Complex system evaluation method based on fuzzy multi-objective decision

Abstract

The invention belongs to the technical field of complex system evaluation, and provides a complex system evaluation method based on fuzzy multi-objective decision, which comprises the following steps: S1, constructing a multi-level and multi-dimensional complex system evaluation model; s2, performing fuzzification processing on the indexes under each evaluation target by using a fuzzy set theory; s3, introducing a dynamic weight distribution mechanism, and dynamically adjusting the weight of each target by adopting an intelligent algorithm according to the relative importance among the targets and the current system state; according to the method, a multi-level and multi-dimensional evaluation model is constructed, uncertainty and fuzziness in the evaluation process are processed by utilizing a fuzzy set theory, a dynamic weight distribution mechanism and an intelligent algorithm are introduced to optimize weights, an improved multi-objective decision algorithm is applied to perform comprehensive analysis, and finally optimization suggestions are proposed; according to the method, the overall condition of the complex system can be reflected more accurately, the timeliness and pertinence of evaluation are ensured, and the scientificity and accuracy of evaluation are improved.

Description

Technical Field

[0001] The invention belongs to the technical field of complex system evaluation, in particular to a complex system evaluation method based on fuzzy multi-objective decision making. Background Art

[0002] In the existing technology, the evaluation methods of complex systems often face many challenges. On the one hand, complex systems usually have multi-level and multi-dimensional characteristics. Their performance, stability, cost-effectiveness, environmental impact and user satisfaction are both interrelated and conflicting, making it difficult for traditional single-objective or simple multi-objective evaluation methods to fully and accurately reflect the overall status of the system; on the other hand, there are often a lot of uncertainties and ambiguities in the evaluation process of complex systems. For example, some evaluation indicators are difficult to describe with precise numerical values, or are affected by multiple factors and present ambiguity. These uncertainties and ambiguities bring great difficulties to the evaluation work and easily lead to deviations or inaccuracies in the evaluation results.

[0003] At present, traditional evaluation methods often adopt a fixed weight allocation mechanism, which is unable to dynamically adjust the weight of each goal according to changes in system status, thereby reducing the timeliness and pertinence of the evaluation.

[0004] To this end, those skilled in the art have proposed a complex system evaluation method based on fuzzy multi-objective decision-making to solve the problems raised by the background technology. Summary of the invention

[0005] In order to solve the above technical problems, the present invention provides a complex system evaluation method based on fuzzy multi-objective decision-making to solve the problem that the evaluation method in the prior art often adopts a fixed weight allocation mechanism and cannot dynamically adjust the weight of each objective according to the changes in the system state, thereby reducing the timeliness and pertinence of the evaluation.

[0006] A complex system evaluation method based on fuzzy multi-objective decision making, including:

[0007] S1. Construct a multi-level and multi-dimensional complex system evaluation model; the model covers multiple interrelated and conflicting objectives such as performance, stability, cost-effectiveness, environmental impact and user satisfaction;

[0008] S2. Using fuzzy set theory, the indicators under each evaluation target are fuzzified to form a fuzzy evaluation indicator set to deal with the uncertainty and ambiguity in the evaluation process;

[0009] S3. Introduce a dynamic weight allocation mechanism, and use intelligent algorithms to dynamically adjust the weights of each goal based on the relative importance of each goal and the current system status to ensure the timeliness and pertinence of the evaluation;

[0010] S4. Apply the improved multi-objective decision-making algorithm to conduct a comprehensive analysis on the fuzzy evaluation index set and obtain the fuzzy comprehensive evaluation value of each scheme;

[0011] S5. Based on the fuzzy comprehensive evaluation value, put forward specific optimization suggestions or improvement strategies.

[0012] Preferably, in step S1, a system dynamics model is also included, and the interaction relationship between various factors within the system is more deeply understood by constructing a system flow chart and a state equation.

