Gas turbine combustion profile monitoring

Abstract

Systems and methods for gas turbine combustion profile monitoring are disclosed. In one embodiment, a method for detecting an anomaly in a combustion section of a gas turbine is disclosed. The method includes receiving, from a plurality of thermal sensors disposed around an exhaust section of a gas turbine, exhaust profile data of the gas turbine. The method further analyzes the exhaust profile data to calculate statistical features associated with a peak-trough pattern. The method further determines, using a machine learning algorithm, that the statistical features are abnormal. In response to the determination, the method processes the exhaust profile data for a predetermined period of time and reports an anomaly in a combustion section of the gas turbine if the statistical features remain abnormal for the predetermined period of time.

Description

TECHNICAL FIELD

The disclosure relates to the art of turbomachines, and, more particularly, to systems and methods of gas turbine combustion profile monitoring.

BACKGROUND

Turbomachines can include a compressor portion linked to a turbine portion through a common compressor/turbine shaft and a combustor assembly. An inlet airflow can pass through an air intake toward the compressor portion. In the compressor portion, the inlet airflow can be compressed through a number of sequential stages toward the combustor assembly. In the combustor assembly, the compressed airflow can mix with fuel to form a combustible mixture. The combustible mixture can be combusted in the combustor assembly to form hot gases. The hot gases can be guided along a hot gas path of the turbine portion through a transition piece. The hot gases can expand along a hot gas path through a number of turbine stages acting upon turbine bucket airfoils mounted on wheels to create work that is output, for example, to power a generator. The hot gases can pass from the turbine portion through an exhaust system as exhaust gases. A number of thermocouples can be arranged in the exhaust system to measure temperatures of the exhaust gases.

The temperatures of the exhaust gases measured by the thermocouples can form an exhaust profile. The exhaust profile can be used to assess the health of combustion hardware. Certain hardware issues may cause a combustor to run unusually hot or cold, which can disrupt the typical exhaust profile. An atypical exhaust profile pattern may indicate an abnormal operation of one or more combustors. The typical exhaust profile for some turbomachines is uniform, where the individual exhaust thermocouples deviate only slightly from the mean. For such turbomachines, detection of combustion hardware anomalies can be performed by identifying thermocouple groups that deviate significantly from the mean. Other turbomachines may have an exhaust profile that has a peak-trough pattern during normal operation. Typically, a number of peaks and a number of troughs in the peak-trough pattern correspond to the number of combustors of the turbomachine. The approach described above may not be effective at detecting combustion anomalies for turbomachines with a peak-trough pattern since the peak-trough profile pattern may be treated as abnormal deviations from the mean.

SUMMARY OF THE DISCLOSURE

This disclosure relates to systems and methods for gas turbine combustion profile monitoring. Certain embodiments can facilitate detecting an anomaly in a combustion section of a gas turbine. According to one embodiment of the disclosure, a method for detecting an anomaly in a combustion section of a gas turbine includes receiving, by at least one processor, from a plurality of thermal sensors disposed around an exhaust section of a gas turbine, the exhaust profile data of the gas turbine. The method may further include analyzing the exhaust profile data to calculate statistical features associated with a peak-trough pattern. The method may facilitate determination, using a machine learning algorithm, that the statistical features are abnormal. The method may further include, in response to the determination, processing the exhaust profile data for a predetermined period of time and reporting an anomaly in a combustion section of the gas turbine if the statistical features remain abnormal for the predetermined period of time.

According to another embodiment of the disclosure, a system for detecting an anomaly in a combustion section of a gas turbine is provided. The system may include a plurality of combustors associated with a combustion section and a plurality of thermal sensors disposed around an exhaust section of a gas turbine. The thermal sensors are configured to provide exhaust profile data of the gas turbine. The system further includes a processing circuit communicatively coupled to a memory, with the memory storing instructions which, when executed by the processing circuit, perform operations.

Other embodiments, systems, methods, features, and aspects will become apparent from the following description taken in conjunction with the following drawings.

BRIEF DESCRIPTION OF THE DRAWINGS

FIG. 1 is a block diagram of an example gas turbine, according to an embodiment of the disclosure.

FIG. 2 is an axial view of an example exhaust system of a gas turbine and a combustion anomaly detection system, according to an embodiment of the disclosure.

FIG. 3A is a normal profile of thermocouple exhaust data, according to an embodiment of the disclosure.

