Picking robots have become an important development direction of smart agriculture, and the position detection of fruit is the key to realizing robot picking. However, the existing detection models ...have the shortcomings of missing detection and slow detection speed when detecting dense and occluded grape targets. Meanwhile, the parameters of the existing model are too large, which makes it difficult to deploy to the mobile terminal. In this paper, a lightweight GA-YOLO model is proposed. Firstly, a new backbone network SE-CSPGhostnet is designed, which greatly reduces the parameters of the model. Secondly, an adaptively spatial feature fusion mechanism is used to address the issues of difficult detection of dense and occluded grapes. Finally, a new loss function is constructed to improve detection efficiency. In 2022, a detection experiment was carried out on the image data collected in the Bagui rural area of Guangxi Zhuang Autonomous Region, the results demonstrate that the GA-YOLO model has an mAP of 96.87%, detection speed of 55.867 FPS and parameters of 11.003 M. In comparison to the model before improvement, the GA-YOLO model has improved mAP by 3.69% and detection speed by 20.245 FPS. Additionally, the GA-YOLO model has reduced parameters by 82.79%. GA-YOLO model not only improves the detection accuracy of dense and occluded targets but also lessens model parameters and accelerates detection speed.
It is difficult to comprehensively master and precisely regulate the external factors distribution of automobile weathering in non-uniform thermal environment as well as the consequent disequilibrium ...weathering problem, while exploring weather-resistant materials in uniform thermal environment. Thus, a numerical calculation method for the weathering external factors is proposed, on the basis of annual experimental study on the outdoor weathering inconsistencies of auto-parts. The time–space distribution characteristics and day–night variation rules of the external factors are studied, and the disequilibrium weathering mechanism among parts is revealed from the perspective of non-uniform distribution of external factors. The laws of automotive physical parameters, orientations and locations, as well as their influences on external factors distribution are analyzed in detail, and hereby the targeted schemes to effectively reduce the local external factor intensity and the thermal gradient between parts are investigated. The method can be used to rapidly predict weathering external factors distribution of vehicle exposed to outdoor in any direction during day and night, so as to provide auto-parts with differentiated test schemes in accelerated tests and IP/DP box tests, and it also contributes to present some pertinence guidance for the accurate regulation of automobile disequilibrium weathering on regions at different levels.
In online battery model identification by recursive least squares (RLS), the identification biases are generated by the noises in the voltage and current measurements, further resulting in the ...accuracy degradation of model-based state of charge (SOC) estimation. Firstly, the detailed formula derivation presents the relationship between noise variances and identification biases in least squares. Then, through the practical identification on a general battery model, the consistent results from the formulas and simulations both adequately and quantitatively verify that the model identified by RLS is biased, when either only one of voltage and current measurements or both are corrupted by noises. To further assess the noise effects on SOC and parameter estimations, a conventional co-estimation algorithm joining RLS and extended Kalman filter (EKF) is applied into the simulations and experiments especially under noise corrupted measurements, the numerical results show that the estimation accuracy degradation generated by noises is quite considerable. Hence, bias compensation RLS and EKF co-estimation algorithms are proposed to alleviate the impact of the noises. Simulation and experiment studies show that the proposed algorithms can compensate the model identification biases caused by noises and can enhance SOC estimation accuracy under noise corrupted measurements.
•Noise corruption on battery model identification bias in RLS is investigated.•Biases generated even only voltage or current measurement is corrupted by noise.•Noise effect on conventional RLS based co-estimation algorithm is investigated.•Three bias compensation RLS based co-estimation algorithms are proposed.•The superiority of the proposed methods is verified by simulations and experiments.
