CN115146455A - Complex supply chain multi-target decision-making method supported by calculation experiment - Google Patents
Complex supply chain multi-target decision-making method supported by calculation experiment Download PDFInfo
- Publication number
- CN115146455A CN115146455A CN202210751540.8A CN202210751540A CN115146455A CN 115146455 A CN115146455 A CN 115146455A CN 202210751540 A CN202210751540 A CN 202210751540A CN 115146455 A CN115146455 A CN 115146455A
- Authority
- CN
- China
- Prior art keywords
- supply chain
- scheme
- decision
- target
- experiment
- 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.)
- Granted
Links
- 238000002474 experimental method Methods 0.000 title claims abstract description 106
- 238000000034 method Methods 0.000 title claims abstract description 57
- 238000004364 calculation method Methods 0.000 title claims abstract description 43
- 238000005457 optimization Methods 0.000 claims abstract description 64
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 27
- 238000012163 sequencing technique Methods 0.000 claims abstract description 16
- 238000011156 evaluation Methods 0.000 claims description 42
- 238000010606 normalization Methods 0.000 claims description 15
- 230000035945 sensitivity Effects 0.000 claims description 15
- 238000011161 development Methods 0.000 claims description 13
- 239000011159 matrix material Substances 0.000 claims description 13
- 230000007246 mechanism Effects 0.000 claims description 12
- 230000008569 process Effects 0.000 claims description 12
- 238000012795 verification Methods 0.000 claims description 9
- 238000005094 computer simulation Methods 0.000 claims description 6
- 230000003993 interaction Effects 0.000 claims description 6
- 238000004590 computer program Methods 0.000 claims description 5
- 238000013507 mapping Methods 0.000 claims description 5
- 238000012545 processing Methods 0.000 claims description 5
- 230000003068 static effect Effects 0.000 claims description 5
- 239000000203 mixture Substances 0.000 claims description 4
- 238000012360 testing method Methods 0.000 claims description 4
- 239000013598 vector Substances 0.000 claims description 4
- QAPUWNJNUGPVPM-NTUXHYESSA-N (17z,23z)-3-butyl-4,6,8,10,12,14,16,27-octahydroxy-17,28-dimethyl-1-oxacyclooctacosa-17,19,21,23,25-pentaen-2-one Chemical compound CCCCC1C(O)CC(O)CC(O)CC(O)CC(O)CC(O)CC(O)\C(C)=C/C=CC=C\C=C/C=CC(O)C(C)OC1=O QAPUWNJNUGPVPM-NTUXHYESSA-N 0.000 claims description 3
- QAPUWNJNUGPVPM-UHFFFAOYSA-N chainin Natural products CCCCC1C(O)CC(O)CC(O)CC(O)CC(O)CC(O)CC(O)C(C)=CC=CC=CC=CC=CC(O)C(C)OC1=O QAPUWNJNUGPVPM-UHFFFAOYSA-N 0.000 claims description 3
- 238000010276 construction Methods 0.000 claims description 3
- 238000004321 preservation Methods 0.000 claims description 3
- 230000002860 competitive effect Effects 0.000 claims 1
- 230000002452 interceptive effect Effects 0.000 claims 1
- 238000013461 design Methods 0.000 abstract description 5
- 230000007547 defect Effects 0.000 abstract description 4
- 230000000694 effects Effects 0.000 abstract description 2
- 238000004519 manufacturing process Methods 0.000 description 13
- 238000004088 simulation Methods 0.000 description 12
- 238000009826 distribution Methods 0.000 description 10
- 239000003795 chemical substances by application Substances 0.000 description 7
- 230000002068 genetic effect Effects 0.000 description 7
- OKKJLVBELUTLKV-UHFFFAOYSA-N Methanol Chemical compound OC OKKJLVBELUTLKV-UHFFFAOYSA-N 0.000 description 6
- 238000004458 analytical method Methods 0.000 description 5
- 230000006870 function Effects 0.000 description 5
- 238000011160 research Methods 0.000 description 5
- 238000013459 approach Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 230000009326 social learning Effects 0.000 description 3
- 241000196324 Embryophyta Species 0.000 description 2
- 241001235534 Graphis <ascomycete fungus> Species 0.000 description 2
- 239000006185 dispersion Substances 0.000 description 2
- 238000013508 migration Methods 0.000 description 2
- 230000005012 migration Effects 0.000 description 2
- 239000002243 precursor Substances 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 description 1
- 235000013400 Quercus lobata Nutrition 0.000 description 1
- 240000001749 Quercus lobata Species 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 229910052799 carbon Inorganic materials 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 238000012790 confirmation Methods 0.000 description 1
- 238000000354 decomposition reaction Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000012797 qualification Methods 0.000 description 1
- 238000010845 search algorithm Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/16—Matrix or vector computation, e.g. matrix-matrix or matrix-vector multiplication, matrix factorization
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/02—Reliability analysis or reliability optimisation; Failure analysis, e.g. worst case scenario performance, failure mode and effects analysis [FMEA]
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Human Resources & Organizations (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Economics (AREA)
- Computational Mathematics (AREA)
- Educational Administration (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- General Engineering & Computer Science (AREA)
- Pure & Applied Mathematics (AREA)
- Development Economics (AREA)
- Data Mining & Analysis (AREA)
- Entrepreneurship & Innovation (AREA)
- Strategic Management (AREA)
- Databases & Information Systems (AREA)
- Software Systems (AREA)
- Algebra (AREA)
- Computing Systems (AREA)
- Geometry (AREA)
- Evolutionary Computation (AREA)
- Game Theory and Decision Science (AREA)
- Computer Hardware Design (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a complex supply chain multi-objective decision method supported by a calculation experiment, which can explore and predict the multi-element emergence of a scheme in a complex supply chain, and perform multi-objective optimization and sequencing on the scheme based on the emergence result to obtain a decision suggestion. Firstly, designing a calculation experiment to construct a supply chain model; after the design of the calculation experiment model is finished, the calculation experiment and the multi-objective evolutionary algorithm NSGA-II are integrated in a closed loop mode, so that the multi-element evolution and optimization of the scheme are realized; after the multi-objective optimization of the scheme is completed, the pareto optimization scheme is selected in a sequencing mode through an entropy weight-TOPSIS method. The invention provides a supply chain multi-target normative decision method for the first time under the theoretical background of a complex system, the decision-making method can make up the decision-making defect of a manager based on subjective preference, increase the decision-making alternative space of the manager and improve the decision-making effect.
