Study to Cost of Air Spares Support Based on IPSO

Air spares support is general term of using and repairing of aircrafts which is the material foundation of aero technical support, its effectiveness influences operational effectiveness and equipments of aircrafts directly. Based on particle swarm optimization algorithm, a new model is proposed to optimize the distribution of the cost of air spares, it take the funds as resource and the improvement of performance efficiency as objective and deduces the expressions to get the best distribution plan. The results of experiments indicate that this model can make full use of the limited funds and obtain the highest efficiency of air spares support.

Location and allocation problem for spare parts depots on integrated logistics support

In equipment integrated logistics support(ILS), the supply capability of spare parts is a significant factor. There are lots of depots in the traditional support system, which makes too many redundant spare parts and causes high cost of support. Meanwhile,the inconsistency among depots makes it difficult to manage spare parts. With the development of information technology and transportation, the supply network has become more efficient. In order to further improve the efficiency of supply-support work and the availability of the equipment system, building a system of one centralized depot with multiple depots becomes an appropriate way.In this case, location selection of the depots including centralized depots and multiple depots becomes a top priority in the support system. This paper will focus on the location selection problem of centralized depots considering ILS factors. Unlike the common location selection problem, depots in ILS require a higher service level. Therefore, it becomes desperately necessary to take the high requirement of the mission into account while determining location of depots. Based on this, we raise an optimal depot location model. First, the expected transportation cost is calculated.Next, factors in ILS such as response time, availability and fill rate are analyzed for evaluating positions of open depots. Then, an optimization model of depot location is developed with the minimum expected cost of transportation as objective and ILS factors as constraints. Finally, a numerical case is studied to prove the validity of the model by using the genetic algorithm. Results show that depot location obtained by this model can guarantee the effectiveness and capability of ILS well.

Prioritizing Maintenance Spare Parts Based on Supportability Analysis and Neural Network

In order to facilitate spare parts management,an integrated approach of BP neural network and supportability analysis(SA)was proposed to evaluate the criticality of spare parts as well as to prioritize spare parts.Influential factors of prioritizing spare parts were detailedly analyzed.Framework of the integrated method was established.The modelling process based on BP neural network was presented.As the input of the neural network,the values of influential factors were determined by supportability analysis data.Based on the presented method,spare parts could be automatically prioritized after supportability analysis for a new system.A case study results showed that the new method was applicable and effective.

MBSE在直升机航材支持场景建模中的应用

介绍了基于Rhapsody的直升机航材支持场景建模与开发的流程与方法;通过模型的方式建立用例图、活动图、顺序图和可用于执行验证的状态机来描述航材支持场景;指导直升机航材支持方案设计过程中的需求分析、功能分析和设计综合;探索MBSE方法在直升机运营保障领域的指导作用,为直升机用户航材支持提供初始建议。

基于小样本数据的风电备品备件需求预测方法研究

全球风电装机容量不断攀升,我国风电产业也出现跨越式发展,风电行业的蓬勃发展给运维管理工作带来巨大挑战。风电运维管理中的备品备件需求预测是决定运维成本的重要因素,尤其是复杂工况下的备品备件预测是风电运维管理面临的亟待解决的问题。本文围绕风电行业运维数据呈现的小样本特征,对风电行业的小样本备品备件需求预测方法开展研究。根据风电行业备品备件运维需求特征,选择小波变换提取备品备件的历史需求数据的趋势与细节特征,选择合适的时间窗将时间序列转化为监督学习形式的时间序列对,提出混合遗传算法和支持向量回归的预测算法GA-dwtSVR,最后开展了验证实验,实验结果表明:相较于传统预测方法,GA-dwtSVR在风电备品备件需求预测中有较好的性能,可以满足风电行业备品备件基于小样本数据的预测需求。

System optimization-oriented spare parts dynamic configuration model for multi-echelon multi-indenture system

In order to optimize the spares configuration project at different stages during the life cycle, the factor of time is considered to relax the assumption of the spares steady demand in multi-echelon technique for recoverable item control (METRIC) theory. According to the method of systems analysis, the dynamic palm theorem is introduced to establish the prediction model of the spares demand rate, and its main influence factors are analyzed, based on which, the spares support effectiveness evaluation index system is studied, and the system optimization-oriented spares dynamic configuration method for multi-echelon multi-indenture system is proposed. Through the analysis of the optimization algorithm, the layered marginal algorithm is designed to improve the model calculation efficiency. In a given example, the multi-stage spares configuration project during its life cycle is gotten, the research result conforms to the actual status, and it can provide a new way for the spares dynamic optimization.

