Rapid and non-destructive estimation of leaf flavonol content (Flav) is important for assessing crop physiological status and stress response. In this study, unmanned aerial vehicle (UAV)-based red, green, and blue (RGB) and multispectral imagery was used to estimate sunflower leaf Flav across the seedling, budding, flowering, and maturity stages. Data were collected at a single experimental site in the Yellow River Delta, China, during the 2025 growing season. UAV images were acquired at flight heights of 30 m, 50 m, and 80 m, and ground measurements of Flav were obtained within the same acquisition window using an MPM-100 plant multispectral pigment meter. A total of 320 plot-level observations were obtained from 80 sampling plots, which were divided at the plot level into 56 training plots and 24 testing plots, with all four growth-stage observations from the same plot assigned to the same subset. Feature selection and model development were conducted using the training data, which were further divided for hyperparameter optimization, whereas the testing set was used for comparative performance evaluation. A total of 44 UAV-derived features, including 22 vegetation indices, 16 texture features, and six color features, were extracted from sunflower canopy imagery. Pearson correlation coefficient (PCC) analysis and the Boruta algorithm were combined to identify compact feature subsets, and six regression models, including K-nearest neighbors, random forest, CatBoost, support vector regression, LightGBM, and Transformer regression, were evaluated. Genetic algorithm (GA), particle swarm optimization (PSO), and grey wolf optimizer (GWO) were further used to tune the Transformer model at the intermediate flight height of 50 m. The PCC-Boruta strategy reduced feature dimensionality and produced favorable predictive performance on the testing set. Among the evaluated regression models, the Transformer model achieved the best overall performance. Using the optimal feature combination, the PCC-Boruta-Transformer model obtained test-set R2 values of 0.932, 0.911, and 0.909 at 30 m, 50 m, and 80 m, respectively, with corresponding root mean square error (RMSE) values of 0.060, 0.069, and 0.070. Thus, the 30 m model provided the highest predictive accuracy among the three unoptimized flight-height models. The 50 m dataset, representing the intermediate level among the three evaluated flight heights, was used for subsequent hyperparameter optimization. Among the evaluated optimization configurations, the GWO-tuned Transformer achieved the best observed testing-set performance, with an R2 of 0.947 and an RMSE of 0.053. These results demonstrate the feasibility of the evaluated workflow under the specific site, growing-season, sensor, and management conditions of this experiment.

Conventional fixed time-delay control (FTDC) is limited by its design, which requires compromise optimization across the entire frequency domain, resulting in constrained overall performance under broadband road excitations. This study reveals that vibration reduction performance can be significantly enhanced if the time-delay control parameters adapt in real-time to varying excitation frequencies. Based on this finding, a novel frequency domain optimized Time-Varying Delay Control (TVDC) strategy is proposed for preview suspension systems. The proposed framework utilizes the Short-Time Fourier Transform (STFT) to perform time-frequency analysis on the predicted road profile within the preview horizon, thereby extracting dominant frequency components. To reduce real-time computational complexity, an equivalent frequency band is introduced to represent the main excitation, and Particle Swarm Optimization (PSO) is employed to dynamically optimize the control parameters within this band. Experiments conducted on a proportionally scaled-down suspension model show that, compared to FTDC under Class C road excitation, the TVDC strategy reduces the root mean square (RMS) values of vehicle body acceleration, velocity, and displacement by 10.9%, 8.2%, and 20.48%, respectively. This preliminarily validates the effectiveness of the proposed method, providing a preliminary foundation for future real-vehicle applications.

