基于模糊神经网络的自适应精确曝气系统设计

基于模糊神经网络理论,将自回归各态历经(ARX)模型与模糊神经网络模型(FNNM)相结合,设计一套具有自适应能力的前馈-反馈精确曝气控制系统,解决目前污水处理曝气过程中冗余曝气能源浪费、溶解氧波动大的问题.以污水厂处理PID控制生物池数据作为训练样本,以模糊神经网络自适应精确曝气模型仿真与传统PID控制比较,发现该系统...     

Key techniques for predicting the uncertain trajectories of moving objects with dynamic environment awareness

Railway Engineering Science - Emerging technologies of wireless and mobile communication enable people to accumulate a large volume of time-stamped locations, which appear in the form of a...     

Grey Clustering Theory to Assess the Effect of Mineral Admixtures on the Cyclic Sulfate Resistance of Concrete

Concrete specimens made with ordinary portland cement or ordinary portland cement incorporating fly ash with the replacement of 10% or 20%, ground blast furnace slag with the replacement of 15% or 30%, or 15% fly ash and 15% ground blast furnace slag were made and exposed to a cyclic sulfate environment. Concrete properties including relative dynamic elastic modulus, chloride ion diffusion coefficient, compressive strength and flexural strength were measured. Effect of mineral admixtures on the cyclic sulfa...     

Earth pressure balance control for EPB shield

This paper mainly deals with the critical technology of earth pressure balance (EPB) control in shield tunneling. On the assumption that the conditioned soil in the working chamber of the shield is plasticized, a theoretical principle for EPB control is proposed. Dynamic equilibrium of intake volume and discharge volume generated by thrust and discharge is modeled theoretically to simulate the earth pressure variation during excavating. The thrust system and the screw conveyor system for earth pressure cont...     

阻火器的选用

阻火器的选用是石油化工厂、石油和天然气工厂、有可燃性气体的工厂生产安全保护和工程设计中常遇到并需解决的问题，本文对阻火器产品的选用步骤提出了个人的一些理解意见。     

PF用低收缩添加剂的研究

通过调整物料配比合成了端羟基封端和端羧基封端的聚氨酯 (PU)预聚物 ,并分别与酚醛树脂 (PF)固化 ,制备了两种低收缩体系的复合物 ,利用红外光谱对其结构进行表征。通过测试固化物的体系收缩率表明 :随着聚氨酯预聚物加入量的增加 ,PF/PU共混物的体积收缩率明显变小 ,并能达到负值。端羧基PU的低收缩性能更为显著 ,当其加入量在 5 相似文献   

二苯甲酮-β-环糊精包合物的制备表征

采用研磨法合成了二苯甲酮-β-环糊精包合物,经差示量热扫描分析、热重分析、红外分析、X射线衍射分析、对包合物进行了鉴定,证明二苯甲酮-β-环糊精确实形成了一种新的体系.     

Study of UAV tracking based on CNN in noisy environment

Multimedia Tools and Applications - Recently, there are lots of tracking methods proposed to improve the performance of visual tracking in videos with challenging situations, such as background...     

基于多季相Sentinel-2影像的白洋淀湿地信息提取

白洋淀湿地是华北平原上重要的浅水湖泊湿地,对雄安新区绿色发展具有重要的生态价值。对白洋淀高度异质化的景观格局进行分类,能够为白洋淀湿地资源的遥感监测提供指导意义。针对湿地季节变化的特点,对白洋淀每个季节选取一期具有代表性的Sentinel-2影像,采用分类与回归树（CART）、支持向量机（SVM）、随机森林（RF）3种常用的机器学习分类器对15种季相组合实验方案进行分类,分析不同季相遥感影像及其组合对白洋淀湿地信息提取的优劣。结果表明：相较于使用单一季相影像分类,多季相影像的组合能够显著提高分类精度,春&夏季相组合能够得到最优的分类效果,相对单季影像总体分类精度提高了10.9%~25.5%,Kappa系数提高了0.09~0.29;SVM分类器的分类表现较为稳定,能够得到最高的平均分类精度,CART分类器在处理高维特征的能力不如随机森林和SVM;不同特征类型对湿地信息提取的贡献度从高到底依次是红边光谱特征、传统光谱特征、缨帽变换特征、主成分分析特征、纹理特征。实验成果能为湿地信息的遥感识别提供依据。