Temperature Online Monitoring System for Aerospace Manufacturing Process Based on Gradient Boosting Decision Tree (GBDT) Algorithm

The temperature measurement is important in aerospace manufacturing, with the increasing demand for online temperature monitoring. However, it is difficult to obtain high accuracy in traditional temperature detection methods using look-up tables and hardware compensation methods. This paper proposes an online temperature monitoring method for thermocouples based on the gradient boosting decision tree (GBDT) algorithm which enhanced the accuracy of cold end compensation and reduced nonlinear error of thermocouple during online temperature monitoring. Through experimental measurement, it can be seen that the accuracy of thermocouple online temperature monitoring improved by the gradient boosting decision tree algorithm provides a new method for online temperature monitoring in the aerospace manufacturing process.