Description
Technical Field
The invention belongs to the field of computer simulation optimization, and particularly relates to a complex supply chain multi-objective decision method supported by a computational experiment.
Background
Based on computational experiments, the multivariate emerging of the scheme can be explored to realize predictive decision, and the application fields include but are not limited to: <xnotran> (Q.Q.Long.2014.An agent-based distributed computational experiment framework for virtual supply chain network development.Expert Systems with Applications,41 (9), 4094-4112;Q.Q.Long.2015.Three-dimensional-flow model of agent-based computational experiment for complex supply network evolution.Expert Systems with Applications,42 (5), 2525-2537.), (X.Xue, S.F.Wang, L.J.Zhang, Z.Y.Feng, Y.D.Guo.2019.Social learning evolution (SLE): computational experiment-based modeling framework of social manufacturing.IEEE Transactions on Industrial Informatics,15 (6), 3343-3355;X.Xue,S.F.Wang,L.J.Zhang,Z.Y.Feng.2019.Evaluating of dynamic service matching strategy for social manufacturing in cloud environment.Future Generation Computer Systems,91,311-326;X.Xue,H.F.Han,S.F.Wang,C.Z.Qin.2019.Computational experiment-based evaluation on context-Aware O2O service recommendation.IEEE Transactions on Services Computing,12 (6), 910-924;X.Xue,Y.M.Kou,S.F.Wang,Z.Z.Liu.2018.Computational experiment research on the equalization-oriented service strategy in collaborative manufacturing.IEEE Transactions on Services Computing,11 (2), 369-383;X.Xue,S.F.Wang,B.Gui,Z.W.Hou.2016.A computational experiment-based evaluation method for context-aware services in complicated environment.Information Sciences,373,269-286.), (G.Y.Jiang, F.C.Ma, J.Shang, P.Y.K.Chau.2014.Evolution of knowledge sharing behavior in social commerce: an agent-based computational approach.Information Sciences,278,250-266.). </xnotran>
Currently, few documents propose multi-objective decision-making methods supported by computational experiments, but some studies have utilized a method combining simulation and evolutionary algorithm to solve complex supply chain decision-making problems. Noordhoek et al (M.Noordhoek, W.Dullaert, D.S.W.Lai, S.de Leeuw.2018.A relation-optimization for a service-constrained multi-iteration distribution network. Transmission Research Part E: logics and transport views, 114, 292-311.) developed a simulation optimization method incorporating a scatter search algorithm to optimize a multi-level distribution network with defined delivery time, delay delivery and order fulfillment rate constraints. Frazzon et al (E.M. Frazzon, A.Albrecht, M.Pires, E.Israel, M.K. Huck, M.Fretitag.2018.hybrid approach for the integrated scheduling of Production and transport processes along with the industry resources, 56 (5), 2019-2035) propose a supply chain scheduling method integrating simulation and genetic algorithms in an attempt to reduce the number of overdue orders at a controlled cost. Taghdisian et al (h.taghdisian, m.r.pishvaie, f.faradai.2015.multi-objective optimization for green design of methanol plant based on CO 2-efficiency indication. Journal of Cleaner Production,103 (15), 640-650.) use genetic algorithms to optimize methanol Production to maximize yield and minimize carbon emissions. The optimization problem in these studies is multi-objective in nature, but is often determined by weighting preferences (h.taghdisian, m.r.pishvaie, f.farada.2015.multi-objective optimization for green design of turbine plant based on CO 2-efficiency indicator. Journal of cleaning process, 103 (15), 640-650.), or by converting parts of the targets to constraints (h.ch _ vez, k.k.castillo-Villar, l.herrera, A.Bustos.2017.Simulation-based multi-object model for applying channels with disparities in transfer. Robots and Computer-Integrated Manufacturing,43,39-49 A.Pan, S.Y.S.Leung, K.L.Moon, K.W.Yeung.2009. Optical recorder definition-mapping in the agent-based applied protocol housing. Expression Systems with Applications,36 (4), 8571-8581, J.F. Robles, M.Chica, O.Cordon.2020.Evolution multiobjective optimization to target social network in visual marking. Expert Systems with Applications,147, 113183.) into a single target problem. The resulting scheme in this way is highly sensitive to weight vectors, or performs well on some targets but not well on others (n.srinivas, k.deb.1994.Multi-objective optimization using non-oriented encoding in genetic algorithms, evolution, calculation, 2 (3), 221-248.). These solutions are called pareto optimal or non-dominated solutions (N.Srinivas, K.Deb.1994.Multi-objective Optimization using non-oriented simulation in genetic algorithms, evolution calculation, 2 (3), 221-248 V.Chankong, Y.Y.Haimes.1983.Multi-objective resolution mapping the same and method (North-Holland, new York); A.E.Hans.1988. Multi-objective Optimization for high availability acquisition system. Multi-objective Optimization Engineering and science, 19, 309-352.). NSGA-II (K.Deb, A.Pratap, S.Agarwal, T.Meyarivan.2002.A fast and elitist multiobjective genetic algorithm: NSGA-II.IEEE Transactions on evolution, 6 (2), 182-197.) is one of the most popular pareto optimization algorithms today because of its good solution distribution diversity and better convergence near the true pareto frontage. Robles et al (J.F. Robles, M.Chica, O.Cordon.2020.Evolution multiobjective optimization to target network in visual tagging. Expert Systems with Applications,147, 113183.) adopt a simulation optimization method combined with NSGA-II to solve the problem of influence maximization of social networks, and it is found that the multi-objective algorithm is more excellent than the single-objective algorithm, and that NSGA-II can obtain more schemes than the multi-objective algorithm (MOEA/D) based on decomposition in terms of the number of pareto frontage schemes. Avci et al (M.G.Avci, H.Selim.2017.A Multi-object, simulation-based optimization frame for custom chains with precursors front. Expert Systems with Applications 67, 95-106.) and Avci et al (M.G.Avci, H.Selim.2018.A Multi-object simulation-based optimization approach with precursors front. Omega. 80, 153-165.) discuss the optimal inventory strategy under the different inventory principles, and NSGA-II finds better than MOEA/D when finding optimal. The combination of simulation and a multi-objective evolutionary algorithm NSGA-II is an effective method for processing a multi-objective normative decision problem.
