Green building design scheme evaluation system based on multi-objective optimization algorithm

Abstract

The invention belongs to the technical field of combination of a green building design evaluation technology and a multi-objective optimization algorithm, and provides a green building design scheme evaluation system based on a multi-objective optimization algorithm, and the system comprises the steps: screening quantifiable and optimizable green building design targets, and recognizing the strong conflicts between the targets; if the strong conflict exists, the anti-interference capability of a to-be-selected optimal solution set obtained through multi-objective optimization on weight fluctuation is checked through a judgment module; if the anti-interference performance of the solution set is poor, a weight sensitive target is positioned through sensitivity analysis; a reliable reference weight is generated by combining subjective weighting, objective weighting and sensitive target characteristics; and finally, giving consideration to the comprehensive performance and stability of the scheme through priority calculation, and outputting the priority of the to-be-selected scheme, thereby solving the problems of subjective weight setting and poor anti-interference performance of the scheme in the existing green building design evaluation, remarkably improving the scientificity and reliability of the evaluation result, and providing precise support for decision making of the green building design scheme.

Description

Technical Field

[0001] This invention belongs to the technical field of green building design evaluation technology combined with multi-objective optimization algorithm, specifically a green building design scheme evaluation system based on multi-objective optimization algorithm. Background Technology

[0002] Green building design needs to simultaneously consider multiple dimensions of objectives, including environmental (low carbon emissions, energy efficiency), economic (initial construction costs, life-cycle costs), and performance (indoor comfort, air quality). Multi-objective optimization algorithms have become a core tool for selecting design solutions. However, the following key issues exist in the current evaluation process for green building design solutions: Ambiguous identification of conflicting objectives: Existing assessments often directly adopt multi-objective optimization, but fail to accurately identify whether there are strong conflicts between objectives. If there are no conflicts between objectives (such as a positive correlation between operating energy consumption and low carbon emissions), single-objective optimization can meet the requirements, while multi-objective optimization increases computational complexity. If there are strong conflicts between objectives (such as a negative correlation between low carbon emissions and initial construction costs) but these are not identified, it can easily lead to deviations in the optimization direction.

[0003] Weight setting is subjective and sensitive: In multi-objective optimization, weight setting often relies on expert experience or owner's subjective judgment, lacking objective basis; at the same time, under strong conflict of objectives, small changes in weight can cause large fluctuations in the ranking of the candidate optimal solution set (i.e. weight sensitivity). Existing evaluations have not tested the anti-interference ability of the solution set, so even a slight change in weight can change the optimal solution, making the evaluation results unreliable.

[0004] Solution selection ignores stability: Existing solution priority ranking only focuses on the overall performance under the baseline weight, without considering the stability of the solution when the weight fluctuates. Although some solutions have excellent performance, they are sensitive to the weight and are prone to failure due to weight errors in practical applications, making it difficult to guide actual design decisions.

[0005] Therefore, this invention provides a green building design scheme evaluation system based on a multi-objective optimization algorithm. Summary of the Invention

[0006] In order to overcome the shortcomings of the prior art, at least one technical problem raised in the background art is solved.

[0007] The technical solution adopted by this invention to solve its technical problem is: a green building design scheme evaluation system based on a multi-objective optimization algorithm, comprising the following modules: Optimization Conflict Judgment Module: Performs correlation analysis on the optimization objectives of green building design schemes, and determines whether there are strong optimization conflicts among the optimization objectives based on the analysis results; Anti-interference judgment module: If it exists, perform weight sensitivity analysis on the set of candidate optimal solutions obtained by the multi-objective optimization algorithm to determine whether the set of candidate optimal solutions is anti-interference; Sensitivity analysis module: If the set of candidate optimal solutions does not have anti-interference properties, the stability of each candidate optimal solution in the set of candidate optimal solutions is correlated with the stability of each target to be optimized, and the sensitivity coefficient of each target to be optimized is obtained. The benchmark weight calculation module performs subjective and objective weighting on the target to be optimized, calculates the subjective-objective fusion coefficient based on the sensitivity coefficient of the target to be optimized, and obtains the benchmark weight of the target to be optimized through the combined weighting method. Priority Calculation Module: Calculates the weighted comprehensive score of each candidate optimal solution in the candidate optimal solution set under the benchmark weight, and obtains the priority of the candidate optimal solution by combining the stability of each candidate optimal solution.

