quantum machine learning approach for the prediction of surface roughness in additive manufactured specimens

One of the most important factors affecting the functioning and performance of additively produced components is surface roughness. precise estimation of surface roughness is essential for streamlining production procedures and guaranteeing product quality. recently, quantum computing has drawn interest as a possible way to solve challenging issues and produce accurate prediction models. for the first time, we compare three quantum algorithms in-depth in this research paper for surface roughness prediction in additively manufactured specimens: the quantum neural network (qnn), quantum forest (q-forest), and variational quantum classifier (vqc) modified for regression. mean squared error (mse), mean absolute error (mae), and explained variance score (evs) are the assessment metrics we use to evaluate the algorithms’ performance. with an mse of 56.905, an mae of 7.479, and an evs of 0.2957, the q-forest algorithm outperforms the other algorithms, according to our data. on the other hand, the qnn method shows a negative evs of -0.444 along with a higher mse of 60.840 and mae of 7.671, suggesting that it might not be the best choice for surface roughness prediction in this application. the regression-adapted vqc has an mse of 59.121, an mae of 7.597, and an evs of -0.0106, indicating that it performs inferior to the q-forest approach as well.