一种基于偏好免疫网络多特征辨识的油茶果分选识别方法

针对油茶果采摘、脱壳后机器视觉分选效率不高的问题,提出一种多特征偏好人工免疫网络算法,该算法应用人工免疫网络的多目标优化与偏好数据库特征,提取油茶目标的颜色、形态多特征输入免疫网络进行仿真测试。试验结果表明,本文提出的多特征偏好免疫网络的识别率最高达到90%以上。相比单特征分选方法有了较大的提升,证明本文分选方法的有效性,并为农林业目标智能化分选辨识提供一种可行的方案。     

拖拉机田间作业参数无线检测系统研究

针对当前拖拉机检测系统功能集成度低、检测参数不全面、传输距离有限的问题，开发了拖拉机田间作业参数无线检测系统。该系统由传感器、数据采集仪及上位机软件监测平台3部分组成，能够实现PTO转矩及转速、油耗、发动机转速、悬挂提升力、力位调节加载力、加载角度、行驶速度、车轮转速、牵引力等多种参数的采集、无线发送与存储。系统工作时，数据采集仪中的车载检测仪将采集的传感器数据发送至无线数据接收器，无线数据接收器通过串口将数据传输至上位机软件监测平台，实现对各类试验参数的实时监测与数据处理。为验证检测系统的可行性与稳定性，对系统进行了采集通道的计量，结果显示模拟信号通道绝对误差绝对值最大为0.003V，引用误差最大为0.03%，频率信号通道检测绝对误差最大为2Hz，引用误差最大为0.013%，满足对拖拉机作业参数的采集需求。在此基础上，进行了PTO转矩参数及拖拉机无负载行驶速度采集试验。试验结果表明，检测系统可以实现转矩参数的稳定采集及数据的无线传输；在5、8、14km/h 3挡车速匀速行驶下，拖拉机车轮转速与实际行驶速度基本一致，最大相对误差分别为2.0%、1.2%及0.7%。本系统可满足对拖拉机工作性能参数的无线检测需求，数据采集稳定且采集精度较高，为拖拉机多作业参数的无线采集提供有效手段。     

基于模型预测控制的农机主从跟随作业控制方法

针对实际环境中由于农业机械（简称农机）作业过程的作业量以及土壤条件的变化等不确定性因素的影响，导致协同作业跟随农机的行驶工况不稳定、跟随协同作业响应慢、控制困难等问题，在综合考虑不确定性以及响应性能的基础上，提出了一种农机跟随分层控制架构，搭建农机田间作业下的纵向跟随动力学模型，并以间距保持、速度跟随、燃油经济性、加速度跟随性能为目标，进行基于模型预测控制（MPC）算法的上层控制器推导，基于前馈以及PI反馈的控制器作为下层控制，以上层控制器获得的控制加速度为目标，进行力矩（电流）跟踪，在保证抗不确定性以及干扰噪声的同时，提高跟随农机的响应能力。通过Matlab/Simulink仿真和田间试验验证，结果表明，该控制方法可以有效解决农机作业的跟随控制问题，与滑模变结构控制器相比，能够实现稳定跟随行驶，且速度误差和加速度误差更小，速度误差控制在-0.29132~0.18001m/s，加速度误差控制在-0.05678~0.05628m/s2，稳定跟随距离误差为±0.45m，具有良好的跟随效果。     

农产品监测预警模型集群构建理论方法与应用

【目的】农产品供给与需求的准确分析测定,是农业监测预警能力提升的重要表现。构建产品多品种多环节模型集群理论方法,可高效解决单一环节或单一模型难以解决的分析技术难题。【方法】在农产品供需的重要要素即生产量、消费量、贸易量、价格等分析预测过程中,针对农产品品种间关联性强,自然、社会、经济诸多影响因素纠缠,模型多变量强耦合、非线性、参数时变的特点,提出多品种农产品“因素分类解耦、参数转用适配”方法,以构建多时空维度的监测预警模型集群。【结果】利用“因素分类解耦、参数转用适配”技术方法,研究构建了不同农产品的生产类、消费类、贸易类、价格类的模型集群。这些模型集群可用于对不同时空维度的水稻、玉米、小麦、肉类等主要农产品供需的长中短期的分析预测,支撑形成了农业展望中的主要农产品平衡表,其中主要农产品全国年度生产量6年平均预测精度高于97%。【结论】研究提出的农产品监测预警模型集群构建理论及其方法,有效提升了农产品多品种模型集群的求解效率和准确率,增强了农产品供需分析预测的系统性与智能性,为系统揭示农产品复杂的时空供需变化特征、促进农产品市场调控科学性和可预见性,提供了新技术方法。     