FIG. 3B is an abnormal profile of the thermocouple exhaust data, according to an embodiment of the disclosure.

FIG. 4 is a flow chart illustrating an example method of detecting an anomaly in a combustion section of a gas turbine, according to an embodiment of the disclosure.

FIG. 5 is a flow chart illustrating an example method for identifying peaks and troughs locations in thermocouple exhaust data, according to an embodiment of the disclosure.

FIG. 6 is a block diagram illustrating an example controller for controlling a gas turbine, according to an embodiment of the disclosure.

DETAILED DESCRIPTION

The following detailed description includes references to the accompanying drawings, which form part of the detailed description. The drawings depict illustrations, in accordance with example embodiments. These example embodiments, which are also referred to herein as “examples,” are described in enough detail to enable those skilled in the art to practice the present subject matter. The example embodiments may be combined, other embodiments may be utilized, or structural, logical, and electrical changes may be made, without departing from the scope of the claimed subject matter. The following detailed description is, therefore, not to be taken in a limiting sense, and the scope is defined by the appended claims and their equivalents.

Certain embodiments of the disclosure concern methods and systems for gas turbine combustion profile monitoring which can facilitate detecting an anomaly in a combustion section of a gas turbine. The disclosed methods and systems may also provide for determining a non-uniform temperature profile during operation of a gas turbine.

In some example embodiments of the disclosure, a processing circuit may receive, from a plurality of thermal sensors disposed around an exhaust section of a gas turbine, the exhaust profile data of the gas turbine. The exhaust profile data can be analyzed to calculate statistical features associated with a peak-trough pattern. The analysis may include identifying, based on the exhaust profile data, a peak-trough couple associated with each thermal sensor and calculating the statistical features for each peak-trough couple. The processing circuit may further determine, using a machine learning algorithm, that the statistical features are abnormal. In response to the determination, processing the exhaust profile data may continue for a predetermined period of time. If the statistical features remain abnormal for the predetermined period of time, an anomaly in a combustion section of the gas turbine may be reported.

Technical effects of certain embodiments of the disclosure may include combustion monitoring of gas turbines. Further technical effects of certain embodiments of the disclosure may increase the probability of detecting combustion anomalies in gas turbines before the combustion anomalies may result in significant events or hardware failures. The disclosed embodiments of the disclosure may provide insight in the combustion health of the gas turbines to reduce combustion related trips, forced outage time, and unplanned costs.

The following provides the detailed description of various example embodiments related to systems and methods for operational impact modeling using statistical and physics-based methodologies.

A gas turbomachine system, in accordance with an example embodiment of the disclosure, is illustrated generally at 2, in FIG. 1. Gas turbomachine system 2 may include a gas turbomachine 4 having a compressor portion 6 fluidically connected to a turbine portion 8 through a combustor assembly 10. Combustor assembly 10 may include one or more combustors 12, which may be arranged in a can-annular array. Compressor portion 6 may also be mechanically linked to turbine portion 8 through a shaft 14. Compressor portion 6 may include an air inlet 16 and turbine portion 8 may include an exhaust outlet 18. An air intake system 20 may be fluidically connected to air inlet 16. Air intake system 20 may condition air passing into compressor portion 6. For example, air intake system 20 may remove or reduce moisture that may be carried by air passing into air inlet 16. An exhaust system 22 may be fluidically connected to exhaust outlet 18. Exhaust system 22 may condition exhaust gases passing from turbine portion 8 prior to introduction to an environment. Exhaust system 22 may include a plurality of temperature sensors 50. Gas turbomachine system 2 may also include a driven load 30 that could take the form of a generator, a pump, or a vehicle. The gas turbomachine system 2 may further include a combustor anomaly detection system 60 that may be operatively connected to an alarm 74.

As shown in FIG. 2, exhaust system 22 may include a housing 40 having an outer surface 42 and an inner surface 44 that defines an exhaust gas flow path 46. Exhaust system 22 may include a plurality of temperature sensors, one of which is indicated at 50, arranged on housing 40. Temperature sensors 50 may take the form of thermocouples that are circumferentially arrayed about inner surface 44 and exposed to exhaust gas flow path 46. In accordance with an embodiment of the disclosure, the combustor anomaly detection system 60 is operatively connected to each of the plurality of temperature sensors 50. It should be understood that combustor anomaly detection system 60 may be co-located with gas turbomachine 4, may be integrated into the turbine controller, or may be in a central global monitoring station. Thus, combustor anomaly detection system 60 may receive data from and simultaneously monitor multiple gas turbomachine systems located anywhere in the world from a single monitoring location. Combustor anomaly detection system 60 may include a central processing unit (CPU) 62, and a computer readable storage medium 64 provided with a set of program instructions 68 and a memory 70. As will be discussed in more detail below, combustor anomaly detection system 60 may be operatively connected to an alarm 74 that may provide a visual and/or an audible alarm upon detecting a combustion anomaly.