[0008] Furthermore, the method for determining whether there is a strong optimization conflict among the objectives to be optimized is as follows: Calculate the Pearson correlation coefficient r between any two objectives to be optimized, and compare |r| with the preset correlation coefficient. If there exists a |r| between any two objectives to be optimized that is greater than the preset correlation coefficient and r<0, then there is a strong optimization conflict between the objectives to be optimized.

[0009] Furthermore, the process for determining whether the set of candidate optimal solutions has anti-interference capabilities is as follows: Apply a small perturbation of ±1% to ±5% to each weight in the current weight vector to generate multiple perturbation weight vectors; Consistency coefficients are calculated by performing consistency analysis on the ranking of each candidate optimal solution under the current weight and each group of perturbation weights. The consistency coefficients between the current weights and the perturbation weights of each group are integrated into a set of consistency coefficients. The ranking stability coefficient is obtained by calculating the proportion of numbers in the set of consistency coefficients that have a consistency coefficient greater than a threshold. If the sorting stability coefficient is less than the preset stability coefficient, then the set of candidate optimal solutions does not have anti-interference properties.

[0010] Furthermore, the method for performing consistency analysis on the ranking of each candidate optimal solution under the current weight and each group of perturbation weights is as follows: Generate all possible unordered pairs of optimal solutions from all candidate optimal solutions, that is, combinations of two candidate optimal solutions without considering their order; For each pair of candidate optimal solutions, a consistency analysis is performed on the ranking of the candidate optimal solution pair under the current weight and the perturbation weights of each group, and the candidate optimal solution pairs are divided into consistent pairs and inconsistent pairs. Based on the number of consistent and inconsistent pairs C and D, according to the formula The consistency coefficient τ is calculated, where M is the total number of candidate optimal solutions. , where n is the number of potential optimal solutions.

[0011] Furthermore, the sensitivity coefficients of each target to be optimized are calculated as follows: For each set of perturbation weights, calculate the perturbation weight difference for each target to be optimized, and finally form the independent variable matrix X, where each row corresponds to a set of perturbation weight differences and each column corresponds to the perturbation weight difference for a target to be optimized. Wherein, the perturbation weight difference is the difference between each group of perturbation weights in the perturbation weight vector and the current weight; For each set of perturbation weights, calculate the weighted composite score fluctuation of all candidate optimal solutions to form the dependent variable matrix Y; Based on the independent variable matrix X and the dependent variable matrix Y, a multiple linear regression equation is constructed, and the regression coefficients of the independent variables are obtained by fitting the model using the least squares method. The absolute value of the regression coefficients of the independent variables after standardization is the sensitivity coefficient of each objective to be optimized.

[0012] Furthermore, the process of subjectively assigning weights to the targets to be optimized is as follows: The importance score of the objective to be optimized was obtained using the 1-9 scale method. Using the comprehensive performance of green buildings as the target layer and the importance score of the target to be optimized as the quasi-measurement layer, a reciprocal judgment matrix is ​​constructed. Normalize each column of the reciprocal judgment matrix, and sum the normalized reciprocal judgment matrix row by row to obtain the row vectors W'. Add the row vectors W' together to get the sum of the row vectors; For any objective to be optimized, the subjective weight of the objective is W. i ' / Sum of row vectors, where W i ' is the row vector of the i-th row in the reciprocal judgment moments.

[0013] Furthermore, the process of objectively assigning weights to the targets to be optimized is as follows: Obtain a database of green building projects in the same climate zone and of the same building type within the historical period, with each project in the database corresponding to a quantitative value of the target to be optimized; The quantified values ​​of the optimization target are standardized to obtain a standardized data matrix; The probability distribution of each optimization objective in different projects is calculated using the probability distribution formula; Based on the probability distribution of each target to be optimized in different projects, the information entropy of each target to be optimized is calculated using the information entropy formula. For any objective to be optimized, the formula g j =1-H j The difference coefficient is calculated, and the difference coefficient is normalized to obtain the objective weight of the target to be optimized, where g j H is the difference coefficient for the j-th objective to be optimized. j Let be the objective weight of the j-th objective to be optimized.

[0014] Furthermore, the subjective-objective fusion coefficient is calculated as follows: Subjective-objective fusion coefficient α i Defined as the proportion of objective weighting in the combined weights of the i-th objective to be optimized, the corresponding proportion of subjective weighting is 1-α. i ; The relative sensitivity coefficients are obtained by standardizing the sensitivity coefficients of each target to be optimized to the [0,1] interval. The relative sensitivity coefficient is mapped to the subjective-objective fusion coefficient using a linear mapping method to ensure α i ∈[α min ,α max ], α i =α min +(α max -α min )×S ’ i , where [α min ,α max [This represents the range of values ​​for objective weighting.]

