Method for identifying an imbalance of an engine rotor based on engine vibrations

Abstract

Predictive models for diagnosing an unbalanced condition in an aircraft engine (e.g., a jet engine) based on engine vibrations and other known and / or determinable parameters are disclosed. Methods for developing the predictive models and using the models to identify aircraft engine imbalances are also disclosed.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to methods and systems for identifying sources of imbalance in a rotor system of a jet engine and determining corrective actions at a heavy maintenance shop or maintenance, repair, overhaul (MRO) shop. BACKGROUND

[0002] Rotating machinery, such as that found in the core of an aircraft jet engine, can be highly sensitive to small imperfections in the balance of its rotating parts. Operation of such machinery with imbalanced components can result in, for example, uneven distribution of forces, damage to engine components, and excessive wear of components during normal use. In the case of a jet engine, such imperfections can cause the center of mass of the compressor and turbine assemblies to become misaligned with the geometric axis of rotation of the assemblies. In the case of a jet engine, vibrations caused by imbalanced components can be transmitted to adjacent portions of the aircraft and can cause noise and passenger discomfort, and result in increased wear, fatigue, and damage to engine components. Traditional methods of addressing jet engine imbalance are very time consuming, resulting in increased time and expense associated with engine repair.

[0003] Accordingly, there is a need for a method of accurately and efficiently identifying sources of imbalance and determining appropriate corrective actions prior to an aircraft jet engine reaching an MRO shop. SUMMARY

[0004] Embodiments of a predictive model for diagnosing a state of imbalance in a jet engine based on engine vibration and operating parameters at an MRO are disclosed herein.

[0005] Methods for developing a model that identifies sources of imbalance in a jet engine and determines appropriate corrective actions are also disclosed.

[0006] In one embodiment disclosed herein, a method for developing a predictive diagnostic model includes: (a) measuring a core vibration data set and an operating parameter data set associated with a jet engine; (b) storing the core vibration data set and the operating parameter data set; (c) identifying a state of imbalance associated with a combination of the core vibration data set and the operating parameter data set; (d) repeating steps (a)-(c) until a sufficient number of data sets have been recorded to generate a predictive model for determining the state of imbalance; and (e) using the predictive model in step (d) to determine the state of imbalance from measured core vibration and operating parameter data.

[0007] In another embodiment disclosed herein, a method for identifying an unbalance condition of a jet engine includes: (a) generating one or more linear vibration ratio-to-unbalance relationship sets for different operating parameter sets based on a database; (b) generating one or more individual analytical models for each linear set of vibration ratio-to-unbalance data; (c) recording core vibration signatures and operating parameter sets of the jet engine; (d) inputting the core vibration signatures and operating parameter sets into one or more individual analytical models of step (b); (e) identifying a best fit linear set based on the operating parameters; (f) identifying a possible unbalance location and magnitude by comparing the measured core vibration signatures to historical vibration signatures recorded for the best fit linear set; and (g) applying one or more weights to at least one of the compressor or turbine or a combination of both in the jet engine having an allowed unbalance correction limit of the module.

[0008] Also disclosed herein are embodiments of a model for predicting a diagnosis of an unbalance condition of a jet engine, including: a database consisting of a correlated set of core vibration data, key engine operating parameters, and engine unbalance conditions; an input function configured to allow a user to input: core vibration input data; engine operating parameters; and a tolerance function configured to identify one or more engine unbalance conditions based on the core vibration data and key engine operating parameters.

[0009] The foregoing and other objects, features and advantages of the present application will become more readily apparent from the following detailed description, which proceeds with reference to the accompanying drawings. BRIEF DESCRIPTION OF DRAWINGS

[0010] The present specification sets forth in detail preferred embodiments of the application for the person of ordinary skill in the art, which are capable of being disclosed without departing from the essential nature thereof, and is to be considered as comprising all of the obvious and inherent modifications that come within the scope of the appended claims.

[0011] Figure 1 illustrates a cross-sectional view of an exemplary jet engine;

[0012] Figure 2A and 2B is a flowchart illustrating an exemplary method for identifying an unbalance of an engine rotor based on engine vibrations;

[0013] Figure 3 is a table relating to an exemplary validation process for identifying an unbalance condition of an engine rotor;

[0014] Figure 4 illustrates an exemplary validation process including comparing identified core vibration ratios to actual core vibration ratios for simulated unbalance conditions;

[0015] Figure 5FIG. illustrates an example validation process including user input of vibration and / or vibration ratio data;

[0016] Figure 6 FIG. is a flowchart illustrating an example method of identifying imbalance of an engine rotor based on engine vibration; and

[0017] Figure 7 FIG. illustrates an example embodiment showing multiple linear sets. DETAILED DESCRIPTION

[0018] Embodiments of various methods and systems are disclosed herein for identifying sources of rotor imbalance in jet engines and determining appropriate corrective actions based on measured vibration and identified operating parameters in those engines.

