基于数据驱动的重症监护病房脱机拔管预测模型的研究

目的 开发并评估一种基于数据驱动的重症监护病房脱机拔管预测模型。方法 收集重症监护病房有创机械通气患者的非时序数据、低频生命体征时序数据和高频机械通气时序数据,采用决策树、朴素贝叶斯、支持向量机、分类集成、广义线性模型和神经网络等算法构建预测模型,并进行性能评估。结果 共纳入204例患者,其中脱机成功患者122例,失败患者82例。含有163例高频机械通气时序数据的深度神经网络模型在预测脱机拔管成功率方面表现最佳,准确度94.2%,AUC值0.81,灵敏度100%,特异性80%。其他模型表现相对逊色,分类集成模型的准确率75%,AUC值0.76,灵敏度83.3%,特异性62.5%。结论 利用远程高频时序数据建立的深度神经网络模型在预测重症监护病房患者脱机拔管成功率上展现出卓越性能,明显超越未采用此类数据的模型。

基于模糊理论的数控机床液压系统故障树分析

以某数控机床液压系统为研究对象,针对其故障发生概率具有模糊性和不确定性的特点,将模糊理论引入故障树分析中,采用三角型模糊数来描述底事件发生概率。通过分析该系统故障发生的机理,建立了该系统的模糊故障树,在定性分析的基础上进行定量计算,得到了基本事件的模糊重要度这项可靠性指标,为系统的可靠性评估、故障诊断以及维修决策提供了理论依据。

模糊数据下基于连续时间贝叶斯网络的整流回馈系统可靠性建模与评估

动态故障树分析方法以故障树的直观表达形式来对系统建模,以马尔科夫方法来求解模型,同时具有故障树方法与马尔科夫方法的优点,这使其得到广泛的运用。贝叶斯网络模型在不确定性的表达、量化和推理方面具有较强的处理能力。整流回馈系统作为大型矿用挖掘机电气控制系统的重要组成部分,其工作可靠性对整个挖掘机系统的正常工作及各个动作的顺利执行具有重要的影响。考虑到该系统内部采用了大量冗余结构,采用基于连续时间贝叶斯网络的建模及分析方法对其动态特性进行动态故障树建模与评估。另一方面,考虑到这种大型复杂系统样本数量少、难以进行失效参数的精确估计等,采用模糊数来表征其基本失效率参数。通过对整流回馈系统的可靠性建模及分析验证了本方法的可行性。

数控机床可靠性评价体系探究

在分析数控机床关键故障部位、早期故障原因、性能要求的基础上,从系统、寿命周期及评价要素这3个维度,建立了可靠性评价体系的三维模型。以某型数控落地铣镗床为研究对象,通过对售后维修数据的分析确定了该机床发生故障较多的子系统,通过早期故障原因分析确定了该机床寿命周期各阶段的可靠性工作重心,进而结合该机床的性能要求建立了其可靠性评价体系。

发展不平衡不充分视阈下新时代精准扶贫的反思研究

自党的十八大以来不平凡的五年中,我们取得了一系列新的历史性成就,但也面临着发展不平衡不充分的困难和挑战,脱贫攻坚任务依然艰巨。发展不平衡不充分是新时代下精准扶贫工作面临的严峻挑战,它制约着精准扶贫的有效推进,束缚着人们对美好生活的追求。因此,大力实施乡村振兴战略,推进我国城乡、区域协调发展是新时代下精准扶贫工作的必由路径。

新起点 新境界 新任务 新征程——学习党的二十大精神的思考和认识

党的二十大“是在全党全国各族人民迈上全面建设社会主义国家新征程、向第二个百年目标进军的关键时刻召开的一次十分重要的大会。”大会的主题是,“高举中国特色社会主义伟大旗帜,全面贯彻新时代中国特色社会主义思想,弘扬伟大建党精神,自信自强、守正创新,踔厉奋发、勇毅前行,为全面建设社会主义现代化国家、全面推进中华民族伟大复兴而团结奋斗。”以主题为引领,党的二十大思想内涵系统展开,形成思想成果、政治成果和实践成果。学习贯彻二十大精神,是当前和今后长期的重要任务。这要求我们深入研读大会报告等重要文献,系统全面学习领会二十大精神。就此,本文谈几点思考和认识.

