Search

Agricultural pests and diseases pose major losses to agricultural productivity, leading to significant economic losses and food safety risks. However, accurately identifying and controlling these pests is still very challenging due to the scarcity of labeling data for agricultural pests and the wide variety of pest species with different morphologies. To this end, we propose a two-stage target detection method that combines Cascade RCNN and Swin Transformer models. To address the scarcity of labeled data, we employ random cut-and-paste and traditional online enhancement techniques to expand the pest dataset and use Swin Transformer for basic feature extraction. Subsequently, we designed the SCF-FPN module to enhance the basic features to extract richer pest features. Specifically, the SCF component provides a self-attentive mechanism with a flexible sliding window to enable adaptive feature extraction based on different pest features. Meanwhile, the feature pyramid network (FPN) enriches multiple levels of features and enhances the discriminative ability of the whole network. Finally, to further improve our detection results, we incorporated non-maximum suppression (Soft NMS) and Cascade R-CNN's cascade structure into the optimization process to ensure more accurate and reliable prediction results. In a detection task involving 28 pest species, our algorithm achieves 92.5%, 91.8%, and 93.7% precision in terms of accuracy, recall, and mean average precision (mAP), respectively, which is an improvement of 12.1%, 5.4%, and 7.6% compared to the original baseline model. The results demonstrate that our method can accurately identify and localize farmland pests, which can help improve farmland's ecological environment. [ABSTRACT FROM AUTHOR]

Existing methods for spectral image reconstruction from low spatial/spectral resolution inputs are typically in discrete manners, only producing results with fixed spatial/spectral resolutions. However, these discrete methods neglect the continuous nature of three-dimensional spectral signals, limiting their applicability and performance. To address this limitation, we propose a novel method leveraging implicit neural representation, which allows for spectral image reconstruction with arbitrary resolutions in both spatial and spectral dimensions for the first time. Specifically, we design neural spatial-spectral representation (NeSSR), which projects the deep features extracted from low-resolution inputs to the corresponding intensity values under target 3D coordinates (including 2D spatial positions and 1D spectral wavelengths). To achieve continuous reconstruction, within NeSSR we devise: a spectral profile interpolation module, which efficiently interpolates features to the desired resolution, and a coordinate-aware neural attention mapping module, which aggregates the coordinate and content information for the final reconstruction. Before NeSSR, we design the spatial-spectral encoder leveraging large-kernel 3D attention, which effectively captures the spatial-spectral correlation in the form of deep features for subsequent high-fidelity representation. Extensive experiments demonstrate the superiority of our method over existing methods across three representative spatial-spectral reconstruction tasks, showcasing its ability to reconstruct spectral images with arbitrary and even extreme spatial/spectral resolutions beyond the training scale. [ABSTRACT FROM AUTHOR]

In this paper, a unified method is proposed to predict the free and forced vibration behavior of the combined conical-cylindrical shell (CCS) structure in the steady-state thermal environment. The first-order shear deformation theory (FSDT) and the thermal strain are utilized to establish the energy equation of the combined structure, and the artificial virtual spring technique is introduced to realize the coupling between the substructures and the arbitrary boundary conditions of the CCS. The displacement function of the structure is constructed by the spectral-geometry method, and the vibration equation is solved by using the Rayleigh–Ritz method. The accuracy of the present model is verified by comparing the numerical results with the finite element method. The factors that may affect the vibration behavior of the CCS under thermal environment are analyzed specifically, and the results demonstrate that point constraints on the shell surface can effectively suppress shell vibration. This paper provides a compelling reference for vibration control of CCS in practical applications. [ABSTRACT FROM AUTHOR]

[Display omitted] • The vibro-acoustic model of the cavity-ECCDS panel-cavity is demonstrated from an analytical perspective for the first time. • This model can calculate the sound transmission loss of ECCDS panels and its accuracy has been verified experimentally. • The effect of various parameters on the sound transmission loss of ECCDS panels is analysed in detail. The embedded co-cured composite damping structures (ECCDS) are widely used in engineering fields, it is necessary to build a predictive model of the dynamics of the ECCDS panel. In this paper, a method is promoted for the first time that can predict the acoustic-vibration coupling characteristics of the coupled cavity-ECCDS panel-cavity system. This paper innovatively combines the spectral-geometry method (SGM), penalty-function method (PFM), and the energy-generalised variational principle to develop coupling model of the ECCDS panel with two closed cavities. The displacement of the ECCDS panel and the sound pressure in the cavities are expressed as improved Fourier series. The modal parameters of the cavities and the ECCDS panel are obtained by solving the standard matrix eigenvalue problem, and the accuracy of this method is verified by comparing it with the finite element method (FEM) and experiment. On this basis, the sound transmission loss (STL) can be obtained by the sound pressure method. The factors affecting the sound insulation performance of the ECCDS panel are investigated by parametric analysis. The results show that the addition of a damping layer can improve the sound insulation performance of composite panels. This paper provides a reference for the application of ECCDS panels in engineering. [ABSTRACT FROM AUTHOR]

In this paper, a unified method is proposed for the first time to predict the free and forced vibration behavior of the combined conical–cylindrical shells coupled with annular plates in the steady-state thermal environment. The energy equations of each substructure are obtained based on the first-order shear deformation theory (FSDT), and the artificial spring technique is introduced to realize the coupling between each substructure, the circumferential closure of each substructure, and the arbitrary boundary conditions. The displacements of the midface in each sub-structure are expanded using the spectral-geometry method (SGM), and the energy expression is solved by using the Rayleigh–Ritz method to obtain the free and forced vibration behavior of the combined structure. The numerical examples derived from the calculations are compared with the results obtained by the finite element method (FEM) to verify the accuracy of the present method. The effects of boundary conditions, temperature and geometric parameters on the free and forced vibration behaviors of the combined structure are investigated. The method in this paper is a meshless method, which is faster and more efficient as it is less dimensional and less computationally expensive than the FEM. This paper provides a compelling reference for vibration control of the combined conical–cylindrical shells coupled with annular plates in practical applications. • A unified method is proposed to predict the vibration of combined conical–cylindrical shells coupled with annular plates. • The model can be applied to arbitrary boundary conditions and a large number of elastic materials. • The influence of various parameters on the vibration behavior of the combined structure is analyzed in detail. [Display omitted] [ABSTRACT FROM AUTHOR]

This paper presents a method for predicting the free and forced vibration behavior of open and closed cylindrical shells in the steady-state thermal environment. The vibration characteristics of cylindrical shells in thermal environment are studied by considering the changes of the thermal strain in the cylindrical shell and the material properties caused by temperature rise. Based on Spectral-Geometry Method (SGM), the displacement functions of cylindrical shell are expressed as the improved Fourier series. The potential energy and kinetic energy of the cylindrical shell are obtained based on the first-order shear deformation theory (FSDT). Three sets of linear springs and one set of rotating springs are used to simulate arbitrary boundaries of the cylindrical shell, and the circumferential coupling springs are used to ensure the continuity of circumferential boundaries of the shell. The accuracy of the present method is verified by comparing with results derived by the finite element method (FEM), and a comprehensive parametric analysis was performed. • A unified efficient method is proposed to predict the vibration of cylindrical shells under steady thermal environment. • An analytical thermal mode model of cylindrical shells is established for arbitrary boundary conditions. • The effect of various parameters on the vibration of cylindrical shells under thermal environment is studied. [ABSTRACT FROM AUTHOR]