[0019] In some embodiments, the methods and systems disclosed herein generally include receiving information about engine vibration from one or more sensors, identifying engines having vibration levels above a predetermined tolerance, and determining imbalance conditions for those engines based on vibration levels and operating parameters.

[0020] Reference will now be made in detail embodiments of the disclosed technology, one or more examples of which are illustrated in the drawings. Each example is provided by way of explanation of the disclosed technology and not as a limitation of the disclosure. In fact, it will be apparent to those skilled in the art that various modifications and variations can be made in the disclosed technology without departing from the scope or spirit of the disclosure. For instance, features illustrated or described as part of one embodiment, can be used with another embodiment to yield still a further embodiment. Thus, it is intended that the disclosure cover such modifications and variations as come within the scope of the appended claims and their equivalents.

[0021] The terms "shipping limit," "vibration tolerance," and "maximum vibration limit" are used herein to refer to a predetermined maximum amount of vibration measured by one or more vibration sensors for a particular jet engine in good operating condition. The terms "core vibration ratio" and "core vibe ratio" are used herein to refer to the ratio of measured vibration condition to the shipping limit for a turbofan engine.

[0022] The word "example" is used herein to mean "serving as an example, instance, or illustration." Any implementation described herein as "example" is not necessarily to be construed as preferred or advantageous over other implementations.

[0023] As used herein, the terms "first," "second," and "third" can be used interchangeably to distinguish one component from another and are not intended to signify location or importance of the individual components.

[0024] The terms "forward" and "aft" refer to relative positions within a jet engine or vehicle and refer to the normal operating attitude of the jet engine or vehicle. For example, with respect to a jet engine, forward refers to a position proximate to the engine inlet, and aft refers to a position proximate to the engine nozzle or exhaust. The terms "upstream" and "downstream" refer to the direction of fluid flow in a fluid path. For example, "upstream" refers to the direction from which fluid flows, and "downstream" refers to the direction to which fluid flows.

[0025] Further, unless otherwise stated, the terms "low," "high," or their respective comparative forms (e.g., lower, higher, if applicable) each refer to relative speeds within a jet engine. For example, a "low pressure turbine" operates at a pressure that is generally lower than a "high pressure turbine." Alternatively, unless otherwise stated, the aforementioned terms can be understood in their superlative form. For example, a "low pressure turbine" can refer to the lowest maximum pressure turbine within a turbine section, and a "high pressure turbine" can refer to the highest maximum pressure turbine within a turbine section.

[0026] Unless otherwise stated, the terms "coupled," "fixed," "attached to," and the like, each refer to direct coupling, fixation, or attachment, as well as indirect coupling, fixation, or attachment via one or more intermediate components or features, unless otherwise stated.

[0027] Unless the context clearly indicates otherwise, the singular forms "a," "an," and "the" include plural referents. Approximating language is applied to modify any quantitative representation that could possibly vary, depending on the values of other quantities as could possibly vary, within the limits of this disclosure. Accordingly, a value modified by a term or terms, such as "about," "approximately," and "substantially,” is not limited to the precise value specified. In at least some instances, the approximating language can correspond to the precision with which the instrument used to measure the value, or the precision to which the process, machine, or other apparatus producing the value can be controlled. For example, the approximating language can correspond to the precision of ±1%, ±2%, ±4%, ±5%, ±10%, ±15%, or ±20%, as well as any other suitable level of precision, within at least some instances. If not indicated otherwise, approximating language should be understood to refer to a tolerance within ±10% of the base value stated.

[0028] Herein and throughout the specification and claims, range limitations are combined and interchanged, such ranges are identified and include all the sub-ranges included therein unless context or language indicates otherwise. For example, all ranges disclosed herein are inclusive of the endpoints, and the endpoints are independently combinable with each other.

[0029] Unwanted vibration behavior of an aircraft jet engine can sometimes be reduced by adding / removing balancing mass to one or more components of the engine core to reposition the mass center of the compressor and turbine assemblies. To perform such balancing, the misaligned aircraft jet engine is typically removed from active operation so that the precise nature of the misalignment can be determined and appropriate corrective steps taken.

[0030] In the case of an aircraft jet engine, the observed total engine rotational misalignment can include individual misalignments in a number of engine components. Identifying the exact source of the imbalance can involve a complex and often time-consuming trial-and-error process. This process results in significant loss of engine operating time and requires skilled technicians to expend significant time to analyze, diagnose, and correct the imbalance of the aircraft turbine engine.

