Javad Makarian

Extensive research in smart manufacturing and industrial grinding has targeted the enhancement of surface roughness for diverse materials including Inconel alloy. Recent studies have concentrated on the development of neural networks, as a subcategory of machine learning techniques, to predict non-linear roughness behavior in relation to various parameters. Nonetheless, this study introduces a novel set of parameters that have previously been unexplored, contributing to the advancement of surface roughness prediction for the grinding of Inconel 738 superalloy considering the effects of dressing and grinding parameters. Hence, the current study encompasses the utilization of a deep artificial neural network to forecast roughness. This implementation leverages an extensive dataset generated in a recent experimental study by the authors. The dataset comprises a multitude of process parameters across diverse conditions, including dressing techniques such as four-edge and single-edge diamond dresser, alongside cooling approaches like minimum quantity lubrication and conventional wet techniques. To evaluate a robust algorithm, a method is devised that involves different networks utilizing various activation functions and neuron sizes to distinguish and select the best architecture for this study. To gauge the accuracy of the methods, mean squared error and absolute accuracy metrics are applied, yielding predictions that fall within acceptable ranges for real-world industrial roughness standards. The model developed in this work has the potential to be integrated with the Industrial Internet of Things to further enhance automated machining.

The significant effect of the dressing process on the surface of the grinding wheel (GW) and the need to provide an optimal dressing condition are the requirements of reduction machining time and energy consumption in the sustainable grinding process. In this study, for the first time, the results of changes in the parameters of the dressing process and changes in the topography of the grinding surface on the surface roughness of the Inconel 738 have been presented using single-edge and four-edge diamond dressers. The use of minimum quantity lubrication (MQL) and wet condition are other variables in this study to reduce the consumption of cutting fluid and prevent its destructive effects on the environment. The results indicate that the MQL technique increases the grinding performance of Inconel 738 by reducing ground workpiece surface roughness and decreasing the coolant–lubricant consumption comparing to the conventional wet grinding process. Additionally, it has been found from the experimental results that applying a single-edge dresser generates finer topography on the grinding wheel and, consequently, has a better surface finish in the grinding process compared to the multipoint diamond dressing tool with the same dressing and grinding parameters. In other words, increasing the dressing feed rate during dressing of the grinding wheel using a multipoint dresser makes a finer wheel surface topography and as a result decreases the surface roughness of the ground workpiece compared to a single-edge dresser. With multipoint diamond tools, the grinding performance during the life of the dressing tool also tends to remain more consistent, which is a definite advantage in automated production. Therefore, application of a multipoint dresser leads to a reduction in dressing time and increased production capability.