Use of Response Surface Methodology and Exponential Desirability Functions to Paper Feeder Design

Applying parameter design to a system that has a binary-type performance, an efficient metric is to employ the operating window (OW) which is the range between two performance limit thresholds. Paper feeder design is a typical problem of the OW method. The wider OW, the higher performance of the system is. This study uses an approach based on artificial neural networks (ANN) and desirability functions to optimizing the OW design of a paper feeder. The approach employs an ANN to construct the response function model (RFM) of the OW system. A novel performance measure (PM) is developed to evaluate the OW responses. Through evaluating the PM of the predicted OW responses, the best control factor combination can be obtained from the full control factor combinations. A simulated example of a paper feeder design is analyzed. Performing the approach to parameter design problems, engineers do not require much background in statistics but instead rely on their knowledge of engineering. Key-Words: Artificial Neural Networks, Exponential Desirability Functions, Operating Windows, Response Surface Methodology, Response Function Model, Paper Feeder Design