Rapid and nondestructive identification of metabolites in fresh tobacco leaves is crucial for understanding quality formation and optimizing production. This study utilized hyperspectral imaging (400-1000 nm) to analyze fresh tobacco leaves at three maturity stages (M1, M2, and M3) and identified 11 key metabolites with significant differences. Four machine learning models-Random Forest (RF), extreme gradient boosting (XGB), convolutional neural network (CNN), and long short-term memory (LSTM)-were employed to predict metabolite content. Experimental results demonstrated that CNN achieved the highest prediction accuracy, with an average R2 of 0.917, outperforming RF (0.896), XGB (0.895), and LSTM (0.915). The superior performance of CNN highlights the potential of deep learning in metabolomics research. These findings provide insights into the metabolic dynamics of tobacco maturation and offer practical applications for quality control and production optimization in the industry.

Visual detection for automated fruit harvesting in unstructured environments constitutes a critical technical challenge, especially for fruit peduncles, which exhibit greater sensitivity to environmental factors than the fruits themselves. To address this challenge, this paper proposes a top-down keypoint detection method for pepper peduncles in unstructured environments. The proposed method enables accurate estimation of peduncle poses. The first step of the research involves validating different object detection models and employing ones to identify the bounding boxes of pepper peduncles. Subsequently, a new keypoint detection model based on the Lite Vision Transformer is proposed, leveraging the Transformer's capacity to capture long-range spatial and semantic dependencies. Experimental results on the pepper dataset collected in unstructured environments demonstrate that the proposed model achieves an AP50 of 94.6 %. This performance surpasses multiple state-of-the-art keypoint detection methods while maintaining lightweight parameters and low computational complexity. Moreover, a series of tests reveals that the proposed method outperforms other algorithms in complex environments, especially in occlusion scenarios. Finally, a comprehensive evaluation of the top-down approach is conducted, examining the influence of object detection and keypoint detection models on overall performance. The proposed keypoint detection model achieves the highest performance, with a detection speed of 9.38 FPS when using YOLOv8s as the object detection model, and an AP50 of 83.6 % when using YOLOv8l. Experiments conducted in real unstructured environments demonstrated the robustness of the proposed method, effectively detecting the posture of dense and occluded chili pepper peduncles. This research can be extended to the detection of fruit peduncles in other crops, providing a foundation for pose estimation of fruit peduncles in complex environments.

Accurately measuring tobacco harvest maturity is crucial for optimizing quality and crop management. Traditional methods heavily rely on qualitative evaluation and chemical experiments, which introduce subjectivity and inherent limitations. This study proposes a novel method that combines deep learning with proximal hyperspectral imaging (HSI) to achieve precise recognition of tobacco leaf maturity. Unlike traditional techniques, HSI captures rich spectral and spatial data, enabling comprehensive analysis. It adopts a pixel-level annotation strategy to annotate each pixel based on its maturity level, thereby preserving spectral complexity. The dataset comprises 3000 randomly extracted cubes (5x5x176) from 150 original hyperspectral images, encompassing five maturity levels. Spectral and spatial features are extracted from hyperspectral data using a three-dimensional convolutional neural network (3D-CNN) architecture. This method effectively leverages complex spectral patterns for maturity recognition. During testing, the model demonstrated an impressive average accuracy of 99.93%. Visual predictions vividly illustrate the model's proficiency in maturity recognition, affirming its practical utility. This study pioneers the integration of deep learning and hyperspectral near-end sensing technology in tobacco maturity assessment, mitigating the constraints of traditional methods, and establishing the groundwork for real-time monitoring and quality control of tobacco.

Due to the economic differences of chili peppers at different maturity levels and the absence of differentiation of maturity in existing harvesting processes, it is crucial to accurately identify the maturity during harvesting for improving economic benefits. This paper investigated pepper maturity recognition models using hyperspectral technology to realize intelligent pepper harvesting with high accuracy and monitor maturity. Hyperspectral data (400-1000 nm) for field line peppers were collected, preprocessed using normalization, Savitzky-Golay convolutional smoothing, and standard normal variable transformation and subsequently used to train back propagation neural network (BP) and kernel based extreme learning machine (KELM) models. Principal component analysis (PCA) was used to reduce data dimensionality and identify characteristic spectral wavelengths for pepper maturity at 862.2, 676.9, 578.1, and 980.7 nm; and BP, PCA-BP, KELM, and PCA-KELM models were subsequently established. The precision for the KELM and PCA-KELM models (99.5% and 97.3%, respectively) was superior to the other two models; however, the PCA-KELM model used only four of the feature wavelengths as inputs, hence it required only 1/44 the data compared with the KELM model. Thus, the PCA-KELM model achieved high recognition accuracy and training speed, offering an effective method to discriminate pepper ripeness based on hyperspectral features.

