存在融资的模糊决策投资组合模型的研究及应用

利用应用效果较好的均值-半偏差投资组合模型对存在融资情况的投资组合进行分析研究。将存在融资情况的均值-半偏差模型的收益和风险目标进行模糊化,并构造了使用较多且效果佳的线性隶属度函数μmax(x)和μmin(x)。运用模糊决策理论引进变量μ将模糊环境下存在融资的双目标模型转化为线性的基于模糊决策存在融资的投资组合模型。本模型不仅简化了模型的计算量,同时也将投资者的主观投资意愿表示清楚。最后通过实例说明了模型的实用性和有效性。     

一类变量为梯形模糊数的线性规划

针对变量为梯形模糊数的模糊线性规划问题,利用结构元方法定义了一种模糊数的排序准则,讨论了如何将变量是梯形模糊数的线性规划去模糊化,即将含有变量为梯形模糊数的模糊线性规划转化为经典模糊线性规划.同时,证明了该模型的最优解等价于经典的线性规划的最优解,再利用单纯形法求出最优解.并设计了求解该类模型的算法.通过算例验证了该方法的可行性和算法的有效性,从而为变量模糊的广义模糊线性规划问题的研究提供了新的方法.     

基于模糊贝叶斯网络的态势威胁评估模型

针对传感器测量数据的不确定性,提出基于模糊贝叶斯网络的态势威胁评估模型,该模型首先将不确定性数据分为模糊域和概率域两大类,然后在模糊域使用模糊综合评判得到威胁目标的动态威胁度,接着运用可能性概率转换理论将模糊表示的动态威胁度转化成概率域知识,最后在概率知识域使用贝叶斯网络推理算法得到目标的威胁等级.实例计算表明,该方法能够较好的反映威胁源的威胁等级,为武器系统选择跟踪打击目标提供决策依据,具有一定的实用性.     

网络分析法在军工研究所R&D人力资本投资风险评估中的应用

在对军工研究所RD人力资本投资风险因素进行识别的基础上,建立风险评价指标体系,发现指标之间存在相互影响与反馈的关系,提出基于网络分析法并同时考虑评估意见模糊性的军工研究所RD人力资本投资风险模糊评估模型,给出相关算法。最后,通过实例说明该方法的分析结果更合理、直观,而且还能为决策者提供更为详细的决策信息。     

模糊逻辑系统在船舶风险评估中的应用

为了合理进行船舶风险评估，提出了一种基于模糊逻辑系统的船舶风险评估方法．根据模糊逻辑系统的基本原理，建立了船舶风险评估的模糊逻辑模型；按照国家标准、规范，并结合经验建立了风险指标的模糊集合、风险矩阵厦模糊规则，然后进行了模糊推理，得到了系统的风险等级，并制定了预防风险的措施．以某艇消防系统的风险评估为例，证明了其能够合理地评估出系统的风险，可为决策提供参考，     

模糊群决策方法在物流服务商选择中的应用

针对物流服务商选择中评价指标的不确定性和模糊性,提出用三角形模糊数来描述评价指标;构造了基于三角形模糊数和群决策理论的基本算法;并利用模糊数排序公式对决策方案进行排序和择优.最后进行了实例分析.数值结果表明该方法可行且有效.     

基于模糊综合评判的多指标匹配算法性能评估

评估图像匹配算法的优劣很难用"好"或"不好"来界定,评估结果往往存在一定的模糊性,因此,可以利用模糊理论中的综合评判方法对图像匹配算法的性能进行评估,指明评估结果隶属于某个评语的程度,得出更加科学的评估结论.本文结合多种图像匹配算法性能评估指标重点说明了模糊综合评判模型的建立过程及权重的确定方法,经过评估实验,对灰度相关匹配算法和相位相关匹配算法两类算法进行性能评估,得出了比单一指标评估体系更好的评估结果,验证了评估模型的实用性和有效性.     

