Adrienn Dineva

55635385900

Publications - 18

Early Detection of ITSC Faults in PMSMs Using Transformer Model and Transient Time-Frequency Features

Adrienn Dineva Adam Zsuga

Publication Name: Energies

Publication Date: 2025-08-01

Volume: 18

Issue: 15

Page Range: Unknown

Description:

Inter-turn short-circuit (ITSC) faults in permanent magnet synchronous machines (PMSMs) present a significant reliability challenge in electric vehicle (EV) drivetrains, particularly under non-stationary operating conditions characterized by inverter-driven transients, variable loads, and magnetic saturation. Existing diagnostic approaches, including motor current signature analysis (MCSA) and wavelet-based methods, are primarily designed for steady-state conditions and rely on manual feature selection, limiting their applicability in real-time embedded systems. Furthermore, the lack of publicly available, high-fidelity datasets capturing the transient dynamics and nonlinear flux-linkage behaviors of PMSMs under fault conditions poses an additional barrier to developing data-driven diagnostic solutions. To address these challenges, this study introduces a simulation framework that generates a comprehensive dataset using finite element method (FEM) models, incorporating magnetic saturation effects and inverter-driven transients across diverse EV operating scenarios. Time-frequency features extracted via Discrete Wavelet Transform (DWT) from stator current signals are used to train a Transformer model for automated ITSC fault detection. The Transformer model, leveraging self-attention mechanisms, captures both local transient patterns and long-range dependencies within the time-frequency feature space. This architecture operates without sequential processing, in contrast to recurrent models such as LSTM or RNN models, enabling efficient inference with a relatively low parameter count, which is advantageous for embedded applications. The proposed model achieves 97% validation accuracy on simulated data, demonstrating its potential for real-time PMSM fault detection. Additionally, the provided dataset and methodology contribute to the facilitation of reproducible research in ITSC diagnostics under realistic EV operating conditions.

Open Access: Yes

DOI: 10.3390/en18154048

Evaluation of Advances in Battery Health Prediction for Electric Vehicles from Traditional Linear Filters to Latest Machine Learning Approaches

Adrienn Dineva

Publication Name: Batteries

Publication Date: 2024-10-01

Volume: 10

Issue: 10

Page Range: Unknown

Description:

In recent years, there has been growing interest in Li-ion battery State-of-Health (SOH) estimation due to its critical role in ensuring the safe and reliable operation of Electric Vehicles (EVs). Effective energy management and accurate SOH prediction are essential for the reliability and sustainability of EVs. This paper presents an in-depth review of SOH estimation techniques, starting with an overview of seminal methods that lay the theoretical groundwork for battery modeling and SOH prediction. The review then evaluates recent advancements in Machine Learning (ML) and Artificial Intelligence (AI) techniques, emphasizing their contributions to improving SOH estimation. Through a rigorous screening process, the paper systematically assesses the evolution of these advanced methods, addressing specific research questions to evaluate their effectiveness and practical implications. Key findings highlight the potential of hybrid models that integrate Equivalent Circuit Models (ECMs) with Deep Learning approaches, offering enhanced accuracy and real-time performance. Additionally, the paper discusses limitations of current methods, such as challenges in translating laboratory-based models to real-world conditions and the computational complexity of some prospective methods. In conclusion, this paper identifies promising future research directions aimed at optimizing hybrid models and overcoming existing constraints to advance SOH estimation and battery management in Electric Vehicles.

