Among various optimization problems that the steel industry is facing, we are tackling some discrete optimization problems related to production design and operations scheduling. Most of these problems have been regarded as so hard that only experienced experts can handle them and the problems are considered too hard for computers to tackle. Thanks to the development of optimization techniques in the areas of operations research and artificial intelligence and to increases of computing power, computers can now handle some very large problems that even human experts cannot handle, and computers can even outperform human experts, producing higher quality solutions. IBM Tokyo Research Laboratory, jointly with IBM Watson Research Center, has been researching optimization techniques for various hard optimization problems, and developing a library of optimization solutions called PDOS (Production Design and Operations Scheduling). PDOS is composed of six optimization modules: Inventory Application, Slab Design, Plate Design, Melting Shop Scheduling, Hot Mill Scheduling, and Finishing Line Scheduling. PDOS has been successfully delivered to many clients.
Six optimization modules of PDOS