A method for comprehensive evaluation and decision of engine conceptual design multiple schemes

Abstract

This invention relates to the field of aircraft propulsion system technology, and discloses a comprehensive evaluation and decision-making method for multiple engine concept design schemes. By introducing game theory concepts, it achieves deep coupling of subjective and objective weights, and combines the maximum entropy criterion and deviation penalty factor to seek the optimal compromise between expert experience judgment and the inherent laws of data, thereby obtaining the optimal combination of weights. Based on this, a quantifiable comprehensive evaluation index is constructed to achieve a comprehensive and objective assessment and ranking of engine concept design schemes. Simultaneously, the Euclidean distance considering the standard deviation of technical indicators is introduced into the ranking of alternative schemes, enhancing the discriminative power and robustness of the evaluation results, effectively solving the problem of the difficulty in comprehensively balancing multiple technical indicators such as performance, structure, and cost. This invention can identify and screen the most promising innovative schemes, providing decision support for subsequent component design, thereby improving the overall engine performance and reasonably controlling R&D costs.

Description

Technical Field

[0001] This invention relates to the field of aircraft propulsion system technology, and discloses a method for comprehensive evaluation and decision-making of multiple schemes in engine conceptual design. Background Technology

[0002] In the conceptual design phase of engine development, design schemes need to be constructed within a high-dimensional parameter space, including pressure ratio and temperature, while comprehensively balancing multiple technical indicators such as performance, structure, and cost. Because this stage involves a wide range of design dimensions, the selection of the overall scheme in the early stages often determines more than 70% of the subsequent cost structure. Therefore, making scientific and forward-looking decisions at the starting point of equipment development is crucial.

[0003] However, traditional methods rely excessively on expert experience and analogies with existing products, lacking systematic and rapid evaluation and optimization capabilities. This not only limits the scope of exploration and protracts the process but also makes it difficult to effectively balance multiple objectives, easily overlooking potentially innovative solutions. Faced with numerous design factors and complex evaluation indicators, there is an urgent need to integrate various technical indicators into a quantifiable evaluation metric to rank and select the best alternatives, assisting decision-makers in identifying the design path that best meets engineering requirements. Summary of the Invention

[0004] The purpose of this invention is to provide a comprehensive evaluation and decision-making method for multiple engine concept design schemes, which can achieve a comprehensive and objective evaluation and ranking of engine concept design schemes, and enhance the discrimination and robustness of the evaluation results, effectively solving the problem of the difficulty in comprehensively balancing multiple technical indicators such as performance, structure and cost.

[0005] To achieve the above-mentioned technical effects, the technical solution adopted by the present invention is as follows:

[0006] A method for comprehensive evaluation and decision-making of multiple schemes in engine concept design, including: S1. Obtain multiple technical indicators from multiple concept schemes of the engine, and perform positive standardization processing on the technical indicators according to the attribute value of each technical indicator to construct a positive standardization matrix of the engine concept schemes; the technical indicators include thrust, power extraction, cost, fuel consumption rate, and efficiency. S2. Obtain the subjective scores of multiple decision-makers on the importance of each technical indicator, and use the fuzzy weighting method to analyze the normalized fuzzy weights of each technical indicator. S3. Determine the information entropy of each technical indicator based on the attribute values ​​of each technical indicator in all conceptual schemes, and obtain the normalized entropy weight of each technical indicator based on the information entropy analysis. S4. A linear weighted composite initial model is constructed using the game theory combined weighting method, based on the normalized fuzzy weight and normalized entropy weight of each technical indicator. The maximum entropy criterion is used as a regularization constraint to construct the optimization function of the linear weighted composite initial model. The optimization objective is to minimize the output value of the optimization function, and to optimize the weighting coefficients of the normalized fuzzy weight and normalized entropy weight in the linear weighted composite initial model. S5. Normalize the weighted coefficients obtained by optimization, update the initial linear weighted comprehensive weight model based on the normalized weighted coefficients and the introduced deviation penalty factor, and obtain the function expression of the linear weighted comprehensive weight analysis model. Use the expression to analyze and obtain the game combination weight of each technical indicator. S6. Use the game combination weights of each technical indicator to weight the positive and standardized matrices of the corresponding technical indicators, construct a weighted attribute matrix of technical indicators, and extract the maximum value, minimum value and standard deviation of the weighted attribute of each technical indicator from the weighted matrix of the technical indicators. S7. Using the standard deviation of the weighted attribute of each technical indicator as an adjustment factor, construct the maximum adaptive weighted distance between the weighted attribute values ​​of all technical indicators and the maximum value of the weighted attribute in each conceptual scheme, and the minimum adaptive weighted distance between the weighted attribute values ​​of all technical indicators and the minimum value of the weighted attribute in each conceptual scheme. S8. Based on the maximum and minimum adaptive weighted distances in each conceptual scheme, analyze and obtain the proportion of the minimum adaptive weighted distance of the corresponding conceptual scheme, and select the conceptual schemes with the proportions greater than the preset ratio threshold as candidate schemes for engine conceptual design.

