Suleiman Obeidat

Mathematical Foundations for Form Inspection and Adaptive Sampling

Nonlinear forms such as the cone, sphere, cylinder, and torus present significant problems in representation and verification. In this paper we examine linear and nonlinear forms using a heavily modified support vector machine (SVM) technique. The SVM approach applied to regression problems is used to derive quadratic programming problems that allow for generalized symbolic solutions to nonlinear regression. We have tested our approach to several geometries and achieved excellent results even with small data sets, making this method robust and efficient. More importantly, we identify process or inspection tendencies that could help in better designing the processes. Adaptive feature verification can be achieved through effective identification of the manufacturing pattern.

Six Sigma implementation to minimise weight variation for Baby Lido Diaper manufacturing company

The increasing demand in baby diaper products in addition to customer requirements has compelled companies to improve the quality of their production processes. This paper presents a customised Six Sigma procedure to reduce weight variation in diaper products. To this end, a define, measure, analyse, improve and control (DMAIC) model is developed and applied at a production line at a local company to identify and control root causes. Thorough analysis of collected data revealed that excess fluff, sap and pulp are the main causes for variations. As a result, several changes have been adopted at the improvement phase; these improvements decreased defects per million opportunities (DPMO) form 292,157 to 88,152 and increased the sigma level from 2.05 to 2.85.