Fleet level prognostics for improved maintenance of vehicles
A ground-based computing system receives data of performance parameters for like components disposed on like aircraft, and determines corresponding levels of degradation and rates of change of degradation for the respective like components. A fleet-level of degradation for groups of like components is generated based on analysis of the combined degradations of the like components in the respective group. At least one of a remaining useful lifetime (RUL) and a state-of-health (SOH) for each of the respective like components is determined based on a comparison of the levels of degradation for each of the like components and the fleet-level of degradation of the group of like components. A predicted time for maintenance for each like component is determined based on the corresponding at least one of the RUL and SOH of the like component, thereby enabling cost effective maintenance determinations for components based on a fleet-level information.
1. A method implemented by a ground-based computing system comprising the steps of:
receiving data of performance parameters for like components disposed on a plurality of like aircraft, the data including identification of an operational mode of the aircraft for the performance parameters;
storing the data in memory of the ground-based computing system;
determining by a microprocessor of the ground-based computing system corresponding levels of degradation and rates of change of degradation for the respective like components based on the stored performance parameters and the operational mode of the aircraft associated with the respective performance parameters;
generating a fleet level of degradation for groups of like components by the microprocessor based on analysis of the combined degradations of the like components in the respective group;
determining at least one of a remaining useful lifetime (RUL) and a state-of-health (SOH) by the microprocessor for each of the respective like components based on a comparison of the levels of degradation for each of the like components and the fleet level of degradation of the group of like components;
determining a predicted time for maintenance by the microprocessor for each like component based on the corresponding at least one of the RUL and SOH of the like component, thereby enabling cost effective maintenance determinations for components based on a fleet level information.
2. The method of claim 1 wherein the receiving of data includes transferring a plurality of like components' data from a respective like aircraft to the ground-based computing system while the aircraft is on the ground, the data based on component performance parameters stored in an aircraft data storage device while the aircraft was in flight.
3. The method of claim 1 wherein the receiving of data includes transferring via a wireless communication link a plurality of like components' data from a respective like aircraft to the ground-based computing system while the aircraft is in flight.
4. A method implemented by a ground-based computing system comprising the steps of:
receiving data of performance parameters for like components disposed on a plurality of like aircraft;
storing the data in memory of the ground-based computing system;
determining by a microprocessor of the ground-based computing system corresponding levels of degradation and rates of change of degradation for the respective like components;
generating by the microprocessor a fleet level of degradation for groups of like components based on analysis of the combined degradations of the like components in the respective group;
determining by the microprocessor at least one of a remaining useful lifetime (RUL) and a state-of-health (SOH) for each of the respective like components based on a comparison of the levels of degradation for each of the like components and the fleet level of degradation of the group of like components;
determining by the microprocessor a predicted time for maintenance for each like component based on the corresponding at least one of the RUL and SOH of the like component, thereby enabling cost effective maintenance determinations for components based on a fleet level information;
wherein determining corresponding levels of degradation and rates of change of degradation for the respective like components comprises:
determining, by at least one of a physics-based model of the respective like components and an empirical model of the respective like components, a first residue that is a difference between a current state of the performance parameters of the like components and corresponding states of the performance parameters of the like components as determined by the at least one of the physics-based model and the empirical model;
determining by a physical system model of the respective like components a second residue that is a difference between the current state of the performance parameters of the like components and predetermined ranges of states of performance parameters of the corresponding like components as determined by the physical system model; and
determining, based on a combination of the first and second residues, a level of degradation for the respective like components and a rate of change of degradation for the respective like components.
5. The method of claim 1 wherein generating the fleet level of degradation for respective like components comprises:
generating a weighted average for the RUL of all the like components.
6. A method implemented by a ground-based computing system comprising the steps of:
receiving data of performance parameters for like components disposed on a plurality of like aircraft,
storing the data in memory of the ground-based computing system;
determining by a microprocessor of the ground-based computing system corresponding levels of degradation and rates of change of degradation for the respective like components;
generating by the microprocessor a fleet level of degradation for groups of like components based on analysis of the combined degradations of the like components in the respective group;
determining by the microprocessor at least one of a remaining useful lifetime (RUL) and a state-of-health (SOH) for each of the respective like components based on a comparison of the levels of degradation for each of the like components and the fleet level of degradation of the group of like components;
determining by the microprocessor a predicted time for maintenance for each like component based on the corresponding at least one of the RUL and SOI of the like component, thereby enabling cost effective maintenance determinations for components based on a fleet level information;
wherein determining the SOH for each of the respective like components comprises:
determining a current SOH for each like component;
comparing for each like component the current corresponding SOH with a state of 100% performance to generate a current SOH for the like component.
7. The method of claim 6 wherein determining the RUL for each of the respective like components comprises:
determining the RUL for each like component based on a previous determination of RUL of the like component and the rate of degradation of performance of the respective like component.