frequency shifts accompanied by resonance amplitude differences of up to 20.9 dB in the 950–1050 Hz range, with an average change of 3.34 dB between extreme cases. Monte Carlo analysis indicated mean changes of 0.54 dB in the main resonance band, with some cases reaching 2.54 dB. The findings demonstrate that even within standard production limits, wall thickness tolerances can measurably affect gearbox NVH behavior. Considering such variability in early-stage design can help reduce unit-to-unit noise differences and improve acoustic robustness.

Abstract: Accurate detection and localization of traffic objects are essential for autonomous driving tasks such as path planning. While semantic segmentation is able to provide pixel-level classification, existing networks often fail under challenging conditions like nighttime or rain. In this paper, we introduce a new training framework that combines unsupervised domain adaptation with high dynamic range imaging. The proposed network uses labeled daytime images along with unlabeled nighttime HDR images. By utilizing the fine details typically lost in conventional SDR images due to dynamic range compression, and incorporating the UDA training strategy, the framework effectively trains a model which is capable of semantic segmentation across the adverse weather conditions. Experiments conducted on four datasets have demonstrated substantial improvements in inference performance under nighttime and rainy scenarios. The accuracy for daytime images is also enhanced through expanded training diversity. Source code is available at https://github.com/ZackChen1140/RMSeg-HDR.

Abstract: Income tax fraud is a serious challenge to revenue authorities, which involves large amounts of money losses and erodes public trust. The conventional methods of detection through manual audits and rule-based systems tend to be slow and ineffective for large volumes of data. This study suggests an AI - and ML-based framework for the detection of tax fraud through fraudulent returns by using both supervised and unsupervised learning algorithms. Major models adopted are Random Forest, XG-Boost, and Isolation Forest, selected based on their performance in classification and outlier detection. Feature engineering is directed toward significant features like income patterns, deductions, exemptions, and past filing behavior to detect abnormal patterns that signify fraud. Experimental outcomes reveal that Random Forest performed best with an accuracy of 96%, followed by XG-Boost with an accuracy of 95%, and Isolation Forest with an accuracy of 80%, showing the best performance of tree-based ensemble models for the task. The system provides a risk score for every tax return, allowing authorities to rank audits and reduce false positives. These results show that machine learning models far surpass conventional methods, delivering a scalable and automated solution for effective fraud detection. The research provides a realistic basis for incorporating AI-based strategies in financial fraud management, leading to increased compliance, minimized revenue leakage, and better decision-making by tax authorities.

Abstract: Lightweight gearbox housings often raise NVH risk, yet full finite-element evaluations are too slow for early design screening. This study tests whether a few frequency-band descriptors of radiated sound are enough to classify housing stiffness. Using an open dataset of electric-vehicle gearbox spectra for three rib-configurations—flexible, intermediate and rigid—we averaged sound-pressure levels in five 1 kHz bands. Principal-component analysis separated the twelve samples into three non-overlapping groups, confirmed by k-means clustering (adjusted Rand index = 1.00). The random-forest model achieved 75 % classification accuracy on the present 12-sample data set (leave-one-out evaluation). Owing to the small sample size this figure should be regarded as explorative, and a larger validation study is required to confirm generalizability; permutation analysis confirmed the 3–4 kHz and 2–3 kHz bands as most important for classification. In contrast, total integrated spectral energy showed no significant group difference (p = 0.81). The results These findings suggest that mid-frequency band energy may encode structural-stiffness differences, although validation on larger datasets is necessary. The workflow—load spectra, compute five band means, classify—offers a rapid, interpretable tool for NVH-aware lightweight design.

