Narrow Results

Most of the researchers have developed Artificial Neural Network (ANN) models to forecast the cutting tool life based on whether it has either a flank wear or a crater wear or a nose wear. In this paper, an attempt has been made to classify the cutting tool wear based on whether it has flank wear, chipped-off cutting edge or a combination of both failures. To obtain the experimental results, both the failures namely flank wear and chipped-off cutting edge have been produced using Electric Discharge Machining (EDM) process. Experiments were carried out using cemented carbide-coated inserts on EN-8 steel and all the responses were acquired by using virtual instruments. The acquired data were analyzed to develop the ANN models to forecast the condition of cutting tool. Vibration and strain data were recorded using accelerometer and strain gauge half-bridge circuit.

The Johnson–Cook model is the popular constitutive relation for the simulation of metal cutting process because of the availability of various sets of parameters for different materials. Different sets of Johnson–Cook parameters are observed to be available for a particular material due to dissimilarity in the initial condition of the material and experimental methods utilized for the calibration. Hence, it is difficult to choose an accurate parameter set for modeling the behavior of a material for the finite element simulation of its cutting process. In this regard, a strategy is proposed and validated in this study for choosing an accurate Johnson–Cook parameter set for Inconel 718. Twelve sets of Johnson–Cook parameters were collected from the literature for Inconel 718 and their flow stress predictions were investigated by comparing with experimental flow stress values for wide ranges of strain rates and temperatures as encountered during the cutting process. The Johnson–Cook parameter sets corresponding to the predicted flow stress curves that agree with the experimental values are chosen for modeling the behavior of Inconel 718. This comparison also helps in indexing the parameter sets according to the initial condition of the material since it is not reported mostly in the literature. The chosen material parameter sets are validated further for the orthogonal cutting simulation of Inconel 718 for a wide range of cutting conditions by comparing the cutting force and chip thickness predictions with the experimental values. Thus, the analysis of predicted flow stress values helps in choosing the accurate Johnson–Cook parameters for an Inconel 718 specimen which in turn helps in conducting accurate orthogonal cutting simulations. The finite element simulation of metal cutting helps in identifying the optimum cutting parameters which would help to reduce energy consumption and thus make the process more efficient and sustainable.

Metal cutting is an important process in industrial manufacturing. Using the mechanical quantities of metal cutting to optimize process design is helpful to improve productivity. However, it is expensive to obtain these quantities due to the complexity of the cutting process, including material nonlinearity, geometric nonlinearity, state nonlinearity and their interactions. In this paper, a prediction model is constructed by combining machine learning (ML) and simulation data to quickly acquire multi-difficult-to-obtain metal cutting mechanical quantities to solve this problem. First, Adaptive Smoothed Particle Hydrodynamics (ASPH) is used to generate a simulation dataset of 2000 metal cutting cases. Based on the simulation data, six machine learning (ML) methods are employed to establish two prediction models, single-task learning and multi-task learning, to predict the mechanical quantities of metal cutting. The experimental results demonstrate that the ML method can predict abundant reference data efficiently after understanding the relationship between simulation parameters and mechanical quantities from simulation data, which is expected to replace some similar and repetitive simulation work. The Multilayer Perceptron (MLP) model under the multi-task setting provides the best prediction performance, fastest prediction time efficiency, and stable model behavior. Additionally, input erasure experiments reveal that the prediction of maximum equivalent plastic strain is significantly affected by particle spacing, and cutting speed plays a vital role in predicting maximum velocity. This work highlights the promotion of the data-driven ML method in quickly obtaining abundant reference data for the metal cutting process, and provides an auxiliary means for process optimization.

This study determined the optimum HSS cutting tool technique parameters for milling W-Al-Si-C rods using Taguchi methodology. This paper explains the empirical results of the selection of appropriate cutting settings that assure lower power consumption in high-end Computer Numerical Control (CNC) machines. An experiment employing the Taguchi methodology on an extruded W-Al- Si-C rod was performed on a CNC lathe with cutting speed, feed rate, and depth of cut as the process parameters. The performance characteristics (energy usage) were quantified by a data collection system. Minor energy process parameters were selected after data analysis. Experimental results are presented to demonstrate the worth of the chosen methodology. A total of 350rpm, 0.37mm/rev feed rate, and 1mm of cut depth produced the best MRR result. The maximum material removal rate (MRR) is obtained at lower levels of spindle speed and depth of cut, i.e., 1.452g/sec.

Computer simulation of the metal cutting process has been done for von Mises yielding criterion and Prandtl-Reuss flow rule. Based on the physical model, mathematical modeling is brought forth with modified lagrangian matrix equation. Super-over-relaxation method is applied for solving the elastro-plastic deformation problems. Programs for grid plotting, calculating and graphically-reporting are edited and successfully executed. Experiments have shown that the simulating system is able to supply the reliable and acceptable decision-making of the machining design for technicians or workers.