[0007] Furthermore, the positively normalized matrix Z of the engine concept scheme constructed in S1 is:

[0008] in For the first The first of the conceptual schemes The values ​​of each technical indicator after positive standardization. , To obtain the total number of conceptual schemes, , The total number of technical indicators; If the first The first conceptual scheme If a technical indicator is a positive indicator, then , For the first The first conceptual scheme The attribute values ​​of each technical indicator, The first of all conceptual schemes The maximum attribute value of each technical indicator. The first of all conceptual schemes Minimum attribute value of each technical indicator; If the first The first conceptual scheme If a technical indicator is negative, then ; If the first The first conceptual scheme If a technical indicator is considered a suitable indicator, then... , For the first The lower limit of the appropriate range given by a technical indicator. For the first The upper limit of the appropriate range given by each technical indicator.

[0009] Furthermore, the process of analyzing the normalized fuzzy weights of various technical indicators using the fuzzy weighting method in S2 includes: According to the decision-maker to the The triangular fuzzy number specified by the technical indicator is used to analyze and obtain the opinions of all decision-makers on the first... Initial fuzzy weights of each technical indicator ,in , , For all decision-makers, the first The average of the triangular fuzzy numbers of each technical indicator; Using the area center method to divide the first Initial fuzzy weights of each technical indicator Convert to the optimal unfuzzy performance BNP value ; Based on all technical indicators, the optimal non-fuzzy performance BNP value is used for the first... The optimal non-fuzzy performance BNP value of the first technical indicator is normalized to obtain the second... Normalized fuzzy weights of individual technical indicators ,in For risk preference factors, The value range is 0 to 1. For the given reference weights, This refers to the total number of technical indicators.

[0010] Furthermore, the method for obtaining the normalized entropy weights for each technical indicator in S3 includes: The information entropy of each technical indicator is determined based on the attribute values ​​of each technical indicator in all conceptual schemes. ,in For the first Information entropy of a technical indicator For coefficients, ,like Then let Set to 0; The normalized entropy weight of each technical indicator is obtained based on the information entropy analysis of the technical indicators. ,in For the first Normalized entropy weights for each technical indicator.

[0011] Furthermore, in S4, a game-theoretic combinatorial weighting method is used to construct an initial linear weighted composite weight model based on normalized fuzzy weights and normalized entropy weights for each technical indicator. , , The first The initial model coefficients of the linear weighted composite weights of the technical indicators. For the first Normalized fuzzy weights for each technical indicator, For the first Normalized entropy weights for each technical indicator.

[0012] Furthermore, in S4, the maximum entropy criterion is used as a regularization constraint to construct the optimization function for the initial linear weighted composite weight model. ,in For Lagrange multipliers, The value range is 0.1 to 0.5. This refers to the total number of technical indicators.

[0013] Furthermore, the game combination weights for each technical indicator in S5 are: ,in For the first The game-theoretic combination weights of various technical indicators, , These are the weighting coefficients after optimization and normalization. , , As the deviation penalty factor, , This is an empirical adjustment coefficient. The value range is 0.1 to 0.3. This is the preset weight adjustment step size.

