A neural-network-based methodology is proposed for predicting the surface roughness in a turning process by taking the acceleration of the radial vibration of the tool holder as feedback. Upper, most likely and lower estimates of the surface roughness are predicted by this method using very few experimental data for training and testing the network. The network model is trained using the back-propagation algorithm. The learning rate, the number of neurons in the hidden layer, the error goal, as well as the training and the testing dataset size, are found automatically in an adaptive manner. Since the training and testing data are collected from experiments, a data filtration scheme is employed to remove faulty data. The validation of the methodology is carried out for dry and wet turning of steel using high speed steel and carbide tools. It is observed that the present methodology is able to make accurate prediction of surface roughness by utilising small sized training and testing datasets.
Thick-walled cylinders such as gun barrels, high pressure containers, and rocket shells are designed to withstand high pressure. The cylinder material may crack if the induced pressure exceeds the material yield strength. Therefore, the thick-walled cylinders are autofrettaged in order to withstand very high pressure in service condition. The most commonly practiced autofrettage processes are hydraulic autofrettage and swage autofrettage. Hydraulic autofrettage involves very high internal pressure at the bore of the cylinder, and in swage autofrettage an oversized mandrel is pushed through the cylinder bore to cause the plastic deformation of the inner wall of the cylinder leaving the outer wall at the elastic state. This results in compressive residual stresses at and around the inner wall of the cylinder, which reduces the maximum stress in the cylinder during next stage of loading by pressurization. Both the processes are well established, but still there are certain disadvantages associated with the processes. The present work proposes a novel method of autofrettage for increasing the pressure carrying capacity of thick-walled cylinders. The method involves only radial temperature gradient in the cylinder for achieving autofrettage. The proposed process is analyzed theoretically for thick-walled cylinders with free ends. The numerical simulations of the process for typical cases and preliminary experiments show encouraging results for the feasibility of the proposed autofrettage process.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.