Ground surface roughness is difficult to predict through a physical model due to its complex influencing factors. BP neural networks (BPNNs), a promising method, have been widely applied in the prediction of surface roughness. This paper uses the concept of BPNN to predict ground surface roughness considering the state of the grinding wheel. However, as the number of input parameters increases, the local optimum solution of the model that arises is more serious. Therefore, “identify factors” are designed to judge the iterative state of the model, whilst “memory factors” are designed to store the best weights during network training. The iterative termination conditions of the model are improved, and the learning rate and update rules of the weights are adjusted to avoid the local optimal solution. The results show that the prediction accuracy of the presented model is higher and more stable than the traditional model. Under three types of iteration steps, the average prediction accuracy is improved from 0.071, 0.065, 0.066 to 0.049, 0.042, 0.039 and the standard deviation of prediction decreased from 0.0017, 0.0166, 0.0175 to 0.0017, 0.0070, 0.0076, respectively. Therefore, the proposed method provides guidance for improving the global optimization ability of BPNNs and developing more accurate models for predicting surface roughness.

The crack distribution characteristics in grinding damage have a significant impact on subsequent polishing efficiency and part strength. Grinding tests were carried out on fused quartz using grinding wheels with different wear states. The results showed that the cracks produced by sharp abrasive grits were mainly near chevron cracks and had no preferred direction. However, the blunt abrasive grits produced near partial cone cracks had a preferred direction. At a depth of 96.7 μm from the surface, the amount of cracks in the range of 50°~90° with an inclination angle between the crack and the cutting direction could reach 88.9%. The statistical results showed that the depth and total length of cracks produced by sharp grits were larger than those produced by blunt grits (the maximum crack depth difference was about 40 μm). Therefore, it was concluded that sharp abrasive grits were not conducive to damage control. The findings of this research enhance our understanding of the formation mechanism of grinding damage.