초록 ▼

A method to predict equipment life is disclosed. The method includes making available a set of input parameters, and defining a model of a health of the equipment as a function of the set of input parameters. The method continues with receiving at least one signal representative of a respective one

A method to predict equipment life is disclosed. The method includes making available a set of input parameters, and defining a model of a health of the equipment as a function of the set of input parameters. The method continues with receiving at least one signal representative of a respective one of an actual sensor output relating to an actual operation attribute margin of the equipment, predicting a remaining useful equipment life based upon a sequence of outputs of the model of the health of the equipment, and generating a signal corresponding to the remaining useful equipment life.

대표청구항 ▼

What is claimed is: 1. A method to predict equipment life comprising: making available a set of input parameters, wherein the making available comprises making available an operating condition, a degraded abnormal health condition, and a deterioration condition; executing a computational model with

What is claimed is: 1. A method to predict equipment life comprising: making available a set of input parameters, wherein the making available comprises making available an operating condition, a degraded abnormal health condition, and a deterioration condition; executing a computational model with the set of input parameters to define at least one modeled operation attribute margin; comparing the modeled operation attribute margin defined using the set of input parameters absent the degraded abnormal health condition with a corresponding modeled operation attribute margin defined using the set of input parameters comprising the degraded abnormal health condition to develop a normalized operation attribute margin; defining a health index based upon the normalized operation attribute margin; defining a model of a health of the equipment as a function of the set of input parameters; receiving from the model of the health of the equipment at least one signal representative of a respective one of an actual sensor output relating to an actual operation attribute margin of the equipment; predicting a remaining useful equipment life based upon a sequence of outputs of the model of the health of the equipment; and generating a signal corresponding to the remaining useful equipment life. 2. The method of claim 1, wherein the predicting comprises: assessing a plurality of operational data prior to an end of equipment useful life. 3. The method of claim 1, wherein the predicting comprises: extrapolating a trajectory of the sequence of outputs of the model of the health of the equipment. 4. The method of claim 3, wherein the extrapolating comprises: extrapolating the trajectory of the sequence of outputs of the model of the health of the equipment using an exponential curve fit. 5. The method of claim 1, further comprising: defining the health of the equipment by a most limiting one of the at least one modeled operation attribute margin. 6. The method of claim 1, wherein: the making available the set of input parameters comprises supplying the set of input parameters of a gas turbine engine; and the executing the computational model with the set of input parameters to define the modeled operation attribute margin comprises defining the modeled operation attribute margin to comprise at least one of booster stall, high pressure compressor stall, high pressure compressor pressure ratio, low pressure turbine clearance, high pressure turbine inlet temperature, high pressure turbine clearance, high pressure turbine exit temperature, and core speed. 7. The method of claim 6, wherein the making available comprises: making available a degraded abnormal health condition comprising efficiency and flow. 8. The method of claim 1, further comprising: executing a computational model with the set of input parameters to define at least one modeled sensor output; and predicting a deterioration magnitude via a deterioration model using the operating condition and the modeled sensor output. 9. The method of claim 8, further comprising: comparing the predicted deterioration magnitude with the deterioration condition to define a deterioration estimation error; and changing the deterioration model to reduce the deterioration estimation error. 10. The method of claim 1, wherein: the comparing comprises comparing a plurality of modeled operation attribute margins defined using the set of input parameters absent the degraded abnormal health level with a corresponding plurality of modeled operation attribute margins defined using the set of input parameters comprising the degraded abnormal health level to develop a plurality of normalized operation attribute margins; the method further comprising defining a limiting normalized operation attribute margin as a normalized operation attribute margin of the plurality of normalized operation attributes having a minimum value at a specific degraded abnormal health level; and the defining the health index comprises defining the health index based upon the limiting normalized operation attribute margin. 11. The method of claim 1, further comprising: executing the computational model with the set of input parameters to define at least one modeled sensor output; and developing a transfer function that makes available a predicted health index using the modeled sensor output and a predicted deterioration condition. 12. The method of claim 11, further comprising: comparing the predicted health index to the defined health index to define a health estimation error; and changing the transfer function to reduce the health estimation error. 13. The method of claim 11, further comprising: determining a change in the signal representative of the actual sensor output; and predicting an expected change in the health index via the transfer function using the change in the signal representative of the actual sensor output; wherein the predicting the remaining useful equipment life comprises predicting the remaining useful equipment life based upon the expected change in the health index. 14. The method of claim 13, further comprising: detecting a degraded abnormal health condition; wherein the determining the change occurs subsequent to the detecting the degraded abnormal health condition. 15. The method of claim 1, further comprising: estimating a set of confidence intervals for the predicted remaining useful equipment life via a statistical technique. 16. The method of claim 15, wherein the estimating comprises: estimating the set of confidence intervals for the predicted remaining useful equipment life via bootstrapping. 17. A program storage device readable by a computer, the device embodying a program or instructions executable by the computer to perform the method of claim 1. 18. A prediction system for predicting life of equipment, the system comprising: a database comprising a set of input parameters; a processor in signal communication with the database; a computational model application for executing on the processor, the computational model performing a method, the method comprising: executing a computational model application with the set of input parameters to define at least one modeled operation attribute margin wherein the set of input parameters comprise an operating condition, a degraded abnormal health condition, and a deterioration condition; comparing the modeled operation attribute margin defined using the set of input parameters absent the degraded abnormal health condition with a corresponding modeled operation attribute margin defined using the set of input parameters comprising the degraded abnormal health condition to develop a normalized operation attribute; defining a health index based upon the normalized operation attribute margin; defining a model of a health of the equipment as a function of the set of input parameters; receiving from the model of the health of the equipment at least one signal representative of a respective one of an actual sensor output relating to an actual operation attribute margin of the equipment; predicting a remaining useful equipment life based upon a sequence of outputs of the model of the health of the equipment; and generating a signal corresponding to the remaining useful equipment life. 19. The system of claim 18, wherein: the equipment comprises gas turbine engine equipment; and the modeled operation attribute margin comprises at least one of booster stall, high pressure compressor stall, high pressure compressor pressure ratio, low pressure turbine clearance, high pressure turbine inlet temperature, high pressure turbine clearance, high pressure turbine exit temperature, and core speed. 20. The system of claim 18, wherein the computational model application further performs: executing the computational model application with the set of input parameters to define at least one modeled sensor output; predicting a deterioration magnitude via a deterioration model using the operating condition and the modeled sensor output; comparing the predicted deterioration magnitude with the deterioration condition to define a deterioration estimation error; and changing the deterioration model to reduce the deterioration estimation error. 21. The system of claim 18, wherein the computational model application further performs: executing the computational model with the set of input parameters to define at least one modeled sensor output; developing a transfer function that makes available a predicted health index using the modeled sensor output and a predicted deterioration condition; comparing the predicted health index to the defined health index to define a health estimation error; and changing the transfer function to reduce the health estimation error. 22. The system of claim 21, wherein the computational model application further performs: determining a change in the signal representative of the actual sensor output; and predicting an expected change in the health index via the transfer function using the change in the signal representative of the actual sensor output; wherein the predicting the remaining useful equipment life comprises predicting the remaining useful equipment life based upon the expected change in the health index.