Because the calculation experiment is further developed by simulation, the multi-objective decision method combined with the calculation experiment support of the multi-objective evolutionary algorithm NSGA-II should perform well. Although few papers have proposed multi-objective decision-making methods supported by Computational experiments for use in the field of complex supply chain evolution, some researchers have utilized single objective evolutionary algorithms in Computational experiments to predict and analyze the outcome of a solution, such as optimizing supply chain paths in experiments (x.xue, y.m.kou, s.f.wang, z.z.liu.2018.Computational evolution research on the estimation-oriented service in chemical evolution. Ieee Transactions on Services Computing,11 (2), 369-383.), or in Computational experiments to characterize the evolution process of supply chain individuals with single objective evolutionary algorithms (x.xue, s.f.wang., zhang, z.y.feed, y.d.guide.9.2019. Source evolution) (ieee.336. Analysis-336), information-analysis of sample analysis, sleep-engineering, sleep-33. Sub.43). Xue et al (X.Xue, Y.M.Kou, S.F.Wang, Z.Z.Liu.2018.Computational implementation research on the estimation-oriented service protocol in a collaborative management on Services Computing,11 (2), 369-383.), use computational experiments to evaluate different service strategies and use genetic algorithms in the experiments to process manufacturing service composition problems. The social manufacturing framework is modeled from the perspective of social learning evolution by using Computational experiments, and the evolution of individual enterprises is described by using genetic algorithms (X.Xue, S.F.Wang, L.J.Zhang, Z.Y.Feng, Y.D.Guo.2019.Social Learning Evolution (SLE): computational experiment-based modeling frame of social manufacturing. IEEE Transactions on Industrial information, 15 (6), 3343-3355.). These two articles demonstrate the effectiveness of a combination of computational experiments with evolutionary algorithms. However, there is still room for further exploration:
(1) Since both articles focus on multi-objective prediction or analytical decisions in complex supply chains, the problem of how to extend predictive or analytical decisions to multi-objective normative decisions is not addressed;
(2) Because the single-target optimization algorithm cannot realize multi-target optimization of the scheme, and the supply chain performance target and the additional stability target cannot be simultaneously optimized, the actual optimization scheme may not be good enough, and therefore, the scheme needs to be optimized by using the multi-target evolution algorithm NSGA-II.
In the multi-objective normative decision method, after a manager adopts a multi-objective evolutionary algorithm NSGA-II to realize multi-objective optimization, a multi-objective decision analysis method is adopted to sort and screen the pareto optimal schemes. As an extension of the classic TOPSIS method in terms of objective preference, the fusion of TOPSIS with Entropy weight method (i.e., entropy weight-TOPSIS method) has been successfully used to solve the problems of green vendor selection (b.m.dos Santos, l.p.goody, l.m.s.campos.2019.performance evaluation of green producers using expression-TOPSIS-f.journal of Cleaner Production,207, 498-509.) and public evaluation block chain (h.m.tang, y.shi, p.w.dong.2019.public block evaluation using expression and sis. Expert Systems with Applications,117, 204-210.). These studies show that the entropy weight-TOPSIS method can rank pareto optimal solutions obtained after solution optimization within a framework to support multi-objective decisions. But after the evolution optimization of the scheme supported by the calculation experiment is finished, fewer articles are provided for sequencing the obtained pareto optimal scheme by adopting an entropy weight-TOPSIS method.
By summarizing the research, it can be found that the multi-objective evolutionary algorithm NSGA-II is a popular optimization method at present and is widely applied to the optimization problem of the supply chain, and some articles integrate simulation and the multi-objective algorithm NSGA-II to support multi-objective decision of the supply chain. In these studies, the successful application of simulation optimization shows that the multi-objective decision-making method supported by computational experiments can help solve the complex decision-making problem in the view of the evolution of a complex system, but related studies are few.
In addition, in order to make up for the defect of subjective preference of a manager, the pareto optimal scheme needs to be selected based on objective preference so as to further improve the multi-objective decision method. However, there are few articles that combine the entropy weight-TOPSIS approach with a multi-objective decision method supported by simulation optimization or computational experiments.
Disclosure of Invention
The invention aims to provide a complex supply chain multi-target decision method supported by computational experiments aiming at the defects of the prior art. The method can explore and predict the multi-element emergence of the scheme in a complex supply chain, perform multi-objective optimization on the scheme based on the emergence result, and sort the optimization scheme under objective preference to obtain decision suggestions.
The purpose of the invention is realized by the following technical scheme: a complex supply chain multi-target decision method supported by a calculation experiment comprises the following steps:
(1) Computational experiments were designed to construct supply chain models: a computational experiment model is designed to describe a supply chain, and a mapping relation between a model decision variable and a decision target is established through computational experiment development and parameter verification, so that the multi-element evaluation of a scheme is realized. The description of the supply chain includes: the decision mechanism of the supply chain entity, the interaction mode between the supply chain entities, and the decision variables and decision targets of the model.
(2) Supply chain multi-objective optimization: after a calculation experiment model is established based on the step (1), a scheme is generated through a multi-objective evolutionary algorithm NSGA-II, the scheme is evaluated from the perspective of a supply chain performance target and a stability target through a deployment calculation experiment, and the result of the scheme evaluation is used as the basis for performing elite reservation on the NSGA-II and generating a new scheme so as to realize further evolution optimization. The scheme evaluation based on the calculation experiment comprises three steps of situation establishment, exploration and prediction of a multivariate emerging phenomenon and scheme evaluation. This step is repeated until a termination condition is met. And obtaining a solution set which is a pareto optimization solution set after the termination condition is met.
(3) Pareto optimization scheme ordering: after the multi-objective optimization of the scheme in the step (2) is completed, considering that the obtained pareto optimization scheme is centralized and the decision selection of a manager is difficult due to the non-uniqueness of the scheme, calculating multi-objective weights through an entropy weight method, and calculating TOPSIS scores of the pareto optimization scheme based on the entropy weights to sort so as to realize the pareto optimization scheme sorting selection under objective preference.
Further, step (1) comprises the following sub-steps:
(1.1) defining supply chain boundaries and bodies: as part of the socioeconomic system, the supply chain in reality is often in the form of a "supply network" and is a complex giant system, so that the supply chain needs to be reasonably abstracted according to the situation, and the boundary and the internal composition of the supply chain are clarified. The internal components include supply chain agents and agent decision mechanisms, as well as interaction mechanisms between the agents of the supply chain.
