Cost Estimation Of Cable Route Engineering Based On Random Weight Optimization

With the rapid development of science and technology,the electric power project can meet the needs of the society by expanding the scale.As one of the important projects of electric power line engineering,the demand of cable line project will be expanded,and the investment of engineering will increase.The traditional engineering cost budget method can not meet the actual engineering needs,It is necessary to study the new scientific method to estimate the cost of the project.In recent years,with the introduction of intelligent algorithms,a lot of evaluation methods have appeared in engineering cost evaluation.Many methods have been studied,such as fuzzy mathematics,gray relational degree,neural network,particle swarm and support regression theory.By analyzing the characteristics of the historical engineering of cable lines,it is concluded that the historical engineering data is characterized by small samples and belongs to the small sample data.Support vector regression has the ideal effect on small sample learning.Therefore,support vector regression model will be used to estimate the cost of cable line engineering.In practice,support vector regression is lacking in the accuracy and generalization ability of regression estimation due to blindness of parameter selection.,which can not meet the requirements of practical application.Particle Swarm Optimization has ideal effect on parameter adjustment,so it will adopt Particle Swarm Optimization to optimize support vector regression parameters.At the same time,the particle swarm is improved by balancing the random weights to improve the accuracy of the particle swarm regulation parameter and to increase the stability and accuracy of the estimation model.Combined with the preliminary design of the cable line project,the paper analyzed the characteristics of cost data of cable line project and establishes the evaluation index system.It used the data normalization to the historical data and used the principal component analysis method to extract the characteristics of the evaluation index,which can improve the rationality and validity of the index.Combined with support vector regression and improved particle swarm optimization algorithm,it builded the evaluation model of cable line project cost and gived an example analysis.The result and analysis show that the model can effectively estimate the cost of the cable line project,and can effectively guide the cost evaluation of the new construction of the cable line project.