The occurrence of cracks as a common surface defect in tunnel linings is influenced by a combination of internal and external factors. In recent years, computer vision methods have been widely applied in the field of...
The occurrence of cracks as a common surface defect in tunnel linings is influenced by a combination of internal and external factors. In recent years, computer vision methods have been widely applied in the field of crack detection. Deep learning has the capability to handle large-scale crack image data and automatically extract crack features. However, owing to numerous difficulties, including low-quality images, intricate cracks, and complex background environments, it is challenging to solve these tricky issues in tunnel crack detection. Therefore, this paper proposes a tunnel lining crack detection model based on Crack-aware Vision Transformer (CAViT), which includes a perceptual vision transformer backbone network and an improved decoding network. The vision Transformer model has a stronger contextual modeling ability and is suitable for the task of extracting features from tunnel cracks with long, fine, and irregular characteristics. Due to the limitations of the attention mechanism based on a fixed window in modeling long-range relationships, we propose Crack-aware self-attention with the ability to increase the attention to relevant features and extract long-distance feature dependencies. This attention mechanism focuses on the crack area by learning the transformation parameters of the sampled window and reference points from the prediction module, and the position bias generated by the transformation compensate in the position encoding. Subsequently, we employ recurrent convolution layers to enhance the fusion network's ability to integrate contextual information. Our proposed CAViT is evaluated on the Crack500 dataset and a self-made tunnel crack dataset. Experimental results show that our network achieves the highest scores in terms of crack intersection-over-union (IoU) and accuracy (Acc) compared to other transformer models in both datasets. These results demonstrate the suitability of our CAViT for pavement crack and tunnel crack detection tasks, sho
Traditional carbon fiber-reinforced polymers based on thermoset matrix have been extensively used in the fields of wind turbine blades,automotive sector,and aerospace,among many ***,there is still a major challenge of...
详细信息
Traditional carbon fiber-reinforced polymers based on thermoset matrix have been extensively used in the fields of wind turbine blades,automotive sector,and aerospace,among many ***,there is still a major challenge of recycling those polymers due to the high cost and adverse impacts on the *** this work,we apply a polyimine network as matrix,which possess considerable tensile and thermal properties,to prepare the carbon fiber reinforced polyimine materials with trifluoromethyl diphenoxybenzene units(CFRFP)using a prepreg-based compression molding *** CFRFP can be reshaped or reprocessed by heat or with water rapidly,and exhibited multifunction,including welding,chemical recycling,*** unique findings gained from our study will facilitate the manufacturing capability and enrich the types of fiber-reinforced composites.
Y_(3)Fe_(5)O_(12)(YIG)crystals are highly desirable for the fabrication of mid-infrared isolators with the rapid growth of optical communications,although it is rather challenging to grow large size and high-quality s...
详细信息
Y_(3)Fe_(5)O_(12)(YIG)crystals are highly desirable for the fabrication of mid-infrared isolators with the rapid growth of optical communications,although it is rather challenging to grow large size and high-quality single ***^(3+)doping is expected to improve the optical and magneto-optical prope ***,high quality Dy:YIG crystals and the adjustment of Dy^(3+)on the structure and optical behavior of YIG crystal remain unclear,impeding its practical ***,a series of Y_(3-x)Dy_(x)Fe_(5)O_(12)(x=0,0.5,1.0,1.5,3)solid solution crystals was grown by the flux-Bridgman method and single crystals up to 25 mm were *** the introduction of Dy^(3+),lattice parameters are gradually enlarged from 1.2379 nm(YIG)to 1.2420 nm(DyIG).Typical Dy^(3+)absorption peaks are observed around 1070,1265 and 1670 *** refractive index decreases from 2.37(500 nm)to 2.10(2500 nm)for YIG crystal,and it reduces from 2.47(500 nm)to 2.16(2500 nm)for DyIG *** optical bandgaps remain almost unchanged for Dy:YIG *** optical dispersion of the refractive indices was finely fitted by the Wemple and DiDomenico(WDD)and the Sellmeier models,*** the increase of Dy^(3+)content,the saturation magnetization(Ms)decreases significantly from 23.62 emu/g(YIG)to 5.33 emu/g(DyIG).Small coercive field is persisted for this system,endowing small external magnetic *** results provide valuable references for the manipulation of rare earths on the properties of magnetooptical crystals,which is beneficial to the design of high-performance garnet crystals for the application of optical switching and non-reciprocal related devices.
Perfluoroalkyl acids(PFAAs)are emerging organic pollutants that have attracted significant attention in the fields of environmental chemistry and *** PFAAs are pervasive in soils and sediments,there is a paucity of re...
