Search

With the progress of social life, the aging of building facilities has become an inevitable phenomenon. The efficiency of manual crack detection is limited, so it is necessary to explore intelligent detection technology. This article proposes a novel crack detection method TF-MobileNet. We took into account the effect of lightweight and crack feature extraction, so we developed a novel crack feature extraction backbone network, which combined Transformer and MobileNetV3. Then we improved the feature fusion network by using the multi-headed attention mechanism of the Bottleneck Transformer, which enables the feature fusion effect to be improved. Then, we integrated SENet and SimAM attention mechanisms into the networks used for feature extraction and feature fusion, thereby further improving the crack detection performance. Finally, we deployed our model in edge devices (NVIDIA Jeston Nano). The findings indicate that our proposed model has achieved 90.8% mAP on the dataset and worked well on the edge device side, which meet the requirements of automatic crack detection. Our model enables real-time monitoring of pavement using edge devices. This approach allows for timely maintenance and repair of the pavement. In the future, we can train the model to recognize more pavement distress features, addressing road safety issues effectively.

With the continuous development and construction of new power systems, using drones to inspect the condition of transmission line insulators has become an inevitable trend. To facilitate the deployment of drone hardware equipment, this paper proposes IDD-YOLO (Insulator Defect Detection-YOLO), a lightweight insulator defect detection model. Initially, the backbone network of IDD-YOLO employs GhostNet for feature extraction. However, due to the limited feature extraction capability of GhostNet, we designed a lightweight attention mechanism called LCSA (Lightweight Channel-Spatial Attention), which is combined with GhostNet to capture features more comprehensively. Secondly, the neck network of IDD-YOLO utilizes PANet for feature transformation and introduces GSConv and C3Ghost convolution modules to reduce redundant parameters and lighten the network. The head network employs the YOLO detection head, incorporating the EIOU loss function and Mish activation function to optimize the speed and accuracy of insulator defect detection. Finally, the model is optimized using TensorRT and deployed on the NVIDIA Jetson TX2 NX mobile platform to test the actual inference speed of the model. The experimental results demonstrate that the model exhibits outstanding performance on both the proprietary ID-2024 insulator defect dataset and the public SFID insulator dataset. After optimization with TensorRT, the actual inference speed of the IDD-YOLO model reached 20.83 frames per second (FPS), meeting the demands for accurate and real-time inspection of insulator defects by drones.

Hole detection is an important means of crack detection for aero-engine blades, and the current technology still mainly relies on manual operation, which may cause safety hazards for visual reasons. To address this problem, this paper proposes a deep learning-based, aero-engine blade crack detection model. First, the K-means++ algorithm is used to recalculate the anchor points, which reduces the influence of the anchor frame on the accuracy; second, the backbone network of YOLOv5s is replaced with Mobilenetv3 for a lightweight design; then, the slim-neck module is embedded into the neck part, and the activation function is replaced with Hard Sigmoid for redesign, which improves the accuracy and the convergence speed. Finally, in order to improve the learning ability for small targets, the SimAM attention mechanism is embedded in the head. A large number of ablation tests are conducted in real engine blade data, and the results show that the average precision of the improved model is 93.1%, which is 29.3% higher; the number of parameters of the model is 12.58 MB, which is 52.96% less, and the Frames Per Second (FPS) can be up to 95. The proposed algorithm meets the practical needs and is suitable for hole detection.

