Fusion Performance Research Articles

MEEAFusion: Multi-Scale Edge Enhancement and Joint Attention Mechanism Based Infrared and Visible Image Fusion.

Infrared and visible image fusion can integrate rich edge details and salient infrared targets, resulting in high-quality images suitable for advanced tasks. However, most available algorithms struggle to fully extract detailed features and overlook the interaction of complementary features across different modal images during the feature fusion process. To address this gap, this study presents a novel fusion method based on multi-scale edge enhancement and a joint attention mechanism (MEEAFusion). Initially, convolution kernels of varying scales were utilized to obtain shallow features with multiple receptive fields unique to the source image. Subsequently, a multi-scale gradient residual block (MGRB) was developed to capture the high-level semantic information and low-level edge texture information of the image, enhancing the representation of fine-grained features. Then, the complementary feature between infrared and visible images was defined, and a cross-transfer attention fusion block (CAFB) was devised with joint spatial attention and channel attention to refine the critical supplemental information. This allowed the network to obtain fused features that were rich in both common and complementary information, thus realizing feature interaction and pre-fusion. Lastly, the features were reconstructed to obtain the fused image. Extensive experiments on three benchmark datasets demonstrated that the MEEAFusion proposed in this research has considerable strengths in terms of rich texture details, significant infrared targets, and distinct edge contours, and it achieves superior fusion performance.

Fault detection method for transmission line components based on lightweight GMPPD-YOLO

Abstract This paper designs a lightweight high-precision transmission line component detection model, named grouped dense, monotonic self-regularized, and partial faster convolution, pruning, and distillation optimized—you only look once (GMPPD-YOLO), in transmission line inspection. It addresses the issue of low detection accuracy of target detection algorithms due to the complex background, large differences in target shape, location, texture, etc, as well as diversified and smaller defects in insulator and vibration hammer images taken by unmanned aerial vehicles from multiple angles. To enhance the model’s feature extraction capabilities in complex backgrounds and across different scales, the grouped dense C3 dense feature extraction module was designed, enabling the model to more effectively handle diverse defect forms. Simultaneously, the monotonic self-regularized pyramid pooling–fast (MSPPF) module is proposed to enhance the model’s capability to process multi-scale information. Additionally, the partial-faster C3 feature awareness module is designed to improve feature fusion performance, enhancing the model’s ability to perceive features at different scales. Finally, channel pruning was used to reduce redundant parameters, and knowledge distillation was employed to compensate for the accuracy loss caused by pruning. This approach further compressed the model size while ensuring its detection performance. The experimental results demonstrate that compared to the original YOLOv5s algorithm, the proposed GMPPD-YOLO algorithm achieves a reduction in parameters by 68.4%, a decrease in Giga floating-point operations per second by 58.2%, and a reduction in the model size by 66.4%, while achieving an increase in precision by 1%, mAP50 by 1.1%, and mAP95 by 0.4%. This confirms the significant potential of the GMPPD-YOLO algorithm for deployment in real-time drone-based power transmission line inspections.

Flat-top plasma operational space of the STEP power plant

Abstract STEP is a spherical tokamak prototype power plant that is being designed to demonstrate net electric power. The design phase involves the exploitation of plasma models to optimise fusion performance subject to satisfying various physics and engineering constraints. A modelling workflow, including integrated core plasma modelling, MHD stability analysis, SOL and pedestal modelling, coil set and free boundary equilibrium solvers, and whole plant design, has been developed to specify the design parameters and to develop viable scenarios. The integrated core plasma model JETTO is used to develop individual flat-top operating points that satisfy imposed criteria for fusion power performance within operational constraints. Key plasma parameters such as normalised beta, Greenwald density fraction, auxiliary power and radiated power have been scanned to scope the operational space and to derive a collection of candidate non-inductive flat-top points. The assumed auxiliary heating and current drive is either from electron cyclotron systems only or a combination of electron cyclotron and electron Bernstein waves. At present stages of transport modelling, there is a large uncertainty in overall confinement for relevant parameter regimes. For each of the two auxiliary heating and current drive systems scenarios, two candidate flat-top points have been developed based on different confinement assumptions, totalling to four operating points. A lower confinement assumption generally suggests operating points in high-density, high auxiliary power regimes, whereas higher confinement would allow access to a broader parameter regime in density and power while maintaining target fusion power performance.