[0015] Furthermore, the benchmark weights are calculated as follows: The baseline weight ω of the target to be optimized 基 For: ω 基 =α×ω 客 +(1-α)×ω 主 Where α is the subjective-objective fusion coefficient, ω 客 For objective weights, ω 主 Subjective weighting.

[0016] Furthermore, the priority of the candidate optimal solution is calculated as follows: For any candidate optimal solution in the set of candidate optimal solutions, the weighted sum of each optimization objective in the candidate optimal solution is calculated based on the benchmark weight to obtain the weighted comprehensive score; Arrange the candidate optimal solutions in descending order of weighted comprehensive score to obtain the weighted comprehensive score sequence; Calculate the coefficient of variation of the weighted composite score of each candidate optimal solution under all perturbation weights, and sort the candidate optimal solutions in ascending order of coefficient of variation to obtain the coefficient of variation sequence; The priority index is obtained by adding the index of the candidate optimal solution in the weighted comprehensive score sequence to the index in the coefficient of variation sequence score. The candidate optimal solutions are then sorted in ascending order according to the priority index to obtain the priority of the candidate optimal solutions.

[0017] The beneficial effects of this invention are as follows: It screens quantifiable and optimizable targets and accurately identifies strong conflicts based on Pearson correlation coefficients, avoiding redundant calculations in multi-objective optimization for non-conflicting targets or optimization deviations caused by unidentified conflicting targets. This ensures that the optimization direction is focused and efficient. By calculating the consistency coefficient through slight perturbations in weights, it quantifies the stability of the solution set to weight fluctuations, avoiding the use of unreliable solution sets sensitive to weights for decision-making, and reducing engineering risks caused by weight setting errors. It locates weight-sensitive targets through multiple linear regression, providing a targeted basis for subsequent benchmark weight calculations. Highly sensitive targets are given a higher proportion of objective weighting, reducing subjective bias and improving the reliability of weight setting. The benchmark weight calculation module combines expert experience (subjective weighting), historical data (objective weighting), and sensitive target characteristics (fusion coefficients) to avoid experience bias in purely subjective weighting or scenario disconnect in purely objective weighting, generating benchmark weights that are more in line with actual needs. The priority calculation module considers the comprehensive performance and anti-interference stability of the scheme through a priority index of weighted comprehensive score + coefficient of variation, ensuring that the final selected scheme is both high-performing and risk-resistant, providing accurate and reliable support for green building design decisions. Attached Figure Description

[0018] The invention will now be further described with reference to the accompanying drawings.

[0019] Figure 1 This is a flowchart of the steps of a green building design scheme evaluation system based on a multi-objective optimization algorithm as described in this invention; Figure 2 This is a logic judgment diagram for determining whether the set of candidate optimal solutions has anti-interference capabilities, as described in this invention. Detailed Implementation

[0020] To make the technical means, creative features, objectives and effects of this invention easier to understand, the invention will be further described below in conjunction with specific embodiments.