This review concentrated on proton exchange membrane fuel cell (PEMFC) water management, which introduces the latest research contents and progresses on membrane electrode assembly (MEA) components, ...and summarizes the influencing factors about the properties of them. The PEMFC's core component is MEA which consists of proton exchange membrane, catalyst layer, microporous layer and carbon fiber paper. The properties of each component have significant impacts on the fuel cell (FC) performance, and there will be strong interactions between some properties. Therefore, the FC performance is determined by the properties of each component and their interactions. It is the basis for the design of the high-performance FCs to clarify the influence mechanism of various properties and their interactions on the FC performance, but there is currently no summary on this aspect. Therefore, the conclusions about the same component or property drawn from all literatures are sorted and combined, so that we can intuitively know which literatures have studied and reached the conclusions, and comprehensively realize the influence mechanism of a certain property. Based on the development and achievement of each component in some aspects, this article makes some predictions and discussions on the future research direction and development prospects of each component.
•The influence relationships between the properties of MEA components are discussed.•The influences of MEA components' properties on fuel cell performance are analyzed.•Pointed out the ambiguity in some conclusions and explained the possible reasons.•The joint effect of MEA components on the water management capability are presented.
In the paper, crashworthiness of the S-shaped rail extracted from the frontal frame in a car is studied. In order to reduce the peak impact force while increasing the total absorbed energy, the ...hybrid materials are employed in that rail, where aluminum alloy is used for its front part and advanced high strength steel (AHSS) for its back part. By designing 16 experiments based on orthogonal experiment, the effect of five influence factors with four levels on the crash performance of the steel–aluminum hybrid S-shaped front rail is emphatically investigated. These influence factors include the different material types of aluminum alloy and AHSS, the sheet thicknesses of the two parts, and length proportion for the aluminum part. The AHSS includes dual-phase (DP) steel, transformation induced plasticity (Trip) steel and Mart steel; the aluminum alloy series include 5000 and 6000 series. The research result shows that the use of steel–aluminum hybrid materials can reduce the peak impact force and the total weight for the S-shaped front rail, while the total absorbed energy can be greatly increased, so the crashworthiness and lightweight of the S-shaped front rail are significantly improved.
Focusing on the problem that corn plant in different growth periods is grayed out by known methods, the gray scale difference of different part is large or the soil discrimination degree is not high, ...the navigation path is low in accuracy and speed. This paper proposed a new method for extracting cornfield navigation baselines, which is used to control walking of agricultural robots. Design method included image segmentation, navigation point extraction, and navigation path fitting. Image segmentation is based on a new grayscale factor combined with median filtering, OSTU method and morphological operations to achieve the separation of crops and soil. The extraction of the navigation point is based on the binary image vertical projection map to obtain the region of interest, and the navigation point coordinates are determined by calculating the relative center point of the white pixel points of the sampling line in the region of interest. The Hough transform is used to fit the navigation point obtained by the vertical projection map to determine the navigation path, and then the control parameters are obtained. The gray scale factor that is improved in this paper combined with the vertical projection map can extract the target ridge with an accuracy rate of 92%, and the accuracy of extracting the navigation line is more than 90%. When conducting navigation tracking experiments in corn field, the maximum error is 5cm.
RESUMO: Depois de usar o método conhecido como escala de cinza para plantas de milho, a diferença de escala de cinza entre diferentes partes da planta é grande ou a diferenciação do solo não é alta, a precisão do trajeto de navegação é baixa e a velocidade é lenta. Neste trabalho foi proposto um novo método de extração da linha de referência de navegação para campos de milho, que é usado para controlar a caminhada de robôs agrícolas. Os métodos de projeto incluem: segmentação de imagem, extração de ponto de navegação e encaixe de linha de navegação. A segmentação por imagem é baseada na separação de culturas e solos com base no novo fator de escala de cinza combinado com a filtragem mediana, método de Otsu e operação morfológica. A extração de pontos de navegação é baseada em um mapa de projeção vertical de imagem de dois valores para obter a área de interesse, e as coordenadas do ponto de navegação são determinadas por cálculo do ponto central relativo no pixel branco da linha amostral na área de interesse. O fator de escala de cinza melhorado nesta pesquisa irá extrair o centro da entre linha de plantio alvo com uma taxa de precisão de 92%. A precisão de extração da linha de navegação é mais de 90%. O erro máximo foi de 5cm quando o experimento de rastreamento de navegação em tempo foi é realizado em campos de milho.
