基于最小二乘支持向量机的矿用振弦式称重传感器非线性校正

Nonlinear correction of mine-used vibro-string transducers for dynamic weighting based on least square support vector machine

依据矿用振弦式称重传感器样本,提出了一种采用最小二乘支持向量机辨识传感器逆模特征的校正矿用振弦式称重传感器非线性误差的方法。该方法不需逆模型函数形式的先验知识,能够保证找到的极值解就是局最优解,具有较好的泛化能力。实例应用表明,其检测误差小于1.0%。

According to the sample of vibro-string transducers for dynamic weighting in a mine, a method of correcting nonlinear error of this kind of transducers, which can identify the contrary model characteristic of the transducers correctly, is given based on the least square support vector machine. The method does not need any priori knowledge inform of contrary model function and it is able to guarantee that the extremal solution is local optimal solution. The results from application reveal that the error of the sensor is less than 1.0%.