Total quality management and quality engineering
S. Pal; S. Gauri
Abstract
In the real world, the overall quality of a product is often represented partly by the measured values of some quantitative variables and partly by the observed values of some ordinal variables. The settings for the manufacturing processes of such products are required to be optimized considering the ...
Read More
In the real world, the overall quality of a product is often represented partly by the measured values of some quantitative variables and partly by the observed values of some ordinal variables. The settings for the manufacturing processes of such products are required to be optimized considering the quantitative as well as the ordinal response variables. But the simultaneous optimization of the quantitative and the ordinal response variables are rarely attempted by the researchers. In this paper, a new approach for simultaneous optimization of quantitative and ordinal responses are presented, which are developed by integrating multiple regression techniques, ordinal logistic regression technique, and Taguchi’s Signal-to-Noise Ratio (SNR) concept. The effectiveness of the proposed method is evaluated by analyzing two experimental data sets taken from the literature. The comparison of results reveals that the proposed method leads to the best optimal solution with respect to the total SNR as well as the Mean Square Error (MSE) of individual responses