[0013] Preferably, in step S2, the fuzzy set theory is used to fuzzify the indicators under each evaluation target, including: using a triangular fuzzy number method to more accurately describe the uncertainty of the indicator, and combining a fuzzy clustering analysis method to perform more scientific fuzzy processing on the indicator.

[0014] Preferably, in step S3, it also includes using an intelligent optimization algorithm such as a genetic algorithm or a particle swarm optimization algorithm to dynamically adjust and optimize the weights.

[0015] Preferably, in step S4, the application of the improved multi-objective decision-making algorithm includes: combining fuzzy set theory and neural network model, constructing a fuzzy neural network multi-objective decision-making model, and introducing a support vector machine (SVM) algorithm to more accurately classify and predict the fuzzy evaluation index set.

[0016] Preferably, in step S5, the schemes are compared and evaluated more comprehensively based on the fuzzy comprehensive evaluation value combined with the entropy weight method.

[0017] Preferably, it also includes establishing a feedback mechanism to continuously optimize the evaluation model and evaluation method according to the actual application effect to ensure the adaptability and accuracy of the evaluation system.

[0018] A complex system evaluation system based on fuzzy multi-objective decision making, using the above-mentioned complex system evaluation method based on fuzzy multi-objective decision making, includes:

[0019] A construction module is used to construct a multi-level and multi-dimensional complex system evaluation model, which covers multiple interrelated and conflicting objectives such as performance, stability, cost-effectiveness, environmental impact and user satisfaction, and includes a system dynamics model to deeply understand the interaction between various factors within the system by constructing system flow diagrams and state equations;

[0020] The fuzzy processing module uses fuzzy set theory to perform fuzzy processing on the indicators under each evaluation target to form a fuzzy evaluation indicator set to deal with the uncertainty and ambiguity in the evaluation process. The fuzzy processing includes using a triangular fuzzy number method to more accurately describe the uncertainty of the indicator and combining a fuzzy clustering analysis method to perform a more scientific fuzzy processing on the indicator.

[0021] The weight allocation module introduces a dynamic weight allocation mechanism. Based on the relative importance of each goal and the current system status, it uses intelligent algorithms such as genetic algorithms or particle swarm optimization algorithms to dynamically adjust the weight of each goal to ensure the timeliness and pertinence of the evaluation.

[0022] A comprehensive evaluation module, which uses an improved multi-objective decision-making algorithm to comprehensively analyze the fuzzy evaluation index set to obtain a fuzzy comprehensive evaluation value of each scheme, wherein the improved multi-objective decision-making algorithm includes combining fuzzy set theory and neural network model to build a fuzzy neural network multi-objective decision-making model, and introducing a support vector machine (SVM) algorithm to more accurately classify and predict the fuzzy evaluation index set;

[0023] The optimization suggestion module proposes specific optimization suggestions or improvement strategies based on the fuzzy comprehensive evaluation value, and combines the entropy weight method to conduct a more comprehensive comparison and evaluation of the solutions;

[0024] Feedback optimization module establishes a feedback mechanism to continuously optimize the evaluation model and evaluation method based on the actual application effect to ensure the adaptability and accuracy of the evaluation system.

[0025] A processor is configured to execute the above-mentioned complex system evaluation method based on fuzzy multi-objective decision making.

[0026] A computer-readable storage medium stores a computer program, which implements the above-mentioned complex system evaluation method based on fuzzy multi-objective decision-making when executed by a processor.

[0027] Compared with the prior art, the present invention has the following beneficial effects:

[0028] 1. The present invention constructs a multi-level and multi-dimensional complex system evaluation model, covering multiple interrelated and conflicting objectives such as performance, stability, cost-effectiveness, environmental impact and user satisfaction; this comprehensive evaluation model can more accurately reflect the overall status of the complex system and avoid the limitations of traditional single-objective or simple multi-objective evaluation methods.

[0029] 2. The present invention utilizes fuzzy set theory to fuzzify the indicators under each evaluation target to form a fuzzy evaluation indicator set; this method can effectively deal with the uncertainty and ambiguity in the evaluation process and improve the accuracy and reliability of the evaluation.

