Prediction of Machining Conditions Using Machine Learning

Main Article Content

Ashutosh Bhatt, Pooja Joshi, Gaurav Aggarwal


The new blast of Machine Learning (ML) and Artificial Intelligence (AI) shows extraordinary expectations in the forward leap of additive manufacturing (AM) process displaying, which is an important step toward determining the cycle structure-property relationship. The advancement of standard AI apparatuses in information science was primarily attributed to the extraordinarily huge amount of named informational collections, that may be obtained throughout the trials or first-rate reenactments. To completely take advantage of the force of AI in AM metal while lightening the reliance on "enormous information", everybody set an Improved Neural Network (INN) structure if the wires the two information and first actual standards include the preservation laws of energy, mass, and energies, towards the NN to illuminate the growing experiences. We suggest compressed-type strategies in the Dirichlet limit regulation in light of a Heaviside capability, that may precisely uphold the BCs and speed up the growing experience. The hotel structure was applied to two agent metal assembling issues, that includes the NIST AM-Benchmark series test. The examinations show that the Motel, owing to the extra actual information, may precisely foresee the temperature and also liquefy pool elements throughout the AM processes in metal along a moderate measure of named informational collections.

Article Details

How to Cite
Gaurav Aggarwal, A. B. P. J. (2024). Prediction of Machining Conditions Using Machine Learning. International Journal on Recent and Innovation Trends in Computing and Communication, 12(2), 194–199. Retrieved from