A Novel PF-LSSVR-based Framework for Failure Prognosis of Nonlinear Systems with Time-varying Parameters

Particle filtering (PF) is being applied successfully in nonlinear and/or non-Gaussian system failure prognosis. However, for failure prediction of many complex systems whose dynamic state evolution models involve time-varying parameters, the traditional PF-based prognosis framework will probably generate serious deviations in results since it implements prediction through iterative calculation using the state models. To address the problem, this paper develops a novel integrated PF-LSSVR framework based on PF and least squares support vector regression (LSSVR) for nonlinear system failure prognosis. This approach employs LSSVR for long-term observation series prediction and applies PF-based dual estimation to collaboratively estimate the values of system states and parameters of the corresponding future time instances. Meantime, the propagation of prediction uncertainty is emphatically taken into account. Therefore, PF-LSSVR avoids over-dependency on system state models in prediction phase. With a two-sided failure definition, the probability distribution of system remaining useful life (RUL) is accessed and the corresponding methods of calculating performance evaluation metrics are put forward. The PF-LSSVR framework is applied to a three-vessel water tank system failure prognosis and it has much higher prediction accuracy and confidence level than traditional PF-based framework.     

超导核磁共振技术在航天员生命保障中的应用前景探究

长期空间飞行会对航天员的身心健康造成一定的不利影响,开展航天员生命保障的研究是非常必要的。核磁共振技术是疾病检查诊断的重要手段,同样在航天员生命保障医疗中将发挥重要的作用。文章结合国内外相关研究进展以及航天员选拔、训练和航天员医监医保的相关知识,探究了超导核磁共振技术在航天员生命保障中的应用前景。     

卫星姿态控制系统在轨实时健康评估

面向航天器在轨智能自主管控的技术需求,提出一种基于多级模糊综合评价架构的卫星姿态控制系统的在轨实时健康评估方法.根据卫星姿态控制系统的性能特点,按实际功能将其划分为姿态测量、控制器和执行机构3个部分.在确定各部分单元部件健康信息的基础上,基于模糊综合评价算法对各部分的健康度分别进行评估.基于评估所得到的姿态测量、控制器和执行机构3部分健康信息,根据各部分对系统健康的影响情况结合变权综合原理确定健康影响权重,采用模糊综合评价算法实现对姿态控制系统整体健康性能的综合评估.仿真实验结果表明,所提出的方法能够有效实现卫星姿态控制系统的在轨实时健康评估.     

航空智能发动机发展需求及关键控制技术

介绍了航空智能发动机的概念及国外发展背景,智能发动机的需求和未来所面临的技术挑战,并且分析了智能发动机所需的关键控制技术,最后根据现代航空发动机的特点,详细研究分析了使现阶段航空发动机更加智能化并且易于实现的关键控制技术。     

基于KPCA 和DBN 的航空发动机排气温度基线模型

为了给航空发动机整体性能的实时监控与健康管理提供技术手段,提出1种基于核主成分分析和深度置信网络相结合的航空发动机排气温度基线模型构建方法。以配装CFM56-7B发动机的飞机在运行过程中各系统产生的快速存取数据作为原始的数据样本,利用核主成分分析进行降维处理,选用高斯函数作为核函数,将降维后的数据作为深度置信网络的输入,建立航空发动机EGT基线模型,通过大量QAR数据验证了模型的有效性和正确性。与传统神经网络建模方法相比,所提出的建模方法不但降低了网络结构的复杂度,同时也提高了模型的精度。     

飞机结构健康监测技术

飞机结构健康监测技术已经在实验室实验及飞行试验中得到了成功验证,随着技术成熟度的持续提升,在未来数年,该项技术具备极大的装机应用的可能性。飞机结构健康监测技术是一项通过传感器等硬件获取结构或系统数据信息为核心的创新性技术,该项技术能够在飞机的设计、制造、运营和维护等各个过程中发挥重要作用,同时,也是未来智能航空的关键组成部分。此外,随着人工智能、大数据、5G以及物联网概念的推进,航空结构健康监测技术的发展得到了一次飞跃的契机。本文首先全面的分析了飞机结构健康监测技术为航空领域带来的益处,并对其关键技术和应用现状进行了系统性的阐述,最后基于现有理论知识与先前工程经验创新性地提出一套民用飞机健康管理策略。     