Abstract: With air resistance being one of the two major energy losses in on-road vehicles (the other one being tire losses) and therefore heavily contributing to the range of battery-electric and fuel cell-electric vehicles, it is necessary to account for realistic air resistance in a-priori assessments like vehicle range esti-mations, component dimensioning, and system simulations. However, lack of input data tempts analysts to instead assume unrealistic “nom-inal conditions” throughout – a simplification which usually underestimates the amount of energy actually required to overcome air resistance and completely ignores the fact that varying environmental conditions will lead to significant variances in energy consumption and therefore vehicle range. Using “nominal conditions” it is thus impossible to assess the robustness of these measures and therefore difficult to design robust systems and to perform meaningful trade-off studies. In this study we show how publicly available data from weather observations can be used to assess the long-term variation of air resistance of a truck with semitrailer. Realistic distributions of energy losses due to air resistance, covering multiple years are derived – showing not only average values but the complete envelope in which the energy losses vary. This, in turn, enables to follow up with probabilistic calculations of vehicle per-formance in order to assess robustness and trade-offs on various system levels of interest. As a consequence consumption and range predictions of EVs and ICE vehicles can be performed with higher accuracy and confidence.

Abstract:

The operating conditions of engines in motor vehicles used in conditions of high air dustiness resulting from sandy ground and in helicopters using temporary landing sites were analyzed. The impact of mineral dust on accelerated abrasive and erosive wear of components and assemblies of piston and turbine engines was presented. Attention was drawn to the formation of dust deposits on turbine engine components. The possibilities of minimizing abrasive wear by using two-stage intake air filtration systems in motor vehicle engines were presented. The filtration properties of cyclones used as the first stage of air filtration were discussed. Three forms of protection for helicopter engines against the intake of contaminated air and to extend their service life were presented: intake barrier filters (IBF), tube separators (VTS), and particulate separators (IPS) called Engine Air Particle Separation (EAPS). It has been shown that pleating the filter bed significantly increases the filtration area without increasing the frontal area, whereby optimization of the filter bed geometry is of great importance here. An important advantage of the VTS air filtration system was demonstrated in the form of no maintenance due to the use of a system for the continuous removal of separated dust, whereby increasing the suction flow increases separation efficiency and pressure drop and energy losses. IPS is an air filtration system integrated with a turbine engine, characterized by a compact design, low external resistance, and no periodic maintenance, but with lower separation efficiency than VTS and IBF systems. The primary goal of such systems is to separate as many solid particles as possible at the lowest possible energy cost. The results of experimental research conducted by the author are presented, the aim of which was to demonstrate the advantages of a filtration unit consisting of cyclones and a porous partition in terms of increased filtration efficiency and filter operating time. During the research, an innovative method was used to determine the characteristics of a barrier filter operating in a two-stage filtration system, which reduces testing time and energy losses. It was a single VTS axial flow cyclone with a test barrier filter arranged in series behind it, whose filter bed was pleated paper with a suitably selected surface area. The results confirmed the advisability of using two-stage filtration systems to purify the intake air for internal combustion engines of motor vehicles and helicopter turbine engines. Since a porous partition increases pressure drop during operation, it is advisable to use permissible resistance sensors to limit their use due to increasing engine energy losses.

Abstract: This study presents the design, real-time implementation, and full-scale experimental validation of a novel rule-based Energy Management Strategy (EMS) for a dual-stack Fuel Cell Hybrid Electric Vehicle (FCHEV) developed on a Jeep Wrangler platform. Unlike previous studies limited to simulations or single-stack configurations, this work experimentally demonstrates, for the first time, a deterministic real-time EMS for a dual fuel cell system in an SUV class vehicle. The control algorithm, deployed on a National Instruments CompactRIO embedded controller, ensures real-time energy distribution and stable hybrid operation under dynamic load conditions. Simulation analysis performed over eight consecutive WLTC cycles confirmed that both fuel cell stacks operated within their optimal efficiency range (25–35 kW), achieving an average DC efficiency of 68% and a hydrogen consumption of 1.35 kg/100 km. Experimental validation on the Wrangler FCHEV demonstrator yielded an equivalent hydrogen consumption of 1.67 kg/100 km, corresponding to 1.03 kg/100 km·m² after aerodynamic normalization (Cd·A = 1.624 m²), comparable to commercial fuel cell vehicles. The results demonstrate that the proposed EMS maintains over 80% of operating time within high-efficiency zones, reducing fuel cell cycling and enhancing durability. This work bridges the gap between theoretical EMS design and real-world embedded validation, establishing a scalable benchmark for future hydrogen powertrain control systems.