Spare Parts Demand Forecasting:a Review

Spare parts are very common in industry and military fields, and the investigations of spare parts demand forecasting methods have draws much attention in recent years. However,to the best of our knowledge,only few papers reviewed the forecasting papers systematically. This paper is an attempt to provide a novel and comprehensive view to summarize these methods. A new framework was proposed to classify the demand forecasting methods into four categories,including empirical methods,methods based on historical data,analytical methods and simulation methods. Some typical literatures related to each category were reviewed.Moreover, a general spare parts forecasting procedure was summarized and some evaluation criteria were presented. Finally,characteristics of different forecasting methods and some avenues for further research were illustrated. This work provides the managers with a systematical idea about the spare parts demand forecasting and it can be used in practical applications.

Ship spare parts demand forecast based on RBF neural network

Due to the fact that in ship maintena n ce process,the method of determining the number of spare parts is not scientific and the actual operation is complicated,this paper analyzes four major facto rs affecting the number of ship spare parts,including number of main planned op eration s,total times of disassembling in maintenance,accumulated working time and mea n t ime between failures.It also establishes a spare parts demand forecast model b ased on the affecting factors and radial-basis function(RBF) neural network.F inally,the paper provide s forecast examples and makes a comparison between the examples and back propaga tion(BP) neura l network forecast result.The comparison results s how that the forecast based on RBF neural network is simple and the forecast res ult fits the actual situa tion and fitting effect is better than that based on BP.

基于邻域粗糙集优化支持向量机的备件分类研究

针对现有备件分类中存在的备件种类繁多、属性复杂多样及分类标注不统一等问题,文中提出了一种基于邻域粗糙集的支持向量机(NRS-SVM)的多准则备件分类方法。首先,基于历史数据使用邻域粗糙集理论对备件属性进行约简,再将约简后的属性及数据输入支持向量机算法训练分类模型,最后可以将训练好的模型对真实的备件集进行分类。该方法对一家卷烟厂的实际备件数据进行试验验证,结果表明:基于邻域粗糙集的支持向量机在Z企业备件分类中具有高的分类准确率和优秀的泛化能力,验证了所提方法的有效性和优越性,从而更好地支持备件的管理。

武器系统备品备件储备策略研究

针对武器系统备品备件储备策略尚缺乏有效制定方法,备品备件种类和数目与实战化条件下进行演习训练需求有较大差距这一现实问题,论文提出一种基于武器装备可靠性、使用场景,通过泊松分布计算备品备件充足率和利用率,从战斗力保持和经济性两个角度评价备品备件储备策略的方法,可指导新型武器装备备品备件储备策略的制定,也可对现役装备策略的合理性进行检验。

基于机器学习性能度量理论的保障资源指标综合权衡研究

为了解决装备RMS指标论证过程中保障资源指标订立可能存在不合理的问题,以维修过程中常见的现场更换维修为背景,对备件利用率和备件满足率这对典型保障资源指标进行重新解读,借鉴机器学习领域中的性能度量理论,结合典型寿命分布条件下的备件需求量预测模型,提出了不同备件分类条件下的保障资源指标综合权衡方法。利用实际案例对该模型进行应用解析,并给出了参数分析结果。结果表明:基于机器学习性能度量理论的保障资源指标综合权衡方法在指标论证方面具有理论优势和工程可实践性,可提高保障资源指标论证工作的效率。

基于北斗的电子对抗装备备件保障模式研究

随着新电子对抗变革的发展,我军电子对抗装备备件保障工作由传统的“粗放型”向“精准化”转变。为主动适应战时装备备件保障工作,构建“三化融合”视域下的战时电子对抗装备备件保障模式,以北斗定位技术为支持,5G技术为补充,利用北斗系统提供的备件运输工具的相关实时数据,形成强有力的集机械化的装备备件配送系统、智能化的地面仓储中心以及信息化的战时后勤指挥体系于一体的保障模式,提高电子对抗装备备件保障工作的透明性、精准性和及时性,并对我军电子对抗装备备件保障的未来发展方向进行展望。