High-Cycle Fatigue Performance of Laser Powder Bed Fusion Ti-6Al-4V Alloy with Inherent Internal Defects: A Critical Literature Review

The inadequate fatigue performance of Laser Powder Bed Fusion (L-PBF) Ti-6Al-4V alloy, primarily due to intrinsic defects, poses a significant challenge for industrial applications. Internal defects often serve as initiation sites for fatigue cracks, significantly impacting the fatigue life of L-PBF Ti-6Al-4V components. Accurate evaluation of the role of internal defects in fatigue performance and quantitative analysis of influential parameters are crucial for guiding optimal L-PBF manufacturing design. This study aims to critically review recent notable contributions focusing on high-cycle fatigue (HCF) in these alloys, with many of the presented insights being easily transferred to other types of AM alloys. Efforts have been made to identify correlations between fatigue life at various stages and critical internal defects. Key aspects, including microstructure and post-processing treatments, and their effects on HCF have been thoroughly analyzed. The findings enhance the scientific understanding of fatigue performance of L-PBF Ti-6Al-4V alloy and open new avenues for future research.

Enhancing three-source cross-modality image fusion with improved DenseNet for infrared polarization and visible light images

The fusion of multi-modal images to create an image that preserves the unique features of each modality as well as the features shared across modalities is a challenging task, particularly in the context of infrared (IR)-visible image fusion. In addition, the presence of polarization and IR radiation information in images obtained from IR polarization sensors further complicates the multi-modal image-fusion process. This study proposes a fusion network designed to overcome the challenges associated with the integration of low-resolution IR, IR polarization, and high-resolution visible (VIS) images. By introducing cross attention modules and a multi-stage fusion approach, the network can effectively extract and fuse features from different modalities, fully expressing the diversity of the images. This network learns end-to-end mapping from sourced to fused images using a loss function, eliminating the need for ground-truth images for fusion. Experimental results using public datasets and remote-sensing field-test data demonstrate that the proposed methodology achieves commendable results in qualitative and quantitative evaluations, with gradient based fusion performance QAB/F, mutual information (MI), and QCB values higher than the second-best values by 0.20, 0.94, and 0.04, respectively. This study provides a comprehensive representation of target scene information that results in enhanced image quality and improved object identification capabilities. In addition, outdoor and VIS image datasets are produced, providing a data foundation and reference for future research in related fields.

LFDT-Fusion: A latent feature-guided diffusion Transformer model for general image fusion

For image fusion tasks, it is inefficient for the diffusion model to iterate multiple times on the original resolution image for feature mapping. To address this issue, this paper proposes an efficient latent feature-guided diffusion model for general image fusion. The model consists of a pixel space autoencoder and a compact Transformer-based diffusion network. Specifically, the pixel space autoencoder is a novel UNet-based latent diffusion strategy that compresses inputs into a low-resolution latent space through downsampling. Simultaneously, skip connections transfer multiscale intermediate features from the encoder to the decoder for decoding, preserving the high-resolution information of the original input. Compared to the existing VAE-GAN-based latent diffusion strategy, the proposed UNet-based strategy is significantly more stable and generates highly detailed images without adversarial optimization. The Transformer-based diffusion network consists of a denoising network and a fusion head. The former captures long-range diffusion dependencies and learns hierarchical diffusion representations, while the latter facilitates diffusion feature interactions to comprehend complex cross-domain information. Moreover, improvements to the diffusion model in noise level, denoising steps, and sampler selection have yielded superior fusion performance across six image fusion tasks. The proposed method illustrates qualitative and quantitative advantages, as evidenced by experimental results in both public datasets and industrial environments. The code is available at: https://github.com/BOYang-pro/LFDT-Fusion.