[0030] 3. The present invention introduces a dynamic weight allocation mechanism, which uses an intelligent algorithm to dynamically adjust the weight of each goal based on the relative importance of each goal and the current system status. This dynamic evaluation method can ensure the timeliness and pertinence of the evaluation, making the evaluation results more in line with changes in the system status and the influence of the external environment.

[0031] 4. The present invention applies an improved multi-objective decision-making algorithm in the evaluation process, such as combining fuzzy set theory and neural network model to construct a fuzzy neural network multi-objective decision-making model, and introducing a support vector machine (SVM) algorithm to more accurately classify and predict the fuzzy evaluation index set; these advanced algorithms and technologies improve the scientificity and accuracy of the evaluation.

[0032] 5. The present invention also establishes a feedback mechanism to continuously optimize the evaluation model and evaluation method according to the actual application effect; this continuous optimization capability ensures the adaptability and accuracy of the evaluation system, enabling it to continuously adapt to the development and changes of complex systems. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] Figure 1 It is a flow chart of the complex system evaluation method based on fuzzy multi-objective decision-making of the present invention;

[0034] Figure 2 This is a framework diagram of the complex system evaluation system based on fuzzy multi-objective decision-making of the present invention. DETAILED DESCRIPTION

[0035] The following embodiments of the present invention are described in further detail in conjunction with the accompanying drawings and examples. The following examples are used to illustrate the present invention, but are not intended to limit the scope of the present invention.

[0036] Embodiment: The present invention provides a complex system evaluation method based on fuzzy multi-objective decision making, such as Figure 1 As shown, including:

[0037] S1. Construct a multi-level and multi-dimensional complex system evaluation model; the model covers multiple interrelated and conflicting objectives such as performance, stability, cost-effectiveness, environmental impact and user satisfaction;

[0038] S2. Using fuzzy set theory, the indicators under each evaluation target are fuzzified to form a fuzzy evaluation indicator set to deal with the uncertainty and ambiguity in the evaluation process;

[0039] S3. Introduce a dynamic weight allocation mechanism, and use intelligent algorithms to dynamically adjust the weights of each goal based on the relative importance of each goal and the current system status to ensure the timeliness and pertinence of the evaluation;

[0040] S4. Apply the improved multi-objective decision-making algorithm to conduct a comprehensive analysis on the fuzzy evaluation index set and obtain the fuzzy comprehensive evaluation value of each scheme;

[0041] S5. Based on the fuzzy comprehensive evaluation value, put forward specific optimization suggestions or improvement strategies.

[0042] From the above, we can see that the method constructs a multi-level and multi-dimensional evaluation model, uses fuzzy set theory to deal with the uncertainty and ambiguity in the evaluation process, introduces a dynamic weight allocation mechanism and an intelligent algorithm to optimize the weights, and applies an improved multi-objective decision-making algorithm for comprehensive analysis, and finally puts forward optimization suggestions; this method can more accurately reflect the overall situation of the complex system, ensure the timeliness and pertinence of the evaluation, improve the scientificity and accuracy of the evaluation, and provide strong support for the optimization and improvement of the complex system.

[0043] Furthermore, in step S1, a system dynamics model is also included, and the interaction relationship between various factors within the system is more deeply understood by constructing a system flow chart and a state equation. The state equation of the system dynamics model is as follows:

[0044] dx / dt=f(x,u,t);

[0045] in, x represents the system state variable, u represents the input variable, t Indicates time.

[0046] From the above, we can see that the introduction of system dynamics models has significant beneficial effects by constructing system flow charts and state equations to gain a deeper understanding of the interaction between various factors within the system. Specifically, system dynamics models can reveal the dynamic feedback mechanism between various components within a complex system, helping evaluators to more comprehensively grasp the operating laws and potential impacts of the system. It can not only enhance the accuracy and reliability of the evaluation model, but also provide a more solid theoretical basis for subsequent fuzzy processing, weight allocation and multi-objective decision-making. Through the analysis of system dynamics models, evaluators can construct evaluation models more scientifically, ensure the objectivity and effectiveness of the evaluation results, and provide strong support for the optimization decision-making of complex systems.

