Real-world Operating Conditions Research Articles

Optimization of the cruising speed for high-speed trains to reduce energy consumed by motion resistances

As one of the effective measures to reduce energy consumption of high-speed railway, train operation control has gained much attention because of its cost-effectiveness. Conventional approaches to eco-driving generally rely on single-mass train models and lack a thorough investigation into the vehicle cruising process, which can overlook real-world operation conditions and hinder further improvements in energy efficiency. To address these issues, this paper proposes a comprehensive framework for optimizing the cruising speed of high-speed trains (HSTs) based on track conditions to reduce energy consumed by motion resistances (ECMR). Firstly, a multibody dynamics simulation model of the HST is developed and validated to accurately evaluate ECMR under a range of operation scenarios. Simulation results show that the impact of speed on ECMR varies considerably according to track characteristics. Subsequently, a neural network is constructed to derive the regressive relationship between operation conditions and ECMR. On this basis, an optimization model for the cruising speed under different track conditions is formulated to minimize the ECMR of a railway segment with a given operation time. Finally, the effectiveness of the model is validated through case studies, which demonstrate that ECMR can be reduced by up to 27.85% compared to traditional control strategies. The proposed optimization method can be integrated with current train speed profiles to further enhance energy efficiency. This framework has broad applicability for addressing engineering problems related to train operation optimization.

LSTA-Net framework: Pioneering intelligent diagnostics for insulating bearings under real-world complex operational conditions and its interpretability

Deep Learning has been attracting considerable attention as it can autonomously learn important signal features and has shown great potential for fault diagnosis. However, given the variability of high-power variable-frequency industrial systems, especially under unfavorable service conditions such as voltage and load fluctuations, the identification of insulated bearing faults in variable-frequency motors has become a key challenge to be addressed. Moreover, the time-varying nature of insulated bearing data poses common technical difficulties for existing models. To bridge these gaps, this research spearheaded the development of a lightweight spatial–temporal focusing framework equipped with a novel optimizer called LSTA-Net, which was designed to address the challenging problem of insulated bearing fault identification in real-world engineering scenarios. Specifically, this involves an innovative design of the Weight Reducing Recursive Unit (WDRU) strategy and an updated backpropagation formulation, which was skillfully applied to the feature extraction module of the LSTA-Net framework for the first time. Furthermore, a novel optimizer called Stochastic Newton Descent (SND) has been developed and skillfully integrated into the LSTA-Net framework with the newly derived weight update formula, providing unique insights to improve diagnostic performance. Finally, the diagnostic performance of the LSTA-Net framework was evaluated from multiple dimensions based on the same dataset, proving its superiority, generalizability, and robustness. t-SNE technique integration intuitively explains the framework’s fault characterization mining process, improving its credibility, reliability, and accuracy.

Investigation of emission characteristics of a marine cargo ship in real-world conditions

Pollution caused by ship emissions will considerably impact coastal areas. A test system that matched the actual conditions of a ship was designed based on a portable emission measurement system (PEMS), and the emission characteristic of gaseous and particle emissions and the particle size distribution of the ship's main engine were investigated under real-world operating conditions. The results showed that the emission concentrations of the main pollutants fluctuated greatly under the departure, anchoring, and docking conditions, and the peaks of CO, CO2, and NOx emissions appeared under these transient conditions. The emission concentrations of CO2, hydrocarbons, particle number (PN), and particulate mass increased with the increase in speed. The PN-based particle size distribution of the engine presented a unimodal distribution under daily operating conditions. The maximum emission factor of NOx based on the engine power was 29.53 g/kWh at the engine speed of 66 r/min. The results of the study may contribute to supplementing the emission factors of this type of ship, and provide data support for monitoring and assessment of the marine environment.