[0031] The methods of identifying an imbalance condition in a high pressure rotating machine disclosed herein can be used with various embodiments of a jet engine. The jet engine used with the presently disclosed imbalance condition identification methods can have a core engine with a low pressure compressor (booster), a high pressure compressor, a combustion section, a high pressure turbine, and a low pressure turbine. The core engine can be disposed within a substantially tubular casing. The jet engine can also include a fan section upstream of the core engine and an exhaust downstream of the core engine.

[0032] For example, Figure 1 A cross-sectional view of a jet engine 100 suitable for use with the imbalance condition identification methods of the present disclosure is depicted in accordance with one example embodiment. More specifically, Figure 1 The gas turbine engine shown in FIG. 1 is a high-bypass turbofan jet engine 100, referred to herein as "turbofan engine 100." As shown, Figure 1 The turbofan engine 100 defines an axial direction A (extending parallel to a longitudinal centerline 102 provided for reference) and a radial direction R (extending perpendicular to the axial direction A). Generally, the turbofan 100 includes a fan section 104 and a core engine 106 arranged downstream from the fan section 104. Although Figure 1 A direct drive turbofan is depicted, it should be understood that other engine architectures are possible, such as a geared architecture in which a plurality of gears couples a gas turbine shaft to a fan shaft.

[0033] The exemplary core engine 106 described generally includes a substantially tubular outer casing that defines an annular inlet 110. The outer casing encases, in serial flow relationship, a compressor section including a booster or low pressure (LP) compressor 112 and a high pressure (HP) compressor 114; a combustion section 116; a turbine section including a high pressure (HP) turbine 118 and a low pressure (LP) turbine 120; and a jet exhaust nozzle section 122. A high pressure (HP) shaft or spool drivingly connects the high pressure turbine 118 to the high pressure compressor 114. A low pressure (LP) shaft or spool 126 drivingly connects the low pressure turbine 120 to the low pressure compressor 112. Moreover, the compressor section, the combustion section 116, and the turbine section together at least partially define a core air flowpath 128 extending therethrough.

[0034] For the depicted embodiment, the fan section 104 can include a variable pitch fan 130 having a plurality of fan blades 132 coupled in spaced apart relation to a disk 134. As shown, the fan blades 132 extend generally radially outwardly from the disk 134. As the fan blades 132 are operably coupled to suitable actuating members 136 configured to collectively vary the pitch of the fan blades 132, each fan blade 132 is rotatable relative to the disk 134 about a pitch axis P. The fan blades 132, the disk 134, and the actuating members 136 are rotatable together about the longitudinal axis 102 by the LP shaft 126.

[0035] Still referring to Figure 1 the exemplary embodiment, the disk 134 is covered by a rotatable front nacelle 140 having an aerodynamic profile to facilitate airflow through the plurality of fan blades 132. Moreover, the exemplary fan section 104 includes an annular fan casing or outer nacelle 142 that circumferentially surrounds the fan 130 and / or at least a portion of the core engine 106. For the described embodiment, the nacelle 142 is supported relative to the core engine 106 by a plurality of circumferentially spaced apart outlet guide vanes 144. Moreover, a downstream section 146 of the nacelle 142 extends to an exterior of the core engine 106 so as to define a bypass airflow passage 148 therebetween.

[0036] During operation of the turbofan engine 100, a volume of air 150 enters the turbofan 100 through the nacelle 142 and / or an associated inlet 152 of the fan section 104. As the volume of air 150 passes through the fan blades 132, a first portion of the air 150, as indicated by arrow 154, is directed or routed into the bypass airflow passage 148, while a second portion of the air 150, as indicated by arrow 156, is directed or routed into the low pressure compressor 112. The ratio between the first portion of air 154 and the second portion of air 156 is commonly referred to as the bypass ratio. The pressure of the second portion of air 156 is then increased as it is routed through the high pressure (HP) compressor 114 and into the combustion section 116, where it is mixed with fuel and burned to provide combustion gases 158.

[0037] The combustion gases 158 are directed through the HP turbine 118, where a portion of the thermal and / or kinetic energy from the combustion gases 158 is extracted via sequential stages of HP turbine stator vanes 160 coupled to the outer casing 108 and HP turbine rotor blades 162 coupled to the HP shaft or spool 124, causing the HP shaft or spool 124 to rotate, which in turn drives the operation of the HP compressor 114. The combustion gases 158 then pass through the LP turbine 120, where a second portion of the thermal and / or kinetic energy from the combustion gases 158 is extracted via sequential stages of LP turbine stator vanes 164 coupled to the outer casing 108 and LP turbine rotor blades 166 coupled to the LP shaft or spool 126, causing the low pressure shaft or spool 126 to rotate, which in turn drives the operation of the low pressure compressor 112 and / or the rotation of the fan 130.

