Study On The Risk Assessment Of Construction Project In Xinjiang Area Based On GA-BP Neural Network

In recent years,the risk assessment as an important part of risk management is receiving more and more attention in the production practice of construction industry.The risk assessment of the construction project problems become a hot spot of research.With the strengthening of national assistance efforts in Xinjiang region,Xinjiang building industry has good development environment and opportunities.Therefore,the local construction project risk assessment research is particularly important in project management.The risk of construction project is influenced by many factors.Considering the particularity of Xinjiang region and basic characteristics of uncertainty and complexity of the risk factors,construction project in this region is used as an example to identify the risk factors. Based on using the analytic hierarchy process(AHP) to ascertain the weight of each risk factor,a multi-level grey comprehensive evaluation model was set up for the comprehensive evaluation and sorting of each risk assessment index.Then,the risk assessment index system was constructed with regional characteristics.This article used genetic algorithm to optimize the neural network method(GA-BP neural network) based on the Multi-level Grey Evaluation method,established the construction project risk assessment model of Xinjiang region.Then this model is applied to the construction project risk assessment analysis in Xinjiang region.The predicted values of GA-BP neural network model were in good agreement with the multi-level grey evaluation results,which verified the feasibility of the risk assessment model of GA-BP neural network.GA-BP neural network has a higher convergence speed and prediction accuracy,providing a new idea and method for the research on construction project risk assessment in Xinjiang region.