Saved Queries

Signals with flexible control over polarity and frequency provide an essential foundation for reliable and high-speed information transmission. To generate chaotic signals with flexible output characteristics in low-dimensional systems, a novel chaotic system model is proposed by introducing a nonlinear term into the classical Chen chaotic system. Dynamical analysis and MATLAB numerical simulations show that the system is not only highly sensitive to initial conditions but also capable of generating three distinct chaotic attractors. Further simulations confirm that the proposed system demonstrates arbitrary unidirectional and multidirectional offset boosting behaviors, with offset amplitudes in all directions having a wide adjustable range. Furthermore, arbitrary offset constants can effectively control the frequencies of all state variables. This chaotic system, which combines flexible offset control with frequency regulation, is rare in existing research. Additionally, certain parameter ranges in the chaotic regime are relatively narrow. To address this, a method involving control constants to enhance system complexity is proposed, and its effectiveness in increasing system complexity is validated through Lyapunov spectrum and spectral entropy (SE) analysis. Based on the constructed chaotic system, an equivalent circuit model was built using the Multisim 14.0 platform. Experimental results confirm that the system generates chaotic attractors with distinct structures and demonstrates offset boosting behavior in arbitrary directions. Additionally, DSP hardware experiments further validate the physical realizability of the system. To fully exploit the system’s advantages, a synchronization controller was designed for both the drive and response systems, enabling synchronization control of the chaotic system with three offset constants. Based on this, data encryption and transmission experiments were conducted, further establishing the theoretical and experimental foundation for applying the new chaotic system in secure communication. Full article

(This article belongs to the Special Issue Nonlinear Dynamics of Complex Systems)

►▼ Show Figures

Figure 1

15 pages, 4491 KB

Open AccessReview

Research Advances of Carica papaya in Agriculture, Food Science, and Bioactive Compounds: A Bibliometric Study

by Juan Daniel Cruz-Castillo, Thelma Beatriz González-Castro, Germán Alberto Nolasco-Rosales, David Ruiz-Ramos, Ghandy Isidro Juárez-De la Cruz, Alma Mileira Zetina-Esquivel, Diana María Dionisio-García, Crystell Guadalupe Guzmán-Priego, Viridiana Olvera-Hernández, Jorge Luis Ble-Castillo, Manasés González-Cortazar and Isela Esther Juárez-Rojop

Horticulturae 2026, 12(3), 282; https://doi.org/10.3390/horticulturae12030282 (registering DOI) - 27 Feb 2026

Abstract

Studies on Carica papaya have focused on addressing challenges in cultivation, postharvest management, and its medicinal properties. Given the extensive volume of information produced, a quantitative analysis is required to clarify the intellectual framework of C. papaya research. This study aims to delineate the scientific landscape of C. papaya, identify research trends in agriculture and food science, and analyze correlations between secondary metabolites and bioactivities using bibliometric analysis. Our analysis examined 6546 documents from 1737 journals, consisting of 6076 articles, 379 reviews, and 91 conference papers. The United States, India, Brazil, and China lead scientific production and maintain robust international partnerships. The main research domains were applied sciences (40.9%), analytical studies (36.6%), and experimental research (16.9%), with topics including postharvest quality, disease resistance, genomic sequencing, and biological activities. A co-occurrence analysis revealed an association between polar leaf extracts and phenolic and flavonoid compounds, which are linked to antioxidant, anticancer, and antimicrobial activities. Furthermore, antioxidant activity was the most frequent finding (945 articles). In conclusion, scientific knowledge of C. papaya primarily comprises studies on the plant genome, crop diseases, and bioactive compounds. Research highlights the plant as a valuable resource for sustainable agriculture, specifically its leaves as a source of novel phytopharmaceuticals. Full article

(This article belongs to the Section Medicinals, Herbs, and Specialty Crops)