[0038] The combustion gases 158 are then directed through the jet exhaust nozzle section 122 of the core engine 106 to provide propulsive thrust. At the same time, the pressure of the first portion of air 154 is significantly increased as the first portion of air 154 is directed through the bypass airflow passage 148 before being exhausted from the fan nozzle exhaust section 168 of the turbofan 100, also providing propulsive thrust. The HP turbine 118, the LP turbine 120, and the jet exhaust nozzle section 122 at least partially define a hot gas path 170 for directing the combustion gases 158 through the core engine 106.

[0039] An imbalance can occur in jet engine 100 when the center of mass of any of compressors 112, 114 or turbines 118, 120 does not match the geometric axis of rotation of core engine 106. This can be caused by a mass imbalance in any of the core engine 106 components, such as components in low pressure compressor 112, high pressure compressor 114, high pressure turbine 118, or low pressure turbine 120. Such a mass imbalance can be caused by a defect in engine manufacturing, damage to one or more engine components (such as ingestion of foreign objects), normal wear of engine components, or any other cause sufficient to change the mass, size, shape, or position of a jet engine component.

[0040] In addition, other rotating components of the turbine fan, including fan blades 132 and / or fan disk 134, can become imbalanced. It should be understood that identifying an imbalance in other rotating components, such as fan blades and / or fan disk, can be accomplished in a similar manner as discussed herein for imbalances in core engine components, such as compressors and / or turbines.

[0041] When a component in jet engine 100 becomes imbalanced, the engine will experience vibrations that can cause it to suffer damage in use. Vibrations caused by an imbalanced engine component can cause passenger discomfort and lead to turbine or compressor component damage, increased part distortion from imbalanced stresses, and increased metal fatigue of engine components.

[0042] One or more vibration sensors 172 can be mounted on jet engine 100 to obtain data regarding vibrations of different engine components. Vibration data can include, for example, the location, amplitude, and phase of vibrations measured by each vibration sensor. Figure 1 Vibration sensors 172 are shown coupled to engine 100 at high pressure compressor 114 and high pressure turbine 116 to measure vibrations associated with each of these engine components. It should be understood that additional vibration sensors can be provided to provide additional vibration measurements of the high pressure compressor and turbine or to provide vibration measurements of other components of engine 100, such as the low pressure compressor and / or turbine. One or more vibration sensors can also be provided in the vicinity of other rotating components, such as the fan blades and / or fan disk discussed above.

[0043] Diagnosing and correcting the source of engine imbalance typically involves removing the jet engine from the aircraft and repairing damage that caused the imbalance and / or attaching corrective weights to the compressors 112, 114 and / or turbines 118, 120 to bring the center of mass of the compressors and / or turbines into alignment with the geometric rotational axis of the core 106. The engine with the corrective weights attached can then be tested over the entire operating range of rotational speeds to determine if the adjustment to the compressors 112, 114 and / or turbines 118, 120 has been effective. If not, the corrective mass can be added, removed, and / or repositioned as necessary.

[0044] However, since the measured vibrations of a turbine engine include contributions from the rotational characteristics of the compressors 112, 114 and turbines 118, 120, it is not always apparent whether the engine core imbalance is caused by an imbalance in one or more compressors, one or more turbines, or both. Therefore, correcting an engine with vibration levels that exceed acceptable limits often requires checking the balance of both the compressors and the turbines, and sometimes requires trial and error rebalancing of one component before rebalancing the other.

[0045] In some embodiments disclosed herein, a method of diagnosing the source of jet engine imbalance can include developing a model of the relationship between measured vibrations and imbalance. The model can be developed from data collected while the aircraft is in operation and compared to observed states of imbalance. The model can then be used to determine the state of imbalance in an engine with measured vibrations that exceed a predetermined maximum vibration limit. Although the methods disclosed herein are described in connection with an exemplary jet engine, it should be understood that these methods can also be applied to other gas turbine engines.

[0046] In one embodiment of the methods disclosed herein, as shown in FIG. 1, Figure 2A The method can include collecting vibration data while the aircraft with one or more jet engines 100 is in operation. During the operational use of the jet engines 100, core vibration data can be acquired from one or more vibration sensors mounted thereon. The vibration data can include the location, amplitude, and phase of the vibrations measured by each vibration sensor. The vibration data can be stored in a data recorder such as a digital flight data recorder or an onboard vibration monitor, or transmitted to a recording station (e.g., to a ground-based recording station). In this way, engines with vibration levels that exceed pre-established acceptable vibration limits (sometimes referred to as shipping limits) can be identified.