[0014] Furthermore, the weighted attribute matrix for technical indicators in S6 is constructed as follows:

[0015] Where X is the weighted attribute matrix of technical indicators, For the first The first conceptual scheme The weighted attribute values ​​of each technical indicator.

[0016] Furthermore, in step S7, the maximum adaptive weighted distance between the weighted attribute values ​​and the maximum weighted attribute values ​​of all technical indicators in the conceptual scheme is calculated. ,in For the first The maximum adaptive weighted distance corresponding to each conceptual scheme The first of all conceptual schemes The maximum weighted attribute value of each technical indicator. The first of all conceptual schemes The standard deviation of the weighted attribute values ​​of each technical indicator. To prevent extremely small positive numbers with a denominator of zero, The value range is 0.00001 to 0.001; The minimum adaptive weighted distance between the weighted attribute values ​​of all technical indicators and the minimum value of the weighted attribute in the conceptual scheme. ,in For the first The minimum adaptive weighted distance corresponding to each conceptual scheme The first of all conceptual schemes The minimum weighted attribute value of each technical indicator.

[0017] Furthermore, the proportion of the minimum adaptive weighted distance in the conceptual scheme of S8 .

[0018] Compared with existing technologies, the beneficial effects of this invention are as follows: By introducing game theory concepts, this invention achieves a deep integration of subjective and objective weights, and introduces a deviation penalty factor based on the maximum entropy criterion, seeking the optimal compromise between expert experience judgment and the inherent laws of data, thereby obtaining the optimal combined weights. Based on this, by combining the improved Euclidean distance of the standard deviation of technical indicators, the Euclidean distance between each alternative scheme and the positive maximum and negative minimum values ​​is obtained, integrating multiple complex technical indicators in engine conceptual design into a specific evaluation index, thereby comprehensively and objectively evaluating and ranking the performance of the schemes. This method can effectively handle the challenges of numerous design factors and complex evaluation indicators, scientifically and rationally selecting the best conceptual design scheme that meets engineering requirements, providing a reliable basis for subsequent detailed component scheme design, and has the advantages of high evaluation efficiency and minimal influence from subjective factors. It effectively avoids the technical difficulty of intuitively selecting the optimal scheme due to the inconsistent performance of each scheme on different technical indicators. Attached Figure Description

[0019] Figure 1 This is a flowchart of the comprehensive evaluation and decision-making method for multiple schemes of engine concept design in Example 1 or 2. Detailed Implementation

[0020] The present invention will now be described in further detail with reference to the embodiments and accompanying drawings. However, this should not be construed as limiting the scope of the above-described subject matter of the present invention to the following embodiments; all technologies implemented based on the content of the present invention fall within the scope of the present invention.

[0021] Example 1 See Figure 1 A method for comprehensive evaluation and decision-making of multiple schemes in engine concept design, including: S1. Obtain multiple technical indicators from multiple concept schemes of the engine, and perform positive standardization processing on the technical indicators according to the attribute value of each technical indicator to construct a positive standardization matrix of the engine concept schemes; the technical indicators include thrust, power extraction, cost, fuel consumption rate, and efficiency. S2. Obtain the subjective scores of multiple decision-makers on the importance of each technical indicator, and use the fuzzy weighting method to analyze the normalized fuzzy weights of each technical indicator. S3. Determine the information entropy of each technical indicator based on the attribute values ​​of each technical indicator in all conceptual schemes, and obtain the normalized entropy weight of each technical indicator based on the information entropy analysis. S4. A linear weighted composite initial model is constructed using the game theory combined weighting method, based on the normalized fuzzy weight and normalized entropy weight of each technical indicator. The maximum entropy criterion is used as a regularization constraint to construct the optimization function of the linear weighted composite initial model. The optimization objective is to minimize the output value of the optimization function, and to optimize the weighting coefficients of the normalized fuzzy weight and normalized entropy weight in the linear weighted composite initial model. S5. Normalize the weighted coefficients obtained by optimization, update the initial linear weighted comprehensive weight model based on the normalized weighted coefficients and the introduced deviation penalty factor, and obtain the function expression of the linear weighted comprehensive weight analysis model. Use the expression to analyze and obtain the game combination weight of each technical indicator. S6. Use the game combination weights of each technical indicator to weight the positive and standardized matrices of the corresponding technical indicators, construct a weighted attribute matrix of technical indicators, and extract the maximum value, minimum value and standard deviation of the weighted attribute of each technical indicator from the weighted matrix of the technical indicators. S7. Using the standard deviation of the weighted attribute of each technical indicator as an adjustment factor, construct the maximum adaptive weighted distance between the weighted attribute values ​​of all technical indicators and the maximum value of the weighted attribute in each conceptual scheme, and the minimum adaptive weighted distance between the weighted attribute values ​​of all technical indicators and the minimum value of the weighted attribute in each conceptual scheme. S8. Based on the maximum and minimum adaptive weighted distances in each conceptual scheme, analyze and obtain the proportion of the minimum adaptive weighted distance of the corresponding conceptual scheme, and select the conceptual schemes with the proportions greater than the preset ratio threshold as candidate schemes for engine conceptual design.

