Temperature Compensation Model for Intelligent Gas Sensor Based on LS-SVR

An intelligent gas sensor is developed which used for gas concentration measurement. This device applies ARM7 kernel as the Microcontroller to measure the thin film´s resistance. After calibrating the gas concentration with component´s resistance, the sensor displays the gas concentration. To reduce adjunctive error which result from temperature drift, and improve the precise of the sensor, a compensational model based on LS-SVR which has banal inputs and single output is suggested. LS-SVR algorithm 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 RBF networks, compensation accuracy of LS-SVR is significantly improved, and reliability of the pressure sensors is enhanced greatly.