Data rectification based on Bayesian network

Mass balance model is the basis of data rectification, however, in industrial applications, model is changed when scheduling is performed. There are few good ways to deal with this problem. A new method is thus proposed based on Bayesian network, which can be used to put discussions about causality on a solid mathematical basis. By using Bayesian network scheme can be inferred from key variables. Accordingly, mass balance equation is modified in time when the scheduling events happen. In this way, the feasibility of data rectification is enhanced, so reliable information can be provided for ClMS (computer integrated manufacture system).