This paper proposes an effective material delivery algorithm to address the challenges associated with Unmanned Aerial Vehicle (UAV) material transportation and delivery, which include complex route planning, low detection precision, and hardware limitations. This novel approach integrates the Whale-Swarm Hybrid Algorithm (WSHA) with the APCR-YOLOv8 model to enhance efficiency and accuracy. For path planning, the placement paths are transformed into a Generalized Traveling Salesman Problem (GTSP) to be able to compute solutions. The Whale Optimization Algorithm (WOA) is improved for balanced global and local searches, combined with an Artificial Bee Colony (ABC) Algorithm and adaptive weight adjustment to quicken convergence and reduce path costs. For precise placement, the YOLOv8 model is first enhanced by adding the SimAM attention mechanism to the C2f module in the detection head, focusing on target features. Secondly, GhoHGNetv2 using GhostConv is the backbone of YOLOv8 to ensure accuracy while reducing model Params and FLOPs. Finally, a Lightweight Shared Convolutional Detection Head (LSCDHead) further reduces Params and FLOPs through shared convolution. Experimental results show that WSHA reduces path costs by 9.69% and narrows the gap between the best and worst paths by about 34.39%, compared to the Improved Whale Optimization Algorithm (IWOA). APCR-YOLOv8 reduces Params and FLOPs by 44.33% and 34.57%, respectively, with mAP@0.5 increasing from 88.5 to 92.4 and FPS reaching 151.3. This approach can satisfy the requirements for real-time responsiveness while effectively preventing missed, false, and duplicate detections during the inspection of emergency airdrop stations. In conclusion, combining bionic optimization algorithms and image processing significantly enhances the efficiency and precision of material placement in emergency management.

Printed circuit board (PCB) surface defect detection is an essential part of the PCB manufacturing process. Currently, advanced CCD or CMOS sensors can capture high-resolution PCB images. However, the existing computer vision approaches for PCB surface defect detection require high computing effort, leading to insufficient efficiency. To this end, this article proposes a local and global context-enhanced lightweight CenterNet (LGCL-CenterNet) to detect PCB surface defects in real time. Specifically, we propose a two-branch lightweight vision transformer module with local and global attention, named LGT, as a complement to extract high-dimension features and leverage context-aware local enhancement after the backbone network. In the local branch, we utilize coordinate attention to aggregate more powerful features of PCB defects with different shapes. In the global branch, Bi-Level Routing Attention with pooling is used to capture long-distance pixel interactions with limited computational cost. Furthermore, a Path Aggregation Network (PANet) feature fusion structure is incorporated to mitigate the loss of shallow features caused by the increase in model depth. Then, we design a lightweight prediction head by using depthwise separable convolutions, which further compresses the computational complexity and parameters while maintaining the detection capability of the model. In the experiment, the LGCL-CenterNet increased the mAP@0.5 by 2% and 1.4%, respectively, in comparison to CenterNet-ResNet18 and YOLOv8s. Meanwhile, our approach requires fewer model parameters (0.542M) than existing techniques. The results show that the proposed method improves both detection accuracy and inference speed and indicate that the LGCL-CenterNet has better real-time performance and robustness.

This research presents a comprehensive dynamic finite element analysis (FEA) of a cryogenic fuel tank made from an innovative aluminium/lithium–graphene nano-composite material, assessing its suitability for aerospace launch vehicles carrying cryogenic hydrogen and oxygen. The study focuses on the effects of lightweighting, utilizing 0.5 wt.% reinforced graphene in the Al 2195 matrix, a material poised to revolutionize the aerospace industry. Objectives include developing a digital twin of the fuel tank, CAD modeling to aerospace standards, and conducting ANSYS simulations under launch conditions to evaluate stress, strain, and deformation. Numerical results reveal a significant weight reduction of approximately 19,420 kg and a notable maximum stress reduction of 1.3% compared to traditional Al 2195 alloy tanks. The novelty of this research lies in its pioneering analysis of aluminium/lithium–graphene composites for lightweighting in cryogenic fuel tanks under space launch conditions. Conclusions affirm the composite’s viability, advocating for the development of lighter yet robust aerospace structures and fostering innovation in spacecraft design and materials science.

