# US 12,602,037 B2 · Methods and apparatus to generate a predictive asset health quantifier of a turbine engine > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,602,037 B2 - Document ID: US12602037B2 - Status: Granted - Kind: B2 - Application number: 17/531,911 - Filed: 2021-11-22 - Published: 2022-03-17 - Granted: 2026-04-14 - Earliest claimed: 2017-11-10 - Assignees: General Electric Company - Applicants: General Electric Company - Inventors: Srikanth Akkaram; Mariusz Wiklo; Youngwon Shin; Ricardo Cuevas; William Keith Kincaid; Jesus Miguel Valenzuela; Gregory Jon Chiaramonte; Vasanth Muralidharan; Charles Larry Abernathy; Venkata Vamsi Bhagavan; Andrew Scott Kessie - Web page: https://patentgrep.com/patent/US12602037B2 ## CPC - G05B 23/0254: {based on a quantitative model, e.g. mathematical relationships between inputs and outputs; functions: observer, Kalman filter, residual calculation, Neural Networks} - G05B 23/0289: {Reconfiguration to prevent failure, e.g. usually as a reaction to incipient failure detection} - G05B 23/0294: {Optimizing process, e.g. process efficiency, product quality} - F05B 2260/80: Diagnostics - G05B 23/0267: {Fault communication, e.g. human machine interface [HMI]} - G05B 2219/45071: Aircraft, airplane, ship cleaning manipulator, paint stripping - G06Q 10/06375: {Prediction of business process outcome or impact based on a proposed change} - G05B: CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS (systems for controlling or regulating non-electric variables G05D; systems for regulating electric or magnetic variables G05F; control devices or systems insofar as characterised by mechanical features only G05G) - F05B: INDEXING SCHEME RELATING TO WIND, SPRING, WEIGHT, INERTIA OR LIKE MOTORS, TO MACHINES OR ENGINES FOR LIQUIDS COVERED BY SUBCLASSES F03B, F03D AND F03G - G06Q: INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR ## Abstract Methods, apparatus, systems, and articles of manufacture are disclosed to generate a predictive asset health quantifier of a turbine engine. An example apparatus includes a performance model analyzer to determine a fleet behavior parameter by generating a reference performance model using historical information for a fleet of operators using turbine engines, generate a residual performance model based on calculating a difference between the fleet behavior parameter and a plurality of operator behavior parameters, identify an operator as a candidate improvement target based on comparing the operator behavior parameters corresponding to the operator to the fleet in the residual performance model, and determine an adjusted operator behavior parameter for the candidate improvement target. The example apparatus further includes a system updater to update a computer-based model to replace the operator behavior parameter with the adjusted operator behavior parameter, and a task optimizer to determine a workscope for the turbine engine. ## Claims ### Claim 1 An asset workscope generation system, comprising: one or more memory devices; and one or processors configured to: obtain asset monitoring information, the asset monitoring information comprising asset sensor data obtained by at least one sensor associated with a turbine engine; calculate asset parameters associated with the turbine engine based on the asset monitoring information; generate a reference performance model based on the asset parameters associated with the turbine engine; calculate deviations based on a comparison of an operator behavior to the reference performance model, the operator behavior quantifying how an operator of the turbine engine has used the turbine engine in operation; generate one or more severity models based on the asset parameters and the deviations, the one or more severity models comprising a plurality of severity models being generated based on a mapping of an asset health quantifier associated with the turbine engine to a severity factor, the severity factor comprising the operator behavior, wherein the one or more severity models are configured to estimate an effect of the operator behavior on the asset health quantifier; identify the operator as a candidate improvement target based on the one or more severity models; generate a report including a candidate improvement plan for the operator identified as the candidate improvement target; and trigger generation of a workscope for the turbine engine based on the report. ### Claim 2 (depends on 1) The asset workscope generation system of claim 1, wherein the asset health quantifier is associated with an asset component of the turbine engine, and wherein the one or more processors are further configured to: generate the asset health quantifier as a function of time-on-wing and the severity factor. ### Claim 3 (depends on 1) The asset workscope generation system of claim 1, wherein the severity factor is a takeoff temperature or a climb temperature for a region in which the turbine engine operates. ### Claim 4 (depends on 1) The asset workscope generation system of claim 1, wherein the asset health quantifier is associated with an asset component of the turbine engine, and wherein the one or more processors are further configured to: determine whether the asset health quantifier satisfies a threshold based on the mapping, and when the asset health quantifier satisfies the threshold, identify the asset component as a candidate for a maintenance operation. ### Claim 5 (depends on 1) The asset workscope generation system of claim 1, wherein the one or more severity models include a plurality of severity models that each correspond to an asset component of the turbine engine, and wherein the workscope includes a recommendation to improve operator behavior for the operator identified as the candidate improvement target, and wherein the recommendation to improve operator behavior is based on determining a sensitivity for each of the asset components to the severity factor. ### Claim 6 (depends on 1) The asset workscope generation system of claim 1, wherein the asset health quantifier associated with the turbine engine is a pre-workscope asset health quantifier of the turbine engine prior to performing the workscope on turbine engine, and wherein the one or more processors are further configured to: calculate a post-workscope asset health quantifier associated with the turbine engine after completing the workscope on the turbine engine; compare the pre-workscope asset health quantifier to the post-workscope asset health quantifier; and determine a workscope quantifier based on comparing the pre-workscope asset health quantifier to the post-workscope asset health quantifier, the workscope quantifier representing an accuracy