Aiming at the nonlinear temperature drift problem of a pressure scanner

a temperature compensation model based on the improved grey wolf optimization algorithm optimized back propagation neural network using the Bagging method in ensemble learning (IGWO-BP-Bagging)is proposed.Firstly

the linear factor

a

and the position update function of the GWO algorithm are improved.Then

the initial weights and biases of the BP neural network are optimized using the IGWO algorithm to obtain the IGWO-BP compensation model.Secondly

combining the concept of ensemble learning

the IGWO-BP-Bagging model is established using the Bagging method.Finall

y

the generalization performance of the IGWO-BP-Bagging model is tested.Experimental results show that compared to the BP neural network model

the maximum full-scale error on the test set of the IGWO-BP-Bagging model is improved from 0.0615%FS to 0.035%FS.