METHOD AND SYSTEM FOR ADVISING OPERATOR ACTION

Info

Publication number: 20150066418
Type: Application
Filed: Mar 3, 2013
Publication Date: Mar 5, 2015
Inventors: Alberto Ceccherini (Florence), Abdurrahman Abdalah Khalidi (Doha), Arul Saravanapriyan (Doha), David Bianucci (Florence), Antonio Pumo (Florence), Alessandro Betti (Florence), Riccardo Crociani (Florence), Osama Naim Ashour (Doha)
Application Number: 14/382,013

Abstract

A system and computer-implemented method for monitoring and diagnosing anomalies in a wheel-space of a gas turbine is implemented using a computer device coupled to a user interface and a memory device and includes storing a plurality rule sets in the memory device, the rule sets relative to the wheel-space, the rule sets including at least one rule expressed as a relational expression of a real-time data output relative to a real-time data input, the relational expression being specific to a temperature of the wheel-space. The method also includes receiving real-time and historical data inputs from a condition monitoring system associated with the gas turbine, the data inputs relating to sources providing heat to the wheel-space and estimating a wheel-space temperature value using the inputs relating to a temperature of the wheel-space.

Description

Description

FIELD OF THE INVENTION

This description relates to generally to mechanical/electrical equipment operations, monitoring and diagnostics, and more specifically, to systems and methods for automatically advising operators of anomalous behavior of machinery.

BACKGROUND OF THE INVENTION

Monitoring machinery health and alerting operators to anomalous machinery conditions is an important part of operating one or a fleet of machines. Specifically, monitoring wheel-space temperatures is important to health monitoring of gas turbines. There is currently no known monitoring system for online estimation of this temperature, and only the measured temperature is monitored. By not comparing the measured value to an expected value, the dynamic baseline and physical insight to define alarm thresholds are unknown. Without this calculation, only static thresholds based on constant deviation from preset values is available. Further, troubleshooting is hindered without an estimation of the wheel-space temperature. For example, a determination can be made as to the source of a deviation between the expected value and the measured value and whether it is due to for example, but not limited to, a lack of cooling, a leakage, or worn seals. Moreover, rapidly changing operational conditions or very slowly changing operational conditions may make it difficult for an operator to recognize anomalous conditions or what operational changes can be made to mitigate the anomalous conditions.

At least some known wheel-space monitoring systems monitor the measured values only and using historical data for the same type of machine static thresholds are predefined, so that if the measured value exceeds the predefined threshold, an alarm is raised. Many attempts are needed to define and refine these thresholds, which do not take into account the machine running or load conditions. Such systems are prone to too many false alarms, and actual faults are generally detected too late. Moreover, only limited or no troubleshooting information is provided in such systems.

SUMMARY OF THE INVENTION

In one embodiment, a computer-implemented method for monitoring and diagnosing anomalies in a wheel-space of a gas turbine implemented using a computer device coupled to a user interface and a memory device includes storing a plurality rule sets in the memory device, the rule sets relative to the wheel-space, the rule sets including at least one rule expressed as a relational expression of a real-time data output relative to a real-time data input, the relational expression being specific to a temperature of the wheel-space. The method also includes receiving real-time and historical data inputs from a condition monitoring system associated with the gas turbine, the data inputs relating to sources providing heat to the wheel-space and estimating a wheel-space temperature value using the inputs relating to a temperature of the wheel-space.

In another embodiment, a wheel-space monitoring and diagnostic system for a gas turbine including an axial compressor and a low pressure turbine in flow communication includes a wheel-space temperature rule set, the rule set including a relational expression of a real-time data output relative to a real-time data input, the relational expression being specific to inputs relating to sources of heat in the wheel-space.

In yet another embodiment, one or more non-transitory computer-readable storage media has computer-executable instructions embodied thereon, wherein when executed by at least one processor, the computer-executable instructions cause the processor to receive a measured value of a temperature in a wheel-space of a gas turbine, receive measured values and inferred values of parameters associated with sources of heat into the wheel-space, estimate an expected temperature of the wheel-space, compare the expected temperature to the measured temperature of the wheel-space, and generate an advisory message recommending an action to be taken based on the comparison.

BRIEF DESCRIPTION OF THE DRAWINGS

FIGS. 1-5 show exemplary embodiments of the method and system described herein.

FIG. 1 is a schematic block diagram of a remote monitoring and diagnostic system in accordance with an exemplary embodiment of the present invention;

FIG. 2 is a block diagram of an exemplary embodiment of a network architecture of a local industrial plant monitoring and diagnostic system, such as a distributed control system (DCS);

FIG. 3 is a block diagram of an exemplary rule set that may be used with LMDS shown in FIG. 1;

FIG. 4 is a side elevation view of an architecture of a wheel-space cooling system of a gas turbine engine partially shown in FIG. 1 in accordance with an exemplary embodiment of the present disclosure; and

FIG. 5 is a flow diagram of a method of determining advice for an engine wheel-space temperature that exceeds a predetermined range in accordance with an exemplary embodiment of the present disclosure.