FIGS. 3A and 3B illustrate two example profiles of thermocouple exhaust data, according to an embodiment of the disclosure. The data may be presented as plots in polar coordinates. An angle coordinate of a point on the plot may correspond to the angle of a temperature sensor from the plurality of temperature sensors. Radius of the point may correspond to temperature data provided by the temperature sensor.

FIG. 3A represents an example normal profile of thermocouple exhaust data for a turbomachine including 6 combustors. The normal profile may correspond to normal operation of the combustors. In the example of FIG. 3A, the normal profile includes 6 peaks that correspond to six combustors of gas turbomachine system 2. The six peaks alternate with six troughs. Overall, six peaks and six troughs may form a normal peak and trough pattern for six combustor turbomachines.

FIG. 3B represents an example abnormal profile of thermocouple exhaust data for a turbomachine including six combustors. Unlike the normal profile of FIG. 3A, the abnormal profile of FIG. 3B misses one peak at area 80. Missing a peak in a peak-trough pattern may indicate an anomaly in operations of combustors of the gas turbomachine system 2.

FIG. 4 is a flow chart showing an example method 400 for detecting an anomaly in a combustion section of a gas turbine, according to an embodiment of the disclosure. The operations of the method 400 may be performed by combustion anomaly detection system 60. The operations of method 400 may be embedded in program instructions 68 of the combustor anomaly detection system 60. The method 400 may analyze thermocouple exhaust data to detect an abnormal peak-trough pattern. In some embodiments of the disclosure, the system 60 is configured to perform processing of the exhaust data one time per minute.

In block 402, combustion anomaly detection system 60 may receive thermocouple (TC) exhaust data from temperature sensors 50. In block 404, the system 60 may perform data quality checks. At decision block 406, the system 60 may determine whether the turbomachine is running above a predetermined load, at which a peak-trough pattern is expected. If the turbomachine is not running above the predetermined load then, in block 408, the system 60 may proceed with evaluating subsequent data (for example, thermocouple exhaust data received in a subsequent minute).

If the turbomachine is running above the predetermined load, then the system 60 may calculate the deviation from mean exhaust temperature for each thermocouple in block 410. In block 412, the system 60 may identify peaks and troughs in exhaust data. In block 414, the system 60 may calculate statistical features (for example, a feature vector) for the peak-trough pairs. The statistical features may include the peak-to-trough temperature difference (delta), mean deviation from all peaks or troughs, minimum peak temperature, maximal peak temperature, minimal trough temperature, maximal trough temperature, maximal peak-to-trough delta, minimal peak-to-trough delta, and so on.

In decision block 416, the system 60 may determine whether the profile corresponding to the thermocouple exhaust data is abnormal. In some embodiments of the disclosure, the determination includes processing the feature vector evaluated at block 414 through a machine learned classification model. It should be appreciated by those skilled in the art, that the type of suitable classification models can include but are not limited to Support Vector Machine (SVM), Artificial Neural Network (ANN), decision tree model, or other classifiers. The model may be trained offline using the feature vectors of both normal exhaust data samples and failure exhaust data samples. By processing the feature vector using the trained model, the system 60 may determine whether there is an abnormal peak-trough pattern in the thermocouple exhaust data. If the profile (peak-trough pattern) is normal, then the system 60 may proceed with evaluating subsequent thermocouple exhaust data in block 418.

If profile is abnormal, system 60 may count the persistence of the abnormality and evaluate the latching of the abnormality. If the abnormal peak-trough pattern is present for a predefined period of time and an alarm has not already been generated during a predefined latch period, an alarm may be triggered for further evaluation and action in block 422.

