Convolutional neural networks, in which each layer receives features from the previous layer(s) and then aggregates/abstracts higher level features from them, are widely adopted for image ...classification. To avoid information loss during feature aggregation/abstraction and fully utilize lower layer features, we propose a novel decision fusion module (DFM) for making an intermediate decision based on the features in the current layer and then fuse its results with the original features before passing them to the next layers. This decision is devised to determine an auxiliary category corresponding to the category at a higher hierarchical level, which can, thus, serve as category-coherent guidance for later layers. Therefore, by stacking a collection of DFMs into a classification network, the generated decision fusion network is explicitly formulated to progressively aggregate/abstract more discriminative features guided by these decisions and then refine the decisions based on the newly generated features in a layer-by-layer manner. Comprehensive results on four benchmarks validate that the proposed DFM can bring significant improvements for various common classification networks at a minimal additional computational cost and are superior to the state-of-the-art decision fusion-based methods. In addition, we demonstrate the generalization ability of the DFM to object detection and semantic segmentation.
Display omitted
•Two-stage data augmentation method is developed, improves deep learning models' performance.•Semantic segmentation in SEM fractographic analysis marks new phase in this ...field.•SegFormer accurately segments complex fracture patterns, outperforming UNet, DeepLabV3+.
Fractographic analysis poses a significant challenge for field researchers without specialized training in fractography. To address this issue, this study introduces a comprehensive integrated workflow that encapsulates the entire process from dataset preparation and data enhancement to leveraging the SegFormer model for deep learning-driven semantic segmentation. An extensive collection of fractography images is formulated and augmented to train the SegFormer model, enabling precise semantic segmentation of morphological fracture regions including cleavage, ductile, dimple, fatigue striations, and others. To accommodate the demanding SEM imaging conditions which frequently include distortions, noise, and aberrations, we developed a two-stage method with diverse data augmentation strategies. This method resulted in a robust model demonstrating exceptional performance, as evidenced by a high mean Intersection over Union (mIOU) score of 59.7 and other metrics. The findings validate the potential of deep learning techniques, particularly the SegFormer model's efficacy in morphological fractography image segmentation for the first time. Our work offers a cost-effective, and efficient alternative deep learning approach to traditional experimental fracture analysis, thereby expanding opportunities for a broader range of professionals in the engineering domain.
The integration of healthcare monitoring with Internet of Things (IoT) networks radically transforms the management and monitoring of human well-being. Portable and lightweight electroencephalography ...(EEG) systems with fewer electrodes have improved convenience and flexibility while retaining adequate accuracy. However, challenges emerge when dealing with real-time EEG data from IoT devices due to the presence of noisy samples, which impedes improvements in brainwave detection accuracy. Moreover, high inter-subject variability and substantial variability in EEG signals present difficulties for conventional data augmentation and subtask learning techniques, leading to poor generalizability. To address these issues, we present a novel framework for enhancing EEG-based recognition through multi-resolution data analysis, capturing features at different scales using wavelet fractals. The original data can be expanded many times after continuous wavelet transform (CWT) and recombination, alleviating insufficient training samples. In the transfer stage of deep learning (DL) models, we adopt a subtask learning approach to train the recognition model to generalize efficiently. This incorporates wavelets at various scales instead of exclusively considering average prediction performance across scales and paradigms. Through extensive experiments, we demonstrate that our proposed DL-based method excels at extracting features from small-scale and noisy EEG data. This significantly improves healthcare monitoring performance by mitigating the impact of noise introduced by the external environment.
•Effects of microstructure and defect on fatigue behavior in Ti-6Al-4V is quantitatively characterized.•A modelling strategy is designed to highlight notch morphology/orientation effect in ...Ti-6Al-4V.•Roundness for notch morphology is linearly correlated with fatigue accumulation around defect.•Corner angle defined for notch orientation reflects the heterogeneous features of microstructure.
Fatigue accumulation in dual-phase Ti-6Al-4V is strongly associated with the combined effects of microstructure and defects in itself, which is experimentally challenging to be characterized and quantified. Based on crystal plasticity finite element method (CPFEM), the present work aims to address the coordinated effect of microstructure and defect on fatigue behavior in Ti-6Al-4V, highlighting the influence of morphology and orientation of defects, in conjunction with the designated idealized microstructure. In light of these considerations, a modelling strategy is proposed to focus on defect morphology and orientation in polycrystalline RVE models. Firstly, the geometric roundness parameter is adopted to characterize the diverse defect morphology and is quantitatively correlated with the characteristic of fatigue accumulation in Ti-6Al-4V. Secondly, a liner relationship with respect to corner angle and plastic deformation is formulated to characterize the influence of defect orientation, reflecting the microstructural heterogeneity in dual-phase Ti-6Al-4V. The proposed modelling strategy overcomes the experimental limitation on characterizing the complex effect of microstructure and defect, holding the potential of revealing fatigue mechanism around defects in metal alloys.
