航空发动机虚拟自学习控制方法研究

随着人工智能技术的发展，智能航空发动机逐渐成为当今航空领域研究的热点。传统的航空发动机控制对发动机模型的依赖性过强，而基于发动机气热动力学公式的机理建模会引入较大的建模误差，给控制器设计带来困难。对此，提出一种基于强化学习的航空发动机控制虚拟自学习方法，首先利用航空发动机的试验数据通过LSTM 神经网络建立虚拟学习环境，然后采用深度强化学习TD3 算法，在虚拟环境中训练智能控制器，最后采用JT9D 发动机模型验证智能控制器的性能。结果表明：相比于传统PID 控制，智能控制器产生的超调量更小，调节时间更短。     

考虑飞行器动力系统进排气效应的设计参数灵敏度分析研究

面向飞行器内外流一体化设计,基于自主研发的大规模并行化结构化网格RANS求解器以及离散伴随方程求解器,开展了考虑推进系统动力状态下进排气边界条件的变分研究,通过链式求导法则避免直接对守恒变量变分,进一步引入中间变量大幅度简化了进排气边界条件变分的难度,建立了考虑进排气效应的设计变量灵敏度高效分析方法,并通过TPS标准模型计算验证了进排气数值模拟精度,与有限差分对比验证了灵敏度计算精度,以翼上发动机气动布局进排气影响数值模拟为例,系统分析了低速、高速、定攻角、定升力状态,推进系统有无动力工况灵敏度的变化以及影响机理。     

驾驶员诱发振荡的抑制方法

对电传操纵系统驾驶员诱发振荡（ＰＩＯ）的现象进行了分析，指出了舵回路速率饱和是造成ＰＩＯ的主要原因，并有针对对给出了一种非常规的用于解决饱和非线性问题的程序控制方法。这种方法主要是通过舵回路反馈的状态信息来改变驾驶杆输入信号的放大系数，从而达到有效抑制ＰＩＯ的目的，同时用Ｈｕｒｗｉｔｚ稳定判据进行了机理分析，最后给出了仿真验证结果，证明该方法是简单而有效的。     

箭遥时间指令参数实时处理方法研究

火箭遥测数据的实时挑点处理结果是发射中心实时监视火箭飞行状态的重要依据,尤其是时间指令参数的处理结果为判别运载火箭发动机点火、关机、星箭分离等关键事件发生与否提供主要依据。根据某型号运载火箭时间指令参数在遥测帧格式中的波道和码位分配,分析目前箭遥时间指令实时处理方法存在的缺陷,提出"增加判别帧数,充分利用冗余信息",通过分析"时序指令"与"时串指令"间存在的"关联"建立"关联知识库",使用知识库进行辅助判别,实现不错判、不漏判的改进设想。     

Development of an improved ground-based prototype of space plant-growing facility

Based on a formerly developed ground-based prototype of space plant-growing facility, the development of its improved prototype has been finished, so as to make its operating principle better adapt to the space microgravity environment. According to the developing experience of its first generation prototype and detailed demonstration and design of technique plan, its blueprint design and machining of related components, whole facility installment, debugging and trial operations were all done gradually. Its growing chamber contains a volume of about 0.5 m³ and a growing area of approximate 0.5 m²; the atmospheric environmental parameters in the growing chamber and water content in the growing media were controlled totally and effectively; lighting source is a combination of both red and blue light emitting diodes (LED). The following demonstrating results showed that the entire system design of the prototype is reasonable and its operating principle can nearly meet the requirements of space microgravity environment. Therefore, our plant-growing technique in space was advanced further, which laid an important foundation for next development of the space plant-growing facility and plant-cultivating experimental research in space microgravity condition.     

A strategic flight conflict avoidance approach based on a memetic algorithm

Conflict avoidance （CA） plays a crucial role in guaranteeing the airspace safety. The cur- rent approaches, mostly focusing on a short-term situation which eliminates conflicts via local adjust- ment, cannot provide a global solution. Recently, long-term conflict avoidance approaches, which are proposed to provide solutions via strategically planning traffic flow from a global view, have attracted more attentions. With consideration of the situation in China, there are thousands of flights per day and the air route network is large and complex, which makes the long-term problem to be a large-scale combinatorial optimization problem with complex constraints. To minimize the risk of premature convergence being faced by current approaches and obtain higher quality solutions, in this work, we present an effective strategic framework based on a memetic algorithm （MA）, which can markedly improve search capability via a combination of population-based global search and local improve- ments made by individuals. In addition, a specially designed local search operator and an adaptive local search frequency strategy are proposed to improve the solution quality. Furthermore, a fast genetic algorithm （GA） is presented as the global optimization method. Empirical studies using real traffic data of the Chinese air route network and daily flight plans show that our approach outper- formed the existing approaches including the GA .based approach and the cooperative coevolution based approach as well as some well-known memetic algorithm based approaches.     

民用飞机试飞规划与管理软件适用性研究

飞行试验是民机研制的重要手段,也是飞机取得适航证的必经过程。随着现代大型民用飞机的设计越来越复杂,试飞制约因素越来越多样,任务量越来越庞大。试飞成为制约型号进度和研制成本的重要因素。对于试飞工作者而言,必须采用科学的方法对试飞任务进行合理规划和管理。为此,国内某飞机设计研究院历时三年,开发了一款用于试飞任务管理的软件——民用飞机试飞规划与管理软件(Flight Test Control System,简称FTCS)。以国内某型号飞机试飞为例,对FTCS的适用性进行了分析和评估,为FTCS的应用和发展提供建议。     

L波段数字航空通信系统研究

随着全球航空运输的发展,空中交通管制与航空公司运控等航空业务对航空通信系统的数据传输速率、频谱利用率、航空通信网容量等性能提出了更高的要求。虽然现阶段基于甚高频的航空通信系统得到了迅速的发展,但仍受限于标准体制、技术壁垒等因素,难以满足持续增长的运行需求。L波段数字航空通信（L-band digital aeronautical communication system,L-DACS）数据链技术作为新一代航空通信系统的预选方案,是有效解决频谱资源饱和难题、满足高速率传输需求的有效途径。本文在总结L-DACS数据链技术发展现状的基础上,阐述了该通信系统现阶段的技术标准,分析了L-DACS发展所面临的挑战,提出了对应的发展建议,为面向航空宽带通信L-DACS的研究提供了参考与借鉴。     

无人机集群路径规划算法研究综述

无人机集群路径规划算法是无人机集群控制的重要研究方向之一.多无人机路径规划相较于单无人机路径规划,会考虑空间协同和时间协同约束、飞行安全等问题.首先对无人机集群路径规划算法进行分类,分为传统路径规划算法、智能优化算法和深度强化学习算法.其次对各类算法进行简要分析和总结,针对缺陷,给出相应的改进思路及例子.再着重对深度强...     

蜂窝结构件的数控加工

以某型机底部蒙皮结构件中的铝基低密度和纸基蜂窝为例,阐述了蜂窝结构件数控加工中的机床选择、装夹定位方案、切削刀具选择、编程方法、切削参数选择以及加工过程中的产品保护等内容.