United Technologies Corporation

Raytheon Technologies Corporation

University of Southern California

Inha University

Allan J Volponi

Ravi Rajamani

Liang Tang

Thomas Woodley Brotherton

Zaffir A Chaudhry

Gregory S Hagen

Sheridon Everette Haye

Yan Chen

Jason B Solomonides

Danbing Seto

Robert H Luppold

Angelo Martucci

Jun Liu

C Bruce Wood

Andrew F Geib

Sang Jun Lee

Chung Chieh Kuo

Lichu Zhao

Martin Gawecki

Wonik Choi

Frederick A Just-Agosto

David Serrano

Hans R Depold

Steven W Butler

Bruce C Wood

Thomas Brotherton

A method for fault diagnosis of a bearing includes detecting, using an oil debris monitor (ODM) sensor, ODM data corresponding to an amount of debris flowing downstream from the bearing. The method also includes detecting, using a vibration sensor, vibration data corresponding to vibration of the bearing during use. The method also includes determining, by a controller, a vibration stage flag corresponding to a severity of damage of the bearing based on the vibration data. The method also includes determining, by the controller, a severity level of the damage of the bearing based on a combination of the vibration stage flag and the ODM data. The method also includes outputting, by an output device, the severity level.

Integrated vibe/ODM fusion and trending analysis for prognostic health management of engine bearing

A fault isolation and ambiguity resolution system includes one or more analytic engines executable by a processing system and a reasoning system. The one or more analytic engines are operable to detect a fault associated with a monitored system based on data extracted from one or more data repository. The reasoning system includes a single fault isolator operable to identify an ambiguity group including the fault and one or more related faults of the monitored system. The reasoning system also includes an inference system operable to utilize evidence to resolve ambiguity between the fault and the one or more related faults of the ambiguity group as a diagnosis result.

System fault isolation and ambiguity resolution

The present disclosure provides methods, systems, and computer-readable media for the fault detection and identification in an aircraft that may occur in real time during a flight, or any time the aircraft is operating. For example, a controller may receive and calculate various parameter values at various times during an aircraft flight, and compare those values to baseline values in order to determine if a fault has occurred. Additionally, the controller may identify a fault that has occurred by comparing a calculated fault signature value with a fault signature database comprising fault signatures and their associated faults.

Fault detection methods and systems

System and methods for detecting anomalies and identifying faults of a gas turbine engine may include a recorder in communication with a processor. The recorder may be configured to capture archival data of the gas turbine engine. A flight normalizer module may be configured to produce normalized results based on the archival data. A flight parameter features module may be configured to generate flight parameter features based on the normalized results. A data warehouse module may be configured to determine suspected fault classes by comparing the flight parameter features against training parameter features stored in the data warehouse module based on queries from the flight parameter features module. A majority vote module may be configured to determine a diagnosed fault class based on the suspected fault classes.

Gas turbine engine anomaly detections and fault identifications

An example data assessment method for a diagnostic system includes receiving a set of initialization data, analyzing the set of initialization data to identify a data outlier in the set of initialization data, and determining whether the set of initialization data is bimodal. The method further includes establishing a set of cleaned data based on the analysis and establishing a baseline operating condition for the device using the set of cleaned data.

Anomalous data detection method

The invention increases the fidelity of gas turbine engine module performance estimates that in turn enhance performance tracking and visibility. The methodology obviates input signal filtering since filtering may mask the onset and detection of a rapid measurement shift indicative of serious engine performance issues. The invention supports trend detection processes for timely detection, isolation and alerting of performance and engine system related faults.

Reducing gas turbine performance tracking estimation non-repeatability

A method for monitoring performance of an actuator is provided that includes the steps of: 1) determining an actuator response time constant in a control system, which actuator response time constant is representative of a task time taken by the actuator to complete a selected percentage of a task; 2) determining a rate of change of the actuator response time constant over a predetermined number of events; 3) determining a fault value indicative of when the actuator response time constant will equal or exceed an error time constant using the determined rate of change of the actuator response time constant; and 4) outputting a signal from the control system representative of the determined fault value.

