Machining quality monitoring of blades and source tracing based on dynamic Bayesian network

A methodology of monitoring the machining quality of blades and tracing the error source based on dynamic Bayesian network is proposed for solving the low accuracy of blade machining quality. Dynamic Bayesian network is used to establish the relationship between blade machining operations to realize the control of the whole machining process. The causal relation between the elements in the main process factor set that affects blade machining operations is built by Bayesian network. The control chart T² is used to monitor the factor set of each operation to judge whether the operation is out of control or not. While tracing error sources, the T² statistics of the samples out of control are decomposed according to causal variables described by aforementioned causal relation, and the decomposed variable control limits are built as error source judgment conditions are built. A simulation study on a blade machining process is carried out, which demonstrates that the proposed method is reasonable.