سیستم پیش بینی مبتنی بر مدل خاکستری برای جریان بازگشتی وسایل نقلیه پایان عمر  Grey modelling based forecasting system for return flow of end-of-life vehicles

1. Introduction Growing interest in the reuse and recovery of products and materials has resulted from the scarcity of natural resources and raw materials, environmental reasons and governmental regulations about end-oflife products. Effective and efficient management of a series of activities required to retrieve a product from a customer and either recover value or dispose of it defines reverse supply chain management (Prahinski and Kocabasoglu, 2006). Managing product recovery operations efficiently is a challenging problem because of uncertainty in terms of the quantity, time and quality of the returned products. Return reasons of products can be classified as manufacturing-related returns, distribution-related returns and customer/user returns (De Brito and Dekker, 2002). For any type of return flow, assessment of the expected quantity, timing or location of return will provide insight to the managers of the reverse supply chain (Thierry et al., 1995). Main theme of this paper is management of return flow of end-oflife products by providing a supportive forecasting tool. Forecasting the return flow of an end-of-life product is important for all decision levels of the reverse supply chain, including network design decisions at the strategic level, capacity planning decisions at the tactic level and production planning and inventory control decisions at the operational level (Toktay et al., 2003). Managing product return flows will be beneficial for the stability and profitability of a reverse supply chain. The automotive industry is one of the largest industries in most countries because of its significant contributions to the economy. The increase in the production and sales of the automotive industry will also increase the number of end-of-life vehicles (Tian and Chen, 2014). Moreover, as reported by European Environment Agency (EEA) due to tighter environmental regulations, improvement in the environmental performance of new vehicles will result in rapid replacement of old vehicles with new ones (EEA, 2009). The European Automotive Manufacturers Association (ACEA) reported that, in 2014, 90.6 million motor vehicles were produced globally and 89.3 million vehicles were sold worldwide (ACEA, 2015). Considering the perspective of Turkey, according to the Turkish Statistical Institute (TURKSTAT), the number of registered vehicles on the roads in Turkey increased 83.9% in the years 2004–2014 and reached nearly 19 million vehicles. The number of vehicles on the road increases by an average of 860,000 annually. In addition, in the years 2005–2014, 729,212 motor vehicles were scrapped in Turkey for recovery and recycling operations (TURKSTAT, 2015). Vehicles are strong pollutants during their useful life and at the end-of-life stage (Mahmoudzadeh et al., 2013), so a reverse supply chain should be formed to manage end-of-life vehicles’ product recovery operations. In this context, forecasting the return flow of end-of-life vehicles is critical for constructing a reliable and profitable reverse supply chain (Govindan et al., 2015), and is main topic of this study. The topic is of interest to the managers and practitioners of the reverse supply chain or related economic operators.