Hyundai Research Institute

In retail lending, offering preferential interest rates is a core marketing instrument for balancing customer acquisition with portfolio profitability. Accurately predicting the effect of interest-rate discounts for each customer is pivotal for optimizing the discount strategy: offering overly generous discounts erodes margins, while insufficient discounts drive price-sensitive customers to defect. Off‑the‑shelf machine learning uplift models rarely respect the complex operational constraints of financial business, such as tiered rate grids, regulatory guard‑rails, and marketing budget ceilings. We propose an integrated system that fuses causal inference and domain adaptation to produce constraint‑aware, customer‑specific discount recommendations. To further enhance practitioner adoption, a large language model layer translates model outputs into actionable narratives. Developed in Hyundai Capital Services, the system boosted transaction volume by 13%, demonstrating both technical soundness and material business impact.

As the global transportation sector accelerates toward net-zero targets, the rapid deployment of alternative fuels like hydrogen, ammonia, and batteries introduces complex and novel safety challenges. This study systematically maps the intellectual structure of safety and risk research on zero-emission transportation systems to evaluate field maturity and identify critical knowledge gaps. We conducted a comprehensive bibliometric analysis of 151 core publications retrieved from the Web of Science from 2000 to 2025. By integrating quantitative performance analysis with qualitative science mapping techniques, the results identify that the domain is nascent and rapidly expanding, and a distinct inflection in publication occurred in 2020. However, science mapping reveals a fragmented intellectual structure. Among the four identified research clusters, two dominant streams emerge as the primary drivers of the field. The first is a “motor theme” focused on lithium-ion battery reliability and thermal runaway, while the second is a “basic theme” focused on hydrogen dispersion and toxicity risks. The analysis exposes a blind spot regarding the lack of cross-modal research addressing the physical safety interactions between different fuel systems operating in the shared infrastructure. Finally, this study proposes a future research agenda focusing on gathering real-world accident data and using system-theoretic approaches to manage integrated alternative fuel risks.

This paper proposes a sensorless phase synchronization method for single-phase grid-connected inverters that avoids the requirement for a voltage sensor. The method models the actual grid impedance as a virtual impedance and represents the grid voltage in the corresponding synchronous reference frame. To construct the synchronous voltage, a 90-degree phaseshifted virtual voltage is then generated, which is used to estimate the grid phase and frequency. The estimated voltage subsequently undergoes processing through a low-pass filter (LPF) and a disturbance observer to extract the final phase and frequency components. The proposed method features low computational complexity and is amenable to real-time implementation on low-cost microcontrollers. It also exhibits robustness against grid-impedance mismatch and harmonic distortion, maintaining stable phase and frequency estimation. The effectiveness of the proposed approach was demonstrated through both simulation and experimental results.

This paper presents the design optimization of a permanent magnet shaft generator (PMSG) to improve the overall shaft generator system efficiency for large vessels. The study focuses on selecting appropriate system constraints and determining the optimal design parameters of the PMSG, with consideration for both cost-effectiveness and operational system-level efficiency. To validate the proposed design, a prototype was manufactured and tested with a variable frequency drive under realistic operating conditions. The results indicate that the optimized shaft generator system achieves up to a 0.79% increase in total system efficiency compared to a conventional configuration, demonstrating the potential advantages of applying advanced electrical machine optimization to marine propulsion systems.

A 73-year-old male patient was referred to our hospital for evaluation of a suspected mediastinal tumor observed on chest radiograph.The electrocardiogram showed sinus rhythm with an incomplete right bundle branch block.Chest radiograph revealed mild rightward deviation of the heart, mimicking a mediastinal mass in the right side of the thorax.Transthoracic echocardiography demonstrated a prominent outpouching involving the basal portion of the right ventricle (RV) and a substantial portion of the right atrium (RA).Cardiac computed tomography and cardiac magnetic resonance revealed a partial pericardial defect involving the RA and the base of the RV, with associated herniation of the right heart structures through the defect.Given the absence of symptoms, prophylactic surgical intervention was not recommended.This case highlights the critical role of multimodality imaging in accurately differentiating a suspected mediastinal tumor from right-sided partial absence of the pericardium.

