The connection between the leg members and diagonal members of the urban transmission line tower is mostly in the form of single-limb connection. This paper puts forward a new connection form of pipe double-limb double-plate connection joint, which is based on the model of key joints in an urban narrow base tower structure. The traditional pipe single-limb single-plate and new pipe double-limb double-plate joint are analyzed and studied from three aspects of theory, numerical simulation and experimental study. Through finite element analysis, it is obtained that the section stress of angle steel under eccentric load is 2.05 times of that under axial load, which is basically consistent with the 2.5 times of the theoretical calculation. This shows that the stress of the angle steel in the pipe double-limb double-plate joint is greatly reduced as the axial stress component, which can ensure the safety of the angle steel. Based on the theoretical analysis of the tensile force of two kinds of joints, through the test research and corresponding numerical simulation of pipe single-limb single-plate and pipe double-limb double-plate joints, under the same load, compared with pipe single-limb single-plate joints, the pipe double-limb double-plate joints designed in this paper can greatly reduce the stress of connection plates and members, and compared with the existing joint forms, the bending stress of joint plates can be reduced by about four times, which greatly improves the bearing capacity of the joint. The research on the pipe double-limb double-plate connection joint will provide the basis for the design of new connection joints of narrow base towers in urban areas.

Visual recognition for automated cigarette inventory faces significant hurdles, including illumination changes, diverse box dimensions, and partial feature occlusion, which complicate brand verification and misplaced box detection. This article proposes an improved real-time detection model to deal with image recognition problems and improve accuracy. Firstly, an adaptive downsampling module is deployed to replace the downsampling convolution module in both the backbone and neck networks of YOLO series as the baseline or original detector, which effectively retains more feature details and realizes the lightweight of the model. Secondly, an inverted efficient multi-scale attention module is introduced to capture the spatial context information of different scales and generate a more accurate spatial attention map, which improves the prediction accuracy of the baseline model for complex features and occlusion targets. Finally, a dynamic detection head module replaces theoriginal detection head of the baseline model and performs multi-scale object detection on the feature map extracted from the backbone and neck networks to achieve accurate positioning and category division of the predicted target. To evaluate the performance of the improved model in the field, we constructed a visual dataset of the cigarette box brand. The dataset was augmented using region-specific copy-paste and traditional augmentation techniques, and the obtained dataset includes complex background, occlusion, and overlap, small target, and other factors. The experiment demonstrates that the improved model presented in this article effectively meets the requirements for real-time detection in the field. The proposed model achieves a mAP of 97.9%, with parameters and FLOPs of 1,849,679 and 5.1 G, respectively. Compared with the baseline model, the proposed model improves mAP by 0.9% while reducing parameters by 28.78% and floating-point operations by 1.4 G. Additionally, the model reaches an inference speed of 38.5 FPS, satisfying the requirements for real-time industrial detection.

Visual recognition for automated cigarette inventory faces significant hurdles, including illumination changes, diverse box dimensions, and partial feature occlusion, which complicate brand verification and misplaced box detection. This article proposes an improved real-time detection model to deal with image recognition problems and improve accuracy. Firstly, an adaptive downsampling module is deployed to replace the downsampling convolution module in both the backbone and neck networks of YOLO series as the baseline or original detector, which effectively retains more feature details and realizes the lightweight of the model. Secondly, an inverted efficient multi-scale attention module is introduced to capture the spatial context information of different scales and generate a more accurate spatial attention map, which improves the prediction accuracy of the baseline model for complex features and occlusion targets. Finally, a dynamic detection head module replaces theoriginal detection head of the baseline model and performs multi-scale object detection on the feature map extracted from the backbone and neck networks to achieve accurate positioning and category division of the predicted target. To evaluate the performance of the improved model in the field, we constructed a visual dataset of the cigarette box brand. The dataset was augmented using region-specific copy-paste and traditional augmentation techniques, and the obtained dataset includes complex background, occlusion, and overlap, small target, and other factors. The experiment demonstrates that the improved model presented in this article effectively meets the requirements for real-time detection in the field. The proposed model achieves a mAP of 97.9%, with parameters and FLOPs of 1,849,679 and 5.1 G, respectively. Compared with the baseline model, the proposed model improves mAP by 0.9% while reducing parameters by 28.78% and floating-point operations by 1.4 G. Additionally, the model reaches an inference speed of 38.5 FPS, satisfying the requirements for real-time industrial detection.

Most of rolled sheet metals belong to orthorhombic aggregates of cubic crystallites. The texture coefficients, characterized by the preferred orientation of the crystallites, are important to set up the yield function. Although Hosford yield function is more suitable for describing both yield and plastic deformation of orthorhombic material than Hill, it suffers from the restriction that the three principal stresses have to be coaxial with the orthotropy of materials. Hence, this paper proposes a new Hosford yield function of cubic orthorhombic metal sheet at any stress states by introducing orientation-dependent functions. As well, the new yield function which covers 3 material parameters and 3 texture coefficients is more general than Hosford yield function. The plastic anisotropy of the q-value and yield stress under any stress states is obtained from the new yield function. This yield function lay a theoretical foundation for analyzing the mechanical properties of metal materials.