►▼ Show Figures

Graphical abstract

15 pages, 282 KB

Open AccessArticle

Does Digital Finance Foster Financial Stability? Empirical Evidence from Cross-Country Analysis

by Md. Nur Alam Siddik, Muzafar Shah Habibullah, Sajal Kabiraj and Shakib Hassan Rakib

Economies 2026, 14(3), 72; https://doi.org/10.3390/economies14030072 (registering DOI) - 27 Feb 2026

Abstract

The World Bank asserts that reducing extreme poverty and achieving shared prosperity are both made possible through financial inclusion. Digital finance may enhance financial stability, thereby supporting more inclusive and sustainable economic growth. Despite its potential benefits, the link between digital finance and financial stability remains underexplored in the literature. The present study addresses this research gap in the literature by exploring the relationship between digital finance and financial stability. Panel data of 160 countries over the period of 2004–2024 have been collected and analyzed by using Moment Quantile Regression (MMQREG). The robust outcomes show that digital finance significantly improves financial stability. This study aims to contribute to the existing literature. The findings of this study will help policymakers in designing effective or supportive policies for digital financial services. Findings may inform policies aligned with SDG 8: promote sustained, inclusive, and sustainable economic growth. Full article

35 pages, 1483 KB

Open AccessReview

Cross-Study Machine Learning Analysis of Structure–Property–Performance Relationships in Macroporous PolyHIPE-Based Magnetic Polymer Composites

by Carolina L. Recio-Colmenares, Roxana B. Recio-Colmenares and César A. García-García

J. Compos. Sci. 2026, 10(3), 128; https://doi.org/10.3390/jcs10030128 (registering DOI) - 27 Feb 2026

Abstract

Elucidating the complex structure–property–performance relationships in multifunctional polymer matrix composites (PMCs) remains a formidable challenge. This difficulty stems from the intricate coupling between formulation variables, porous morphology, physicochemical attributes, and functional outcomes, particularly under the “small-data” constraints inherent to experimental materials research. This study introduces a robust, interpretable machine learning (ML) framework tailored for the analysis of macroporous polyHIPE-based magnetic composites. All analyses were conducted exclusively on curated experimental data reported in the literature. By leveraging a curated dataset synthesized from multiple independent studies with harmonized characterization protocols, we integrated processing parameters and quantitative morphological descriptors to predict two critical engineering outputs: dye removal efficiency (%) and saturation magnetization (M_s). Nonlinear ensemble ML models were rigorously trained and evaluated using repeated cross-validation and cross-study validation strategies to ensure predictive robustness and domain transferability. The superior performance of nonlinear models over linear baselines underscores that composite functionality is governed by synergistic, non-additive interactions. Model-agnostic interpretability analyses further revealed that pore interconnectivity and accessible surface area are the primary determinants of adsorption performance. Conversely, while increased magnetic nanoparticle loading enhances magnetic responsiveness, it induces a significant trade-off with adsorption efficiency. These findings demonstrate that uncertainty-aware ML can extract generalizable, physically grounded design insights from heterogeneous experimental literature, providing a streamlined, data-driven pathway for the rational design and screening of multifunctional porous materials without necessitating additional experimental overhead. Full article

(This article belongs to the Special Issue Hybrid Composites—from Fundamental Studies to Intelligent and Sustainable Solutions)

►▼ Show Figures

Figure 1

20 pages, 629 KB

Open AccessArticle

A Hybrid Approach to Universal Intrusion Detection Systems for Automotive Security

by Md Rezanur Islam, Mahdi Sahlabadi, Munkhdelgerekh Batzorig and Kangbin Yim

Sensors 2026, 26(5), 1489; https://doi.org/10.3390/s26051489 (registering DOI) - 27 Feb 2026