A Simulation Approach for Analysis of the Regenerative Potential of High-Speed Train Suspensions

This study primarily investigates the adaptability and performance of hydraulic–electric regenerative dampers for high-speed trains by substituting conventional primary dampers with hydraulic–electric regenerative dampers. The primary objectives are to develop a detailed model of primary suspension regenerative damper (PSRD) energy conversion that incorporates factors such as oil pressure loss, motor efficiency, and overall system efficiency, and to perform a comprehensive comparative analysis of vibration responses, wheel wear, comfort indices, and power generation using an integrated MATLAB and SIMPACK co-simulation platform. The results reveal that at an operational speed of 350 km/h, the dynamic responses of the carbody, bogie, wheelset, and dampers equipped with the proposed PSRD systems closely align with those of conventional primary vertical damper systems. The detailed PSRDs’ hydraulic–mechanical–electrical model effectively captures the subtleties of oil pressure fluctuations and their impacts. The wear distribution and magnitude across the vehicle remain consistent during acceleration, constant, and deceleration speeds, ensuring uniform wear characteristics. Under real-world railway operational conditions, the ride comfort metrics of vehicles fitted with regenerative dampers are comparable to those with conventional primary vertical dampers. Furthermore, each regenerative damper can generate up to 21.72 W of electrical power, achieving a generation efficiency of 45.28%. Finally, a test rig was designed and fabricated to validate the primary suspension regenerative damper (PSRD) model, showing good agreement between predicted and actual damping force and power regeneration, with results indicating a peak damping force of 12.5 kN and approximately 230 W of regenerated power. This research provides a theoretical foundation and experimental validation for implementing power regeneration mechanisms in railway transportation, demonstrating that the hydraulic–mechanical–electrical PSRD model can fulfil the performance criteria of conventional dampers while offering substantial energy harvesting capabilities. This advancement not only enhances energy efficiency but also contributes to the sustainable development of high-speed rail systems.

Investigation Lubricity Performance of Lubricating Oil Used in Marine Diesel Engine—Fuel Injection Pump

Diesel engines commonly suffer from oil contamination by fuel and other chemicals during operation and maintenance. This contamination alters the oil’s lubricating properties, leading to increased wear, corrosion, and other potential problems. Therefore, it is crucial to understand how oil degrades and becomes contaminated due to different replacement strategies is crucial for both engine operators and manufacturers. This study focuses on the impact of fuel dilution on specific properties of engine oil under real-world operating conditions in a marine diesel engine. Oil samples were collected regularly from the crankcase of the engine fuel injection pump and tribological tests were performed. These tests aimed to assess how marine gas oil affects the oil lubricity performance and how it maintains its useful life. The results confirm that diesel dilution primarily affects the oil lubricating abilities as well as overall performance.

Integrating vehicle trajectory planning and arterial traffic management to facilitate eco-approach and departure deployment

Eco-approach and departure (EAD) enable continuous vehicle motion in urban signalized corridors. Since such a motion can extend to the EAD vehicles’ followers, it makes EAD a promising technology to benefit the traffic flow where automated vehicles and conventional vehicles coexist. Most existing EAD studies envision an ideal setting that neglects real-world operational conditions such as lane changes, multi-movement intersection configuration, partially automated fleet, and/or limited traffic state awareness. This study aims to fill the gap by designing an EAD algorithm considering real-world traffic operation constraints. The proposed algorithm uses a model predictive controller to minimize vehicle speed reduction and variation based on the real-time traffic signal control plan and measured queues at the intersection. The required inputs are readily available at many modern intersections. We observed that the proposed controller’s performance might degrade because of lane-changing maneuvers and lead-left turn traffic signals. These observations motivated our development of a lane change management strategy and a signal control implementation strategy to facilitate the EAD implementation. The lane change management strategies separate the EAD operations and lane-changing maneuvers in time and space. The signal control implementation strategy applies lag-left turn signals to enable EAD operation for both the through and left-turn vehicles. Compared to the non-EAD case, our EAD approach produces 2.5% to 7.8% energy savings while keeping similar intersection mobility. Notably, this approach brings about 2.5% to 3.6% energy savings in a 2% CAV case. This result demonstrates the feasibility of deploying EAD at low connected automated vehicle penetration rates.