(1.2) computational model development: based on the abstract real supply chain SC, the calculation model development is to establish a supply chain model ASC through an abstract mathematical language and design a program module to realize the construction of the supply chain model. Supply chain modelAs an approximation of the real supply chain SC (i.e., ASC ≈ SC), it is largely composed of a static directed graph that reflects the structure of the supply chainAnd a function DF reflecting the evolution trend of the supply chain. Structured directed graph in supply chainIn the middle, V represents a node in the supply chain, that is, a supply chain subject, such as an enterprise or an individual, which has differences in identity, decision mechanism and resource constraint, often has its individual attribute characteristics C, its decision mechanism D and constraint R, and needs to be described through parameter setting, algorithm model and the like. E represents the interaction means and the connection between the supply chain main bodies. Based on this directed graphA static supply chain model may be built. The evolution trend DF of the supply chain model can be expressed as a directed graphI.e. the evolution trend of the connection between nodes in the directed graph. After quantitative description of a supply chain model is realized through a mathematical language, a computational experiment system needs to be developed to perform supply chain analysis in a computer programAnd (5) realizing system evolution. The system is mainly divided into an experiment parameter module, an experiment execution module and a result evaluation module.
(1.3) computational model implementation: after the development of the computational experimental model is completed, the computational experimental model needs to be implemented by a computer program. The experimental parameter module mainly comprises the setting of system environment variable World and decision variable Solution (one group of decision variables is Solution) i I =1,2, \ 8230;, I. I is the total number of the schemes), the setting of the parameters is often from the real situation, expert knowledge and the justified axiom. Inputting parameters (including system environment variables and decision variables) and finishing initialization of the system and establishment of a situation at the beginning of execution of each experiment, deploying a calculation experiment and carrying out the experiment to obtain a Solution in a scheme i The results of the next single macroscopic emergence (denoted as jth, j =1,2, \ 8230;, j.j is the number of protocol repetitions)Can use the vectorDescribing the macroscopic emergence phenomenon from M index dimensions (namely M decision targets), and determining a decision variable Solution in an environment variable World i The value of the mth decision target of the supply chain under in a single experiment is abbreviatedConsidering the diversity of the macroscopic emergence phenomenon, the experiment needs to be repeated for many times to realize the emergence as sufficient as possible and obtain the Solution in the scheme i Results of the following experimentsBased on the obtained macro occurrence, performance values for M performance indicators of the supply chain may be calculated, typically expressed as a mean of performance values over a number of macro occurrences,
(1.4) parameter sensitivity verification: considering the influence of the setting of some parameters (including the system environment variable World and the decision variable Solution) in the calculation experiment model on the experiment result, the value of the experiment parameter (non-decision variable) and the value range of the decision variable should be further adjusted and confirmed through actual data, expert knowledge and the like for the parameter setting of the system environment variable. And sensitivity verification is performed on the parameters in the model after confirmation.
(1.5) evaluation of test results: after the reasonability of the calculation model parameters is verified, the scheme and the experimental result thereof are evaluated mainly from two aspects of M performance indexes and 1 stability target of a supply chain. Each performance indicator KPI m Is the average value of the corresponding target in a plurality of repeated experiments. The stability target reflects the fluctuation of all performance indicators in repeated experiments, so that a standard deviation function is used
Solution of presentation scheme i Stability of the results. Smaller values of standard deviation indicate higher stability of the protocol.
Further, the step (2) comprises the following sub-steps:
(2.1) initialization: initializing decision variable information and setting evolution algebra to be 1.
(2.2) generating a new generation of population: in the value range of the variable, a population is randomly generated, and the evolution algebra is increased by one generation.
(2.3) selecting one member of the population: and sequentially selecting one member in the population, and carrying out the next scheme evaluation.
(2.4) protocol evaluation: and (4) inputting the members selected in the step (2.3), namely a group of decision variables, into a calculation experiment model, establishing a situation, deploying and implementing a calculation experiment. And (3) repeating the experiment for multiple times to explore and predict the multiple emergence of the scheme in the supply chain, calculating the experiment result after the requirement of the number of times of repetition (the multiple emergence exploration is completed), obtaining a performance target value and a stability target value of the supply chain, completing multi-target evaluation, and using the evaluation as the basis for sequencing the scheme in the step (2.5). This procedure was repeated until the evaluation of all members (protocols) in the population was completed.
(2.5) scheme ordering: after all members in the population, i.e., all solutions, have been evaluated, non-dominated sorting is performed according to the results of the evaluation of each solution in step (2.4). And if the evolution algebra is 1 at the moment, sequencing the whole population, and if the evolution algebra is more than 1 at the moment, merging the parent population and the newly generated child population and sequencing. In the sorting process, non-dominant sorting is performed and the crowdedness of the scheme at each layer is calculated.
(2.6) Elite preservation: the entire non-dominant layers are added to the next-generation parent population in sequence according to the order of the non-dominant layers until all of the non-dominant layers cannot be added to the next-generation population (if the dominant layer is added to the next-generation parent population, the number of next-generation parent populations will overflow). For the solutions at this non-dominant level, they are sorted based on the degree of congestion, the greater the degree of congestion, the higher the likelihood of entering the next generation parent population.
And (2.7) if the quit condition is met, ending the scheme optimization to obtain a pareto optimization scheme set, otherwise, carrying out tournament selection and crossing and variation of the population to generate a new generation of population, and repeating the steps (2.2) to (2.6).
Further, the step (3) comprises the following sub-steps:
(3.1) normalization of target values: for the pareto optimal scheme set obtained after the multivariate evolution and optimization, target values of the schemes under multiple targets can be obtained, and the target values of N groups of schemes on M +1 targets form a fractional matrix. Firstly, normalizing the fractional matrix under each target dimension, namely: dividing the score of a solution in a target dimension by the sum of all solution scores in the target dimension
(3.2) calculating information entropy: by the formula:And calculating information entropy under different target dimensions. In order to make the information entropy in all target dimensions within the interval [0,1, k is here assumed to be k =1/lnN.
