论文部分内容阅读
根据城市轨道交通车站工程项目造价的影响因素,利用BP神经网络的基本原理构建关于城市轨道交通车站工程项目造价的神经元输入输出向量,建立了相应的BP神经网络模型。在对实际工程项目样本分析的基础上,利用MATLAB的人工神经网络模块,模拟从工程项目特征到工程项目造价的非线性映射关系,将其应用于实际的城市轨道交通车站工程项目造价估算,精度达到造价估算要求。通过对某市轨道交通路线的历史车站造价样本训练和实例样本计算分析,得到了较好的计算结果,验证了该方法的预测准确性和收敛性。
According to the factors affecting the construction cost of urban rail transit station project, the input and output vectors of the neuron about the construction cost of the urban rail transit station project are constructed based on the basic principle of BP neural network, and the corresponding BP neural network model is established. Based on the analysis of the samples of the actual project, the artificial neural network module of MATLAB is used to simulate the nonlinear mapping relationship from the characteristics of the project to the construction cost of the project, which is applied to the actual cost estimation of the engineering project of the urban rail transit station. The precision Reached the estimated cost of construction. Through the calculation and analysis of historical station cost sample training and example samples of a city rail transit route, the better calculation results are obtained, and the prediction accuracy and convergence of the method are verified.