[0047] Furthermore, in step S2, the fuzzy set theory is used to perform fuzzification processing on the indicators under each evaluation target, including: using a triangular fuzzy number method to more accurately describe the uncertainty of the indicator, and combining a fuzzy clustering analysis method to perform more scientific fuzzification processing on the indicator;

[0048] The formula involved in the triangular fuzzy number method is as follows:

[0049]

[0050] Among them, a represents the lower limit of the fuzzy number, m represents the most likely value of the fuzzy number, and a represents the upper limit of the fuzzy number;

[0051] The objective function of the fuzzy clustering analysis is as follows:

[0052]

[0053] Among them, c represents the number of clusters, X i represents the i-th cluster, m i represents the center of the i-th cluster, x j Represents a data point.

[0054] From the above, we can see that by using fuzzy set theory to fuzzify the indicators under each evaluation target, and using triangular fuzzy number method and fuzzy cluster analysis method, we can more accurately describe the uncertainty of the indicators and scientifically perform fuzzy processing; this processing method not only improves the accuracy and reliability of the evaluation, but also helps to reveal the potential relationship and rules between indicators, and provide more comprehensive and in-depth information support for subsequent multi-objective decision-making; through the triangular fuzzy number method, the evaluator can more carefully characterize the uncertainty range of the indicator, and fuzzy cluster analysis can further explore the similarities and differences between indicators, thereby providing a more scientific basis for the construction and optimization of the evaluation model.

[0055] Furthermore, in step S3, it also includes using an intelligent optimization algorithm such as a genetic algorithm or a particle swarm optimization algorithm to dynamically adjust and optimize the weights;

[0056] The fitness function of the genetic algorithm is as follows:

[0057]

[0058] Among them, w i represents the weight of the i-th target, g i (x) represents the evaluation value of the i-th objective under scheme x;

[0059] The speed update formula of the particle swarm optimization algorithm is as follows:

[0060]

[0061] in, represents the velocity of the ith particle in the dth dimension, w represents the inertia weight, c 1 and c 2 represents the learning factor, r 1 and r 2 Represents a random number, represents the individual optimal position of the ith particle in the dth dimension, Represents the global optimal position of the entire particle swarm in the dth dimension.

[0062] From the above, it can be seen that by dynamically adjusting and optimizing the weights using intelligent optimization algorithms such as genetic algorithms or particle swarm optimization algorithms, the rationality and accuracy of weight distribution can be significantly improved; through the fitness function of the genetic algorithm and the speed update formula of the particle swarm optimization algorithm, the optimal weight combination can be efficiently searched, so that the weights of each evaluation target are more in line with the actual situation, thereby enhancing the comprehensive performance of the evaluation model; this approach of dynamically adjusting weights not only improves the objectivity and fairness of the evaluation, but also provides decision makers with a more scientific and reliable decision-making basis, which is helpful to achieve optimal management and decision-making of complex systems.

[0063] Further, in step S4, the application of the improved multi-objective decision-making algorithm includes: combining fuzzy set theory and neural network model to construct a fuzzy neural network multi-objective decision-making model, and introducing a support vector machine (SVM) algorithm to more accurately classify and predict the fuzzy evaluation index set;

[0064] The output formula of the fuzzy neural network is as follows:

[0065]

[0066] Among them, w i represents the weight of the i-th fuzzy rule, μ i (x) represents the membership function of the i-th fuzzy rule, and f represents the activation function of the neural network;

[0067] The decision function of the support vector machine is as follows:

[0068]

[0069] Among them, a i represents the Lagrange multiplier, K(x,x i ) represents the kernel function, and b represents the bias term.