(3.3) entropy inversion processing: the target values are distributed differently in different target dimensions, and in some target dimensions, the target values are distributed concentratedly, and in some target dimensions, the target values are distributed dispersedly. Attention should be paid more to the target dimension where the target value distribution is more dispersed, so the entropy value obtained in step (3.2) is processed in reverse: e m′ ′=1-E m′ 。
(3.4) weight normalization: based on E determined in step (3.3) m′ ' can be used to describe the forward relationship between the target value distribution dispersion degree and the attention degree, considering that in the subsequent step, the information entropy will be used as the weight of multiple targets, so the obtained E is used here m′ ' further normalization process is performed:
(3.5) fractional matrix normalization: considering the difference in different target dimension dimensions, the fractional matrix is normalized in each target dimension by the following formula:
(3.6) determining ideal and non-ideal conditions: after the normalization operation is completed, calculating the maximum values of different target dimensionsMinimum value z' m′ (M' =1,2, \ 8230;, M + 1), ideal and irrational conditions are determined for each target dimension:
(3.7) calculating the distance of the solution to ideal and non-ideal cases: after determining the ideal and non-ideal conditions in each target dimension, the euclidean distance between the solution and the two is calculated:
(3.8) calculating TOPSIS score: calculating TOPSIS score based on the distance between the scheme obtained in the step (3.7) and the corresponding ideal and non-ideal situations under different target dimensions Wherein, w m′ And weights corresponding to different target dimensions. After the TOPSIS scores are obtained, the plans are ranked based on the score, with higher scores indicating better performance of the plans.
The invention has the beneficial effects that: the method can support macroscopic emergence and multivariate evolution of a complex supply chain, predict possible results of a scheme in reality, and give a decision suggestion according to the emergence result, namely expanding a decision from predictability to normativity. The invention can make up the decision defect of the manager based on subjective preference, increase the decision alternative space of the manager and improve the decision effect.
Drawings
FIG. 1 is a block diagram of the method of the present invention;
FIG. 2 is a detailed flow chart of the method of the present invention.
Detailed Description
The invention provides a complex supply chain multi-target decision method supported by a computational experiment, and provides a comprehensive, effective and reliable decision analysis tool for a manager.
As shown in fig. 1 and fig. 2, an embodiment of a complex supply chain multi-objective decision method for multi-generation smart phone marketing of the present invention includes the following steps:
(1) Computational experiments were designed to construct supply chain models: a computational experiment model is designed to describe a supply chain, and a mapping relation between a model decision variable and a decision target is established through computational experiment development and verification, so that the multi-element evaluation of a scheme is realized. The description of the supply chain includes: the decision variables and decision targets of the model, the decision mechanism of the supply chain entity, the interaction mode between the supply chain entities and the internal entity of the supply chain structure.
(1.1) defining supply chain boundaries and bodies: the present embodiment is a two-level supply chain with one enterprise and a large number of consumers. Enterprises offer three generations of smartphone products to the marketplace, maximizing enterprise revenue, innovation technology acceptance, consumer utility, and supply chain stability by considering pricing, production, and advertising decisions for these products. All consumers have differences in price sensitivity and technical sensitivity, in the decision making process, the consumers can obtain preliminary consumer utility according to product price and technical attributes by combining the differences in the attributes (price sensitivity and technical sensitivity), and then the migration phenomenon in the decision making process of the consumers is considered to obtain final decisions.
(1.2) computational model development: based on the abstracted supply chain SC, the calculation model development is to establish a supply chain model ASC through an abstracted mathematical language and design a program module to realize the construction of the supply chain model. Supply chain modelAs an approximation of the real-world supply chain SC, namely ASC ≈ SC, primarily by the static, reflected supply chainStructured directed graphAnd a function DF reflecting the evolution trend of the supply chain.
Structured directed graph in supply chainIn the specification, V represents a node in the supply chain, i.e., a supply chain body, which in the present embodiment is composed of an enterprise manager and a large number of Consumer consumers; one Consumer is denoted as Consumer s S =1,2, \8230;, S, i.e. V = { Manufacturer, consumer = { (manufacturing, S) } 1 ,Consumer 2 ,…,Consumer S And S is the number of consumers.
These nodes V have differences in identity characteristics, decision mechanism and resource constraints, and in this embodiment, price sensitive Price Sensitivity is used s And Technology Sensitivity s To describe the individual attribute characteristics C of the consumers, i.e., C = { Price Sensitivity = { Price Sensitivity = s ,Technology Sensitivity s }, S =1,2, \8230;, S. The consumer decision mechanism D comprises three steps: (1) calculating a consumer utility function according to the consumer discrete selection model; (2) calculating the utility of the consumer under the influence of the advertisement; (3) and (4) considering randomness in the consumer decision, and representing the change of the consumer decision by adopting a migration matrix to obtain a final decision. In the consumer decision process, the constraint R is: utility needs to be 0 or more and once the product is sold out, the consumer can no longer purchase it. The connection mode E is that the manufacturer provides products to the consumer, and the consumer chooses to buy one product (of the three products) or not.
Based on such a directed graphA static supply chain may be established. The evolution trend DF of the supply chain can be expressed as a directed graphIs being developed.
After quantitative description of the supply chain is realized through a mathematical language, a computational experiment system needs to be developed so as to realize the evolution of the supply chain system in a computer program. The calculation experiment system is mainly divided into an experiment parameter module, an experiment execution module and a result evaluation module.
(1.3) computational model implementation: after the experimental model development is completed through the calculation in the step (1.2), the experimental model development needs to be realized through a computer program.
The experimental parameter module mainly comprises the setting of a system environment variable World and a decision variable Solution; one set of decision variables is denoted Solution i I =1,2, \ 8230;, I; i is the total number of the protocol, and I =19920. In this embodiment, the system environment variables World include the consumer price sensitive and technology sensitive distributions (mean and variance), the vendor's historical sales, and the like. Price with decision variable of three products pi And yield qualification pi Pi =1,2,3, and advertising impressions of the latest product, i.e. ads
The experiment execution module comprises: inputting parameters including system environment variables and decision variables at the beginning of each experiment execution; and completing the initialization of the system and the establishment of the situation, deploying a calculation experiment and carrying out the experiment to obtain a Solution in the scheme i Results of the next j (single) macroscopic emergenciesJ is the number of protocol repetitions, taking J =50. Can use the vectorDescribing macroscopic emergence phenomena from M index dimensions (decision targets), wherein M =3; in the environment variable World and decision variable Solution i The value of the m-th decision object of the supply chain under in the j-th test is recorded
Considering the diversity of the macroscopic emergence phenomenon, the experiment needs to be repeated for many times to realize the emergence as sufficient as possible and obtain the Solution in the scheme i Results of the following experimentsBased on the obtained macro occurrence, performance values for M performance indicators of the supply chain may be calculated, typically expressed as a mean of performance values over a number of macro occurrences,
(1.4) parameter sensitivity verification: considering the influence of the setting of some parameters (including system environment variable World and decision variable Solution) in the experimental model on the experimental result.
For the parameter setting of the system environment variables, the values of experimental parameters (non-decision variables) and the value ranges of decision variables are confirmed through further adjustment of actual data, expert knowledge and the like; and carrying out sensitivity verification on related parameters in the model.
