Quality Evaluation Approach for Prefabricated Buildings Using Ant Colony Algorithm and Simulated Annealing Algorithm to Optimize the Projection Pursuit Model

Abstract

There are problems with an inadequate quality assurance system and non-standard construction organization and administration while creating prefabricated buildings. There are currently fewer quality assessments employing prefabricated component combinations as the research focus, and the quality evaluation methodology is more subjective. We propose a method for evaluating the quality of prefabricated buildings using an ant colony algorithm and a simulated annealing algorithm to optimize the projection pursuit model: firstly, create a prefabricated building quality index system; secondly, questionnaires were distributed, tested for reliability and validity to avoid the influence of questionnaire subjectivity on the results, and structural equation modeling was used to calculate the weights of the quality influencing factors; thirdly, quantify the quality factors of prefabricated components by using the quality function development method, and construct a quality optimization model for the prefabricated component combinations; fourthly, use the ant colony algorithm to solve the quality optimization model to obtain a set of prefabricated component combinations to satisfy the quality requirements; and lastly, use a simulated annealing to optimize the projected pursuit method for evaluating the quality of prefabricated component combination solutions. The results show that (1) The use of optimization algorithms can successfully avoid the issue of a more subjective evaluation approach and increase the efficiency and accuracy of evaluation. (2) Residential Comfort (RC), Usage Durability (UD) and Structural Reliability (SR) have a substantially negative association, but Residential Comfort (RC) and Installation Stability (IS) have strong positive correlations. (3) Based on the magnitude of the vector of the ideal projection direction of the quality indicators, it was determined that the Installation Stability (IS) indicator had the greatest influence on the evaluation of the program, and the Structural Reliability (SR) indicator had the least influence on the program.