Page 183 - Data Science Algorithms in a Week

The Estimation of Cutting Forces in the Turning of Inconel 718 Assisted … 167

CONCLUSION

In this study, three different ANN models for estimation of cutting force components
in turning of Inconel 718 under HPC conditions were developed. The considered process
parameters include diameter of the nozzle, distance between the impact point of the jet
and the cutting edge, pressure of the jet, cutting speed, and feed. First, cutting forces were
modeled by using conventional multilayer feed-forward ANN trained using a BP
algorithm. These model were found to predict the output with the 94.9%, 94.2% and
93.9% accuracy, for main cutting force, feed force and passive force, respectively. These
results indicate good agreement between the predicted values and experimental values.
However, due to the limitations of BP-based ANN, such are risk of being trapped in local
minima, very slow convergence rate in training, etc. an effort was made to apply two
bio-inspired algorithm, namely GA and PSO, as a training methods of ANN. The results
obtained indicated that GA-based ANN can be successfully used for predicting of main
cutting force, feed force and passive force, with the 96.2%, 94.7% and 95.8% accuracy,
respectively. The predicted results of PSO-based ANN have accuracy of 96.2%, 96.3%
and 96.2%, for main cutting force, feed force and passive force, respectively. It is evident
that results obtained using the GA-based and PSO-based ANN models are more accurate
compared to BP-based ANN. However, PSO-based ANN model predicted cutting force
components with better accuracy compared to the GA-based ANN model. Hence, the
learning of ANN using bio-inspired algorithms can significantly improve the ANN
performance, not only in terms of precision, but also in terms of convergence speed. The
results showed that the GA-based and PSO-based ANN can be successfully and very
accurately applied for the modeling of cutting force components in turning under HPC
conditions.

REFERENCES

Alajmi, M. S. & Alfares, F. (2007). Prediction of cutting forces in turning process using
de-neural networks.
Aykut, Ş., Gölcü, M., Semiz, S. & Ergür, H. (2007). Modeling of cutting forces as
function of cutting parameters for face milling of satellite 6 using an artificial neural
network. Journal of Materials Processing Technology, 190(1), 199-203.
Cica, D., Sredanovic, B., Lakic-Globocki, G. & Kramar, D. (2013). Modeling of the
cutting forces in turning process using various methods of cooling and lubricating: an
artificial intelligence approach. Advances in Mechanical Engineering.