数据挖掘故障诊断专家系统

为了及时准确地对防空导弹飞行试验故障进行诊断,克服传统专家系统获取专家知识的瓶颈,立足于防空导弹飞行试验历史数据,利用数据挖掘的方法获得飞行试验故障模式判定决策树,进而得出导弹故障判定规则,形成故障诊断专家知识库,构建防空导弹故障诊断专家系统.这使数据挖掘和专家系统两者的优点得到充分发挥.     

Real-time prediction of projectile penetration to laminates by training machine learning models withfinite element solver as the trainer

Studies on ballistic penetration to laminates is complicated, but important for design effective protection of structures. Experimental means of study is expensive and can often be dangerous. Numerical simu-lation has been an excellent supplement, but the computation is time-consuming. Main aim of this thesis was to develop and test an effective tool for real-time prediction of projectile penetrations to laminates by training a neural network and a decision tree regression model. A large number of finite element models were developed;the residual velocities of projectiles fromfinite element simulations were used as the target data and processed to produce sufficient number of training samples. Study focused on steel 4340tpolyurea laminates with various configurations. Four different 3D shapes of the projectiles were modeled and used in the training. The trained neural network and decision tree model was tested using independently generated test samples using finite element models. The predicted projectile velocity values using the trained machine learning models are then compared with thefinite element simulation to verify the effectiveness of the models. Additionally, both models were trained using a published experimental data of projectile impacts to predict residual velocity of projectiles for the unseen samples. Performance of both the models was evaluated and compared. Models trained with Finite element simulation data samples were found capable to give more accurate predication, compared to the models trained with experimental data, becausefinite element modeling can generate much larger training set, and thus finite element solvers can serve as an excellent teacher. This study also showed that neural network model performs better with small experimental dataset compared to decision tree regression model.     

基于时域平均的齿轮故障诊断

提出了信号时域平均处理的新算法,解决了周期截断误差对平均结果的影响,并对测取的齿轮箱齿轮故障振动信号进行了处理。实验结果表明:该方法在齿轮故障信号的处理中能够消除背景噪声的影响,取得比较理想的效果。     

粗糙神经网络的航空电子系统故障诊断方法

提出了一种基于粗糙神经网络的航空电子系统故障诊断方法.该方法运用粗糙集理论进行知识规则的提取,用提取的规则对航空电子系统输出数据进行分类,再用神经网络对每一类进行辨识,最后用粗糙集分类结果与各个神经网络输出进行综合得到系统一步预测结果,将该预测结果与航空电子系统实际输出进行阀值比较,进而进行故障诊断.实际应用表明该方法可行并能够有效地检测系统故障,故障诊断率高.     

Transient analysis of Markov models of fault‐tolerant systems with deferred repair using split regenerative randomization

The (standard) randomization method is an attractive alternative for the transient analysis of continuous time Markov models. The main advantages of the method are numerical stability, well‐controlled computation error, and ability to specify the computation error in advance. However, the fact that the method can be computationally very expensive limits its applicability. In this paper, we develop a new method called split regenerative randomization, which, having the same good properties as standard randomization, can be significantly more efficient. The method covers reliability‐like models with a particular but quite general structure and requires the selection of a subset of states and a regenerative state satisfying some conditions. For a class of continuous time Markov models, model class C₂, including typical failure/repair reliability‐like models with exponential failure and repair time distributions and deferred repair, natural selections are available for both the subset of states and the regenerative state and, for those natural selections, theoretical results are available assessing the efficiency of the method in terms of “visible” model characteristics. Those results can be used to anticipate when the method can be expected to be competitive. We illustrate the application of the method using a large class C₂ model and show that for models in that class the method can indeed be significantly more efficient than previously available randomization‐based methods. © 2006 Wiley Periodicals, Inc. Naval Research Logistics, 2006     

一种针对HIGHT的改进差分故障的分析

为评估HIGHT轻型分组密码抗故障攻击能力,基于单字节故障模型,提出一种改进的HIGHT故障攻击方法．首先在HIGHT最后1轮注入单字节故障恢复SK124和SK1262个轮密钥,然后增加故障注入深度,在HIGHT倒数第5轮注入单字节故障恢复HIGHT另外10个轮密钥,从而恢复HIGHT的全部主密钥．实验结果表明：仅需22次故障注入即可恢复HIGHT全部128位主密钥,优于现有故障攻击方法所需的32次故障注入．     

基于面向对象技术的柴油机在线状态监测系统设计

将软件设计中的面向对象思想扩展到系统设计中,针对柴油机实车运行在线监测中的变速变载及空间有限等问题,基于CAN总线的可靠性、信息传输的实时性和多主工作方式,设计分布式智能监测节点和上位机监控中心．分布式监测节点同步采集柴油机运行数据并进行降噪和简单特征提取后,将实时采样数据和在线监测结果上传至基于嵌入式PCI04的上位机监控中心,进行二次特征提取和智能模式识别,从而实现柴油机在线状态监测与故障预警和诊断．     

面向无人环境的机器人生态圈自主任务决策方法

借鉴自然界生态系统的典型特征,提出机器人生态圈概念。通过使集群机器人进行智能协同与复杂演化,涌现自我维持、自我复制与自我进化等生命特征,实现无人条件下的长期生存、繁衍与进化,并执行特定的任务。针对机器人生态圈典型任务场景的自主任务决策需求,分析不同机器学习任务决策方法的特点,建立机器人生态圈自主任务决策的决策树模型和神经网络模型。分析表明,两种模型的正确率均在80%~90%,且均具有良好的稳定性。这说明,机器人生态圈自主任务决策问题可以通过决策树、神经网络等机器学习方法来很好地加以解决,从而为面向无人化场景的任务应用提供技术支持。     

基于PCA-RBF网络的储运过程管道堵塞故障诊断方法

针对现代储运过程管道堵塞故障诊断时,提取的过程参数多导致诊断速度慢、性能差等问题,提出了基于主成分分析（PCA）和径向基函数（RBF）神经网络故障的诊断方法。首先利用PCA方法对储运过程高维历史数据矩阵进行特征提取,提取的故障特征信息作为训练集,并给出故障特征信息的分类号;然后将其作为RBF神经网络分类器的输入输出进行故障模式识别。仿真实验表明：该方法应用于储运过程管道堵塞故障诊断,不仅大幅度地降低了诊断模型的训练时间,而且提高了诊断正确率。     

新型舰炮武器系统的自动检测系统

阐述了某新型舰炮武器系统应用仿真技术、控制技术、网络技术和信息处理技术实现自动检测,以及自动检测系统的组成和工作原理。用内模拟仿真驱动技术,实现了舰炮武器系统全自动工作方式下的点迹提取、航迹建立、目标识别、威胁判断、目标指示、捕获跟踪、求解射击诸元,全系统动态联动精度在线评估,以及在线实时故障检测。为海军新装备的操作、使用和维护提供了有效的技术手段。将提高系统可维性和生命力。