A multi-objective optimization and renovation decision-making method for existing buildings based on ga-rbf algorithm

Abstract

The present invention is a multi-objective optimization and reconstruction decision-making method for existing buildings based on the GA-RBF algorithm. The method includes the following steps: taking cooling energy consumption, thermal comfort, and renovation costs to be minimized at the same time as the existing building renovation optimization goal, And build the objective function to determine the type and quantity P of decision variables for multi-objective optimization and renovation of existing buildings, and at the same time determine the optimization interval of each decision variable; determine the reference building and design the orthogonal table; establish the RBF neural network model for simulating the performance of existing buildings ; Using NSGA-Ⅱ algorithm for multi-objective optimization calculation, NSGA-Ⅱ algorithm calls RBF neural network model in each iteration to obtain the output vector matrix to update the population of the next iteration, realizing the combination of RBF neural network model and NSGA-Ⅱ algorithm Dynamic coupling to obtain the Pareto optimal solution set; through statistical analysis of the calculated Pareto optimal solution set, the distribution of decision variables can be obtained, so as to obtain the required optimal transformation measures. Improve the efficiency of the actual project.

Description

technical field [0001] The invention relates to a multi-objective optimization and reconstruction decision-making method for existing buildings based on GA-RBF algorithm Background technique [0002] Existing buildings in the early construction period often have problems of poor thermal performance. In the process of simply using HVAC to improve thermal comfort, the expected effect is often not achieved or the energy consumption is too high, no matter from improving the livability level or saving. From the perspective of resources, reasonable renovation of existing buildings is necessary. However, the renovation of existing buildings is a complex multi-objective decision-making problem with multiple factors and multiple objectives, and it is difficult to intuitively obtain the renovation decision. [0003] The key to solving this problem is how to select the transformation measures and optimization goals in a targeted manner and carry out reasonable and efficient optimizati...

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to solve the problem that the decision-making process of multi-objective optimization and transformation of existing buildings is relatively difficult. Through software simulation, data collection, neural network model establishment, coupling optimization, data analysis and other means, a GA-RBF algorithm is provided. The existing building multi-objective optimization and renovation decision-making method, the method collects the input and output data of the existing building performance simulation, couples the RBF neural network with the NSGA-Ⅱ algorithm, and uses the high-efficiency and high-precision GA-RBF multi-objective optimization The algorithm obtains the Pareto optimality of the decision variables, and performs statistical analysis on the Pareto optimal solution set to obtain the optimal transformation measures

Images