Fast and accurate counting and positioning of flowers is the foundation of automated flower cultivation production. However, it remains a challenge to complete the counting and positioning of high-density flowers against a complex background. Therefore, this paper proposes a lightweight flower counting and positioning model, Light-FC-YOLO, based on YOLOv8s. By integrating lightweight convolution, the model is more portable and deployable. At the same time, a new efficient detection head, Efficient head, and the integration of the LSKA large kernel attention mechanism are proposed to enhance the model’s feature detail extraction capability and change the weight ratio of the shallow edge and key point information in the network. Finally, the SIoU loss function with target angle deviation calculation is introduced to improve the model’s detection accuracy and target positioning ability. Experimental results show that Light-FC-YOLO, with a model size reduction of 27.2% and a parameter reduction of 39.0%, has a Mean Average Precision (mAP) and recall that are 0.8% and 1.4% higher than YOLOv8s, respectively. In the counting comparison experiment, the coefficient of determination (R2) and Root Mean Squared Error (RMSE) of Light-FC-YOLO reached 0.9577 and 8.69, respectively, both superior to lightweight models such as YOLOv8s. The lightweight flower detection method proposed in this paper can efficiently complete flower positioning and counting tasks, providing technical support and reference solutions for automated flower production management.

The extensive use of carbon fiber-reinforced composites and aluminum alloys represents the highest level of automotive body-in-white lightweighting. The effective and secure joining of these heterogeneous materials remains a prominent and actively researched topic within the scientific community. Among various joining techniques, clinching has emerged as a particularly cost-effective solution, experiencing significant advancements. However, the application of clinching is severely limited by the properties of the joining materials. In this work, various clinching processes for the joining of composites and aluminum alloys reported in recent research are described in detail according to three broad categories based on the principle of technological improvement. By scrutinizing current clinching technologies, a forward-looking perspective is presented for the future evolution of clinching technology in terms of composite–aluminum joints, encompassing aspects of tool design, process analysis, and the enhancement of joint quality. This work provides an overview of current research on clinching of CFRP and aluminum and serves as a reference for the further development of clinching processes.

In the field of defect detection in sewers, some researches focus on high accuracy. However, it is challenging for portable on-site devices to provide high performance. This paper proposes a lightweight sewer defect detection model, You Only Look Once (YOLO) v5-Sewer. Firstly, the backbone network of YOLOv5s is replaced with a stacked MobileNetV3 block. Secondly, the C3 module of the neck of YOLOv5s is improved with a C3-Faster module. Thirdly, to compensate for the accuracy loss due to the lightweight network, a channel attention (CA) and convolutional block attention module (CBAM) are added to the proposed method. Finally, the Efficient Intersection over Union (EIOU) is adopted as the localization loss function. Experimental validation on the dataset shows that YOLOv5-Sewer achieves a 1.5% reduction in mean Average Precision (mAP) while reducing floating-point operations by 68%, the number of parameters by 55%, and the model size by 54%, compared to the YOLOv5s model. The detection speed reaches 112 frames per second (FPS) with the GPU (RTX 3070Ti). This model successfully implements a lightweight design while maintaining the detection accuracy, enhancing its functionality on low-performance devices.

Distracted behavior detection is an important task in computer-assisted driving. Although deep learning has made significant progress in this area, it is still difficult to meet the requirements of the real-time analysis and processing of massive data by relying solely on local computing power. To overcome these problems, this paper proposes a driving distraction detection method based on cloud–fog computing architecture, which introduces scalable modules and a model-driven optimization based on greedy pruning. Specifically, the proposed method makes full use of cloud–fog computing to process complex driving scene data, solves the problem of local computing resource limitations, and achieves the goal of detecting distracted driving behavior in real time. In terms of feature extraction, scalable modules are used to adapt to different levels of feature extraction to effectively capture the diversity of driving behaviors. Additionally, in order to improve the performance of the model, a model-driven optimization method based on greedy pruning is introduced to optimize the model structure to obtain a lighter and more efficient model. Through verification experiments on multiple driving scene datasets such as LDDB and Statefarm, the effectiveness of the proposed driving distraction detection method is proved.