Graph-based unsupervised feature selection algorithms have been shown to be promising for handling unlabeled and high-dimensional data. Whereas, the vast majority of those algorithms usually involve ...two independent processes, i.e., similarity matrix construction and feature selection. This incurs a poor similarity matrix that is obtained from original data, which retains constant for the following feature selection process and heavily affects the corresponding performance. Aiming to integrate these two processes into a unified framework, this paper proposes a novel unsupervised feature selection algorithm, named Graph Learning Unsupervised Feature Selection (GLUFS) to ensure the two processes proceed simultaneously. In particular, a new similarity matrix is derived from the original one, while the new matrix can adaptively maintain the manifold structure of data. Due to the fact that good individual features do not necessarily guarantee efficient combinations, the GLUFS algorithm adopts the ℓ2,0-norm sparsity constraint to achieve group feature selection. Eventually, we perform experiments on six public datasets with sufficient analysis, while the obtained results illustrate the effectiveness and superiority of our GLUFS over the considered algorithms.
•Coordinated effects of LM and microdefect on fatigue behavior of Ti-6Al-4V is studied.•A weight approach is proposed to account for intragranular accumulative deformation.•Parametric ADI is defined ...to relatively quantify the lamellar microstructural effect.•Increase of β lath and synchronized refinement of intragranular LM improve LM effect.
Fatigue performance of metal alloys is inseparably associated with heterogenous microstructure and existing microdefects. The coordinated effects of lamellar microstructure (LM) and microdefect on fatigue performance of bimodal Ti-6Al-4V is studied within the framework of CPFEM. We propose an intragrain weight integration approach able to account for intragranular accumulative deformation. Parametric accumulative difference indicator (ADI) for stress is defined to relatively quantify the lamellar microstructural effect, overcoming the limitations of experimental procedures. The results demonstrate that the increase of β lath and synchronized refinement of LM appreciably improve lamellar microstructural effect. These attributes can be applied to the material design and manufacturing of advanced metal alloys.
Investigating fatigue failure in titanium alloys is crucial for material design and engineering. Fatigue behavior in dual‐phase titanium alloys is strongly correlated with microstructural features ...and microdefects. This work formulates an improved modeling method to investigate fatigue behavior of bimodal Ti–6Al–4V, emphasizing the effects of lamellar orientation and microdefects. Using an improved Voronoi tessellation method, we establish representative volume element (RVE) models with various grain size distributions. Crystal plasticity finite element modeling (CPFEM) is used to analyze fatigue deformation in bimodal Ti–6Al–4V, considering microdefects and lamellar orientation. Fatigue indicator parameters are then incorporated into CPFEM to predict fatigue life and verified with experimental data. Numerical results highlight the significant influence of lamellar orientation and microdefects on fatigue behavior, with predicted life within the 3‐error band. This method efficiently overcomes challenges in quantitatively characterizing microstructural lamellae that experiments are short of, paving the way for designing fatigue‐resistant alloy materials with similar microstructures.
Highlights
The proposed method effectively addresses the effects of lamellar orientation and microdefects.
The improved VT modeling can reflect grain size distribution in bimodal Ti–6Al–4V.
CPFEM‐based modeling method achieves acceptable fatigue life prediction accuracy.
Many works have shown that the adversarial examples being generated on a known substitute model have the ability to mislead other unknown black-box models, which has attracted widespread attention. ...Recently, many model augmentation methods have been presented to boost the corresponding transferability of adversarial examples by transforming the images to simulate diverse models for attack. However, existing model augmentation methods focus on the transformations in a single domain and may restrict the diversity of simulated models. To overcome this limitation, we present a novel model augmentation method named Hybrid Augmentation Method (HAM). Our approach comprises two components, channel-wise scaling (CS) and spectrum masking (SM). Specifically, we first transform the images with CS in the spatial domain, which enhances the diversity of transformed images by randomly scaling the channel. Then we apply SM to randomly remove some frequency information of the images in the frequency domain, further increasing the diversity of the transformed images. Instead of confining the transformations in a single domain, we take transformations both in the spatial and frequency domain simultaneously. This enables us to get more various transformed images and largely increases the diversity of simulated models to create more powerful adversarial examples. We conduct extensive experiments to demonstrate the superiority of our method on both undefended and defense models, which largely outperforms the considered attacks. Moreover, our method can be integrated with other attacks to further enhance the adversarial transferability.
Abstract Microstructural defects and inhomogeneity of titanium alloys fabricated by additive manufacturing technology make their fatigue performance much more complicated, especially reflected in the ...dispersion of fatigue life. This work employs crystal plasticity finite element method (CPFEM) to predict high cycle fatigue (HCF) life of bi-lamellar Ti-6Al-4V alloy. We first propose a modified VT technique to build representative volume element (RVE) models highlighting lamellar microstructure and micro-defects. Subsequently, fatigue indicator parameter (FIP) is adopted to analyse fatigue deformation under cyclic loading. Finally, HCF life determined by critical fatigue indicator parameter is compared with experimental data collected from published literatures. The results demonstrate that our approach is able to reflect the dispersion of fatigue life and to predict HCF life of bi-lamellar Ti-6Al-4V in a satisfactory manner.