精密机电设备寿命评估方法

寿命评估技术既是确保设备安全、可靠运行的核心和关键,也是设备定寿、延寿的重要依据。从工程的视角,根据精密机电设备的工作状态,将精密机电设备分为新研设备、工作态设备、贮存态设备3类,分析这3种状态机电设备的特点及可以获取的信息资源,进而对新研设备、工作态设备、贮存态设备的寿命评估方法进行了系统研究和评述,对存在的问题及未来发展趋势进行了分析和展望。鉴于难以对复杂精密机电设备的机理进行建模,数据驱动的寿命估计已成为当前研究的主流,本文在3种状态机电设备分类的框架下,重点分析了数据驱动寿命估计的研究动态。     

基于长短期记忆网络时序数据趋势预测及应用

为了研究状态监测大数据对设备运行状态的估计和预测,提出了一种人工经验与主成分分析相结合的长短期记忆网络方法（AEPCA-LSTM）,利用运行过程中的监测时序数据对设备运行趋势进行预测。首先,通过基于人工经验的主要成分分析方法（AEPCA）从状态监测系统中提取与目标变量最相关的状态变量作为输入;其次,利用长短期记忆网络（LSTM）对目标变量趋势变化进行预测,并考虑运行过程中新数据样本的持续产生,对模型进行定期更新,以提高模型的动态适应性。最后,将所提出的方法应用于船舶副机系统的涡轮增压器转速预测中,结果表明该方法相对于传统的PCA-LSTM和LSTM,具有更小的预测平均误差0.18037,即展现了其在时序数据趋势预测的优势。     

一种航空发动机运行可靠性评估方法

航空发动机运行过程中,可靠性评估是航空发动机可靠性评估领域的关键问题之一,而合理的评估方法能够提高可靠性分析的效率和精度,因此本文提出一种支持评估飞机任务过程中航空发动机运行可靠性的方法。结合飞行任务特点和航空发动机工作特性,以快速存取记录器信息为分析数据,考虑当前运行环境、飞机瞬时状态、发动机当前工作状态 3 类因素对运行可靠性进行分析;将随机森林算法与分层抽样法结合对数据进行拟合、预测并计算特征重要度;以 B737-800 机型一次北京—乌鲁木齐的飞行任务为例,对方法的有效性和可行性进行验证。结果表明：本文提出的可靠性评估方法解决了航空发动机运行过程中数据量大、维度高导致的数据处理困难问题。     

一种基于投影寻踪的航天器健康评估方法

针对常用健康评估方法在航天器测控管理领域应用过程中出现的通用性、易用性和适用性方面的不足,提出了一种基于投影寻踪评估模型的航天器健康评估方法.该方法首先计算得出分系统运行状态的可信度;然后利用卫星故障预案和故障实例构建投影寻踪评估模型,自动获取运行状态指数评价权重;最后通过构建等级评价标准对航天器健康状态进行评估.以某在轨卫星为例进行仿真测试,验证结果显示该方法所构建模型简便且易于升级维护,评估结果与实际情况吻合,对解决实际的工程问题具有实用价值.     

基于 Stacking集成学习的飞行模拟器设备故障预判

为精准研判飞行模拟器故障问题,提升飞行模拟器故障应急处理能力,提出了 1种基于 Stacking集成学习的设备故障预判方法。首先,针对设备故障数据具有高维度和时序性的特点,采用正态分布法,对采集的原始故障数据进行缺失值和异常值处理,获取归一化数据,并基于核主成分分析法,提取数据的特征并降低数据维度;然后,构建以 CNN、RF、BP神经网络为基分类器,XGBoost为元分类器的 Stacking集成学习模型,采用交叉验证训练策略,对设备的故障类型作出预判;最后,构架典型案例。仿真结果表明,所提方法可正确有效地识别设备的多种故障状态。     

基于大数据的空管运行安全预警研究

空中交通管制的任务是确保航空器的安全飞行,为了保证飞行安全,需要进行空中交通管制系统运行安全评估及预警的研究.借鉴大数据理论建立空中交通管制大数据概念,从影响空中交通管制系统运行的主要风险因素出发,建立空中交通管制安全运行的状态向量空间,利用主成分分析法去除基础向量线性相关性,再利用聚类分析过程建立空中交通管制运行安全预警知识库,实现空中交通管制运行安全评估和及时预警.结果表明:所用的预警分类分析方法能够很好地实现预警分类和安全评估,为管制部门的相关决策提供理论依据.     