In crop breeding experiments, numerous breeding plots are established, requiring unmanned vehicles to autonomously navigate to designated locations based on breeding material identifiers, for phenotypic data collection. Currently, the identification of navigation target points largely relies on manual measurement. To address this limitation, this study proposes a path planning method for phenotyping vehicles in breeding fields, integrating RGB imagery acquired by unmanned aerial vehicles (UAVs) with an improved A* algorithm. The method begins with UAV image mosaicking and geometric correction. Orthophotos and DSMs are then generated. Regions of interest (ROIs) are then extracted and rectified based on affine transformation principles. The colour space of each ROI is converted from RGB to HSV. Rough locations of breeding plots are identified using an energy function method combined with a Savitzky-Golay filter, and precise plot boundaries are subsequently extracted through further application of the energy function method. This approach achieves an average Intersection over Union (IoU) of 95.17% for individual plots, with maximum and minimum rates of 99.8% and 87.8%, respectively. Navigable areas between breeding plots are derived from the DSM. A theoretical roll angle calculation method is developed by simulating the motion of an unmanned vehicle within the field, allowing traversability weights across these areas to be assessed. The A* algorithm is improved by incorporating jump point search (JPS) and diagonal distance heuristics. The improved algorithm then performs path planning by integrating these traversability weights. Simulation results show that the improved algorithm reduces travel distance by 32.12% and planning time by 72.69% compared with the conventional A* algorithm. Field trials in maize breeding plots further validate that the proposed method, based on DSM and the improved A* algorithm, effectively guides unmanned vehicles to avoid highly uneven terrain and select optimal travel paths.

Sunflower is one of the preferred oil crops in the mildly to moderately saline-alkali soils,due to its strong tolerance to nutrient-poor soils and drought.Among them,sunflower disk rot can be caused by sclerotinia sclerotiorum infection,leading to increasing sterile seed rates.Nutritional components can also decline,such as kernel protein and oil content.Thereby,both the edible and commercial value of the seeds are often required for high yield.Consequently,it is crucial to efficiently and accurately detect disk rot severity for early disease control,precision pesticide application,and yield estimation.However,conventional disease classification has been limited to manual efficiency and subjectivity in recent years.In this study,an improved YOLOv12n-RCL model was proposed to detect the severity of sunflower disk rot at the mature stage.1)C3K2-RC modules were used to replace C3K2 ones in the backbone and neck networks.Receptive-field attention convolution(RFAConv)and coordinate attention(CA)mechanisms were integrated to enhance the feature extraction from the different severity grades of disk rot in complex environments.2)A lightweight upsampling operator,CARFAE,was integrated into the neck network for feature reconstruction.3)A lightweight shared convolutional detection head with separated batch normalization(LSCSBD)was introduced to improve the detection accuracy and speed for small-scale lesions.Experimental results show that the YOLOv12n-RCL model achieved a precision,recall,mAP0.5,and mAP0.5～0.95 of 83.4％,81.2％,84.8％,and 50.2％,respectively,which was improved by 3.8,3.2,3.4,and 4.0 percentage points over the baseline model.The number of parameters,computational complexity,and model size were reduced to 2.11 M,5.7 GFLOPs,and 4.5 MB,respectively,corresponding to reductions of 17.9％,12.3％,and 19.6％,compared with the original model.The normalized confusion matrix indicated that the recall for the disease severity grades 0,1,2,3,and 4 were 83.0％,81.2％,79.1％,80.7％,and 82.0％,respectively,indicating a balanced recognition over all five grades.Furthermore,8.2％of samples with a true label of grade 2 were misclassified as grade 3,and 9.3％of samples with a true label of grade 3 were misclassified as grade 2.Therefore,the confusion between severity grades occurred primarily between grades 2 and 3.The misclassification rate remained below 10％in the rest,indicating its strong performance for the disk rot at different grades.A field test was conducted on 70 images with 1298 samples of different grades of disk rot.The YOLOv12n-RCL model achieved only 10 missed detections and 8 false detections.Compared with the baseline YOLOv12n model,the superior performance was achieved with a higher frame rate of 27.5 frames per second(FPS).Visualization was also conducted on the sunflower disk rot areas using UAV orthophotography.The improved model maintained stable performance even in complex scenarios with dense target distribution and leaf occlusion,without significantly missing or false detections.In summary,the YOLOv12n-RCL model improved the detection accuracy to effectively balance the lightweight deployment efficiency.The finding can also serve as an algorithmic reference to detect the sunflower disk rot at the mature stage in smart agriculture.

