神经网络预测算法在抽油机节能电机系统中的应用

Application of Neural Network Prediction Algorithm in Energy-SavingMotor System of Pumping Unit

抽油机在工作时,每台电机的实际负载都是不相同的,如何根据工作过程中抽油机的实际负载来调整电机的实际输入电压对提高抽油机的效率有着明显的提升。本文采用了神经网络预测算法对电机实际输入电压进行预测,讨论了神经网络预测算法参数对预测结果的影响,并对神经网络预测算法获得的预测值与实测值进行了对比。结果表明本文提出的神经网络预测算法能够对电机最佳工作电压进行预测。

When the pumping unit is working,the actual load of each motor is different.How to adjust the actual input voltage of the motor according to the actual load of the pumping unit during the working process can significantly improve the efficiency of the pumping unit.This paper uses the neural network prediction algorithm to predict the actual input voltage of the motor,discusses the influence of the parameters of the neural network prediction algorithm on the prediction results,and compares the predicted value obtained by the neural network prediction algorithm with the measured value.The results show that the neural network prediction algorithm proposed in this paper can predict the optimal working voltage of the motor.