This study centered around the practical problem that there is no machine available for deep planting with large holes in hilly and mountainous areas of China. According to the principle of spiral lifting, a conical, double-spiral hole-forming machine was innovatively designed. The structural design and parameter calculation were completed. By discrete-element-method (DEM) simulation, the optimal lead and rotation speed of the hole former were obtained, and the hole-forming mechanisms of soil cutting, soil lifting, soil discharging, soil extruding, and soil returning were further revealed. The field test results indicated that the prototype had the advantages of convenient operation and good performance, and the formed holes met the agronomic requirements, with a qualification rate of 88.5%. In addition, it was found that the soil moisture content has a great influence on the formation of holes. Under the condition of low moisture content, the residence time at the bottom of a hole should be appropriately increased to improve the qualification rate of the holes formed. Our research results provided theoretical guidance and technical support for the design, optimization, popularization, and application of a hole-forming machine for deep planting with large holes (DPLH).

为解决黏重土壤条件下机械移栽作业时栽植器易粘土、严重影响移栽质量和效率的问题,根据翠鸟嘴部外轮廓、野猪吻突部位和蜣螂体表非光滑结构,采用曲线提取、拟合、构造及相似原理设计并加工出两种仿生栽植器.在自制移栽试验平台上进行试验研究,结果表明:最小粘附土壤量栽植条件为仿生栽植器Ⅱ,土壤含水率为21.3％,入土深度为50mm,栽植频率为40株/min.通过验证对比试验可知:土壤含水率为21.3％,栽植频率为40株/min,栽植深度分别为50、70、90mm时,仿生栽植器Ⅱ的粘附土壤量相比于原型栽植器的粘附土壤量分别减少21.8％、15.5％、27.4％.仿生栽植器有较好的减粘降阻效果,其思路可为农机具触土部件的减粘设计提供参考.

烤烟油分含量评价对烟叶等级的评判具有重要影响,为了对烤烟油分等级进行科学预测,创建烤烟微观纹理与油分含量的关系模型,论文以贵州安顺平坝烟区烤烟样品为研究对象,基于LBP—GLCM(融合灰度共生矩阵与局部二进制模式)特征融合提取烤烟表面纹理特征,结合BP人工神经网络模型,对烤烟油分等级进行预测.结果表明:采用LBP-GL-CM算法结合BP神经网络对烤烟油分等级预测正确识别率为93.33%,模型相关系数为0.91486,可见该算法对于烤烟油分等级预测具有一定的优势.

为实现烟叶快速准确的识别分级,提出了一种改进的Faster R-CNN分级算法.以VGG16网络为训练原型,通过调整训练图像的尺寸、学习率、mini-batch等全连接层参数,在此基础上将ROI pooling改进为ROI align,再去掉网络模型的第8、第12、第15层卷积层,同时引入Inception结构层为研究的最终分级模型.以准确率和召回率作为分级模型性能的评价指标,利用最终分级模型训练7个等级的烟叶图像,识别准确率最低为90.62%,最高为92.46%,召回率最低为91.72%,最高为92.87%,平均识别准确率达到92.35%,识别速度达到0.2s/幅.改进后的模型平均识别准确率相比原始网络平均识别准确率提高了3.98%.

小型自走式施肥机在田间工作时,由于速度不同、地表不平整等因素,会对施肥机造成较大的振动影响,降低工作效率且对人体产生一定的影响.为此,采用正交试验分析的方法,分析了影响小型自走式施肥机排肥导管和扶手振动因素的主次顺序;采用快速傅里叶变换的方法,分析了排肥导管及扶手的固有频率.结果表明:排肥导管的固有频率为4.39～41.10Hz、速度为v=0.5m/s时,激振频率fe=17.60Hz,排肥导管振动最剧烈.这是由于激振频率接近排肥导管的固有频率所引起的,说明v=0.5m/s时排肥导管的振动频率最接近于排肥导管的固有频率.扶手的固有频率在5.01～17.69Hz、v=1.5m/s、激振频率为6.80Hz时,振动最激烈,说明此速度下扶手的振动频率最接近扶手固有频率.

贵州烟区烟草种植多采用人工方式覆膜,作业成本高、劳动强度大、机械化水平低.为解决这一问题,根据贵州烟草种植农机农艺融合要求,研制了一款小型电动覆膜机,并简述了覆膜机的结构和工作原理.覆膜机采用主动培土方式实现覆土,分析了培土刀刀轴轴线与水平面夹角对覆膜质量的影响;通过EDEM软件对培土刀的入土过程进行仿真分析,确定了培土机构的结构和工作参数.田间试验结果表明,当覆膜机培土刀刀轴轴线与水平面夹角为5°时,覆膜后垄基宽、垄顶宽、垄高、覆土宽度、透光面宽度的稳定性系数均大于80%,断条率小于5%.

