IEEE AccessPub Date : 2025-07-25DOI: 10.1109/ACCESS.2025.3592728
Yangyang Ma;Wenle Song;Jie Gao;Yang Liu;Yilei Shang;Weimei Zhao;Fuyao Yang
{"title":"Vibration Analysis and Optimization of Iron-Core Reactors Based on Fe-Based Soft Magnetic Composite Materials","authors":"Yangyang Ma;Wenle Song;Jie Gao;Yang Liu;Yilei Shang;Weimei Zhao;Fuyao Yang","doi":"10.1109/ACCESS.2025.3592728","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3592728","url":null,"abstract":"To effectively reduce the vibration of iron-core reactors, a vibration optimization method considering the magnetostrictive properties of Fe-based soft magnetic composite materials is proposed. First, an improved magnetostrictive model incorporating stress effects is established based on the classical Jiles–Atherton (J-A) model and the quadratic domain rotation theory. The characteristic parameters of the improved model are identified using the particle swarm optimization–simulated annealing (PSO-SA) algorithm, with the identified root mean square error not exceeding 3.5, verifying the model’s accuracy. Then, an electromagnetic-structural coupled simulation model of the iron-core reactor is developed to calculate the magnetic field and vibration distribution. Based on multiphysics simulation and Latin hypercube sampling, combined with sensitivity analysis techniques, the influence of each parameter on vibration is identified, and optimization objectives and variables are hierarchically classified. Finally, response surface methodology (RSM) and Kriging methods are employed for the parameter optimization design of the reactor, yielding the optimal structural parameters under different optimization strategies. The results show that, compared to the initial parameters, the maximum vibration displacement of the iron core is reduced by 13.93% and 24.64% using the RSM and Kriging methods, respectively. Additionally, both core loss and conductor consumption are significantly reduced. Therefore, under the premise of meeting performance requirements, the Kriging optimization method can significantly reduce the vibration displacement of the iron-core reactor, providing valuable guidance for its vibration reduction and optimization.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"132599-132610"},"PeriodicalIF":3.6,"publicationDate":"2025-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11096582","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144758484","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
IEEE AccessPub Date : 2025-07-25DOI: 10.1109/ACCESS.2025.3592759
Zimo Yuan;Anders Hallén;Mietek Bakowski
{"title":"On the Design of Junction Termination for 4H-SiC High-Voltage Devices","authors":"Zimo Yuan;Anders Hallén;Mietek Bakowski","doi":"10.1109/ACCESS.2025.3592759","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3592759","url":null,"abstract":"Junction termination design has become a crucial process in ultrahigh-voltage 4H-SiC device design since it enhances the reliability and ensures that the device can reach the designed breakdown voltage. In this work, we review the blocking performances, fabrication considerations and area efficiencies of several typical termination structures widely used for ultrahigh-voltage 4H-SiC devices, and aim to optimize the termination design of next generation devices, focusing on improved termination efficiency, simultaneous design of breakdown voltage and surface field without introducing extra fabrication complexity and costs. The relationship between area efficiency, surface electric field and breakdown voltage is first described, indicating that improving the uniformity of electric field at the SiC/oxide interface is essential to improve the area efficiency. A buried termination structure, where implanted zones are buried under a thin field buffer layer is proposed to obtain a nearly rectangular field distribution at the SiC/oxide interface. The termination pattern is then directly scaled without any iterative design process to optimize the termination area, and the simulation results show that the field distribution can be mostly preserved. Optimization and limitations that are related to fabrication and design considerations are also addressed in the end.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"132659-132669"},"PeriodicalIF":3.6,"publicationDate":"2025-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11096605","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144750868","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
IEEE AccessPub Date : 2025-07-25DOI: 10.1109/ACCESS.2025.3592797
Fábio Mendonça;Sheikh Shanawaz Mostafa;Fernando Morgado-Dias;Antonio G. Ravelo-García;Mário A. T. Figueiredo