[0022] In this embodiment, game theory is introduced to achieve a deep integration of subjective and objective weights. A deviation penalty factor is introduced based on the maximum entropy criterion to seek the optimal compromise between expert judgment and the inherent laws of data, thereby obtaining the optimal combined weights. Based on this, a quantifiable comprehensive evaluation index is constructed to achieve a comprehensive and objective assessment and ranking of engine concept design schemes. Simultaneously, Euclidean distance considering the standard deviation of technical indicators is introduced into the ranking of candidate schemes, effectively improving the discriminative power and robustness of the evaluation results, thus solving the problem of the difficulty in comprehensively balancing multiple technical indicators such as performance, structure, and cost. This invention can identify and screen the most promising innovative schemes and effectively avoid the technical difficulty of intuitively selecting the optimal scheme due to the inconsistent performance of various schemes on different technical indicators. It provides scientific and forward-looking decision support for subsequent component design, improving the overall performance of the engine from the design source and reasonably controlling R&D costs.

[0023] Example 2 See Figure 1 This embodiment takes the conceptual design of a certain type of engine development as an example to explain in detail the steps of the multi-scheme comprehensive evaluation and decision-making method for engine conceptual design of the present invention. The specific process is as follows: S1. Obtain multiple technical indicators from multiple concept schemes of the engine, and perform positive standardization processing on the technical indicators according to the attribute value of each technical indicator to construct a positive standardization matrix of the engine concept schemes; the technical indicators include thrust, power extraction, cost, fuel consumption rate, and efficiency. In this embodiment, the engine concept scheme set is assumed to be: The set of technical indicators is Then the evaluation matrix D for the engine system scheme evaluation problem can be obtained:

[0024] In the formula, For the first The first of the conceptual schemes The attribute values ​​of each technical indicator, , To obtain the total number of conceptual schemes, , This refers to the total number of technical indicators.

[0025] There are generally three types of indicators: Positive indicators, the higher the attribute value, the better, such as thrust, power extraction, etc. Negative indicators, the smaller the attribute value, the better, such as cost, fuel consumption rate, etc. Appropriate indicators, such as the efficiency of compressors and turbines, are best when the attribute values ​​are within a certain range.

[0026] Therefore, the process for positively standardizing each technical indicator in this embodiment is as follows: If the first The first conceptual scheme If a technical indicator is a positive indicator, then , For the first The first conceptual scheme The attribute values ​​of each technical indicator, The first of all conceptual schemes The maximum attribute value of each technical indicator. The first of all conceptual schemes Minimum attribute value of each technical indicator; If the first The first conceptual scheme If a technical indicator is negative, then ; If the first The first conceptual scheme If a technical indicator is considered a suitable indicator, then... , For the first The lower limit of the appropriate range given by a technical indicator. For the first The upper limit of the appropriate range given by each technical indicator.

[0027] Therefore, the positive normalization matrix Z of the constructed engine concept scheme is:

[0028] in For the first The first of the conceptual schemes The values ​​of each technical indicator after positive standardization.