Performance assessment of novel catalytic spouted-bed vapor jet flow heat exchanger in amine-based carbon capture process

This study introduced a spouted bed and jet flow catalytic heat exchanger (SBJ-EX). This novel non-agitated technology can potentially integrate with a conventional desorption column to enhance heat transfer and CO2 desorption performance in amine-based post-combustion carbon capture systems. As its first research in the carbon capture field, this work experimentally evaluated key factors including overall heat transfer coefficient, logarithmic mean temperature difference, temperature distribution along the reactor, and cyclic loading under varied parameters such as inlet temperature of the heating oil, inlet solvent temperature, rich CO2 loadings, and mass of catalysts to simulate real-world operating conditions using benchmark MEA solvent and solid acid catalyst HZSM-5. Compared to conventional plate heat exchangers, the SBJ-EX demonstrated over a 70 % enhancement in heat transfer performance due to its effective overall heat transfer coefficient. It also exhibited impressive CO2 desorption performance even at lower temperatures with sufficient catalysts. Unlike agitated-type heat exchangers, the SBJ-EX could minimize catalyst attrition and offer more excellent stability. In contrast to fixed-bed catalyst desorbed columns, this equipment offered a more compact design for quicker and simpler catalyst replacement to reduce downtime for operators significantly. The SBJ-EX can also function as an optional backup or add-on unit to provide operators with flexibility. This work further discussed advantages and challenges of the SBJ-EX operation. This work enriched the future research outlook for this technology, and contributed a commercially viable approach to catalysts in carbon capture processes.

Challenges and Solutions to Meet the Euro 7 NOx Emission Requirements for Diesel Light-Duty Commercial Vehicles

AbstractThe improvement of air quality requires a further reduction of pollutant emissions, especially in urban areas. The Euro 7 regulations aim at the development of a new generation of internal combustion engine vehicles capable of achieving ultra-low pollutant emissions under demanding, real-world operating conditions. They introduce new technical challenges in the holistic design of a vehicle’s powertrain and emission control system. To identify these, four real-world Euro 7 driving scenarios are investigated, covering demanding urban, highway and mountain driving situations. Technical solutions are then presented to address these challenges and ensure compliance with the Euro 7 emission requirements as set out in the latest regulation proposal of the European Commission. The study focuses on the NOx emissions of an N1 Class III light commercial vehicle with 3.5 t mass and a P2 diesel mild-hybrid powertrain. To ensure emission compliance, a Euro 6e exhaust gas aftertreatment system with enlarged catalysts is combined with NOx raw emission improvements. For low-load cold starts, a 4-kW electric heater in the exhaust system is considered in addition to a 2-l DOC and a 6-l DPF with SCR coating. For high-load cycles with high raw emissions, a 10-l underfloor SCR is considered to ensure the necessary deNOx performance.

Fault detection and diagnosis in light commercial buildings’ HVAC systems: A comprehensive framework, application, and performance evaluation

The data-driven approach currently dominates the field of Automatic Fault Detection and Diagnosis (AFDD) in HVAC systems. However, a significant concern lies in the prevalent use of labeled experimental and simulation data, which often does not represent real-world operational conditions. This study unveils a comprehensive framework for AFDD in light commercial buildings, effectively leveraging unlabeled raw data extracted directly from their Building BAS. Its main goal is to provide a versatile methodology tailored for real-world applicability. Buildings classified as “light commercial” typically have less than 2,500 square meters of floor area and no more than six stories, such as small offices, medical facilities, banks, small manufacturing facilities, etc. A common feature of these buildings is the fact that the HVAC systems tend to be relatively simple and have similar configurations, thus making it easy to develop scalable and reproducible fault detection methods. This paper focuses on a practical case study in a light commercial building HVAC system situated in Montreal, Canada, encompassing a single Air Handling Unit (AHU) and four Variable Air Volume (VAV) reheating boxes to evaluate the framework. This comprehensive framework encompasses a sequence of sub-objectives: creating a sizable, synchronized raw dataset from diverse BAS sensor tags, comprehensive data cleansing to address inconsistencies, developing an anomaly detection method, investigating these anomalies to extract underlying rules, and finally, dataset labeling. An AFDD classification model is then applied to evaluate its ability to distinguish normal from faulty conditions across various fault types. The study highlights the potential of dimensional reduction techniques and unsupervised clustering for effective anomaly detection in light commercial buildings, as well as the power of the Decision Tree classifier for uncovering hidden patterns, especially in anomaly conditions. It also highlights the significance of addressing imbalanced datasets in AFDD and the complexities of detecting sizing-related faults. Despite these challenges, the framework exhibits robust performance in detecting and diagnosing a range of HVAC faults. It offers a systematic and adaptable approach for handling real-world operational data in light commercial building HVAC systems, extendible to other building types, bridging the gap between data-driven methods and practical applications.

