基于结构熵权 TOPSIS 法的产品设计方案评估研究

为了提高企业在产品设计方案评估阶段进行合理决策的效率,提出了一种基于结 构熵权双基点法(TOPSIS)的产品设计方案评估方法。在评估流程中,首先确定产品设计方案评 价指标,专家对各评价指标进行重要度排序,在得到了“典型排序”后经过结构熵计算和“认识盲 度”计算,得出各评价指标的权重,以替代双基点法中专家主观设定的权重系数;其次,构建设 计方案各指标加权标准决策的矩阵,进而求得各指标的理想解,基于以上可得到各设计方案距 离理想解的相对贴近度,经对比后确定设计方案的排序情况,从而得到各方案的优劣。最后, 将该评估流程应用于录音笔设计方案评估的决策中,验证了该方法的可行性与有效性。     

基于未确知集和模糊TOPSIS决策的故障模式风险评估

为了解决列车控制系统无线闭塞中心设备故障模式与影响分析的风险评估过程中专家评判的认知模糊性和未知不确定性问题,本文提出基于未确知集和模糊TOPSIS决策的故障模式风险评估方法。该方法采用三角模糊数对发生度、严重度、可检测度、维修度4项风险评价指标分别进行模糊化处理,运用未确知数理论来处理各评价指标权重的不确定性以表现其相对重要度;通过使用模糊TOPSIS多准则决策理论对故障模式进行排序最终得到风险评估结果。最后,应用实例对提出的评估方法有效性和可行性进行了验证,结果表明,该方法能有效减少专家主观性对指标权重量化的影响,适用于一些依赖于专家评估经验的故障模式风险评估领域。     

一种供应商选择与评价模型

供应商的选择是决定企业成本及产品质量的重要因素,本文提出一种利用信息不完全的多准则层次分类方法来解决供应商选择评价问题,该方法利用训练集的分类和准则权系数的不完全信息,通过数学模型计算各准则的偏好值以及一致性指标,进而确定候选供应商是否属于所需分类,最后通过一个具体实例验证了该方法的有效性.     

基于改进距离和相似度的区间值概率不确定语言决策方法

针对属性值为区间值概率不确定语言术语集(interval-valued probabilistic uncertain linguistic term set, IVPULTS)、专家权重未知的多属性群决策问题,提出一种融合距离和相似度的决策方法。首先,由于现有的IVPULTS中元素的无序性导致距离测度及决策结果不唯一,利用区间优势度方法对区间值概率进行排序,从而形成有序的IVPULTS;同时考虑到现有距离测度区分能力不高,利用不确定语言距离度量方法扩充现有距离公式。其次,基于距离与相似测度存在的对偶关系,为IVPULTS定义了距离相似度公式,并利用改进的相似—信任网络分析法确定不同专家的权重。再次,设计了基于改进距离和相似—信任网络的TOPSIS决策方法(improved distance and similarity-trust network TOPSIS,IDSTN-TOPSIS),从而得到唯一且稳定的方案排序。最后,以新冠疫情下某医疗用品制造公司熔喷布弹性供应商选择为例,验证了所提方法的有效性和优越性。     

基于云模型的Pythagorean模糊语言多属性决策方法

针对专家给出的属性值为Pythagorean模糊语言且专家权重与属性权重均未知的多属性决策问题进行了研究,提出一种基于云模型的多属性决策方法。首先,根据Pythagorean模糊语言决策信息的距离熵计算得到属性权重;其次,计算决策矩阵间的距离从而得到各决策专家权重;再次,构建Pythagorean模糊云模型决策矩阵并利用专家权重和属性权重进行信息集结;最后,基于TOPSIS方法求取正、负理想解,依据理想解计算各方案贴近度并据此对各备选方案进行排序选择。案例分析表明,该方法优化了复杂环境下的决策,避免了决策信息的丢失,能够较好解决决策信息的不确定性和决策过程的随机性,具有一定的可行性和有效性。     

基于马氏距离的改进型TOPSIS在供应商选择中的应用

由于传统逼近理想解排序法(TOPSIS)的应用中各属性指标之间普遍存在线性相关,导致运用欧氏距离公式计算各评价对象到正负理想解的距离失效.运用马氏距离不受量纲影响以及消除变量间相关性的特性改进传统TOPSIS的距离计算,改进后的TOPSIS具有明显的科学性与合理性.最后,给出了该方法在供应商选择中的应用.     

