A computer-implemented method for performing a fault analysis of one or more machinery units and an associated system

Abstract

The present disclosure provides a computer-implemented method for performing fault analysis of one or more machinery units (1). The method includes A) obtaining event data associated with an event in the one or more machinery units (M), B) identifying fault indicators from the event data, C) obtaining a logical structure (311) of the one or more machinery units (M) comprising interconnected signal nodes, D) identifying a first node (314) associated with a first detected failure signal and a root node (312), E) performing a root search process to identify a path between the root node (312) and the first node (314), F) identifying associated hardware signal nodes, and G) forming a modified path representative of a sequence of signals associated with the event. The method enables automated fault analysis by traversing the logical structure of the one or more machinery units (M) to trace the propagation of fault signals.

Description

A COMPUTER-IMPLEMENTED METHOD FOR PERFORMING A FAULT ANALYSIS OF ONE OR MORE MACHINERY UNITS AND AN ASSOCIATED SYSTEMDescriptionTECHNICAL FIELD

[0001] The present disclosure concerns a computer implemented method for performing a fault analysis of one or more machinery units. The present method is capable to rapidly diagnose failures and eventually propose actionable resolutions.

[0002] The present disclosure also concerns a fault event analyser system comprising a storage unit and a processor for performing a fault analysis of the one or more machinery units.BACKGROUND ART

[0003] Industrial and power generation systems, such as machinery unit(s), are often subject to trips, failed starts, and other unplanned outages or load reductions, each of which can significantly impact customer operations, product performance, and system availability.

[0004] The reliability of a machinery unit, such as a turbomachinery unit, can be measured using the Mean Time Between Trips (MTBT), which serves as a critical Key Performance Indicator (KPI) of the unit availability.

[0005] A trip or failed start is typically initiated as a safety function by a control system of the machinery unit, which forces at least one component of the machinery unit into a predetermined safe state to prevent damage or unsafe operating conditions. Following such an event, it is essential to quickly identify the root cause of the event to facilitate faster troubleshooting, issue resolution, and system restart.

[0006] Currently, the identification of the cause of such failures involves a manual process of reviewing alarm logs, software data, and time-series trends to reconstruct the sequence of events leading to the trip or failure. This traditional method is time-consuming, prone to human error, and often results in delays in system / unit recovery, impacting productivity and operational efficiency.

[0007] There is, therefore, a need for a near to real-time cause identification system that can automatically analyse trip events and failed starts, and may provide immediate diagnostic insights, and eventually suggest possible corrective actions to minimize downtime, enable faster recovery, and prevent recurrence.SUMMARY

[0008] Certain aspects commensurate in scope with the originally claimed disclosure are summarized below. These aspects are not intended to limit the scope of the claimed disclosure, but rather these aspects are intended only to provide a brief summary of possible forms of the disclosure. Indeed, the full disclosure may encompass a variety of forms that may be similar to or different from the aspects set forth below.

[0009] In one aspect, there is provided a computer-implemented method for performing a fault analysis of one or more machinery units, said method comprising the following steps: obtaining event data, said event data being associated to an event that has occurred in the one or more machinery units; identify from the event data one or more fault indicators, each fault indicator comprising a respective first detected failure signal; obtaining a logical structure of said the one or more machinery units, said logical structure comprising a plurality of signal nodes, each node being representative of either a hardware signal or logical signal of the one or more machinery units, each node being logically associated to at least another node of the plurality of signal nodes so as to form an interconnected tree of signal nodes; identify a plurality of signal nodes of the interconnected tree, said plurality of identified nodes comprising a first node and a root node, said first node being associated with the first detected failure signal and said root node being the highest signal node of the plurality of signal nodes of the interconnected tree; and performing a root search process of the interconnected tree to identify a path between the root node to the first node, said path traversing a sequence of the plurality of signal nodes of the interconnected tree, said path comprising at least one branch, each branch connecting a higher signal node with a lower signal node; identify one or more associated hardware signal nodes associated to said sequence of signal nodes, said identified one or more associated hardware signal nodes being representative of an input signal of the one or more machinery units; continuing said path to reach the identified one or more associated hardware signal nodes so as to form a modified path, said modified path being representative of the sequence of signals associated to said event.

[0010] In another aspect, there is provided a fault event analyser system comprising: a storage unit comprising historic database of events being configured to store one or more datasets comprising the first detected failure, the modified path and the one or more associated hardware input / output signals associated to the corresponding one or more hardware signal nodes; and at least one processor communicatively connected with the storage unit and configured to perform the above method.