IMQFusion: Infrared and visible image fusion via implicit multi-resolution preservation and query aggregation

The infrared and visible image fusion (IVIF) task aims to generate high-resolution images with richer texture details and finer salient information to enhance visual understanding for downstream tasks. However, current IVIF techniques often focus on exploring complementary information from source images at a single resolution, neglecting valuable information available at other resolutions. To effectively exploit multi-resolution semantics, we propose a novel framework called IMQFusion, which enhances fusion performance by leveraging intra-modality multi-resolution preservation and inter-modality multi-resolution query aggregation. Specifically, our method introduces an implicit neural representation (INR) with a robust continuous map that vertically reduces the semantic gap among adjacent paired resolutions, avoiding reliance on simple upsampling. Additionally, we employ a bidirectional guided strategy to horizontally facilitate resolution preservation. Moreover, to integrate multi-resolution semantics across both modalities and resolutions effectively, we develop an efficient aggregation strategy that incorporates a query mechanism, thereby enhancing inter-modality interactions among multi-resolution features. Extensive experiments demonstrate that, compared to state-of-the-art IVIF methods, the fused images generated by IMQFusion exhibit superior visual balance between salient information and texture details, as well as higher quantitative metrics. Furthermore, IMQFusion possesses the potential to improve object detection and can be extended to the field of medical image fusion.

Disentangled variational auto-encoder for multimodal fusion performance analysis in multimodal sentiment analysis

Multimodal Sentiment Analysis (MSA) holds extensive applicability owing to its capacity to analyze and interpret users' emotions, feelings, and perspectives by integrating complementary information from multiple modalities. However, inefficient and unbalanced cross-modal information fusion substantially undermines the accuracy and reliability of MSA models. Consequently, a critical challenge in the field now lies in effectively assessing the information integration capabilities of these models to ensure balanced and equitable processing of multimodal data. In this paper, a Disentanglement-based Variable Auto-Encoder (DVAE) is proposed for systematically assessing fusion performance and investigating the factors that facilitate multimodal fusion. Specifically, a distribution constraint module is presented to decouple the fusion matrices and generate multiple low-dimensional and trustworthy disentangled latent vectors that adhere to the authentic unimodal input distribution. In addition, a combined loss term is modified to effectively balance inductive bias, signal reconstruction, and distribution constraint items to facilitate the optimization of neural network weights and parameters. Utilizing the proposed evaluation method, we can evaluate the fusion performance of multimodal models by contrasting the classification degradation ratio derived from disentangled hidden representations and joint representations. Experiments conducted with eight state-of-the-art multimodal fusion methods on the CMU-MOSEI and CMU-MOSEI benchmark datasets demonstrate that DVAE is capable of effectively evaluating the effects of multimodal fusion. Moreover, the comparative experimental results indicate that the equalizing effect among various advanced mechanisms in multimodal sentiment analysis, as well as the single-peak characteristic of the ground label distribution, both contribute significantly to multimodal data fusion.

One improved YOLOX-s algorithm for lightweight section-steel surface defect detection

This study introduces an improved lightweight section-steel surface detection (ILSSD) YOLOX-s algorithm model to enhance feature fusion performance in single-stage target detection networks, addressing the low accuracy in detecting defects on section-steel surfaces and limited computing resources at steel plants. The ILSSD YOLOX-s model is improved by introducing the deep-wise separable convolution (DSC) module to reduce parameter count, a dual parallel attention module for improved feature extraction efficiency, and a weighted feature fusion path using bi-directional feature pyramid network (BiFPN). Additionally, the CIoU loss function is employed for boundary frame regression to enhance prediction accuracy. Based on the NEU-DET dataset, experimental results demonstrate that the ILSSD YOLOX-s algorithm model achieves a 75.9% mean average precision with an IoU threshold of 0.5 (mAP@0.5), an improvement of 7.1 percentage points over the original YOLOX-s model, with a detection speed of 78.4 frames per second (FPS). Its practicality is validated through training and validating it with a lightweight section-steel surface defect dataset from an industrial steel plant, further confirming its viability for industrial defect detection applications.

Biomimetic Porous Ti6Al4V Implants: A Novel Interbody Fusion Cage via Gel-Casting Technique to Promote Spine Fusion.