Abstract: Auxiliary systems (HVAC, thermal management) significantly impact the range of electric vehicles under varying weather conditions. This study developed an XGBoost machine learning framework to predict auxiliary power using 95,028 real-world measurements of electric vehicles in Poland, Italy, and Germany (−8°C to +33.5°C). A physics-based energy decomposition combined with feature engineering achieved R² = 0.9986 with a mean ab-solute error of 35 W. The feature importance analysis revealed the position of the accelera-tor pedal (0.4153) as the strongest predictor, alongside the heating efficiency per tempera-ture differential (0.2716), indicating the coupling between traction demand and auxiliary loads. Heating dominated cooling by a 7:1 ratio with a 44-fold power variation in the temperature range. The contribution of the additional power ranged from 75% during idle to 12% during highway driving, contradicting static overhead assumptions. Results demonstrate that auxiliary loads require context-aware prediction rather than fixed as-sumptions, enabling improved range forecasting for electric vehicles.

Abstract: This work provides an updated report on the progress and prospects of quantum computing for advancing transport modeling. Despite recent developments in classical methods, their use in computationally intensive transport tasks such as traffic assignment, traffic signal control, logistics, and pedestrian modeling remains limited due to the combinatorial complexity and uncertainty associated with the real-world transport scenarios. Quantum optimization algorithms offer the potential for addressing transport problems, although most studies still remain at the proof-of-concept stage. In this work, we highlight key challenges in traffic and logistics optimization and investigate how quantum optimization tools could lead to novel and efficient solutions. Our perspective offers a clear and concise timeline for the development of quantum optimization techniques and their practical implementation aspects by highlighting key hardware/software challenges and proposed solutions. We also discuss the barriers to adoption within transport contexts and possible pathways to overcome current limitations to the application of quantum optimization techniques in real-world transport systems. Finally, we provide our perspective for the applications of quantum computing in addressing challenges pertaining to large crowd management and transport optimization during the Olympics and Paralympics 2032 Games which may coincide with the development of a large-scale quantum computer.

Abstract: A non-pneumatic tyre (hereby referred to as “NPT”) is a tyre that is not supported by any internal air pressure. Hence, they tend to be more reliable than a conventional tyre supported by compressed air. They have a wide range of advantages mainly due to their run-flat properties and low rolling resistance. While pneumatic tyres are still preferred, it has displayed some disadvantages such as the necessity to maintain interior air pressure and the possibility to burst while driving. Recently, non-pneumatic tyres have been developed in the hope that they may replace conventional tyres one day. However, most of the research conducted is mainly based on spokes with a uniform degree. In this paper, we discuss the behaviour of a non-pneumatic tyre with a varying degree of honeycombed structured spokes. The density of spokes will decrease when approaching the surface of the tyre which is on contact with the road, and increases when approaching the centre hub of the wheel. The new design was modelled on Autodesk Inventor and analysed on Ansys Workbench to obtain results similar to what we expected. By altering the distance and shape between the spokes, it has displayed significant improvement over existing NPT’s showing less stress and deformation in the wheel.

Abstract: Urban air pollution and emission reduction commitments have stimulated interest in cleaner vehicle technologies in Latin America, yet hybrid vehicle penetration in Ecuador, particularly in Guayaquil, remains limited. This study analyzes technical and commercial determinants of purchase intention using a mixed methods design that combines a survey of 384 consumers with interviews of 20 dealership representatives. Spearman correlations indicate that technical attributes show stronger associations with purchase intention than commercial variables: technology and performance (ρ = 0.65, p < 0.001) and maintenance (ρ = 0.61, p < 0.001) are the most influential, followed by environmental influence (ρ = 0.53, p < 0.001); public policies (ρ = 0.48, p < 0.001) and purchase price (ρ = 0.45, p < 0.001) display moderate effects. Overall, 51.5% of respondents report a favorable intention to purchase a hybrid vehicle in the short to medium term. Interviews confirm an information gap on tax incentives at the point of sale and underscore the potential of financing schemes to mitigate upfront cost barriers. Findings suggest that, in this market, narratives emphasizing long term operating savings and reliability outperform purely environmental appeals. We discuss implications for dealership communication, targeted credit programs, and public awareness campaigns to accelerate sustainable mobility transitions in urban Ecuador.