In response to the global concern for carbon emission reduction and the challenges posed by climate change, the efficient conversion of energy across different forms is essential for modern energy systems and power plants. Thus, a novel hydrogen-fueled hydraulic engine (HFHE) is proposed in this study, capable of directly converting hydrogen energy into hydraulic energy while simultaneously outputting both mechanical and hydraulic energy. An integrated HFHE model, which accounts for time-varying and nonlinear factors, is established by modeling the internal combustion engine and the integrated synchronous plunger pump using GT-Power and AMESim, respectively, with data exchange facilitated through Simulink. The results indicate that efficiency improvements in the HFHE are primarily concentrated in medium-speed conditions, and the regulation of mechanical and hydraulic energy distribution significantly influences system efficiency. With increasing hydraulic load pressure (HLP), efficiency improvements gradually rise, and the peak efficiency region shifts toward lower mechanical load conditions. A maximum system efficiency of 43.8% is achieved under an HLP of 8 MPa, a mechanical load of 38 N m, and a speed of 1600 rpm. Parameter analysis further reveals that speed exerts a significantly greater impact on system efficiency and output power compared to HLP and air-fuel ratio.

Expanding the path of hydrogen energy conversion and utilization is beneficial to carbon emission reduction, so this research proposes a hydrogen-fueled hydraulic engine (HFHE) that uses green hydrogen energy at the energy input side, and integrates mechanical and hydraulic energy at the energy output side. In order to have a command of the effects of main operating parameters on characteristics of HFHE, the compression ratio (CR) and hydrogen blending ratio (HBR) are adjusted in the range of 14 to 18 and 0 %-30 %, respectively, on the basis of HFHE model. The results show that, the increase of CR and HBR is beneficial for performance, combustion and energy efficiency of HFHE generally, but too large CR may lead to a decrease in hydraulic power, and improper HBR easily leads to early ignition and lower efficiency. In addition, the working state may be rough under low speed, high CR and HBR conditions.

The electro-hydraulic hybrid system has emerged as a critical technology in new energy vehicles, owing to the remarkable power density and efficient energy regeneration capabilities of hydraulic technology, coupled with the high energy density of electric power. This system effectively enhances vehicle range and battery life. We developed an energy management strategy (EMS) for the electro-hydraulic hybrid system (EHHS) to ensure smooth energy conversion, while ensuring the full utilization of electrical and hydraulic energy within a reasonable and efficient range. To enhance the system’s overall performance, it is imperative to address pivotal technologies, including power coupling and energy management. In this research, the structure of an electro-hydraulic hybrid vehicle (EHHV) is classified, compared and discussed. The application of existing EHHVs is studied. Subsequently, an analysis and summary are conducted on the current status and development trends of EMSs and collaborative operation control strategies (COCSs), and a novel mechanical-electro-hydraulic power-coupled system (MEHPCS) is put forward that successfully converts mechanical, electrical, and hydraulic energy in performance. Simultaneously, other applications of the system are forecasted. Finally, some suggestions for the electro-hydraulic hybrid systems’ future development are made. This study can promote the development of sustainable transportation technologies. The system integrates mechanical engineering, control theory, and environmental science, enabling interdisciplinary methodological innovation. In addition, relevant studies provide data support for policy makers by quantifying energy consumption indicators.

In order to accurately obtain the seedling emergence rate of breeding sunflower and to assess the quality of sowing as well as the merit of sunflower varieties, a method of extracting the sunflower seedling emergence rate using multi-source remote sensing information from unmanned aerial vehicles is proposed. Visible and multispectral images of sunflower seedlings were acquired using a UAV. The thresholding method was used to segment the excess green image of the visible image into vegetation and non-vegetation, to obtain the center point of the vegetation to generate a buffer, and to mask the visible image to achieve weed removal. The components of color models such as the hue–saturation value (HSV), green-relative color space (YCbCr), cyan-magenta-yellow-black (CMYK), and CIELAB color space (L*A*B) models were compared and analyzed. The A component of the L*A*B model was preferred for the optimization of K-means clustering to segment sunflower seedlings and mulch using the genetic algorithm, and the segmentation accuracy was improved by 4.6% compared with the K-means clustering algorithm. All told, 10 geometric features of sunflower seedlings were extracted using segmented images, and 10 vegetation indices and 48 texture features of sunflower seedlings were calculated based on multispectral images. The Pearson’s correlation coefficient method was used to filter the three types of features, and the geometric feature set, the vegetation index set, the texture feature set, and the preferred feature set were constructed. The construction of a sunflower plant number estimation model using the crested porcupine optimizer–support vector machine is proposed and compared with the sunflower plant number estimation models constructed based on decision tree regression, BP neural network, and support vector machine regression. The results show that the accuracy of the model based on the preferred feature set is higher than that of the other three feature sets, indicating that feature screening can improve the accuracy and stability of models; assessed using the CPO-SVR model, the accuracy of the preferred feature set was the highest, with an R² of 0.94, an RMSE of 5.16, and an MAE of 3.03. Compared to the SVR model, the value of the R2 is improved by 3.3%, the RMSE decreased by 18.3%, and the MAE decreased by 18.1%. The results of the study can be cost-effective, accurate, and reliable in terms of obtaining the seedling emergence rate of sunflower field breeding.