[0021] Please see Figure 1 As shown in the embodiment of the present invention, a green building design scheme evaluation system based on a multi-objective optimization algorithm includes the following modules: Optimization Conflict Judgment Module: Performs correlation analysis on the optimization objectives of green building design schemes, and determines whether there are strong optimization conflicts among the optimization objectives based on the analysis results; The process of determining whether there is a strong optimization conflict between the objectives to be optimized includes: Based on green building evaluation standards and the actual needs of the project, preliminary optimization targets were selected, such as: Environmental dimensions: low carbon emissions, energy efficiency, water resource utilization, etc. Economic dimensions: initial construction costs, total life cycle costs, etc. Performance dimensions: indoor comfort, indoor air quality, etc.; The initial selection of optimization objectives should be quantified and optimized, eliminating those that are uncontrollable or cannot be adjusted through the design scheme, such as: |Target Category|Target to be Optimized|Quantitative Indicator|Target Attribute|; |Environment|A. Low carbon emissions|Life cycle carbon emissions|The lower the better|; |Economy|B. Initial construction cost|Cost per unit area|The smaller the better|; |Performance|Operating energy consumption|Annual power consumption per unit area|The lower the better|; Calculate the Pearson correlation coefficient r between any two objectives to be optimized, and compare |r| with the preset correlation coefficient. If there exists a |r| between any two objectives to be optimized that is greater than the preset correlation coefficient and r<0, then there is a strong optimization conflict between the objectives to be optimized. The purpose of determining whether there is a strong optimization conflict between the objectives to be optimized is: Multi-objective optimization provides effective and necessary optimization objects and determines whether a multi-objective optimization method is needed. If there is no conflict between objectives, single-objective optimization is sufficient. Anti-interference judgment module: If it exists, perform weight sensitivity analysis on the set of candidate optimal solutions obtained by the multi-objective optimization algorithm to determine whether the set of candidate optimal solutions is anti-interference; Please see Figure 2 As shown, the process of determining whether the set of candidate optimal solutions has anti-interference capabilities includes: The set of candidate optimal solutions S={S1,S2,...,S...} obtained by the multi-objective algorithm n}, where n is the number of solutions, and each solution corresponds to a set of target performance values ​​to be optimized; The current weight vector is W0, which contains the weights of each objective to be optimized. Each weight in the current weight vector W0 is perturbed by a small amount of ±1% to ±5%, generating multiple perturbed weight vectors. For each set of perturbation weights in the perturbation weight vector, calculate the weighted composite score of all candidate optimal solutions: Where p is the number of objectives to be optimized. Let be the weight of the k-th objective to be optimized in the j-th group of perturbation weights. Let i be the standardized performance value of the i-th candidate optimal solution on the k-th optimization objective; The objectives to be optimized need to be standardized first, and each objective needs to be standardized to [0,1]: If the target to be optimized is to be as small as possible... =(max k -x i ) / (max k -min k ), where max k min k The target to be optimized is x i The maximum and minimum values ​​in the Pareto solution; If the goal of optimization is to approach T after optimization... =1-|x i -T| / max(|max k -T|,|min k -T|), where, max k min k Let x be the target to be optimized. i The maximum and minimum values ​​in the set of candidate optimal solutions; Sort the candidate optimal solutions in descending order of their weighted composite scores to generate a sorted sequence R(ω)=[r1,r2,...,r n ], where r n S is the nth candidate optimal solution n Ranking; From all candidate optimal solutions, generate all possible unordered pairs of candidate optimal solutions, i.e., combinations of two candidate optimal solutions regardless of their order. The total number of candidate optimal solution pairs is: ; For each pair of candidate optimal solutions (S) i ,S k Let's examine the ranking relationships under the current weight and each perturbation weight: Consistent pair: If S under the current weight i Ranked higher than S k And under the perturbation weights S i The ranking is still higher than S k Or both are S i Ranked below S k If the candidate optimal solution pair is a consistent pair, it is denoted as C; Inconsistent pairs: If S under the current weight i Ranked higher than S k However, under the perturbation weights, S i Ranked below S k If so, then the candidate optimal solution pair is an inconsistent pair; Based on the number of consistent pairs C and inconsistent pairs D, the formula for calculating the consistency coefficient is: Where M is the total number of pairs of candidate optimal solutions; It is understandable that the physical meaning of the consistency coefficient calculation formula is as follows: when all candidate optimal solution pairs are consistent pairs (D=0), τ=1, indicating that the two sets of rankings are completely consistent; when all candidate optimal solution pairs are inconsistent pairs (C=0), τ=-1, indicating that the two sets of rankings are completely opposite; when C=D, τ=0, indicating that the two sets of rankings are unrelated. Calculate the consistency coefficient between the current weight and each group of perturbation weights to obtain a set of consistency coefficients; The ranking stability coefficient is obtained by calculating the proportion of numbers in the set of consistency coefficients that have a consistency coefficient greater than a threshold. The sorting stability coefficient is compared with the preset stability coefficient. If the sorting stability coefficient is less than the preset stability coefficient, the set of candidate optimal solutions does not have the ability to resist interference. Understandably, the logic for judging the anti-interference ability is as follows: if the ranking stability coefficient is greater than the preset stability coefficient, it means that each of the candidate optimal solutions in the set of candidate optimal solutions remains stable in most weight fluctuations and has low overall sensitivity; conversely, it means that the ranking is extremely susceptible to weight influence. The purpose of determining whether the set of candidate optimal solutions has anti-interference properties is as follows: Under the premise of strong conflict between objectives, we test the ability of the set of candidate optimal solutions obtained by multi-objective optimization to resist the interference of weight setting error—that is, whether the sorting of solutions is stable when the weight changes slightly, so as to avoid the situation that the optimal solution becomes unreliable when the weight changes slightly. Sensitivity analysis module: If the set of candidate optimal solutions does not have anti-interference properties, the stability of each candidate optimal solution in the set of candidate optimal solutions is correlated with the stability of each target to be optimized, and the sensitivity coefficient of each target to be optimized is obtained. The calculation process for the sensitivity coefficients of each target to be optimized includes: For each set of perturbation weights in the perturbation weight vector, calculate the weighted comprehensive performance score of all candidate optimal solutions; The difference between each group of perturbation weights in the perturbation weight vector and the current weight is the perturbation weight difference; For each set of perturbation weights, calculate the perturbation weight difference for the k-th objective to be optimized. , where, where, ω 0k It is the current weight of the kth target to be optimized, which ultimately forms the independent variable matrix X, with each row corresponding to a set of perturbation