合作伙伴选择的多准则群决策算法

针对合作伙伴选择问题,提出一种基于群体理想解的TOPSIS求解算法.求出对每个决策者而言各合作伙伴与其群体理想解的相对贴近度.基于备选合作伙伴集的群体理想解和负理想解,计算决策群体对各备选合作伙伴的最终排序.最后以一个供应商选择算例表明该方法的实用性.     

电力无线通信异构多网共存环境中的网络选择算法

综合考虑电力业务需求和无线专网性能因素,针对邻域网、LTE无线专网、WiMAX无线专网和230 MHz无线专网等构成的异构多网混合共存场景,提出一种网络选择算法。该算法以AHPTOPSIS算法为基础,首先构建能表征候选网络与决策属性之间关系的决策矩阵,归一化处理获得归一化决策矩阵;利用AHP算法,依据不同业务类型下决策属性与网络性能之间的相对关系定义权重,对归一化决策矩阵加权获得加权归一化决策矩阵;然后对TOPSIS算法进行改进,依据加权归一化决策矩阵确定正负理想值,利用正理想值与候选网络之间的最小距离以及负理想值与候选网络之间的最大距离确定理想网络,计算各候选网络与理想网络之间的有效距离;据此执行候选网络排序和最佳网络选择,以避免运行TOPSIS算法可能存在的排序异常。仿真结果表明,该算法能根据电力业务需求对候选网络进行正确排序和最优选择,且能在满足业务服务质量的同时,提高资源利用率。     

基于改进TOPSIS的航空发动机维修性评估方法

针对民用航空发动机维修性设计方案优选时缺少对定量指标评估的问题,提出一种基于改进TOPSIS的维修性评估方法;该方法首先根据民用航空发动机的设计准则、相关维修标准和持续适航的约束,构建定性的维修性指标体系和定量的维修性指标体系;以层次分析法和熵权法相结合的方式确定各指标的权重系数;通过建立虚拟仿真维护环境计算出各定量指标,在此基础上,运用改进TOPSIS法对航空发动机不同维修性设计方案的维修性进行综合评估;实验验证提出的方法能够得出最佳的维修性设计方案,可为民用航空发动机的维修性评估提供参考。     

考虑决策者心理行为的软件质量评价方法

针对软件质量评价方法中缺乏考虑决策者心理行为的问题,提出一种基于区间二元语义的交互式多准则决策（TODIM）软件质量评价方法。首先,通过区间二元语义表征专家对软件质量的评价信息;其次,利用主观赋权法和逼近理想解排序法（TOPSIS）分别计算软件质量属性的主客观权重,并在此基础上通过组合赋权法获取软件质量属性的综合权重;然后,为更好地刻画专家在软件质量评价过程中的心理行为,将TODIM引入软件质量评价中。利用TODIM方法对高速铁路调度系统的助理调度员终端进行软件质量评价,结果表明铁路软件供应商提供的第3款助理调度员终端软件的占优度值最高,质量最优。将该方法与后悔理论方法以及II类偏好序结构排序法（PROMETHEE-II）进行对比分析,所得结果表明三种方法在质量最优软件的选取上具有一致性,然而三者的总体排序有所差异,说明所构建方法在描述多准则的交互关系和决策者的心理行为上具有较强的优越性。     

基于直觉梯形模糊TOPSIS的多属性群决策方法

提出一种改进的逼近理想解排序(TOPSIS)方法,即直觉梯形模糊TOPSIS多属性群决策方法。首先,应用直觉梯形模糊数形式表示方案属性偏好和属性权重信息且专家权重完全未知;然后,利用直觉梯形模糊数间距离测度和期望值及直觉梯形模糊加权平均算子来确定决策者权重信息和属性权重信息;进而给出直觉梯形模糊环境下方案优选的算法;最后,通过算例进一步说明了该直觉梯形模糊TOPSIS方法的有效性。     

