再入飞行器自适应最优姿态控制

针对再入飞行器姿态控制问题，应用自适应动态规划（ADP）理论设计了姿态控制器。将再入飞行器的姿态控制建模为非线性系统的最优控制问题，提出单网络积分型强化学习（SNIRL）算法进行求解，该算法简化了积分型强化学习（IRL）算法在迭代计算中的执行-评价双网络结构，只需要采用评价网络估计值函数就可以求得最优控制律，其收敛性得到了理论证明。基于SNIRL算法设计了自适应最优控制器，并证明了闭环系统的稳定性。通过数值仿真校验了SNIRL算法比IRL算法计算效率更高，收敛速度更快，并校验了自适应最优姿态控制器的有效性 。     

PSO-LSSVM在民机气动性能数学建模上的应用

目前风洞试验仅为民用飞机飞行性能提供有限数据.全飞行包线的技术支持对于民机飞行试验十分重要,需要采用数学建模和参数辨识的方法.选择合适的机器学习算法是参数辨识中最为关键的一步.支持向量机(SVM)采用结构风险最小化原理,尤其适用于小样本情形.根据A320非巡航起降阶段的几组真实数据,以及全机气动力估算的结果,使用最小二乘支持向量机建立预测模型.随后采用粒子群算法优化模型参数从而提升泛化能力.由此实现民机飞行包线的气动性能整体建模与辨识.与Ma=0.78时的实验数据相比较,PSO-LSSVM模型的预测结果吻合,是一种有效的气动数学建模方法.     

黄渤海晴空像元下雾霾识别的机器学习算法

为实时有效地识别和监测雾霾，选取2013年10月4日与10月5日的两景MODIS遥感图像，利用不同类型像元的光谱差异，基于神经网络模型，建立海上雾霾的遥感识别机器学习算法。经检验表明，在晴空条件下，机器学习算法反演精度相对较高，已超过98%，利用算法可以实现对中国近海上空雾霾的监测。     

TopPixelLoss:类别不均衡的遥感影像语义分割损失函数

针对遥感影像中类别不均衡的小目标分割效果不理想的问题，提出了一种类别不均衡小目标二分类分割的损失函数——TopPixelLoss损失函数。首先计算出每个像素的交叉熵，然后将所有像素的交叉熵按从大到小进行排序，随后确定一个K值作为阈值，筛选出前K个交叉熵最大的像素，最后对于筛选出的K个像素交叉熵取平均，做为损失值。在ISPRS 提供的 Vaihingen 数据集上，使用PSPNet网络与普通交叉熵、FocalLoss、TopPixelLoss三种损失函数分别对车辆进行二分类分割试验。结果表明，不同的K值，使用TopPixelLoss损失函数的平均交并比（MIoU）、F1-score、准确度（ACC）都最高;当K值为5×104时效果最佳，MIoU、F1-score、ACC分别比FocalLoss提高了3.0%、5.0%、0.1%。TopPixelLoss损失函数是一种针对类别不均衡分割非常有效的损失函数     

Modeling irregular small bodies gravity field via extreme learning machines and Bayesian optimization

Close proximity operations around small bodies are extremely challenging due to their uncertain dynamical environment. Autonomous guidance and navigation around small bodies require fast and accurate modeling of the gravitational field for potential on-board computation. In this paper, we investigate a model-based, data-driven approach to compute and predict the gravitational acceleration around irregular small bodies. More specifically, we employ Extreme Learning Machine (ELM) theories to design, train and validate Single-Layer Feedforward Networks (SLFN) capable of learning the relationship between the spacecraft position and the gravitational acceleration. ELM-base neural networks are trained without iterative tuning therefore dramatically reducing the training time. Analysis of performance in constant density models for asteroid 25143 Itokawa and comet 67/P Churyumov-Gerasimenko show that ELM-based SLFN are able learn the desired functional relationship both globally and in selected localized areas near the surface. The latter results in a robust neural algorithm for on-board, real-time calculation of the gravity field needed for guidance and control in close-proximity operations near the asteroid surface.     

Multi-state autonomous drilling for lunar exploration

Due to the lack of information of subsurface lunar regolith stratification which varies along depth, the drilling device may encounter lunar soil and lunar rock randomly in the drilling process. To meet the load safety requirements of unmanned sampling mission under limited orbital resources, the control strategy of autonomous drilling should adapt to the indeterminable lunar environments. Based on the analysis of two types of typical drilling media (i.e., lunar soil and lunar rock), this paper proposes a multi-state control strategy for autonomous lunar drilling. To represent the working circumstances in the lunar subsurface and reduce the complexity of the control algo-rithm, lunar drilling process was categorized into three drilling states:the interface detection, initi-ation of drilling parameters for recognition and drilling medium recognition. Support vector machine (SVM) and continuous wavelet transform were employed for the online recognition of dril-ling media and interface, respectively. Finite state machine was utilized to control the transition among different drilling states. To verify the effectiveness of the multi-state control strategy, drilling experiments were implemented with multi-layered drilling media constructed by lunar soil simulant and lunar rock simulant. The results reveal that the multi-state control method is capable of detect-ing drilling state variation and adjusting drilling parameters timely under vibration interferences. The multi-state control method provides a feasible reference for the control of extraterrestrial autonomous drilling.     

数控机床及工装的发展与创新设计

在现代数控加工中,由于被加工件的精度要求以及复杂度不断提高,传统加工系统无法满足使用需求,为解决这一问题,数字控制系统的核心算法以及驱动系统得到了快速发展,一些创新机构也应用到了数控机床的整机结构设计中.这些解决措施大幅提升了被加工件的精度和表面质量,促进了市场上一系列新型数控机床的出现,如复合机床、镜像铣削机床等,与之配合的新型加工工装技术也取得了相应的突破.     

MBD环境下计算机辅助零件分类技术

针对MBD环境下的零件分类问题，研究MBD信息提取、零件编码转换和深度学习分类算法技术，并创建MBD-计算机辅助零件分类系统（MBD-CAPC），实现从输入MBD模型到输出零件分类结果的自动化。     

气动钣金快速成形机的研制

针对电动钣金成形机制造成本高、效率低、易产生死点的问题,提出一种采用气液增力装置代替液压传动系统的气动钣金成形机设计方案。气液增力装置采用精密气压转换阀控制,实现行程平稳控制和加工成形过程平稳加载,显著提高了生产效率;配套研制的多种无齿收缩成形模具,可加工不同形状钣金件并获得更好的表面质量。该技术在钣金快速成形方面的研究处于国内领先水平,已获得3项国家专利。     

分数槽集中绕组永磁同步电机设计与分析

分数槽集中绕组永磁同步电机由于转矩密度高、弱磁性能好、齿槽转矩小和效率高等特点,广泛应用于航空航天、电动汽车等领域。本文研究了机载雷达伺服系统用分数槽集中绕组永磁同步电机,建立了电机的解析模型,分析了长径比、裂比、磁密系数等设计参数对电机性能的影响规律。结果表明,电机的输出转矩和质量分别与定子外径D3os,D2os成正比,绕组端部比重与长径比λ成反比,综合转矩密度和绕组端部比重两个因素,λ宜在0.2~0.4范围内选择。当定子裂比γ增加时,转矩密度先增大后减小,为使转矩密度最大,γ宜在0.6~0.8范围内选择。当磁密系数χ增加时,输出转矩先增大后减小,为使输出转矩最大,χ宜设计在1.75附近。基于理论分析和仿真计算,文中设计并加工了一台45槽38极分数槽集中绕组永磁同步电机,最后通过实验测试了其性能。