We here show the characterization techniques we have developed to study the chemical degradation of proton-exchange membrane fuel cells with a focus on perfluoro sulfonic acid (PFSA) ionomer (e.g., Nafion) degradation in the catalyst layers. The study of catalyst layer ionomer degradation is particularly challenging because of the low amount of PFSA mass in the electrode and its adsorption to complex catalyst particles. Furthermore, effluent water and MEA analysis are often overwhelmed by the signal coming from the PFSA membrane. An additional challenge is the lack of specific accelerated stress tests for the ionomer in the electrode. Here we present methods of targeting the electrode ionomer in accelerated stress tests (ASTs) and separating out the electrode ionomer in chemical analyses. Quantitative nuclear magnetic resonance (qNMR) and fluoride ion selective electrode (ISE) measurements, among other techniques, were selected to study those degradations. We will discuss the spin relaxation of fluorine atoms in the ionomer, accurate post-processing of 19F NMR data, the calculation of the equivalent weight (EW), and other important considerations for accurate qNMR and ISE measurements.

The increasing adoption of high-strength steel in automotive manufacturing has made laser welding a preferred technique due to its ability to reduce thermal deformation and facilitate single-sided welding. Despite these advantages, challenges persist, particularly in achieving precise welds at the edges of seat frame assemblies. This study explores the application of laser weaving techniques to improve joint strength and penetration depth. The critical variables evaluated include defocusing distance and weaving parameters, which were assessed for their impact on penetration depth, effective joint width, and edge weld quality in a three-sheet stack of dual-phase (DP) steel. Results indicate that increasing the defocusing distance from 5 mm to 20 mm at a fixed oscillation frequency of 20 Hz leads to a corresponding increase in surface bead width. A significant correlation was found between the effective joint width and maximum tensile shear strength, with the highest strength of 34.6 kN observed at an 8 mm defocusing distance. Additionally, the use of oscillation in the welding process improved tensile shear strength by approximately 9 kN compared to line welding without oscillation. Oscillation also enhanced microstructural properties, demonstrating that optimal welding conditions can be achieved even with off-position welding. These improvements are attributed to minimized heat-affected zone (HAZ) effects, which contributed to increased joint strength and hardness.

<div class="section abstract"><div class="htmlview paragraph">The recent technological development trend in the automobile market is in the huge flow of MECA (Mobility, Electrification, Connectivity, Autonomous). The role of the seat is to provide convenience functions in addition to providing safe and comfortable performance. The development of autonomous driving technology reduces fatigue during long-term driving, but on the contrary, the risk of drowsy driving due to overconfidence in the autonomous driving system is increasing. In this study, the massage function was developed by utilizing the existing pneumatic system, and the contents of research on objectification through medical verification of the effect of preventing drowsy driving and recovering from fatigue due to long-term driving are described.</div></div>

The flow behaviors of metallic materials are sensitive to state variables, including strain, strain rate, and temperature. In particular, the temperature effect on the flow behavior is of great importance. The flow information is usually obtained at the sample strain rates and temperatures from the hot cylinder compression test. However, this test is inevitably exposed to undesirable effects of friction and temperature on flow characterization. This study reveals their impact on the flow curve of an A6082 alloy. The unique features of its flow behavior and the inaccuracy of as-received, primitive flow information are emphasized. Using a systematic way of correcting the friction and temperature effects, the flow curves with high accuracy in terms of the compression load–stroke curve obtained from the test are calculated. It was revealed that the both the friction and temperature compensation of the primitive flow curves bring a minor change in the flow curves of the A6082 alloy, which is quite different from other commercial light metals. This phenomenon caused by the unique features of the flow behavior of the A6082 or other aluminum alloys will be critical to solving various process and quality matters confronted by the engineers in the hot metal forming industry.

In this article, we propose a new methodology to fuse visual-inertial measurements for land vehicles in a challenging urban environment in which a GNSS signal is not available nor reliable. Motivated by a degenerate case caused by a large bias of a MEMS IMU, we redesign a system model of visual-inertial odometry in a framework of extended Kalman filter. In particular, the system model is propagated through a reduced inertial sensor system composed of a 3-axis gyroscope, a 2-axis accelerometer, and a single-axis odometer. An analytical observability derivation reveals unobservable bases of our estimator, and these directions are resolved by using intermittent position measurements from a GNSS receiver. Furthermore, we inspect the uncertainties of the state vector in a Monte-Carlo simulation that agrees with our theoretical results. The proposed method is validated through the KITTI benchmark dataset and an extensive field testing showing a position drift as 1.25% in tunnels on average and a mean position error of 2.81m in the street canyon over a 6.7km driving.