Although specific features of various embodiments may be shown in some drawings and not in others, this is for convenience only. Any feature of any drawing may be referenced and/or claimed in combination with any feature of any other drawing.

DETAILED DESCRIPTION OF THE INVENTION

The following detailed description illustrates embodiments of the invention by way of example and not by way of limitation. It is contemplated that the invention has general application to analytical and methodical embodiments of monitoring equipment operation in industrial, commercial, and residential applications.

Health monitoring of gas turbines is important to reduce maintenance costs and outage periods. The wheel-space temperature in the low pressure turbine (power turbine) of a gas turbine is a significant signal to monitor. Exposed to the hot gas path, the wheel-space may be vulnerable to fatigue/creep failure from thermal stresses. Estimating the wheel-space temperature requires knowing the sources of temperatures contribute to the wheel-space temperature and indicate how to monitor it and better estimate it. Knowing the sources of heat in the wheel-spaces permits a greater understanding of the status of the cooling system of the machine to highlight improper thermal behavior and excessive temperatures in the wheel-space area. In addition, by comparing this estimated wheel-space temperature to the actual measured wheel-space temperature, alarms based on this difference and define troubleshooting activities can be devised. The wheel-space temperature calculation method described below links the different components of a gas turbine together and simplifies identifying the source of the fault, for example, an excessive wheel-space temperature. Described herein is a method for online estimation of wheel-space temperature and generation of an engineering rule to prevent trips and/or prolonged shutdown periods and to provide meaningful troubleshooting.

Possible sources of heat contributing to the wheel-space temperature in a gas turbine engine include: hot gas form the combustion process that can be ingested, axial compressor bleed (cooling) air, and rotor windage effects. The bleed temperature is used initially as a baseline for the wheel-space temperature and compensate for the other effects to estimate it. The bleed temperature is calculated online using a thermodynamic simulation software that is used to monitor the performance of the machine. This is done by calculating the polytropic efficiency of the axial compressor and, then, extracting the bleed temperature (air temperature where the bleed is extracted). The difference between the wheel-space temperature and the bleed (cooling) temperature is not constant and depends on the flow path temperature. In some gas turbine engines, the turbine exhaust temperature is the only flow path temperature directly measured and is used herein to estimate the wheel-space temperature. There is a linear relationship between the wheel-space temperature rise above the bleed temperature on one hand and the exhaust temperature rise above the bleed temperature on the other. When the rule is initially deployed, the slope of this curve is calculated and averaged over a suitable period of time. This is then used to calculate the wheel-space temperature using the measured exhaust temperature and the calculated bleed temperature as described below in greater detail.

Embodiments of the present disclosure are not limited to detecting a high wheel-space temperature but is able to identify trends of a difference of wheel-space temperature and a real-time determined value of expected wheel-space temperature. A statistical tuning approach is added to the thermodynamic equation that enables the tuning directly on a running machine for all environments from an ambient inlet condition and correlating with machine running conditions.

FIG. 1 is a schematic block diagram of remote monitoring and diagnostic system 100 in accordance with an exemplary embodiment of the present invention. In the exemplary embodiment, system 100 includes a remote monitoring and diagnostic center 102. Remote monitoring and diagnostic center 102 is operated by an entity, such as, an OEM of a plurality of equipment purchased and operated by a separate business entity, such as, an operating entity. In the exemplary embodiment, the OEM and operating entity enter into a support arrangement whereby the OEM provides services related to the purchased equipment to the operating entity. The operating entity may own and operate purchased equipment at a single site or multiple sites. Moreover, the OEM may enter into support arrangements with a plurality of operating entities, each operating their own single site or multiple sites. The multiple sites each may contain identical individual equipment or pluralities of identical sets of equipment, such as trains of equipment. Additionally, at least some of the equipment may be unique to a site or unique to all sites.

In the exemplary embodiment, a first site 104 includes one or more process analyzers 106, equipment monitoring systems 108, equipment local control centers 110, and/or monitoring and alarm panels 112 each configured to interface with respective equipment sensors and control equipment to effect control and operation of the respective equipment. The one or more process analyzers 106, equipment monitoring systems 108, equipment local control centers 110, and/or monitoring and alarm panels 112 are communicatively coupled to an intelligent monitoring and diagnostic system 114 through a network 116. Intelligent monitoring and diagnostic (IMAD) system 114 is further configured to communicate with other on-site systems (not shown in FIG. 1) and offsite systems, such as, but not limited to, remote monitoring and diagnostic center 102. In various embodiments, IMAD 114 is configured to communicate with remote monitoring and diagnostic center 102 using for example, a dedicated network 118, a wireless link 120, and the Internet 122.

Each of a plurality of other sites, for example, a second site 124 and an nth site 126 may be substantially similar to first site 104 although may or may not be exactly similar to first site 104.

