基于BN和A-star的矿井提升机制动系统故障诊断

Fault Diagnosis for Braking System of Mine Hoist Based on BN and A-star

针对提升机制动系统故障诊断推理不确定因素多及故障诊断中推理不准确等问题,提出了贝叶斯网络和改进的A-star推理算法相融合的不确定性推理故障诊断方法。首先利用组态王进行数据的采集,并将采集到数据库中的数据用MATLAB进行预处理,将得出的结果导入到Netica软件中进行参数学习和不确定推理,最后利用改进的A-star算法搜索出发生故障最大的路径,并按路径排除故障。经实验验证:该故障诊断方法具有较高的准确性和稳定性。

The fault diagnosis for braking system of hoist existed many uncertainty factors and inaccurate results. Aimed at the problems, an uncertain fault diagnosis method based on Bayesian network and improved A-star algorithm was proposed. First-ly, the data was collected by Kingview, and was transmitted to the database. Then, the data in database was preprocessed by MATLAB, and the results were imported into the Netica software for parameter learning and uncertainty reasoning. Finally, the improved A-star algorithm was used to search for the path with the largest fault, and the fault was eliminated according to the path. The experimental results proved that this fault diagnosis method had high accuracy and stability.