The paper presented studies on reducing traction energy consumption with a decrease in the weight of an all-metal gondola car. Based on the proposed mathematical criterion, a new form of a blind floor was obtained, which makes it possible to reduce the weight of an all-metal gondola car. The aim of the paper was to reduce traction energy consumption with a decrease in the weight of an all-metal gondola car. For an all-metal gondola car with a modified form of a blind floor, strength studies were performed based on the finite element method. The equivalent stresses of the blind floor of an all-metal gondola car were 140.6 MPa, and the equivalent strains were 7.08 × 10−4. The margin of safety of the blind floor of an all-metal gondola car was 1.57. The weight of an all-metal gondola car with a modified form of a blind floor was reduced by 5.1% compared to a typical all-metal gondola car. For an all-metal gondola car with a modified form of a blind floor, a comparison was made of the traction energy consumption with typical all-metal gondola cars. Traction energy consumption with empty all-metal gondola cars were reduced by 2.5–3.1%; with loaded all-metal gondola cars by 2.4–7.3%, depending on the travel time interval.

Due to the fact that the green features of papaya skin are the same colour as the leaves, the dense growth of fruits causes serious overlapping occlusion phenomenon between them, which increases the difficulty of target detection by the robot during the picking process. This study proposes an improved YOLOv5s-Papaya deep convolutional neural network for achieving dense multitarget papaya detection in natural orchard environments. The model is based on the YOLOv5s network architecture and incorporates the Ghost module to enhance its lightweight characteristics. The Ghost module employs a strategy of grouped convolutional layers and weighted fusion, allowing for more efficient feature representation and improved model performance. A coordinate attention module is introduced to improve the accuracy of identifying dense multitarget papayas. The fusion of bidirectional weighted feature pyramid networks in the PANet structure of the feature fusion layer enhances the performance of papaya detection at different scales. Moreover, the scaled intersection over union bounding box regression loss function is used rather than the complete intersection over union bounding box regression loss function to enhance the localisation accuracy of dense targets and expedite the convergence of the network model training. Experimental results show that the YOLOv5s-Papaya model achieves detection average precision, precision, and recall rates of 92.3%, 90.4%, and 83.4%, respectively. The model’s size, number of parameters, and floating-point operations are 11.5 MB, 6.2 M, and 12.8 G, respectively. Compared to the original YOLOv5s network model, the model detection average precision is improved by 3.6 percentage points, the precision is improved by 4.3 percentage points, the number of parameters is reduced by 11.4%, and the floating-point operations are decreased by 18.9%. The improved model has a lighter structure and better detection performance. This study provides the theoretical basis and technical support for intelligent picking recognition of overlapping and occluded dense papayas in natural environments.

An approach to the simulation of foamed injection molded Polypropylene parts subjected to impact loading is presented in this paper. The proposed method, which considers strain-rate-dependent material properties and the possible occurrence of fracture, is, in particular, suitable for parts manufactured with core-back technology. The method was developed to be used within the functionality of a commercial Finite Element solver using a shell-type element mesh. The material model is based on a three-layer structure, with two compact skin layers and a foamed core layer made of expanded material. The properties of the foamed material are assumed as those of the compact grade scaled by a suitable factor, which is identified via inverse engineering on a set of bending tests executed on specimens having different foam densities. The fracture of the material is then predicted using a damage model which considers the effects of triaxiality. The approach is then validated on industrial parts from the automotive sector, subjected to impact in a component test. Despite the simplicity of the presented approach, which makes this method suitable for industrial applications and especially for early-stage design, the validation shows a sufficiently accurate simulation of part behavior under the impact, with a reasonable prediction of damage and fracture.