An interbody fusion cage (Cage) is crucial in spinal decompression and fusion procedures for restoring normal vertebral curvature and rebuilding spinal stability. Currently, these Cages suffer from issues related to mismatched elastic modulus and insufficient bone integration capability. Therefore, a gel-casting technique is utilized to fabricate a biomimetic porous titanium alloy material from Ti6Al4V powder. The biomimetic porous Ti6Al4V is compared with polyetheretherketone (PEEK) and 3D-printed Ti6Al4V materials and their respective Cages. Systematic validation is performed through mechanical testing, in vitro cell, in vivo rabbit bone defect implantation, and ovine anterior cervical discectomy and fusion experiments to evaluate the mechanical and biological performance of the materials. Although all three materials demonstrate good biocompatibility and osseointegration properties, the biomimetic porous Ti6Al4V, with its excellent mechanical properties and a structure closely resembling bone trabecular tissue, exhibited superior bone ingrowth and osseointegration performance. Compared to the PEEK and 3D-printed Ti6Al4V Cages, the biomimetic porous Ti6Al4V Cage outperforms in terms of intervertebral fusion performance, achieving excellent intervertebral fusion without the need for bone grafting, thereby enhancing cervical vertebra stability. This biomimetic porous Ti6Al4V Cage offers cost-effectiveness, presenting significant potential for clinical applications in spinal surgery.

Observation of alpha-particles in recent D–T experiments on JET

The fusion reaction between deuterium and tritium, D(T,n)4 He is the main source of energy in future thermonuclear reactors. Alpha-particles (4 He-ions) born with an average energy of 3.5 MeV transferring energy to the thermal plasma during their slowing down, should provide the self-sustained D–T plasma burn. The adequate confinement of α-particles is essential to provide efficient heating of the bulk plasma and steady burning of a reactor plasma. That is why the fusion-born α-particle studies have been a priority task in the second D–T experiments (DTE2) on the Joint European Torus (JET) to understand the main mechanisms of their slowing down, redistribution and losses and to develop optimal plasma scenarios. JET with Be-wall and W-divertor, enhanced auxiliary heating systems and improved energetic-particle diagnostic capabilities, producing significant population of α-particles, provided the possibility for comprehensive studying of the α-particle behaviour. Selected results of the confined and lost α-particle measurements, evidence of α-particle self-heating and assessments of the fusion performance are presented in this paper giving an opportunity for further modelling and extrapolation to the International Thermonuclear Experimental Reactor and burning plasma reactors.

Verification of the Laser Powder Bed Fusion Performance of 2024 Aluminum Alloys Modified Using Nano-LaB6.

The application of 2024 aluminum alloy (comprising aluminum, copper, and magnesium) in the aerospace industry is extensive, particularly in the manufacture of seats. However, this alloy faces challenges during laser powder bed fusion (PBF-LB/M) processing, which often leads to solidification and cracking issues. To address these challenges, LaB6 nanoparticles have been investigated as potential grain refiners. This study systematically examined the impact of adding different amounts of LaB6 nanoparticles (ranging from 0.0 to 1.0 wt.%) on the microstructure, phase composition, grain size, and mechanical properties of the composite material. The results demonstrate that the addition of 0.5 wt.% LaB6 significantly reduces the average grain size from 10.3 μm to 9 μm, leading to a significant grain refinement effect. Furthermore, the tensile strength and fracture strain of the LaB6-modified A2024 alloy reach 251 ± 2 MPa and 1.58 ± 0.12%, respectively. These findings indicate that the addition of appropriate amounts of LaB6 nanoparticles can effectively refine the grains of 2024 aluminum alloy, thereby enhancing its mechanical properties. This discovery provides important support for the broader application of 2024 aluminum alloy in the aerospace industry and other high-performance fields.

YOLOv8 Model for Weed Detection in Wheat Fields Based on a Visual Converter and Multi-Scale Feature Fusion.