推进基于性能的备件供应保障改革的几点建议

通过分析基于性能保障的国内外发展现状,借鉴国外基于性能的保障的实施经验,并结合我国目前保障体制现状,提出选择备件供应保障作为推行基于性能的保障的重要实施项目。从军方需求、工业部门需求、通用质量特性提升需求三个方面和物流信息、数字化客户服务系统、工业部门能力三个方面分别阐述了推行基于性能的备件供应保障的迫切需求和可行性。最后,提出了关于推进基于性能的备件供应保障改革的建议。

多约束下编队随船备件配置优化方法

针对舰艇编队备件配置方案的确定需要综合考虑多项约束指标因素的特点,以编队出海执行任务准备阶段备件配置为研究背景,以舰船载荷、排水量及保障费用为约束条件,构建了以编队备件保障概率为目标函数的编队随舰备件库存优化模型,应用拉格朗日乘子法及边际效应法原理给出了编队随船备件库存模型计算及优化流程,并运用罚函数原理对保障资源约束因子进行了确定及动态调整。最后,通过案例分析验证了本文提出的方法能够为解决多约束下编队随船备件配置优化问题提供新的途径。

战时可修复备件供应保障优化模型

把战时备件供应保障看做一个多阶段过程,建立了典型三级备件供应保障结构下的战时备件供应保障规划模型,模型中采用阶段期望缺货数作为备件供应保障系统的性能参数,并给出了其定义及表达式。给出了通过迭代方法获得备件供应保障优化策略时阶段期望缺货数的计算过程,且考虑全部可修及部分可修两种情形。当供应渠道中备件数量服从Poisson分布时,基于动态Palm定理给出了期望缺货数的计算公式。最后给出一个数值计算实例。

基于备件保障率的备件运行量模型

给定运输能力的条件下,较好的备件运行量可以减少维修备件的缺货率,从而提高部队的维修保障能力。基于此,提出了一般情况下备件运行量模型,并给出了相应的启发式求解方法。备件运行量模型的目标函数主要由备件对装备承担任务的影响确定,不同情况下模型可能不一样。对此,建立了两种特殊情况下的备件运行量模型,并给出了相应的快速求解方法。实验结果表明:基于备件保障率的备件运行量模型可以较好地反映了备件运行量,模型求解方法简便易行,计算结果接近实际情况,满足战场环境下实时确定备件运行量的需要。

基于支持向量机的飞机备件需求预测

支持向量机是一种机器学习算法,在国外已广泛应用于工程实践领域。首先探讨了支持向量机回归预测模型的学习和预测机制,分析其中三个重要参数对算法的影响规律,得出一套定性的参数选择方法,然后将支持向量机引入到装备综合保障分析之中,构建了飞机备件智能预测模型,并对某型军用飞机备件需求进行了预测和分析,结果表明:基于支持向量机的备件需求预测是有效的、可行的。

基于非齐次泊松过程的航空备件需求研究和应用

针对航空装备的六种故障率特性,引入非齐次泊松过程,用以解决航空备件需求和预测问题。根据不同故障率曲线给出相应的故障分布模型,最后通过实际故障数据的参数估计和模型检验来确定符合该故障数据的故障率曲线,并计算具有最小维修特点的航空备件的需求量和剩余平均寿命。算例分析表明,结果更为合理,具有较大的应用价值。

备件配置优化问题研究

首先对备件配置优化问题进行了概述,并研究了目前国内外备件配置优化问题现状,归纳了以备件需求量为中心的预测模型以及以缺货为中心的优化模型。把备件配置优化问题看作是一个组合优化问题,然后给出了传统边际效益分析方法解决问题的步骤,接着给出采用仿真优化方法解决问题的思路,即采用优化模块缩减策略空间并采用仿真模块评估策略的优劣。并给出一个应用实例对仿真优化方法进行验证。

战时任务条件下舰艇装备多级备件优化

战时舰艇装备通常为三级备件维修保障体制和四级备件供应保障模式,各级备件库存是影响舰艇编队任务持续能力的重要因素.在分析编队作战任务过程和备件保障流程基础上,对动态帕尓姆定理进行了扩展,使其适用于车间可更换单元(SRU)在修件数概率分布计算.综合考虑战时动态任务、装备的自然故障和战损故障、备件的报废和采购等因素,建立了战时备件维修和供应保障模式下的舰艇编队任务成功性评估模型.以备件保障费用为目标函数,舰艇编队任务成功性为约束条件,建立了基于舰艇编队任务成功性的备件库存优化模型,并运用边际效应方法对该优化模型进行求解.实例运算表明,该模型可以为战时各舰艇装备保障单位制定保障方案提供一定的决策支持.