weight differences and each column corresponding to the perturbation weight difference of a target to be optimized; For each set of perturbation weights, calculate the weighted composite score fluctuation of all candidate optimal solutions. : Among them, Score(S i ,ω0) is the candidate optimal solution S iThe weighted composite score under each group of perturbation weights is finally used to form the dependent variable vector Y. Based on the independent variable matrix X and the dependent variable matrix Y, construct the following multiple linear regression equation: Y = β0 + β1X1 + β2X2 + ... + β p X p +ε, where β0 is a constant term, β1~β p ε is the partial regression coefficient, reflecting the direction and absolute strength of the influence of the weight fluctuation of the k-th objective to be optimized on the result, and ε is the random error term; By fitting the model using the least squares method, the partial regression coefficients β1~β2 are obtained. p ; The partial regression coefficients are standardized to obtain the standardized regression coefficients: , where σ(X) k Let σ(Y) be the standard deviation of the k-th independent variable, and let σ(Y) be the standard deviation of the dependent variable. The absolute value of the standardized regression coefficient of each objective to be optimized is the sensitivity coefficient; The purpose of calculating the sensitivity coefficients for each objective to be optimized is as follows: When the set of candidate optimal solutions has poor anti-interference ability, find out which target's weight change has the greatest impact on the solution's score, that is, locate the sensitive target, and provide a targeted basis for subsequent reasonable weighting (the weight of highly sensitive targets needs to be set more carefully). The benchmark weight calculation module performs subjective and objective weighting on the target to be optimized, calculates the subjective-objective fusion coefficient based on the sensitivity coefficient of the target to be optimized, and obtains the benchmark weight of the target to be optimized through the combined weighting method. The process of subjectively assigning weights to the optimization targets includes: Multiple cross-disciplinary experts were selected and scored on the optimization objectives using a 1-9 scale (1 = equally important, 9 = extremely important). Using the comprehensive performance of green buildings as the target layer and the optimization target as the quasi-measurement layer, a reciprocal judgment matrix A is constructed: |Criterion Layer|G1|G2|...|G n |; |G1|a 11 |a 12 |...|a 1n |; |G2|a 21 |a 22 |...|a 2n |; |...|...|...|...|...|; |G n |a n1 |a n2 |...|ann |; Matrix elements satisfy: diagonal element a ii =1 (the importance of the target itself is equal to its own), and the off-diagonal elements satisfy a. ij =1 / a ji (If G) i Compared to G j If the importance scale is 3, then G j Compared to G i (The scale is 1 / 3). For the judgment matrix A, calculate the sum of the products of matrix A and the normalized column vectors, and then find the mean to obtain the largest eigenvalue λ of the matrix. max Specifically: Normalize each column of the judgment matrix A, and sum the rows of the normalized matrix to obtain vector W'. The largest eigenvalue is: , where A×W' is the product of matrix A and vector W', and (A×W')i is the i-th element; Through formula This yields the consistency deviation of the matrix; The consistency ratio CR is calculated by combining the average random consistency index RI to eliminate the influence of matrix order. The formula is: CR=CI / RI, where the average random consistency index RI is obtained by looking up a table. If CR < 0.1, the matrix passes the consistency test (there is no logical contradiction). The subjective weights are obtained using the eigenvalue method: the sum of vectors W' is calculated, and the subjective weights are ω. i组 =W i ' / sum, where i is the i-th objective to be optimized; The process of objectively assigning weights to the targets to be optimized includes: Obtain a database of green building projects in the same climate zone and of the same building type within the historical period, with each project in the database corresponding to a quantitative value of the target to be optimized; The quantified values ​​of the optimization target are standardized to obtain a standardized data matrix X'; Calculate the probability distribution p of the j-th target. ij : Where m is the number of items; Calculate the information entropy H of the j-th target. j : Where 1 / lnm is the normalization factor, ensuring H j ∈[0,1]; Through formula g j =1-H j The difference coefficient is calculated, and the difference coefficient is normalized to obtain the objective weight: ; The calculation process of the subjective-objective fusion coefficient includes: Subjective-objective fusion coefficient α i Defined as the proportion of objective weighting in the combined weights of the i-th objective to be optimized, the corresponding proportion of subjective weighting is 1-α. i The calculation process must follow the principle of high sensitivity → high objective proportion: The sensitivity coefficients of each target to be optimized are standardized to the relative sensitivity coefficients in the interval [0,1]. The relative sensitivity coefficient is mapped to the subjective-objective fusion coefficient using a linear mapping method to ensure α i ∈[α min ,α max ]:α i =α min +(α max -α min )×S ’ i , where [α min ,α max The range of values ​​for objective weighting is determined based on project requirements; It should be noted that the calculation logic of the subjective-objective fusion coefficient is as follows: the higher the sensitivity coefficient of the target to be optimized (the greater the impact of small fluctuations in weight on the overall score of the solution), the greater the proportion of objective weighting in the combined weight of that target. The higher the percentage of subjective empowerment, the greater the proportion of subjective empowerment. The lower the value, the less subjective bias will affect the weight of sensitive targets, thus ensuring the reliability of the benchmark weight. The baseline weight of the objective to be optimized is ω 基 =α×ω 客 +(1-α)×ω 主 ; The purpose of calculating the benchmark weights is: To address the issue of unreasonable weight settings and avoid purely subjective weighting (expert experience bias) or purely objective weighting (ignoring the actual needs of the project), a reliable benchmark weight is generated by combining the sensitivity coefficient of the target to be optimized, providing a fair and reasonable evaluation standard for subsequent priority calculations. Priority Calculation Module: Calculates the weighted comprehensive score of each candidate optimal solution in the candidate optimal solution set under the baseline weight, and obtains the priority of the candidate optimal solutions by combining the stability of each candidate optimal solution; The priority calculation process for the scheme includes: For any candidate optimal solution in the set of candidate optimal solutions, the weighted sum of each optimization objective in the candidate optimal solution is calculated based on the benchmark weight to obtain the weighted comprehensive score; Arrange the candidate optimal solutions in descending order of weighted comprehensive score to obtain the weighted comprehensive score sequence; Calculate the coefficient of variation of the weighted composite score of each candidate optimal solution under all perturbation weights, and sort the candidate optimal solutions in ascending order of coefficient of variation to obtain the coefficient of variation sequence; The priority index is obtained by adding the index of the candidate optimal solution in the weighted comprehensive score sequence to the index in the coefficient of variation sequence score. The candidate optimal solutions are then sorted in ascending order according to the priority index to obtain the priority of the candidate optimal solutions. It is understandable that the physical meaning of the priority index is: the smaller the sum of the serial numbers, the better the overall performance of the solution under the benchmark weight and the anti-interference stability when the weight fluctuates, and the higher the priority in the candidate set.