Open Access: Yes

DOI: 10.3390/batteries10100356

Machine Learning for Multi-Fault Classification in Park's Vector Trajectories of PMSMs

Adrienn Dineva Adam Zsuga

Publication Name: 2024 IEEE 22nd Mediterranean Electrotechnical Conference MELECON 2024

Publication Date: 2024-01-01

Volume: Unknown

Issue: Unknown

Page Range: 133-137

Description:

Space Vector Theory, also known as Park's Vector Method, is a frequently utilized technique for analyzing, modeling, and controlling electrical machines and drives. In motor diagnostics applications based on Park's Vector trajectory patterns, the assistance of domain experts is indispensable for Fault Detection and Diagnosis (FDD). Yet, simultaneously occurring faults may lead to feature overlap or accumulation, posing additional challenges for identification. In this paper a comparative analysis of automating Park's Vector Approach is presented, with combining the method with advanced ML techniques. Utilizing a magnetics-based Permanent Magnet Synchronous Motor (PMSM) model, a custom simulated fault dataset is created for training purposes. The dataset is used to train three distinct models: a Siamese Network, EfficientNet and the Vision Transformer model. Throughout the evaluation, key classification metrics including the F1-score, precision, and recall are analyzed, alongside an examination of the training curves. The results indicate that the Park's Vector Approach combined with State-of-the-Art ML models efficiently detects anomalies and multiple faults. It highlights the models' ability to identify local features, accurately classify, and detect simultaneous faults, which is often challenging for domain experts due to the difficulty in distinguishing fault features of multiple faults even through visual inspection.

Open Access: Yes

DOI: 10.1109/MELECON56669.2024.10608573

AI-Driven IoT-based Energy Community Platform Design, Model Experimentation and Implementation Insights

Adrienn Dineva Rita Fleiner Ágnes Gerse Istvan Lovas Zsolt Bringye

Publication Name: 2024 22nd International Conference on Intelligent Systems Applications to Power Systems Isap 2024

Publication Date: 2024-01-01

Volume: Unknown

Issue: Unknown

Page Range: Unknown

Description:

In recent years, decentralized renewable energy production has gained increasing importance. Challenges of distributed energy production include fluctuations in weather-dependent energy generation, which may not always meet peak consumption periods and can result in significant overproduction during low-load periods. Managing production and consumption is a fundamental task for efficient renewable energy utilization. The application of lithium-ion or other advanced battery technologies as community energy storage provides a more reliable power supply when operated optimally with advanced energy management and control systems. Digital platforms form the basis of Energy Communities, supporting necessary processes and functionalities, and enabling the integration of smart grids that utilize data from IoT devices, meteorological sources, and energy markets. This paper presents a design of an Energy Community management platform and digital tools that provide a systematic framework for mapping energy consumption trend within energy communities. Adopting a digital platform for an energy community involves the integration of IoT devices, a centralized database, and a software platform equipped with AIbased forecasting tools. Additionally, investigations into various modeling approaches have highlighted the superior performance of hybrid deep learning models, specifically those combining GRU and LSTM architectures, in predicting energy consumption. These models excel in forecasting consumption peaks, which is crucial for optimizing energy distribution and storage within the community and are able to overcome the limitations of classical forecasting methods, which usually do not account for external variables like weather changes, consumer trends, and technological advancements that might affect energy use.

Open Access: Yes

DOI: 10.1109/ISAP63260.2024.10744343

Spatial Allocation of Wind Farms and Flexibility Requirements: A Genetic Algorithm-based Optimization Approach

Adrienn Dineva Endre Borcsok Rita Fleiner Ágnes Gerse

Publication Name: 2024 22nd International Conference on Intelligent Systems Applications to Power Systems Isap 2024

Publication Date: 2024-01-01

Volume: Unknown

Issue: Unknown

Page Range: Unknown

Description:

This paper addresses the impact of spatial allocation on the flexibility requirements of wind farms in the context of the mid-term development of wind energy exploitation in Hungary. As a starting point for evaluating flexibility requirements, a wind power simulation model is adopted that converts hourly wind speed time series derived from climate reanalysis into hourly aggregate power output using theoretical power curves. This simulation model allows for evaluating various flexibility metrics for both existing and hypothetical wind farms. As a second step, a Genetic Algorithm (GA) is integrated with the simulation environment to find an optimal subset of hypothetical wind farms with respect to flexibility requirements. The application of GA reveals insights into how spatially optimizing wind farm placement can significantly reduce flexibility requirements. This finding can have practical implications for policy-makers and planners in the renewable energy sector, especially given the evolving regulatory landscape and increasing focus on grid stability.

