Using PF to train the neural networks can overcome the drawbacks of BP algorithm such as falling into local minima and slow convergence, and the linearized error of Extended Kalman Filter.

• 采用粒子滤波训练神经网络克服了BP算法收敛速度慢、易陷入局部极小值的缺陷，及扩展卡尔曼滤波方法带来的模型线性化损失；