Research on forecasting approach of key parameters of PWR pressurizer water level

Abstract Nuclear power has special safety requirements and must be generated on the premise of nuclear safety. It is necessary to forecast abnormal situation system equipment as soon possible, so we can control accident beforehand prevent risk caused by failure accident. At present, pre-accident method in plant mainly relies subjective experience personnel. In contrast, intelligent forecasting timely reasoning change trend possible impact key safety-related parameters bring data reference staff plant, help before it happens effectively reduce probability occurrence. PWR(Pressurized Water Reactor), closely related primary loop such pressurizer water level. Adequate level ensure normal discharge reactor heat, changes may lead accidents. Therefore, our paper analyzes models function PWR, operation history this collected well. Then a network model built based transformer do information mining, which successfully pressurized provides for staff.