双斜盘多排式轴向柱塞马达转矩特性分析

为了实现多级转速和转矩的输出,轴向柱塞马达必须使用节流阀、减压阀等耗能元件来改变输入压力和流量,但同时降低了效率。新型双斜盘多排式轴向柱塞马达可以利用其结构的特殊性,实现输出转矩的多样性。本文基于双斜盘多排式轴向柱塞马达的结构特点及工作原理,推导了该马达在不同工作方式下的理论瞬时转矩和转矩不均匀系数,并通过Matlab分析了内外马达转矩系数比对转矩不均匀系数的影响,设计了马达的实验液压系统并搭建了实验平台,对马达进行了原理性实验,并进行了数据分析。实验结果表明,在额定压力和额定排量下,该马达能实现多种不同的转速与转矩输出,随着内外马达转矩系数比的增大,低速大转矩的转矩不均匀系数越小,高速低转矩不稳定系数越大,通过合理设计可以实现马达在不同工作状态下的稳定运行,验证了新型马达在结构原理上的可行性,为新型轴向柱塞马达的改进设计提供了实验依据。     

Transmission ecology of rodent‐borne diseases: New frontiers

Rodents are recognized reservoir hosts for many human zoonotic pathogens. The current trends resulting from anthropocene defaunation suggest that in the future they, along with other small mammals, are likely to become the dominant mammals in almost all human‐modified environments. Recent intricate studies on bat‐borne emerging diseases have highlighted that many gaps exist in our understanding of the zoonotic transmission of rodent‐borne pathogens. This has emphasized the need for scientists interested in rodent‐borne diseases to integrate rodent ecology into their analysis of rodent‐borne pathogen transmission in order to identify in more detail the mechanisms of spillover and chains of transmission. Further studies are required to better understand the true impact of rodent abundance and the importance of pathogen sharing and circulation in multi‐host– multi‐pathogen communities. We also need to explore in more depth the roles of generalist and abundant species as the potential links between pathogen‐sharing, co‐infections and disease transmission.     

基于神经网络的多功能收割机发动机性能仿真及优化

随着全球经济和工业的快速发展,能源危机和环境保护问题越来越突出,传统内燃式发动机受到了巨大冲击,因此研究高效、节能的发动机显得尤为重要。为此,研究一种压缩比为10.6多功能收割机,并设计了基于MatLab仿真平台的GT-Power神经网络模型,利用神经网络训练和测试的数据自动进行仿真和储存,采用拉丁超立方采样算法设计试验,简化运算过程提高寻优效率。实验结果表明:神经网络模型转矩、比油耗和温度等参数模型预测误差很小、精度很高,可用于多功能收割机发动机的性能预测,使其各项指标参数最优化。     

断层和裂缝尺度识别的地球物理方法探讨

由于地球物理方法本身受分辨率和保真度的限制,其在断层和裂缝识别上的应用也就有精度和尺度上的差异。为此,可采用不同的方法技术来识别不同尺度的断层和裂缝,即在断层识别上,利用地震剖面和水平切片解释大断层,采用相干分析方法识别小断层;在裂缝识别上,主要采用多方位AVO方法识别大尺度裂缝的发育特征,采用成像测井来识别微小裂缝的特征情况。实际应用表明,上述方法在相应尺度断层和裂缝上的识别效果较好。     

A social learning video method: Identifying and sharing successful transformation knowledge for sustainable soil management in Switzerland

To enhance sustainable land use, a From Farmer to Farmer project was conducted in Switzerland (2001–2010). A multi‐stakeholder discussion group co‐produced nine videos with experienced farmers and wine producers showing sustainable soil management practices. We analysed the video audio‐visual content and drew on reflections of the co‐production process, referring to concepts of system, target and transformation knowledge, as well as on social learning. The analysis showed a broad range of means (or actions) for sustainable soil management in arable land management, fodder production and wine growing that are aligned to transformation knowledge. The research showed that farmers refer to three phases of social learning, light‐bulb moments, coping with challenges and gaining successful expertise. These are not just linear processes of individuals. Four types of social learning were found in the video analysis: (a) learning from observing actions of others, (b) sharing experiences with storytelling, (c) informal social interactions and (d) being a role model with a large social network. Videos enable transformation knowledge to be shared with peers using storytelling; this powerful narrative communication style provides credibility and respects the ‘thought style’ of the target audience group. We conclude that for successful implementation of sustainable actions, it is important to address a specific target group and share their transformation knowledge built upon system and target knowledge. The social learning video method is a viable way to enable social learning between science, administration and practice and has potential for fostering change in sustainable soil management.     

Cause Analysis and Treatment Measure on Cracks in New Reinforced Concrete Restricted by Old Web Concrete

In this paper, the cause analysis about cracks on the new concrete web poured in multi -span continuous box -girder of a main bridge was introduced. This bridge is a prestressed concrete one with variable cross sections and an 80 -meter main span. When casting reinforced concrete in large volume in box girder during vehicle transport service, the shrinkage cracks in cast -in place reinforced web concrete were formed due to the restriction of old web concrete. Then, the control measure taken on these cracks is discussed.