[0022] The purpose of determining the priority of candidate optimal solutions is: After determining the baseline weights, taking into account both overall performance and anti-interference stability, all candidate optimal solutions are sorted, and the final optimal solution that best suits the practical application is selected.

[0023] The technical solution and advantages of this application are as follows: A correlation analysis is performed on the optimization objectives of the green building design scheme. Based on the analysis results, it is determined whether there is a strong optimization conflict among the optimization objectives. If so, a weight sensitivity analysis is performed on the set of candidate optimal solutions obtained by the multi-objective optimization algorithm to determine whether the set of candidate optimal solutions has anti-interference properties. If the set of candidate optimal solutions does not have anti-interference properties, a correlation analysis is performed between the stability of each candidate optimal solution in the set of candidate optimal solutions and the stability of each optimization objective to obtain the sensitivity coefficient of each optimization objective. Subjective and objective weighting are applied to the optimization objectives respectively, and a subjective-objective fusion coefficient is calculated based on the sensitivity coefficient of the optimization objective. The baseline weight of the optimization objective is obtained through a combined weighting method. The weighted comprehensive score of each candidate optimal solution in the set of candidate optimal solutions under the baseline weight is calculated, and the priority of the candidate optimal solutions is obtained by combining the stability of each candidate optimal solution. This invention addresses the problems of subjective weight setting and poor anti-interference capabilities in existing green building design assessments by screening quantifiable and optimizable green building design objectives and identifying strong conflicts between objectives. If strong conflicts exist, a judgment module verifies the resilience of the candidate optimal solution set obtained from multi-objective optimization to weight fluctuations. If the solution set has poor anti-interference capabilities, sensitivity analysis is used to locate weight-sensitive objectives. Then, by combining subjective weighting, objective weighting, and the characteristics of sensitive objectives, reliable benchmark weights are generated. Finally, priority calculation takes into account both the comprehensive performance and stability of the schemes and outputs the priority of the candidate schemes. This invention solves the problems of subjective weight setting and poor anti-interference capabilities in existing green building design assessments, significantly improving the scientific rigor and reliability of the assessment results and providing precise support for green building design decision-making.