Actuator performance monitoring system

Systems and methods involving engine models are provided. A representative method for updating a gas turbine engine reference model includes: determining whether an absolute difference between a dominant time constant of a sensor and an assumed sensor model time constant is outside a tolerance value; and responsive to determining that the absolute difference is outside the tolerance value, updating the assumed sensor model time constant with the dominant time constant of the sensor.

Systems and methods involving engine models

A system and method for narrowing an assessment of root cause to a single stage within a gas turbine engine module using coupling factors and known instrumentation non-repeatability. Embodiments examine certain root cause (RC) effects that manifest themselves as coupling levels, or ratios (CR), between an engine module's efficiency change &#x394;&#x3b7; and its flow parameter change &#x394;FP.

Process and methodology for root cause identification in gas turbine engine performance tracking

An apparatus for assessing health of a device comprising a data alignment module for receiving a plurality of sensory outputs and outputting a synchronized data stream, an analysis module for receiving the synchronized data stream and outputting at least one device health feature, and a high level diagnostic feature information fusion module for receiving the at least one device health feature and outputting a device health assessment.

System for gas turbine health monitoring data fusion

An isolation method and system is described for distinguishing between turbine case cooling (TCC) and high pressure turbine (HPT) performance faults. A trend is observed in gas path parameter data during cruise and a resulting percent &#x394; signature across the shift in the gas path parameters is assignable to either an HPT or TCC performance fault. During either fault, exhaust gas temperature (EGT) will shift upward. Since take-off EGT margin is calculated from take-off data, the shift, or lack of shift in EGT margin may be used to differentiate between TCC and HPT faults.

Method and system for identifying gas turbine engine faults

A real-time on board engine component performance tracking system for deriving high fidelity engine models capable of providing a reference level from which performance changes can be trended with reduced operating cost, increased safety, and increased reliability while minimizing memory requirements and maximizing speed.

Empirical tuning of an on board real-time gas turbine engine model

A method and system is described that estimates gas turbine engine module performance changes from gas path measurement data using a linear predictor-corrector estimation process. A measurement configuration matrix Mand a fault configuration Fmatrix are assembled. The configuration matrices Mand Fare used to adapt a typical linear predictor-corrector type of performance estimation process to a given measurement suite and are ideally suited for linear estimation systems such as those using a Kalman filter.

Process for adapting measurement suite configuration for gas turbine performance diagnostics

Method for detecting faults in a device comprising the steps of receiving a plurality of performance parameters, applying the plurality of performance parameters to a first model to produce a plurality of estimated performance parameters, applying the plurality of performance parameters to a second model to produce a plurality of estimated device parameters, computing a plurality of residuals from the plurality of estimated device parameters, computing a plurality of distance measuring from the plurality of residuals, detecting at least one parameter deviation using the plurality of residuals and the plurality of estimated performance parameters, and setting at least one detection flag if the detected at least one parameter deviation is persistent.

Hybrid model based fault detection and isolation system

A method for modeling engine operation comprising the steps of: 1. collecting a first plurality of sensory data, 2. partitioning a flight envelope into a plurality of sub-regions, 3. assigning the first plurality of sensory data into the plurality of sub-regions, 4. generating an empirical model of at least one of the plurality of sub-regions, 5. generating a statistical summary model for at least one of the plurality of sub-regions, 6. collecting an additional plurality of sensory data, 7. partitioning the second plurality of sensory data into the plurality of sub-regions, 8. generating a plurality of pseudo-data using the empirical model, and 9. concatenating the plurality of pseudo-data and the additional plurality of sensory data to generate an updated empirical model and an updated statistical summary model for at least one of the plurality of sub-regions.

Growing community of inventors

West Simsbury, CT, United States of America

Allan J Volponi