(1.5) evaluation of test results: the result evaluation module is used for evaluating the scheme and the experimental result thereof mainly from two aspects of M performance indexes and 1 stability target (total M +1= 4) of the supply chain after verifying the reasonability of the calculation model parameters.
Each performance indicator KPI m The values of (a) are the corresponding target average values in a plurality of repeated experiments. The Stability target reflects the fluctuation of all performance indicators in repeated experiments, so the standard deviation function Stability is used i Solution of expression i Stability of the results, the smaller the value of the standard deviation, the higher the stability of the protocol.
(2) And (3) supply chain multivariate evolution and optimization: after a calculation experiment model is established based on the step (1), a scheme is generated through a multi-objective evolutionary algorithm NSGA-II, a calculation experiment is implemented to evaluate the scheme from the perspective of a supply chain performance target and a stability target, the result of the scheme evaluation is used as the basis for performing elite reservation on the NSGA-II, and a new scheme is generated to realize further evolution optimization.
And (3) evaluating the scheme based on the calculation experiment, wherein the evaluation comprises three steps of situation establishment, exploration and prediction of a multivariate emerging phenomenon and scheme evaluation, the three steps are repeated until a termination condition is met, and the obtained scheme is integrated into a pareto optimization scheme set after the termination condition is met. The method specifically comprises the following steps:
(2.1) initialization: and initializing decision variable information, setting an evolutionary algebra to be 1, and setting the number of individuals in the population to be 120.
(2.2) generating a new generation population: in the value range of the variable, a population is randomly generated, and the evolution algebra is increased by one generation.
(2.3) selecting one member of the population: and sequentially selecting one member in the population, and carrying out the next scheme evaluation.
(2.4) protocol evaluation: and (4) inputting the members selected in the step (2.3), namely a group of decision variables, into a calculation experiment model, establishing a situation, deploying and implementing the calculation experiment. And (3) repeating the experiment for multiple times to explore and predict the multivariate emergence of the scheme in the supply chain, completing the multivariate emergence exploration after the requirement of the repetition times is met, calculating an experiment result to obtain a performance target value and a stability target value of the supply chain, completing multi-target evaluation, and using the results as the basis for sequencing the scheme in the step (2.5). Step (2.4) is repeated until the evaluation of all members of the population (protocol) is completed.
(2.5) scheme ordering: after the evaluation of all members (i.e., all protocols) in the population is completed, non-dominated ranking is performed according to the evaluation results of each protocol in step (2.4). If the evolution algebra is 1, sequencing the whole population; and if the evolution algebra is larger than 1, merging the parent population and the newly generated child population, and sequencing. In the sorting process, non-dominant sorting is performed and the crowdedness of the scheme at each layer is calculated.
(2.6) Elite preservation: the entire non-dominant layer is added to the next-generation parent population in sequence according to the order of the non-dominant layers until all of one non-dominant layer cannot be added to the next-generation parent population. For the solutions at the non-dominant level, they are sorted based on the degree of congestion, the greater the degree of congestion, the higher the probability of entering the next generation parent population.
(2.7) if the quit condition is met (200 generations of filial generations are generated), finishing the scheme optimization to obtain a pareto optimization scheme set; otherwise, when the quit condition is not met, the selection of the tournament system and the crossing and variation of the population are carried out to generate a new generation of population, and the steps (2.2) to (2.6) are repeated.
(3) Pareto optimization scheme ordering selection: after the multi-element evolution and optimization of the scheme in the step (2) is completed, considering that the obtained pareto optimization scheme is centralized and the decision selection difficulty of a manager caused by the non-uniqueness of the scheme is considered, calculating the multi-target weight through an entropy weight method, calculating the TOPSIS score of the pareto optimization scheme based on the entropy weight, and sequencing to realize the pareto optimization scheme sequencing selection under the objective preference.
(3.1) normalization of the target value by p n,m′ : for the pareto optimal scheme set obtained after the multivariate evolution and optimization, target values of the schemes under multiple targets can be obtained, the target values of N groups of schemes on M +1 targets form a fractional matrix, and the fractional matrix is normalized under each target dimension, namely: scoring u a solution in a certain target dimension n,m′ Divided by the sum of all solution scores for that target dimension:
wherein M' =1 to M +1.
(3.2) calculating information entropy E under different target dimensions m′ :
In order to make the information entropy in all target dimensions within the interval [0,1, let k =1/lnN here.
(3.3) entropy inversion E m′ ': the distribution of target values varies in different target dimensions: under some target dimensions, the target values are distributed centrally; in some target dimensions, the target value distribution is scattered. Attention should be paid more to the target dimension where the target value distribution is more dispersed, so the entropy value obtained in step (3.2) is processed in reverse:
E m′ ′=1-E m′ 。
(3.4) weight normalization of w m′ : based on E determined in step (3.3) m′ ' may be used to describe the positive relationship between the target value distribution dispersion degree and the attention degree; considering that in the subsequent steps the information entropy will be the weight of the multiple targets, the obtained E is therefore referred to here m′ ' further normalization processing is performed:
(3.5) fractional matrix normalization z n,m′ : considering the difference in different target dimension dimensions, the fractional matrix is normalized in each target dimension by the following formula:
(3.6) determining ideal and non-ideal conditions: after the normalization operation is finished, calculating the maximum values under different target dimensionsMinimum value z' m′ (M' =1,2, \8230;, M + 1), the ideal situation a for each target dimension is determined * And non-rational condition A':
(3.7) calculating the distance of the solution to the ideal caseAnd distance S 'from solution to non-ideal case' n 。
After determining the ideal and non-ideal conditions in each target dimension, the euclidean distance between the solution and the two is calculated:
(3.8) calculating TOPSIS score: calculating TOPSIS score C based on the distance between the scheme obtained in step (3.7) and the corresponding ideal and non-ideal cases under different target dimensions n (ii) a After the TOPSIS score is obtained, the schemes are ranked based on the score, and the higher the score is, the better the scheme performance is represented; the decision result is the scheme with the highest score.
Wherein, w m′ And weights corresponding to different target dimensions.
The present invention is not limited to the above embodiments, and all other embodiments obtained by those skilled in the art without any inventive work are within the scope of the present invention in the same or similar manner as the above embodiments of the present invention.