In order to improve the accuracy of multispectral image inversion of soil and plant analytical development (SPAD) of the cotton canopy, image segmentation methods were utilized to remove the background interference, such as soil and shadow in UAV multispectral images. UAV multispectral images of cotton bud stage canopies at three different heights (30 m, 50 m, and 80 m) were acquired. Four methods, namely vegetation index thresholding (VIT), supervised classification by support vector machine (SVM), spectral mixture analysis (SMA), and multiple endmember spectral mixture analysis (MESMA), were used to segment cotton, soil, and shadows in the multispectral images of cotton. The segmented UAV multispectral images were used to extract the spectral information of the cotton canopy, and eight vegetation indices were calculated to construct the dataset. Partial least squares regression (PLSR), Random forest (FR), and support vector regression (SVR) algorithms were used to construct the inversion model of cotton SPAD. This study analyzed the effects of different image segmentation methods on the extraction accuracy of spectral information and the accuracy of SPAD modeling in the cotton canopy. The results showed that (1) The accuracy of spectral information extraction can be improved by removing background interference such as soil and shadows using four image segmentation methods. The correlation between the vegetation indices calculated from MESMA segmented images and the SPAD of the cotton canopy was improved the most; (2) At three different flight altitudes, the vegetation indices calculated by the MESMA segmentation method were used as the input variable, and the SVR model had the best accuracy in the inversion of cotton SPAD, with R2 of 0.810, 0.778, and 0.697, respectively; (3) At a flight altitude of 80 m, the R2 of the SVR models constructed using vegetation indices calculated from images segmented by VIT, SVM, SMA, and MESMA methods were improved by 2.2%, 5.8%, 13.7%, and 17.9%, respectively, compared to the original images. Therefore, the MESMA mixed pixel decomposition method can effectively remove soil and shadows in multispectral images, especially to provide a reference for improving the inversion accuracy of crop physiological parameters in low-resolution images with more mixed pixels.

As the main energy consumption terminal and emission source, the engine is expected to achieve zero carbon emission with the help of hydrogen energy. Focusing on the current status and difficult issues of hydrogen engine research, this paper firstly emphasizes the importance of applying hydrogen energy in the future development of engines, secondly reviews and summarizes the development of hydrogen engines in terms of traditional structural inheritance and innovation, and then provides updated ideas for the development route of pure hydrogen fuel and the promotion of hydrogen fuel applications from the perspective of new combined fuels and industrialization challenges. A summary of the classification of hydrogen engine operating strategies is included to point out the prevailing regulation and influencing factors on hydrogen engines and the understanding of the working process. The obstacles to industrialization are related to a broader field, besides the field of scientific research, there are issues of infrastructure development, cost control, and safety standards development.