Abstract: Modern automotive design has increasingly embraced plastics for bumper construction, however it can lead to material degradation. To overcome these limitations, the automotive industry is turning to fiber‑resin material, namely carbon-epoxy composites. Our research focuses on knowing layer thickness and orientation angles effect into structural stress of car bumper, examining the combinations of material into the impact strength, and performing impact tests in various speeds. To build research gaps, machine learning (ML) has an important position to predict the certain value of parameters and measure data normality through various algorithms. By combining ML and FEA simulations, the result shows strong data performance. Bridging from 3 mm mesh sizing of 100% carbon-epoxy woven laminate in 6 mm thickness at 0° orientation shows the most distributed von Mises stresses which converged toward stable values. The elevated impact velocities improve stress magnitudes at 10.247 MPa, 16.857 MPa, and 23.438 MPa in 11.11 m/s, 15.61 m/s, and 22.22 m/s, respectively. For comprehensive research, total deformation was included in ML analysis as second targets to build multivariate analysis. Overall, Random Forest (RF) shows as the best model which indicates MSE (0.18) and R² (0.79), indicating superior robustness when modeling equivalent stress and total deformation.

Abstract: Engine oil is fundamental to the performance and longevity of internal combustion engines, fulfilling critical roles in lubrication, heat dissipation, corrosion prevention, and contaminant suspension. However, water contamination poses a significant and often underestimated threat, ranking among the most destructive pollutants affecting oil stability. This research examines the sources, states, and multifaceted impacts of water ingress on engine oil properties, chemical composition, and overall engine health. Beyond reviewing known mechanisms of degradation, the study introduces a novel experimental approach by investigating the influence of water contamination on the viscosity of used engine oil, a less frequently addressed aspect in the literature. By analyzing real data obtained from practical testing, the work provides new insight into how residual operational by-products interact with water to alter oil behavior, aiming to spark interest in advancing diagnostic methods and preventive practices.

Abstract: The implementation of Euro 7 emission standards demands advanced real-time NOₓ monitoring systems for diesel vehicles. This study develops a novel Mixture of Experts (MoE) architecture to predict NOₓ emissions under varying thermal and kinematic conditions. Data from a Euro 6d commercial vehicle equipped with PEMS yielded 3,247 samples during real-world driving campaigns. Engine operations were classified into three phases: cold (&lt;70°C coolant temperature), hot low-speed (&lt;90 km/h), and hot high-speed (≥90 km/h), based on aftertreatment system thermal dynamics. The MoE framework dynamically routes predictions to optimized XGBoost specialized regressors for each operational phase, achieving high performance precision (R² = 0.918, RMSE = 1.825 mg/s) with 58% RMSE reduction compared to unified models. Phase separability analysis using t-SNE confirmed distinct emission mechanisms (silhouette coefficient = 0.73). Integration with autoencoder-based anomaly detection achieved 95.2% sensitivity, while Model Predictive Control implementation demonstrated 11-13% NOₓ reduction across driving scenarios. The framework operates within real-time constraints (&lt;1.5 ms inference latency) suitable for embedded automotive applications and Euro 7 compliance through intelligent, context-aware emission prediction.

Abstract: This study explicitly considers dynamic axle load transfer and load-sensitive tire–road friction characteristics in estimating the safe speed of multi-axle trucks negotiating curved road segments. Conventional standards, which assume a constant friction coefficient, fail to capture wheel-specific load variations and tend to underestimate rollover and skidding risks. To overcome these limitations, a load-sensitive friction model is integrated with the friction ellipse and the static rollover threshold (SRT), and a forward–backward pass is applied to compute dynamically feasible speed trajectories. The framework was demonstrated through accident reconstruction of a curved ramp rollover scenario using TruckSim–Simulink co-simulation based on reported geometric and vehicle parameters. The results show that ignoring load sensitivity systematically overestimates safe speeds and underestimates lateral deviations. Moreover, variations in the SRT level demonstrated the trade-off between structural stability and frictional constraints, with rollover dominating at lower stability and skidding at higher stability. These findings highlight the necessity of incorporating dynamic load distribution and load-sensitive friction into truck safety speed estimation. The proposed framework provides a foundation for speed control strategies in autonomous trucks and for improvements in road design standards, with potential for enhanced applicability when combined with emerging real-time friction estimation and load measurement technologies.

