论文部分内容阅读
针对传统径向基神经网络(RBF)在大坝安全监测应用中易陷入局部最优及预测精度不高的问题,引入粒子群算法(PSO),对输入的大坝安全监测数据进行初步的聚类处理,找出初步聚类中心后令其为PSO的初值,根据运算法则更新初值以寻求适合训练数据的最优基函数中心。以小湾大坝为例,应用Matlab仿真模拟计算了大坝变形量,结果表明PSO-RBF与传统RBF的拟合效果都很好,PSO-RBF预测准确度更高。
Aiming at the problem that traditional radial basis neural network (RBF) is easy to fall into the local optimum and the prediction accuracy is not high in the dam safety monitoring application, the particle swarm optimization (PSO) is introduced to initialize the dam safety monitoring data, Class processing, find the initial clustering center to make it the initial value of PSO, update the initial value according to the algorithm to find the best basis function center suitable for training data. Taking Xiaowan Dam as an example, the dam deformation was calculated by Matlab simulation. The results show that the fitting effect between PSO-RBF and traditional RBF is good and the prediction accuracy of PSO-RBF is higher.