FIG. 2 is a block diagram of an exemplary embodiment of a network architecture 200 of a local industrial plant monitoring and diagnostic system, such as a distributed control system (DCS) 201. The industrial plant may include a plurality of plant equipment, such as gas turbines, centrifugal compressors, gearboxes, generators, pumps, motors, fans, and process monitoring sensors that are coupled in flow communication through interconnecting piping, and coupled in signal communication with DCS 201 through one or more remote input/output (I/O) modules and interconnecting cabling and/or wireless communication. In the exemplary embodiment, the industrial plant includes DCS 201 including a network backbone 203. Network backbone 203 may be a hardwired data communication path fabricated from twisted pair cable, shielded coaxial cable or fiber optic cable, for example, or may be at least partially wireless. DCS 201 may also include a processor 205 that is communicatively coupled to the plant equipment, located at the industrial plant site or at remote locations, through network backbone 203. It is to be understood that any number of machines may be operatively connected to network backbone 203. A portion of the machines may be hardwired to network backbone 203, and another portion of the machines may be wirelessly coupled to backbone 203 via a wireless base station 207 that is communicatively coupled to DCS 201. Wireless base station 207 may be used to expand the effective communication range of DCS 201, such as with equipment or sensors located remotely from the industrial plant but, still interconnected to one or more systems within the industrial plant.

DCS 201 may be configured to receive and display operational parameters associated with a plurality of equipment, and to generate automatic control signals and receive manual control inputs for controlling the operation of the equipment of industrial plant. In the exemplary embodiment, DCS 201 may include a software code segment configured to control processor 205 to analyze data received at DCS 201 that allows for on-line monitoring and diagnosis of the industrial plant machines. Data may be collected from each machine, including gas turbines, centrifugal compressors, pumps and motors, associated process sensors, and local environmental sensors including, for example, vibration, seismic, temperature, pressure, current, voltage, ambient temperature and ambient humidity sensors. The data may be pre-processed by a local diagnostic module or a remote input/output module, or may transmitted to DCS 201 in raw form.

A local monitoring and diagnostic system (LMDS) 213 may be a separate add-on hardware device, such as, for example, a personal computer (PC), that communicates with DCS 201 and other control systems 209 and data sources through network backbone 203. LMDS 213 may also be embodied in a software program segment executing on DCS 201 and/or one or more of the other control systems 209. Accordingly, LMDS 213 may operate in a distributed manner, such that a portion of the software program segment executes on several processors concurrently. As such, LMDS 213 may be fully integrated into the operation of DCS 201 and other control systems 209. LMDS 213 analyzes data received by DCS 201, data sources, and other control systems 209 to determine an operational health of the machines and/or a process employing the machines using a global view of the industrial plant.

In the exemplary embodiment, network architecture 100 includes a server grade computer 202 and one or more client systems 203. Server grade computer 202 further includes a database server 206, an application server 208, a web server 210, a fax server 212, a directory server 214, and a mail server 216. Each of servers 206, 208, 210, 212, 214, and 216 may be embodied in software executing on server grade computer 202, or any combinations of servers 206, 208, 210, 212, 214, and 216 may be embodied alone or in combination on separate server grade computers coupled in a local area network (LAN) (not shown). A data storage unit 220 is coupled to server grade computer 202. In addition, a workstation 222, such as a system administrator's workstation, a user workstation, and/or a supervisor's workstation are coupled to network backbone 203. Alternatively, workstations 222 are coupled to network backbone 203 using an Internet link 226 or are connected through a wireless connection, such as, through wireless base station 207.

Each workstation 222 may be a personal computer having a web browser. Although the functions performed at the workstations typically are illustrated as being performed at respective workstations 222, such functions can be performed at one of many personal computers coupled to network backbone 203. Workstations 222 are described as being associated with separate exemplary functions only to facilitate an understanding of the different types of functions that can be performed by individuals having access to network backbone 203.

Server grade computer 202 is configured to be communicatively coupled to various individuals, including employees 228 and to third parties, e.g., service providers 230. The communication in the exemplary embodiment is illustrated as being performed using the Internet, however, any other wide area network (WAN) type communication can be utilized in other embodiments, i.e., the systems and processes are not limited to being practiced using the Internet.

In the exemplary embodiment, any authorized individual having a workstation 232 can access LMDS 213. At least one of the client systems may include a manager workstation 234 located at a remote location. Workstations 222 may be embodied on personal computers having a web browser. Also, workstations 222 are configured to communicate with server grade computer 202. Furthermore, fax server 212 communicates with remotely located client systems, including a client system 236 using a telephone link (not shown). Fax server 212 is configured to communicate with other client systems 228, 230, and 234, as well.

Computerized modeling and analysis tools of LMDS 213, as described below in more detail, may be stored in server 202 and can be accessed by a requester at any one of client systems 204. In one embodiment, client systems 204 are computers including a web browser, such that server grade computer 202 is accessible to client systems 204 using the Internet. Client systems 204 are interconnected to the Internet through many interfaces including a network, such as a local area network (LAN) or a wide area network (WAN), dial-in-connections, cable modems and special high-speed ISDN lines. Client systems 204 could be any device capable of interconnecting to the Internet including a web-based phone, personal digital assistant (PDA), or other web-based connectable equipment. Database server 206 is connected to a database 240 containing information about industrial plant 10, as described below in greater detail. In one embodiment, centralized database 240 is stored on server grade computer 202 and can be accessed by potential users at one of client systems 204 by logging onto server grade computer 202 through one of client systems 204. In an alternative embodiment, database 240 is stored remotely from server grade computer 202 and may be non-centralized.

