PREDICTING TIME TO MAINTENANCE BY FUSION BETWEEN MODELING AND SIMULATION FOR ELECTRONIC EQUIPMENT ON BOARD AN AIRCRAFT

• US 20120179326A1
• Filed: 01/04/2012
• Published: 07/12/2012
• Est. Priority Date: 01/06/2011
• Status: Active Grant

• Current Assignee: Airbus Helicopters
• Original Assignee: Eurocopter
• Inventors: Ghelam, Samir
• Granted Patent: US 8,478,479 B2
• Time in Patent Office: Days
• US Class Current: 701/31.9
• CPC Class Codes: G05B 17/02 electric
• CPC Class Codes: G05B 23/0245 based on a qualitative model, e.g. rule based; if-then decisions
• CPC Class Codes: G05B 23/0283 Predictive maintenance, e.g. involving the monitoring of a system and, based on the monitoring results, taking decisions on the maintenance schedule of the monitored system; Estimating remaining useful life [RUL] preventive maintenance, i.e. planning maintenance according to the available resources without monitoring the system G06Q10/06
• CPC Class Codes: G06F 11/008 Reliability or availability analysis
• CPC Class Codes: G06F 11/27 Built-in tests
• CPC Class Codes: G06F 11/3013 where the computing system is an embedded system, i.e. a combination of hardware and software dedicated to perform a certain function in mobile devices, printers, automotive or aircraft systems testing or monitoring of control systems or parts thereof G05B23/02
• CPC Class Codes: G06F 11/3058 Monitoring arrangements for monitoring environmental properties or parameters of the computing system or of the computing system component, e.g. monitoring of power, currents, temperature, humidity, position, vibrations thermal management in cooling arrangements of a computing system G06F1/206
• CPC Class Codes: G07C 5/085 using electronic data carriers

Abstract

A method and system for predictive maintenance of electronic equipment on board an aircraft (1). To produce a prognosis, the following are provided: a step (48) of modeling the equipment (3) with a model (53) for damage by an external aggression; a step (49) of simulating the damage up to failure; a learning step (64); a step (65) of classifying calculated and normalized values; and a fusion step (61) giving the real prognosis of the time to maintenance in units of time. The invention applies in particular to a rotary wing aircraft (1), e.g. a helicopter drone.

Claims

1. An avionics system including at least one piece of on-board electronic equipment suitable for submitting a technical prognosis concerning its mean time to failure (TTF(t)) in time units, wherein the avionics system includes a connection to an expert station on the ground, said on-board electronic equipment possessing a plurality of components and at least one sentinel device that participates in the real time calculation of said time to failure in units of time, said sentinel device having on a printed circuit at least:

a microcontroller;

connections to the microcontroller;

a sensor in the form of an accelerometer; and

another sensor for measuring external signals;

said prognosis executing the following steps;

a modeling step of modeling the equipment, said step providing at least;

a phase of parameterizing an aggression external to said equipment with defining at least one physical parameter reflecting this external aggression as a function of time; and

a phase of producing a damage model of the damage to the equipment due to said external aggression;

a damage simulation step of simulating the damage to the equipment caused by repeated aggression in operation represented at least by said physical parameter, up to at least one failure state;

said damage simulation step comprising at least one stage of measuring values of said physical parameter during the repeated aggression, said measured values being integrated in said definition of said at least one physical parameter; and

a stage of selecting at least one critical component within the equipment;

a data collection step of collecting data specific to the damage to the equipment from said damage model and from measured values of said physical parameter in operation of the equipment;

a learning step, said learning step providing at least;

a phase of selecting at least one internal signal V_i(t) of the equipment, said signal being determined as revealing a failure state of said at least one critical component;

a phase of capturing operating data of the equipment; and

a phase of generating a correlation function between said operating data and values of said internal signal of said critical component of said equipment;

a classification step of classifying said internal signal values and said operating data;

said classification step including a phase of calculating and standardizing data representative of real distances to failure;

a fusion step of fusing said data specific to damage and said data representative of real distances to failure once normalized, in order to obtain a real prognosis of the time to failure in units of time before maintenance; and

a step of making available to said expert station on the ground, said real prognosis of time to failure in units of time of the on-board electronic equipment.

2. A technical prognosis method for making a prognosis available on an expert station on the ground about the mean time to failure (TTF(t)) in units of time of at least one piece of electronic equipment on board an aircraft;

said equipment possessing a plurality of components, wherein, during a life cycle of the equipment it comprises the following steps;

a modeling step of modeling the equipment, said step providing at least;

a phase of parameterizing an aggression external to said equipment and defining at least one physical parameter representative of said external aggression as a function of time; and

a phase of producing a damage model of the damage to the equipment due to said external aggression;

a damage simulation step of simulating the damage to the equipment caused by repeated aggression in operation represented at least by said physical parameter, up to at least one failure state;

said damage simulation step comprising at least one stage of measuring values of said physical parameter during the repeated aggression, said measured values being integrated in said definition of said at least one physical parameter; and

a stage of selecting at least one critical component within the equipment;

a data collection step of collecting data specific to the damage to the equipment from said damage model and from measured values of said physical parameter in operation of the equipment;

a learning step, said learning step providing at least;

a phase of selecting at least one internal signal V_i(t) of the equipment, said signal being determined as revealing a failure state of said at least one critical component;

a phase of capturing operating data of the equipment; and

a phase of generating a correlation function between said operating data and values of said internal signal of said critical component of said equipment;

a classification step of classifying said internal signal values and said operating data;

said classification step including a phase of calculating and standardizing data representative of real distances to failure;

a fusion step of fusing said data specific to damage and said data representative of real distances to failure once normalized, in order to obtain a real prognosis of the time to failure in units of time before maintenance; and

a step of making available to said expert station on the ground, said real prognosis of time to failure in units of time of the on-board electronic equipment.

3. A technical prognosis method according to claim 2, wherein the collection step groups together data specific to unit amounts of damage for each physical parameter in application of a damage superposition rule.

4. A technical prognosis method according to claim 3, wherein the collection step provides:

processing to identify a cycle;

processing to read a number of cycles from a matrix coming from the modeling step; and

processing to add unit amounts of damage using equation;

5. A technical prognosis method according to claim 2, wherein the learning step determines a failure threshold V_imax for each internal signal V_i(t) of said equipment.

6. A technical prognosis method according to claim 5, wherein it provides for the classification step to determine data representative of real distances to failure

7. A technical prognosis method according to claim 6, wherein the fusion step calculates said time before maintenance in the form of a mean time to failure TTF(t) in units of time on the basis of the following equation:

8. A technical prognosis method according to claim 2, wherein, during the parameterizing phase, it provides for defining at least one physical parameter representative of an external aggression on said equipment as a function of time, which parameter takes account at least of one level of vibration to which the equipment is subjected.

9. An aircraft enabling the technical method according to claim 2 to be implemented, wherein the aircraft is a rotary wing aircraft.

10. An aircraft according to claim 9, including at least one avionics system having at least one on-board piece of electronic equipment provided with at least one sentinel device suitable for submitting in real time to said prognosis a time to failure in units of time;

the sentinel device being connected to at least one probe of the aircraft that is suitable for measuring internal signals of at least one component of said piece of equipment;

said sentinel device comprising a printed circuit carrying at least;

a microcontroller;

connections to the microcontroller;

a sensor in the form of an accelerometer;

at least one other sensor for measuring external signals; and

a digital display.