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.     

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.     

智能制造环境下的数控系统发展需求

"智能"是"中国制造2025"的核心要素,数控系统是制造装备实现智能化的关键要素。论文首先提出机床的信息互通和开放式标准数据接口是实现机床智能化的前提,举例说明了STEP-NC在通用数据接口方面的优越性,概述了适用于数控系统的通讯总线特征;在此基础上,介绍了工艺大数据对生产加工的重要性和其对新一代数控系统的要求,针对制造业数据平台的需求,对大数据信息挖掘技术做了相关介绍。依托于以上两点,总结了智能化数控系统可具备的功能,依托于工艺大数据平台,重点分析了智能工艺规划和加工参数自整定的实现方案,以及智能数控对高速高精加工所提供的便利。     

基于液体静压导轨的大行程快刀伺服系统设计

采用了理论设计和有限元仿真分析相结合的方法,设计了基于液体静压导轨的大行程快刀伺服系统(最大加工行程30mm,行程4mm时频响不低于50Hz).首先,设计得到了基于液体静压导轨的大行程快刀伺服系统的结构模型和相关参数;接着,利用ANSYS/FLUENT软件对液体静压导轨的变形、模态以及油膜压力分布进行仿真分析,并且将油膜刚度的理论计算值和仿真计算值进行比较,验证了导轨设计的可靠性;最后,选用能够满足要求的音圈电机、位置反馈装置以及功能强大的MPAC运动控制器等完成了控制系统的搭建.     

基于小波变换和支持向量机的开关电流电路故障诊断新方法

针对开关电流(Switched current,SI)电路的故障诊断和定位问题，为进一步提高故障诊断准 确率，提出了基于小波变换和粒子群优化(Particle swarm optimization，PSO)支持向量机 (Support vector machine，SVM)的开关电流电路故障诊断新方法。该方法首先对节点电流 信号进行蒙特卡罗分析，然后通过小波分解计算分形维数，再利用核主元分析（Kernel pri ncipal component analysis，KPCA）降低特征值维数，实现最优故障特征的提取。最后通 过PSO SVM完成对各种故障模式的分类。对六阶切比雪夫低通滤波器进行了仿真实验验证， 获取了较高的故障诊断准确率，与其他方法进行比较，实验结果显示了本文方法的优越性。     

抗离群值的鲁棒正则化贯序超限学习机

针对离群值环境下的在线学习问题,提出一种鲁棒正则化贯序超限学习机(Robust regularized online sequential extreme learning machine,RR-OSELM)。RR-OSELM以增量学习新样本的方式实现在线学习,并在学习过程中基于样本的先验误差进行逆向加权计算以降低学习模型对于离群值的敏感性;同时RR-OSELM通过融合使用Tikhonov正则化技术进一步增强了其在实际应用中的稳定性。实验结果表明,RR-OSELM具有较同类算法更好的鲁棒性和实用性,对于离群值环境下的在线建模与预测问题是积极有效的。     

Behavior and functional modeling methods of doubly salient electromagnetic generators for aircraft electrical power system applications

The Doubly Salient Electromagnetic Generator(DSEG) is a promising candidate in aircraft generator application due to the simplicity, robustness and reliability. However, the field windings and the armature windings are strongly coupled, which makes the inductance characteristics non-linear and too complex to model. The complex model with low precision also leads to difficulties in modeling and analysis of the entire aircraft Electrical Power System(EPS). A behavior level modeling method based on modified inductance Support Vector Machine(SVM) is proposed. The Finite Element Analysis(FEA) inductance data are modified based on the experiment results to improve the precision. A functional level modeling method based on input–output characteristics SVM is also proposed. The two modeling methods are applied to a 9 kW DSEG prototype. The steady state and transient process precision of the proposed methods are proved by comparing with the experiment results. Meanwhile, the modeling time consumption, the application time consumption and the calculation resource demand are compared. The DSEG behavior and functional modeling methods provide precious results with high efficiency, which accelerates theoretical analysis and expands the application foreground of the DSEG in the aircraft EPS.     

基于欠采样的零阶优化算法

非平衡学习吸引了许多研究者的关注。一般情况下,少数类是更值得关注的,并且其误分类代价要远高于多数类。由于非平衡数据分布的非均衡性,标准的分类算法将难以适用。为了解决非平衡数据分类问题,给出了基于欠采样的零阶优化算法。首先,为了降低数据非平衡分布的影响,针对不同非平衡比的数据集给出了不同的两种采样策略。然后,采用了一种引入间隔均值项的支持向量机(Support vector machine,SVM)优化模型进行分类,并使用带有方差减小的零阶随机梯度下降算法进行求解,提高了算法的精度。在非平衡数据上进行了对比实验,实验证明提出的方法有效提高了非平衡数据的分类效果。     

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。     

基于特征的数控编程技术在航空企业的推广应用

针对国内航空企业飞机结构件数控编程中存在的重复工作量大、效率低、质量不稳定、规范性差等问题,通过面向多主机厂推广基于特征的数控编程技术,切实提高飞机结构件数控编程的效率与质量.首先概述了基于特征的快速程编(FBM NUAA)系统的整体架构,并且介绍了基于特征的数控编程技术在多家主机厂中的推广与应用情况,以及前期推广中遇到的问题,并提出了解决方案.根据多主机厂多机型过百项飞机结构件的实际应用结果表明采用基于特征的快速程编系统进行数控编程,刀轨平均自动生成率超过90％,编程时间较传统编程方式平均缩短70％以上.