Open Access: Yes

DOI: 10.1109/ISAP63260.2024.10744302

Data Enrichment with Climate Reanalysis Data and Machine Learning for Analyzing Supply Adequacy in Renewable Power Systems

Adrienn Dineva Rita Fleiner Ágnes Gerse

Publication Name: Cinti 2024 IEEE 24th International Symposium on Computational Intelligence and Informatics Proceedings

Publication Date: 2024-01-01

Volume: Unknown

Issue: Unknown

Page Range: 167-172

Description:

To overcome the limitations in using historical time series data for the supply adequacy analysis of renewable power systems, a data enhancement process is implemented allowing for a temporal enrichment of the available historical data. The methodology is based on the direct conversion of gridded climate reanalysis time series into aggregate output estimates where the simulated aggregate output is estimated by machine learning and historical power system data are used as training and testing data set. As a case study, the data enrichment methodology was accomplished with Hungarian power system data. From the enriched wind and solar electricity generation time series, availability statistics were derived that can be integrated into analytical probabilistic adequacy risk assessment models to describe the availability of wind and solar energy as aggregate, multi-state units.

Open Access: Yes

DOI: 10.1109/CINTI63048.2024.10830913

Case Study: Optimizing Grading Ring Design for High Voltage Polymeric Insulators in Power Transmission Systems for Enhanced Electric Field and Voltage Distribution by Using a Finite Element Method

Fatiha Aouabed Adrienn Dineva Esraa Aziz Hossam Abdellah

Publication Name: Energies

Publication Date: 2023-07-01

Volume: 16

Issue: 13

Page Range: Unknown

Description:

This research paper aims to investigate the optimal design of grading rings for high-voltage polymeric insulators in an actual power transmission system, with a focus on improving the electrical representation of the insulator strings. One such subsidiary accessory commonly used with porcelain and polymer insulator strings is the grading ring, which is employed to improve the electric field and voltage distribution surrounding the insulator string. The efficiency of insulator strings can be enhanced by grading rings, as they facilitate a more linear potential division along the strings. The design parameters of grading rings significantly influence their performance on insulator strings. In this study, we examine the optimal design of the grading rings of high-voltage polymer insulators, since no uniform design methodology has been developed for high-voltage polymer insulators, and their optimization is currently the subject of many research studies. The electric field on an outdoor polymeric insulator is examined using finite element method (FEM) software and COMSOL Multi-Physics program. A 2D model is utilized to simulate a 220 kV polymeric insulator. The effectiveness of high-voltage polymeric insulators greatly depends on the dimensions and locations of the grading rings. Therefore, the impacts of the radius of the grading ring and that of its tube and the tube’s vertical position are thoroughly investigated, under dry and humid conditions. To achieve this objective, a search algorithm is employed to adjust the dimensions and locations of the grading ring. The optimization approach in this study is based on determining the maximum electric field across the insulator surface, while ensuring that it remains below the corona initiation level.

Open Access: Yes

DOI: 10.3390/en16135235

Data-Driven Onboard Inter-Turn Short Circuit Fault Diagnosis for Electric Vehicles by Using Real-Time Simulation Environment

Adrienn Dineva Adam Zsuga

Publication Name: IEEE Access

Publication Date: 2023-01-01

Volume: 11

Issue: Unknown

Page Range: 145447-145466

Description:

Various fault detection methods, particularly focused on onboard Condition-Based Monitoring (CBM) in Electrical Machines and Drives (EMDs), face limitations such as sensitivity to load variations, slow fault detection, and the absence of fully automated solutions. AI and Data-Driven methods offer flexible alternatives, utilizing historical data for pattern and anomaly identification. Among Electrical Signature Analysis techniques for electrical motor diagnostics, the Space Vector Theory (SVT) is extensively used, while Park's Vector based diagnostic solutions lack real-time Inter-Turn Short Circuit (ITSC) fault severity assessment, with available techniques often limited to binary classifiers. Implementing AI with SVT for real-time Electric Vehicle (EV) use is underdeveloped, hindered by data scarcity and diverse dataset collection challenges. Real-time simulation, accurate fault modeling, and hardware limitations pose challenges, especially for embedding AI models into processors. To achieve intelligent onboard diagnosis for ITSC fault severity in this paper, a multi-modal approach model is proposed, employing MobileNetV2 to classify Park's Vector trajectories based on the fault features related to the number of shorted turns. Performance assessments encompass both the standard MobileNetV2 and the proposed multi-modal approach model across various fault severity levels. Furthermore, to address the challenge of limited data availability, an accelerated real-time AI development environment is designed using an FPGA to generate synthetic fault pattern datasets, aligning with the standards of the Electric Vehicle industry. For modeling PMSM with ITSC faults, a fault circuit model is employed. The dataset of 900 Park's Vector trajectory images is automatically generated by varying the torque request from 10 to 100 Nm with a 10 Nm resolution. At each torque operating point, the motor currents are recorded by adjusting the number of shorted turns. Simulation results confirm the outstanding performance of MobileNetV2 in binary classification, achieving an accuracy of 99.26 %. In case of 5-class ITSC fault severity classification, the prediction accuracy reaches only 72.55 %. The here proposed multi-modal MobileNetV2 model excels, achieving a remarkable accuracy of 99.163 % in the 3-class fault severity classification and 84.907 % in the 5-class classification. These results support the superiority of the proposed multi-modal MobileNetV2 model, which is trained on the generated rich dataset. It outperforms existing Park's Vector Analysis based ITSC fault detection methods, particularly in early ITSC fault detection as it can detect faults from 6 shorted turns. Additionally, it allows for online fault severity assessment during transient operation and meets stringent requirements for onboard applications. Altogether, the results of investigations prove the presence and extractability of fine detail information in Park's Vector trajectories, for assessing ITSC fault severity. This contributes to a deeper understanding and analysis of faults in electrical motors through the use of Park's Vector trajectories.

Open Access: Yes

DOI: 10.1109/ACCESS.2023.3344483

Testing and Modeling Procedure of the 18650 Lithium Battery at Different Temperatures

Adrienn Dineva István Lakatos Szabolcs Kocsis Szurke

Publication Name: 2022 22nd International Symposium on Electrical Apparatus and Technologies Siela 2022 Proceedings

Publication Date: 2022-01-01

Volume: Unknown

Issue: Unknown

Page Range: Unknown

Description:

In this paper a two-time constant (TTC) electrical model is investigated to simulate the operation of 18650 batteries at different temperatures. To determine the parameters of the model, a new test procedure is developed, which can be used to obtain a wide range of information on the behavior of the tested batteries after 10 measurements. After performing the tests, detailed information on the constant, transient, and dynamic behavior of the battery over a wide temperature range is available. After, a statistics-based Ordered Weighted Averaging (OWA) aggregation operator is applied to evaluate the results. The general model is developed based on standardized parameters. Worldwide Harmonized Light Vehicle Test Procedure (WLTP) tests are performed to validate the simulation results. The operation of the model has been tested at 4 different temperatures: -15 °C, 0 °C, 25 °C, 60 °C. The simulation results are compared and evaluated with real measurement data.

Open Access: Yes

DOI: 10.1109/SIELA54794.2022.9845767

Determination of critical deformation regions of a lithium polymer battery by dic measurement and wowa filter

Adrienn Dineva István Lakatos Szabolcs Szalai Szabolcs Kocsis Szurke

Publication Name: Acta Polytechnica Hungarica

Publication Date: 2022-01-01

Volume: 19

Issue: 2

Page Range: 113-134

Description:

This paper considers the determination method of deformation location of lithium polymer batteries. Measurements are performed using the Digital Image Correlation (DIC) technique and the obtained results are sorted into a database as a function of the charge level. A statistically based algorithm is used to eliminate measurement errors and outliers. This paper adopts the Weighted Ordered Weighted Averaging (WOWA) operator-based 2D filtering method with the purpose of determining the critical regions of the cell. During the tests, several lithium polymer batteries of the same type but in different states are compared. Measurements on completely new and also on worn-out batteries are performed. The results support that the regions where greater deformation is expected during charging and discharging can be predicted. Results of investigations validate that the proposed approach is suitable for determining the critical deformation regions with high accuracy.