Accurate weed detection is essential for the precise control of weeds in wheat fields, but weeds and wheat are sheltered from each other, and there is no clear size specification, making it difficult to accurately detect weeds in wheat. To achieve the precise identification of weeds, wheat weed datasets were constructed, and a wheat field weed detection model, YOLOv8-MBM, based on improved YOLOv8s, was proposed. In this study, a lightweight visual converter (MobileViTv3) was introduced into the C2f module to enhance the detection accuracy of the model by integrating input, local (CNN), and global (ViT) features. Secondly, a bidirectional feature pyramid network (BiFPN) was introduced to enhance the performance of multi-scale feature fusion. Furthermore, to address the weak generalization and slow convergence speed of the CIoU loss function for detection tasks, the bounding box regression loss function (MPDIOU) was used instead of the CIoU loss function to improve the convergence speed of the model and further enhance the detection performance. Finally, the model performance was tested on the wheat weed datasets. The experiments show that the YOLOv8-MBM proposed in this paper is superior to Fast R-CNN, YOLOv3, YOLOv4-tiny, YOLOv5s, YOLOv7, YOLOv9, and other mainstream models in regards to detection performance. The accuracy of the improved model reaches 92.7%. Compared with the original YOLOv8s model, the precision, recall, mAP1, and mAP2 are increased by 10.6%, 8.9%, 9.7%, and 9.3%, respectively. In summary, the YOLOv8-MBM model successfully meets the requirements for accurate weed detection in wheat fields.

CUFNet: A fusion network based on cross-reconstruction uniqueness for visible and infrared images

Image fusion is crucial in computer vision, offering numerous advantages across various applications. However, current fusion methods often face challenges in striking a balance between preserving specific features, which are susceptible to subjective bias, and avoiding the distortion of unique information, thus limiting overall fusion performance. Given these challenges, we have proposed a cross-reconstruction uniqueness fusion network (CUFNet) to fuse visible and infrared images. Initially, we developed the cross-reconstruction uniqueness module to objectively measure feature uniqueness and enhance the accurate retention of distinctive features. Subsequently, we devised the feature compensation module to improve the interaction among medium, deep, and shallow features, generating a fused image with enhanced texture details. Finally, the multilayer feature fusion model was utilized to optimize the retention of specific features across different layers. Experimental validation conducted using two publicly available datasets, TNO and RoadScene, demonstrates that our proposed method, CUFNet, outperforms twelve comparative methods in terms of both quantitative and qualitative perspectives.

Performance of an inertial electrostatic confinement fusion device having a multi-grid configuration

The aim of this work is to enhance the performance of an inertial electrostatic confinement fusion (IECF) device, addressing the issues with glow discharge voltage, current, and gas pressure while achieving significant fusion reactions at reduced pressure. Previous success involved a fusion rate of 106 n/s in a single-grid IECF system, but broader applications require higher neutron production by improving ion density, ion energy, and plasma confinement. Electrostatic focusing ion beams are proposed for better ion confinement. Comparing a single-grid IECF device with a triple-grid one, computational modeling using a 2D-3 V XOOPIC code suggests significant improvements in ion confinement with tailored potentials in the triple-grid device. The simulation demonstrates that modifying electrostatic fields in the triple-grid setup creates a potential well with humps, guiding ion beams to the central region and enhancing ion density.

Build Orientation Effect on Bending Fatigue Performance and Impact Toughness of Laser Powder Bed Fusion Manufactured Ti6Al4V Without Heat Treatment

Titanium alloys are highly valued in various industries due to their exceptional qualities. This study examines how the build orientation affects the mechanical and fatigue properties of Laser Powder Bed Fusion (PBF-LB) produced Ti6Al4V, without heat treatment. The research shows mechanical properties vary based on build orientation with vertically oriented specimens exhibiting the highest yield and tensile strengths, while vertical orientation excels in ductility, measured through elongation at break. Impact toughness sees variations with horizontal orientation performing the best. However, build orientation has minimal influence on flexural bending fatigue performance. Both diagonal and vertical orientations show similar fatigue limits at around 40 MPa. Dry electropolishing proves to be an effective technique, significantly enhancing fatigue performance with limits stabilizing at about 150 MPa. This study underscores the importance of considering build orientation in PBF-LB manufacturing for specific mechanical and impact properties and the potential of dry electropolishing in improving the fatigue performance of Ti6Al4V components. These findings offer valuable insights for the additive manufacturing industry, aiding in the optimization of Ti6Al4V component production.

