Research on Minimum Wall Thickness Prediction of Pressure Vessel Based on Bayesian Optimization BP Neural Network
The minimum wall thickness of pressure vessels plays an important role in the structural strength and stability of pressure vessels.In view of this,the Bayesian optimisation method combined with BP neural network is used to achieve accurate prediction of the minimum wall thickness of pressure vessels.First,the Bayesian method is used to optimise the number of neurons in the hidden layer to obtain the optimal number of neurons in the hidden layer.Then,the model is trained using this optimal number of neurons.Finally,the validation set is input into the model for validation to obtain the prediction of the minimum wall thickness of the pressure vessel.The results show that the model based on the Bayesian approach to optimise the BP neural network is able to accurately predict the minimum wall thickness of the pressure vessel cylinder and head with a mean square error of only 0.267 8 and 0.744 8,and the model is able to provide a more reliable design and decision-making basis,which can make an important contribution to the improvement of the efficiency and safety of the structural design of pressure vessels.
万方数据
维普
