US 11,983,002 B2
Failure probability assessment system and method therefor
Hiroaki Amakawa, Tokyo (JP); Yosuke Ueki, Tokyo (JP); and Takahide Shinge, Tokyo (JP)
Assigned to Hitachi, Ltd., Tokyo (JP)
Appl. No. 17/622,572
Filed by Hitachi, Ltd., Tokyo (JP)
PCT Filed Jun. 10, 2020, PCT No. PCT/JP2020/022890
§ 371(c)(1), (2) Date Dec. 23, 2021,
PCT Pub. No. WO2021/005943, PCT Pub. Date Jan. 14, 2021.
Claims priority of application No. 2019-125861 (JP), filed on Jul. 5, 2019.
Prior Publication US 2022/0357734 A1, Nov. 10, 2022
Int. Cl. G05B 23/02 (2006.01)
CPC G05B 23/0283 (2013.01) [G05B 23/024 (2013.01)] 4 Claims
OG exemplary drawing
 
1. A system for assessing a failure probability of a target object, the system comprising:
a computer comprising one or more processors and memory, the computer configured to:
store, in a failure probability density function parameter database, past failure probability density function parameters for determining a failure probability density function of the target object;
store, in a failure history database, past failure history data for the target object;
store, in a time series operation database, time series operation data showing operational states of the target object;
generate survival analysis data using the past failure history data and the time series operation data;
identify the survival analysis data showing a variation of the failure probability density function of the target object that satisfies a predefined condition, wherein the variation of the failure probability density function of the target object is minimized;
estimate, using Bayesian estimation, a posterior probability distribution with a probability distribution determined based on the time series operation data, the survival analysis data and the past failure probability density function parameters;
calculate a present or future failure probability density function parameter from the posterior probability distribution; and
display an estimated failure probability of the target object.