FIG. 5 is a flow chart illustrating an example method 500 for identifying peaks and troughs locations in thermocouple exhaust data, in accordance with an embodiment of the disclosure. The method 500 may provide details of block 412 of the method 400 shown in FIG. 4. In block 502, the method 500 may include receiving thermocouple exhaust data. The thermocouple data may include temperatures Y(i) provided by temperature sensors 50 for a given minute. In block 504, the method may include detecting the locations of peaks. The location of peaks may be defined by condition Y(i)>Y(i−1) and Y(i)>Y(i+1). In block 506, the method 500 may include detecting the location of troughs. Each of the troughs may be defined as the minimal Y(i) between two subsequent peaks. In block 508, the method 500 may include filling in undetected peaks based on gaps in spatial location. In block 510, the method 500 may include performing data correction if more than M peaks are detected, wherein M is the number of combustors in the turbomachine. In block 512, the method 500 may provide for outputting final peak and trough location.

FIG. 6 depicts a block diagram illustrating an example controller 600 for detecting an anomaly in a combustion section, in accordance with an embodiment of the disclosure. More specifically, the elements of the controller 600 may be used to run a gas turbine under a plurality of operational conditions while within predetermined combustion operational boundaries, automatically collect operational data associated with the gas turbine while the gas turbine is running, store the operational data, generate a set of constants for one or more predetermined combustion transfer functions based on the operational data, and store the set of constants in the gas turbine combustion control system to be used during the commissioning of the gas turbine. The controller 600 may include a memory 610 that stores programmed logic 620 (e.g., software) and may store data 630, such as operational data associated with the gas turbine, the set of constants, and the like. The memory 610 also may include an operating system 640.

A processor 650 may utilize the operating system 640 to execute the programmed logic 620, and in doing so, may also utilize the data 630. A data bus 660 may provide communication between the memory 610 and the processor 650. Users may interface with the controller 600 via at least one user interface device 670, such as a keyboard, mouse, control panel, or any other device capable of communicating data to and from the controller 600. The controller 600 may be in communication with the gas turbine combustion control system online while operating, as well as in communication with the gas turbine combustion control system offline while not operating, via an input/output (I/O) interface 680. Additionally, it should be appreciated that other external devices or multiple other gas turbines or combustors may be in communication with the controller 600 via the I/O interface 680. In the illustrated embodiment of the disclosure, the controller 600 may be located remotely with respect to the gas turbine; however, it may be co-located or even integrated with the gas turbine. Further, the controller 600 and the programmed logic 620 implemented thereby may include software, hardware, firmware, or any combination thereof. It should also be appreciated that multiple controllers 600 may be used, whereby different features described herein may be executed on one or more different controllers 600.

References are made to block diagrams of systems, methods, apparatuses, and computer program products, according to example embodiments of the disclosure. It will be understood that at least some of the blocks of the block diagrams, and combinations of blocks in the block diagrams, may be implemented at least partially by computer program instructions. These computer program instructions may be loaded onto a general purpose computer, special purpose computer, special purpose hardware-based computer, or other programmable data processing apparatus to produce a machine, such that the instructions which execute on the computer or other programmable data processing apparatus create means for implementing the functionality of at least some of the blocks of the block diagrams, or combinations of blocks in the block diagrams discussed.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means that implement the function specified in the block or blocks. The computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions that execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the block or blocks.

One or more components of the systems and one or more elements of the methods described herein may be implemented through an application program running on an operating system of a computer. They also may be practiced with other computer system configurations, including hand-held devices, multiprocessor systems, microprocessor based or programmable consumer electronics, mini-computers, mainframe computers, and the like.

Application programs that are components of the systems and methods described herein may include routines, programs, components, data structures, and so forth that implement certain abstract data types and perform certain tasks or actions. In a distributed computing environment, the application program (in whole or in part) may be located in local memory or in other storage. In addition, or alternatively, the application program (in whole or in part) may be located in remote memory or in storage to allow for circumstances where tasks are performed by remote processing devices linked through a communications network.

Many modifications and other embodiments of the example descriptions set forth herein to which these descriptions pertain will come to mind having the benefit of the teachings presented in the foregoing descriptions and the associated drawings. Thus, it will be appreciated that the disclosure may be embodied in many forms and should not be limited to the example embodiments described above.

Therefore, it is to be understood that the disclosure is not to be limited to the specific embodiments disclosed and that modifications and other embodiments are intended to be included within the scope of the appended claims. Although specific terms are employed herein, they are used in a generic and descriptive sense only and not for purposes of limitation.