[0024] The foregoing has shown and described the basic principles, main features, and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The embodiments and descriptions in the specification are merely illustrative of the principles of the invention. Various changes and modifications can be made to the invention without departing from its spirit and scope, and all such changes and modifications fall within the scope of the present invention as claimed. The scope of protection of the present invention is defined by the appended claims and their equivalents.

Claims

1. A green building design scheme evaluation system based on a multi-objective optimization algorithm, characterized in that: Includes the following modules: Optimization Conflict Judgment Module: Performs correlation analysis on the optimization objectives of green building design schemes, and determines whether there are strong optimization conflicts among the optimization objectives based on the analysis results; Anti-interference judgment module: If it exists, perform weight sensitivity analysis on the set of candidate optimal solutions obtained by the multi-objective optimization algorithm to determine whether the set of candidate optimal solutions is anti-interference; Sensitivity analysis module: If the set of candidate optimal solutions does not have anti-interference properties, the stability of each candidate optimal solution in the set of candidate optimal solutions is correlated with the stability of each target to be optimized, and the sensitivity coefficient of each target to be optimized is obtained. The benchmark weight calculation module performs subjective and objective weighting on the target to be optimized, calculates the subjective-objective fusion coefficient based on the sensitivity coefficient of the target to be optimized, and obtains the benchmark weight of the target to be optimized through the combined weighting method. Priority Calculation Module: Calculates the weighted comprehensive score of each candidate optimal solution in the candidate optimal solution set under the benchmark weight, and obtains the priority of the candidate optimal solution by combining the stability of each candidate optimal solution.

2. The green building design scheme evaluation system based on a multi-objective optimization algorithm according to claim 1, characterized in that: The method for determining whether there is a strong optimization conflict between the objectives to be optimized is as follows: Calculate the Pearson correlation coefficient r between any two objectives to be optimized, and compare |r| with the preset correlation coefficient. If there exists a |r| between any two objectives to be optimized that is greater than the preset correlation coefficient and r<0, then there is a strong optimization conflict between the objectives to be optimized.

3. The green building design scheme evaluation system based on a multi-objective optimization algorithm according to claim 2, characterized in that: The process for determining whether the set of candidate optimal solutions is resistant to interference is as follows: Apply a small perturbation of ±1% to ±5% to each weight in the current weight vector to generate multiple perturbation weight vectors; Consistency coefficients are calculated by performing consistency analysis on the ranking of each candidate optimal solution under the current weight and each group of perturbation weights. The consistency coefficients between the current weights and the perturbation weights of each group are integrated into a set of consistency coefficients. The ranking stability coefficient is obtained by calculating the proportion of numbers in the set of consistency coefficients that have a consistency coefficient greater than a threshold. If the sorting stability coefficient is less than the preset stability coefficient, then the set of candidate optimal solutions does not have anti-interference properties.

4. The green building design scheme evaluation system based on a multi-objective optimization algorithm according to claim 3, characterized in that: The method for performing consistency analysis on the ranking of each candidate optimal solution under the current weight and each group of perturbation weights is as follows: Generate all possible unordered pairs of optimal solutions from all candidate optimal solutions, that is, combinations of two candidate optimal solutions without considering their order; For each pair of candidate optimal solutions, a consistency analysis is performed on the ranking of the candidate optimal solution pair under the current weight and the perturbation weights of each group, and the candidate optimal solution pairs are divided into consistent pairs and inconsistent pairs. Based on the number of consistent and inconsistent pairs C and D, according to the formula The consistency coefficient τ is calculated, where M is the total number of candidate optimal solutions. , where n is the number of potential optimal solutions.