Other industrial plant systems may provide data that is accessible to server grade computer 202 and/or client systems 204 through independent connections to network backbone 204. An interactive electronic tech manual server 242 services requests for machine data relating to a configuration of each machine. Such data may include operational capabilities, such as pump curves, motor horsepower rating, insulation class, and frame size, design parameters, such as dimensions, number of rotor bars or impeller blades, and machinery maintenance history, such as field alterations to the machine, as-found and as-left alignment measurements, and repairs implemented on the machine that do not return the machine to its original design condition.

A portable vibration monitor 244 may be intermittently coupled to LAN directly or through a computer input port such as ports included in workstations 222 or client systems 204. Typically, vibration data is collected in a route, collecting data from a predetermined list of machines on a periodic basis, for example, monthly or other periodicity. Vibration data may also be collected in conjunction with troubleshooting, maintenance, and commissioning activities. Further, vibration data may be collected continuously in a real-time or near real-time basis. Such data may provide a new baseline for algorithms of LMDS 213. Process data may similarly, be collected on a route basis or during troubleshooting, maintenance, and commissioning activities. Moreover, some process data may be collected continuously in a real-time or near real-time basis. Certain process parameters may not be permanently instrumented and a portable process data collector 245 may be used to collect process parameter data that can be downloaded to DCS 201 through workstation 222 so that it is accessible to LMDS 213. Other process parameter data, such as process fluid composition analyzers and pollution emission analyzers may be provided to DCS 201 through a plurality of on-line monitors 246.

Electrical power supplied to various machines or generated by generated by generators with the industrial plant may be monitored by a motor protection relay 248 associated with each machine. Typically, such relays 248 are located remotely from the monitored equipment in a motor control center (MCC) or in switchgear 250 supplying the machine. In addition, to protection relays 248, switchgear 250 may also include a supervisory control and data acquisition system (SCADA) that provides LMDS 213 with power supply or power delivery system (not shown) equipment located at the industrial plant, for example, in a switchyard, or remote transmission line breakers and line parameters.

FIG. 3 is a block diagram of an exemplary rule set 280 that may be used with LMDS 213 (shown in FIG. 1). Rule set 280 may be a combination of one or more custom rules, and a series of properties that define the behavior and state of the custom rules. The rules and properties may be bundled and stored in a format of an XML string, which may be encrypted based on a 25 character alphanumeric key when stored to a file. Rule set 280 is a modular knowledge cell that includes one or more inputs 282 and one or more outputs 284. Inputs 282 may be software ports that direct data from specific locations in LMDS 213 to rule set 280. For example, an input from a pump outboard vibration sensor may be transmitted to a hardware input termination in DCS 201. DCS 201 may sample the signal at that termination to receive the signal thereon. The signal may then be processed and stored at a location in a memory accessible and/or integral to DCS 201. A first input 286 of rule set 280 may be mapped to the location in memory such that the contents of the location in memory is available to rule set 280 as an input. Similarly, an output 288 may be mapped to another location in the memory accessible to DCS 201 or to another memory such that the location in memory contains the output 288 of rule set 280.

In the exemplary embodiment, rule set 280 includes one or more rules relating to monitoring and diagnosis of specific problems associated with equipment operating in an industrial plant, such as, for example, a gas reinjection plant, a liquified natural gas (LNG) plant, a power plant, a refinery, and a chemical processing facility. Although rule set 280 is described in terms of being used with an industrial plant, rule set 280 may be appropriately constructed to capture any knowledge and be used for determining solutions in any field. For example, rule set 280 may contain knowledge pertaining to economic behavior, financial activity, weather phenomenon, and design processes. Rule set 280 may then be used to determine solutions to problems in these fields. Rule set 280 includes knowledge from one or many sources, such that the knowledge is transmitted to any system where rule set 280 is applied. Knowledge is captured in the form of rules that relate outputs 284 to inputs 282 such that a specification of inputs 282 and outputs 284 allows rule set 280 to be applied to LMDS 213. Rule set 280 may include only rules specific to a specific plant asset and may be directed to only one possible problem associated with that specific plant asset. For example, rule set 280 may include only rules that are applicable to a motor or a motor/pump combination. Rule set 280 may only include rules that determine a health of the motor/pump combination using vibration data. Rule set 280 may also include rules that determine the health of the motor/pump combination using a suite of diagnostic tools that include, in addition to vibration analysis techniques, but may also include, for example, performance calculational tools and/or financial calculational tools for the motor/pump combination.