{"title":"ProBoost: Reducing Uncertainty Using a Boosting Method for Probabilistic Models","authors":"Fábio Mendonça;Sheikh Shanawaz Mostafa;Fernando Morgado-Dias;Antonio G. Ravelo-García;Mário A. T. Figueiredo","doi":"10.1109/ACCESS.2025.3592797","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3592797","url":null,"abstract":"Uncertainty analysis of classification or regression models is a key feature of probabilistic approaches to supervised learning, allowing the assessment of how trustworthy predictions are. Just as boosting algorithms aim at obtaining accurate ensembles of simple classifiers, using a process guided by the accuracy of each of these classifiers, the method proposed in this paper builds an ensemble guided by the uncertainty of each of its individual models. The proposed method, named ProBoost (probabilistic boosting), uses the epistemic uncertainty of each training sample to determine those about which each model is most uncertain; the importance of these samples is then increased for the next learner, producing a sequence that progressively focuses on samples found to have the highest uncertainty. In the end, the learned models are combined into an ensemble. Thus, the approach goes beyond standard boosting methods, which usually focus on deterministic error correction, by quantifying predictive uncertainty to guide sequential training through dataset manipulation. Three methods are proposed to update the importance of the samples according to the uncertainty estimates at each stage: undersampling, oversampling, and weighting. Furthermore, two approaches are studied regarding the final ensemble combination. The learners herein considered are standard convolutional neural networks, and the probabilistic models underlying the uncertainty estimation use either variational inference or Monte Carlo dropout. The experimental evaluation carried out on MNIST and CIFAR 10 benchmark datasets shows that ProBoost yields significant performance improvement, compared to not using ProBoost, and outperforms a wider single model with a similar number of parameters.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"132006-132021"},"PeriodicalIF":3.6,"publicationDate":"2025-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11096562","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144751010","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
IEEE AccessPub Date : 2025-07-25DOI: 10.1109/ACCESS.2025.3592699
Hongtao Wang;Li Gong
{"title":"Heterogeneous AI Music Generation Technology Integrating Fine-Grained Control","authors":"Hongtao Wang;Li Gong","doi":"10.1109/ACCESS.2025.3592699","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3592699","url":null,"abstract":"As artificial intelligence algorithms continue to advance, researchers have increasingly harnessed their capabilities to generate music that resonates with human emotions, offering a novel means of alleviating the escalating pressures of contemporary life. To tackle the persistent issue of low accuracy in current emotion recognition and music generation systems, an innovative approach was proposed that fused a graph convolutional neural network with a channel attention mechanism for emotion recognition. This integrated model was subsequently paired with a Transformer architecture, creating a sophisticated framework capable of fine-grained control and heterogeneous music generation. In comparing the performance of the emotion recognition model against other leading models, the results underscored its exceptional accuracy across five distinct electroencephalogram signal bands: 97.3%, 95.8%, 96.9%, 98.4%, and 97.6%, respectively. Crucially, all these accuracy metrics exceeded the 95% benchmark, clearly demonstrating superiority over the comparative models. Additionally, a rigorous performance assessment was conducted to evaluate the music generation model’s capabilities against alternative approaches. The findings revealed that the suggested model achieved an average mean square error of 0.27 and an average root mean square error of 0.24. These error rates were notably lower than those of the competing models, highlighting the enhanced precision and fidelity of the music generated. Together, these results validated the effectiveness of both the emotion recognition and music generation models developed in this research. This research not only propelled the existing frontiers of emotion detection and musical composition forward, but also laid a robust theoretical framework to facilitate subsequent investigations into the emerging field of emotion-aware music generation.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"132870-132883"},"PeriodicalIF":3.6,"publicationDate":"2025-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11096601","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144751056","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