基于隶属度的供应链风险评估模型研究

本文指出供应链风险主要来源于供应链内外部的不确定性,并回顾了相关文献,将其分为3个风险类型,依此构建评估模型。通过不同风险评分对应不同风险状态的隶属度,运用模糊运算,得出风险水平值,为企业供应链风险评估提供一种新的思考。     

模糊分布参数的全局灵敏度分析新方法

为合理度量随机输入变量分布参数的模糊性对输出性能统计特征的影响,提出了模糊分布参数的全局灵敏度效应指标,并研究了指标的高效求解方法。首先,分析了不确定性从模糊分布参数至模型输出响应统计特征的传递机理,以输出性能期望响应为例,利用输出均值的无条件隶属函数与给定模糊分布参数取值条件下的隶属函数的平均差异来度量模糊分布参数的影响,建立了模糊分布参数的全局灵敏度效应指标。其次,为减少所提指标的计算成本、提高计算效率,采用了扩展蒙特卡罗模拟法(EMCS)来估算输入变量分布参数与模型输出响应统计特征的函数关系。最后通过对算例的计算,验证该文所提方法的准确性和高效性。     

基于模糊神经网络的设备故障预测研究

对模糊神经网络技术进行了研究，提出了预测分析的模糊神经网络模型；建立了故障指标评定方法，利用预测算法运用参数历史故障指标对参数指标进行趋势预测，预测得到的参数指标可以根据专家诊断系统判据进行诊断，对未来设备的健康状况进行可信度较高的评估。经仿真结果验证，该算法预测精度较高，预测结果可信.     

Feasibility study of the tactical design justification for reconfigurable manufacturing systems using the fuzzy analytical hierarchical process

Reconfigurable manufacturing systems (RMSs) are designed based on the current and future requirements of the market and the manufacturing system (MS). The first stage of designing an RMS at the tactical level is the evaluation of economic and manufacturing/operational feasibility. Because of risk and uncertainty in an RMS environment, this major task must be performed precisely before investment in the detailed design. The present paper highlights the importance of manufacturing capacity and functionality for the feasibility of an RMS design during reconfiguration processes. Due to uncertain demands of product families, the RMS key-design factors, i.e. capacity value, functionality degree and reconfiguration time, are characterized by the identified fuzzy sets. Consequently, an integrated structure of the analytical hierarchical process and fuzzy set theory is presented. The proposed model provides additional insights into a feasibility study of an RMS design by considering both technical and economical aspects. The fuzzy analytical hierarchical process model is examined in an industrial case study by means of Expert Choice software. Finally, the fuzzy multicriteria model is sensitively analysed within the fuzzy domains of those attributes, which are considered to be critical for the case study.     

Provident decision making by considering dynamic and fuzzy environment for FMS evaluation

When evaluating complexity, cost and risk increase, it is difficult to make a proper decision. In such situations it is necessary to develop a model which simulates a decision maker's mind and consider both a dynamic and a fuzzy environment. In this study future oriented indices are presented which enable us to consider the effect of future changes in the index value during the decision making process. These future oriented indices are named provident indices. Also in this study to effectively integrate these multiple criteria into the decision making process, based on the analysis of the decision situation in such assessments, a suitable concept is selected. This method is based on the preference ranking organisation method for enrichment evaluations (PROMETHEE) which brings together flexibility and simplicity for the user and is therefore chosen for the enhancement towards the evaluation of fuzzy data on preferences, scores and weights. The model developed to investigate these impacts cannot perfectly reproduce all the events of the real system, but it can consider a fair number of elements of variability, which should be identified and analysed by considering present conditions and prediction about criteria values in future periods. Such a model may provide solutions with a high degree of robustness and reliability, comparable with those obtained by direct experimentation, but with a low computational cost. The uniqueness of this paper lies in two important areas: first, the incorporation of variability fuzzy and provident measures in the performance of alternatives into the decision making process; and second, is in the application of fuzzy PROMETHEE that provides the decision maker with effective alternative choices by identifying significant differences among alternatives and appropriate choices through considered future periods, and presents graphic aids for better interpretation of results. A comprehensive numerical example of a flexible manufacturing system (FMS) is provided to illustrate the results of the analysis. In a real-world manufacturing environment, the dynamics of an FMS and its stochastic characteristics require a specific approach for evaluation. This paper specifically focuses on FMSs due to the complexities involved in their proper evaluation that include factors such as high operational and managerial expertise in system implementation phases, high costs and risks. Due to these, evaluation, justification, and implementation of an FMS have been areas of major concern and importance for practitioners and researchers. In this case, various strategic, economic and operational criteria that envelop quantitative, qualitative, tangible, and intangible factors are considered.     

