基于SSA-LSSVM模型的差动电感式位移传感器的温度补偿

Temperature Compensation for Differential Inductance Displacement Sensor Based on ASS-LSSVM

针对差动电感式位移传感器的温度漂移问题,提出了一种新的温度补偿模式。采用一种麻雀搜索算法(SSA),进一步优化最小二乘支持向量机(LSSVM)的计算;为了提高模型性能,进一步优化了惩罚因子和RBF核函数参数;为了弥补传统LSSVM需要凭借历史经验选取参数的弊端,利用差动电感式位移传感器的二维标定试验得到位移及温度的标定数据建立数据集,通过训练构建了SSA-LSSVM模型。研究结果表明:经过温度补偿后,传感器的零点温度系数减小了2个数量级,灵敏度温度系数减小了1个数量级,相比已有研究结果具有更高的精度。

A new temperature compensation mode is proposed to address the temperature drift problem of differential inductance displacement sensors.A Sparrow Search Algorithm(SSA)is adopted to further optimize the calculation of Least Squares Support Vector Machine(LSSVM).To improve model performance,the penalty factor and RBF kernel function parameters are further optimized.To compensate for the disadvantage of traditional LSSVM which requires selecting parameters based on historical experience,a dataset is established using two-dimensional calibration experiments of differential inductance displacement sensors to obtain calibration data of displacement and temperature.The SSA-LSSVM model is constructed through training.The research results show that the zero temperature coefficient of the sensor is reduced by 2 orders of magnitude after temperature compensation,and the sensitivity temperature coefficient is reduced by 1 order of magnitude,which has higher accuracy compared to existing research results.