[0029] S2. Obtain the subjective scores of multiple decision-makers on the importance of each technical indicator, and use the fuzzy weighting method to analyze the normalized fuzzy weights of each technical indicator. The fuzzy weighting method uses fuzzy numbers to reflect the decision-maker's subjective emphasis on each technical indicator, and then determines the weight of each attribute. Fuzzy numbers are a fuzzy set that expresses fuzzy information and the degree of fuzzy preference of the decision-maker. This embodiment uses triangular fuzzy numbers for explanation.

[0030] 2.1 Triangular Fuzzy Number Decision-makers categorize the importance of technical indicators into five levels: very low (VL), low (L), medium (M), high (H), and very high (VH). Each level of importance corresponds to a set of normalized triangular fuzzy numbers, as shown in Table 1.

[0031] Table 1. Triangular Fuzzy Number Table Corresponding to the Importance of Technical Indicators

[0032] 2.2 Optimal Unfuzzy Performance If there are M decision-makers, the k-th decision-maker designates the first... The importance of each technical indicator was determined by the number of... The fuzzy weights (triangular fuzzy numbers) of each technical indicator are: Then all decision-makers will have a say in the first Fuzzy weights of technical indicators ,in , , For all decision-makers, the first The average of the triangular fuzzy numbers of each technical indicator; Using the area center method to divide the first Initial fuzzy weights of each technical indicator Convert to the optimal unfuzzy performance BNP value .

[0033] 3.3 Fuzzy Weights The optimal nonfuzzy performance value reflects the importance of the technical specifications of the design scheme. The optimal nonfuzzy performance value is normalized to obtain the first... Fuzzy weights for each technical indicator. Subjective weights, once determined, are treated as fixed inputs, lacking consideration for the reliability of weight reassignment. Therefore, a risk preference factor can be introduced. The value ranges from 0 to 1, representing the decision-maker's confidence level in the subjective weights. The optimal unfuzzy performance (BNP) value among all technical indicators is used to evaluate the... The optimal non-fuzzy performance BNP value of the first technical indicator is normalized to obtain the second... Normalized fuzzy weights of individual technical indicators ,in For risk preference factors, The value range is 0 to 1. The given reference weights, based on experience or historical data, are used to ensure that the weights themselves have adjustable confidence boundaries.

[0034] S3. Determine the information entropy of each technical indicator based on the attribute values ​​of each technical indicator in all conceptual schemes, and obtain the normalized entropy weight of each technical indicator based on the information entropy analysis. Information entropy represents a measure of the uncertainty of a random variable, used to express the average amount of information after eliminating redundant information. The entropy weight method determines the information entropy of each technical indicator based on the evaluation data of different schemes. The greater the difference in the entropy attribute value of a certain technical indicator among the schemes, the smaller the information entropy, the lower the disorder of the information, the greater the utility value of the information, and the greater the weight of the attribute. Conversely, the smaller the difference in a certain technical indicator among the schemes, the greater the information entropy, the higher the disorder of the information, the lower the utility of the information, and the smaller the weight of the attribute.

[0035] The information entropy of each technical indicator is determined based on the attribute values ​​of each technical indicator in all conceptual schemes. ,in For the first Information entropy of a technical indicator For coefficients, ,like Then let Set to 0; The normalized entropy weight of each technical indicator is obtained based on the information entropy analysis of the technical indicators. , For the first The normalized entropy weights of each technical indicator, and satisfying .

[0036] S4. A linear weighted composite initial model is constructed using the game theory combined weighting method, based on the normalized fuzzy weight and normalized entropy weight of each technical indicator. The maximum entropy criterion is used as a regularization constraint to construct the optimization function of the linear weighted composite initial model. The optimization objective is to minimize the output value of the optimization function, and to optimize the weighting coefficients of the normalized fuzzy weight and normalized entropy weight in the linear weighted composite initial model. In this embodiment, an initial linear weighted comprehensive weight model is constructed based on the normalized fuzzy weight and normalized entropy weight of each technical indicator. , , The first The initial model coefficients of the linear weighted composite weights of the technical indicators. For the first Normalized fuzzy weights for each technical indicator, For the first Normalized entropy weights for each technical indicator.