Distance-based fuzzy MCDM approach for evaluating flexible manufacturing system alternatives

Considering the high required capital outlay and moderate risk of a flexible manufacturing system (FMS) investment, economic justification techniques are insufficient by themselves since they cannot cope with the benefits such as flexibility and enhanced quality offered by advanced manufacturing technologies. A robust decision-making procedure for evaluating FMS requires the consideration of both economic and strategic investment measures. A distance-based fuzzy multicriteria decision-making (MCDM) framework based on the concepts of ideal and anti-ideal solutions is presented for the selection of an FMS from a set of mutually exclusive alternatives. The proposed method provides the means for integrating the economic figure of merit with the strategic performance variables. The multicriteria decision approach presented here enables us to incorporate data in the forms of linguistic variables, triangular fuzzy numbers and crisp numbers into the evaluation process of FMS alternatives. Linguistic variables are also used to indicate the criteria's importance weights assigned by the decisionmakers. A comprehensive example illustrates the application of the multicriteria decision analysis.     

Fuzzy quality feature monitoring model

In this paper we study the modern techniques and also present a fuzzy quality monitoring model that can be used at various stages in a production operation (the raw material input stage, between production stages). The product quality may be of several types (i.e. sensory, physical, time orientation) that sometimes may not be sensed, measured, or calculated precisely due to uncertain situations. Therefore, the γ -level fuzzy Bayesian model for quality monitoring of a manufacturing process is proposed. In order to apply the Bayesian concept, the fuzzy quality characteristics are assumed as fuzzy random variables. Using the fuzzy quality characteristics, the newly developed model calculates the risk of operation for the manufacturing process, which results in determining the out-of-control process. A numerical example is also presented to demonstrate the application of the model.     

Fuzzy-based analysis of process capability for assembly quality assessment in mechanical assemblies

Process capability indices are useful tools for evaluating the ability of a process to produce products that meet certain specifications. The assembly quality is dependent on the distribution of variations of assembly dimensions, which is in turn dependent on mating conditions in the mechanical assembly. Since it is often difficult to measure the assembly dimensions in the production stages, they are not considered as a direct inspection objective. Rather, the inspection and evaluation of quality is carried out by specifying whether the assembly requirements satisfy the specified limits. Therefore, we can basethe process capability indices on the assembly dimensions. In most real life cases, the observations are fuzzy. In this paper, a novel method based on fuzzy concepts for process capability analysis of assembly dimensions in mechanical assemblies is presented. According to this scheme, sample observations of manufactured variables are described as fuzzy numbers. The proposed method is able to estimate the ability of the manufacturing process in satisfying the assembly quality in the mechanical assemblies with asymmetric tolerances which have non-normal distributions. In this paper, a proper criterion based on the probability of fuzzy set to interpret the computed fuzzy results is proposed, so these results are converted to the interpretable results for making a decision to evaluate the assembly quality. Furthermore, a new fuzzy-based quantity factor for expressing the percent contributions of effective manufacturing variables on the assembly quality is presented. The application of the presented method is demonstrated through an example and its results are discussed.     

