Research on Temperature Compensation of SO2 Gas Sensor Based on RBF Neural Network
(0) SO2 electrochemical gas sensor is vulnerable to the impact of environmental temperature;thereby its accuracy is limited. In order to overcome this shortcoming, the paper proposes a new temperature compensation method based on RBF neural network, which is realized with MATLAB 6. X program software. The result of experiment indicates that the maximum error of the sensor outputs may be up to 20.0 percent before temperature compensation. After the adoption of the temperature compensation method based on BP neural network, the maximum error is reduced to 1.44 percent, even down to 0.12 percent through the compensation based on RBF network. Therefore this way has a better effect on the temperature compensation, which proves that the SO2 electrochemical gas sensor may have a higher accuracy and temperature stability after compensation.
RBF neural network BP neural network SO2 gas sensor Temperature compensation
Gong Rnikun Zhao Yanjun Nian Shanpo Chen Lei Tian Qing
College of Computer and Automatic Control Hebei Polytechnic University, China No.46, Xinhua West Road, Lunan District, Tangshan, 063009 China
国际会议
沈阳
英文
471-474
2009-08-27（万方平台首次上网日期，不代表论文的发表时间）