Claims

1. A system for detecting an anomaly in a combustion section of a gas turbine, the system comprising: a plurality of combustors associated with a combustion section;a plurality of thermal sensors disposed at an exhaust section of a gas turbine, wherein the thermal sensors are configured to provide exhaust profile data of the gas turbine;a processing circuit communicatively coupled to a memory, the memory storing instructions which when executed by the processing circuit perform operations comprising:receiving, from the plurality of thermal sensors, the exhaust profile data of the gas turbine;analyzing the exhaust profile data to calculate statistical features associated with a peak-trough pattern;determining, using an algorithm or model, that the statistical features are abnormal; andin response to the determination, continuing processing of the exhaust profile data for a predetermined period of time; andreporting an anomaly in the combustion section of the gas turbine when the statistical features remain abnormal for the predetermined period of time.

2. The system of claim 1, wherein the algorithm or model is based on historical exhaust profile data, the historical exhaust profile data including normal data samples and false data samples.

3. The system of claim 1, wherein the thermal sensors are positioned radially around an exhaust component associated with the turbine.

4. The system of claim 1, wherein the sensors are disposed in an evenly spaced array.

5. The system of claim 1, wherein the exhaust profile data includes a plurality of peak and trough couples, each peak and trough couple of the plurality of peaks and troughs corresponding to at least one combustor of the plurality of the combustors.

6. The system of claim 5, wherein the analyzing includes evaluating each peak and trough couple relative to an expected peak-trough pattern.

7. The system of claim 5, wherein analyzing includes: identifying, based on the exhaust profile data, a peak and trough couple associated with each thermal sensor; andcalculating the statistical features for each peak and trough couple.

8. The system of claim 1, wherein the exhaust profile data includes statistical features associated with the plurality of thermal sensors, the statistical features including at least one of the following: a minimum peak temperature, a maximum peak temperature, a minimum trough temperature, a maximum trough temperature, a minimum peak-to-trough delta, and a maximum peak-to-trough delta.

9. The system of claim 1, wherein the determining that the statistical features are abnormal includes creating a feature vector based at least on the statistical features and processing the feature vector through a classification model.

10. The system of claim 1, further comprising prior to the analyzing: determining a quality of the exhaust profile data versus a predetermined quality level; andin response to the determining that the quality is below a predetermined quality level, adjusting the exhaust profile data.

11. The system of claim 1, wherein the analyzing is performed after the gas turbine is operating above a predetermined load.

12. The system of claim 1, further comprising issuing an alarm based at least in part on the detecting of the anomaly in the combustion section of the gas turbine.

13. The system of claim 12, wherein the alarm triggers at least one of the following: a further evaluation and a responsive action.

14. A method for detecting an anomaly in a combustion section of a gas turbine, the method comprising: receiving, from a plurality of thermal sensors disposed at an exhaust section of a gas turbine, exhaust profile data of the gas turbine;analyzing the exhaust profile data to calculate statistical features associated with a peak-trough pattern;determining, using an algorithm or model, that the statistical features are abnormal; andin response to the determination, continuing processing of the exhaust profile data for a predetermined period of time; andreporting an anomaly in a combustion section of the gas turbine when the statistical features remain abnormal for the predetermined period of time.

15. The method of claim 14, wherein: the algorithm or model is based on historical exhaust profile data, the historical exhaust profile data including normal data samples and false data samples.

16. The method of claim 14, wherein the thermal sensors are: positioned radially around an exhaust component associated with the gas turbine and disposed in an evenly spaced array.

17. The method of claim 14, wherein the exhaust profile data includes a plurality of peak and trough couples, each peak and trough couple of the plurality of peaks and troughs corresponding to at least one combustor of the plurality of combustors.

18. The method of claim 17, wherein the calculating the statistical features includes: identifying, based on the exhaust profile data, a peak and trough couple associated with each thermal sensor; andcalculating statistical features for each peak and trough couple.

19. The method of claim 14, wherein the determining that the statistical features are abnormal includes creating a feature vector based at least on the statistical features and processing the feature vector through a classification model.

20. A non-transitory computer-readable medium having stored instructions, which when executed by at least one processor, perform operations comprising: receiving, from a plurality of thermal sensors disposed at an exhaust section of a gas turbine, exhaust profile data of the gas turbine;analyzing the exhaust profile data to calculate statistical features associated with a peak-trough pattern;determining, using an algorithm or model, that the statistical features are abnormal; andin response to the determination, continuing processing of the exhaust profile data for a predetermined period of time; andreporting the anomaly in a combustion section of a gas turbine when the statistical features remain abnormal for the predetermined period of time.