[0047] Data can also be collected regarding additional operating parameters of the jet engine 100. Such operating parameters can include, for example, inlet temperature, outlet temperature, supply pressure, physical properties, chemical properties, ambient temperature, combustor temperature, compressor outlet pressure, compressor outlet temperature, high pressure rotor speed, low pressure rotor speed, damper manufacturing variations, bearing manufacturing variations, damper operating conditions, bearing operating conditions, engine operator, engine operating region, and altitude. This data can be measured at the same time as the corresponding set of vibration data. Alternatively, the data can be measured at different time periods and then correlated together. For operating parameters that experience a range of operating conditions, a particular operating condition and / or a maximum or minimum value can be selected. For example, the compressor outlet temperature can be calculated as the maximum temperature during operation and / or can be selected for a particular operating condition (e.g., cruise, SLTO).

[0048] Table 1 below shows a list of relevant operating parameters that can be considered in identifying the unbalance conditions described herein.

[0049]

[0050]

[0051] When an engine is identified for core vibration analysis according to process block 202, the combined core vibration data and operating parameter data can be stored for modeling purposes (process block 204). As described above, this storage can be performed on-board the aircraft, for example on a digital flight data recorder or on-board vibration monitor, or remotely, for example by transmitting the data to a remote location such as an aircraft maintenance, repair, and overhaul (MRO) facility.

[0052] When a jet engine 100 is identified that exceeds the pre-established acceptable vibration limits, the jet engine 100 can then be removed from the aircraft, for example by an MRO technician, and the source of the engine unbalance responsible for the measured core vibration levels (e.g., LP compressor, HP compressor, HP turbine, and LP turbine) can be determined, for example by using the diagnostic techniques previously discussed (process block 206). In some embodiments, the measured vibration data and operating parameter data can then be correlated to the corresponding engine unbalance condition (process block 208), and the engine data-unbalance condition data can be saved for later use.

[0053] When there is not enough data available to develop a predictive diagnostic model according to method 200, additional data can be collected according to the previously discussed processes (decision block 210). However, if enough data has already been collected to support the development of a predictive diagnostic model according to method 200 (decision block 210), then once a sufficient amount of vibration data-imbalance state data is available, the accumulated vibration data-imbalance state pairings can be used to construct a prediction relating measured vibrations to expected engine imbalance states.

[0054] In Figure 2B In the illustrated embodiment with continuous illustration, models can be constructed according to data regarding core vibrations, operating parameters, and imbalance states. In one exemplary embodiment, construction of the models can include generating a linear set of vibration ratio-imbalance state data pairings for each given combination of operating parameters in the MRO database (process block 212). For each linear set of vibration ratio-imbalance state data, a separate analysis model can be developed to allow for operating parameter-specific identification of imbalance states (process block 214). In one particularly preferred embodiment, the separate analysis models can employ a random forest modeling approach.

[0055] Figure 7 An exemplary embodiment illustrating a plurality of linear sets is illustrated: Set 1, Set 2, Set 3, Set 4, Set 5, and Set 6. Each linear set reflects vibration ratio-imbalance state data pairings for a combination of operating parameters obtained from the MRO database. Thus, for example, Set 1 can include a certain set of operating parameters received and input into the model, a certain engine (e.g., Engine A) operating in a certain region. The other sets reflect similar inputs providing different linear sets. Different linear sets can reflect different engines, different regions, and / or different operating parameters. In some cases, the same engine operating in different regions or different operating parameters can result in different linear sets.

[0056] In some embodiments, the predictive models generated in process block 212 can then be analyzed for validation according to an exemplary process illustrated in Figures 3-5 As illustrated in Figure 3 As illustrated in Figure 4As shown, the validation process can further involve comparing the identified core vibration ratios to actual core vibration ratios for simulated imbalance conditions of the compressors 112, 114 and / or turbines 118, 120 of the jet engine 100, thereby allowing the user to check the accuracy of the correlation of the model between the vibration ratios and the engine imbalance conditions. The analysis validation process can also include user input of vibration and / or vibration ratio data, such as Figure 5 As shown, this will allow the model to predictively identify the source of the imbalance condition causing the core vibration.

[0057] The predictive diagnostic model developed according to the method 200 can then be used to identify and diagnose imbalance conditions that cause future engine vibrations, such as imbalance conditions and vibrations that can occur in the jet engine 100.

[0058] In some embodiments of the predictive imbalance condition diagnostic method disclosed herein, a method of diagnosing the source of a jet engine imbalance can include using the model discussed previously to identify an imbalance condition of a jet engine having a vibration level above an acceptable vibration limit, the acceptable vibration limit being associated with a particular engine family and operating parameters. The predicted imbalance condition can then be used to define a work scope for engine repair and correction operations. Although the following description of the engine imbalance condition identification method 300 is made with reference to the jet engine 100 described previously, it should be understood that the same method can be used to diagnose other jet engines.

