基于BP神经网络的高精度陀螺恒流源补偿方法

为了提高陀螺恒流源精度，提出一种基于BP神经网络的陀螺恒流源补偿方法.采用BP神经网络训练恒流源控制指令与恒流源输出之间的非线性映射稳态模型，以实时估计恒流源输出偏差.设计恒流源控制指令补偿判据，当输出偏差超出设定裕度时，按比例对恒流源控制指令值进行实时补偿，使得恒流源输出更接近控制目标值，以实现更优的精度.通过实物在回路仿真验证了上述方案的有效性，并通过与传统对控制指令进行分段线性标定方法相比较，显示了上述方案的恒流控制优势.

The Design of Precise Gyro Constant-Current Source Based on BP Neural Network Compensation

In order to improve the accuracy of gyro constant current source, a compensation method of gyro constant current source is proposed based on back propagation (BP) neural network. Firstly, with BP neural network, a nonlinear steady state model that represents the relationship between the control input and the output of gyro constant current source is trained. The model is used to estimate the output deviation of constant current source. Secondly, a compensation criterion is confirmed, which is used to determine whether or not to modify the control command. Once the constant current output deviation exceeds the margin, a certain proportion deviation is added up to the control command. Finally, the HIL(hardware in the loop) simulation is carried out. The results show that the proposed method improves the output accuracy of the gyro constant current greatly compared with the conventional piecewise linear correction method.