“…Bayesian Networks (BN), also known as Belief Network or Directed Acyclic Graphical Model (DAGM), consists of a Directed Acyclic Graph (DAG) and the corresponding conditional probability table, the nodes in the directed acyclic graph represent random variables, the directed edges between nodes represent the dependencies relationships between nodes, the direction of the edges is from the parent node to the child node, the two nodes The strength of the relationship between the nodes is expressed by the conditional probability, 6 VOLUME XX, 2017 and the information of the nodes without parent nodes is expressed by the prior probability. In recent years, Bayesian networks have been applied in many fields such as causal analysis [9], artificial intelligence [10], fault diagnosis [11,12], and medical research [13,14]. At present, Bayesian network structure learning has been proved to be an NP (Non-deterministic Polynomial Hard, NP-hard) problem.…”