Abstract

Security measures are essential in the automotive industry to detect intrusions in-vehicle networks. However, developing a one-size-fits-all intrusion detection system (IDS) is challenging because each vehicle has a unique data profile. This is due to the complex and dynamic nature of the data generated by vehicles regarding their model, driving style, test environment, and firmware update. To address this issue, a universal IDS has been developed that can be applied to all types of vehicles without the need for customization. Unlike conventional IDSs, the universal IDS can adapt to data distribution shifts caused by changes in driving style, vehicle platform, or firmware updates. In this study, a new hybrid approach has been developed, combining Pearson correlation with deep learning techniques. This approach has been tested using data obtained from four distinct mechanical and electronic vehicles, including Tesla, Sonata, and two Kia models. The data has been combined into two frequency datasets, and wavelet transformation has been employed to convert them into the frequency domain, enhancing generalizability. Additionally, a statistical method based on independent rule-based systems using Pearson correlation has been utilized to improve system performance. The system has been compared with eight different IDSs, three of which utilize the universal approach, while the remaining five are based on conventional techniques. The accuracy of each system has been evaluated through benchmarking, and the results demonstrate that the hybrid system effectively detects intrusions in various vehicle models. Full article

(This article belongs to the Special Issue Security and Privacy in Connected and Autonomous Vehicles)

►▼ Show Figures

Figure 1

24 pages, 7108 KB

Open AccessArticle

ResUCTransNet: An InSAR Phase Unwrapping Network Combining Residual Structure and Channel Transformer

by Yuejuan Chen, Yu Han, Pingping Huang, Weixian Tan, Zhiguo Wang and Yaolong Qi

Remote Sens. 2026, 18(5), 705; https://doi.org/10.3390/rs18050705 (registering DOI) - 27 Feb 2026

Abstract

Phase unwrapping in interferometric synthetic aperture radar (InSAR) aims to recover a continuous phase field from wrapped observations, which enable accurate topographic reconstruction and surface deformation measurements. With the recent advances in deep learning (DL), several DL-based unwrapping approaches have shown promising performance. However, deep learning networks suffer from inconsistent feature representations between encoder and decoder stages. This leads to incompatible skip connections that provide limited benefits and even degrade reconstruction quality. To overcome this limitation, we propose ResUCTransNet that integrates residual learning with transformer-based feature modeling. The network employs a multi-scale residual backbone derived from Res_UNet to extract stable deep features. Then, to replace conventional skip connections, a channel transformer (CTrans) module is introduced that composed of channel-wise cross fusion transformer (CCT) and channel-wise cross attention (CCA). This design effectively reduces the semantic gap in different network stages, which allows adaptive integration of local CNN features and global transformer representations. Experiments on the public InSAR-DLPU dataset demonstrate that ResUCTransNet effectively reduces model complexity and achieves substantial improvements over existing deep learning models and classical unwrapping algorithms. Specifically, the proposed method attains the best performance in terms of RMSE and SSIM (RMSE = 1.6247, SSIM = 0.7741). Compared with the second-best model, Res_Unet (RMSE = 2.8409, SSIM = 0.7733), ResUCTransNet achieves an approximately 42.8% reduction in RMSE while maintaining nearly identical structural similarity. The proposed method provides higher reconstruction accuracy and better structural fidelity, while maintaining strong robustness and generalization in complex terrain or severe noise conditions. Full article

(This article belongs to the Special Issue Artificial Intelligence Algorithm for Remote Sensing Imagery Processing (5th Edition))

►▼ Show Figures

Figure 1

31 pages, 4771 KB

Open AccessArticle

Benchmark Operational Condition Multimodal Dataset Construction for the Municipal Solid Waste Incineration Process

by Yapeng Hua, Jian Tang and Hao Tian

Sustainability 2026, 18(5), 2282; https://doi.org/10.3390/su18052282 (registering DOI) - 27 Feb 2026

