基于LSTM的飞行数据挖掘模型构建方法

提出了一种基于LSTM （Long Short Time Memory）模型的飞行历史数据挖掘模型的构建方法，此模型可以将飞行数据中有价值的目标数据自动提取出来。首先，通过滑动窗口法获得待检测数据；然后，将预先做好的训练样本数据输入到所构造的LSTM模型中进行训练，得到数据挖掘模型；最后，将待检测数据导入到训练好的LSTM模型中进行模式识别，将目标数据片段挖掘出来。结果表明，基于LSTM模型的飞行数据挖掘模型构建方法通用化程度高，可用于挖掘不同类型的目标数据，且识别率高，具有很高的工程应用价值。     

基于AFI混合聚类算法的轴承故障诊断方法

针对滚动轴承振动信号标记数据量小、故障模式多样的现状，提出了一种基于AFI混合聚类算法的半监督式轴承振动信号故障诊断方法。利用小波包分解方法提取了信号的能量特征谱，并通过主成分分析方法增强了信号的特征；参考迭代自组织数据分析的“分裂”和“合并”的思想，为人工鱼群算法中的个体鱼增加了“分裂进化”和“合并进化”行为；采用模糊C均值方法定义了隶属度矩阵和目标函数，并利用改进的人工鱼群算法，迭代搜寻了目标函数的全局最优解，得到了各故障模式的聚类中心；通过计算测试数据的最近邻聚类中心，实现了故障模式识别。结果表明，该方法无需指定聚类簇数，能在标记数据量小的情况下完成训练，较同类方法表现出了更优的故障模式识别性能。     

流量调节器管路系统自激振荡特性研究

流量调节器管路系统在小流量大压降工况下会出现低频自激振荡现象。为了深入认识自激振荡产生机理，结合某稳流型流量调节器及管路系统，基于流量调节器弹簧振子动力学模型开展数值仿真研究。数值仿真得出自激振荡频率为94Hz，与发动机试验结果一致。分析了流量调节器结构参数对系统稳定性的影响作用，三角形滑阀节流口能够抑制管路系统自激振荡。自激振荡产生机理是液动力随滑阀节流口型面振荡，并对管路系统形成正反馈作用，当流量调节器综合刚度系数<0时，管路系统就失稳产生振荡。某流量调节器的负载特性试验表明，随着流量调节器压降升高，管路系统稳定性变差。仿真获得的幅频特性，稳定边界与试验结果一致。     

A progressive approach to predict shot peening process parameters for forming integral panel of Al7050-T7451

In this paper, a progressive approach to predict the multiple shot peening process parameters for complex integral panel is proposed. Firstly, the invariable parameters in the forming process including shot size, mass flow, peening distance and peening angle are determined according to the empirical and machine type. Then, the optimal value of air pressure for the whole shot peening is selected by the experimental data. Finally, the feeding speed for every shot peening path is predicted by regression equation. The integral panel part with thickness from 2 mm to 5 mm and curvature radius from 3200 mm to 16000 mm is taken as a research object, and four experiments are conducted. In order to design specimens for acquiring the forming data, one experiment is conducted to compare the curvature radius of the plate and stringer-structural specimens, which were peened along the middle of the two stringers. The most striking finding of this experiment is that the outer shape error range is below 3.9%, so the plate specimens can be used in predicting feeding speed of the integral panel. The second experiment is performed and results show that when the coverage reaches the limit of 80%, the minimum feeding speed is 50 mm/s. By this feeding speed, the forming curvature radius of the specimens with different thickness from the third experiment is measured and compared with the research object, and the optimal air pressure is 0.15 MPa. Then, the plate specimens with thickness from 2 mm to 5 mm are peened in the fourth experiment, and the measured curvature radius data are used to calculate the feeding speed of different shot peening path by regressive analysis method. The algorithm is validated by forming a test part and the average deviation is 0.496 mm. It is shown that the approach can realize the forming of the integral panel precisely.     