Claims (6)
1. A complex supply chain multi-target decision method supported by a calculation experiment is characterized by comprising the following steps:
(1) Computational experiments were designed to construct supply chain models: by designing a calculation experiment model to describe a supply chain, and by calculating experiment development and parameter verification, establishing a mapping relation between a model decision variable and a decision target to realize multi-element evaluation on a scheme; the description of the supply chain includes: a supply chain structure and an internal entity, a decision mechanism of the supply chain entity, an interactive mode among the supply chain entities, and a decision variable and a decision target of a model;
(2) Supply chain multi-objective optimization: after a calculation experiment model is established based on the step (1), a scheme is generated through a multi-objective evolutionary algorithm NSGA-II, a calculation experiment evaluation scheme from the perspective of a supply chain performance target and a stability target is deployed, and the result of the scheme evaluation is used as the basis for performing elite reservation on the NSGA-II and generating a new scheme to realize further evolution optimization; the scheme evaluation based on the calculation experiment comprises three parts of situation establishment, exploration and prediction of a multivariate emerging phenomenon and scheme evaluation; repeating the step (2) until a termination condition is met; the scheme set obtained after the termination condition is met is a pareto optimization scheme set;
(3) Pareto optimization scheme ordering: after the scheme multi-target optimization is realized in the step (2), calculating multi-target weights through an entropy weight method, and calculating TOPSIS scores of the pareto optimization scheme based on the entropy weights to carry out sequencing so as to realize sequencing selection of the pareto optimization scheme.
2. The complex supply chain multi-objective decision making method supported by computational experiments according to claim 1, wherein the step (1) comprises the following sub-steps:
(1.1) defining supply chain boundaries and bodies: defining the boundary and internal composition of the supply chain; the internal composition comprises a supply chain main body, a main body decision mechanism and an interaction mechanism among all main bodies of the supply chain;
(1.2) computational model development: establishing a supply chain model ASC based on a real supply chain SC, and designing a program module to realize the construction of the supply chain model; supply chain modelAs an approximation of the real supply chain SC, namely ASC ≈ SC, a directed graph that reflects the structure of the supply chain, primarily by staticAnd a function DF reflecting the evolution trend of the supply chain; structured directed graph in supply chainIn the middle, V represents a node in the supply chain, and the node V has its individual attribute characteristics C, its decision mechanism D and constraint R; e represents the interaction and relation among the supply chain main bodies; based on directed graphsEstablishing a static supply chain model; the evolution trend DF of the supply chain model is expressed as a directed graphAfter the quantitative description of the supply chain model, the evolution trend of the connection between the middle nodes and the nodes needs to develop a calculation experiment system to realize the supply chain system evolution in a computer program;
(1.3) calculating the realization of an experimental model: after the development of the calculation experiment model is completed, the calculation experiment model needs to be realized through a computer program; the experimental parameter module mainly comprises the setting of a system environment variable World and a decision variable Solution, and one group of decision variables is marked as Solution i I =1,2, \ 8230;, I; i is the total number of the schemes; inputting parameters and completing initialization of the system and establishment of the situation when the execution of each experiment is started, deploying a calculation experiment and performing the experiment to obtain a Solution in a scheme i Result of next j-th macroscopic emergenceJ is the number of repetitions of the protocol; the input parameters comprise system environment variables and decision variables; using vectorsDescribing the macroscopic emergence phenomenon from M index dimensions, namely the environment variable World and the decision variable Solution i The value of the m-th decision target of the supply chain under in a single experiment is recordedRepeating the experiment for a plurality of times to obtain the Solution in the scheme i Results of the following experimentsCalculating performance values for the M performance indicators of the supply chain, based on the obtained macro occurrence, expressed as an average of the performance values over the plurality of macro occurrences,
(1.4) parameter sensitivity verification: carrying out sensitivity verification on related parameters in the calculation experiment model, wherein the related parameters comprise a system environment variable World and a decision variable Solution;
(1.5) evaluation of test results: after the reasonability of the parameters of the experimental model is verified and calculated, evaluating the scheme and the experimental result thereof mainly from two aspects of M performance indexes and 1 stability target of a supply chain; each performance indicator KPI m The value of (b) is the average value of the corresponding target in multiple repeated experiments; the stability target reflects the fluctuation condition of all performance indexes in repeated experiments, so that the standard deviation function is used for representing the Solution i The stability of the results; the smaller the value of the standard deviation, the higher the stability of the protocol;
3. the complex supply chain multi-objective decision making method supported by computational experiments as claimed in claim 2, wherein the node V in the supply chain is a supply chain subject including enterprises and individuals.
4. The complex supply chain multi-objective decision making method supported by computational experiments according to claim 1, wherein the step (2) comprises the following sub-steps:
(2.1) initialization: initializing decision variable information, and setting an evolution algebra to be 1;
(2.2) generating a new generation population: randomly generating a population in a variable value range, and increasing one generation by evolution algebra;
(2.3) selecting one member of the population: sequentially selecting one member in the population, and carrying out the next scheme evaluation;
(2.4) protocol evaluation: inputting the members selected in the step (2.3), namely a group of decision variables, into a calculation experiment model, establishing a situation, deploying and implementing a calculation experiment; repeating the experiment for multiple times to explore and predict the multivariate emergence of the scheme in the supply chain, completing the multivariate emergence exploration after the requirement of the repetition times is met, calculating the experiment result to obtain a performance target value and a stability target value of the supply chain, completing multi-target evaluation, and using the results as the basis for sequencing the scheme in the step (2.5); repeating this step until the evaluation of all members of the population is completed;
(2.5) scheme ordering: after the evaluation of all members in the population is completed, performing non-dominated sorting according to the evaluation result of each scheme in the step (2.4); if the evolution algebra is 1 at the moment, sequencing the whole population, and if the evolution algebra is more than 1 at the moment, merging the parent population and the newly generated child population and sequencing; in the sorting process, non-dominated sorting is carried out and the crowding degree of the scheme at each layer is calculated;
(2.6) Elite preservation: according to the order of the non-dominant layers, adding the whole layer of non-dominant layer into the next generation parent population in sequence until the situation that a certain non-dominant layer can not be added into the next generation population completely occurs; for the scheme at the non-dominant layer, the scheme is sorted based on the crowding degree, and the larger the crowding degree is, the higher the possibility of entering the next generation parent population is;
(2.7) if the exit condition is met, finishing the scheme optimization to obtain a pareto optimization scheme set; otherwise, selecting the competitive tournament system, crossing and mutating the population to generate a new generation of population, and repeating the steps (2.2) to (2.6).
