基于神经网络模型的学习诊断

基于故障树模型的诊断把故障树的底事件分成三部分：必然的故障源集（ＣＦＳ）、正常底事件集（ＮＥＳ）和可能的故障源集（ＰＦＳ），及如何进一步确定ＰＦＳ中各元素的状态（正常或异常）。在存在大量训练样本的情况下，可采用基于神经网络模型的学习诊断方法来确定ＰＦＳ中各元素的状态，并通过对某卫星能源系统故障模拟原理性试验台的故障诊断验证了该方法的有效性。     

竞争学习模糊神经网络及在导弹故障诊断中的应用

尽管基于解析冗余的故障诊断方法有许多突出的优点而越来越多地得到的研究和应用，但它依赖于系统的模型，当系统存在非线性或不确定性时，存在难以建模的困难，模糊神经网络可以通过学习建立系统的模型，且模型参数有明确的物理意义，初始参数易于选择，成为解决这一问题的优选途径，作者通过把模糊神经网络的学习转化为竞争聚类和线性优化问题，基于竞争聚类和最小二乘原理，提出了一种模糊神经网络学习算法，并在某伺服机构上进行     

基于改进人工蜂群算法的多值属性系统故障诊断策略

针对实际工程应用中常见的多值属性系统故障诊断策略问题,在传统人工蜂群算法(Artificial Bee ColonyAlgorithm,简称 ABC算法)的基础上,提出改进蜂群算法用于多值属性系统的测试序列寻优。首先,在蜂群算法中重新定义多值 D矩阵和五元组的含义;其次,引入方向信息概率矩阵,设置状态转移规则和矩阵元素更新策略;最后,采用导弹舵系统实例说明算法的实现过程和有效性。最终测试序列寻优结果表明:与传统的多值 Rollout算法相比,文中所提算法能得到较好的诊断策略结果,具有一定的应用价值。     

一种基于条件熵的航电设备故障诊断方法

针对目前航电设备故障诊断能力相对较弱的现状，提出一种将粗糙集中的条件熵算法应用于故障诊断的方法，并将该方法应用于实例．结果表明诊断结果准确简化，有助于提高装备可靠性和维修性。     

基于导航定位原理的火箭涡轮泵轴承故障诊断

为准确判断火箭发动机涡轮泵轴承在试验台上试验时发生故障的部位，同时避免通过轴承特征频率诊断轴承故障的方法所带来的不确定性，基于GPS卫星导航定位原理，利用时幅曲线的相位信息，提出一种新的轴承故障诊断方法:振源坐标定位法，即通过四个已知坐标的振动传感器测得同一振动波的时幅曲线相位差判定振源位置。将试验台上轴承和四个振动信号传感器安放在坐标已知的直角坐标系中，利用时幅曲线拐点分析法准确捕获振动信号到达四个传感器的时刻，再利用这四个时刻和已知坐标计算出振源位置坐标，最后根据振源位置坐标判断其是否为轴承故障及具体故障部位。通过仿真计算证明该方法理论上可行。     

A critique of reliability prediction techniques for avionics applications

Avionics (aeronautics and aerospace) industries must rely on components and systems of demonstrated high reliability. For this, handbook-based methods have been traditionally used to design for reliability, develop test plans, and define maintenance requirements and sustainment logistics. However, these methods have been criticized as flawed and leading to inaccurate and misleading results. In its recent report on enhancing defense system reliability, the U.S. National Academy of Sciences has recently discredited these methods, judging the Military Handbook (MIL-HDBK-217) and its progeny as invalid and inaccurate. This paper discusses the issues that arise with the use of handbook-based methods in commercial and military avionics applications. Alternative approaches to reliability design (and its demonstration) are also discussed, including similarity analysis, testing, physics-of-failure, and data analytics for prognostics and systems health management.     

基于FDG和GA的故障诊断技术在电子对抗装备中的应用

探讨了模糊有向图（Fuzzy Directed Graph,FDG）和遗传算法（Genetic Algorithm,GA）相结合的故障诊断技术及其在电子对抗装备故障诊断中的具体应用。根据电子对抗装备组件的实际状态,应用模糊理论得出各组件发生故障的可能性,建立电子对抗装备的模糊有向图,利用遗传算法搜索出模糊有向图中可能的故障传播路径。实践表明,该技术应用在电子对抗装备的故障诊断中是行之有效的,取得了较好的诊断结果。     

飞机健康状况量化分析方法浅析

提出与飞机健康状况相关的事件参数、风险参数的概念，具体阐述了建立量化模型的思路和方法。该方法简单可靠，具有较强的可扩展性，可为飞机的技术派遣提供决策支持。     

基于BHS-树的定性故障诊断方法

基于定性模型的诊断方法,由于无需系统定量模型,尤其适用于航天器等复杂系统的故障诊断.该方法推理过程包括冲突集的确定及诊断集的生成.基于BHS-树的方法,是一种由冲突集生成诊断集的有效途径,但存在诊断结果冗余及反向递归过程复杂的问题.采取异常/正常特征量相结合的措施,有效地解决了诊断结果冗余的问题,能够准确确定诊断集;同时在系统单故障的假设前提下,对反向递归过程进行适当简化,降低了推理的复杂程度,并通过实例对上述改进进行了验证.     

A data-driven health indicator extraction method for aircraft air conditioning system health monitoring

Prognostics and Health Management (PHM) has become a very important tool in modern commercial aircraft. Considering limited built-in sensing devices on the legacy aircraft model, one of the challenges for airborne system health monitoring is to find an appropriate health indicator that is highly related to the actual degradation state of the system. This paper proposed a novel health indicator extraction method based on the available sensor parameters for the health monitoring of Air Conditioning System (ACS) of a legacy commercial aircraft model. Firstly, a specific Airplane Condition Monitoring System (ACMS) report for ACS health monitoring is defined. Then a non-parametric modeling technique is adopted to calculate the health indicator based on the raw ACMS report data. The proposed method is validated on a single-aisle commercial aircraft widely used for short and medium-haul routes, using more than 6000 ACMS reports collected from a fleet of aircraft during one year. The case study result shows that the proposed health indicator can effectively characterize the degradation state of the ACS, which can provide valuable information for proactive maintenance plan in advance.