[0059] In one embodiment, as shown in Figure 6 As shown, the imbalance condition identification method 300 can include identifying a jet engine 100 in operation for core vibration analysis (process block 302). The core vibration can include the location, amplitude, and phase of the vibration, and the location, amplitude, and phase of the vibration can be collected from the jet engine 100 using, for example, vibration sensors, and can be recorded on, for example, an onboard flight recorder or transmitted to, for example, an MRO facility (process block 304). Operating parameter data of the jet engine 100 can also be acquired (process block 304). The operating parameter data can include, for example, inlet temperature, outlet temperature, supply pressure, physical properties, chemical properties, ambient temperature, combustor temperature, compressor outlet pressure, compressor outlet temperature, high pressure rotor speed, low pressure rotor speed, damper manufacturing variations, bearing manufacturing variations, damper operating conditions, bearing operating conditions, engine operator, engine operating region, and altitude.

[0060] In some disclosed embodiments, core vibration data and operating parameter data can be input into a predictive diagnostic model, such as the model developed in process blocks 212 and 214, having a linear set of core vibration-imbalance state data for each given combination of operating parameters in the MRO database (process block 306). For example, based on a best fit of measured vibration data and operating parameters for jet engine 100, the input core vibration data can be matched to a linear set of historical imbalance and core vibration ratio data (process block 308). In some embodiments, the assignment to the linear set can then be completed based on known tolerances for the parameters and responses. The response tolerance can be calculated as a function of the first actual response, the second actual response, the first predicted response, and the second predicted response. The load tolerance can be calculated as a function of the actual high pressure compressor imbalance, the actual high pressure turbine imbalance, the predicted high pressure compressor imbalance, and the predicted high pressure turbine imbalance.

[0061] With continued reference to Figure 6 The upper and lower bounds of the estimate of the identified one or more sets of imbalance are then used in a two-step random forest prediction (process block 310). A first imbalance prediction having a first amplitude and a first phase and a second imbalance prediction having a second amplitude and a second phase are plotted against the first core vibration ratio. The first imbalance, the first phase, the second imbalance, the second phase, and the first core vibration ratio are then plotted against the second core vibration ratio. The amplitude and location of the imbalance are then estimated based on a comparison to historical data values using a random forest prediction model (process block 312).

[0062] From the amplitude and location of the identified imbalance determined by the random forest prediction model, an engine repair plan can then be generated that identifies which compressor 112, 114 or turbine 118, 120 should be rebalanced to correct the observed engine vibration and / or imbalance condition, identifying one or more locations on the engine shaft 124, 126 to which a balancing weight should be attached. A weight of the required mass can then be attached at the one or more identified locations on the engine shaft 124, 126 to correct the observed imbalance condition of the jet engine 100. Advantageously, this saves technician time and fuel costs associated with conventional trial-and-error methods for identifying the correct engine repair plan, and reduces the time that the jet engine 100 must be left in the repair shop when an unacceptably large imbalance or core vibration is observed.

[0063] In some embodiments of the predictive engine diagnostic method 300, the accuracy of the identification can then be evaluated based on whether the identified imbalance condition matches an imbalance condition empirically observed during repair of the jet engine 100.

[0064] In some embodiments of the disclosed method, the data regarding whether the identification was accurate or inaccurate can be further used to improve the diagnostic model. Returning now to Figure 2B As shown, in some embodiments, the individual analysis models generated in process block 214 can be adjusted (process block 220) in collecting information regarding the accuracy of the identification generated by the prediction model. In one example embodiment, the models are updated to account for correct and incorrect identifications of the unbalance location in the jet engine 100.

[0065] Additional description of embodiments of interest

[0066] Clause 1. A method for correcting rotor unbalance of a jet engine, comprising:

[0067] (a) generating one or more linear vibration ratio-unbalance relationship sets for different sets of operating parameters based on a database;

[0068] (b) generating one or more individual analysis models for each linear set of vibration ratio-unbalance data;

[0069] (c) recording core vibration signatures and sets of operating parameters of a jet engine;

[0070] (d) inputting the core vibration signatures and sets of operating parameters into the one or more individual analysis models of step (b);

[0071] (e) identifying a best fit linear set based on operating parameters;

[0072] (f) determining an unbalance condition by comparing measured core vibration signatures to historical vibration signatures recorded for the best fit linear set; and

[0073] (g) applying one or more weights to at least one of a compressor, a turbine, a fan blade, a fan disk, or any combination thereof of the jet engine.

[0074] Clause 2. The method of clause 1, wherein the unbalance condition of step (f) further comprises a location, a magnitude, and a phase component.