Integrative BNN-LHS Surrogate Modeling and Thermo-Mechanical-EM Analysis for Enhanced Characterization of High-Frequency Low-Pass Filters in COMSOL.

This paper pioneers a novel approach in electromagnetic (EM) system analysis by synergistically combining Bayesian Neural Networks (BNNs) informed by Latin Hypercube Sampling (LHS) with advanced thermal-mechanical surrogate modeling within COMSOL simulations for high-frequency low-pass filter modeling. Our methodology transcends traditional EM characterization by integrating physical dimension variability, thermal effects, mechanical deformation, and real-world operational conditions, thereby achieving a significant leap in predictive modeling fidelity. Through rigorous evaluation using Mean Squared Error (MSE), Maximum Learning Error (MLE), and Maximum Test Error (MTE) metrics, as well as comprehensive validation on unseen data, the model's robustness and generalization capability is demonstrated. This research challenges conventional methods, offering a nuanced understanding of multiphysical phenomena to enhance reliability and resilience in electronic component design and optimization. The integration of thermal variables alongside dimensional parameters marks a novel paradigm in filter performance analysis, significantly improving simulation accuracy. Our findings not only contribute to the body of knowledge in EM diagnostics and complex-environment analysis but also pave the way for future investigations into the fusion of machine learning with computational physics, promising transformative impacts across various applications, from telecommunications to medical devices.

Suitability Study of Biofuel Blend for Light Commercial Vehicle Application under Real-World Transient Operating Conditions

<div>Driving schedule of every vehicle involves transient operation in the form of changing engine speed and load conditions, which are relatively unchanged during steady-state conditions. As well, the results from transient conditions are more likely to reflect the reality. So, the current research article is focused on analyzing the biofuel-like lemon peel oil (LPO) behavior under real-world transient conditions with fuel injection parameter MAP developed from steady-state experiments. At first, engine parameters and response MAPs are developed by using a response surface methodology (RSM)-based multi-objective optimization technique. Then, the vehicle model has been developed by incorporating real-world transient operating conditions. Finally, the developed injection parameters and response MAPs are embedded in the vehicle model to analyze the biofuel behavior under transient operating conditions. The results obtained for diesel-fueled light commercial vehicle (LCV) have shown better fuel economy than LPO biofuel with their developed fuel injection parameter MAP. The maximum BTE obtained was 29.7% for diesel and 29.5% for LPO at 2100 rpm and 20 Nm torque. The mean HC emissions were identified as 0.02046 g/km for diesel and 0.03488 g/km for LPO fuel over the modified Indian driving cycle (MIDC). Except for NOx emission, LPO biofuel exhibited diesel-like performance and emission characteristics under the MIDC.</div>

Study on the decompression behavior during large-scale pipeline puncture releases of CO2 with various N2 compositions: Experiments and mechanism analysis

Impurities in the captured CO2 stream from various industrial sources may introduce uncertainty into the transient releases of transportation pipelines. Due to limitations in the experimental scale, there is currently limited analysis of the vertical cross-sectional temperature distribution and the pressure response along the pipeline during the releases of impure CO2. The mechanism by which impurities affect the decompression wave and the alterations in phase-change pathways remains unclear. In this study, building upon the existing large-scale pipeline, we established an impurity injection system. Using the common impurity, N2, as a variable, the decompression behavior of the CO2+N2 mixture in the puncture releases and the influence mechanism of N2 were investigated. The results show that the effect of N2 on sound velocity causes a significant decrease in the decompression wave speed. N2 raises the minimum temperature, and it is more pronounced in large-diameter releases; for instance, the minimum temperature during the 100 mm release is always higher than that in the 50 mm release. The gas-liquid mixture closely follows the dew point line, conforming to the Gibbs equilibrium criterion. The experimental scale mirrors real-world operating conditions, endowing the research findings with practical applicability. Concurrently, it furnishes dependable data for numerical researches.

