摘要
Abstract
In order to improve the economic cost prediction accuracy of existing building strengthening and renovation projects,principal com-ponent analysis(PCA)was used to pre-process the original data,and the economic cost prediction model of existing building strengthening and renovation projects was established by PACC-BP neural network,and tested and verified.The results show that the cumulative variance contribution rate of the three principal components extracted by PCA is 85.668%,which is greater than 85%,that is,the extracted principal components are reasonable and reliable.After the establishment of the model,the predicted value and the actual value of the cost show an ap-proximate linear positive correlation trend,and the average error of the two is 3.21%,which proves that the model has good prediction accura-cy.Therefore,the model building method can be used to predict the project cost in the investment stage.关键词
既有建筑工程/PCA-BP神经网络/工程造价/预估模型Key words
Existing building project/PCA-BP neural network/Project cost/Prediction model分类
建筑与水利