[0075] Clause 3. The method of any of the preceding clauses, wherein step (f) further comprises identifying the location, the magnitude, and the phase component using a two-step random forest prediction method.

[0076] Clause 4. The method of any of the preceding clauses, wherein step (e) further comprises estimating an upper and lower bound of possible unbalance values of the best fit linear set.

[0077] Clause 5. The method of any of the preceding clauses, wherein the determination of step (f) is further used to define a scope of an engine repair plan.

[0078] Clause 6. The method of any of the preceding clauses, wherein the engine repair plan further comprises determining one or more locations to attach the one or more weights to correct the unbalance condition at step (g).

[0079] Clause 7. The method of any of the preceding clauses, wherein the method further comprises evaluating an accuracy of the determination of step (f).

[0080] Clause 8. The method of any of the preceding clauses, wherein the evaluation of the accuracy of the determination of step (f) is further used to update the model and / or the one or more linear vibration ratio- unbalance relationship sets.

[0081] Clause 9. A model for determining an unbalance condition of a jet engine, comprising:

[0082] a database containing correlated core vibration data sets, key engine operating parameters, and engine unbalance conditions;

[0083] an input function configured to allow a user to input:

[0084] core vibration input data;

[0085] engine operating parameters; and

[0086] an output function configured to identify one or more engine unbalance conditions based on the core vibration input data and key engine operating parameters.

[0087] Clause 10. The model of clause 9, wherein the core vibration input data is obtained by measuring one or more vibrations of a jet engine in operation.

[0088] Clause 11. The model of any of clauses 9-10, wherein core vibration input data is in the form of a ratio between the measured vibration and a maximum vibration tolerance or shipment limit.

[0089] Clause 12. The model of any of clauses 9-11, wherein engine operating parameters include one or more of an inlet temperature, an outlet temperature, a supply pressure, a physical property, a chemical property, an ambient temperature, a combustor temperature, a compressor outlet pressure, a compressor outlet temperature, a high pressure rotor speed, a low pressure rotor speed, a damper manufacturing variation, a bearing manufacturing variation, a damper operating condition, a bearing operating condition, an engine operator, an engine operating region, and an altitude.

[0090] Clause 13. The model of any of clauses 9-12, wherein the one or more engine unbalance states further comprise a location, a magnitude, and a phase component.

[0091] Clause 14. The model of any of clauses 9-13, wherein the output function further provides an engine repair plan.

[0092] Clause 15. A method of developing a model for determining engine unbalance states, comprising:

[0093] (a) measuring a core vibration data set and an operating parameter data set associated with a jet engine;

[0094] (b) storing the core vibration data set and the operating parameter data set;

[0095] (c) determining an engine unbalance state associated with a combination of the core vibration data set and the operating parameter data set;

[0096] (d) repeating steps (a)-(c) until a sufficient number of data sets are recorded to generate a predictive model for determining unbalance states; and

[0097] (e) developing the predictive model for determining one or more unbalance states based on the measured core vibration and operating parameter data.

[0098] Clause 16. The method of clause 15, wherein step (e) further comprises (i) generating one or more linear vibration ratio-unbalance relationship sets for different operating parameter sets based on the database, and (ii) generating one or more separate analytical models for each linear set of vibration ratio-unbalance data.

[0099] Clause 17. The method of any of clauses 15-16, wherein step (e) further comprises using a random forest predictive model to determine the one or more unbalance states.

[0100] Clause 18. The method of any of clauses 15-17, wherein the one or more unbalance states of step (e) further comprise a location, a magnitude, and a phase component.

[0101] Clause 19. The method of any of clauses 15-18, wherein (b) further comprises storing the core vibration data set and the operating parameter data set when the core vibration data set is outside of or within a core vibration shipment limit of the jet turbine engine.

[0102] Clause 20. The method of any of clauses 15-19, wherein the model of step (e) is further used to determine an imbalance condition of the engine based on the measured core vibration data and operating parameter data.

[0103] Clause 21. The method of any of clauses 15-20, wherein the model of step (e) is further updated based on an assessment of accuracy of the determination of one or more imbalance conditions from the model.

[0104] In view of the many possible embodiments to which the principles of the disclosed application can be applied, it should be recognized that the embodiments shown are only preferred examples of the application and should not be considered limiting of its scope. Rather, the scope of the application is defined by the following claims. Therefore, we claim all that comes within the scope and spirit of these claims.