针对烤烟等级分类问题,论文利用数字图像处理技术对烤烟图像进行处理,根据烤烟等级影响因子,提取了烤烟正反两面的颜色特征、纹理特征与形状特征,并建立了一种烤烟等级分类模型——RF-PSO-SVM模型.首先利用RF-SVM对烤烟特征按其对分类模型的贡献度排序,筛选出对分类模型准确率影响较大的特征建立最优特征子集,并利用PSO对SVM的C、g参数寻优,建立RF-PSO-SVM分类模型,对筛选的特征子集进行学习训练,最后将RF-PSO-SVM分类模型与SVM分类模型、PSO-SVM分类模型进行对比,验证该方法的可靠性.经实验结果表明:1)烟叶的反面颜色特征与纹理特征对分类模型贡献度较大,形状特征对模型贡献度较小.2)RF-PSO-SVM算法建立的烟叶分类模型可以在保证分类准确率的情况下,降低分类算法的运行时间,减少了数据集的特征维度,对烟叶的分类识别具有一定的参考价值.

HighlightsIntermittent fertilizer discharge equipment was designed to realize hole fertilizer application.The optimal structure of the fluted discharge roller was three grooves with conical cross-sections.This study provides a reference for the design of equipment and control systems for hole fertilizer application.Abstract. Fertilizers are necessary for high crop yields. In mechanized application of starter fertilizer for tobacco, discharging the fertilizer immediately below the seedlings promotes root growth and nutrient uptake, resulting in a high utilization rate. This placement is called hole fertilizer application and is fertilizer-saving and environment-friendly. To meet the requirements of hole fertilizer application for crops with specific plant spacing, equipment to intermittently discharge fertilizer has been designed based on the structure of a fluted roller. To explore the influence of the structural and working parameters of the intermittent discharge equipment on the uniformity of hole fertilization and the accuracy of marking fertilizer positions, the fertilizer discharge process and marking process were simulated using a discrete element method based on theoretical analysis. The optimal combination of parameters was a tapered circular groove shape with three grooves, the rotational speed of the fluted roller was 30 rpm, and the center distance between two material bins was 40 cm. In the simulation, the coefficient of variation for single-hole fertilizer application was 3.39%, and the marking error was 1.86 cm. Bench tests were performed using the optimal combination of parameters to verify the simulation results. The intermittent discharge equipment was able to achieve hole fertilizer application and mark the fertilizer position. The coefficient of variation for single-hole fertilizer application was 4.35%, and the marking error was 1.95 cm. The bench tests proved that the discrete element method was feasible for optimizing the equipment parameters. This study provides a reference for developing hole fertilizer application equipment and control systems to improve fertilizer use efficiency. Keywords: Fertilizer performance, Groove structure, Hole fertilizer application, Intermittent fertilizer discharge, Structural parameter.s

针对丘陵山区现有的自走式施肥机变量控制系统存在惯性大、非线性以及不能及时响应等,传统PID控制策略很难达到精准施肥要求.为此,在建立施肥控制系统数学模型的基础上,采用模糊PID对排肥轴转速进行控制,然后在Simulink工具箱搭建该控制系统的PID仿真模型.分析、对比传统参数整定的PID控制和自适应模糊PID控制系统性能差异.模型仿真和田间试验结果表明:自适应模糊PID控制器改进后的系统模型,响应时间为0.7 s,超调量3.36％,相比传统PID控制模型具有更好的动静态特性;而且在排肥控制性能试验中,单穴排肥量误差为1.52％～5.10％,变异系数最大为4.31％,排肥量准确性和均匀性均达到要求,改进的控制系统性能更优.

烟叶含水量的快速检测在烟草种植业中起着关键的作用,检测采摘期烟叶水分含量,对烟草工艺具有重要意义.为了快速、无损地检测采摘期烟叶水分含量,提出一种主成分分析(PCA)结合马氏距离算法(MD)的方法来剔除异常样本,再使用偏最小二乘法(PLS)估测采摘期烟叶水分含量.首先,利用GaiaSky-mini2机载高光谱成像仪获取到141个采摘期烟叶的高光谱数据,采用多元散射校正(MSC)、标准正态变量交换(SNV)和Savitzky-Golay卷积平滑法等对原始光谱进行预处理.然后,应用主成分分析结合马氏距离法对校正集中的异常样品进行剔除.最后,使用偏最小二乘法(PLS)建立采摘期烟叶水分含量分析模型.结果 表明:利用SG卷积平滑法预处理的PCA-MD-PLS模型效果最佳,对烟叶含水量预测能力最好,预测模型相关系数为0.8527,均方差为1.3766.

