Saman Malekian - Department of Industrial Engineering, Arak Branch, Islamic Azad University, Arak, Iran
Mohammad Izadikhah - Department of Mathematics, Islamic Azad University, Arak, Iran
Mohammad Ehsanifar - Department of Industrial Engineering, Arak Branch, Islamic Azad University, Arak, Iran

One of the problems facing plant managers, is evaluating the performance of different units. Maintenance groups that their job is to repair factory equipment and machinery are the units that evaluate their efficiency is very important because their accurate and timely performance will be reducing costs. Planning unit of Iranian Aluminum Company (IRALCO) evaluates these units monthly and the reports are presented to senior managers. This assessment is based on the difference between finished orders and requested orders, but the index is not appropriate. So, we use a chance-constrained DEA model with random input and output data on the input oriented. A super-efficiency model with chance constraints is used for ranking. However, for convenience in calculations a non-linear deterministic equivalent model is obtained to solve the models, the non-linear model is converted into a model with quadratic constraints to solve the non-linear deterministic model. Finally, twenty-eight maintenance groups of IRALCO evaluated with these models, that Repairs of pots unit selected as the best group, so, other groups can considering this unit and improve their efficiency.

Data Envelopment Analysis; chance constraints; random variables; quadratic constraints; Super-efficiency; IRALCO