Claims

1. A method for correcting rotor imbalance of a jet engine, characterized by, Comprising: (a) generating one or more linear sets for different sets of operating parameters based on a database, wherein for each linear set, there is a linear relationship between vibration ratio data and imbalance state data, wherein the vibration ratio corresponds to a ratio of a measured vibration state to a predetermined maximum vibration amount, and wherein each linear set is defined for a respective combination of operating parameters; (b) generating one or more separate analytical models for each linear set of vibration ratio-imbalance data; (c) recording core vibration signatures and sets of operating parameters for a jet engine; (d) inputting the core vibration signatures and sets of operating parameters into the one or more separate analytical models of step (b); (e) identifying a best fitting linear set based on the core vibration signatures and operating parameters; (f) determining an imbalance state by comparing a measured core vibration signature to historical vibration signatures recorded for the best fitting linear set; and (g) applying one or more weights to at least one of a compressor, turbine, fan blade, and fan disk, or any combination thereof, of the jet engine based on the determined imbalance state; wherein step (f) further comprises using a two-step random forest prediction method to identify location, amplitude, and phase components of the core vibration signature; and wherein the determination of step (f) is further used to define a scope of an engine repair plan, and wherein the engine repair plan further comprises determining one or more locations to attach the one or more weights in step (g) to correct the imbalance state.

2. The method of claim 1, wherein, wherein the imbalance state of step (f) further comprises location, amplitude, and phase components.

3. The method of claim 1, wherein, wherein step (e) further comprises estimating an upper and lower bound of possible imbalance values for the best fitting linear set.

4. The method of claim 1, wherein, wherein the method further comprises evaluating an accuracy of the determination of step (f).

5. The method of claim 4, wherein, wherein the evaluation of the accuracy of the determination of step (f) is further used to update the model and / or the one or more linear sets.

6. A model for determining an unbalance state of a jet engine using the method according to claim 1, characterized in that Comprising: a database comprising correlated core vibration data sets, key engine operating parameters, and engine imbalance states; an input module configured to allow a user to input: core vibration input data; engine operating parameters; and an output module configured to identify one or more engine imbalance states based on the core vibration input data and key engine operating parameters. wherein the core vibration input data is obtained by measuring one or more vibrations of a jet engine in operation.

7. The model of claim 6, wherein, wherein the core vibration input data is in the form of a ratio between a measured vibration and a maximum vibration tolerance or shipment limit.

8. The model of claim 6, wherein, ​ 9. The model of claim 6, wherein, wherein the engine operating parameters include one or more of inlet temperature, outlet temperature, supply pressure, physical properties, chemical properties, ambient temperature, combustor temperature, compressor outlet pressure, compressor outlet temperature, high pressure rotor speed, low pressure rotor speed, damper manufacturing variations, bearing manufacturing variations, damper operating conditions, bearing operating conditions, engine operator, engine operating region, and altitude.

10. The model of claim 6, wherein, wherein the one or more engine imbalance states further include a location, a magnitude, and a phase component.

11. The model of claim 6, wherein, wherein the output module further provides an engine repair plan.

12. A method of developing a model for determining an engine unbalance condition of a jet turbine engine, characterized by, comprising: (a) measuring a core vibration data set and an operating parameter data set associated with a jet engine; (b) storing the core vibration data set and the operating parameter data set; (c) determining the engine imbalance states associated with a combination of the core vibration data set and the operating parameter data set; (d) repeating steps (a)-(c) until a sufficient number of data sets are recorded to generate a predictive model for determining imbalance states; and (e) developing a predictive model for determining one or more imbalance states based on the measured core vibration and operating parameter data; and (f) generating one or more linear vibration ratio-imbalance relationship sets for different operating parameter sets based on the database, and one or more separate analysis models for each linear set of vibration ratio-imbalance data; wherein for each linear vibration ratio-imbalance relationship set, there is a linear relationship between the vibration ratio data and the imbalance state data, wherein the vibration ratio corresponds to a ratio of a measured vibration state to a predetermined maximum vibration amount; wherein step (e) further comprises determining an imbalance state by comparing a measured core vibration characteristic to historical vibration characteristics; and wherein step (e) further comprises determining the one or more imbalance states using a two-step random forest predictive model.

13. The method of claim 12, wherein, wherein the one or more imbalance states of step (e) further include a location, a magnitude, and a phase component.

14. The method of claim 12, wherein, wherein (b) further comprises storing the core vibration data set and the operating parameter data set when the core vibration data set is outside of or within a core vibration shipment limit of the jet turbine engine.

15. The method of claim 12, wherein, wherein the model of step (e) is further for determining an imbalance state of an engine based on measured core vibration data and operating parameter data. wherein the one or more imbalance states of step (e) further include a location, a magnitude, and a phase component. wherein (b) further comprises storing the core vibration data set and the operating parameter data set when the core vibration data set is outside of or within a core vibration shipment limit of the jet turbine engine. wherein the model of step (e) is further for determining an imbalance state of an engine based on measured core vibration data and operating parameter data.

Images