基于粒子群-小波神经网络的水工隧洞造价预测

Tunnel Cost Prediction Based on Particle Swarm Optimization and Wavelet Neural Network

隧洞是水利水电工程中常见的水工建筑物,隧洞的投资是方案比选、投资决策的重要影响因素。为了快速准确地预测隧洞的造价,建立粒子群-小波神经网络的预测模型。针对小波神经网络容易陷入局部最优区和初始值选择较敏感的问题,利用粒子群算法优化其初始权值和阈值,加快小波神经网络的收敛速度。将模型应用于某隧洞的造价预测中,预测值与实际值的最大预测误差为4.4%,表明模型满足工程建设前期造价预测的精度要求,计算较简便,效率较高。

Tunnel is a common hydraulic structure in water conservancy and hydropower projects.The investment of tunnel is an important factor in scheme comparison and investment decision-making.In order to quickly and accurately predict the cost of the tunnel,establishes the prediction model of particle swarm optimization wavelet neural network.Aiming at the problem that wavelet neural network is easy to fall into the local optimal region and the selection of initial value is sensitive,particle swarm optimization algorithm is used to optimize its initial weight and threshold,which speeds up the convergence speed of wavelet neural network.When the model is applied to the cost prediction of a tunnel,the maximum prediction error between the predicted value and the actual value is 4.4%,which shows that the model meets the accuracy requirements of the previous cost prediction,and the calculation is simple and efficient.