In operation, rule set 280 is created in a software developmental tool that prompts a user for relationships between inputs 282 and outputs 284. Inputs 282 may receive data representing, for example digital signals, analog signals, waveforms, processed signals, manually entered and/or configuration parameters, and outputs from other rule sets. Rules within rule set 280 may include logical rules, numerical algorithms, application of waveform and signal processing techniques, expert system and artificial intelligence algorithms, statistical tools, and any other expression that may relate outputs 284 to inputs 282. Outputs 284 may be mapped to respective locations in the memory that are reserved and configured to receive each output 284. LMDS 213 and DCS 201 may then use the locations in memory to accomplish any monitoring and/or control functions LMDS 213 and DCS 201 may be programmed to perform. The rules of rule set 280 operate independently of LMDS 213 and DCS 201, although inputs 282 may be supplied to rule set 280 and outputs 284 may be supplied to rule set 280, directly or indirectly through intervening devices.

During creation of rule set 280, a human expert in the field divulges knowledge of the field particular to a specific asset using a development tool by programming one or more rules. The rules are created by generating expressions of relationship between outputs 284 and inputs 282 such that no coding of the rules is needed. Operands may be selected from a library of operands, using graphical methods, for example, using drag and drop on a graphical user interface built into the development tool. A graphical representation of an operand may be selected from a library portion of a screen display (not shown) and dragged and dropped into a rule creation portion. Relationships between input 282 and operands are arranged in a logical display fashion and the user is prompted for values, such as, constants, when appropriate based on specific operands and specific ones of inputs 282 that are selected. As many rules that are needed to capture the knowledge of the expert are created. Accordingly, rule set 280 may include a robust set of diagnostic and/or monitoring rules or a relatively less robust set of diagnostic and/or monitoring rules based on a customer's requirements and a state of the art in the particular field of rule set 280. The development tool provides resources for testing rule set 280 during the development to ensure various combinations and values of inputs 282 produce expected outputs at outputs 284.

In one embodiment, a wheel-space temperature rule set is configured to calculate an expected wheel-space temperature with respect to operating conditions of the gas turbine engine. The benefit of the wheel-space temperature rule set is a predictive and adaptable threshold that links different GT components and Compressor Performance to predict the upper and lower bounds on the expected wheel-space temperature.

FIG. 4 is a side elevation view of an architecture of a wheel-space cooling system 400 of a gas turbine engine 401 (partially shown in FIG. 1) in accordance with an exemplary embodiment of the present disclosure. A compressor 402 provides high pressure air to components of gas turbine engine 401. In the exemplary embodiment, a first wheel-space forward zone 403 is cooled only by air routed from a compressor discharge section 404. A first wheel-space aft zone 406 is cooled with air routed from compressor discharge section 404 and air bled from a compressor stage 408 upstream from compressor discharge section 404, for example, but not limited to the eleventh stage of compressor 402. Second wheel-space forward 410 and second wheel-space aft 412 are cooled by air bled from upstream compressor stage 408.

The wheel-spaces temperatures in the low pressure turbine of gas turbine engine 401 are monitored by, for example, a first thermocouple 414 and a second thermocouple 416 positioned within first wheel-space forward zone 403 and a third thermocouple 418 and a second thermocouple 420 positioned within second wheel-space aft 412. Two thermocouples for each space furnish the information on air temperature inside the cavities.

A temperature (CDT) of air routed from a compressor discharge section 404 is monitored with sensors and can be directly compared with wheel-space temperature, a temperature of upstream compressor stage 408, which cannot be measured directly is evaluated in a correlation that accounts for operating conditions of compressor.

Rules defined for gas turbine engine 401 are based on providing an expected value for the wheel-space temperature and comparing such a value with measured values. Advice provided by the rules for an anomaly are output when the measured value differs from the expected value by more than a predetermined amount that is not dependent on gas turbine engine 401. The predetermined amount is instead related to package settings, cold clearances, running clearances, and packs mounted on gas turbine engine 401, which all may affect a base value that is defined in the very first period of rules application to gas turbine engine 401.

Compressor Bleed Temperature Calculation

To link the wheel-space temperature to the evaluated upstream compressor stage 408 the following correlations are used. Such a correlation refers to the polytropic efficiency of the compressor which is assumed to be constant through the different stages and allows the evaluation of the air temperature along the compression process at each time step.

Input for such a correlation are:

- T2 Compressor inlet temperature (monitored),
- T3 Compressor outlet temperature (monitored),
- P2 Compressor inlet pressure (monitored)
- P3 Compressor outlet pressure (monitored)

The correlation outputs the bleed pressure and temperature to be compared with the second wheel-space temperature.

Extraction pressure is evaluated as a function of compressor discharge pressure (P3) as:

$\begin{matrix} P_{11} = ?, ? indicates text missing or illegible when filed & (1) \end{matrix}$

where ƒ_P11(T) is a third order polynomial function of compressor inlet temperature whose coefficients are summarized in Table 1.

The actual polytropic efficiency η_actcan be evaluated as:

$\begin{matrix} η_{act} = ? ? indicates text missing or illegible when filed & (2) \end{matrix}$

where γ(T) and ƒ(T) are expressed by third order polynomial functions defined by coefficients in table 1.