An analytical solution to fuzzy TOPSIS and its application in personnel selection for knowledge-intensive enterprise

Personnel selection is a critical enterprise strategic problem in knowledge-intensive enterprise. Fuzzy number which can be described as triangular (trapezoid) fuzzy number is an adequate way to assess the evaluation and weights for the alternatives. In that case, fuzzy TOPSIS, as a classic fuzzy multiple criteria decision making (MCDM) methods, has been applied in personnel selection problems. Currently, all the researches on this topic either apply crisp relative closeness but causing information loss, or employ fuzzy relative closeness estimate but with complicated computation to rank the alternatives. In this paper, based on Karnik–Mendel (KM) algorithm, we propose an analytical solution to fuzzy TOPSIS method. Some properties are discussed, and the computation procedure for the proposed analytical solution is given as well. Compared with the existing TOPSIS method for personnel selection problem, it obtains accurate fuzzy relative closeness instead of the crisp point or approximate fuzzy relative closeness estimate. It can both avoid information loss and keep computational efficiency in some extent. Moreover, the global picture of fuzzy relative closeness provides a way to further discuss the inner properties of fuzzy TOPSIS method. Detailed comparisons with approximate fuzzy relative closeness method are provided in personnel selection application.     

Robot selection by using generalized interval-valued fuzzy numbers with TOPSIS

The aim of this paper is to propose a method to aggregate the opinion of several decision makers on different criteria, regarding a set of alternatives, where the judgment of the decision makers are represented by generalized interval-valued trapezoidal fuzzy numbers. A generalized interval valued trapezoidal fuzzy number based technique for order preference by similarity to ideal solution is proposed that can reflect subjective judgment and objective information in real life. The weights of criteria and performance rating values of criteria are linguistic variables expressed as generalized interval-valued trapezoidal fuzzy numbers. Finally, an illustrative example is provided to elaborate the proposed method for the selection of a suitable robot according to our requirements.     

PERFORMANCE EVALUATION OF SUGAR PLANTS BY FUZZY TECHNIQUE FOR ORDER PERFORMANCE BY SIMILARITY TO IDEAL SOLUTION (TOPSIS)

This study presents the performance evaluation of sugar plants using the technique for order performance by similarity to ideal solution (TOPSIS) under a fuzzy environment. First, the decision criteria used to evaluate the performances are determined, and then the data from financial statements are collected from sugar plants. Accordingly, the ratings of various alternatives under various criteria and the importance weights of various criteria are assessed by evaluators using linguistic terms. The data obtained are converted into a fuzzy triangular number system and then the fuzzy TOPSIS method is applied to make a final decision. According to the closeness coefficients, the sugar plants are ranked from strong to weak. A real case study involving eight evaluation criteria and nine sugar plants assessed by nine evaluators is provided to illustrate the proposed method. The results show that this method is an effective tool for evaluating investment risks based on the heuristic knowledge acquired from experts.     

Multi-criteria group decision making based on trapezoidal intuitionistic fuzzy information

With respect to multi-criteria group decision making (MCGDM) problems under trapezoidal intuitionistic fuzzy environment, a new MCGDM method is investigated. The proposed method can effectively avoid the failure caused by the use of inconsistent decision information and provides a decision-making idea for the case of “the truth be held in minority”. It consists of three interrelated modules: weight determining mechanism, group consistency analysis, and ranking and selection procedure. For the first module, distance measures, expected values and arithmetic averaging operator for trapezoidal intuitionistic fuzzy numbers are used to determine the weight values of criteria and decision makers. For the second module, a consistency analysis and correction procedure based on trapezoidal intuitionistic fuzzy weighted averaging operator and OWA operator is developed to reduce the influence of conflicting opinions prior to the ranking process. For the third module, a trapezoidal intuitionistic fuzzy TOPSIS is used for ranking and selection. Then a procedure for the proposed MCGDM method is developed. Finally, a numerical example further illustrates the practicality and efficiency of the proposed method.     