IEEE AccessPub Date : 2025-07-25DOI: 10.1109/ACCESS.2025.3592792
Ahmad Naderi;Robert Keilmann;Arsham Asgari;Abbas Mehraban;Regine Mallwitz;Markus Henke;Michael Terörde
{"title":"System-Wide Analysis of Electric Power System for a Reference Short-Range Electrified Aircraft","authors":"Ahmad Naderi;Robert Keilmann;Arsham Asgari;Abbas Mehraban;Regine Mallwitz;Markus Henke;Michael Terörde","doi":"10.1109/ACCESS.2025.3592792","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3592792","url":null,"abstract":"This study investigates the electrification of a reference short-range passenger aircraft, focusing on optimizing the Electric Power System (EPS). An iterative optimization method is employed to identify the optimal specifications for individual EPS components, considering gravimetric and volumetric power densities and efficiency as single objectives. The study introduces a structured, decoupled optimization framework that isolates the impact of each design variable on weight, volume, and efficiency, providing clearer insights into system-level trade-offs and offering a novel perspective for EPS design. By incorporating component characteristics into the design process, optimal configurations are achieved. Results indicate that certain motor designs enhance EPS performance by reducing weight, increasing efficiency, or minimizing volume, depending on the optimization objective. Similarly, during the optimization process and selection of power electronics configurations, certain topologies demonstrated superior efficiency, while others excelled in different performance criteria. In transmission line selection, superconducting cables are more efficient than conventional cables in minimizing electrical losses at lower voltages, despite being bulkier. Conversely, conventional cables are more advantageous at higher voltage levels due to their lighter weight. Moreover, modular and scalable circuit breakers are recommended for their adaptability across varying voltage levels. The optimization results are further supported by sensitivity analyses that reveal the influence of voltage level, shaft power, and cable technology on overall system metrics. Additionally, feasibility assessments benchmarked against a conventional ATR-72 propulsion system highlight the current limitations of battery integration and the challenging energy density requirements for full electrification.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"134172-134188"},"PeriodicalIF":3.6,"publicationDate":"2025-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11096568","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144758214","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
IEEE AccessPub Date : 2025-07-25DOI: 10.1109/ACCESS.2025.3592712
Seyed Alireza Bashiri Mosavi;Omid Khalaf Beigi
{"title":"Designing a Four-Group Permutational Hybrid Feature Selection Scheme for Transient Stability Prediction Based on Multivariate Trajectory Data","authors":"Seyed Alireza Bashiri Mosavi;Omid Khalaf Beigi","doi":"10.1109/ACCESS.2025.3592712","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3592712","url":null,"abstract":"Collecting the optimal transient features (OTFs) from multivariate transient time series data is crucial for ensuring precise and prompt transient analysis (TA) in power systems. Realizing the OTFs requires designing a comprehensive hybrid feature selection scheme (FSS). Hence, this work offers a four-group permutational hybrid FSS called FGPHFSS to select OTFs from transient trajectory data. The FGPHFSS includes four hybrid FSS (4HFSS) groups decorated by filter-wrapper mechanisms. The two 4HFSS groups comprise a relevance-based filter and another two 4HFSS groups derived from a conditional relevance-based filter. The 4HFSS groups includes incremental wrapper methods namely incremental wrapper subset selection (IWSS) and IWSS with replacement (IWSSr), which are fed by the support vector machine (SVM) and twin SVM (TWSVM) classifiers. The nonlinear space of transient data causes the SVM and TWSVM to be equipped with elastic and non-elastic kernels. Generally, we have <inline-formula> <tex-math>$mathop {{}_{text {TWSVM}}^{text {SVM}} textrm {IWSS}_{text {RBF/POL}}^{text {RBF/DTW}}}limits ^{text {Relevance}}$ </tex-math></inline-formula>, <inline-formula> <tex-math>$mathop {{}_{text {TWSVM}}^{text {SVM}} textrm {IWSSr}_{text {RBF}/text {POL}}^{text {RBF/DTW}} }limits ^{text {Relevance}}$ </tex-math></inline-formula>, <inline-formula> <tex-math>$mathop {{}_{text {TWSVM}}^{text {SVM}} textrm {IWSS}_{text {RBF/POL}}^{text {RBF/DTW}}}limits ^{text {Cond. Relevance}}$ </tex-math></inline-formula>, and <inline-formula> <tex-math>$mathop {{}_{text {TWSVM}}^{text {SVM}} textrm {IWSSr}_{text {RBF/POL}}^{text {RBF/DTW}}}limits ^{text {Cond. relevance}}$ </tex-math></inline-formula>, which are permuted in a 24-way manner. After selecting OTFs, the OTFs’ performance in transient stability prediction (TSP) is evaluated by a cross-validation technique. The results show that FGPHFSS has a prediction accuracy of 99 % and a processing time of 101.819 milliseconds for TSP.