A Fitting Approach of the Temperature Characteristic Curve of Sensor Based on the Recursive Least Squares Algorithm

摘要

To improve effectively temperature compensation characteristic of sensor, a method fitting the temperature characteristic curve was proposed. The simulating example of the sensitivity-temperature characteristic curve of sensor was given. The result shows that the temperature characteristic fitting curve of sensor using the neural network algorithm is very both smooth and accurate. The fitting precision is up to 10~(-6) . Therefore, the method of curve fitting based on the neural network algorithm is effective.