CN104809546A - Novel multi-objective intelligent weighted grey target decision method - Google Patents
Novel multi-objective intelligent weighted grey target decision method Download PDFInfo
- Publication number
- CN104809546A CN104809546A CN201510118856.3A CN201510118856A CN104809546A CN 104809546 A CN104809546 A CN 104809546A CN 201510118856 A CN201510118856 A CN 201510118856A CN 104809546 A CN104809546 A CN 104809546A
- Authority
- CN
- China
- Prior art keywords
- objective
- decision
- effect
- measure
- target
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a novel multi-objective intelligent weighted grey target decision method. The intelligent weighted grey target decision method aims at a benefit type objective, a cost type objective and a moderate type objective, and benefit type objective effect measure, cost type objective effect measure and moderate type objective lower limit effect measure and moderate type objective upper limit effect measure are correspondingly designed so that degree of objective realization or deviation can be expressed. Consistent effect measure has great properties that normalization is met without dimension, and the measure value is greater when the effect is more ideal. The grey target critical value is further designed into the positive and negative demarcation point of a consistent effect measure function, and two different situations of target hitting and targeting missing in the objective effect values can be fully considered so that the physical meaning is clear, and the resolution of comprehensive effect measure is also greatly enhanced.
Description
Technical field
The present invention relates to a kind of new multi objective intelligence Weighted Grey target decision-making technique.
Background technology
At present, along with economic globalization and scientific and technical continuous progress, the competitive environment that enterprise faces is also more and more fierce: the uncertainty of user's request, to the raising that product quality requires, product life cycle shortens, and product structure is more complicated, and the energy and the prices of raw and semifnished materials skyrocket.Everything makes the production cost of enterprise constantly rise, and main fund and energy are put into and raised brand value with in core competitiveness by enterprise simultaneously, and therefore surplus lines has been given supplier, defines supply chain.
So-called supply chain, be exactly around core enterprise, by the control to information flow, logistics, cash flow, from buying starting material, make intermediate product and final products, finally by sales network product to deliver in consumer's hand one by supplier, manufacturer, retail trader, retailer, until final user is linked to be overall function network structure.And in whole supply chain link, supplier is the most key ingredient.
As a whole, supplier is the source of whole supply chain, is the basis that whole supply chain partnership runs to the selection of supplier.Supplier affects the running of enterprise in many aspects, as product quality, product price, reaction velocity, inventory level, dilivery term etc.The product that supplier provides determines price and the quality of the consumer goods the most at last, also determines the competitiveness of product in market, the market share etc.Current enterprise more and more relies on supplier in some technical field, and therefore concurrent the extending of the buying of science will be conducive to enterprise competitive power with the partnership of supplier.
Therefore, as the selection of the supplier of external resource, directly affects the globality of supply chain, continuity and harmony.The object of Supplier Selection is to manage supplier better, enables enterprise and supplier jointly obtain better performance.Enterprise should set up a set of comprehensive Supplier Selection system, to select and manage according to unified evaluation category and standard to supplier.
The method of Supplier Selection evaluation is deeply broadly divided into three classes along with what study: qualitative examination, the research that quantitative examination and qualitative, quantitative combine.Qualitative examination empirically selects supplier with relation, but accuracy is lower; Quantitative examination is comparatively accurate to the analysis of problem, but data collection is difficult; The method that qualitative, quantitative combines effectively combines the above two advantage, is subject to increasing enterprise and scholar payes attention to.
Qualitative research method mainly contains several as follows:
1. heuristic
Heuristic is the method judging to select supplier according to the data seeked the opinion of and investigate and in conjunction with the analysis of people.This method mainly listens attentively to procurement staff's suggestion, or is directly judged by rule of thumb by procurement staff, and the method is convenient and swift, but is easy to by subjective impact.
2. call for bid method
Bid method proposes the terms of tender by enterprise, and each supplier carries out competitive bidding, is then determined to reach an agreement with the supplier of condition optimum by enterprise.Bid method is competitive strong, can select suitable supplier, but formality is numerous and diverse, is not suitable for emergency in wider scope.
Quantitative research method mainly contains several as follows:
1. activity-based cost analysis method
Activity-based cost analysis method (Activity-Based Costing is called for short ABC), by cost management from transferred product to operation, strengthens the accuracy of pricing.ABC method can not only calculate the operating cost relevant with specific supplier and select, can also to optimization of job on cost basis.
2. multi-objective programming method
Multi-objective programming method (Multiple Objective Programming is called for short MOP) is a kind of on the basis of linear programming technique, for solving the management method that decision-making problem of multi-objective grows up, is also the important branch of operational research.