Abstract: Injection strategies play a crucial role in determining hydrogen engine performance. The diversity of these strategies and the limited number of comparative studies highlight the need for further investigation. This study focuses on the analysis, parameter selection, and comparison of single early and late direct injection, single injection with ignition occurring during injection (the so-called jet-guided operation), and dual injection in a hydrogen spark-ignition engine. The applicability and effectiveness of these injection strategies are assessed using contour maps, with ignition timing and start of injection as coordinates representing equal levels of key engine parameters. Based on this approach, injection and ignition settings are selected for a range of engine operating modes. Simulations of engine performance under different load conditions are carried out using the selected parameters for each strategy. The results indicate that the highest indicated thermal efficiencies are achieved with single late injection, while the lowest occur with dual injection. At the same time, both dual injection and jet-guided operation provide advantages in terms of knock suppression, peak pressure reduction, and reduced nitrogen oxide emissions.

Abstract: Lithium-ion batteries play a key role in electric vehicles, so it is essential to continuously monitor and control their health. However, since today's battery packs are composed of hundreds or thousands of cells, monitoring them all continuously is challenging. Additionally, the performance of the entire battery pack is often limited by the weakest cell. Therefore, developing effective monitoring techniques to reliably forecast the remaining time to depletion (RTD) of lithium-ion battery cells is essential for safe and efficient battery management. However, even in robust systems, this data can be lost due to electromagnetic interference, microcontroller malfunction, failed contacts, and other issues. Gaps in voltage measurements compromise the accuracy of data-driven forecasts. This work systematically evaluates how different voltage reconstruction methods affect the performance of recurrent neural network (RNN) forecasters that are trained to predict RTD through quantile regression. The paper uses experimental battery pack data based on the behavior of an electric vehicle under dynamic driving conditions. Artificial gaps of 500 seconds were introduced at the beginning, middle, and end of each discharge phase, resulting in over 4300 reconstruction cases. Four reconstruction strategies were considered: a zero-order hold (ZOH), an autoregressive integrated moving average (ARIMA) model, a gated recurrent unit (GRU) model, and a hybrid unscented Kalman filter (UKF) model. The reconstructed signals were fed into LSTM and GRU RNNs to estimate RTD, which produced confidence intervals and median values for decision-making purposes.

Abstract: This study explores the factors driving electric vehicle (EV) adoption in Lagos and Abuja using the Unified Theory of Acceptance and Technology (UTAUT) framework. Employing quantitative research method with 200 participants through surveys questionnaire items, and policy analysis, the study identified key predictors of EV purchase intentions. Technological innovation emerged as the strongest predictor (β = 0.42, p < 0.001), followed by regulatory environments (β = 0.37, p < 0.001). Economic factors, including total ownership costs and government subsidies, explained 32.6% of adoption variance. Consumer Priorities towards EV adoption revealed technological reliability (67.4%), environmental impact (52.3%) and long-term economic benefits (41.6%). The combination of technological readiness, charging infrastructure, and policy support accounted for 48.3% of variance in adoption rates across market segments. The research reveals that EV adoption in emerging markets requires integrated approaches addressing technological innovation, economic incentives, and regulatory frameworks simultaneously. Results demonstrate significant socio-economic variations, emphasizing that successful EV transition depends on creating comprehensive ecosystems rather than isolated interventions. The study provides valuable insights for policymakers, manufacturers, and innovators developing sustainable mobility solutions in emerging African markets, highlighting the complex interplay between technology, economics, regulation, and environmental consciousness in driving consumer behavior.