5. The green building design scheme evaluation system based on a multi-objective optimization algorithm according to claim 4, characterized in that: The sensitivity coefficients of each target to be optimized are calculated as follows: For each set of perturbation weights, calculate the perturbation weight difference for each target to be optimized, and finally form the independent variable matrix X, where each row corresponds to a set of perturbation weight differences and each column corresponds to the perturbation weight difference for a target to be optimized. Wherein, the perturbation weight difference is the difference between each group of perturbation weights in the perturbation weight vector and the current weight; For each set of perturbation weights, calculate the weighted composite score fluctuation of all candidate optimal solutions to form the dependent variable matrix Y; Based on the independent variable matrix X and the dependent variable matrix Y, a multiple linear regression equation is constructed, and the regression coefficients of the independent variables are obtained by fitting the model using the least squares method. The absolute value of the regression coefficients of the independent variables after standardization is the sensitivity coefficient of each objective to be optimized.

6. The green building design scheme evaluation system based on a multi-objective optimization algorithm according to claim 1, characterized in that: The process of subjectively assigning weights to the optimization targets is as follows: The importance score of the objective to be optimized was obtained using the 1-9 scale method. Using the comprehensive performance of green buildings as the target layer and the importance score of the target to be optimized as the quasi-measurement layer, a reciprocal judgment matrix is ​​constructed. Normalize each column of the reciprocal judgment matrix, and sum the normalized reciprocal judgment matrix row by row to obtain the row vectors W'. Add the row vectors W' together to get the sum of the row vectors; For any objective to be optimized, the subjective weight of the objective is W. i ' / Sum of row vectors, where W i ' is the row vector of the i-th row in the reciprocal judgment moments.

7. The green building design scheme evaluation system based on a multi-objective optimization algorithm according to claim 6, characterized in that: The process of objectively assigning weights to the targets to be optimized is as follows: Obtain a database of green building projects in the same climate zone and of the same building type within the historical period, with each project in the database corresponding to a quantitative value of the target to be optimized; The quantified values ​​of the optimization target are standardized to obtain a standardized data matrix; The probability distribution of each optimization objective in different projects is calculated using the probability distribution formula; Based on the probability distribution of each target to be optimized in different projects, the information entropy of each target to be optimized is calculated using the information entropy formula. For any objective to be optimized, the formula g j =1-H j The difference coefficient is calculated, and the difference coefficient is normalized to obtain the objective weight of the target to be optimized, where g j H is the difference coefficient for the j-th objective to be optimized. j Let be the objective weight of the j-th objective to be optimized.

8. The green building design scheme evaluation system based on a multi-objective optimization algorithm according to claim 6, characterized in that: The subjective-objective fusion coefficient is calculated as follows: Subjective-objective fusion coefficient α i Defined as the proportion of objective weighting in the combined weights of the i-th objective to be optimized, the corresponding proportion of subjective weighting is 1-α. i ; The relative sensitivity coefficients are obtained by standardizing the sensitivity coefficients of each target to be optimized to the [0,1] interval. The relative sensitivity coefficient is mapped to the subjective-objective fusion coefficient using a linear mapping method to ensure α i ∈[α min ,α max ], α i =α min +(α max -α min )×S ’ i , where [α min ,α max [This represents the range of values ​​for objective weighting.] 9. The green building design scheme evaluation system based on a multi-objective optimization algorithm according to claim 8, characterized in that: The benchmark weight is calculated as follows: The baseline weight ω of the target to be optimized 基 For: ω 基 =α×ω 客 +(1-α)×ω 主 Where α is the subjective-objective fusion coefficient, ω 客 For objective weights, ω 主 Subjective weighting.

10. The green building design scheme evaluation system based on a multi-objective optimization algorithm according to claim 1, characterized in that: The priority of the candidate optimal solution is calculated as follows: For any candidate optimal solution in the set of candidate optimal solutions, the weighted sum of each optimization objective in the candidate optimal solution is calculated based on the benchmark weight to obtain the weighted comprehensive score; Arrange the candidate optimal solutions in descending order of weighted comprehensive score to obtain the weighted comprehensive score sequence; Calculate the coefficient of variation of the weighted composite score of each candidate optimal solution under all perturbation weights, and sort the candidate optimal solutions in ascending order of coefficient of variation to obtain the coefficient of variation sequence; The priority index is obtained by adding the index of the candidate optimal solution in the weighted comprehensive score sequence to the index in the coefficient of variation sequence score. The candidate optimal solutions are then sorted in ascending order according to the priority index to obtain the priority of the candidate optimal solutions.

Images