Non-linearity Estimation and Temperature Compensation of Capacitor Pressure Sensors Using Least Square Support Vector Regression

摘要

A new nonlinear compensation technique to capacitor pressure sensor (CPS) based on least square support vector regression (LSSVR) is proposed. In this technique. LSSVR is used as an inverse model of the CPS; therefore, the proposed technique can automatically compensate the effect of the associated non-linearity to estimate the applied pressure. Furthermore, the flexibility of the proposed technique effectively compensates any variation of the CPS's output occurring due to change in environmental temperature. The results of actual CPS compensation experiment indicate that this LSSVR approach is a useful alternative to the existing ones. This technique would be useful for other types of sensors such as thermocouples, flow sensors, magnetometer etc., possessing similar nonlinear response characteristics. The presented method has a potential future in the field of instrumentation and measurement.