Maintenance policy selection in manufacturing firms using the fuzzy MCDM approach

In manufacturing firms, there is a critical need for proper maintenance of manufacturing facilities. The maintenance process enhances customer satisfaction and reliability of the products, and increases the profit of the manufacturer. Therefore, a proper maintenance policy selection is a critical issue for manufacturers, as an inefficient maintenance policy affects not only the direct cost of the firm but also the other aspects. In the present study, maintenance policy selection at the level of the firm rather than the equipment level is shown, and for selection various criteria have been identified. The presented work not only provides the best alternatives but also provides an alternative ranking, which facilitates decision-makers in choosing alternatives according to their constraints. These selection criteria are different in nature, as some give a crisp value, whereas others are defined in linguistic terms. To select the appropriate maintenance policy, a distance-based fuzzy multicriteria decision-making (MCDM) approach has been employed. The proposed method provides the means for integrating the economic figure of merit with the strategic performance variables. The MCDM approach is efficient in incorporating data, in the form of linguistic variables, triangular fuzzy numbers, and crisp numbers, into the evaluation process of maintenance policy alternatives. A comprehensive example illustrates the application of the distance-based fuzzy MCDM approach.     

Measuring the manufacturing process yield based on fuzzy data

The process yield is the most basic and common criterion used in the manufacturing industry as the basis for measuring process performance. In the conventional case, the underlying data for a manufacturing process are obtained from the output responses of continuous quantities that are always assumed to be real numbers. However, measurement of the output process occasionally appears to be imprecise in practical situations. Accordingly, the output responses should be assumed to be so-called fuzzy data. We propose a constructive methodology to obtain the fuzzy estimate of the yield index S _pk with the help of the extension principle of fuzzy sets theory. This study, based on an analytical approach, is an advancement over existing technology in the area of process capability analysis that is easy to implement in plant applications.     

基于模糊层次分析的空间谱估计性能评价方法

在已经形成的多种空间谱估计方法中,为根据需求选择最优算法,建立了一种基于模糊层次分析的空间谱估计性能评价方法。从空间谱估计方法的处理性能和可实现性角度建立一种具有层次结构模型的性能评价准则,对各项性能评价指标做属性值规范化和权重系数模糊化处理,得到各评价指标的评价得分,累加得到处理算法性能量化评价的综合判决结果。基于仿真试验和某次海试试验结果,对常规波束形成(Conventional Beam Forming,CBF)、最小方差无畸变响应(Minimum Variance Distortion Response,MVDR)、多信号分类(Multiple SIgnal Classification,MUSIC)三种空间谱估计方法进行评价,在较高输入信噪比和弱化计算量条件下,MUSIC为评价最优算法。试验结果表明,此评价方法可以按需求实现最优空间谱估计方法的选择。     

A manufacturing resource allocation method with knowledge-based fuzzy comprehensive evaluation for aircraft structural parts

Manufacturing of aircraft structural parts has the characteristics of multiple varieties, complex structures and small batches, which make the manufacturing resource allocation highly difficult. This paper proposes a manufacturing resource allocation method with knowledge-based fuzzy comprehensive evaluation, considering multiple manufacturing resources including process planners, machine tools and cutting tools, as well as manufacturing process schemes of aircraft structural parts. Knowledge in terms of experts’ experience and historical data is used for fuzzy comprehensive evaluation. A manufacturing resource allocation model is proposed based on the analysis of manufacturing processes of aircraft structural parts. The capability of planners, the complexity of structural parts, the reliability of machine tools, the reliability of cutting tools and the correlations between manufacturing resources and structural parts are evaluated using the fuzzy comprehensive evaluation method. Multiple manufacturing resources are allocated based on the fuzzy comprehensive evaluation results. A prototype system has been implemented and a case study is used to validate the proposed approach.     

项目区域风险的模糊综合评价方法研究

针对项目区域风险诸多非精确量且属性复杂的评价条件，建立了系统、完整的项目区域风险评价指标体系。基于多层模糊推理，结合层次分析法提出了一种多属性、多层次、综合考虑项目区域风险因素的三级模糊综合评价方法。这种方法按风险来源作为风险因素对项目区域风险进行分类，每大类再按其属性分层次评价，并依次将评价结果进行合成后得出最终的综合评价排序。最后通过一个简单算例说明了该方法的具体步骤及其有效性。