TABLE 1 Coefficients for Polynomial Expressions Function C0 C1 C2 C3 fP 11 (T) 2.22457469922934E+00 −4.63874892302590E−03 2.44926189613996E−05 −1.27947433407930E−07 γ(T) 1.40029450459100E+00 −1.87667861261292E−06 −9.09273412720000E−08 4.44183762000000E−11 f(T) −6.71976186797772E+01 3.75674097649753E+00 −4.16444150209530E−02 2.11683533804297E−04

Finally the upstream stage (stage 11, for example,) air temperature can be calculated as:

$\begin{matrix} T_{11} = T_{2} (\frac{P_{11}}{\underset{2}{P}}) ? ? indicates text missing or illegible when filed & (3) \end{matrix}$

where T₃* is evaluated as:

$\begin{matrix} T_{3}^{*} = \frac{2 T_{3} + f (T_{2})}{2} & (4) \end{matrix}$

Analysis of data for different machines indicates that a simple ΔT based correlation is not sufficiently accurate. The data indicate a large variability between the wheel-space temperature and the upstream stage (stage 11, for example,) air temperature bleed temperature.

The flow path temperature is taken into account. The only flow path temperature measurement in, for example, gas turbine engine 401 is a turbine exit temperature (T5). The temperatures of second wheel-space forward 410 and second wheel-space aft 412 were observed to be closely dependent on turbine exit temperature (T5).

Because such an effect in the correlation is useful a constant θ is introduced, which can be expressed as:

$\begin{matrix} θ = \frac{(TTWS 2 - T 11)}{(T 5 - T 11)} = const . & (5) \end{matrix}$

A value for θ is defined for each gas turbine engine and has characteristic values for the type of machine. Once the θ value is set for the forward and after side of the second wheel-space, the predicted wheel-space temperature is evaluated as:

TTWS2_fwd=T11+θ_fwd(T5−T11) (6)

for the forward side and as:

TTWS2_aft=T₁₁+θ_aft(T5−T11) (7)

for the aft side.

The rules for wheel-space temperature based on signals acquired or inferred by the system are described below, as well as the expected values and the thresholds.

A first wheel-space forward temperature is strongly related to the Compressor Discharge Temperature (T3). A simple but still reliable correlation is to set a constant temperature difference between the two. Such a difference is a characteristic of the machine even if its value can be assumed be in the range 0-60° Celsius. The standard machine has a typical base line temperature difference of approximately 40-60° Celsius while other machines may have a lower temperature difference of approximately 10-15° Celsius. Once a base line temperature difference is fixed, the wheel-space temperature is expected not to vary more than approximately ±15° Celsius.

First wheel-space aft cooling is provided from a combination of compressor discharge air and the upstream compressor stage air, for example, the 11^thstage air. Comparing both temperatures to the measured wheel-space temperature indicates a relatively large dependency on the turbine exit temperature.

In one embodiment, because both the compressor discharge air and the upstream compressor stage air flows affect the wheel-space temperature an average of the two is used for comparison:

$\begin{matrix} T_{mix} = \frac{T 11 + T 3}{2}, & (8) \end{matrix}$

where T11 is evaluated following the steps described above and T3 is the measured value of compressor discharge temperature. There is a linear dependency of (TTWS1AFT−Tmix) on (T5−Tmix). In various embodiments, other combinations of compressor discharge air and the upstream compressor stage air flows are used for the comparison. For example, each may be weighted with respect to one other or other flows may also be combined with the compressor discharge air and the upstream compressor stage air flows.

The following step is therefore to evaluate the θ ratio that can be assumed constant and used to evaluate the wheel-space temperature as:

TTWS1_aft=T_mix+θ(T5−T_mix) (9)

In other embodiments, a mass-flow average value for T_mixmay be used.

The source for cooling the forward and after second wheel-spaces is for example, the compressor 11^thstage bleed air. The temperature for the cooling air flow is evaluated from the measured values of pressure and temperature at the inlet and outlet section of the compressor according to the procedure described above.

The wheel-space temperature can be evaluated by introducing a constant, θ which allows for an accurate prediction of the wheel-space temperature.

In one case, θ constants, were determined to be θ_fwd=0.289 and θ_aft=0.345. Using such constants it is possible to predict the wheel-space temperature with an error included of approximately ±10° Celcius.

Rules for the second wheel-spaces temperature and first wheel-space aft were determined to account for turbine exit temperature and allowing for an error in a prediction lower than approximately ±15° Celsius in all cases. First wheel-space forward temperature is correlated with compressor discharge temperature without a need for other parameters to be evaluated. All rules described in above take into account expected values and machine dependent settings. Each rule definition is preceded by a period of calibration during which the characteristic parameters are set according to the monitored results.