3. DEA Method
DEA Method (Date Envelopment Analysis, vehicle economy A) proposed by Cha Ensi, Ku Bai and Lodz at first, be a kind of integrated evaluating method based on relative efficiency, the method is applicable to have the efficiency evaluation that multiple-input and multiple-output counts identical type unit.
4. TOPSIS
TOPSIS (Technique for Order Preference by Similarity to IdealSolution, be called for short TOPSIS) by constructing ideal solution and the minus ideal result of many attribute question, and using close ideal solution with away from the foundation of minus ideal result two benchmark as evaluation of programme feasibility.
The qualitative, quantitative research method that combines mainly contains several as follows:
1. analytical hierarchy process
Analytical hierarchy process (Analytic Hierarchy Process is called for short AHP) plans strategies for scholar Satty in the proposition eighties in last century, for the decision-making technique that multi-scheme or multiobject qualitative, quantitative combine by the U.S..
2. artificial neural network algorithm
Artificial neural network algorithm (Artificial Neural Network, be called for short ANN) be similar to cerebral nerve Synaptic junction structure and carry out the mathematical model of information processing.This pattern die apery brain working method, obtains the knowledge of expert, experience and tendency, and is reproduced when selection judges.
Above method, through development practice for many years, supplier selection problem has had significant achievement, but still there is following problem:
(1) assessment indicator system is uncomprehensive, comprehensive, objective, and institute's fetching indicates and lays particular stress on dependence subjective experience, and some lays particular stress on dependence objective data, fails to combine with actual.
(2) evaluation model set up cannot consider the relation between supplier and enterprise, and model can't be applied completely in actual applications.
Summary of the invention
The defect that the present invention seeks to exist for prior art provides a kind of new multi objective intelligence Weighted Grey target decision-making technique.
The present invention for achieving the above object, adopts following technical scheme: a kind of new multi objective intelligence Weighted Grey target decision-making technique, is characterized in that,
1st step: according to the event set A={a of setting
1, a
2..., a
nand countermeasure collection B={b
1, b
2..., b
mstructure decision scheme collection S={s
ij=(a
i, b
j) | a
i∈ A, b
j∈ B};
2nd step: determine decision objective k, k=1,2 ..., s;
3rd step: the right to make decision η determining each decision objective k
1, η
2..., η
s;
4th step: according to decision objective k, ask corresponding target effect sample matrix:
5th step: the effect critical value of setting decision objective K;
6th step: the consistent measure of merit matrix asking decision objective k:
7th step: by
obtaining synthesis effect measure matrix is:
8th step: determine optimizing decision scheme
Beneficial effect of the present invention: intelligent Weighted Grey target decision-making technique of the present invention is for profit evaluation model target, cost type target and moderate type target, estimate respective design, cost type target effect estimates and moderate type target floor effect is estimated and moderate type target upper limit measure of merit, with the degree expressing realization of goal or depart from by profit evaluation model target effect.Wherein, consistent measure of merit have meet standardization, dimensionless, effect is unreasonable thinks the good nature that measure value is larger, further grey target critical value is designed to the positive and negative separation of consistent measure of merit function, take into full account that target effect value hits and two kinds of different situations of missing the target, physics meaning is clear, and the resolution of synthesis effect measure also improves greatly.
Embodiment
1. problem describes
First, event entirety within the scope of certain Study on Decision Problems is called the event set of this decision problem, is designated as A={a
1, a
2..., a
n, wherein a
i(i=1,2 ..., n) be i-th event.Institute likely countermeasure entirety is called countermeasure collection, is designated as B={b
1, b
2..., b
m, wherein b
j(j=1,2 ..., m) be jth kind countermeasure.
By event set A={a
1, a
2..., a
nand countermeasure collection B={b
1, b
2..., b
mcartesian product A × B={ (a
i, b
j) | a
i∈ A, b
j∈ B} is called decision scheme collection, is denoted as S=A × B.To arbitrary a
i∈ A, b
j∈ B, claims (a
i, b
j) be decision scheme, be denoted as s
ij=(a
i, b
j).
If S={s
ij=(a
i, b
j) a
i∈ A, b
j∈ B} is decision scheme collection,
for decision scheme s
ijeffect value under decision objective k, R is set of real numbers, then claim
for the effect of S under decision objective k maps.
Referring to of Gray-target decision is exactly the region relatively optimizing promising result place under meaning.But all can not obtain optimal result under many occasions, therefore people often have to take the second best and seek a satisfied result.In addition also grey target can be shunk gradually and degenerate into a point, be optimal case.