An integrated fuzzy multi-criteria approach for the performance evaluation of multiple manufacturing plants

The performance evaluation is regarded as a multiple criteria decision making (MCDM) problem and has a significant impact on the operations of the enterprise. This paper develops an integrated MCDM approach that combines the voting method and the fuzzy TOPSIS (technique for order preference by similarity to ideal solution) method to evaluate the performance of multiple manufacturing plants in a fuzzy environment. Fuzzy TOPSIS helps decision-makers carry out analysis and comparisons in ranking their preference of the alternatives with vague or imprecise data. Since the evaluation result is often greatly affected by the weights used in the evaluation process, the voting method is used in this study to determine the appropriate criteria weights. A case study demonstrating the applicability of the proposed model is presented. The case company is the world’s largest manufacturer of power supplies. It has three primary manufacturing bases located in Wujiang, Dongguan, and Tianjin, China. The proposed approach is used to evaluate the performance of the company’s five manufacturing plants in Wujiang, which produce switch power, telecom power, DC/DC converters, uninterruptible power systems (UPS) and AC/DC adapters.     

基于直觉梯形模糊数的信息不完全确定的多准则决策方法

针对权系数信息不完全确定和准则值为直觉梯形模糊数的多准则决策问题,提出一种基于直觉梯形模糊的信息不完全确定的多准则决策方法.该方法利用权系数的不完全确定信息,建立关于各方案综合直觉梯形模糊数与理想解和负理想解的Hamming距离的优化模型.通过求解优化模型可得到各准则的最优权系数,进而得到各方案与相对理想解的贴近度,再根据贴近度得到方案集的一个排序.实例分析表明了该方法的有效性和可行性.     

基于模糊结构元的模糊数直觉模糊多准则决策方法

针对准则权重信息不完全确定的模糊数直觉模糊多准则决策问题,采用模糊结构元方法进行处理.基于模糊数直觉模糊集的模糊结构元表示、模糊数比较和排序的模糊结构元方法以及直觉模糊数的记分函数和距离测度,定义了模糊数直觉模糊数的记分函数和距离测度,进而提出两种准则权重信息不完全确定而准则值为模糊数直觉模糊数的多准则决策方法:记分函数法和逼近理想解排序(TOPSIS)法.实例分析表明了这两种方法的可行性和有效性.     

Personnel selection based on intuitionistic fuzzy sets

One of the most important activities carried out by human resource management is personnel selection, concerned with identifying an individual from a pool of candidates suitable for a vacant position. Traditionally, personnel selection is a group decision‐making problem under multiple criteria containing subjectivity, imprecision, and vagueness, which are best represented with fuzzy data. In this article, the Technique for Order Preference by Similarity to Ideal Solution (TOPSIS) method extended to intuitionistic fuzzy environments is proposed to select appropriate personnel among candidates. An intuitionistic fuzzy set (IFS), which is characterized by membership function, nonmembership function, and hesitation margin, is a more suitable way to deal with vagueness when compared to a fuzzy set. To demonstrate the applicability and effectiveness of the intuitionistic fuzzy TOPSIS method, a numerical example of personnel selection in a manufacturing company for a sales manager position is given. © 2011 Wiley Periodicals, Inc.     

Prioritized aggregation operators of trapezoidal intuitionistic fuzzy sets and their application to multicriteria decision-making

A trapezoidal intuitionistic fuzzy set, some operational laws, score and accuracy functions for trapezoidal intuitionistic fuzzy values are presented in this paper. Then, the trapezoidal intuitionistic fuzzy prioritized weighted averaging (TIFPWA) operator and trapezoidal intuitionistic fuzzy prioritized weighted geometric (TIFPWG) operator are proposed to aggregate the trapezoidal intuitionistic fuzzy information. Furthermore, a multicriteria decision-making method based on the TIFPWA and TIFPWG operators and the score and accuracy functions of trapezoidal intuitionistic fuzzy values is established to deal with the multicriteria decision-making problem in which the criteria are in different priority level. Finally, a practical example about software selection for considering various prioritized relationships between the criteria of decision-making is given to demonstrate its practicality and effectiveness.