[0070] From the above, it can be seen that the application of the improved multi-objective decision-making algorithm, combined with fuzzy set theory and neural network model to construct a fuzzy neural network multi-objective decision-making model, and introduced the support vector machine (SVM) algorithm, which can significantly improve the classification and prediction accuracy of the fuzzy evaluation index set; the fuzzy neural network enhances the model's ability to process complex and fuzzy information by integrating fuzzy rules and the characteristics of neural networks, while the support vector machine algorithm further improves the accuracy and reliability of the evaluation results with its powerful classification and prediction capabilities; the approach of combining multiple advanced algorithms not only improves the adaptability and robustness of the evaluation model, but also provides a more accurate and scientific basis for the optimization decision-making of complex systems, which helps to improve the effectiveness of decision-making and implementation effects.

[0071] Furthermore, in step S5, the schemes are more comprehensively compared and evaluated based on the fuzzy comprehensive evaluation value combined with the entropy weight method;

[0072] The weight calculation formula of the entropy weight method is as follows:

[0073]

[0074] Among them, H j Represents the entropy value of the i-th indicator.

[0075] From the above, it can be seen that by combining fuzzy comprehensive evaluation value and entropy weight method to conduct a more comprehensive comparison and evaluation of the schemes, the objectivity and scientificity of the evaluation can be significantly improved; the entropy weight method determines the weight of each indicator by calculating its entropy value, fully considering the amount of information provided by the indicator data, making the weight distribution more reasonable and accurate; this method not only considers the overall performance reflected by the fuzzy comprehensive evaluation value, but also further refines the relative importance of each indicator through the entropy weight method, providing a more accurate and comprehensive basis for the comprehensive comparison and evaluation of the schemes; by combining these two methods, the evaluator can have a deeper understanding of the advantages and disadvantages of each scheme, so as to make more wise and reasonable decisions.

[0076] Furthermore, it also includes establishing a feedback mechanism to continuously optimize the evaluation model and evaluation methods based on the actual application results to ensure the adaptability and accuracy of the evaluation system.

[0077] From the above, we can see that by establishing a feedback mechanism and continuously optimizing the evaluation model and evaluation method according to the actual application effect, we can ensure the adaptability and accuracy of the evaluation system, thereby continuously improving the effectiveness and reliability of the evaluation work; this feedback mechanism makes the evaluation process a dynamic cycle, which can promptly discover and solve problems and deficiencies in the evaluation process, and make necessary adjustments and improvements to the evaluation model and method according to actual conditions; through this continuous optimization, the evaluation system can better adapt to the changes and development of complex systems, maintain the timeliness and pertinence of its evaluation, and provide decision makers with more accurate and reliable evaluation results and decision support.

[0078] Working principle: First, construct an evaluation model covering multiple objectives such as performance, stability, cost-effectiveness, environmental impact and user satisfaction; then, use fuzzy set theory to fuzzify the indicators under each evaluation objective to form a fuzzy evaluation indicator set; then, introduce a dynamic weight allocation mechanism, and use an intelligent algorithm to dynamically adjust the weights according to the relative importance of the objectives and the system status; then, use an improved multi-objective decision-making algorithm that combines fuzzy set theory and neural network model to conduct a comprehensive analysis of the fuzzy evaluation indicator set to obtain a fuzzy comprehensive evaluation value; finally, put forward optimization suggestions based on the evaluation value, and continuously optimize the evaluation model and method through a feedback mechanism to adapt to system changes.

[0079] Furthermore, the beneficial effects of a complex system evaluation method based on fuzzy multi-objective decision-making in this embodiment and the current traditional evaluation method (comparative example) are compared to obtain the following table:

[0080]

[0081]

[0082] It can be seen from the above table that this embodiment is superior to the control example in terms of comprehensiveness, uncertainty processing, flexibility in weight allocation, scientific decision-making and effectiveness of optimization suggestions. This method is suitable for large-scale promotion and application.

