Improved BP Algorithm Applied to Motion Control of UV
Up to now, some technologies of neural networks are developed to solve the non-linearity of research objects and the adaptive control is implemented in many engineering fields, and some good results are achieved. Though the learning mechanism of neural networks is really unknowable, the importance of study ratio is widely realized, and some methods on modification of study ratio are provided. Improving the stability and increasing the convergent rate of networks by defining a good form of study ratio is the main target. A new algorithm named least disturbance BP algorithm is proposed to calculate the ratio online according to the output errors, the weights of network and the input values. The algorithm is applied to the control of an underwater vehicle. The good performance of the algorithm and the controller is demonstrated by the experimental results.