Compared with the traditional automotive suspension, hydro-pneumatic suspension has the characteristics of large energy storage ratio, nonlinear stiffness and can change the ground clearance of the vehicle body, which makes the vehicle have good ride comfort and handling stability during driving. In order to improve the performance of hydro-pneumatic suspension, it is necessary to design hydro-pneumatic suspension test bench for performance test. Aiming at the problem that the output signal of the mechanical test bench used in China is single and has large error, which is difficult to meet the performance test requirements of hydro-pneumatic suspension, a hydro pneumatic suspension test bench based on electro-hydraulic proportional control is designed. Through AMESim/MATLAB joint system modeling and simulation, in the tracking comparison of sinusoidal signal, compared with the traditional PID control method, the fuzzy PID control method reduces the error by 56.8% and the lag time by 70%; Through the experimental analysis of hydro-pneumatic suspension elastic force characteristic diagram, indicator diagram and damping force velocity characteristic diagram, the error rate of the test bench in sinusoidal signal tracking experiment is less than 15%, which meets the test requirements of hydro-pneumatic suspension.

The suspension system’s performance has a direct impact on the ride comfort, handling stability, and driving safety of heavy vehicles. The active air suspension of heavy vehicles can adjust the stiffness, damping parameters, and body height in real-time based on different road conditions. This adjustment ensures that the entire vehicle experiences a smooth ride while also making vehicle loading and unloading more labor efficient. Additionally, the active air suspension system enables the vehicle to achieve automation and intelligence. This study focused on a particular 6 × 4 heavy vehicle and designed an active air suspension system that aligns with the vehicle parameters of the heavy truck. Through the use of a fuzzy PID active control strategy, this study investigated and analyzed the height adjustment of the air spring. The results indicate that at a vehicle speed of 60 km/h on a class A road surface, the vehicle body’s vertical acceleration was reduced by 22.1%, and the dynamic travel of the suspension was reduced by 20.1%. This indicates that the fuzzy PID active air suspension system effectively reduces the vehicle’s vibrations and improves ride comfort.

By effectively integrating traditional engines with reciprocating plunger pumps, the constrained piston hydraulic engine can simultaneously output hydraulic energy and rotational mechanical energy, which effectively solves the problems of the complex structure, long power transmission chain, and low energy conversion efficiency of traditional power sources. Based on a certain single-cylinder diesel engine, a single-cylinder axial constrained piston hydraulic engine was designed, and its thermal–mechanical–liquid coordination mechanism was studied and analyzed in-depth. A mathematical model of the thermal–mechanical–liquid coupling working process of the single-cylinder axial hydraulic engine was established, and the conversion mechanism and output of the three types of energy, thermal, mechanical, and liquid, were simulated and analyzed. The results show that under the premise of improving the overall efficiency, the constrained piston hydraulic engine can effectively output mechanical–hydraulic dual-element power, and its combustion characteristics and output power performance indicators meet the expected design requirements. The maximum amplitude difference of the output hydraulic oil flow rate reaches 248 L/min, and the flow rate fluctuates greatly, so it is necessary to adopt methods to suppress the flow rate pulsation to ensure the reliability of the output flow rate.

Electro-hydraulic hybrid vehicles(EHHVs) have shown astonishing advantages in energy utilization and recovery. However, the key factor affecting the energy efficiency lies in the selection and switching conditions of driving modes. This paper introduces the structure and working principle of an electro-hydraulic hybrid vehicle that combines planetary gear mechanism. And an energy active regulation management strategy combined with driving mode recognition(DMR) and fuzzy control strategy is proposed. Firstly, a driving mode feature parameter evaluation is presented based on the collected speed and the principal component analysis(PCA). Secondly, K-means clustering algorithm is applied to identify offline driving modes through the extraction of driving short cycles. Then, combined with the PCA results, a Learning Vector Quantization neural network(LVQ) is constructed to recognize driving modes. Simultaneously, a fuzzy controller is added to allocate torque ratio. Finally, the DMR and fuzzy controller are combined to realize the energy active regulation of motors and hydraulic pump/motor. Experimental results indicate that energy management strategies based on DMR and fuzzy controller can realize optimal switching between modes according to condition recognition. It improves the utilization rate of the accumulator, and reduces battery energy consumption compared with traditional strategies.