Service life estimation of electric vehicle lithium-ion battery pack using arrhenius mathematical model

Durability is a desired characteristic for all battery packs in Electric Vehicles. In this study, the service life of the EV battery pack under real-world operating conditions is projected using an Arrhenius mathematical simulation model. The model comprises a 39.2 kWh EV Lithium-Ion battery pack integrated with a three-phase inverter to convert the battery pack’s Direct Current output to Alternating Current. In addition, the Alternating Current output is coupled to a 100 kW permanent magnet synchronous motor, which is regarded as the load. A field-oriented controller provides pulse width-modulated output signals that are supplied back to the inverter to generate the correct driving current. Variable conditions of charge rate (C-rate: 1.25C − 4C), discharge rate (C-rate: 0.5C − 4C), temperature (25°C–60°C), and depth of discharge (30%–90%) are evaluated to determine the battery pack’s service life. Under a 4C charge rate/0.5C discharge rate and 50% depth of discharge, the modeling results indicate the battery pack has a service life of approximately 6,000 h at low temperatures (25°C) and roughly 3,000 h at high temperatures (60°C). The model has been validated by comparing the results with experimental data from the literature.

Experimental and numerical investigation of the aerodynamic characteristics of high-performance vehicle configurations under yaw conditions

This study investigates the impact of yaw conditions on the aerodynamic performance and flow field of three high-performance vehicle model configurations by means of wind tunnel testing and unsteady Reynolds-Averaged Navier–Stokes-based computational fluid dynamics simulations. While yaw effects on automotive vehicles have been explored, the effects on far more complex flow fields of high-performance vehicles remain insufficiently researched. This paper reveals that yaw conditions have a significant negative influence both downforce and drag performance. Spoiler and rear wing devices enhance downforce but increase the vehicle's sensitivity to yaw. Furthermore, yaw conditions significantly alter vortex structures and local flow velocities, affecting downstream flow behavior. Surface pressure measurements on the slant confirm these findings and highlight notable yaw effects and upstream effects from spoiler and rear wing devices. Wake analyses through total pressure measurements show that yaw induces a substantial deviation from straight-line wake characteristics, which become dominated by an inboard rotating vehicle body vortex. Overall, this research enhances the understanding of the effects of yaw conditions on high-performance vehicle aerodynamics and provides valuable data for future vehicle aerodynamics research in real-world operating conditions.

Online Adaptive Model Identification and State of Charge Estimation for Vehicle-Level Battery Packs

Accurate state of charge (SOC) estimation of traction batteries plays a crucial role in energy and safety management for electric vehicles. Existing studies focus primarily on cell battery SOC estimation. However, numerical instability and divergence problems might occur for a large-size lithium-ion battery pack consisting of many cells. This paper proposes a high-performance online model identification and SOC estimation method based on an adaptive square root unscented Kalman filter (ASRUKF) and an improved forgetting factor recursive least squares (IFFRLS) for vehicle-level traction battery packs. The model parameters are identified online through the IFFRLS, where the conventional method might encounter numerical stability problems. By updating the square root of the covariance matrix, the divergence problem in the traditional unscented Kalman filter is solved in the ASRUKF algorithm, where the positive semi-definiteness of the covariance matrix is guaranteed. Combined with the adaptive noise covariance matched filtering algorithm and real-time compensation of system error, the proposed method solves the problem of ever-degrading estimation accuracy in the presence of time-varying noise with unknown statistical characteristics. Using a 66.2-kWh vehicle battery pack, we experimentally verified that the proposed algorithm could achieve high estimation accuracy with guaranteed numerical stability. The maximum error of SOC estimation can be bounded by 1%, and the root-mean-square error is as low as 0.47% under real-world vehicle operating conditions.

