Applying nonlinear MODM model to supply chain management with quantity discount policy under complex fuzzy environment
Abstract: The aim of this
paper is to deal with the supply chain management (SCM) with quantity discount
policy under the complex fuzzy environment, which is characterized as the
bi-fuzzy variables. By taking into account the strategy and the process of decision
making, a bi-fuzzy nonlinear multiple objective decision making (MODM) model is
presented to solve the proposed problem.
Design/methodology/approach: The bi-fuzzy variables in the MODM model are
transformed into the trapezoidal fuzzy variables by the DMs's degree of
optimism ?1 and ?2, which are de-fuzzified by the expected value index
subsequently. For solving the complex nonlinear model, a multi-objective
adaptive particle swarm optimization algorithm (MO-APSO) is designed as the
solution method.
Findings: The proposed model and algorithm are applied to a typical
example of SCM problem to illustrate the effectiveness. Based on the
sensitivity analysis of the results, the bi-fuzzy nonlinear MODM SCM model is
proved to be sensitive to the possibility level ?1.
Practical implications: The study focuses on the SCM under complex fuzzy
environment in SCM, which has a great practical significance. Therefore, the
bi-fuzzy MODM model and MO-APSO can be further applied in SCM problem with
quantity discount policy.
Originality/value: The bi-fuzzy variable is employed in the nonlinear
MODM model of SCM to characterize the hybrid uncertain environment, and this
work is original. In addition, the hybrid crisp approach is proposed to
transferred to model to an equivalent crisp one by the DMs's degree of optimism
and the expected value index. Since the MODM model consider the bi-fuzzy
environment and quantity discount policy, so this paper has a great practical
significance.
Keywords: bi-fuzzy variable,
nonlinear, multi-objective programming, sensitivity analysis, particle swarm
optimization
Author: Zhe Zhang, Jiuping Xu
Journal Code: jptindustrigg140073
