Abstract
It is difficult to accurately predict the surface roughness of belt grinding with superalloy materials due to the uneven material distribution and complex material processing. In this paper, a radial basis neural network is proposed to predict surface roughness. Firstly, the grinding system of the superalloy belt is introduced. The effects of the material removal process and grinding parameters on the surface roughness in belt grinding were analyzed. Secondly, an RBF neural network is trained by reinforcement learning of a self-organizing mapping method. Finally, the prediction accuracy and simulation results of the proposed method and the traditional prediction method are analyzed using the ten-fold cross method. The results show that the relative error of the improved RLSOM-RBF neural network prediction model is 1.72%, and the R-value of the RLSOM-RBF fitting result is 0.996.
Highlights
Roughness of Abrasive Belt GrindingSuperalloy at high temperatures has excellent strength, good oxidation resistance, and thermal corrosion resistance properties
This paper improves the self-organization map (SOM) method through reinforcement learning (RL), designs belt-grinding experiments, analyzes the effectiveness of the method, and uses experimental data as training samples and the error curved surface model, the model error, training results, and changes of the parameters as standards to further verify that the proposed method can be used for surface roughness prediction of abrasive belt grinding with superalloy materials
By analyzing the errors and training results of the three algorithm models it can be determined that the RLSOM-radial basis function (RBF) neural network prediction model is more effective than the other two (BP model and SOM-RBF model) in predicting the surface roughness of superalloy under abrasive belt grinding
Summary
Superalloy at high temperatures has excellent strength, good oxidation resistance, and thermal corrosion resistance properties. The RLSOM-RBF (radial basis function) method is proposed for the uneven distribution of abrasive particles in belt grinding to solve the problem whereby the nonlinear relationship between process parameters and surface roughness is not easy to predict. This paper improves the self-organization map (SOM) method through reinforcement learning (RL), designs belt-grinding experiments, analyzes the effectiveness of the method, and uses experimental data as training samples and the error curved surface model, the model error, training results, and changes of the parameters as standards to further verify that the proposed method can be used for surface roughness prediction of abrasive belt grinding with superalloy materials. Prediction Model of Surface Roughness of Abrasive Belt Grinding of Superalloy Material
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
