Taguchi method for parameter design in ACO algorithm for distribution–allocation in a two-stage supply chain

• Published in: International journal of advanced manufacturing technology Vol. 64; no. 9-12; pp. 1333 - 1343
• Main Authors: Vinay, V. P., Sridharan, R.
• Format: Journal Article
• Language: English
• Published: London Springer-Verlag 01.02.2013; Springer Nature B.V
• Subjects: Algorithms; Ant colony optimization; CAE) and Design; Computer-Aided Engineering (CAD; Design parameters; Engineering; Industrial and Production Engineering; Mechanical Engineering; Media Management; Noise prediction; Original Article; Polynomials; Robust design; Signal to noise ratio; Supply chains; Taguchi methods; Transportation problem; Ant colony optimisation algorithm; Distribution–allocation; Fixed charge transportation problem; Taguchi method
• ISSN: 0268-3768; 1433-3015
• DOI: 10.1007/s00170-012-4104-5

In a distribution–allocation problem, when fixed cost for a transportation route is also taken into account in addition to the unit transportation cost, the problem is known as fixed charge transportation problem (FCTP). It is not possible to solve an FCTP optimally in polynomial time. This forces the researchers and practitioners to develop efficient non-traditional optimisation techniques that can provide near-optimal solutions in lesser time. This paper presents a solution methodology using ant colony optimisation (ACO) for a distribution–allocation problem in a two-stage supply chain with fixed cost for a transportation route. Taguchi method for robust design is adopted for finding the optimum combination of parameters of the ACO algorithm. A comparative analysis between the predicted signal-to-noise (S/N) ratio and the actual S/N ratio reveals that the error deviation in the experiment is minimal. From the confirmation tests, a good agreement between the predicted S/N ratio and the actual S/N ratio is observed. This validates the proposed experiment based on Taguchi method for parameter design.