2. consistent measure of merit matrix
Because the meaning of different target Effect value, dimension and character are different, in order to obtain the situation synthesis effect measure with comparability, need first by target effect value
be converted into consistent measure of merit.
If A={a
1, a
2..., a
nbe event set, B={b
1, b
2..., b
mbe countermeasure collection, S={s
ij=(a
i, b
j) a
i∈ A, b
j∈ B} is decision scheme collection,
For decision scheme collection S k (i=1,2 ..., sample results matrix s) under target, then have:
1) set k as benefit target, namely target effect sample value is the bigger the better, and the decision-making ash target under k target is set to
namely
for k target effect critical value, then
Be called that profit evaluation model target effect is estimated.
2) set k as cost type target, namely target effect sample value is the smaller the better, and the decision-making ash target under k target is set to
namely
for k target effect critical value, then
Be called that cost type target effect is estimated.
3) set k as moderate type target, namely target effect sample value is more better close to a certain moderate value A, and the decision-making ash target under k target is set to
namely
be respectively floor effect critical value and the upper limit effect critical value of k target, then
1. when
claim
For moderate type target floor effect is estimated;
2. when
claim
For moderate type target upper limit measure of merit.
The degree of closeness of profit evaluation model target effect measure function reflection sample results value and maximum efficiency sample value, and the degree of its wide effect critical value; The degree of closeness of cost type target effect measure function reflection sample results value and minimum sample results value, and the degree of its wide effect critical value; Moderate type target floor effect measure function reflection is less than the sample results value of moderate value A and the degree of closeness of moderate value A, and it is away from the degree of floor effect critical value, moderate type target upper limit measure of merit function reflection is greater than the sample results value of moderate value A and the degree of closeness of moderate value A, and it is away from the degree of upper limit effect critical value.
The situation of missing the target also can be divided into following four kinds:
1) profit evaluation model target effect value is less than critical value
namely
2) cost type target effect value is greater than critical value
namely
3) moderate type target effect value is less than floor effect critical value
namely
4) moderate type target effect value is greater than upper limit effect critical value
namely
Standardization is met, namely for making all kinds of target effect estimate
For benefit target, Bu Fangshe
For cost type target, Bu Fangshe
Floor effect critical value is less than for moderate type target effect value
situation, Bu Fangshe
Upper limit effect critical value is greater than for moderate type target effect value
situation, Bu Fangshe
Following inference 1 can be obtained thus:
Target effect is estimated
meet the following conditions:
1)
dimensionless;
2) effect is unreasonable thinks,
larger;
3)
For the situation that hits,
for situation of missing the target,
Profit evaluation model target effect is estimated, cost type target effect is estimated, moderate type target floor effect is estimated, moderate type target upper limit measure of merit
be referred to as consistent measure of merit.
3. synthesis effect measure matrix
If η
k(k=1,2 ..., s) be the decision weights of decision objective k, and
claim
For the consistent measure of merit matrix of decision scheme collection S under decision objective k, then for s
ij∈ S, claims
for decision scheme s
ijsynthesis effect measure, and to claim
For synthesis effect measure matrix.
Following inference 2 can be obtained thus:
Synthesis effect measure r
ijmeet the following conditions:
4) r
ijdimensionless;
5) effect is unreasonable thinks, r
ijlarger;
6)r
ij∈[-1,1]。
For the situation that hits, r
ij∈ [0,1]; For situation of missing the target, r
ij∈ [-1,0].
If
then claim b
j0for event a
ioptimal match; If
then claim
for with countermeasure b
jcorresponding optimum event; If
then claim
for optimizing decision scheme.
A kind of intelligence of the new multi objective for Supplier Selection Weighted Grey target decision-making technique of the present invention,
1st step: according to the event set A={a of setting
1, a
2..., a
nand countermeasure collection B={b
1, b
2..., b
mstructure decision scheme collection S={s
ij=(a
i, b
j) | a
i∈ A, b
j∈ B};
2nd step: determine decision objective k, k=1,2 ..., s;
3rd step: the right to make decision η determining each decision objective k
1, η
2..., η
s;
4th step: according to decision objective k, ask corresponding target effect sample matrix:
5th step: the effect critical value of setting decision objective k;
6th step: ask the consistent measure of merit matrix under decision objective k:
7th step: by
obtaining synthesis effect measure matrix is
8th step: determine optimizing decision scheme
Here is the case application of commercial large aircraft key component international suppliers trade-off decision
What the commercial large aircraft project of China adopted is " main manufacturer-supplier " management mode, and a large amount of key component needs the cooperation of international suppliers and coordinates.Therefore, the science of Supplier Selection Decision is the key link being directly connected to Project Success.As the typical decision problem in complex product manufacture process, Supplier Selection is completed by the mode of " bid " usually.Generally proposed to explicitly call for by main manufacturer, Ge Jia supplier formulates bidding plans according to the requirement of main manufacturer, and then main manufacturer carries out Integrated comparative to the scheme that each supplier submits to, chooses the best alternatives, and signs procurement contract book.The factor affecting Supplier Selection Decision is very complicated, for realizing science decision, needs comprehensively to analyze various factors.