基于迁移学习的小样本目标识别研究进展与展望

在空、天、海等复杂环境下的目标识别任务中，高质量的样本数据往往较少。特别是在干扰对抗环境下，某些特定领域的目标信息获取困难，可靠的标注数据较少。小样本问题对深度学习技术在目标识别任务中的应用提出了新的挑战。迁移学习为小样本不确定环境下的目标识别问题提供了新的研究思路。本文针对小样本目标问题，以机载雷达等空天传感器信息对海面目标识别为例，介绍了迁移学习的主要思路和方法，对迁移学习在海面目标识别问题中的应用现状进展进行了总结；分析和归纳了迁移学习在海面目标识别应用中的主要挑战。最后对可解释性及鲁棒性的海洋目标识别技术需求及未来发展方向进行了展望。     

雷达电源系统安全运行健康状态评估研究

雷达电源系统的运行状态直接影响整个雷达设备的安全性与性能指标的实现,如何实现雷达电源的 健康状态评估是亟待解决的问题。首先采用雷达电源正常状态下的健康特征数据训练自组织神经网络;然后 计算监测数据与训练后的自组织神经网络中权重向量的距离,将距离值归一化表示为健康度;最后利用试验数 据计算健康度,并实现健康分级。结果表明:该模型计算的健康度随电源老化时间变化整体呈现下降的特点, 该模型可以实现雷达电源健康状态评估。     

基于机器学习的飞机动力装置运行可靠性

为了研究分析飞机的动力装置在执行飞行任务过程中的运行可靠性,针对运行可靠性影响因素的多维、耦合的特点,采用机器学习方法对动力装置运行可靠性的时变规律及其相关影响因素进行分析。提出了考虑动力装置的工作状态、飞机的运行外界条件、飞机的飞行状态3类因素分析动力装置实时运行状态下的时变可靠性方法;并基于飞机实际运行的快速存取记录器（QAR）数据,梳理了动力装置运行可靠性分析相关的3类因素、16个主要特征。结合飞机运行的时空关系,采用数据包络分析（DEA）方法对飞机动力装置的工作状态特性与性能裕度进行非参数分析,基于提取的QAR数据特征,采用随机森林、多变量神经网络回归算法,建立2种基于机器学习的动力装置运行可靠性分析模型。以B737-800机型为例,对一次北京至珠海的飞行任务的动力装置相关运行数据进行分析,对2种机器学习分析模型进行训练与测试研究。分析结果表明：对动力装置工作状态特性贡献度最大的特征依次为计算空速、飞行时间与飞行高度;对动力装置性能裕度贡献度最大的特征依次为动力装置工作状态特性、雷达气象与飞行时间。所采用的2种机器学习方法能较好反映动力装置运行过程的时变可靠性规律,可为动力装置的运行与特情处理提供参考。     

SLE服务在测控设备中的应用研究

针对CCSDS(空间数据系统咨询委员会)建议的SLE(空间链路扩展)服务并不完全适应现有测控设备运行管理体系和数据交互体系的问题,在介绍SLE服务体系和我国航天测控设备运行管理体系的基础上,对测控设备接口关系、SLE业务对现有测控设备的要求以及SLE服务在测控通信领域的发展等方面进行了重点研究,提出了应用SLE服务的测控设备接口方案和相关设备设计要求,并建议逐步在深空站等具备条件的地面站配置和使用自主开发的SLE服务。     

基于等级状态方法的 军校本科学员学习能力评价模型

文章以等级状态方法为依托,构建军校本科学员学习能力评价指标体系,优选数据采集的方法途径,创建 数学模型,并进行实证分析,验证整套评价系统是比较客观的,具有推广应用价值。     

Rotating machinery fault detection and diagnosis based on deep domain adaptation: A survey

In practical mechanical fault detection and diagnosis, it is difficult and expensive to collect enough large-scale supervised data to train deep networks. Transfer learning can reuse the knowledge obtained from the source task to improve the performance of the target task, which performs well on small data and reduces the demand for high computation power. However, the detection performance is significantly reduced by the direct transfer due to the domain difference. Domain adaptation (DA) can transfer the distribution information from the source domain to the target domain and solve a series of problems caused by the distribution difference of data. In this survey, we review various current DA strategies combined with deep learning (DL) and analyze the principles, advantages, and disadvantages of each method. We also summarize the application of DA combined with DL in the field of fault diagnosis. This paper provides a summary of the research results and proposes future work based on analysis of the key technologies.     

过热蒸汽射流冷却叶片热耦合数值模拟

在对射流冷却平板模型和射流冷却凹板模型数值模拟的基础上,设计了射流冲击冷却式蒸汽冷却叶片,并对其进行了热耦合数值模拟.通过改变平板和凹板的进口雷诺数,射流孔与靶板间距和凹板曲率,对靶板的冷却传热进行了对比研究,得到传热量与各个参数的变化规律.然后根据上面得到的变化规律设计出射流冲击冷却式蒸汽冷却叶片,应用ANSYS CFX 10.0数值程序,对冲击冷却的流动和传热过程进行了三维热耦合数值模拟,得到叶片表面温度和对流换热系数分布.      

