Combined Uncertainty Evaluation of Personal Computer Failure Event Caused by Voltage Sag

The paper proposes a method based on maximum hybrid entropy (MHE) to assess the uncertainty of equipment failure event caused by voltage sag. By considering the data characteristics of the tested samples, the combined uncertainty is decomposed into a random, a fuzzy, and a cross uncertainty. As a case study, PC is tested and assessed when it is in full speed, no-load and normal operation states. During voltage sags, PC is in different result states, such as completely crash, operating error, or false crash. The proposed method is applied to assess the failure rate and compared with existing probability methods and fuzzy methods. The results show that this method overcomes the disadvantages of over-estimating or low-estimating problem and it is more accurate in accord with the engineering practice.