Development of Mathematical Model for Quality-Cost Optimization  
Author N. V. R. Naidu


Co-Author(s) M. Shilpa


Abstract Variation can be viewed as lack of consistency in product performance which gives rise to poor quality. This variation consists of two elements: deviation from the target and variation with respect to others in the group. Taguchi‟s parameter and tolerance design are aimed at reducing both these elements of variation to a great extent. Parameter design determines the right combination of factor levels to obtain optimal results. Selection of optimal levels makes the product / process less sensitive to variations, making it more robust and hence, there is no cost associated with parameter design. Tolerance design is a very important stage of product / process design, which is carried out after parameter design for economic reasons [1]. During this stage appropriate tolerances around the best value are determined. The global world market and the needs of the industry have driven a demand for efficient design and drafting skills, particularly about tolerances. All costs incurred during the product life cycle are divided into two broad categories - processing cost before the product is sold and quality loss after the product is shipped to the customer. The processing cost increases if tighter tolerances are provided around the best or target value. If wide tolerances are provided, product quality diminishes resulting in large quality loss [9]. In the literature [5], mathematical models have been developed to determine optimal tolerances for quality – cost optimization for Nominal – The – Best (NTB) and Smaller – The – Better (STB) types of quality characteristics. In this paper, an attempt is made to develop mathematical model to determine optimum tolerance for Larger – The – Better (LTB) quality characteristic.


Keywords Tolerance design, Larger-the-better quality characteristic, quality loss function, manufacturing cost.
    Article #:  2117
Proceedings of the 21st ISSAT International Conference on Reliability and Quality in Design
August 6-8, 2015 - Philadelphia, Pennsylvia, U.S.A.