Hybrid gears are composed of high-strength steel, carbon fiber reinforced plastic (CFRP), and adhesive bond to join these materials. In this study, the effect of rack tip radius (TR), drive side pressure angle (DSPA), and rim thickness (RT) on the stress of hybrid gears is investigated numerically. In addition, the stress results of hybrid gears are compared with steel gears that are used for validation of the numerical results. Single tooth stiffness (STS) values are calculated based on tooth deformations obtained from numerical analyses. The 2-DOF model is used to observe the influence of DSPA and RT on the dynamic factor (DF) and static transmission error (STE). According to the results, increasing RT has a positive effect on stress, STS, and STE, while DSPA is effective on the dynamic factor at most.

Topology optimization (TO) has been a popular design method among CAD designers in the last decades. This method optimizes the given design domain by minimizing/maximizing one or more objective functions, such as the structure’s stiffness, and at the same time, respecting the given constraints like the volume or the weight reduction. For this reason, the companies providing the commercial CAD/FEM platforms have taken this design trend into account and, thus, have included TO in their products over the last years. However, it is not clear which features, algorithms, or, in other words, possibilities the CAD designers do have using these software platforms. A comparative study among the most applied topology optimization software was conducted for this research paper. First, the authors developed an online database of the identified TO software in the form of a table. Interested CAD designers can access and edit its content, contributing in this way to the creation of an updated library of the available TO software. In addition, a deeper comparison among three commercial software platforms—SolidWorks, ANSYS Mechanical, and ABAQUS—was implemented using three common case studies—(1) a bell crank lever, (2) a pillow bracket, and (3) a small bridge. These models were designed, optimized, and validated numerically, as well as compared for their strength. Finally, the above software was evaluated with respect to optimization time, optimized designs, and TO possibilities and features.

Lightweighting is a design strategy to reduce energy consumption through the reduction of mass of a product. Lightweighting can be applied to machine tools to reduce the amount of energy consumed during the use phase. Thus, the energy cost of machine operation will be reduced. One might also hypothesize that since a lighter-weight machine tool requires less material to build, the cost to produce such a machine will be less. However, it may also be the case that lightweighting a machine tool increases its complexity, which will likely drive up the cost to manufacture the machine. To explore the cost drivers associated with building a machine tool, data on the features associated with a wide variety of vertical milling machine tools are collected. Then, empirical cost models are fit to this data. The results from the cost models show that the machine tool mass is a significant cost driver; other key drivers are the number of axes and spindle power. The models are used to predict the cost benefits of lightweighting in terms of mass, which are compared to potential increased manufacturing costs associated with complexities introduced due to lightweighting.

The use of fibre reinforced composite materials is one method by which the lightweighting of rail vehicles can be achieved. However, the issue of impact damage, amongst other challenges, limits their safety certification. This issue is accentuated by the high levels of loading a rail vehicle may be subjected to during service. This paper addresses the significance of pre-tension on large composite structures, specifically for a composite redesign of a pressure vessel for a freight tank wagon. Preloading was determined to be detrimental to the overall impact resistance of a large composite vessel. At 15.71 J of impact energy, there was a 22% increase in mean absorbed energy for a uniaxially loaded panel over an unloaded panel. However, there was only a 4% difference in penetration depth between uniaxial and biaxial loading. A novel finding from these results is that the effects of preloading are more profound if the loading does not act parallel to a principal fibre direction. Matrix cracking and delaminations are the most common failure modes observed for specimens under low-velocity impact and are intensified by preload.

In order to reduce the negative effect of lightweighting of suspension components on vehicle dynamic performance, the control arm and torsion beam widely used in front and rear suspensions were taken as research objects for studying the lightweight design method of suspension components. Mesh morphing technology was employed to define design variables. Meanwhile, the rigid–flexible coupling vehicle model with flexible control arm and torsion beam was built for vehicle dynamic simulations. The total weight of control arm and torsion beam was taken as optimization objective, as well as ride comfort and handling stability performance indexes. In addition, the fatigue life, stiffness, and modal frequency of control arm and torsion beam were taken as the constraints. Then, Kriging model and NSGA-II were adopted to perform the multi-objective optimization of control arm and torsion beam for determining the lightweight scheme. By comparing the optimized and original design, it indicates that the weight of the optimized control arm and torsion beam are reduced 0.505 kg and 1.189 kg, respectively, while structural performance and vehicle performance satisfy the design requirement. The proposed multi-objective optimization method achieves a remarkable mass reduction, and proves to be feasible and effective for lightweight design of suspension components.