or efficiency of the asset workscope generation system. ### Claim 7 (depends on 6) The asset workscope generation system of claim 6, wherein the one or more processors are further configured to: compare the workscope quantifier to a workscope quantifier threshold; determine whether the workscope quantifier satisfies the workscope quantifier threshold based on comparing the workscope quantifier to the workscope quantifier threshold; and in response to the workscope quantifier threshold satisfying the workscope quantifier threshold, modify one or more components of the asset workscope generation system. ### Claim 8 (depends on 7) The asset workscope generation system of claim 7, wherein in modifying the one or more components of the asset workscope generation system, the one or more processors are configured to update one or more models of the asset workscope generation system. ### Claim 9 (depends on 8) The asset workscope generation system of claim 8, wherein in updating the one or more models of the asset workscope generation system, the one or more processors are configured to update a digital twin associated with the turbine engine. ### Claim 10 (depends on 9) The asset workscope generation system of claim 9, wherein the digital twin associated with the turbine engine is updated with at least one of up-to-date historical trend information, model parameters, and model algorithms. ### Claim 11 (depends on 8) The asset workscope generation system of claim 8, wherein in updating the one or more models of the asset workscope generation system, the one or more processors are configured to update at least one of a historical data model, a physics-based model, a stochastic model, and a hybrid model. ### Claim 12 (depends on 1) The asset workscope generation system of claim 1, wherein in calculating the deviations, the one or more processors are configured to generate a residual performance model by calculating differences between actual asset parameters of operators of a fleet and the asset parameters included in the reference performance model. ### Claim 13 (depends on 1) The asset workscope generation system of claim 1, wherein the asset parameters used to generate the reference performance model are calculated by a historical data model using historical information associated with a fleet of operators using turbine engines. ### Claim 14 (depends on 1) The asset workscope generation system of claim 1, wherein the asset parameters include at least operator-level de-rate parameters and fleet-level de-rate parameters. ### Claim 15 (depends on 1) The asset workscope generation system of claim 1, wherein the asset parameters used to generate the reference performance model are calculated by a physics-based model executing a digital twin model associated with the turbine engine. ### Claim 16 (depends on 15) The asset workscope generation system of claim 15, wherein the reference performance model is generated by the one or more processors by mapping the asset parameters as a function of an engine performance characteristic output by the physics-based model. ### Claim 17 (depends on 16) The asset workscope generation system of claim 16, wherein the engine performance characteristic is an aircraft weight of an aircraft weight to which the turbine engine is mounted. ### Claim 18 A method, comprising: obtaining asset monitoring information, the asset monitoring information comprising asset sensor data obtained by at least one sensor associated with a turbine engine; calculating asset parameters associated with the turbine engine based on the asset monitoring information; generating a reference performance model based on the asset parameters associated with the turbine engine; calculating deviations based on a comparison of an operator behavior to the reference performance model, the operator behavior quantifying how an operator of the turbine engine has used the turbine engine in operation; generating one or more severity models based on the asset parameters and the deviations, the one or more severity models comprising a plurality of severity models being generated based on a mapping of an asset health quantifier associated with the turbine engine to a severity factor, the severity factor comprising the operator behavior, wherein the one or more severity models are configured to estimate an effect of the operator behavior on the asset health quantifier; identifying an operator as a candidate improvement target based on the one or more severity models; generating a report including a candidate improvement plan for the operator identified as the candidate improvement target; and triggering generation of a workscope for the turbine engine based on the report. ### Claim 19 A non-transitory computer readable storage medium comprising instructions, which when executed, cause a machine to at least: obtain asset monitoring information, the asset monitoring information comprising asset sensor data obtained by at least one sensor associated with a turbine engine; calculate asset parameters associated with the turbine engine based on the asset monitoring information; generate a reference performance model based on the asset parameters associated with the turbine engine; calculate deviations based on a comparison of an operator behavior to the reference performance model, the operator behavior quantifying how an operator of the turbine engine has used the turbine engine in operation; generate one or more severity models based on the asset parameters and the deviations, the one or more severity models comprising a plurality of severity models being generated based on a mapping of an asset health quantifier associated with the turbine engine to a severity factor, the severity factor comprising the operator behavior, wherein the one or more severity models are configured to estimate an effect of the operator behavior on the asset health quantifier; identify an operator as a candidate improvement target based on the reference performance model and the one or more severity models; generate a report including a candidate improvement plan for the operator identified as the candidate improvement target, the candidate improvement plan comprising adjustments to the operator behavior; and trigger generation of a workscope for the turbine engine based on the report. ### Claim 20 (depends on 1) The asset workscope generation system of claim 1, wherein the one or processors are further configured to: identify one or more assets operated by the operator as candidate assets for removal from service; generate a removal schedule to remove the one or more assets; and performing the generated workscope on the one or more removed assets based on the removal schedule.