An small deep-placement fertilizer applicator (SDFA), to realize hill fertilization application and mark fertilizer location with lime, was developed. It’s unique structure and working principle were detailed. Orthogonal tests was conducted by the software EDEM virtual simulation in order get the working parameters and structure of the applicator. The rotational torque was much higher than resistant torque after optimization design. Field testing across different sites and seasons showed that the improved applicator consistently placed synthetic fertilizer at the depth of 18–21 cm and plant spacing of 49–52 cm. The average amount of fertilizer released into each hill was 54.5 g when the set amount was 55.0 g, which indicate the design are effective.

针对烤烟油分特征预测模型的特征优选问题,提出一种改进RF(随机森林)算法特征选择策略,首先通过RF特征选择算法计算出各个特征的RF-Score,将特征按RF-Score的大小排序依次添加到特征子集中,若分类器分类准确率提高则保留该特征,若分类器分类准确率没有提高或降低则去除该特征.结果 表明:利用RF特征选择算法对烤烟高光谱特征进行筛选时,将176个高光谱特征中按基尼系数降序排列依次输入SVM分类器中,前64个高光谱波段特征即可使支持向量机分类器性能最佳,特征子集维度为64,其分类准确率为93.33％.利用改进RF特征选择策略对176个烤烟高光谱波段特征进行筛选,只需输入371.08 nm、716.71 nm、378.31 nm、487.77 nm、484.09 nm、535.85 nm六个波段的高光谱特征即可使支持向量机分类器性能最佳,其分类准确率为95％,特征子集维度为6,说明改进的RF特征选择策略可以在保证分类器性能的前提下能较好地进行数据降维,减小特征集的冗余.改进后的RF特征选择算法与全高光谱波段相比,特征数量减少170个,分类准确率提高3.33％;与RF特征选择算法相比,特征数量减少58个,分类准确率提高1.67％.

以贵州毕节地区作为研究区域,对当地残膜污染状况进行调研分析,结果表明:平均残膜数量为48.71片/m2,表层占21.30％,0～10cm土层占53.58％;平均残膜质量为18.70g/m2,表层占60.63％,0～10cm土层占29.79％,调研数据的拟合度均高于0.97.制定贵州烟地残膜污染等级为:大于25g/m2为重度污染,13g/m2～23g/m2为高度污染,6～13g/m2为中度污染,小于6g/m2为轻度污染.针对残膜污染分布情况,创新设计了一款不同高度和入土角度螺旋弹齿的残膜捡拾机,田间测试结果表明:前、中、后3排梳齿入土深度分别为19.5、15.2、10.4cm,各土层残膜捡拾率均高于84％,可满足不同土壤深度残膜捡拾设计要求.

This paper presents a new design for a fertilizer deep applicator that is suitable for twin-row application within one ridge row as is commonly used in flatland regions of Guizhou, China for tobacco production. The applicator is capable of finishing tilling, ridging and precise fertilization at the same time. The fertilizer applicator implement is coupled with a control system that regulates fertilizer application based on operation speed. The implement was tested in a series of field experiments. Results show that the implement is capable of tilling, ridging and fertilizer application at the same time, can apply fertilizer deep and precisely with the variable coefficient of fertilization uniformity of 12.3% and the operation efficiency of 0.41 hm(2)/h with deviation of fertilizer amount under 4.58%, and can make well-shaped ridges with the ridge height, top width and base width of 28 mm, 1,318 mm and 1,755 mm, respectively, which are within the acceptable range of the target values of 30 mm, 1,300 mm and 1,700 mm, respectively.

为进一步提高肥料的利用率,在穴施肥的同时进行土肥混合,不仅可以避免土壤板结、肥料集中引起的烧苗、烧根现象以及肥料浪费造成的土壤、水质污染,还可以保证作物的产量.文章就穴施肥机土肥混合装置可行性展开详细探究.

为解决丘陵山区长期使用微耕机等进行土壤耕作造成土地耕层浅、耕层下形成板结的犁底层,影响作物根系下扎困难,水和肥料无法渗入等问题,结合类似贵州这种丘陵山地的地形地貌设计了一款小型自走式螺旋深耕机.该机由8.8 kW的风冷柴油机及液压系统提供动力,整机包括液压控制系统、液压升降系统、螺旋深耕装置及履带行走装置几大部分.对螺旋深耕装置进行结构静力学分析结果表明:小型自走式螺旋深耕机深耕刀具的最大位移变形量为2.67mm位于深耕刀叶片的拨齿上,螺旋深耕刀具满足强度及刚度上的要求.