TY - GEN

T1 - Statistical machine learning for the cognitive selection of nonlinear programming algorithms in engineering design optimization

AU - Hoeltzel, D. A.

AU - Chieng, Wei-Hua

N1 - Publisher Copyright:
© 1987 American Society of Mechanical Engineers (ASME). All rights reserved.

PY - 1987/9/27

Y1 - 1987/9/27

N2 - In order to overcome the problem of lack of generality in nonlinear programming (NLP) test problem formulation and to introduce the concept of cognitive NLP method switching, statistical machine learning has been applied to a sample data base of nonlinear programming problems. Reasonable conclusions have been drawn about an optimization problem type and a corresponding sequence of NLP solution algorithms using statistical pattern recognition applied to local (vs. global) design information. A program, referred to as OPTDEX-OLDM, with the capability of learning from statistical pattern recognition is discussed. The statistical aspects and algorithmic optimization of the nonlinear programming problem are emphasized in this discussion. A clustering process has been performed on attributes assigned to the NLP problem sample data base, and an example which describes this statistical clustering process is discussed.

AB - In order to overcome the problem of lack of generality in nonlinear programming (NLP) test problem formulation and to introduce the concept of cognitive NLP method switching, statistical machine learning has been applied to a sample data base of nonlinear programming problems. Reasonable conclusions have been drawn about an optimization problem type and a corresponding sequence of NLP solution algorithms using statistical pattern recognition applied to local (vs. global) design information. A program, referred to as OPTDEX-OLDM, with the capability of learning from statistical pattern recognition is discussed. The statistical aspects and algorithmic optimization of the nonlinear programming problem are emphasized in this discussion. A clustering process has been performed on attributes assigned to the NLP problem sample data base, and an example which describes this statistical clustering process is discussed.

UR - http://www.scopus.com/inward/record.url?scp=85105535066&partnerID=8YFLogxK

U2 - 10.1115/DETC1987-0009

DO - 10.1115/DETC1987-0009

M3 - Conference contribution

AN - SCOPUS:0023570447

SN - 9780791897737

T3 - Proceedings of the ASME Design Engineering Technical Conference

SP - 67

EP - 74

BT - Design Methods, Computer Graphics, and Expert

PB - American Society of Mechanical Engineers (ASME)

T2 - ASME 1987 Design Technology Conferences, DETC 1987

Y2 - 27 September 1987 through 30 September 1987

ER -