Abstract The problem of optimization is fundamental to various branches of Science and Engineering.
In CAD and CAM, a present optimization problem is one of searching for patterns in given data which is necessary for recognizing shapes, assessing quality of manufactured goods etc. for the purpose of advanced robotic assisted Manufacturing. In this work, we have developed optimization code using logistic regression. This code can be very useful for manufacturing processes for separating manufactured goods into acceptable and non-acceptable classes. Machine Learning (ML) is a developing branch of science and will be widely applied in Manufacturing in the years to come. The classical optimization problems and their solutions using linear and logistic regression are well suited for ML. In this project we will built a regularized logistic regression optimization problem model for the ML in manufacturing process. We will implement regularized logistic regression to predict whether microchips from a fabrication plant pass Quality Assurance (QA). During QA , each microchip goes through various tests to ensure it is functioning correctly. To make decision, we have data set of test results of past microchips, from which we built a logistic regression model.
Keywords: Optimization, Manufacturing, Machine Learning (ML), logistic regression
|
DOI:
10.17148/IARJSET.2018.5710