【摘要】 将改进的粒子群优化(PSO)算法和函数联接型神经网络(FLANN)相结合,实现传感器的动态线性建模。利用传感器的动态标定实验数据,首先训练FLANN神经网络,网络训练结束后的权值作为粒子群中某个粒子的初始值,而后利用改进的PSO算法继续寻优,得到的全局最优值即为所求的传感器动态模型的系数。实验结果表明,该方法结合了PSO和FLANN两者的优点,建模精度高。更多还原

【Abstract】 The dynamic linear model of a sensor was established here based on improved particle swarm optimization(PSO) algorithm and function link artificial neural network(FLANN).According to measurement data in dynamic calibration,the weights of the network trained were used to initialize one particle station of the whole particle swarm when the training of the FLANN had been finished.Then the improved PSO algorithm was applied,the global best particle station of the particle swarm was the coefficient of the sensor’s dynamic model what we need.The experiment results showed that this approach has advantages of both PSO and FLANN,meanwhile it has better precision.更多还原