To solve the brake caliper disc brake piston sealing ring in the high temperature, pressure, and changeful, complex working environments, such as vibration failure cause brake short service life, low reliability, in the original brake piston O seal ring and cross section, the research, based on the standard of sealing ring, such as special-shaped seal structure is put forward in order to improve the reliability of the caliper disc brake piston sealing performance. Based on the basic concept of time-varying reliability and the theoretical basis of stress-strength interference model, the time-varying reliability model of the plum blossom seal ring of the brake piston under shear stress failure and leakage failure modes was established. The reliability of the plum blossom seal ring under single failure mode and multiple failure modes is obtained. The results show that under the same conditions, the reliability of the plum blossom seal ring is greater than that of the O seal ring, and its sealing performance is better than that of the O seal ring.

单缸轴向约束活塞液压发动机作为一种新型的双元动力源,通过活塞销与柱塞的直接连接和保留传统发动机的曲柄连杆机构,使其可以同时输出液压能和旋转机械能,而且在机-液能量转化上,缩短动力传递链,减小能量损失,但是单缸发动机工作存在不稳定性,容易引起输出高压油的流量脉动较大.通过AMESim仿真软件搭建单缸轴向约束活塞液压发动机机-液工作仿真模型,对机-液动力传递链中的柱塞运动特性、泵腔流量特性、输出液压油脉动特性进行研究,仿真结果表明:柱塞运动以及泵腔的流量特性满足液压发动机设计要求,通过蓄能器的合理选用使输出液压油流量脉动得到较大改善.

The hydraulic accumulator has the advantages of high power density, fast response, stable operation and high cost performance. However, compared with the electric energy storage method, the hydraulic accumulator has low energy density and large pressure fluctuation while absorbing and discharging energy, which severely limits its application in hydraulic excavators. To improve the potential energy loss of the boom during the lowering process, an electro-hydraulic drive and energy recovery system for excavator booms (EHDR-EEB) based on a battery and accumulator is proposed. As a result, a simulation model of the electro-hydraulic drive and energy management strategy of a 1.6 t pure electric hydraulic excavator is built to investigate the energy regeneration and utilization. The simulation outcomes show that the potential energy recovery rate is as high as 92%. This research on EHDR-EEB makes a significant contribution to the economic improvement of electric hydraulic excavators.

[目的]本研究旨在解决人工监测棉花脱叶催熟效果耗时、费力等问题.[方法]利用四旋翼无人机获取喷施棉花脱叶剂前后4次多光谱图像,采用Pix4Dmapper软件拼接无人机图像,计算土壤调整植被指数(SAVI)、比值植被指数(RVI)、差值植被指数(DVI)和归一化植被指数(NDVI)4种植被指数,利用最大熵阈值法和植被指数阈值法提取棉叶覆盖信息.利用支持向量机对喷施脱叶剂的棉花进行监督分类,对4次采集的多光谱图像总体分类精度均大于97％,Kappa系数均大于0.95,因此将支持向量机分类结果作为真值,对最大熵阈值法和基于植被指数阈值法提取的棉花脱叶信息进行验证.将最佳提取方法用于建立棉花脱叶效果监测模型,代替人工监测棉花脱叶效果.根据最佳脱叶效果监测模型制作第2次脱叶剂施药处方图,指导第2次脱叶剂的变量喷施.[结果]在整个棉花脱叶过程中,基于SAVI840植被指数阈值法监测棉花脱叶效果优于基于RVI940最大熵阈值法,前者为最优监测棉花脱叶效果的模型,将最优监测模型提取的结果与田间调查棉叶数拟合,对数模型的R2最高,为0.96,说明无人机遥感监测棉花脱叶效果可行;根据最优监测模型提取棉叶信息制作变量喷施处方图进行施药并验证,结果表明施药效果较好,与常规定量施药相比,可节约农药7.39％,最高节药率达14.61％.[结论]无人机遥感技术可以代替人工大面积、快速和准确监测棉花脱叶效果,利用监测结果生成的处方图进行变量施药,可实现减药增效.

针对我国电商企业如何选择最有利于企业持续发展的物流配送模式问题,通过对我国现有的几种物流模式进行比较与分析,利用AHP层次分析法,以影响物流模式选择的因素为评价指标,建立了物流模式选择的层次结构模型,并为电商企业如何选择适应自身发展需求的物流模式给出了建议,以提高电商企业的竞争力.