In the trade-off decision of commercial large aircraft key component international suppliers, the first run has three international suppliers to be shortlisted for.
The first step: set up event set, countermeasure collection and decision scheme collection.We using the trade-off decision of commercial large aircraft key component international suppliers as event a
1, event set A={a
1.Select supplier 1, supplier 2 and supplier 3 are respectively as countermeasure b
1, b
2, b
3countermeasure collection B=(b
1, b
2, b
3).Decision scheme S={s is constructed by event set A and countermeasure collection B
11, s
12, s
13.
Second step: determine decision objective k.Take turns expert investigation by 3, determine following 5 decision objectives: quality, price, delivery date, design proposal, competitive power.
Wherein competitive power, quality, design proposal is qualitative objective, needs to be evaluated by the way of expert estimation, evaluates score value and is the bigger the better, be profit evaluation model index; Price is more low better, belongs to cost type index; Belong to moderate type index delivery date.
3rd step: the right to make decision determining each decision objective k: the right to make decision of each target and corresponding index is as shown in table 1 to adopt AHP method to determine in present case.
Certain key component international suppliers trade-off decision evaluation objective system of table 1
4th step: the sample results vector asking each decision objective k.
U
(1)=(9.5,9.4,9),U
(2)=(14.2,15.1,13.9),U
(3)=(15.5,17.5,19),
U
(4)=(9.6,9.3,9),U
(5)=(9.5,9.7,9.2)。
5th step: the effect critical value of setting decision objective k.
Competitive power, quality, the critical value of the similar profit evaluation model index of design proposal 3 is taken as
the critical value of price guideline is taken as
belong to moderate type index delivery date, it is 16 months that main manufacturer plans delivery date, and tolerance is limited to 2 months, namely
floor effect critical value is 16-2=14, and upper limit effect critical value is 16+2=18.
6th step: ask the consistent measure of merit vector under decision objective k.Competitive power, quality, the qualitative score value target of design proposal three adopts profit evaluation model target effect to estimate; Price target adopts cost type target effect to estimate; Delivery date is moderate type target.Respective objects is adopted respectively to the profit evaluation model target effect provided in definition 4 is estimated, cost type target effect is estimated, moderate type target floor effect is estimated, moderate type target upper limit measure of merit, consistent measure of merit vector can be obtained as follows:
R
(1)=[1,0.8,0],R
(2)=[0.73,-0.09,1],R
(3)=[0.75,0.25,-0.5],
R
(4)=[1,0.5,0.67],R
(5)=[0.71,1,0.29]。
7th step: by
obtain synthesis effect measure vector
R=[r
11,r
12,r
13]=[0.8463,0.4852,0.2999]
8th step: the determination of optimizing decision scheme.
Due to r
11>0, r
12>0, r
13>0, three suppliers all hit, and it is rational for illustrating that these three suppliers of primary election are shortlisted for.Again by
therefore the final supplier 1 of selection negotiates, contracts.
The foregoing is only preferred embodiment of the present invention, not in order to limit the present invention, within the spirit and principles in the present invention all, any amendment done, equivalent replacement, improvement etc., all should be included within protection scope of the present invention.