[0083] A complex system evaluation system based on fuzzy multi-objective decision making, such as Figure 2 As shown, including:

[0084] A construction module is used to construct a multi-level and multi-dimensional complex system evaluation model, which covers multiple interrelated and conflicting objectives such as performance, stability, cost-effectiveness, environmental impact and user satisfaction, and includes a system dynamics model to deeply understand the interaction between various factors within the system by constructing system flow diagrams and state equations;

[0085] The fuzzy processing module uses fuzzy set theory to perform fuzzy processing on the indicators under each evaluation target to form a fuzzy evaluation indicator set to deal with the uncertainty and ambiguity in the evaluation process. The fuzzy processing includes using a triangular fuzzy number method to more accurately describe the uncertainty of the indicator and combining a fuzzy clustering analysis method to perform a more scientific fuzzy processing on the indicator.

[0086] The weight allocation module introduces a dynamic weight allocation mechanism. Based on the relative importance of each goal and the current system status, it uses intelligent algorithms such as genetic algorithms or particle swarm optimization algorithms to dynamically adjust the weight of each goal to ensure the timeliness and pertinence of the evaluation.

[0087] A comprehensive evaluation module, which uses an improved multi-objective decision-making algorithm to comprehensively analyze the fuzzy evaluation index set to obtain a fuzzy comprehensive evaluation value of each scheme, wherein the improved multi-objective decision-making algorithm includes combining fuzzy set theory and neural network model to build a fuzzy neural network multi-objective decision-making model, and introducing a support vector machine (SVM) algorithm to more accurately classify and predict the fuzzy evaluation index set;

[0088] The optimization suggestion module proposes specific optimization suggestions or improvement strategies based on the fuzzy comprehensive evaluation value, and combines the entropy weight method to conduct a more comprehensive comparison and evaluation of the solutions;

[0089] Feedback optimization module establishes a feedback mechanism to continuously optimize the evaluation model and evaluation method based on the actual application effect to ensure the adaptability and accuracy of the evaluation system.

[0090] The embodiment of the present application provides an electronic device, which is applicable to the above-mentioned complex system evaluation method based on fuzzy multi-objective decision-making, including:

[0091] Memory, used to protect computer programs and data;

[0092] Processor, used to run system programs.

[0093] The embodiment of the present application provides a computer storage medium, which is applicable to the above-mentioned complex system evaluation method system based on fuzzy multi-objective decision-making, and performs hierarchical confidentiality management on the above-mentioned system and data in accordance with confidentiality management requirements.

[0094] Those skilled in the art will appreciate that the embodiments of the present application may be provided as a system or a computer program product. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0095] The present application is described with reference to the flowcharts and / or block diagrams of the devices (systems) and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0096] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0097] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0098] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0099] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0100] Computer readable media include permanent and non-permanent, removable and non-removable media, and can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include transitory media such as modulated data signals and carrier waves.

[0101] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, commodity or device including the elements.

[0102] The embodiments of the present invention are provided for the purpose of illustration and description. Although the embodiments of the present invention have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limitations of the present invention. Ordinary technicians in this field can change, modify, replace and modify the above embodiments within the scope of the present invention.

Claims

1. A complex system evaluation method based on fuzzy multi-objective decision making, characterized by: include: S1. Construct a multi-level and multi-dimensional complex system evaluation model; the model covers multiple interrelated and conflicting objectives such as performance, stability, cost-effectiveness, environmental impact and user satisfaction; S2. Using fuzzy set theory, fuzzify the indicators under each evaluation target to form a fuzzy evaluation indicator set; S3, introduce a dynamic weight allocation mechanism, and use intelligent algorithms to dynamically adjust the weights of each goal based on the relative importance of each goal and the current system status; S4. Apply the improved multi-objective decision-making algorithm to conduct a comprehensive analysis on the fuzzy evaluation index set and obtain the fuzzy comprehensive evaluation value of each scheme; S5. Based on the fuzzy comprehensive evaluation value, put forward specific optimization suggestions and improvement strategies.