核桃产业发展现状及建议

核桃产业"千万亩基地、百亿级产值"的发展目标,把核桃产业作为凉山州百亿级重点支柱产业打造。凉山州核桃产业中长期发展规划纲要(2014—2025年)》。将在未来的三年中(2016-2018年)大力发展6.67万hm2以核桃为主的"1+X"林业产业基地。做到生态建设与开发扶贫、生态效益与经济效益、兴林与富民相统一,促进2020年实现扶贫攻坚目标。

小学歌唱教学有效性的实践与方法刍议

随着我国国家经济发展水平的不断提升,人们的生活质量也有所提高,越来越多的人开始追求精神生活的满足,所以对于艺术人才的培养也提出了较高的要求。教育工作需要从娃娃抓起,本文就是以小学阶段音乐课堂上,歌唱教学工作的有效开展和实施方法进行深入分析,希望能够通过正确的课堂教育工作开展形式,合理地对学生进行引导,使其能够在最佳的状态下,学习到更多的知识内容,提高学习效果的同时,促进学生良好地发展。

20年来国内关于“两弹一星”精神的研究综述

自1999年党中央明确阐释“两弹一星”精神的核心要义后,学术界掀起了对“两弹一星”精神的研究。20年来学术界对“两弹一星”精神的培育发展、基本内涵、时代价值、弘扬路径等方面进行了逐步深入的研究,取得了一系列重要成果。但也存在具有广泛影响力的成果偏少、研究成果的系统性理论性深度不足、历史文献挖掘不足、涉及学科较为单一、研究领域较窄等问题,今后需要在“两弹一星”精神的文化根基、实践应用、整体性研究、口述史研究、学科交叉研究等方面展开进一步探讨。

Fatigue Life Estimation Considering Strengthening of Low Amplitude Loads Using Improved Unequal Interval Grey Model

Under variable loading,fatigue life prediction is very important for the selection,design,and safety assessments of these components.In this study,based on the Miner rule,an improved damage accumulation rule was proposed to consider the strengthening and damaging of low amplitude loads.The complexity of fatigue phenomenon results in predicting fatigue life difficulty.Since grey models(GMs)only require a limited amount of data to estimate the behavior of unknown systems,they are used in this paper to account for the uncertainties resulting from various sources when fatigue life of component is predicted.An improved unequal interval GM(IUGM(1,1))has been developed and applied successfully to estimation of fatigue life.An example is used to illustrate how the method works.The results show that the proposed model not only overcomes the limitations of the traditional grey forecasting model of linear change series,but also increases the scope of GM in the fatigue life prediction of mechanical components,and its accuracy is higher than that of the traditional model.Moreover,the results indicate that the IUGM(1,1)is capable of predicting component fatigue life better than the traditional Miner rule,and yields a high prediction precision.

Interval Fault Tree Analysis of Excavator VariableFrequency Speed Control System

In consideration of the uncertainty of basic events failure rate and lack of probability statistical information in fault tree analysis( FTA) of excavator variable-frequency speed control system, the interval theory was employed and combined with conventional FTA method. The basic events failure probabilities were described by interval numbers,and the interval operators of logical gates in FTA were deduced based on interval theory. Finally,the reliability assessment of excavator variable-frequency speed control system was done by interval FTA method. The result shows that the interval FTA method is suitable for the complex system with insufficient failure data.

Structural Reliability Modeling Based on Imprecise Probability Theory under Insufficient Data

Traditional structural reliability analysis methods adopt precise probabilities to quantify uncertainties and they are suitable for systems with sufficient statistical data.However,the problem of insufficient data is often encountered in practical engineering.Thus,structural reliability analysis methods under insufficient data have caught more and more attentions in recent years and a lot of nonprobabilistic reliability analysis methods are put forward to deal with the problem of insufficient data.Non-probabilistic structural reliability analysis methods based on fuzzy set,Dempster-Shafer theory,interval analysis and other theories have got a lot of achievements both in theoretical and practical aspects and they have been successfully applied in structural reliability analysis of largescale complex systems with small samples and few statistical data.In addition to non-probabilistic structural reliability analysis methods,structural reliability analysis based on imprecise probability theory is a new method proposed in recent years.Study on structural reliability analysis using imprecise probability theory is still at the start stage,thus the generalization of imprecise structural reliability model is very important.In this paper,the imprecise probability was developed as an effective way to handle uncertainties,the detailed procedures of imprecise structural reliability analysis was introduced,and several specific imprecise structural reliability models which are most effective for engineering systems were given.At last,an engineering example of a cantilever beam was given to illustrate the effectiveness of the method emphasized here.By comparing with interval structural reliability analysis,the result obtained from imprecise structural reliability model is a little conservative than the one resulted from interval structural reliability analysis for imprecise structural reliability analysis model considers that the probability of each value is taken from an interval.

