为了建立有效预测3C钢在海水环境中的腐蚀速率模型，提出了一种基于粒子群优化(PSO)的径向基神经网络(RBFNN)方法，通过设计特殊的适应度函数，采用PSO优化算法同时实现对RBFNN模型参数(中心值、扩展系数、权值)的调整和径向基函数(隐含层节点)个数的优选。因此，所提出的PSO-RBFNN方法能够以较高的精度和速度自适应地构建预测模型，通过试验数据测试表明，该模型具有良好的预测精度和自学习能力。

In order to establish an effective model for prediction of corrosion rate of 3C steel in seawater environment, a radial basis function neural network (RBFNN) prediction model based on particle swarm optimization (PSO) was proposed. The PSO algorithm can automatically tune the centers and spreads of each radial basis function and the connection weights. Meanwhile, the number of radial basis functions of the constructed RBFNN can be automatically minimized by choosing a special fitness function. Therefore, the proposed PSO-RBFNN method can construct the prediction model adaptively with relatively high precision within a short training time. Simulation results demonstrate the proposed model has good prediction accuracy and self-learning ability.