2. A complex system evaluation method based on fuzzy multi-objective decision making as claimed in claim 1, characterized in that: In step S1, a system dynamics model is also included, which can build a system flow chart and state equation to gain a deeper understanding of the interaction between various factors within the system.

3. The complex system evaluation method based on fuzzy multi-objective decision making as claimed in claim 1, characterized in that: In step S2, the fuzzy set theory is used to perform fuzzy processing on the indicators under each evaluation target, including: using the triangular fuzzy number method to more accurately describe the uncertainty of the indicator, and combining the fuzzy clustering analysis method to perform more scientific fuzzy processing on the indicator.

4. The complex system evaluation method based on fuzzy multi-objective decision making as claimed in claim 1, characterized in that: In step S3, it also includes using intelligent optimization algorithms such as genetic algorithms or particle swarm optimization algorithms to dynamically adjust and optimize the weights.

5. The complex system evaluation method based on fuzzy multi-objective decision making as claimed in claim 1, characterized in that: In step S4, the application of the improved multi-objective decision-making algorithm includes: combining fuzzy set theory and neural network model to construct a fuzzy neural network multi-objective decision-making model, and introducing a support vector machine algorithm to more accurately classify and predict the fuzzy evaluation index set.

6. The complex system evaluation method based on fuzzy multi-objective decision making as claimed in claim 1, characterized in that: In step S5, the schemes are compared and evaluated more comprehensively based on the fuzzy comprehensive evaluation value combined with the entropy weight method.

7. The complex system evaluation method based on fuzzy multi-objective decision making as claimed in claim 1, characterized in that: It also includes establishing a feedback mechanism to continuously optimize the evaluation model and evaluation methods based on actual application results to ensure the adaptability and accuracy of the evaluation system.

8. A complex system evaluation system based on fuzzy multi-objective decision making, characterized by: A complex system evaluation method based on fuzzy multi-objective decision making as claimed in any one of claims 1 to 7 is used, comprising: A construction module is used to construct a multi-level and multi-dimensional complex system evaluation model, which covers multiple interrelated and conflicting objectives such as performance, stability, cost-effectiveness, environmental impact and user satisfaction, and includes a system dynamics model to deeply understand the interaction between various factors within the system by constructing system flow diagrams and state equations; The fuzzy processing module uses fuzzy set theory to perform fuzzy processing on the indicators under each evaluation target to form a fuzzy evaluation indicator set, wherein the fuzzy processing includes using a triangular fuzzy number method to more accurately describe the uncertainty of the indicator and combining a fuzzy clustering analysis method to perform more scientific fuzzy processing on the indicator; The weight allocation module introduces a dynamic weight allocation mechanism, which uses intelligent algorithms such as genetic algorithms or particle swarm optimization algorithms to dynamically adjust the weights of each goal based on the relative importance of each goal and the current system status; A comprehensive evaluation module, which uses an improved multi-objective decision-making algorithm to comprehensively analyze the fuzzy evaluation index set to obtain a fuzzy comprehensive evaluation value of each scheme, wherein the improved multi-objective decision-making algorithm includes combining fuzzy set theory and neural network model to build a fuzzy neural network multi-objective decision-making model, and introducing a support vector machine algorithm to more accurately classify and predict the fuzzy evaluation index set; The optimization suggestion module proposes specific optimization suggestions or improvement strategies based on the fuzzy comprehensive evaluation value, and combines the entropy weight method to conduct a more comprehensive comparison and evaluation of the solutions; Feedback optimization module establishes a feedback mechanism to continuously optimize the evaluation model and evaluation method based on the actual application effect.

9. A processor, characterized in that: The method is configured to execute the complex system evaluation method based on fuzzy multi-objective decision making according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: A computer program is stored thereon, and when the computer program is executed by a processor, the complex system evaluation method based on fuzzy multi-objective decision-making described in any one of claims 1 to 7 is implemented.

Images