Open Access: Yes

DOI: DOI not available

Application of Machine Learning to Automatic Gear Shift Schedule Design of Alternative Drive Systems

Adrienn Dineva Szabolcs Kocsis Szurke Adam Zsuga

Publication Name: 2022 22nd International Symposium on Electrical Apparatus and Technologies Siela 2022 Proceedings

Publication Date: 2022-01-01

Volume: Unknown

Issue: Unknown

Page Range: Unknown

Description:

Intelligent automatic transmission shift schedule design has been well established in the last decade. However, due to the paradigm change is currently taking place in mobility sector, which resulted in a rapid progress of Electric Vehicles and Autonomous Vehicles, intelligent automatic gear shift strategies are still in the focus of much research. In addition, the proper transmission shift schedule generation is especially important from the viewpoint of energy efficiency optimizing algorithms, which is affected by the driving style, power losses, etc. Fundamentally, conventional shift schedule design relies on lookup tables obtained from test-bench measurements and real-world driving measurements. During real time test data collection, the measurement of some variables may be impractical and/or patterns of important driving conditions may be unavailable during short-distance routes neglecting the comprehensive effects of the transient operation. Machine Learning methods in combination with model-based data generation is a promising alternative, which allows a significant reduction in development time and a more precise calibration by using rich historical data rich. Such models can be easily fitted to alternative drive systems also, which may raise more specific requirements regarding gear shift scheduling issues coupled with efficiency. In this paper the performances of Machine Learning models are investigated in automatic gear shift schedule generation based on simulated driving cycle test data. Results of simulation investigations validate the applicability and efficiency of the proposed approach.

Open Access: Yes

DOI: 10.1109/SIELA54794.2022.9845718

Statistical approach for designing generic 18650 battery model

Adrienn Dineva István Lakatos Krisztian Horvath Szabolcs Kocsis Szurke

Publication Name: 2021 17th Conference on Electrical Machines Drives and Power Systems Elma 2021 Proceedings

Publication Date: 2021-07-01

Volume: Unknown

Issue: Unknown

Page Range: Unknown

Description:

Most battery models are designed by estimating its parameters of one or two different cells. During simulations, these models perform satisfactorily and produce results very close to reality. The problem occurs when measurements are conducted with cells from different manufacturers and large variations are observed during the dynamic loads. The purpose of this paper is to design a general model for 18650 designed batteries, which provides as little deviation as possible when using different cell types. To establish the general model, constant load, transient, and dynamic load tests on 8 different cells are performed. An Ordered Weighted Averaging operator is used to standardize the measurement results and determine the model parameters. Outliers are filtered out using the weight parameter. To create the battery model a two-time-constant circuit model is used in MATLAB Simulink. Worldwide Harmonized Light Vehicle Test Procedure (WLTP) tests are used to validate the results.

Open Access: Yes

DOI: 10.1109/ELMA52514.2021.9503034

Case-study for HW accelerated FEA model for electrical machine control prototyping

Adrienn Dineva Richard B. Szilagyi

Publication Name: 2021 17th Conference on Electrical Machines Drives and Power Systems Elma 2021 Proceedings

Publication Date: 2021-07-01

Volume: Unknown

Issue: Unknown

Page Range: Unknown

Description:

The challenging market in the e-mobility domain requires higher speed of development. To accelerate the time to market of the products, this phenomena is also addressing the tools and methods are used in the procedure of development. System simulations are widely used to control prototyping with validation purposes. Within a frame of a case study this paper presents the most common branches of the e-machine simulation methods. Highlights the main benefits and downsides of the simulation schemes. Draws results and sources from studies, are done in the field of finite element based e-machine modeling and simulation by the engineering community. These applications are evaluated and giving overview about the complexity of model structures, details and the computational sources from the perspective of required value of run-time. Explains the common approaches of the e-machine simulation methods, with an investigation in the field of hardware accelerated finite element analysis. Invests within the available studies and experiences from different non e-machine applications of the finite element method. Consequently notes a form of application and adaption of these techs of the finite element analysis that keep the tempo of development at a high-rate beside to offer a more detailed simulation than traditionally used tools for control prototyping purposes.

