传感器蠕变的一种新的补偿方法——动态神经网络补偿法,可实现蠕变实时精确补偿。引入人工神经网络识别的方法来确定载荷的变化状况,利用传感器的输出变化率,来判断传感器的蠕变起始点,可以确定作用于传感器上的实际载荷。同时这种方法的精度也不会受到传感器载荷、环境等因素的影响,即简单方便,易于实现并且可以批量生产,精度较好,有较好的学习性,这也是一种新的蠕变误差补偿算法。 A New Compensation Method for Sensor Creep - Dynamic Neural Network Compensation Method to Realize Accurate Creep Compensation in Real Time. The method of artificial neural network identification is introduced to determine the change of load. The change rate of the output of the sensor is used to judge the starting point of creep of the sensor and the actual load acting on the sensor can be determined. At the same time the accuracy of this method will not be affected by the sensor load, the environment and other factors, that is simple and convenient, easy to implement and can be mass-produced, better accuracy, better learning, which is also a new creep error Compensation algorithm.