FIG. 5 is a flow diagram of a method 500 of determining advice for an engine wheel-space temperature that exceeds a predetermined range in accordance with an exemplary embodiment of the present disclosure. In the exemplary embodiment, method 500 includes storing 502 a plurality rule sets in the memory device, the rule sets relative to the wheel-space, the rule sets including at least one rule expressed as a relational expression of a real-time data output relative to a real-time data input, the relational expression being specific to a temperature of the wheel-space, receiving 504 real-time and historical data inputs from a condition monitoring system associated with the gas turbine, the data inputs relating to sources providing heat to the wheel-space, and estimating 506 a wheel-space temperature value using the inputs relating to a temperature of the wheel-space.

The logic flows depicted in the figures do not require the particular order shown, or sequential order, to achieve desirable results. In addition, other steps may be provided, or steps may be eliminated, from the described flows, and other components may be added to, or removed from, the described systems. Accordingly, other embodiments are within the scope of the following claims.

It will be appreciated that the above embodiments that have been described in particular detail are merely example or possible embodiments, and that there are many other combinations, additions, or alternatives that may be included.

Also, the particular naming of the components, capitalization of terms, the attributes, data structures, or any other programming or structural aspect is not mandatory or significant, and the mechanisms that implement the invention or its features may have different names, formats, or protocols. Further, the system may be implemented via a combination of hardware and software, as described, or entirely in hardware elements. Also, the particular division of functionality between the various system components described herein is merely one example, and not mandatory; functions performed by a single system component may instead be performed by multiple components, and functions performed by multiple components may instead performed by a single component.

Some portions of above description present features in terms of algorithms and symbolic representations of operations on information. These algorithmic descriptions and representations may be used by those skilled in the data processing arts to most effectively convey the substance of their work to others skilled in the art. These operations, while described functionally or logically, are understood to be implemented by computer programs. Furthermore, it has also proven convenient at times, to refer to these arrangements of operations as modules or by functional names, without loss of generality.

Unless specifically stated otherwise as apparent from the above discussion, it is appreciated that throughout the description, discussions utilizing terms such as “processing” or “computing” or “calculating” or “determining” or “displaying” or “providing” or the like, refer to the action and processes of a computer system, or similar electronic computing device, that manipulates and transforms data represented as physical (electronic) quantities within the computer system memories or registers or other such information storage, transmission or display devices.

While the disclosure has been described in terms of various specific embodiments, it will be recognized that the disclosure can be practiced with modification within the spirit and scope of the claims.

The term processor, as used herein, refers to central processing units, microprocessors, microcontrollers, reduced instruction set circuits (RISC), application specific integrated circuits (ASIC), logic circuits, and any other circuit or processor capable of executing the functions described herein.

As used herein, the terms “software” and “firmware” are interchangeable, and include any computer program stored in memory for execution by processor 205, including RAM memory, ROM memory, EPROM memory, EEPROM memory, and non-volatile RAM (NVRAM) memory. The above memory types are exemplary only, and are thus not limiting as to the types of memory usable for storage of a computer program.

As will be appreciated based on the foregoing specification, the above-described embodiments of the disclosure may be implemented using computer programming or engineering techniques including computer software, firmware, hardware or any combination or subset thereof, wherein the technical effect includes (a) storing a plurality rule sets in the memory device wherein the rule sets pertain to the wheel-space and include at least one rule expressed as a relational expression of a real-time data output relative to a real-time data input wherein the relational expression is specific to a temperature of the wheel-space, (b) receiving real-time and historical data inputs from a condition monitoring system associated with the gas turbine, the data inputs relating to sources providing heat to the wheel-space, (c) estimating a wheel-space temperature value using the inputs relating to a temperature of the wheel-space, (d) comparing the estimated wheel-space temperature to an actual measured wheel-space temperature, (e) generating an advisory message using the comparison, the advisory message including troubleshooting activities relating to the wheel-space temperature, (f) receiving inputs representative of heat contained in at least one of hot gas from a combustion process of the gas turbine, bleed cooling air from an axial compressor of the gas turbine, and rotor windage effects, (g) setting an initial estimated baseline for the wheel-space temperature is equal to a temperature of the axial compressor bleed cooling air and compensated using other sources of heat to the wheel-space, (h) setting an initial estimated baseline for the wheel-space temperature is equal to a temperature of the axial compressor bleed cooling air compensated using at least one of a temperature of hot gas from the combustion process and rotor windage effects, (i) determining the estimated wheel-space temperature online using a thermodynamic simulation of the performance of the gas turbine, (j) determining the estimated wheel-space temperature online using a polytropic efficiency of the axial compressor and the axial compressor bleed cooling air temperature, (k) determining the slope of the linear relationship between the wheel-space temperature and the axial compressor bleed cooling air temperature, (l) determining the slope of the linear relationship between the temperature of the turbine exhaust and the axial compressor bleed cooling air temperature, and (m) iteratively averaging the slope over a selectable period of time. Any such resulting program, having computer-readable code means, may be embodied or provided within one or more computer-readable media, thereby making a computer program product, i.e., an article of manufacture, according to the discussed embodiments of the disclosure. The computer readable media may be, for example, but is not limited to, a fixed (hard) drive, diskette, optical disk, magnetic tape, semiconductor memory such as read-only memory (ROM), and/or any transmitting/receiving medium such as the Internet or other communication network or link. The article of manufacture containing the computer code may be made and/or used by executing the code directly from one medium, by copying the code from one medium to another medium, or by transmitting the code over a network.

