BP神经网络在建筑工程估价中的应用

在建设项目管理中前期工程估价是一项十分重要的工作，根据神经网络的原理和工程造价估算的特点，通过研究工程造价的构成，特别是建筑工程结构和主要分项工程的特征在工程造价中所起的作用，确定了7个主要因素，作为神经网络的输入变量，提出了基于BP神经网络的工程估价模型．共收集了20个住宅工程估价实例，其中18个作为训练样本，2个作为检测实例，经测算其精度基本可以满足实际工程投资估算的需要．因此，神经网络在这方面有很好的应用前景．

The application of neural network in the cost estimation of construction

Cost estimation of construction projects is a very important task for management of construction projects. According to the basic principles of the neural network and the characteristics of project cost estimation, with the breakdown of project cost and factors having effect on them,and the functions of structures and their characteristics reviewed in detail,seven major factors are identified as neural network input variables. On the basis of the theoretical analysis, the paper brings up the model of cost estimation of construction engineering based on the BP Neural Network. Eighteen actual construction projects are used as training samples and two projects are used as test samples. Test results show that the precision meets the estimation requirements well. Therefore, this method shows the promising perspective in cost estimation of construction project.