Hybrid NSGA-II for an imperfect production system considering product quality and returns under two warranty policies

• Published in: Applied soft computing 2019-02, Vol.75, p.333-348
• Main Authors: Taleizadeh, Ata Allah, Pourrezaie Khaligh, Pooya, Moon, Ilkyeong
• Format: Article
• Language: English
• Subjects: Metaheuristics; Non-dominated sorting genetic algorithm; Product quality; Warranty
• ISSN: 1568-4946; 1872-9681
• DOI: 10.1016/j.asoc.2018.11.013

This study presents a new bi-objective mathematical model for an imperfect production system (IPS) that accounts for product returns and quality levels under two different warranty policies. We considered uncertain customer demand as stochastic behavior and product price as a function of return compensation, product quality level, and warranty-period length. We simultaneously looked at the pro rata warranty and free replacement/repair warranty policies and assumed that customers can choose the desired policy. A return policy for an online distributor was also included and two objective functions were used to address the problem. The first objective function maximized the total expected revenue, and the second objective function maximized customer satisfaction. The non-dominated sorting genetic algorithm (NSGA-II) and two others, the basic bee metaheuristic and teaching-learning-based optimization algorithms, were used to generate the initial solution for use in the NSGA-II algorithm. The results from the hybrid algorithms revealed that the proposed method improves the performance of the NSGA-II algorithm. Finally, several specific sensitivity analyses were conducted to determine the effects of the problem parameters. •We developed a new bi-objective (profit and customer satisfaction) model for an imperfect production system.•A non-dominated sorting genetic algorithm was developed.•Uncertain customer demand is modeled as stochastic consumer behavior.•Two optional pro-rata warranty and free replacement/repair warranty policies are considered.