复杂多态系统的区间值模糊贝叶斯网络建模与分析

随着现代工程系统结构复杂度的增加以及运行环境的复杂化,传统的可靠性分析与评估技术已不能满足现代工程系统需求.针对复杂多态系统可靠性分析与评估的需求,本文从部件状态分析、系统结构分析入手,对存在认知不确定性同时考虑失效相关性的复杂多态系统进行可靠性建模与分析.由于现代复杂多态系统信息输入及系统故障影响因素的多样性,以及系统冗余,使得不确定性和共因失效对复杂多态系统可靠性分析和评估至关重要.本文借助贝叶斯网络对多态系统的图形表达和推理优势,采用模糊理论中区间值三角模糊数对部件概率进行描述;同时利用β因子模型对共因失效进行量化,再将其以新增共因节点的方式实现共因失效的贝叶斯网络建模,从而提出基于区间值模糊贝叶斯网络的复杂多态系统可靠性分析方法.最后,将基于区间值模糊多态贝叶斯网络对具有共因失效的多态卫星天线双轴定位机构传动系统进行可靠性分析.通过对实际工程系统的分析,表明本文建立的多种因素影响下复杂多态系统的可靠性建模和分析方法,进一步完善了复杂系统可靠性分析理论与方法.

混合不确定性下机床主轴可靠性建模与分析

重型数控机床肩负着众多关系国民经济与国防安全的产品及关键零部件的加工制造,其质量、性能和技术水平是衡量一个国家工业化水平和综合实力的重要标志.与普通数控机床相比,重型数控机床可靠性建模与分析具有系统结构复杂、样本少、试验数据不足、信息不全、可靠性数据类型多样、故障机理复杂等难点.同时重型数控机床可靠性受到多种不确定性因素的影响,针对重型数控机床不确定性分析难点,本文以重型数控机床主轴为研究对象,分析了影响其可靠性的各种不确定性因素,建立了基于不精确概率理论的混合不确定性量化方法.基于应力-强度干涉理论,提出了针对机床零部件的不精确可靠性建模与分析的一般方法,并以某型号重型数控落地铣镗床铣轴为例,对铣轴的静强度和疲劳强度进行可靠性分析与计算.通过与蒙特卡罗方法的对比,验证了本文所提方法的有效性.

Fault Tree Analysis of Feeding Control System for Computer Numerical Control Heavy-Duty Horizontal Lathes with Multiple Common Cause Failure Groups

The lathes are basic machine tools for manufacturing cylindrical parts. In recent years, the DLseries computer numerical control(CNC) heavy-duty horizontal lathes(HDHLs) have been widely used in the transportation, energy and aviation industries. High availability of the CNC heavy-duty lathes is demanded to guarantee the efficiency and benefit of these manufacturing industries. As one of the key subsystems of the HDHLs, the feeding control system is studied in this paper on reliability modeling and reliability analysis. The fault tree analysis(FTA) method is used for reliability modelling of the feeding control system. Considering the multiple common cause failure groups(CCFGs) existing in the system, a modified beta factor parametric model is introduced to model the common cause failure(CCF) in system. The reliability of feeding control system is then obtained and the effect of CCF on the reliability of the whole system is studied as well.

Reliability Analysis of Excavator Rectifier Feedback System with Multi-State Components Based on Belief Universal Generating Function Method

In view of the complexity and uncertainty of system, both the state performances and state probabilities of multi-state components can be expressed by interval numbers. The belief function theory is used to characterize the uncertainty caused by various factors. A modified Markov model is proposed to obtain the state probabilities of components at any given moment and subsequently the mass function is used to represent the precise belief degree of state probabilities. Based on the primary studies of universal generating function(UGF)method, a belief UGF(BUGF) method is utilized to analyze the reliability and the uncertainty of excavator rectifier feedback system. This paper provides an available method to evaluate the reliability of multi-state systems(MSSs) with interval state performances and state probabilities, and also avoid the interval expansion problem.