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"132022-132037"},"PeriodicalIF":3.6,"publicationDate":"2025-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11096534","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144750987","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
IEEE AccessPub Date : 2025-07-25DOI: 10.1109/ACCESS.2025.3592674
Yukai Wei;Chun He;Zhuo Chen;Yinyuan Guo;Zongyuan Li
{"title":"Optimal Autonomous Control for Distribution Transformer Area With High Photovoltaic Penetration Based on CSBO-LSTM","authors":"Yukai Wei;Chun He;Zhuo Chen;Yinyuan Guo;Zongyuan Li","doi":"10.1109/ACCESS.2025.3592674","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3592674","url":null,"abstract":"With the large-scale deployment of distributed photovoltaic (PV) and energy storage system (ESS) in distribution network transformer area, problems such as low management efficiency and difficult collaborative regulation have become increasingly prominent. To enhance the autonomous control capability of transformer area with high PV penetration, this paper proposes a “data-model” dual-driven collaborative optimization model that integrates the Circulatory System Based Optimization (CSBO) algorithm and Long Short-Term Memory (LSTM), constructing an architecture of “offline optimization-knowledge migration-online inference”. The model takes maximizing PV power consumption as the core objective, while considering voltage stability regulation and minimum network loss, to construct a multi-objective optimization function. Firstly, the improved CSBO is used to solve the multi-objective optimization problem, accurately formulate the PV reactive power regulation and ESS charging/discharging strategies, and generate the optimal operation dataset of the transformer area through multi-scenario simulation. Furthermore, leveraging the advantage of LSTM in processing time-series data, a real-time response model is constructed through deep training to achieve rapid perception of grid status and dynamic control decisions. Experimental results show that the model maintains the voltage of the transformer area near 1.00 p.u., while significantly reducing network losses. The organic combination of CSBO and LSTM effectively improves data completeness construction, model complexity control, and real-time decision response, providing new ideas and implementation solutions for the autonomous control of transformer areas with high PV penetration.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"132793-132803"},"PeriodicalIF":3.6,"publicationDate":"2025-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11096587","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144751011","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
IEEE AccessPub Date : 2025-07-25DOI: 10.1109/ACCESS.2025.3592776
Xunting Yang;Yifeng Xu;Yuhang Dou;Miao Zhang
{"title":"A Dual-Linearly-Polarized Center-Fed Quadrifilar Helix Antenna Loaded With Reverse Helices","authors":"Xunting Yang;Yifeng Xu;Yuhang Dou;Miao Zhang","doi":"10.1109/ACCESS.2025.3592776","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3592776","url":null,"abstract":"This paper proposes a dual-linearly-polarized (DLP) center-fed quadrifilar helix antenna (CF-QHA) loaded with reverse helices. It features a small transverse area, hollow-core structure, enhanced bandwidth, high cross-polarization discrimination (XPD), and high gain. The proposed antenna comprises two pairs of diagonal helical arms along ±45° directions. By changing the feeding point to the center of each helical arm, the center feed mechanism is introduced first to improve the impedance matching, compared with the previous end-fed DLP-QHA. Loading reverse helices with the CF-QHA in parallel further enhances the XPD performance. In addition, each pair of diagonal helical arms employs a differential feed to ensure LP radiations and high isolation. For demonstration, a prototype is fabricated and tested. According to the measured results, the 10-dB return loss bandwidths of the proposed ±45° DLP CF-QHA respectively range over <inline-formula> <tex-math>$2.13-2.68$ </tex-math></inline-formula> GHz (22.87%) and <inline-formula> <tex-math>$2.1-2.69$ </tex-math></inline-formula> GHz (24.63%), where XPDs higher than 21 dB and isolation better than 24 dB are achieved. The DLP CF-QHA is expected to provide the industry with more design options in base station applications.