论文部分内容阅读
为了改善传感器的动态特性,减小系统测量误差,分析了传感器动态性能补偿的基本原理,把模糊RBF神经网络应用到传感器的补偿环节。仿真实验表明,使用补偿的传感器输出达到稳态的时间比没有补偿的缩短了大约9ms,相应的动态特性指标也得到了较大的改善。把该算法用于对瓦斯传感器的非线性校正,大大提高了瓦斯检测的灵敏度和精度。
In order to improve the dynamic characteristics of the sensor and reduce the measurement error of the system, the basic principle of the sensor dynamic performance compensation is analyzed. The fuzzy RBF neural network is applied to the compensation of the sensor. The simulation results show that the output of the compensated sensor reaches the steady state shortened by about 9ms than that without compensation, and the corresponding dynamic characteristic index has also been greatly improved. The algorithm is applied to the non-linear calibration of gas sensors, which greatly improves the sensitivity and accuracy of gas detection.