On utility of inductive learning in multiobjective robust design

Abstract

Most engineering design problems involve optimizing a number of often conflicting performance measures in the presence of multiple constraints. Traditional vector optimization techniques approach these problems by generating a set of Pareto-optimal solutions, where any specific objective can be further improved only at the cost of degrading one or more other objectives. The solutions obtained in this manner, however, are only single points within the space of all possible Pareto-optimal solutions and generally do not indicate to designers how small deviations from predicted design parameters settings affect the performance of the product or the process under study.In this paper we introduce a new approach to robust design based on the concept of inductive learning with regression trees. Given a set of training examples relating to a multiobjective design problem, we demonstrate how a multivariate regression tree can utilize an information-theoretic measure of covariance complexity to capture optimal, tradeoff design surfaces. The novelty of generating design surfaces as opposed to traditional points in the design space is that now designers are able to easily determine how the responses of a product or process vary as design parameters change. This ability is of paramount importance in situations where design parameter settings need to be modified during the lifetime of a product/process due to various economic or operational constraints. As a result, designers will be able to select optimal ranges for design parameters such that the product's performance indices exhibit minimal or tolerable deviations from their target values. To highlight the advantages of our methodology, we present a multiobjective example that deals with optimum design of an electric discharge machining (EDM) process.

A survey on automating configuration and parameterization in evolutionary design exploration

“…Starting from the problem of finding a frame geometry with optimal load characteristics, Hanna (2007) applied the SVM technique to learn a classification that conversely identifies adequate frame constructions for given loads. Forouraghi (1999) used multivariate regression trees to determine variant groups that optimally fulfill a goal function. These groups define ranges for design variables that should be obeyed in order to optimize the objective functions.…”

“…Relating engineering characteristics to requirements (Kwong et al, 2011;Yang & Chen, 2014) 3 † Relating structural attributes to behavioral attributes (Szczepanik et al, 1995;Skibniewski et al, 1997;Ivezic & Garrett, 1998;Reich & Barai, 1999;Neocleous & Schizas, 2002) 3 † Learning metamodels for evaluation in order to Replace costly evaluation functions (Perez & Behdinan, 2002;Lin, 2003) 2 † Broaden the applicability of evaluation functions by abstracting from existing relations (Bhatta & Goel, 1994;Chabot & Brown, 1994;Reffat & Gero, 2000) 2 † Restrict the feasible design space with respect to identified Chunks (Moss et al, 2004;Mukerjee & Dabbeeru, 2012) 4 † † † Design rules (Gero et al, 1994;Forouraghi, 1999;Hanna, 2007;Yogev et al, 2010)…”

Challenges to Bayesian decision support using morphological matrices for design: empirical evidence

“…There has also been work in categorising risks and using this to indicate promising design directions Raine, 2004, 2005). Nonstochastic approaches to risk modelling include inducing regression trees to identify paretooptimal designs (Forouraghi, 1999) and using utility function based approaches for risk mitigation based on designer preferences (Fernandez et al, 2005).…”

An investigation into the ultrasonic machining of co-based super alloy using the Taguchi approach

“…The results show a significant improvement in performance compared with the conventional solution. Design optimisation problem is a cost-effective method for improving product/process quality that is determined by an optimal set of values for controllable variables (CVs), from the point of view of its robustness against various uncontrollable variables (UCVs) (Forouraghi, 1999). Variables are things that we measure, control or manipulate in research.…”