Genetic algorithm optimization based on manufacturing prediction for an efficient tolerance allocation approach

The tolerance allocation is an extremely sensitive task due to the complex effects on quality, product, and cost. Thus, tolerance allocation optimization covers design and manufacturing aspects and can help to bridge the gap between tolerance design and manufacturing process. Consequently, the objective of this paper is to establish a tolerance optimization method based on manufacturing difficulty computation using the genetic algorithm method with optimum parameters. To do this, the objective function of the proposed GA algorithm is to minimize the total cost. The proposed GA constraints are the tolerance equations of functional requirements considering difficulty coefficients. The manufacturing difficulty computation is based on tools for the study and analysis of reliability of the design or the process, as the Failure Mode, Effects and Criticality Analysis (FMECA) and Ishikawa diagram. The proposed approach, based on combining the Difficulty Coefficient Computation (DCC) and the GA optimization method produces the GADCC tool. This model is applied on mechanical assemblies taken from the literature and compared to previous methods regarding tolerance values and computed total cost. This comparative study highlights the benefits of the accomplished GADCC optimization method. The results lead to obtain optimal tolerances that minimize the total cost and respect the functional, quality and manufacturing requirements.

Automated summary

This paper aims to establish a tolerance optimization method based on manufacturing difficulty computation using genetic algorithm. The proposed method combines difficulty coefficient computation and genetic algorithm optimization to minimize total cost and meet functional requirements. The results show the advantages of this optimization method compared to other methods through the application on mechanical assemblies.