Modelling ignition probability with pairwise mixing-reaction model for flame particle tracking

Reduced order models for ignition analysis can offer insights into ignition processes and facilitate the combustor optimization. In this study, a Pairwise Mixing-Reaction (PMR) model is formulated to model the interaction between the flame particle and the surrounding cell mixture during Lagrangian flame particle tracking. Specifically, the model accounts for the two-way coupling of mass and energy between the flame particle and the surrounding shell layer by modelling the corresponding turbulent mixing, chemical reaction and evaporation process if present. The state of a flame particle, e.g., burnt, hot gas or extinguished, is determined based on particle temperature. This model can properly describe the ignition process with a spark kernel being initiated in a nonflammable region, which is of practical importance in certain turbine engines and has not been rigorously accounted for by the existing models based on the estimation of local Karlovitz number. The model is integrated into an ignition probability analysis platform and is demonstrated for a methane/air bluff-body flame with the flow and fuel/air mixing characteristics being extracted from a non-reacting simulation. The results show that for the spark location being at the extreme fuel-lean outer shear layer of the recirculation zone, PMR can yield ignition events with a significant number of active flame particles. The mechanisms for the survival of the initial flame particles and the entrainment of the survived flame particles into the recirculation zone are analyzed. The results also show that the ignition probability map from PMR agrees well with the experimental observation: a high ignition probability in the shear layer of the recirculation zone near the mean stoichiometric surface, and low ignition probabilities inside the recirculation zone and the top stagnation region of the recirculation zone. The parametric study shows that the predicted shape of the ignition progress factor and ignition probability is in general insensitive to the model parameters and the model is adequate for quantifying the regions with high ignition probabilities.     

基于工业物联网的混流车间机器人自适应调度

随着工业物联网技术与人工智能技术深度融合,物料机器人已广泛应用于物联网车间中。针对车间存在实时动态变化和状况不确定等诸多复杂因素,本文提出以组分层建树和以实时状态为根节点的SP–MCTS(Singleplayermonte-carlotreesearchalgorithm)搜索方法实现车间自适应调度决策。该方法将机器人调度问题转化为马尔科夫决策过程(Markov decision process,MDP),并详细描述车间状态、动作、奖励和策略的表示方法。在实时调度过程中,该搜索方法依据工件组分层建树,搜索中只考虑相邻两组间的状态关系,从而简化计算难度。在子树搜索中,应用SP–MCTS以实时状态为根节点进行搜索,同时应用扩展方法和剪支方法进行策略探索和信息累积,使得在子树内实时状态节点越深,就越能够快速精准获取最优策略。最后,通过实际案例模拟分析,验证了该方法的有效性和优越性。     

低轨卫星缺失时序数据的模式识别方法

在航天应用中，低轨卫星经常会由于原始数据缺失而影响卫星时序数据模式识别结果，降低准确率。针对该问题提出了一种新型MR-GRU模型，可有效处理缺失时序数据，并获得较好的模式识别准确率。区别于传统模型的补全缺失数据的方法，MR-GRU模型直接在缺失时序数据上运用循环神经网络进行训练，对传统门控循环单元结构进行了改进，增加了两个新变量：掩蔽项和衰减项。掩蔽项作用于输入，衰减项作用于输入和隐层单元输出。MR-GRU模型不仅能够保持时序数据固有的时间特性，还能有效提高模式识别精度。在卫星时序数据上的模式识别试验表明，MR-GRU模型准确率优于传统模型。     

一种面向工业互联网的云存储方法

工业互联网是工业信息化进程中最受关注的热点，海量异构数据管理是其中的重点之一。传统的关系数据库（RDB）对海量多源异构数据的读写和检索都存在性能瓶颈，而近年来兴起的云数据管理方法主要是针对“键-值”（K-V）模式，无法依靠主键以外的数据属性对数据进行快速查找。提出了一种面向工业互联网的云存储方法——StoreCDB，在异构采样数据统一表达数据模型基础上，实现非结构化存储管理，同时，利用两级索引实现海量数据的快速检索。通过实验，在分布式集群实验平台上，采用海量高铁列车运行模拟数据，验证了StoreCDB具有良好的异构数据存储和检索性能，为工业互联网提供了一种新的数据管理方法。      

基于PTE的多雷达航迹融合算法

针对杂波背景下的多雷达航迹融合时局部估计误差互协方差矩阵未知的问题，提出基于目标存在概率（PTE）的航迹融合算法，提升了正确航迹率和跟踪精度。首先，通过综合概率数据关联得到单接收站的目标航迹估计集合和对应的目标存在概率。然后，在局部估计误差互协方差矩阵未知的条件下，基于PTE信息提出不带记忆的综合广义凸组合航迹融合算法。进而将前一帧的融合状态进行反馈，提出带记忆的综合广义凸组合航迹融合算法。仿真验证了所提算法的有效性。