Celotno besedilo
Dostopno za:
DOBA, IZUM, KILJ, NUK, PILJ, PNG, SAZU, SIK, UILJ, UKNU, UL, UM, UPUK
Currently, many research from domestic and foreign on improving anti-rollover performance of vehicle mainly focus on the electronic control of auxiliary equip- ment, do not make full use of ...suspension layout to optimize anti-rollover performance of vehicle. This investigation into anti-rollover propensity improvement concentrates on the vehicle parameters greatly influencing on anti-rollover propensity of vehicle. A simulation based on fishhook procedure is used to perform design trials and evaluations aimed at ensuring an optimal balance between vehicle's design parameters and various engineering capacities, the anti-rollover propensity is optimized at the detailed design stage of a new SUV model. Firstly a four-DOF theoretical kinematic model is established, then a complete multi-body dynamics model built in ADAMS/car based on the whole vehicle parameters is correlated to the objective handing and stability test results of a mule car. Secondly, in fish- hook test simulations, the Design of Experiments method is used to quantify the effect of the vehicle parameters on the anti-rollover performance. By means of the simulation, the roll center height of front suspension should be more than 30 mm, that of rear suspension less than 150 mm, and the HCG less than 620 mm for the SUV. The ratio of front to rear suspension roll stiffness should be ranged from 1.4 to1.6 for the SUV. As a result, at the detailed design stage of product, the anti-rollover performance of vehicle can be improved by optimizing chassis and integrated vehicle parameters.
The dynamics of assembled structures are significantly dependent on joints. Joints parameters, owing to be difficultly measured, are always ignored by pure rigid in numerical modeling and it will ...result in unreliable or even error descriptions. 1 ~ 3 Hz deviations may cause resonance especially in engineering optimization issues; hence it is necessary to identify joints parameters for structural dynamics investigation. In present work, multiobjective optimization algorithms are used to identify joints parameters by approaching actual test results in each series of structure to decrease unreliable or error for numerical modeling. Taking automotive dynamics with seam-welding and spot-welding as examples, the relationship of joints parameters perturbation and structural dynamics is derived to give the selecting reason of parameters’ identification. The actual dynamics of an SUV’s frame and a thin-walled part in BIW (body in white) are utilized to validate the methodology. Results demonstrate that the validated model has enough accuracy to reflect the dynamics of the actual structure. The methodology provides reliable guarantee for dynamic analysis and the design of structure.
In order to realize the fuel cell (FC) operation with higher power density, researchers have made various attempts to it. The innovative design of bipolar plate (BPP) can contribute about 20% to the ...volumetric power density increase. Mass transfer and drainage capacity are two keys of plate design. In order to improve its mass transfer capacity, many improvements have been made, such as baffle flow field (FF) and biomimetic FF. These FFs have their own advantages and disadvantages. For facilitate comparison, this article summarizes the influence of various FF designs, structures, flow patterns and other parameters on FC performance, and gives the BPP's development direction in the future. The effects of different FF structures, geometric parameters and arrangement forms on the uniformity of i distribution are summarized. The effects of contact area, channel design parameters such as channel width/rib ratio, fillet radius and channel size on the BPP's interfacial contact resistance are reviewed. Guidance is provided for designing FFs that can achieve more uniform i distribution and smaller contact resistance. The main manufacturing processes of BPPs are reviewed, and then the difficulties that need to be overcome in order to manufacture higher performance BPPs are pointed out.
•The influences of various BPP flow field designs on FC performance are summarized.•The effects of BPP on current distribution and contact resistance are summarized.•The fabrication process of BPPs and existing difficulties are summarized.•The development directions of BPP fabrication and flow field design are predicted.