5. The complex supply chain multi-target decision making method supported by computational experiments according to claim 4, wherein in the step (2.6), the case that all non-dominant layers cannot be added into the next generation population is: if the dominance layer is added to the next generation parent population, the number of the next generation parent population will overflow.
6. The complex supply chain multi-objective decision-making method supported by computational experiments according to claim 1, wherein the step (3) comprises the following sub-steps:
(3.1) normalization of target values: obtaining target values of the solutions under multiple targets for the pareto optimal solution set obtained after the multivariate evolution and optimization, wherein the target values of the N groups of solutions on M +1 targets form a fractional matrix; firstly, the score matrix is normalized under each target dimension, namely, the score of a scheme under a certain target dimension is divided by the sum of the scores of all schemes under the target dimension
(3.2) calculating information entropy: by passingCalculating information entropies under different target dimensions; let k =1/lnN here;
(3.3) entropy inversion processing: and (3) carrying out inverse processing on the entropy value obtained in the step (3.2): e m′ ′=1-E m′ ;
(3.4) weight normalization: for E obtained in step (3.3) m′ ' further normalization process is performed:
(3.5) fractional matrix normalization: the fractional matrix is normalized at each target dimension:
(3.6) determining ideal and non-ideal conditions: after the normalization operation is completed, calculating the maximum values of different target dimensionsMinimum value z' m′ Determining ideal and irrational conditions for each target dimension:
(3.7) calculating the distance of the solution to ideal and non-ideal cases: after determining the ideal and non-ideal conditions in each target dimension, the euclidean distance between the solution and the two is calculated:
(3.8) calculating TOPSIS score: calculating TOPSIS score based on the distance between the scheme obtained in the step (3.7) and the corresponding ideal and non-ideal cases under different target dimensionsWherein, w m′ Weights corresponding to different target dimensions; after the TOPSIS scores are obtained, the plans are ranked based on the score, with higher scores indicating better performance of the plans.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210751540.8A CN115146455B (en) | 2022-06-28 | 2022-06-28 | Complex supply chain multi-objective decision method supported by calculation experiment |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210751540.8A CN115146455B (en) | 2022-06-28 | 2022-06-28 | Complex supply chain multi-objective decision method supported by calculation experiment |
Publications (2)
Publication Number | Publication Date |
---|---|
CN115146455A true CN115146455A (en) | 2022-10-04 |
CN115146455B CN115146455B (en) | 2024-04-05 |
Family
ID=83410147
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210751540.8A Active CN115146455B (en) | 2022-06-28 | 2022-06-28 | Complex supply chain multi-objective decision method supported by calculation experiment |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN115146455B (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117132165A (en) * | 2023-09-13 | 2023-11-28 | 深圳达普信科技有限公司 | Dynamic performance evaluation method and system based on data mining |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20080215512A1 (en) * | 2006-09-12 | 2008-09-04 | New York University | System, method, and computer-accessible medium for providing a multi-objective evolutionary optimization of agent-based models |
CN113991751A (en) * | 2021-10-27 | 2022-01-28 | 云南电网有限责任公司电力科学研究院 | Automatic power generation control scheduling method based on hybrid algorithm |
-
2022
- 2022-06-28 CN CN202210751540.8A patent/CN115146455B/en active Active
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20080215512A1 (en) * | 2006-09-12 | 2008-09-04 | New York University | System, method, and computer-accessible medium for providing a multi-objective evolutionary optimization of agent-based models |
CN113991751A (en) * | 2021-10-27 | 2022-01-28 | 云南电网有限责任公司电力科学研究院 | Automatic power generation control scheduling method based on hybrid algorithm |
Non-Patent Citations (2)
Title |
---|
夏澍;周明;李庚银;: "分布式电源选址定容的多目标优化算法", 电网技术, no. 09, 5 September 2011 (2011-09-05) * |
王丽萍;江波;邱飞岳;: "基于决策偏好的多目标粒子群算法及其应用", 计算机集成制造系统, no. 01, 15 January 2010 (2010-01-15) * |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117132165A (en) * | 2023-09-13 | 2023-11-28 | 深圳达普信科技有限公司 | Dynamic performance evaluation method and system based on data mining |
Also Published As
Publication number | Publication date |
---|---|
CN115146455B (en) | 2024-04-05 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Liang et al. | Logistics-involved QoS-aware service composition in cloud manufacturing with deep reinforcement learning | |
US8250007B2 (en) | Method of generating precedence-preserving crossover and mutation operations in genetic algorithms | |
Tekin et al. | Distributed online learning in social recommender systems | |
Ryberg et al. | Metamodel-based multidisciplinary design optimization for automotive applications | |
Xu et al. | A multi-objective decision-making model with fuzzy rough coefficients and its application to the inventory problem | |
US20080104000A1 (en) | Determining Utility Functions from Ordinal Rankings | |
CN107256241B (en) | Movie recommendation method for improving multi-target genetic algorithm based on grid and difference replacement | |
Navgaran et al. | Evolutionary based matrix factorization method for collaborative filtering systems | |
Eraslan et al. | An improved decision support system for ABC inventory classification | |
Chien et al. | An integrated approach for IC design R&D portfolio decision and project scheduling and a case study | |
Çağrı Tolga et al. | Fuzzy multiattribute evaluation of R&D projects using a real options valuation model | |
CN110222838B (en) | Document sorting method and device, electronic equipment and storage medium | |
Sampath et al. | A generalized decision support framework for large‐scale project portfolio decisions | |
CN115146455B (en) | Complex supply chain multi-objective decision method supported by calculation experiment | |
Wang et al. | A novel many-objective recommendation algorithm for multistakeholders | |
Zhou et al. | Intelligent exploration for user interface modules of mobile app with collective learning | |
Kılıç | Supplier selection application based on a fuzzy multiple criteria decision making methodology | |
Huang et al. | Improved collaborative filtering personalized recommendation algorithm based on k-means clustering and weighted similarity on the reduced item space | |
Qu et al. | Learning demand curves in B2B pricing: A new framework and case study | |
CN115965203A (en) | User-side virtual power plant flexible adjustment service transaction strategy optimization implementation method | |
US8090835B1 (en) | Optimizing website traffic among content sources | |
Cinalli et al. | Collective preferences in evolutionary multi-objective optimization: techniques and potential contributions of collective intelligence | |
Soroor et al. | An advanced adoption model and an algorithm of evaluation agents in automated supplier ranking | |
Afshar et al. | An automated deep reinforcement learning pipeline for dynamic pricing | |
Zhang et al. | Fuzzy cognitive map approach for trust-based partner selection in virtual enterprise |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |