Temperature compensation for pressure sensor based on LS-SVR

When the pressure sensor is used, temperature changes bring about actual measurement errors . A suitable temperature compensation algorithm can be selected to reduce the additive errors and improve the accuracy of measurement. Support vector machine (SVM) is based on the principle of minimum structural risk, and has high precision. Least squares support vector regression (LS-SVR) is adopted to adjust temperature errors for real measured data. The results show that the algorithm is simple, fast learning, a good anti-interference capability, and a small sample of learning ability. Contrasted by BP networks and RBF networks, compensation accuracy of LS-SVR is significantly improved, and reliability of the pressure sensors is enhanced greatly.