区间型多属性群体专家权重的确定方法

针对方案偏好和属性值均为区间数的多属性群决策问题，研究了群体专家权重的确定，并提出了一种新的群决策方法．通过定义区间数向量的内积，计算专家评判的相似度和差异度，进而客观地确定了专家的权重．求解最小化主、客观偏差的目标规划模型，得到了属性的权重，利用方案的群体综合属性值给出排序结果．供应商选择的应用实例验证了方法的可行性和合理性．     

考虑决策者风险偏好的区间直觉模糊多属性群决策方法

提出了一种考虑决策者风险偏好且属性权重信息不完全的区间直觉模糊数多属性群决策方法。同时考虑相似度和接近度,确定每一属性的决策者权重。为了考虑决策者风险偏好对决策结果的影响和避免区间直觉模糊矩阵的渐进性,引入了决策者风险偏好系数,将集结后的综合决策矩阵转换成区间数矩阵。然后,为了客观地求出属性权重信息不完全环境下属性的权重,构建了基于区间直觉模糊交叉熵的属性权重目标规划模型,该模型不仅考虑了评价值的偏差,也强调了评价值自身的可信度。最后,通过研发项目选择问题的实例分析说明了所提方法的合理性和优越性。     

风险型多属性群决策的综合集成方法

对一类权重信息未知,并且属性值为区间灰数的风险型多属性群决策问题进行了探讨,提出了在理想状态下(即决策者群体的理想意见趋于一致时)各属性的客观权重的计算方法.构建了以组内偏差最小、组间偏差最大为目标函数的综合集成优化模型,求解出理想状态下各属性的客观权重.然后综合考虑各决策者的主观偏好,借助每一方案与理想最优方案组、理想最劣方案组综合偏离度的大小对方案的优劣进行排序.应用实例说明了该方法的可行性和有效性.     

综合主、客观权重信息的最优组合赋权方法

首先构造了一种多属性决策主观权重确定的偏好比率法,介绍了属性客观权重确定的熵值法,提出了一种基于离差平方和的最优组合赋权方法,并给出了具体算例.通过提出的方法可以将多属性决策问题中主、客观权重的信息进行有效地综合.     

基于相对熵的不完全信息群体专家权重的集结

针对属性权重信息和属性效用信息都不完全的群体多属性决策问题,运用相对熵理论提出了一种专家权重的确定方法．该方法通过集结各方案的综合评价值向量,客观地得到专家的权重,避免系统聚类方法中由给定相似度水平归类而产生的主观性问题．应用实例表明了方法的有效性和实用性．     

基于Vague集的多属性群决策专家权重的确定

针对方案属性值为Vague值的多属性群决策问题,提出了一种新的专家权重的确定方法.定义了Vague值的得分函数、贴近度、运算法则以及信息集成算子.根据专家评判的相似度矩阵,通过其最大模特征值所对应的特征向量客观地确定了专家的权重,进而提出了新的群决策方法.制造资源应用实例验证了方法的可行性和合理性.     

考虑决策者行为的概率不确定语言决策方法

针对属性权重未知的不确定语言多属性群决策问题,提出一种考虑决策者行为的概率不确定语言决策方法.首先,定义概率不确定语言的海明距离,根据与负理想方案的距离偏差最大建立模型,从而确定属性权重.其次,改进经典TODIM方法适用于概率不确定语言决策环境中,得到了方案排序.最后,通过实例验证了所给方法的可行性,并对比传统的TOPSIS方法进行敏感度分析,进一步验证所提方法的有效性.     

构建不确定语言型多属性决策的投影模型

研究不确定语言型多属性决策评价结果与决策者对方案的偏好信息之间存在偏差的问题.通过建立与区间型语言标度对应的术语指标矩阵,及方案综合属性值与决策者主观偏好值之间的投影模型,确定属性的权重,然后运用加权法得到方案的综合属性值,利用已有的可能度矩阵排序公式得到决策方案的排序.构建了一种基于方案综合属性质与决策者主观偏好值之间的投影模型,通过算例对该方法的实用性和有效性进行了证明.     

基于方案贴近度和满意度的交互式不确定多属性决策方法

针对属性权重信息部分确知且对方案有偏好的不确定多属性决策问题,提出一种基于方案贴近度和满意度的交互式决策方法.方法首先利用已知的客观信息和决策者的主观要求建立单目标规划模型,其次通过对方案满意度和综合度的给定与修正来实现人机交互决策.最后,通过实例说明模型及方法的可行性和有效性.     