Abstract

Municipal solid waste incineration (MSWI) is a typical complex industrial process for achieving sustainable development of the global environment. It implements the “perception-prediction–control” mode based on domain experts by using multimodal information. To harness the complementary value of different modal data, prevent information conflicts or fusion failures caused by misalignment, and ensure the availability of multimodal datasets and the reliability of analytical conclusions, constructing a benchmark operational condition multimodal dataset is essential. The objective of this work was to create a multimodal reference database for the operational status of IMSW processes. Based on the description of the MSWI process and the analysis of the characteristics of the multimodal data, the process data is first preprocessed under different missing scenarios, missing value processing and outlier processing. Then, single-frame images of the flame video are captured on a minute scale, and the missing combustion lines are quantized by using machine vision technology. Finally, the alignment of combustion line quantization (CLQ) values with the minute time scale of process data is achieved through the multimodal time synchronization module. Taking an MSWI power plant in Beijing as the research object, the combustion flame video and process data under the benchmark operating conditions were collected. The hybrid missing value management strategy combining linear interpolation with the LRDT model improved data integrity, and a spatiotemporal aligned multimodal dataset was constructed. The standardized benchmark operating condition multimodal data was obtained to support combustion state analysis during the incineration process, pollutant generation prediction, and process optimization. Therefore, the objectives of ‘reduction, harmlessness, and resource utilization’ of municipal solid waste, addressing land resource shortages, protecting the ecological environment, and promoting the dual carbon goal can be supported. Additionally, data and technical support for environmental and urban sustainable development are provided. Full article

(This article belongs to the Section Waste and Recycling)

►▼ Show Figures

Figure 1

18 pages, 12792 KB

Open AccessArticle

Exact Solution and Large-Scale Scaling Analysis of the Imaginary Creutz–Stark Ladder

by Yunyao Qi, Heng Lin, Quanfeng Lu, Dan Long, Dong Ruan and Gui-Lu Long

Entropy 2026, 28(3), 259; https://doi.org/10.3390/e28030259 (registering DOI) - 27 Feb 2026

Abstract

We present an analytical solution for the complex spectrum of a Creutz ladder subject to an imaginary Stark potential. By mapping the system to a momentum-space differential equation, we derive the closed-form solution for the momentum-space wavefunctions. We identify a distinct cross-shaped spectrum consisting of discrete localized sectors and a continuous branch of asymptotically real states. Our derivation reveals that the discrete sectors arise from a global phase winding condition, whereas the asymptotically real branch emerges when the energy magnitude is smaller than the inter-cell hopping strength, a regime in which the momentum-space wavefunction develops singularities. We demonstrate that these singularities prevent standard quantization; instead, the open boundary conditions are satisfied via a size-dependent imaginary energy component that regulates the wavefunction decay. To investigate the properties of this branch in the thermodynamic limit, we perform large-scale finite-size scaling analysis up to system sizes

L \sim 10^{9}

. The numerical results confirm the power-law decay of the residual imaginary energy, supporting the asymptotic reality of these states. Furthermore, scaling of the inverse participation ratio and fractal dimension indicates that these states, while exhibiting size-dependent localization in finite systems, evolve into an extended phase in the thermodynamic limit. Our results establish a theoretical framework for understanding spectral transitions in systems with imaginary Stark potentials, with potential realizations in photonic frequency synthetic dimensions. Full article

(This article belongs to the Special Issue Non-Hermitian Quantum Systems: Emergent Phenomena and New Paradigms)

►▼ Show Figures

Figure 1

34 pages, 2271 KB

Open AccessReview

From Selection to Use: Aptamers as Targeting Reagents in Hematology

by Brandon Albert, Fiona Ebanks, Kimia Gharagozloo, Xinying Hai, Raymond Ngu, Sietse Munting and Maureen McKeague

Biomedicines 2026, 14(3), 534; https://doi.org/10.3390/biomedicines14030534 (registering DOI) - 27 Feb 2026