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"132146-132154"},"PeriodicalIF":3.6,"publicationDate":"2025-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11096590","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144751109","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"An AI-Based Decision Support Framework for Clinical Screening of Iron Deficiency Anemia and Thalassemia","authors":"Kasikrit Damkliang;Thakerng Wongsirichot;Komsai Suwanno;Chutima Cheranakhorn;Sorawat Sangkeaw;Satanun Sottisataworn","doi":"10.1109/ACCESS.2025.3592652","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3592652","url":null,"abstract":"Iron deficiency anemia (IDA) and thalassemia (THL) are common hematological disorders that necessitate efficient and accurate screening for early diagnosis. Traditional blood smear analysis is labor-intensive, prone to subjectivity, and lacks reproducibility, highlighting the urgent need for AI-driven methods to improve diagnostic sensitivity and specificity. This study proposes a novel hybrid AI framework for patient-level classification, integrating soft voting with optimized probability-based thresholds. The model was trained and validated using a real-world dataset from Hatyai Hospital, Thailand, and evaluated at both the patch and patient levels. The proposed approach achieved 96% accuracy on the test set. Specifically, it yielded precision-recall values of 1.00 and 0.83 for IDA, and 0.95 and 1.00 for THL, respectively. At the patient level, sensitivity reached 1.00 for THL and 0.83 for IDA. Bayesian probability updates further confirmed prediction reliability, yielding post-test probabilities exceeding 99.99% for IDA and 80% for THL. The model explained 62.84% of the variance in patient classifications, demonstrating strong discriminatory power. Model interpretability, assessed using SHAP and Grad-CAM, highlighted key red blood cell morphological features. The proposed framework thus serves as a cost-effective screening tool. Limitations include the use of a single-center dataset and the need for adaptive threshold optimization. Future work will focus on multi-center validation and real-world clinical integration. This study thereby establishes a structured baseline for AI-assisted hematology screening, fostering early detection and improved clinical decision-making in resource-limited settings.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"133937-133957"},"PeriodicalIF":3.6,"publicationDate":"2025-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11096537","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144758317","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"A Fluid Mixing Benchmark for Anomaly Detection in CPS With Real and Simulated Data","authors":"Malte Ramonat;Bernd Zimmering;Silke Merkelbach;Felix Gehlhoff;Oliver Niggemann;Alexander Fay","doi":"10.1109/ACCESS.2025.3592815","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3592815","url":null,"abstract":"Ensuring the safety and reliability of Cyber-Physical Systems requires effective anomaly detection. However, research in this field is often limited by the lack of publicly available benchmark datasets that accurately capture real-world system behavior and provide sufficient documentation. This paper addresses this gap by defining requirements for anomaly detection datasets, evaluating existing benchmarks, and introducing a novel dataset collected from a real-world fluid mixing system augmented with a simulation model. The dataset captures diverse operational states, fault scenarios, and non-linear system dynamics, while the simulation model enables further system understanding. To demonstrate its utility, we apply six state-of-the-art unsupervised anomaly detection models on the dataset. The results confirm the dataset’s suitability for anomaly detection research. To promote reproducibility, we publicly provide the software framework for model implementation, along with the datasets, simulation model, and evaluation results, accompanied by comprehensive documentation.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"134113-134128"},"PeriodicalIF":3.6,"publicationDate":"2025-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11096565","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144758341","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}