Claims (1)
1. a new multi objective intelligence Weighted Grey target decision-making technique, is characterized in that,
1st step: according to the event set A={a of setting
1, a
2..., a
nand countermeasure collection B={b
1, b
2..., b
mstructure decision scheme collection S={s
ij=(a
i, b
j) | a
i∈ A, b
j∈ B};
2nd step: determine decision objective k, k=1,2 ..., s;
3rd step: the right to make decision η determining each decision objective k
1, η
2..., η
s;
4th step: according to decision objective k, ask corresponding target effect sample matrix:
5th step: the effect critical value of setting decision objective K;
6th step: the consistent measure of merit matrix asking decision objective k:
7th step: by
obtaining synthesis effect measure matrix is:
8th step: determine optimizing decision scheme
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510118856.3A CN104809546A (en) | 2015-03-18 | 2015-03-18 | Novel multi-objective intelligent weighted grey target decision method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510118856.3A CN104809546A (en) | 2015-03-18 | 2015-03-18 | Novel multi-objective intelligent weighted grey target decision method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN104809546A true CN104809546A (en) | 2015-07-29 |
Family
ID=53694354
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201510118856.3A Pending CN104809546A (en) | 2015-03-18 | 2015-03-18 | Novel multi-objective intelligent weighted grey target decision method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN104809546A (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105654175A (en) * | 2015-12-24 | 2016-06-08 | 北方民族大学 | Part supplier multi-target preferable selection method orienting bearing manufacturing enterprises |
CN105807612A (en) * | 2016-03-08 | 2016-07-27 | 中国人民解放军总参谋部第五十四研究所 | Target system-based control strategy evaluation method |
CN114217142A (en) * | 2021-09-22 | 2022-03-22 | 中国人民解放军空军工程大学 | Battlefield electromagnetic environment complexity evaluation method |
-
2015
- 2015-03-18 CN CN201510118856.3A patent/CN104809546A/en active Pending
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105654175A (en) * | 2015-12-24 | 2016-06-08 | 北方民族大学 | Part supplier multi-target preferable selection method orienting bearing manufacturing enterprises |
CN105807612A (en) * | 2016-03-08 | 2016-07-27 | 中国人民解放军总参谋部第五十四研究所 | Target system-based control strategy evaluation method |
CN114217142A (en) * | 2021-09-22 | 2022-03-22 | 中国人民解放军空军工程大学 | Battlefield electromagnetic environment complexity evaluation method |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Lima-Junior et al. | Combining SCOR® model and fuzzy TOPSIS for supplier evaluation and management | |
Khaleie et al. | Supplier selection using a novel intuitionist fuzzy clustering approach | |
Nielsen et al. | Management accounting and decision making: Two case studies of outsourcing | |
Yeh et al. | A modified two-tuple FLC model for evaluating the performance of SCM: By the Six Sigma DMAIC process | |
Amiri et al. | Group decision making process for supplier selection with VIKOR under fuzzy circumstance case study: an Iranian car parts supplier | |
KR102109162B1 (en) | Loan availability and management analysis system for small business using artificial intelligence | |
Oliveira et al. | Evaluating vehicle painting plans in an automobile assembly plant using an integrated AHP‐PROMETHEE approach | |
Yin et al. | Application of bootstrap-DEA with fuzzy computing in performance evaluation of forklift leasing supplier | |
CN104809546A (en) | Novel multi-objective intelligent weighted grey target decision method | |
Zandieh et al. | A new framework for dynamic sustainability balanced scorecard in order to strategic decision making in a turbulent environment | |
Orji et al. | Assessing the effect of supply chain collaboration on the critical barriers to additive manufacturing implementation in supply chains | |
Chen et al. | Innovation and application of enterprise's supply chain management mode under the background of Industry 4.0 | |
Tceplit et al. | Developing the model for assessing the competitiveness of innovative engineering products | |
CV et al. | An approach for measuring a manufacturer’s preferred supplier status | |
Patalas-Maliszewska et al. | An approach to maintenance sustainability level assessment integrated with Industry 4.0 technologies using Fuzzy-TOPSIS: A real case study | |
Kabir et al. | A multi–criteria decision–making model to increase productivity: AHP and fuzzy AHP approach | |
Misra et al. | Integrated AHP-TOPSIS model for software selection under multi-criteria perspective | |
Aliakbari Nouri et al. | Providing a fuzzy expert system to assess the maturity level of companies in manufacturing excellence in the food industry of iran | |
Tseng et al. | Fuzzy AHP approach to TQM strategy evaluation | |
Huang et al. | Dynamic performance assessment system for Green tourism supply chain | |
Hoberg et al. | How to design human–machine interaction in next-generation supply chain planning | |
Van Nguyen et al. | Digital transformation for cost estimation system via meta-learning and an empirical study in aerospace industry | |
Wessely | Value Determination of Supply Chain Initiatives: A quantification approach based on fuzzy logic and system dynamics | |
Li et al. | BCVR: A methodological framework for industrial performance management and decision-support | |
Kavilal et al. | An integrated Fuzzy AHP and Fuzzy TOPSIS for prioritizing supply chain complexity drivers |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20150729 |