Open Access: Yes

DOI: 10.1109/ELMA52514.2021.9503064

Review and conceptual design of FPGA-based application for data-driven power electronic systems

Adrienn Dineva Adam Zsuga

Publication Name: 2021 17th Conference on Electrical Machines Drives and Power Systems Elma 2021 Proceedings

Publication Date: 2021-07-01

Volume: Unknown

Issue: Unknown

Page Range: Unknown

Description:

AI-based data-driven methods are an emerging research direction in the field of power electronics. However, because of the absence of large datasets, the development of these solutions have some barriers to overcome. To properly train machine learning algorithms and neural networks a large amount of training data is necessary. This dataset can be a union of simulation and measured data. Generating simulation data with computer simulations can be slow process and gathering real data is not cost-effective. Real-Time simulators based on FPGAs can be powerful tools to accelerate simulation, and create datasets for AI applications in a cost-effective and accurate way. In this paper the possible FPGA-based solutions, which can be applicable for the problems, have been reviewed. Their applicability have been discussed, moreover a simplified FPGA-based concept have been designed and embedded into two possible AI-based application area.

Open Access: Yes

DOI: 10.1109/ELMA52514.2021.9503033

Investigation of the performance of direct forecasting strategy using machine learning in State-of-Charge prediction of Li-ion batteries exposed to dynamic loads

Adrienn Dineva Bence Csomós Szabolcs Kocsis Szurke Istvan Vajda

Publication Name: Journal of Energy Storage

Publication Date: 2021-04-01

Volume: 36

Issue: Unknown

Page Range: Unknown

Description:

On account of intense technological advances regarding Electric Vehicles, the state evaluation and prediction issues of Li-ion cells have become increasingly important for ensuring the competitiveness in terms of feasible performance and range. Albeit the wide investigation of various standard modelling and estimation techniques, only limited researches focus on their precision and applicability under heavy transient working conditions. This paper is concerned with Li-ion battery terminal voltage and State-of-Charge (SoC) prediction for two types of dynamic loads. Attention is focused on the investigation of the applicability of direct multi-step forecasting strategy in combination with Machine Learning. Beside that, a feature bank is composed of discharge profiles obtained at different C-rates. The set of discharge curves is proposed to complement the feature extraction, i.e. the additional historical data is considered for model building. Special care is devoted for the design of appropriate training data. Hence, a battery cell model is built for simulating intensive dynamic load scenarios in addition to the experimental setup. The cell model is validated by using measurement data. Results have demonstrated, that in case of WLTP-type discharge load of 0.3C-rate the forecasting performance is highly efficient on measurement data. Under dynamic loads of 1C-rate, or when small historical data is available, the application of feature bank improves the performance. We have obtained comprehensive results proving that the application of direct multi-step forecasting strategy using XGBoost represents a viable alternative to capture real-time the cell dynamics and predict the terminal voltage and SoC of Li-ion batteries exposed to dynamic loads.

