iDCR: Improved Dempster Combination Rule for Multisensor Fault Diagnosis
This work addresses a specific issue in fault diagnosis for engineering applications, offering an incremental improvement to a known method.
The paper tackles the problem of counter-intuitive results in multi-sensor fault diagnosis when using Dempster's Combination Rule under high conflict, proposing an improved rule that shows effectiveness and superiority over existing methods in numerical examples and comparative analysis.
Data gathered from multiple sensors can be effectively fused for accurate monitoring of many engineering applications. In the last few years, one of the most sought after applications for multi sensor fusion has been fault diagnosis. Dempster-Shafer Theory of Evidence along with Dempsters Combination Rule is a very popular method for multi sensor fusion which can be successfully applied to fault diagnosis. But if the information obtained from the different sensors shows high conflict, the classical Dempsters Combination Rule may produce counter-intuitive result. To overcome this shortcoming, this paper proposes an improved combination rule for multi sensor data fusion. Numerical examples have been put forward to show the effectiveness of the proposed method. Comparative analysis has also been carried out with existing methods to show the superiority of the proposed method in multi sensor fault diagnosis.