1 Introduction.In Model-Based Diagnosis(MBD),identifying the most likely faulty components necessitates first calculating candidate diagnoses for all components and then using Bayesian formulas to compute the posterio...1 Introduction.In Model-Based Diagnosis(MBD),identifying the most likely faulty components necessitates first calculating candidate diagnoses for all components and then using Bayesian formulas to compute the posterior probability of failure for each component[1].However,this process requires obtaining the minimal conflict sets(MCSs)for all components to compute all candidate diagnoses,followed by solving the minimal hitting sets(MHSs)of the MCSs,which involves addressing two NP-hard problems.展开更多
基金partially supported by the National Natural Science Foundation of China(Grant Nos.61876071,and 62076108)the Scientific and Technological Developing Scheme of Jilin Province(20180201003SF,20190701031GH).
文摘1 Introduction.In Model-Based Diagnosis(MBD),identifying the most likely faulty components necessitates first calculating candidate diagnoses for all components and then using Bayesian formulas to compute the posterior probability of failure for each component[1].However,this process requires obtaining the minimal conflict sets(MCSs)for all components to compute all candidate diagnoses,followed by solving the minimal hitting sets(MHSs)of the MCSs,which involves addressing two NP-hard problems.