[0037] The maximum entropy criterion is introduced as a regularization constraint in the initial model to construct the optimization function of the linearly weighted composite initial model. ,in For Lagrange multipliers, The value ranges from 0.1 to 0.5, and is used to control the strength of entropy regularization. While minimizing the deviation from subjective and objective weights, it maximizes the information content of the combined weights, ensuring that the final weights respect expert experience and data characteristics while avoiding evaluation distortion caused by weight distribution "abnormalities." With the minimum output value of the optimization function as the optimization objective, the weighting coefficients of the normalized fuzzy weights and normalized entropy weights in the initial linear weighted composite weight model are optimized, and the solution is obtained. , .

[0038] S5. Normalize the weighted coefficients obtained by optimization, update the initial linear weighted comprehensive weight model based on the normalized weighted coefficients and the introduced deviation penalty factor, and obtain the function expression of the linear weighted comprehensive weight analysis model. Use the expression to analyze and obtain the game combination weight of each technical indicator. In the solution , Afterwards, , Normalization is performed, and the weighting coefficients after normalization are calculated. , , , ; Then, a deviation penalty factor is introduced. The combination coefficients are dynamically adjusted, and the final game-theoretic combination weights of the technical indicators are: ,in For the first The game-theoretic combination weights of various technical indicators, , These are the weighting coefficients after optimization and normalization. , , As the deviation penalty factor, , This is an empirical adjustment coefficient. The value range is 0.1 to 0.3. With a preset weight adjustment step size, this mechanism allows indicators with significant discrepancies to receive additional adjustments during the combination process, avoiding information loss caused by simple linear weighting.

[0039] S6. Use the game combination weights of each technical indicator to weight the positive and standardized matrices of the corresponding technical indicators, construct a weighted attribute matrix of technical indicators, and extract the maximum value, minimum value and standard deviation of the weighted attribute of each technical indicator from the weighted matrix of the technical indicators. In this embodiment, the weighted attribute matrix of the constructed technical indicators is as follows:

[0040] Where X is the weighted attribute matrix of technical indicators, For the first The first conceptual scheme The weighted attribute values ​​of each technical indicator.

[0041] Then calculate the positive maximum and negative minimum values, as well as the standard deviation of the weighted attributes: The positive maximum value is composed of the maximum value of each column of the weighted attribute matrix, which is the best virtual object among all technical indicators.

[0042] The negative minimum value is composed of the minimum value of each column of the weighted attribute matrix, which is the virtual object with the worst performance across all technical indicators.

[0043]

[0044]

[0045] In the formula, It is the positive maximum value. It is the negative minimum value;

[0046] The first of all conceptual schemes The average of the weighted attribute values ​​of each technical indicator.

[0047] S7. Using the standard deviation of the weighted attribute of each technical indicator as an adjustment factor, construct the maximum adaptive weighted distance between the weighted attribute values ​​of all technical indicators and the maximum value of the weighted attribute in each conceptual scheme, and the minimum adaptive weighted distance between the weighted attribute values ​​of all technical indicators and the minimum value of the weighted attribute in each conceptual scheme. Traditional Euclidean distance does not consider the impact of the dispersion of data distribution for each indicator on the distance metric. This embodiment introduces the standard deviation of the indicators. As a regulating factor, an adaptive weighted distance is constructed: The maximum adaptive weighted distance between the weighted attribute values ​​and the maximum value of all technical indicators in the conceptual scheme. ,in For the first The maximum adaptive weighted distance corresponding to each conceptual scheme The first of all conceptual schemes The maximum weighted attribute value of each technical indicator. The first of all conceptual schemes The standard deviation of the weighted attribute values ​​of each technical indicator. To prevent extremely small positive numbers with a denominator of zero, The value range is 0.00001 to 0.001; The minimum adaptive weighted distance between the weighted attribute values ​​of all technical indicators and the minimum value of the weighted attribute in the conceptual scheme. ,in For the first The minimum adaptive weighted distance corresponding to each conceptual scheme The first of all conceptual schemes The minimum weighted attribute value of each technical indicator; this is achieved by introducing... It enhances the ability to differentiate the degree of dispersion in the distribution of indicator data.

