An ANN approach for predicting the cutting inserts performances of different geometries in hard turning
Source abstract
Abstract
In this work an artificial intelligent (AI) technique viz. artificial neural network (ANN) is applied for predicting output responses such as wear occurring at the flank face of the cutting insert and the roughness of the machined workpiece's surface during the hard turning process. The experiments were designed using Taguchi's design of experiments (DoE) and suitable L18 orthogonal array (OA) was selected for the chosen parameters: cutting speed, feed rate, depth of cut, material hardness, cutting insert shape, relief angle, and nose radius. They are varied through three different levels. 18 different ISO designated cutting inserts were used for conducting the experiments on a CNC turning centre. An ANN model consisting of two hidden layers with 15 neurons each was modelled based on the complexity of the work. From the 18 experimental data, a set of 12 data was used for training the framed model and a set of 6 data for testing. An overall R-squared value of 0.9926 obtained during training the data showed the supremacy of the ANN technique. From the obtained results, it is obvious that the neural network models can be successfully used for predicting the output responses without performing the experiments.
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Advanced machining processes and optimization · Engineering Technology and Methodologies · Advanced Machining and Optimization Techniques
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References
Reference metadata was not supplied for this record.