Mar-M247 is a nickel-based alloy which is well known as difficult-to-machine material due to its characteristics of high strength, poor thermal diffusion and work hardening. Calculation of shear stress by an analytica...Mar-M247 is a nickel-based alloy which is well known as difficult-to-machine material due to its characteristics of high strength, poor thermal diffusion and work hardening. Calculation of shear stress by an analytical force model to indicate the effect of coating material, cutting speed, feed rate on tool life and surface roughness was conducted experimentally. Cutting tests were performed using round inserts, with cutting speeds ranging from 50 to 300 rn/min, and feed rates from 0.1 to 0.4 mm/tooth, without using cooling liquids. The behavior of the TiN and TiCN layers using various cutting conditions was analyzed with orthogonal machining force model. Cutting results indicate that different coated tools, together with cutting variables, play a significant role in determining the machinability when milling Mar-M247.展开更多
Experimentation data of perspex glass sheet cutting, using CO2 laser, with missing values were modelled with semi-supervised artificial neural networks. Factorial design of experiment was selected for the verification...Experimentation data of perspex glass sheet cutting, using CO2 laser, with missing values were modelled with semi-supervised artificial neural networks. Factorial design of experiment was selected for the verification of orthogonal array based model prediction. It shows improvement in modelling of edge quality and kerf width by applying semi-supervised learning algorithm, based on novel error assessment on simulations. The results are expected to depict better prediction on average by utilizing the systematic randomized techniques to initialize the neural network weights and increase the number of initialization. Missing values handling is difficult with statistical tools and supervised learning techniques; on the other hand, semi-supervised learning generates better results with the smallest datasets even with missing values.展开更多
文摘Mar-M247 is a nickel-based alloy which is well known as difficult-to-machine material due to its characteristics of high strength, poor thermal diffusion and work hardening. Calculation of shear stress by an analytical force model to indicate the effect of coating material, cutting speed, feed rate on tool life and surface roughness was conducted experimentally. Cutting tests were performed using round inserts, with cutting speeds ranging from 50 to 300 rn/min, and feed rates from 0.1 to 0.4 mm/tooth, without using cooling liquids. The behavior of the TiN and TiCN layers using various cutting conditions was analyzed with orthogonal machining force model. Cutting results indicate that different coated tools, together with cutting variables, play a significant role in determining the machinability when milling Mar-M247.
文摘Experimentation data of perspex glass sheet cutting, using CO2 laser, with missing values were modelled with semi-supervised artificial neural networks. Factorial design of experiment was selected for the verification of orthogonal array based model prediction. It shows improvement in modelling of edge quality and kerf width by applying semi-supervised learning algorithm, based on novel error assessment on simulations. The results are expected to depict better prediction on average by utilizing the systematic randomized techniques to initialize the neural network weights and increase the number of initialization. Missing values handling is difficult with statistical tools and supervised learning techniques; on the other hand, semi-supervised learning generates better results with the smallest datasets even with missing values.