[0048] S8. Based on the maximum adaptive weighted distance and the minimum adaptive weighted distance in each concept scheme, analyze and obtain the proportion of the minimum adaptive weighted distance of the corresponding concept scheme, and select the concept scheme with the proportion greater than the preset ratio threshold as the candidate scheme for engine concept design. In this embodiment, the proportion of the minimum adaptive weighted distance of the conceptual scheme is... , This can characterize the proximity of the conceptual solution to the negative minimum of the technical indicator. A larger value indicates that the solution is further from the negative minimum and the solution's performance is better, and vice versa. This invention can be based on... The quantitative results of the values ​​are used to comprehensively rank the alternative schemes in order to select the optimal scheme as the basis for subsequent detailed component scheme design.

[0049] The above are merely preferred embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A method for comprehensive evaluation and decision-making of multiple schemes in engine conceptual design, characterized in that, include: S1. Obtain multiple technical indicators from multiple concept schemes of the engine, and perform positive standardization processing on the technical indicators according to the attribute value of each technical indicator to construct a positive standardization matrix of the engine concept schemes; the technical indicators include thrust, power extraction, cost, fuel consumption rate, and efficiency. S2. Obtain the subjective scores of multiple decision-makers on the importance of each technical indicator, and use the fuzzy weighting method to analyze the normalized fuzzy weights of each technical indicator. S3. Determine the information entropy of each technical indicator based on the attribute values ​​of each technical indicator in all conceptual schemes, and obtain the normalized entropy weight of each technical indicator based on the information entropy analysis. S4. A linear weighted composite initial model is constructed using the game theory combined weighting method, based on the normalized fuzzy weight and normalized entropy weight of each technical indicator. The maximum entropy criterion is used as a regularization constraint to construct the optimization function of the linear weighted composite initial model. The optimization objective is to minimize the output value of the optimization function, and to optimize the weighting coefficients of the normalized fuzzy weight and normalized entropy weight in the linear weighted composite initial model. S5. Normalize the weighted coefficients obtained by optimization, update the initial linear weighted comprehensive weight model based on the normalized weighted coefficients and the introduced deviation penalty factor, and obtain the function expression of the linear weighted comprehensive weight analysis model. Use the expression to analyze and obtain the game combination weight of each technical indicator. S6. Use the game combination weights of each technical indicator to weight the positive and standardized matrices of the corresponding technical indicators, construct a weighted attribute matrix of technical indicators, and extract the maximum value, minimum value and standard deviation of the weighted attribute of each technical indicator from the weighted matrix of the technical indicators. S7. Using the standard deviation of the weighted attribute of each technical indicator as an adjustment factor, construct the maximum adaptive weighted distance between the weighted attribute values ​​of all technical indicators and the maximum value of the weighted attribute in each conceptual scheme, and the minimum adaptive weighted distance between the weighted attribute values ​​of all technical indicators and the minimum value of the weighted attribute in each conceptual scheme. S8. Based on the maximum and minimum adaptive weighted distances in each conceptual scheme, analyze and obtain the proportion of the minimum adaptive weighted distance of the corresponding conceptual scheme, and select the conceptual schemes with the proportions greater than the preset ratio threshold as candidate schemes for engine conceptual design.

2. The method for comprehensive evaluation and decision-making of multiple schemes in engine concept design according to claim 1, characterized in that, The positively normalized matrix Z of the engine concept scheme constructed in S1 is: in For the first The first of the conceptual schemes The values ​​of each technical indicator after positive standardization. , To obtain the total number of conceptual schemes, , The total number of technical indicators; If the first The first conceptual scheme If a technical indicator is a positive indicator, then , For the first The first conceptual scheme The attribute values ​​of each technical indicator, The first of all conceptual schemes The maximum attribute value of each technical indicator. The first of all conceptual schemes Minimum attribute value of each technical indicator; If the first The first conceptual scheme If a technical indicator is negative, then ; If the first The first conceptual scheme If a technical indicator is considered a suitable indicator, then... , For the first The lower limit of the appropriate range given by a technical indicator. For the first The upper limit of the appropriate range given by each technical indicator.