The rising economic and environmental pressures associated with the generation and consumption of energy necessitates the need for lightweighting of railway vehicles. The railway axle is a prime candidate for lightweighting of the unsprung mass. The reduction of unsprung mass correlates to reduced track damage, energy consumption and total operating costs. This paper presents the design of a lightweight multifunctional hybrid metallic-composite railway axle utilising coaxial skins. The lightweight axle assembly comprises a carbon fibre reinforced polymer composite tube with steel stub axles bonded into either end. The structural hybrid metallic-composite railway axle is surrounded by coaxial skins each performing a specific function to meet the secondary requirements. A parametric sizing study is conducted to explore the sensitivity of the design parameters of the composite tube and the stub axle interaction through the adhesive joint. The optimised design parameters of the axle consist of a; composite tube outer diameter of 225 mm, composite tube thickness of 7 mm, steel stub axle extension thickness of 10 mm and a bond overlap length of 100 mm. The optimised hybrid metallic-composite railway axle design concept has a mass of 200 kg representing a reduction of 50% over the solid steel version.

Lightweighting is one of the key solutions to reduce the carbon footprint of vehicles. Nowadays, it is still challenging to achieve this target because there is a conflict between the cost and final material performance, as well as the fact that many lightweight solutions are restricted to laboratory or small-scale production. In this work, a commercially feasible strategy was adopted to fabricate materials for lightweight applications. Hollow glass bubbles, jute fibres, and rubber powder were used as fillers with polypropylene as the base polymer. Various samples were fabricated using conventional and MuCell® injection moulding. Their performance was then characterised by their density and morphological, mechanical, and rheological properties. A comparison among hybrid fillers/polypropylene compounds with and without MuCell® technology was investigated. The filler hybridisation resulted in not only a density reduction of up to approximately 10%, but also improved tensile/flexural modulus and strength. The use of MuCell® led to a further reduction in density of roughly 10%. Meanwhile, although some compounds fabricated by MuCell® exhibited some deterioration in their tensile yield strength, tensile modulus, and impact strength, they maintained acceptable mechanical properties for automotive applications.

A thorough assessment of Life-Cycle effects involved by vehicle lightweighting needs a rigorous evaluation of mass-induced consumption, on which energy and sustainability benefits during use stage directly depend. The paper proposes an analytical calculation procedure to estimate the weight-related energy consumption of pure Electric Vehicles (EVs), since existing literature leaves considerable room for improvement regarding this research area. The correlation between consumption and mass is expressed through the Energy Reduction Value (ERV) coefficient, which quantifies the specific consumption saving achievable through 100 kg mass reduction. The ERV is estimated for a number of heterogeneous case studies derived from real 2019 European market EV models and according to three drive cycles, to consider different driving behaviors. For the case studies under consideration, ERV ranges from 0.47 to 1.17 kWh/(100 km × 100 kg), with the variability mainly depending on vehicle size and driving cycle. Given the high uncertainty of mass-related consumption on car size, an analytical method is refined to estimate accurately the ERV for any real-world EV model, starting from vehicle technical features. Along with energy assessment, the research also evaluates the environmental implications of lightweight design by means of the Impact Reduction Value (IRV), which is estimated for three distinct electricity grid mixes. Finally, the ERV/IRV modeling approach is applied to a series of comparative lightweight case studies taken from the literature. Such an application demonstrates the effective utility of the work to reduce the uncertainty for all cases where no physical tests or computer-aided simulations are available.