摘要
给出一种基于D-S证据理论的多传感器信息融合方法,并应用于某型船用柴油机故障检测中。首先,为克服人为因素和系统误差的干扰,在现场采集数据基础上,采用概率统计的方法来构造D-S证据理论的基本概率分配函数;然后,利用D-S证据理论对多传感器采集的信息进行融合;最后,将该方法应用于某型船用柴油机的故障检测中。实验结果表明,利用D-S证据理论解决了该型柴油机故障检测中多传感器信息融合问题,有效避免了人为因素的干扰,克服了单传感器信息的不确定性和片面性,提高了故障检测的准确度和可信度。
A method of multi-sensor information fusion is proposed based on D-S evidential theory,which is applied to fault detection of a certain marine diesel engine.At first,to avoid the negative effect of human factors and the system error,the basic probability assignment function （BPAF） is constructed by using probability statistics method based on field data acquisition.Then,the D-S evidential theory is applied to multi-sensor information fusion.Finally,this method is applied to fault detection of a certain marine diesel engine.The experiment results indicate that the problem of multi-sensor information fusion in the diesel engine fault detection is solved by using D-S evidential theory,and the human factors in constructing the basic probability assignment function and the uncertainty of single sensor information are avoided,and the accuracy and credibility are improved.
出处
《舰船科学技术》
北大核心
2014年第6期106-110,共5页
Ship Science and Technology
关键词
D-S证据理论
多传感器信息融合
故障检测
dempster-shafer evidential theory
multi-sensor information fusion
fault detection