Abstract

Aptamers are synthetic nucleic acid ligands that have been proposed as alternatives to antibodies for targeting molecules and cells. In hematology, most reviews have organized aptamer literature around diseases or technological platforms. This framing has obscured how unevenly different blood cell types have been covered. In this review, we present developed aptamers organized by blood cell lineages. Specifically, we examine aptamers for B cells, T cells, natural killer cells, and red blood cells. This organization revealed a strong concentration on a small set of canonical surface markers and on malignant cell models. A parallel gap appeared in aptamers that distinguish differentiation stages or functional cell states. Within this framework, we evaluated reported applications, design strategies, and experimental use cases alongside persistent limitations in target selection and biological resolution. Our analysis highlighted both practical constraints and conceptual blind spots in current blood-cell-targeting aptamer research. Together, these observations defined a set of clear opportunities for expanding aptamer development toward more state-resolved, biologically informative, and clinically relevant targeting strategies. Full article

(This article belongs to the Section Molecular and Translational Medicine)

►▼ Show Figures

Figure 1

13 pages, 3327 KB

Open AccessArticle

Simplified See-Through Head-Mounted Display Optics with Achromatic Metalens

by Jiaxing Hao, Yuanmeng Xin, Zijun He, Song Liu and Shan Mao

Photonics 2026, 13(3), 229; https://doi.org/10.3390/photonics13030229 - 27 Feb 2026

Abstract

To address the critical challenges of minimizing optical thickness and correcting chromatic aberrations in optically transparent head-mounted displays (HMDs), we propose a folded hybrid design incorporating freeform prisms and a discrete multi-wavelength achromatic metalens. Our approach integrates advanced optical engineering techniques to achieve optimal performance while maintaining compactness. The system leverages a phase-optimized SiNx/SiO₂ metalens combined with ray-tracing-based system optimization, enabling the development of a compact 12 mm thickness OST-HMD featuring an 8 mm exit pupil and a 39° virtual field of view (FOV). Through simulations, we demonstrate that this configuration achieves impressive modulation transfer function (MTF) values exceeding 0.7 at 50 lp/mm for see-through viewing and maintaining MTFs above 0.3 at 30 lp/mm for virtual imaging across wavebands. Simulation results highlight an improvement both in the miniaturization of the HMD while maintaining high resolution and in effective correction of chromatic aberrations, offering a robust solution for lightweight, high-performance AR display systems. This work represents an advancement in optically transparent display technology by providing an optimized design framework that balances compactness with visual fidelity. Full article

(This article belongs to the Special Issue Optical Systems and Design)

►▼ Show Figures

Graphical abstract

16 pages, 294 KB

Open AccessArticle

Healthcare Infrastructure and Resource Barriers to Preventing Mother-to-Child Transmission of HIV in Ghana: Insights from a Qualitative Study

by Awinaba Amoah Adongo, Dominic Nabil Bodpii, Robert Kuchengye Mokulogo, Lumbwe Chola and James Akazili

Int. J. Environ. Res. Public Health 2026, 23(3), 293; https://doi.org/10.3390/ijerph23030293 - 27 Feb 2026

Abstract

Background: The prevention of the mother-to-child transmission (PMTCT) of HIV is a vital strategy in reducing paediatric HIV infections. However, the delivery of PMTCT services is frequently impeded by resource constraints within the healthcare systems. This study investigates the systemic barriers affecting PMTCT implementation in Ghana and examines the disconnection between health policy design, priority setting, and on-the-ground realities. Methods: The study employed the qualitative approach using a case study research design. The purposive sampling technique was used in selecting the health facilities, with an in-depth interview guide used to solicit views from healthcare providers and mothers participating in PMTCT services. Braun and Clarke’s thematic analysis was employed in analysing the data on the perceptions of infrastructural and resource-related challenges affecting PMTCT services. Results: Participants identified several key barriers, including the absence of dedicated office spaces, a limited outpatient department (OPD) capacity, inadequate storage for antiretroviral therapy (ART) medications, and shortages of HIV-testing equipment affecting care delivery and access. These issues, alongside workforce limitations and supply chain disruptions, were found to significantly undermine the delivery and effectiveness of PMTCT services. Conclusions: The study underscores the need for context-aware health policy development. Effective priority setting and benefits package design must be informed by frontline insights, taking into account infrastructural deficits, human resource constraints, and systemic bottlenecks. Aligning national initiatives, such as the StEPS programme, with operational realities is essential for enhancing PMTCT outcomes. Full article