Fair and Scalable Orchestration of Network and Compute Resources for Virtual Edge Services

The combination of service virtualization and edge computing allows for low latency services, while keeping data storage and processing local. However, given the limited resources available at the edge, a conflict in resource usage arises when both virtualized user applications and network functions need to be supported. Further, the concurrent resource request by user applications and network functions is often entangled, since the data generated by the former has to be transferred by the latter, and vice versa. In this paper, we first show through experimental tests the correlation between a video-based application and a vRAN. Then, owing to the complex involved dynamics, we develop a scalable reinforcement learning framework for resource orchestration at the edge, which leverages a Pareto analysis for provable fair and efficient decisions. We validate our framework, named VERA, through a real-time proof-of-concept implementation, which we also use to obtain datasets reporting real-world operational conditions and performance. Using such experimental datasets, we demonstrate that VERA meets the KPI targets for over <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$96\%$</tex-math></inline-formula> of the observation period and performs similarly when executed in our real-time implementation, with KPI differences below 12.4%. Further, its scaling cost is <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$54\%$</tex-math></inline-formula> lower than a centralized framework based on deep-Q networks.

Testing the fragmentation of railway ballast material by laboratory methods using Proctor compactor

The physical classification of crushed stone and gravel used in railway construction is based on their strength and endurance and is performed by a laboratory test method using a rotating drum or a mortar method. The values of fracture resistance calculated using the Los Angeles method and abrasion calculated using the Micro-Deval method show a corresponding correlation and require further investigation. Purpose. The development of a new method for measuring rock material fracture that is consistent with widely used standards while also being more comparable to real-world railway operating conditions. Certainly, both standard tests are essential for ensuring product homogeneity during production, so the new recommended method is only a supplement. Methodology. The Proctor device was used to induce so-called shock loads from above, similar to railway loading conditions. Unlike the standard method, the andesite material was placed in a standard cylinder in these tests. The samples were pre-screened and sorted; the specified weight was approximately 1,300 g, and the specified sizes of the individual particles were 6.3, 8.0 and 11.2 mm. Only prewashed and dried materials of NZ (fine crushed stone) or KZ (special crushed stone) from four different quarries (Tállya, Szob, Nógrádkövesd, Recsk) with different rock physics characteristics were considered. The Proctor compactor machine was used because of its calculable labor (19.86 J/impact) and the crushing effect of the calculable impacts (64, 128, 256 and 1,028 blows). Even after loading different numbers of impacts, homogeneous samples from different quarries were sieved to measure the masses of fragments per fraction. Findings. The set of measurements made it possible to establish a series of fragmentation and degradation curves for each of the three repeated measurements based on the composition of the material and the number of blows, which showed the degradation of samples with different physical and mechanical properties of the rock material and particle sizes. With an increasing number of impacts, the amount of crushed material in the sample increased, but the distribution of crushed material did not decrease evenly and proportionally as the number of impacts increased. Parameters and indices were also computed to identify various correlations (i. e., FV, d &lt; 22.4, d &lt; 0.5, d &lt; 0.063 mm, CU, M ratio,  ratio). Some of them (e. g., FV) needed to be changed, but they were predefined due to the nature of the tests. Originality. While many standard and alternative railway track ballast fragmentation test methods and measurement tools are available, this paper proposes a new laboratory method and demonstrates the specific measurement and application effectiveness. Practical value. In addition to standard tests that are already widely used, the new method for measuring the fractional composition of railway ballast can help simulate real-world operating conditions of a railroad track in the laboratory. This method will improve the safety of railway operations.