一种基于Yager熵最大化属性权重组合方法

研究了区间型多属性决策中属性权重组合问题。首先,提出了一种客观权重确定方法——平均差极大化方法;其次,基于区间型理想点和熵极大化原理,提出属性权重的组合模型。然后,利用属性的组合权重和投影模型,对方案进行排序。最后,通过算例说明了该方法的可行性和有效性。     

不确定决策环境下绿色供应商选择方法研究

针对不确定环境下绿色供应商选择问题,提出了一种属性权重信息完全未知且属性值以区间数形式给出的多属性决策方法。基于区间数相离度概念,定义了区间数的平均差,建立属性权重计算方法——带参数的平均差极大化方法。此方法具有一定的柔性,可以通过参数来调节属性之间的差别程度。最后把该方法应用于绿色供应商选择,说明了该方法的实用性和有效性。     

离差最大化时基于交叉评价的多属性决策方法

针对属性权重完全未知,且评价系统内既有客观数据、又有主观因素的多属性决策问题,提出一种基于离差最大化和交叉评价的模糊多属性决策方法。该方法首先定义了最小交叉效率、最大交叉效率等概念,将量化指标用交叉评价方法进行处理;然后采用模糊综合评价方法评价非量化指标,并基于离差最大化思想确定权重;最后将模糊化处理之后的量化指标与非量化指标一起进行最终评价,建立离差最大化条件下基于交叉评价的模糊多属性决策模型。最后通过算例验证了方法的可行性及有效性。     

基于前景理论和三角模糊MULTIMOORA的多阶段决策方法

针对时间权重与属性权重完全未知的三角模糊多属性决策问题,基于前景理论和MULTIMOORA提出一种新的决策方法。首先,建立备选方案在不同时段的三角模糊前景决策矩阵,根据时间度及不同时段内备选方案前景值的差异构建时间权重优化模型,并运用最大偏差法的基本思想获得属性权重。其次,基于三角模糊数提出一种新的MULTIMOORA扩展形式,并结合占优理论对备选方案进行比选。最后,通过实例证明了所提方法是可行的,也是有效的。     

Hybrid Multi-attribute Decision Making Method of Electric Coal Procurement in Industry

Electric coal procurement is the basis of electric power production. In this paper, the problem of supplier selection is studied in multi-source procurement of electric coal. Concretely, the index system of supplier selection is presented, including the evaluation attributes of price, quantity, quality, delivery time and the reputation of supplier. Then, the problem of supplier selection is converted into a problem of hybrid multi-attribute decision making, and a projection method based on hybrid technique for order preference by similarity to ideal solution (TOPSIS) is presented to rank all suppliers and select winners. Its decision example is also given to implement the presented decision method and to demonstrate its effectiveness and practicality. This paper gives an effective way to the hybrid multi-attribute decision making for multi-source procurement of electric coal under fuzzy uncertain environment.     

基于三参数区间数群决策的第三方物流服务商选择方法研究

对第三方物流服务质量评价与选择属于多属性的群决策问题.为解决传统物流服务商的选择和评价中专家主观性问题,提出了基于三参数区间数群决策的第三方物流服务商选择方法.分析了三参数区间数的概念,对三参数区间数运用偏差函数确定决策专家的权重,根据三参数区间数偏好序概率矩阵和权重,求解第三方物流服务商的排序问题.最后通过实例验证了三参数区间数群决策算法的有效性和可行性.     

Multi-attribute group decision-making with multi-granularity linguistic assessment information: An improved approach based on deviation and TOPSIS

With respect to group decision-making problems with multi-granularity linguistic assessment information, a new approach is proposed. Firstly, the computational formulae are given in order to transform and unify the multi-granularity linguistic comparison matrices. Secondly, the method of standard and mean deviation is applied to determine the unknown attribute weights, and the weights of the decision makers will be determined by using the extended TOPSIS (technique for order preference by similarity to an ideal solution) method. Finally, based on the LWAA (linguistic weighted arithmetic averaging) operator, information on the preference provided by each decision maker is aggregated into the comprehensive evaluation value of each alternative, and the most desirable alternative is selected. The proposed approach expands the research in multi-attribute group decision-making with multi-granularity linguistic assessment information by both considering the weights of the attributes and decision makers, and objective weighting for them. A numerical example is given to illustrate the practicability and usefulness of the proposed approach.     

Some interval-valued intuitionistic uncertain linguistic Choquet operators and their application to multi-attribute group decision making

In this study a generated admissible order between interval-valued intuitionistic uncertain linguistic numbers using two continuous functions is introduced. Then, two interval-valued intuitionistic uncertain linguistic operators called the interval-valued intuitionistic uncertain linguistic Choquet averaging (IVIULCA) operator and the interval-valued intuitionistic uncertain linguistic Choquet geometric mean (IVIULCGM) operator are defined, which consider the interactive characteristics among elements in a set. In order to overall reflect the correlations between them, we further define the generalized Shapley interval-valued intuitionistic uncertain linguistic Choquet averaging (GS-IVIULCA) operator and the generalized Shapley interval-valued intuitionistic uncertain linguistic Choquet geometric mean (GS-IVIULCGM) operator. Moreover, if the information about the weights of experts and attributes is incompletely known, the models for the optimal fuzzy measures on expert set and attribute set are established, respectively. Finally, a method to multi-attribute group decision making under interval-valued intuitionistic uncertain linguistic environment is developed, and an example is provided to show the specific application of the developed procedure.     

Multi-attribute decision making with generalized fuzzy numbers

This paper proposes a multi-attribute decision-making method with generalized fuzzy numbers (GFNs). In the proposed method, the distance between GFNs is calculated using the Hausdorff distance. Based on the maximizing deviation degree, the attribute weights are determined by a linear programming model. Furthermore, a ranking formula with a modified possibility degree is adopted to rank alternatives. A numerical example is introduced to validate the proposed model, and the results indicate that the proposed model offers a practical and effective way to meet the different assessment requirements of decision makers.