30 pages, 3391 KB

Open AccessArticle

Process Mining in Digital Dental Laboratories: Identifying Iterations Through Actions and Digital Artefacts

by Iris Huić, Petar Kosec, Tomislav Martinec and Stanko Škec

Appl. Sci. 2026, 16(5), 2291; https://doi.org/10.3390/app16052291 - 27 Feb 2026

Abstract

Digitalization has reshaped dental laboratory processes through digital tools and artefacts supporting clinician–laboratory collaboration; however, repeated iterations still increase coordination effort and extend delivery times. This study examined how the custom abutment process was executed in a dental laboratory and identified where and why iterations occurred during computer-aided design (CAD) modelling, design verification, and manufacturing preparation. Ten completed orders were selected, and their event log information was analyzed using process mining in Disco, complemented by contextual inquiry with domain practitioners. The analysis reconstructed observed execution from order initiation to delivery and derived a reference representation summarizing the most frequently observed ordering of actions. Across the ten orders analyzed, nine exhibited at least one iteration. Iterations were most frequently observed as returns between CAD modelling and design verification and occurred in four orders, while rescanning occurred in two orders due to insufficient or incompatible initial scan information. Contextual inquiry linked repeated action sequences to changes in digital artefacts and communication exchanges, indicating that iterations were associated with incomplete information or differences in interpretation across roles. The findings show that combining process mining with contextual inquiry enables the identification of iterations and clarifies the conditions under which they emerge. Full article

►▼ Show Figures

Figure 1

19 pages, 3365 KB

Open AccessArticle

Distinction for Quantum Random Number Generators Based on Machine Learning

by Yu Han, Tao Pei and Fengrong Zhang

Electronics 2026, 15(5), 971; https://doi.org/10.3390/electronics15050971 - 27 Feb 2026

Abstract

Randomness is crucial for our understanding of nature and indispensable in information processing tasks. In practical applications, assessing the quality of random numbers is crucial—particularly in cryptographic applications, where random numbers must exhibit statistical uniformity. Various statistical estimation methods have been developed to test the statistical characteristics of generated random numbers, enabling comprehensive evaluation of their statistical uniformity from multiple perspectives. Despite recent advances in quantum information providing physically well-characterized models for randomness quantification, distinction between different types of random numbers (including quantum random numbers) remains a challenging task, and statistical uniformity is rarely directly applicable to such discrimination scenarios. With the development of artificial intelligence technologies, the problem of random number discrimination is expected to draw on the paradigm of image classification in computer vision. This research proposes a machine learning-based randomness discrimination method, specifically addressing the challenge of quantum random number identification. Specifically, we design an image-based convolutional neural network (CNN) approach: one-dimensional random number sequences are converted into two-dimensional grayscale images, and binary classification of these images is achieved by capturing high-dimensional latent features that are undetectable via traditional statistical tests, thereby enabling effective random number discrimination. Experimental results demonstrate that, for the selected quantum random numbers, the proposed discrimination method successfully achieves two key distinctions: (1) between raw quantum random numbers and classical random numbers; and (2) between raw quantum random numbers and post-processed quantum random numbers—additionally revealing the role of statistical uniformity in these discrimination tasks. This achievement provides significant support for the design of randomness extraction protocols and the security assessment of quantum random number generators. Full article

(This article belongs to the Topic Quantum Information and Quantum Computing, 2nd Volume)