Many of the functional units described in this specification have been labeled as modules, in order to more particularly emphasize their implementation independence. For example, a module may be implemented as a hardware circuit comprising custom very large scale integration (“VLSI”) circuits or gate arrays, off-the-shelf semiconductors such as logic chips, transistors, or other discrete components. A module may also be implemented in programmable hardware devices such as field programmable gate arrays (FPGAs), programmable array logic, programmable logic devices (PLDs) or the like.

Modules may also be implemented in software for execution by various types of processors. An identified module of executable code may, for instance, comprise one or more physical or logical blocks of computer instructions, which may, for instance, be organized as an object, procedure, or function. Nevertheless, the executables of an identified module need not be physically located together, but may comprise disparate instructions stored in different locations which, when joined logically together, comprise the module and achieve the stated purpose for the module.

A module of executable code may be a single instruction, or many instructions, and may even be distributed over several different code segments, among different programs, and across several memory devices. Similarly, operational data may be identified and illustrated herein within modules, and may be embodied in any suitable form and organized within any suitable type of data structure. The operational data may be collected as a single data set, or may be distributed over different locations including over different storage devices, and may exist, at least partially, merely as electronic signals on a system or network.

The above-described embodiments of a method and online wheel-space temperature monitoring system that includes a rule module provides a cost-effective and reliable means for providing meaningful operational recommendations and troubleshooting actions. Moreover, the system is more accurate and less prone to false alarms. More specifically, the methods and systems described herein can predict component failure at a much earlier stage than known systems to facilitate significantly reducing outage time and preventing trips. In addition, the above-described methods and systems facilitate predicting anomalies at an early stage enabling site personnel to prepare and plan for a shutdown of the equipment. As a result, the methods and systems described herein facilitate operating gas turbines and other equipment in a cost-effective and reliable manner.

This written description uses examples to disclose the invention, including the best mode, and also to enable any person skilled in the art to practice the invention, including making and using any devices or systems and performing any incorporated methods. The patentable scope of the disclosure is defined by the claims, and may include other examples that occur to those skilled in the art. Such other examples are intended to be within the scope of the claims if they have structural elements that do not differ from the literal language of the claims, or if they include equivalent structural elements with insubstantial differences from the literal languages of the claims.

Claims

1. A computer-implemented method for monitoring and diagnosing anomalies in a wheel-space of a gas turbine, the method implemented using a computer device coupled to a user interface and a memory device, the method comprising:

storing a plurality of rule sets in a memory device, the rule sets relative to the wheel-space, the rule sets comprising at least one rule expressed as a relational expression of a real-time data output relative to a real-time data input, the relational expression being specific to a temperature of the wheel-space;

receiving real-time and historical data inputs from a condition monitoring system associated with the gas turbine, the data inputs relating to sources providing heat to the wheel-space; and

estimating a wheel-space temperature value using the inputs relating to a temperature of the wheel-space.

2. The method of claim 1, further comprising:

comparing the estimated wheel-space temperature to an actual measured wheel-space temperature; and

generating an advisory message using the comparison, the advisory message comprising troubleshooting activities relating to the wheel-space temperature.

3. The method of claim 1, further comprising receiving inputs representative of heat contained in at least one of hot gas from a combustion process of the gas turbine, bleed cooling air from an axial compressor of the gas turbine, and rotor windage effects.

4. The method of claim 1, further comprising setting an initial estimated baseline for the wheel-space temperature is equal to a temperature of the axial compressor bleed cooling air compensated using at least one of a temperature of hot gas from the combustion process and rotor windage effects.

5. The method of claim 1, further comprising determining the estimated wheel-space temperature online using a polytropic efficiency of the axial compressor and the axial compressor bleed cooling air temperature.

6. A wheel-space monitoring and diagnostic system for a gas turbine comprising an axial compressor and a low pressure turbine in flow communication, said wheel-space monitoring and diagnostic system comprising:

a wheel-space temperature rule set, the rule set comprising a relational expression of a real-time data output relative to a real-time data input, the relational expression being specific to inputs relating to sources of heat in the wheel-space.

7. The system of claim 6, wherein said rule set is configured to determine an estimated wheel-space temperature value using the inputs relating to sources of heat in the wheel-space.

8. The system of claim 6, wherein said rule set is configured to receive inputs representative of heat contained in at least one of hot gas from the combustion process, axial compressor bleed cooling air, and rotor windage effects.

9. The system of claim 6, wherein an initial estimated baseline for the wheel-space temperature is equal to a temperature of the axial compressor bleed cooling air compensated using at least one of a temperature of hot gas from the combustion process and rotor windage effects.

10. The system of claim 6, wherein the estimated wheel-space temperature is determined online using a polytropic efficiency of the axial compressor and the axial compressor bleed cooling air temperature.