Adaptive preventive maintenance for computing systems

摘要

Systems, methods, and other embodiments associated with adaptively determining a preventive maintenance schedule based on historical system operation are described. The prognostic parameter values are continuously partitioned into a number of operating states based on observed maintenance costs associated with the prognostic parameter values. The operating states range from absolutely healthy, one or more degrees of degradation, to fully degraded. A system cost function is used as the discriminant function. The system cost function is an expected maintenance cost when a given preventive maintenance (PM) schedule is adopted. The system cost function calculates the expected cost based on the observed cost of operation in each of the operating states and a probability of the computing system being in each of the operating states as determined by the PM schedule. The PM schedule that minimizes the cost function is determined to be the optimal PM schedule.

主权项

1. A non-transitory computer-readable medium storing computer-executable instructions that when executed by a computer cause the computer to perform a method, the method comprising:
monitoring a prognostic parameter of a computing system; mapping respective maintenance costs of the computing system to respective prognostic parameter values such that the maintenance cost mapped to a given value is an accumulation of maintenance costs while the prognostic parameter is at the given value; partitioning values of the prognostic parameter into two or more partitions based on the maintenance cost, wherein each partition corresponds to a computing system operating state; assigning the maintenance cost for the values in a partition to an operating state that corresponds to the partition; and selecting a preventive maintenance schedule that minimizes a system cost function that calculates an expected maintenance cost when preventive maintenance is performed in the operating states according to a given preventive maintenance schedule.