静态封严篦齿内部流动与换热的数值计算

建立二维篦齿模型,运用数值方法,从分析齿腔内流场和篦齿顶板换热的角度研究了篦齿的封严特性.通过多种工况的计算,探讨了雷诺数、齿顶宽和齿隙之比对篦齿腔内流动、压降损失以及齿腔顶板换热系数之间的关系.计算数据和实验数据进行比较,发现变化规律一致,误差较小.研究结果表明:雷诺数、齿顶宽和齿隙之比影响着齿腔内部流动和换热的状态,是最终成为决定篦齿封严效果的重要因素.      

Transfer learning: A new aerodynamic force identification network based on adaptive EMD and soft thresholding in hypersonic wind tunnel

The aerodynamic test in the pulse combustion wind tunnel is very important for the design, evaluation and optimization of aerodynamic characteristics of the hypersonic aircraft. The test accuracy even affects the success or failure of hypersonic aircraft development. In the aerodynamic test of pulse combustion wind tunnel, the aerodynamic signal is disturbed by the inertial force signal, which seriously affects the test accuracy of aerodynamic force. Aiming at the above problems, this paper innovatively proposes an aerodynamic intelligent identification method, that is the transfer learning network based on adaptive Empirical Modal Decomposition (EMD) and Soft Thresholding (TLN-AE&ST). Compared with the existing aerodynamic intelligent identification model based on deep learning technology, this study introduces the transfer learning idea into the aerodynamic intelligent identification model for the first time. The TLN-AE&ST effectively alleviates the problem of scarcity of training samples for intelligent models due to the high cost of wind tunnel tests, and provides a new idea for further implementation of deep learning technology in the field of wind tunnel aerodynamic testing. And this study designed residual attention block with soft threshold and dense block with adaptive EMD in TLN-AE&ST model. Residual attention block with soft threshold module can more effectively suppress the influence of instrument noise signal on model training effect. Dense block with adaptive EMD makes the deep learning model no longer a black box to a certain extent, and has certain physical significance. Finally, a series of wind tunnel tests were carried out in the Φ = 2.4 m pulse combustion wind tunnel of China Aerodynamic Research and Development Center to verify the effectiveness of TLN-AE&ST.     

航空发动机篦齿封严特性数值模拟

本文运用数值计算方法,从分析齿腔内流场和篦齿顶板换热的角度研究了篦齿的封严特性。通过多种工况的计算,分析了雷诺数和齿顶宽与齿隙之比（T／C）对篦齿腔内流动、压降损失以及齿腔顶板换热系数的影响。计算数据和实验数据吻合良好,误差较小。研究表明：雷诺数、齿顶宽与齿隙之比影响着齿腔内部流动和换热的状态,是决定篦齿封严效果的主要因素。     

State Estimation and Divergence Analysis

A growing memory discrete dynamic model for performing temporal extrapolations along a predetermined path in a random field is presented. This dynamic model is used to drive a linear system that is itself driven by discrete white noise. The coupled system is used to derive a state estimation scheme that recursively processes noisy measurements of the system. In addition, using the aforementioned dynamic model as a reference (truth) model, the authors develop a covariance analysis to measure the estimation errors that occur when the dynamics along the path through the field are modeled as a Markov linear model and state estimation is performed using discrete Kalman filtering. The performance evaluation of an inertial navigation system influenced by the Earth's gravity field aboard a maneuvering ship is provided as a specific illustrative example.     

Calculation of Wall Temperature for Aircraft Exhaust System with Considering Gas Radiation Heat Transfer

The coupled numerical simulation of flow field, solid temperature field, species concentration field and gas radiation transfer/ energy field based on statistical narrow-band correlated-k (SNBCK) model, is employed to accurately predict aerothermodynamic characteristic of aircraft exhaust system. A series of methods to increase computational efficiency and descend computational resources make it possible to finish the calculation in PC. The parameters of narrow-band model are evaluated by HITEMP line-by-line database. Three examples have proved the accuracy of using these methods to solve flow heat transfer coupled problem and radiation transfer/energy equation, which are the calculation of temperature distribution of water-cooling nozzle in rocket engine, the calculation of carbon dioxide absorptivity at 4.3 micron band, and the gas radiation heat transfer evaluation of the cylindrical furnace. Finally, the inner flaps temperature distribution of ejecting nozzle with floating outer flaps is computed, under high-altitude, high-speed and afterburning conditions. Two completely different air-inlet schemes of ejecting channel almost achieve the same effect in cooling inner flaps.     

A generative deep learning framework for airfoil flow field prediction with sparse data

Deep learning has been probed for the airfoil performance prediction in recent years.Compared with the expensive CFD simulations and wind tunnel experiments, deep learning models can be leveraged to somewhat mitigate such expenses with proper means. Nevertheless, effective training of the data-driven models in deep learning severely hinges on the data in diversity and quantity. In this paper, we present a novel data augmented Generative Adversarial Network(GAN), da GAN, for rapid and accurate fl...