Device and method for tracking abnormal state judgment basis by using neural network model

The invention relates to a device for tracking an abnormal state judgment basis by using a neural network model, and the device comprises an abnormal type classification unit which is used for classifying an abnormal state into a plurality of faults in an abnormal operation scene in which a plurality of scenes related to the abnormal state are stored; an operation variable derivation unit for deriving, for each of the plurality of classified faults, an operation variable that affects an abnormal state determination result; the power plant operation variable weighting unit is used for weighting variables related to the abnormal state in the operation variables; and the abnormal state judgment basis generating unit is used for tracking an abnormal state judgment basis from an abnormal state judgment result generated by the power plant operation variable with the weight value. 本发明涉及一种使用神经网络模型跟踪异常状态判断依据的装置，包括：异常类型分类单元，其用于在存储有与所述异常状态相关的多个场景的异常运行场景中将异常状态分类为多个故障；运行变量推导单元，其用于针对经分类的多个故障中的每一个推导对异常状态判断结果产生影响的运行变量；电厂运行变量