基于故障风险标尺的复杂装备健康状态分类模型

针对复杂装备故障呈现出多重性、相关性及模糊性的特点,本文分析了装备健康状态演化规律,利用自适应模糊神经网络、故障模式、影响及危害性分析构建故障风险标尺,实现了对复杂装备故障风险程度的定量化描述及装备健康状态的分类。通过实验分析,本文提出的模型相比于传统的故障预测以及故障风险程度定量方法具有显著优势,实现了对装备从设计生产、部署使用以及退役报废全寿命周期的动态反馈,对提高复杂装备综合保障能力具有重要意义。     

轨道分析解的改进方法及其应用

主要介绍一种通过改进各类轨道摄动项的表达形式,以优化计算效率的轨道分析解改进方法。以低地球轨道为例,阐述了轨道分析解改进后的具体算法,并通过数值仿真分析验证了算法的有效性和实用性。算法以第一类无奇点根数作为轨道状态量,采用开普勒轨道根数计算各类摄动力的长期、长周期和短周期项,通过较简单的组合形式计算无奇点根数的对应摄动项,实现在保持分析解精度和消除小偏心率奇点的同时,提高计算效率。仿真结果表明,分析解算法的模型精度在1E-5量级,符合一阶分析解理论精度的预期;同时计算速度达到传统分析解算法的4倍左右,可有效提升空间碎片轨道预报的计算效率,具有较强的工程应用价值。     

基于概率图的作战任务智能规划方法

针对人工调配作战资源及规划方案效率低下的问题,本文提出一种基于概率图的作战任务智能规划方法,通过统计分析判定任务间因果关系,采用GNN抽取任务中的关键事件构建概率图并计算任务规划方案成功的概率,进而基于时间序列方法预测战场态势变化,实现辅助指挥员智能决策。最后,本文在某联合登岛案例中开展了方法验证,结果表明,所提出的方法可成功实现任务规划并具有可解释性,可实现对战场态势变化的预测和快速响应,在战场上为军队提供强有力的支持。     

Incorporating textual and management factors into financial distress prediction: A comparative study of machine learning methods

Financial distress prediction (FDP) has been widely considered as a promising approach to reducing financial losses. While financial information comprises the traditional factors involved in FDP, nonfinancial factors have also been examined in recent studies. In light of this, the purpose of this study is to explore the integrated factors and multiple models that can improve the predictive performance of FDP models. This study proposes an FDP framework to reveal the financial distress features of listed Chinese companies, incorporating financial, management, and textual factors, and evaluating the prediction performance of multiple models in different time spans. To develop this framework, this study employs the wrapper-based feature selection method to extract valuable features, and then constructs multiple single classifiers, ensemble classifiers, and deep learning models in order to predict financial distress. The experiment results indicate that management and textual factors can supplement traditional financial factors in FDP, especially textual ones. This study also discovers that integrated factors collected 4 years prior to the predicted benchmark year enable a more accurate prediction, and the ensemble classifiers and deep learning models developed can achieve satisfactory FDP performance. This study makes a novel contribution as it expands the predictive factors of financial distress and provides new findings that can have important implications for providing early warning signals of financial risk.     

The industrial asymmetry of the stock price prediction with investor sentiment: Based on the comparison of predictive effects with SVR

As a representative emerging financial market, the Chinese stock market is more prone to volatility because of investor sentiment. It is reasonable to use efficient predictive methods to analyze the influence of investor sentiment on stock price forecasting. This paper conducts a comparative study about the predictive performance of artificial neural network, support vector regression (SVR) and autoregressive integrated moving average and selects SVR to study the asymmetry effect of investor sentiment on different industry index predictions. After studying the relevant financial indicators, the results divide the Shenwan first-class industries into two types and show that the industries affected by investor sentiment are composed of young companies with high growth and high operative pressure and there are a great number of investment bubbles in those companies.     

基于四元数图神经网络的知识图谱嵌入

针对当前大多数知识图谱嵌入方法对实体和关系的表示能力低、难以处理复杂关系的问题,提出一种基于四元数图神经网络的知识图谱嵌入方法,用于解决知识图谱的链路预测问题。该方法为了包含更丰富的关系信息,将四元数引入到知识图谱嵌入中对实体和关系建模,并考虑两者之间的共现关系。模型利用勒维图变换将知识图谱中的实体和关系转换为图网络中的节点,采用两者的共现关系构建图中的边;将四元数图神经网络(quaternion graph neural networks, QGNN)作为编码器模块,学习图节点的四元数嵌入;利用四元数空间内的哈密顿乘积构造评分函数对生成三元组进行排序。实验结果表明,所提模型能够很好地捕捉到实体与关系之间潜在的相互依赖关系,在知识图谱嵌入方面优于现有的嵌入模型。     

运用属性论方法加强供应链牛鞭效应防范

提高预测的准确性是缓解供应链牛鞭效应的关键。目前预测的方法往往很难适应订购量历史数据的变动,导致预测结果的偏差。运用属性论方法,就制造商—零售商—客户三级供应链,提出了一个需求信息预测的方法,由此来提高对这种波动性的适应能力,增强预测的准确性,帮助供应链上各节点企业优化决策过程,最终防范了牛鞭效应,并且还提供了此预测方法的算法流程。     

神经网络模型在面板坝堆石体施工期沉降变形预测中的应用

在分析面板坝堆石体施工期坝体沉降影响因素的基础上,将影响沉降的主要因素作为网络输入参数,以测点沉降量作为网络的输出,建立了神经网络模型.以水布垭面板坝堆石体为例,将模型预测值与实测结果进行了对比,结果表明,预测值与实测结果比较接近,该神经网络能很好地反映面板坝堆石体施工期沉降变形与其影响因素之间的非线性映射关系,预测结果可作为后期填筑反馈设计的依据,同时可通过网络输入参数的调整检验某一因素对坝体沉降的影响程度.     

隧道地表沉降预测的时变参数灰序模型TGM-AR

在趋势项提取法中,针对逐步回归法比较烦琐及灰色模型预测精度低的缺点,结合灰色预报系统的灰色性和时变性,根据变形体的实际变形规律,将时变参数a(t),b(t)及灰色理论应用于时序模型建模中,提出并建立时变参数灰序模型TGM-AR.时变参数灰色模型用于提取趋势项部分,时序模型用于提取随机部分.将模型应用于隧道地表的沉降分析和预测,结果表明模型预报精度高,且趋势项的物理意义明确.     

基于HMM的多维数据下扶贫对象状态预测

针对扶贫领域中贫困、脱贫和返贫状态预测不准确,影响状态变迁的关键因素难以识别的问题,从扶贫基础数据和多个行业数据中提取8个关键特征和22个观测状态,构建观察状态和隐含状态关联关系,建立扶贫对象状态预测隐马尔可夫模型(hidden markov model,HMM)。以某深度贫困县连续3年的数据为样本,进行参数训练、测试实验和结果验证,结果表明该方法对返贫、贫困和脱贫状态有较强的预测能力,误差率较低,且能准确识别出影响返贫的关键要素。该方法对指导精准扶贫工作具有非常重要的实际意义。