3. The method for comprehensive evaluation and decision-making of multiple schemes in engine concept design according to claim 1, characterized in that, The process of analyzing the normalized fuzzy weights of various technical indicators using the fuzzy weighting method in S2 includes: According to the decision-maker to the The triangular fuzzy number specified by the technical indicator is used to analyze and obtain the opinions of all decision-makers on the first... Initial fuzzy weights of each technical indicator ,in , , For all decision-makers, the first The average of the triangular fuzzy numbers of each technical indicator; Using the area center method to divide the first Initial fuzzy weights of each technical indicator Convert to the optimal unfuzzy performance BNP value ; Based on all technical indicators, the optimal non-fuzzy performance BNP value is used for the first... The optimal non-fuzzy performance BNP value of the first technical indicator is normalized to obtain the second... Normalized fuzzy weights of individual technical indicators ,in For risk preference factors, The value range is 0 to 1. Given the reference weights, This refers to the total number of technical indicators.

4. The method for comprehensive evaluation and decision-making of multiple schemes in engine concept design according to claim 2, characterized in that, The methods for obtaining the normalized entropy weights for each technical indicator in S3 include: The information entropy of each technical indicator is determined based on the attribute values ​​of each technical indicator in all conceptual schemes. ,in For the first Information entropy of a technical indicator For coefficients, ,like Then let Set to 0; The normalized entropy weight of each technical indicator is obtained based on the information entropy analysis of the technical indicators. ,in For the first Normalized entropy weights for each technical indicator.

5. The method for comprehensive evaluation and decision-making of multiple schemes in engine concept design according to claim 1, characterized in that, In S4, a game-theoretic combinatorial weighting method is used to construct an initial linear weighted composite weight model based on normalized fuzzy weights and normalized entropy weights for each technical indicator. , , The first The initial model coefficients of the linear weighted composite weights of the technical indicators. For the first Normalized fuzzy weights for each technical indicator, For the first Normalized entropy weights for each technical indicator.

6. The method for comprehensive evaluation and decision-making of multiple schemes in engine concept design according to claim 5, characterized in that, In S4, the maximum entropy criterion is used as a regularization constraint to construct the optimization function of the initial linear weighted composite model. ,in For Lagrange multipliers, The value range is 0.1 to 0.

5. This refers to the total number of technical indicators.

7. The method for comprehensive evaluation and decision-making of multiple schemes in engine concept design according to claim 5, characterized in that, The game combination weight of each technical indicator in S5 is: ,in For the first The game-theoretic combination weights of various technical indicators, , These are the weighting coefficients after optimization and normalization. , , As the deviation penalty factor, , This is an empirical adjustment coefficient. The value range is 0.1 to 0.

3. This is the preset weight adjustment step size.

8. The method for comprehensive evaluation and decision-making of multiple schemes in engine concept design according to claim 7, characterized in that, The weighted attribute matrix for technical indicators in S6 is constructed as follows: Where X is the weighted attribute matrix of technical indicators, For the first The first conceptual scheme The weighted attribute values ​​of each technical indicator.

9. The method for comprehensive evaluation and decision-making of multiple schemes in engine concept design according to claim 8, characterized in that, In step S7, the maximum adaptive weighted distance between the weighted attribute values ​​and the maximum weighted attribute values ​​of all technical indicators in the conceptual scheme is calculated. ,in For the first The maximum adaptive weighted distance corresponding to each conceptual scheme The first of all conceptual schemes The maximum weighted attribute value of each technical indicator. The first of all conceptual schemes The standard deviation of the weighted attribute values ​​of each technical indicator. To prevent extremely small positive numbers with a denominator of zero, The value range is 0.00001 to 0.001; The minimum adaptive weighted distance between the weighted attribute values ​​of all technical indicators and the minimum value of the weighted attribute in the conceptual scheme. ,in For the first The minimum adaptive weighted distance corresponding to each conceptual scheme The first of all conceptual schemes The minimum weighted attribute of each technical indicator.

10. The method for comprehensive evaluation and decision-making of multiple schemes in engine concept design according to claim 9, characterized in that, The proportion of the minimum adaptive weighted distance in the conceptual scheme of S8 .

Images