►▼ Show Figures

Figure 1

24 pages, 525 KB

Open AccessSystematic Review

Gender Diversity and Psychosocial Work Risks from a Non-Binary Perspective: A Systematic Review

by Abel Perez-Gonzalez, Ferdinando Tuscani, Raul Pelagaggi and Mohamed Nasser

Merits 2026, 6(1), 6; https://doi.org/10.3390/merits6010006 - 27 Feb 2026

Abstract

This systematic review examines how gender shapes exposure to and experiences of psychosocial risks in the workplace. Drawing on 89 empirical studies published between 2010 and 2024, the review synthesizes evidence from occupational health psychology, gender studies, and organizational research. Searches were conducted in PubMed, Web of Science, Scopus, CINAHL, and PsycINFO, and included empirical studies published in English and Spanish. Following PRISMA guidelines, a qualitative thematic synthesis was conducted to integrate findings across diverse sectors, populations, and methodological approaches. The evidence reveals persistent gendered patterns in psychosocial risk exposure and outcomes: women are more frequently exposed to emotionally demanding and relational forms of work and report poorer mental health outcomes; men experience performance-driven strain linked to workload, competition, and reward insecurity more often; and transgender and non-binary workers face additional psychosocial burdens associated with stigma, discrimination, and minority stress. Across the literature, structural and cultural determinants—such as occupational segregation, unequal recognition, and gendered organizational norms—emerge as central mechanisms underlying these disparities. Theoretical frameworks including effort–reward imbalance, demand–control, work–family conflict, organizational climate, and minority stress collectively contribute to explaining how gendered psychosocial risks are produced and sustained. Overall, the review underscores the need to move beyond individualistic and binary models of psychosocial risk toward gender-responsive approaches that account for structural, relational, and identity-based dimensions of work, thereby informing research and organizational strategies aimed at promoting equitable and sustainable well-being at work. Full article

►▼ Show Figures

Graphical abstract

18 pages, 1234 KB

Open AccessArticle

STFF-CANet Diagnosis Model of Aero-Engine Surge Based on Spatio-Temporal Feature Fusion

by Chunyan Hu, Yafeng Shen, Qingwen Zeng, Gang Xu, Jiaxian Sun and Keqiang Miao

Aerospace 2026, 13(3), 212; https://doi.org/10.3390/aerospace13030212 - 27 Feb 2026

Abstract

Aero engine surge diagnosis is a key technology in engine health management, and its diagnostic accuracy is of great significance for ensuring operational safety. Traditional threshold-based diagnostic methods are significantly affected by working conditions, which makes it difficult to achieve full working condition coverage. Moreover, due to issues such as varying feature thresholds across conditions, weak signal characteristics, and low identifiability, the diagnostic accuracy remains limited. To address these challenges, this paper proposes an STFF-CANet (Spatio-Temporal Feature Fusion Cross-Attentional Network) diagnosis model of aero engine surge based on spatio-temporal feature fusion. The model first employs a Convolutional Neural Network (CNN) to extract spatial features from the frequency domain of dynamic signals via Fast Fourier Transform (FFT). Simultaneously, a Bidirectional Long Short-Term Memory (BiLSTM) network is used to capture temporal features from signals optimized by Variational Mode Decomposition (VMD). A cross-attention mechanism is further introduced to achieve deep fusion of spatiotemporal features, thereby enhancing the capability to identify weak fault characteristics. In addition, the sliding window slice method is used to expand the sample size for the small sample fault data of the engine surge of an aero engine. This ensures both informational continuity between slices and statistical stability of features, effectively mitigating the difficulty of diagnosing early and weak surge characteristics under small-sample conditions. Experimental results demonstrate that the model achieves an F1-score, Recall, Precision, and Accuracy of 97.96%, 97.52%, 98.43%, and 99.01%, respectively, in surge fault classification. These outcomes meet the practical requirements for aero engine surge diagnosis and provide an effective solution for early fault warning in complex industrial equipment. Full article

(This article belongs to the Section Aeronautics)

►▼ Show Figures

Figure 1

Show export options Show export options

Select all

Export citation of selected articles as:

Error

Oops... you haven't selected anything for export.

Displaying article 1-50 on page 1 of 2000.

Go to page 1 2 3 4 5

Search Results (281,095)

Further Information

Guidelines

MDPI Initiatives

Follow MDPI