Open Access: Yes

DOI: 10.1016/j.est.2021.102351

Data-driven terminal voltage prediction of li-ion batteries under dynamic loads

Adrienn Dineva Szabolcs Kocsis Szurke Istvan Vajda

Publication Name: 2020 21st International Symposium on Electrical Apparatus and Technologies Siela 2020 Proceedings

Publication Date: 2020-06-01

Volume: Unknown

Issue: Unknown

Page Range: Unknown

Description:

Extensive investigation and prediction of the effects of dynamic battery loading is key to on-board Battery Management Systems (BMS) of Electric Vehicles (EVs) in order to ensure reliable operation and efficient energy management. In this paper, measurements of WLTP discharge tests at different temperatures are conducted on a Lithium Nickel Manganese Cobalt Oxide (LiNiMnCoO2) cell. Terminal voltage, discharge rate and temperatures at four points are taken into consideration. After, historical measurement data is used to build ensemble of boosted tree models and then predict cell voltage outcome sequence into the future. The efficiency of the performance is compared in case of various measurement sets. The results support the efficiency and applicability of direct multi-step-ahead forecasting strategy with standard Machine Learning techniques in battery SoC prediction.

Open Access: Yes

DOI: 10.1109/SIELA49118.2020.9167039

High Precision Test System for the Investigation of the Condition of Lithium-ion Batteries

Adrienn Dineva Krisztian Ferko Miklos Szekely Gyula Gyoker Istvan Vajda

Publication Name: 2018 International Symposium on Fundamentals of Electrical Engineering Isfee 2018

Publication Date: 2018-11-01

Volume: Unknown

Issue: Unknown

Page Range: Unknown

Description:

Modern electric drive systems require more sophisticated monitoring and diagnosis methods for determining the expected life-Time and reliability. Recently, continuous assessment of the electrical condition of electrical machines has become increasingly important. Investigations to predict battery life are of the utmost importance for Electric Vehicles (EVs). The evaluation of the instantaneous State-of-Health (SoH) of the battery cell packs requires a precise measurement system that encompasses the especially important specifications related to the operating conditions. In addition modern Battery Management Systems (BMS) rely on empirical battery models whose parametrization is crucial from the reliability's point of view. The model parameters are necessary to be indentified via the appropriate measurement data. To address these considerations, this paper presents a new test system for Li-ion batteries and control software based on LabView, which is capable of conducting high quality and completely automated battery cell measurements defined by user input test vectors and test suites. The test system allows conducting also real time condition monitoring in Li-ion batteries by discharge impulse responses. Finally several measurements on the experimental setup are performed. Analysis of the measured data validate that the designed device ensures high performance testing and post-processing.

Open Access: Yes

DOI: 10.1109/ISFEE.2018.8742422

On the Impact of Magnetic Saturation on Incipient Itsc Fault Signal Detection in Pmsms Under Ev Transient Conditions

Adrienn Dineva Adam Zsuga

Publication Name: 2025 19th International Conference on Electrical Machines Drives and Power Systems Elma 2025 Proceedings

Publication Date: 2025-01-01

Volume: Unknown

Issue: Unknown

Page Range: Unknown

Description:

Incipient inter-turn short-circuit (ITSC) faults in permanent magnet synchronous machines (PMSMs) pose substantial diagnostic challenges, particularly under transient operating conditions common in electric vehicle (EV) applications. Traditional frequency-domain techniques, such as the Fast Fourier Transform (FFT), exhibit poor time-frequency resolution, making them ineffective for capturing non-stationary fault signatures. This study employs FEM-based numerical simulations combined with Continuous Wavelet Transform (CWT) analysis to accurately detect and localize ITSC fault characteristics under dynamic load conditions. While magnetic saturation is known to influence machine behavior, its quantitative impact on electrical fault signal amplitudes has not been explicitly addressed in previous diagnostic approaches. To fill this gap, a high-fidelity FEM simulation framework was developed, encompassing the full operational envelope of PMSMs. The results demonstrate that magnetic saturation leads to a notable attenuation-approximately 20-30% - of fault-induced current components, significantly complicating onboard detection. To the best of the authors' knowledge, such an integrated, EV-specific onboard diagnostic approach for incipient ITSC faults has not yet been reported in the literature. Although onboard thermal management systems exist, incipient ITSC faults may rapidly escalate into severe winding damage within 10 to 60 minutes under continuous load. This highlights the critical need for early detection methods robust to transient dynamics and magnetic nonlinearities.

Open Access: Yes

DOI: 10.1109/ELMA65795.2025.11083495