ReLAP-Net: Residual Learning and Attention Based Parallel Network for Hyperspectral and Multispectral Image Fusion

Remote sensing applications require high-resolution images to obtain precise information about the Earth???s surface. Multispectral images have high spatial resolution but low spectral resolution. Hyperspectral images have high spectral resolution but low spatial resolution. This study proposes a residual learning and attention-based parallel network based on residual network and channel attention. The network performs image fusion of a high spatial resolution multispectral image and a low spatial resolution hyperspectral image. The network training and fusion experiments are conducted on four public benchmark data sets to show the effectiveness of the proposed model. The fusion performance is compared with classical signal processing???based image fusion techniques. Four image metrics are used for the quantitative evaluation of the fused images. The proposed network improved fusion ability by reducing the root mean square error and relative dimensionless global error in synthesis and increased the peak signal-to-noise ratio when compared to other state-of-the-art models.

A Novel Model for Instance Segmentation and Quantification of Bridge Surface Cracks-The YOLOv8-AFPN-MPD-IoU.

Surface cracks are alluded to as one of the early signs of potential damage to infrastructures. In the same vein, their detection is an imperative task to preserve the structural health and safety of bridges. Human-based visual inspection is acknowledged as the most prevalent means of assessing infrastructures' performance conditions. Nonetheless, it is unreliable, tedious, hazardous, and labor-intensive. This state of affairs calls for the development of a novel YOLOv8-AFPN-MPD-IoU model for instance segmentation and quantification of bridge surface cracks. Firstly, YOLOv8s-Seg is selected as the backbone network to carry out instance segmentation. In addition, an asymptotic feature pyramid network (AFPN) is incorporated to ameliorate feature fusion and overall performance. Thirdly, the minimum point distance (MPD) is introduced as a loss function as a way to better explore the geometric features of surface cracks. Finally, the middle aisle transformation is amalgamated with Euclidean distance to compute the length and width of segmented cracks. Analytical comparisons reveal that this developed deep learning network surpasses several contemporary models, including YOLOv8n, YOLOv8s, YOLOv8m, YOLOv8l, and Mask-RCNN. The YOLOv8s + AFPN + MPDIoU model attains a precision rate of 90.7%, a recall of 70.4%, an F1-score of 79.27%, mAP50 of 75.3%, and mAP75 of 74.80%. In contrast to alternative models, our proposed approach exhibits enhancements across performance metrics, with the F1-score, mAP50, and mAP75 increasing by a minimum of 0.46%, 1.3%, and 1.4%, respectively. The margin of error in the measurement model calculations is maintained at or below 5%. Therefore, the developed model can serve as a useful tool for the accurate characterization and quantification of different types of bridge surface cracks.

Axial confinement of wire array Z-pinch precursor plasmas by a pulsed magnetic mirror field

A novel wire-array Z-pinch platform has been developed to study the effect of a pulsed magnetic mirror field on a collisional high energy density plasma. The mirror is driven in series with the Z-pinch target and, therefore, scales with driver current. Axial confinement is observed based on visible imaging and axial flow velocity measurements. The presence of axial compressing J ×B force is determined indirectly based on Thomson scattering and interferometry measurements and corroborated by three-dimensional extended-MHD simulations. Compared to non-magnetized wire array Z-pinch, a modified pulsed mirror configuration is observed to increase precursor plasma thermal energy density by about 30%. If optimized, such a configuration could potentially improve magnetized liner inertial fusion performance by reducing axial plasma end loss.

Comparative study on the process, anisotropy, and mechanical performance of laser powder bed fusion fabricated truss-lattice structures with different unit cell designs

Lattice structures to fabricate bone implants can avoid stress-shielding effects and promote bone-in-growth. However, the performance of bones varies in different body parts, creating a barrier to manufacture an appropriate lattice structure for bone implant. Here, the formability, anisotropy, energy absorption abilities, stress distribution, and deformation mode of the laser powder bed fusion (LPBF) processed face-centered cubic (FCC), Octet, and Kelvin lattice structures were systematically compared through experiments and finite element analysis. The results show that the Kelvin lattice structure had the optimal comprehensive mechanical performance. This research has potential value for the design and manufacturing of specific bone implants.