基于改进平方根无迹卡尔曼滤波方法的涡扇发动机气路状态监控

针对涡扇发动机气路状态监控存在模型未知或不准确导致滤波效果下降甚至发散的问题,研究了一种融入高斯过程回归（GPR）的改进平方根无迹卡尔曼滤波（UKF）方法.该方法利用GPR对训练数据进行学习,建立发动机气路部件状态监控的GPR模型,替代UKF方法中的非线性系统模型;采用超球体单形采样和平方根滤波方法来提高滤波的计算效率和数值稳定性.仿真结果表明:训练的GPR模型解决了UKF方法对发动机原系统模型和噪声协方差矩阵依赖性的问题;与扩展卡尔曼滤波（EKF）和平方根UKF方法相比较,改进平方根UKF方法精度更高,对健康参数的估计精度达到99.9%,实现了对涡扇发动机单个和多个气路部件健系参数的有效跟踪.      

Fault processing policy based on dual-redundant control law for aero-engine control sensors

A fault processing policy was proposed for the circumstance under which all the dual-redundant closed-loop feedback control sensors went wrong. This policy was based on dual-redundant control law and may maintain the performance of turbofan engines. When pair of controlling sensors went wrong and the primary control law was unable to implement, control system performs the backup control law instead of the primary one so that the fault sensors were isolated from the closed control loop. This fault processing policy may not only avoid increasing engine weight and cost with the additional sensors hardware, but also avoid the error of analytical sensor signal. It can improve the engine mission reliability and control quality.     

Possible influence of solar extreme events and related geomagnetic disturbances on human cardio-vascular state: Results of collaborative Bulgarian–Azerbaijani studies

This collaborative study is based on the analysis and comparison of results of coordinated experimental investigations conducted in Bulgaria and Azerbaijan for revealing a possible influence of solar activity changes and related geomagnetic activity variations on the human cardio-vascular state. Arterial blood pressure and heart rate of 86 healthy volunteers were measured on working days during a period of comparatively high solar and geomagnetic activity (2799 measurements in autumn 2001 and spring 2002) in Sofia. Daily experimental investigations of parameters of cardio-vascular health state were performed in Azerbaijan with a permanent group of examined persons. Heart rate and electrocardiograms were digitally registered (in total 1532 records) for seven functionally healthy persons on working days and Saturdays, in the Laboratory of Heliobiology at the Medical Center INAM in Baku, from 15.07.2006 to 13.11.2007. Obtained digital recordings were subjected to medical, statistical and spectral analyses. Special attention was paid to effects of solar extreme events, particularly those of November 2001 and December 2006. The statistical method of the analysis of variance (ANOVA) and post hoc analysis were applied to check the significance of the influence of geomagnetic activity on the cardio-vascular parameters under consideration. Results revealed statistically significant increments for the mean systolic and diastolic blood pressure values of the group with geomagnetic activity increase. Arterial blood pressure values started increasing two days prior to geomagnetic storms and kept their high values up to two days after the storms. Heart rate reaction was ambiguous and not significant for healthy persons examined (for both groups) under conditions with geomagnetic activity changes. It is concluded that heart rate for healthy persons at middle latitudes can be considered as a more stable physiological parameter which is not so sensitive to environmental changes while the dynamics of arterial blood pressure reveals a compensatory reaction of the human organism for adaptation.     

基于QSSE方法的橡胶隔震支座参数识别

采用二次误差平方和(Quadratic sum-squares error,QSSE)方法对橡胶隔震支座参数识别进行研究。建立经典Bouc-Wen模型以模拟橡胶隔震支座的非线性动力学特性。对橡胶隔震支座进行振动台实验,基于实验测量的加速度响应和QSSE方法在线实时地识别橡胶隔震支座的参数和位移。研究结果表明,在两种典型地震波的激励作用下,采用QSSE方法分别对3种参数数量不同的Bouc-Wen模型进行识别,得到的橡胶隔震支座模型参数一致,且识别位移曲线和实际测量位移曲线吻合良好,验证了QSSE方法在橡胶隔震支座参数识别中的有效性与准确性,并证明了本文所得Bouc-Wen模型参数的合理性及Bouc-Wen模型简化的可行性。