Comparison of Modern Deep Learning Models for Speaker Verification

This research presents an extensive comparative analysis of a selection of popular deep speaker embedding models, namely WavLM, TitaNet, ECAPA, and PyAnnote, applied in speaker verification tasks. The study employs a specially curated dataset, specifically designed to mirror the real-world operating conditions of voice models as accurately as possible. This dataset includes short, non-English statements gathered from interviews on a popular online video platform. The dataset features a wide range of speakers, with 33 males and 17 females, making a total of 50 unique voices. These speakers vary in age from 20 to 70 years old. This variety helps in thoroughly testing speaker verification models. This dataset is especially useful for research on speaker verification with short recordings. It consists of 10 clips for each person, each clip being no longer than 10 s, adding up to 500 recordings in total. The total length of all recordings is about 1 h and 30 min, which averages to roughly 100 s for each speaker. This dataset is a valuable tool for research in speaker verification, particularly for studies involving short audio clips. The performance of these models is evaluated using common biometric metrics such as false acceptance rate (FAR), false rejection rate (FRR), equal error rate (EER) and detection cost function (DCF). The results reveal that the TitaNet and ECAPA models stand out by presenting the lowest EER (1.91% and 1.71%, respectively) and thus exhibiting higher discriminative features, ensuring, on the one hand, a reduction in intra-class distance (the same speaker), and, on the other hand, maximizing the distance between different speaker embeddings. This analysis also highlights the ECAPA model’s advantageous balance of performance and efficiency, achieving an inference time of 69.43 milliseconds, slightly longer than the PyAnnote models. This study not only compares the performance of models but also provides a comparative analysis of respective model embeddings, offering insights into their strengths and weaknesses. The presented findings serve as a foundation for guiding future research in speaker verification, especially in the context of short audio samples or limited data. This may be particularly relevant for applications requiring quick and accurate speaker identification from short voice clips.

Modeling and Control Simulation of Power Converters in Automotive Applications

This research introduces a model-based approach for the analysis and control of an onboard charger (OBC) system for contemporary electrified vehicles. The primary objective is to integrate the modeling of SiC/GaN MOSFETs electrothermal behaviors into a unified simulation framework. The motivation behind this project stems from the fact that existing literature often relies on finite element method (FEM) software to examine thermal dynamics, necessitating the development of complex models through partial derivative equations. Such intricate models are computationally demanding, making it difficult to integrate them with circuit equations in the same virtual environment. As a result, lengthy wait periods and a lack of communication between the electrothermal models limit the thorough study that can be conducted during the design stage. The selected case study for examination is a modular 1ϕ (single phase) onboard computer (OBC). This system comprises a dual active bridge (DAB) type DC/DC converter, which is positioned after a totem pole power factor correction (PFC) AC/DC converter. Specifically, the focus is directed toward a 7 kW onboard computer (OBC) utilizing high-voltage SiC/GaN MOSFETs to ensure optimal efficiency and performance. A systematic approach is presented for the assessment and selection of electronic components, employing circuit models for the totem pole power factor correction (PFC) and dual active bridge (DAB) converter. These models are employed in simulations closely mimicking real-world scenarios. Furthermore, rigorous testing of the generated models is conducted across a spectrum of real-world operating conditions to validate the stability of the implemented control algorithms. The validation process is bolstered by a comprehensive exploration of parametric variations relative to the nominal case. Notably, each simulation adheres to the recommended operational limits of the selected components and devices. Detailed data sheets encompassing electrothermal properties are provided for contextual reference.

Representative Real-Time Dataset Generation Based on Automated Fault Injection and HIL Simulation for ML-Assisted Validation of Automotive Software Systems

Recently, a data-driven approach has been widely used at various stages of the system development lifecycle thanks to its ability to extract knowledge from historical data. However, despite its superiority over other conventional approaches, e.g., approaches that are model-based and signal-based, the availability of representative datasets poses a major challenge. Therefore, for various engineering applications, new solutions to generate representative faulty data that reflect the real world operating conditions should be explored. In this study, a novel approach based on a hardware-in-the-loop (HIL) simulation and automated real-time fault injection (FI) method is proposed to generate, analyse and collect data samples in the presence of single and concurrent faults. The generated dataset is employed for the development of machine learning (ML)-assisted test strategies during the system verification and validation phases of the V-cycle development model. The developed framework can generate not only time series data but also a textual data including fault logs in an automated manner. As a case study, a high-fidelity simulation model of a gasoline engine system with a dynamic entire vehicle model is utilised to demonstrate the capabilities and benefits of the proposed framework. The results reveal the applicability of the proposed framework in simulating and capturing the system behaviour in the presence of faults occurring within the system’s components. Furthermore, the effectiveness of the proposed framework in analysing system behaviour and acquiring data during the validation phase of real-time systems under realistic operating conditions has been demonstrated.