详细信息
Perfluoroalkyl acids(PFAAs)are emerging organic pollutants that have attracted significant attention in the fields of environmental chemistry and *** PFAAs are pervasive in soils and sediments,there is a paucity of research regarding their environmental forms and driving *** review provides an overview of the classification and biotoxicity of per-and polyfluoroalkyl substances(PFAS),organic pollutant forms,PFAS extraction and analytical methods,the prediction of PFAS distribution in soils,and current PFAS remediation *** predominant PFAA forms have been proposed in soils:(i)aqueous-extracted PFAAs,(ii)organic-solvent extracted PFAAs,(ii)embedded or sequestered PFAAs,and(iv)covalently bound ***,it suggests suitable extraction methods and predictive models for different PFAA forms,which are instrumental in the research on PFAA speciation and prediction in ***,it was proposed that elemental cycling and microbial activity may affect the speciation of ***,the categorization of PFAA forms facilitated the analysis of pollution *** the interplay between PFAA speciation,element cycling,and bacterial activity during soil remediation is essential for understanding remediation mechanisms and assessing the long-term stability of remediation *** studies should expand the investigation of varying PFAA forms in different media,consider the potential binding forms of PFAAs to minerals,organic matter,and microbes,and evaluate the possible mechanisms of PFAA speciation variation.
Semiconductor moirésuperlattices provide great platforms for exploring exotic collective *** Stark effect,a shift of the electronic transition in the presence of a light field,provides an ultrafast and coherent m...
详细信息
Semiconductor moirésuperlattices provide great platforms for exploring exotic collective *** Stark effect,a shift of the electronic transition in the presence of a light field,provides an ultrafast and coherent method of manipulating matter states,which,however,has not been demonstrated in moiré***,we report the valleyselective optical Stark effect of moiréexcitons in the WSe_(2)/WS_(2)superlattice by using transient reflection *** valley-selective energy shifts up to 7.8 meV have been observed for moiréexcitons,corresponding to pseudomagnetic fields as large as 34 *** results provide a route to coherently manipulate exotic states in moirésuperlattices.
The two-wheel self-balancing robot has the advantages of small size and flexible operation, but it is an inverted pendulum system with electromechanical integration, which has the characteristics of nonlinearity, stro...
详细信息
Noble metal materials have been identified as high efficiency catalysts for electrocatalytic reduction of nitrate,and the synthesis and manufacture of high catalytic activity and environmentally friendly catalysts of ...
详细信息
Noble metal materials have been identified as high efficiency catalysts for electrocatalytic reduction of nitrate,and the synthesis and manufacture of high catalytic activity and environmentally friendly catalysts of activating hydrogen for water purification applications is extremely *** this work,the Pd-Cu single-atom catalysts(Pd-Cu-N-BC)were first prepared by direct growth of Pd-Cu single-atom on bamboo biochar by regulating the concentration of precursors and doping method,and then enhanced electrocatalytic reduction nitrate performance and N2 *** results showed that Pd-Cu-N-BC displayed excellent catalytic activity and reusability in electrocatalytic reduction nitrate with a low potential of 0.47 V ***(@10 mA cm−2).The maximum nitrate removal efficiency and N2 generation could reach about 100%and 72.32%within 180 min,*** density functional theory(DFT)calculations confirmed that Cu atoms could catalyze the electrochemical reduction of nitrate to nitrite,and Pd atoms anchored in the nitrogen-doped biochar(N-BC)lattice could catalyze electrochemical reduction of nitrite to N2 involving the formation of hydrogen radical(H*).The characterization results of XANES showed that electronic synergistic effect between Pd and Cu single atoms significantly promotes the N2 production through hydrogenation while inhibiting the generation of byproducts,leading to significantly enhanced electrocatalytic reduction of nitrate to ***,Pd-Cu-N-BC was designed as a 3D particle electrode for enhanced electrocatalytic reduction of nitrate,exhibiting excellent stability and reusability,which could be considered as a suitable candidate for applications in the remediation of nitrate contamination.
A novel broadband bandpass Frequency Selective Surface (FSS) is designed with the intention of surpassing the performance of previous designs. Through the utilization of cascading multilayers of capacitive patches and...
详细信息
Conceptual modeling is gaining an essential role in designing large-scale systems, especially as the complexity of the latter increases. The design tool for such systems is the development of ontologies for their subj...
详细信息
In this study, we introduce a novel auction-based algorithm modeled as a decentralized coalition formation game, designed for the complex requirements of large-scale multi-robot task allocation under uncertain demand....
详细信息
In this study, we introduce a novel auction-based algorithm modeled as a decentralized coalition formation game, designed for the complex requirements of large-scale multi-robot task allocation under uncertain demand. This context is particularly illustrative in scenarios where robots are tasked to charge electric vehicles. The algorithm begins by partitioning a composite task sequence into distinct subsets based on spatial similarity principles. Subsequently, we employ a coalition formation game paradigm to coordinate the assembly of robots into cooperative coalitions focused on these distinct subsets. To mitigate the impact of unpredictable task demands on allocations, our approach utilizes the conditional value-at-risk to assess the risk associated with task execution, along with computing the potential revenue of the coalition with an emphasis on risk-related outcomes. Additionally, integrating consensus auctions into the coalition formation framework allows our approach to accommodate assignments for individual robot-task pairings, thus preserving the stability of individual robotic decision autonomy within the coalition structure and assignment distribution. Simulative analyses on a prototypical parking facility layout confirm that our algorithm achieves Nash equilibrium within the coalition structure in polynomial time and demonstrates significant scalability. Compared to competing algorithms, our proposal exhibits superior performance in resilience, task execution efficiency, and reduced overall task completion times. The results demonstrate that our approach is an effective strategy for solving the scheduling challenges encountered by multi-robot systems operating in complex environments. IEEE
暂无评论