[0011] In a further aspect, there is provided a plant comprising a machinery unit and the fault event analyser system.

[0012] In a still further aspect, there is provided a computer program product comprising instructions which, when the program is executed by at least one processor of the fault event analyser system, cause the at least one processor to carry out steps of the method.

[0013] In a final aspect, there is provided a computer-readable storage medium having stored thereon the above computer program product.BRIEF DESCRIPTION OF THE DRAWINGS

[0014] A more complete appreciation of the disclosed embodiments of the invention and many of the attendant advantages thereof will be readily obtained as the same becomes better understood by reference to the following detailed description when considered in connection with the accompanying drawings, wherein:FIG. 1 illustrates a schematic view of fault event analyser system, according to an embodiment of the present disclosure;FIG. 2 illustrates a block diagram of the method for performing a fault analysis of a machinery unit, according to an embodiment of the present disclosure;FIG. 3 illustrates another block diagram of the method of FIG. 2 for performing a fault analysis of a machinery unit;FIG. 4 illustrates a further block diagram of the method of FIG. 2 for performing a fault analysis and a block diagram of typical fault analysis; andFIG. 5 illustrates a logical structure of one or more machinery units, the logical structure comprises a plurality of signal nodes and a modified path.DETAILED DESCRIPTION OF EMBODIMENTS

[0015] The present disclosure concerns a fault event analyser system 1, as shown in FIG. 1, for performing a fault analysis of one or more machinery units M. This fault event analyser system 1 may help in identifying and diagnosing faults or abnormal conditions in the one or more machinery units M, potentially improving the overall reliability and efficiency of a plant.

[0016] The one or more machinery units M may be part of the plant, such as a power plant or a waste heat recovery system. The plant is equipped with the fault event analyser system 1 so as to perform the fault analysis. In some examples, the plant may include an expander forperforming a supercritical CO2 cycle. The supercritical CO2 cycle may be used in waste heat recovery applications or as part of a power generation system. However, the plant should not be limited to the specific examples mentioned here, indeed the plant may comprise any type of plant.

[0017] The one or more machinery units M may comprise a turbomachinery unit, such as a gas turbine, an expander, or any other machinery unit. The gas turbine may comprise several main components such as a compressor for compressing air from an intake, a turbine for converting thermal energy to mechanical energy, and a combustor. The compressor draws in ambient air and increases its pressure. The compressed air then enters the combustor, where fuel is injected and ignited. The resulting high-pressure gases expand through the turbine, causing it to rotate and generate power.

[0018] As shown in FIG. 1, the fault analyser system 1 includes a storage unit 21 and a processor 13. The event storage unit 21 comprises an historic database of events 212 for storing data related to detected fault events. The fault analyser system 1 may be communicatively coupled to a storage unit 12 which comprises an event log 121, which contains alarm logs generated during the event. The event log 121 may be accessed by the processor 13 during the analysis to find the first detected failure signal. The processor 13 is communicatively connected to the storage unit 21 and is configured to process information obtained from the one or more machinery units M and perform the method which will be described later with reference to FIG. 2. Data may be stored in an historic database of events 212 as dataset(s). For example, a dataset may comprise the first detected failure signal, the modified path and the one or more hardware input / output signals associated to the corresponding one or more hardware signal nodes 313 i-n.

[0019] The processor 13 may be a processor suitable for the execution of a computer program product including, by way of example, both general and special purpose microprocessor s), and / or any one or more processors of any kind of digital computer. Generally, the processor 13 will receive instructions from a read only memory (ROM), or a random-access memory (RAM), or an external / local memory or any combination thereof and execute the instruction to carry out the method described below. Data may be obtained from a memory (not shown in FIG. 1) which may be external (e.g., a remote server) or local memory of the fault analyser system 1. The instructions may be part of a program product which can be stored on a computer-readable storage medium, such as a memory or storage internal or external to the fault analyser system 1, for example, in a remote server.

[0020] The event storage unit 21 is connected to the processor 13 and is configured to store data for fault analysis. In an example, the event storage unit 21 may comprise an historic database of events 212, allowing the fault analyser system 1 to access and analyse past dataset related to fault events. The software database 31 is also connected to the processor 13 and provides a means for storing a logical structure 311 of the one or more machinery units M, which can be accessed by the processor 13. The logical structure 311 defines how different signals of the one or more machinery units M interact to achieve system objectives. In some embodiments, the storage unit 12 and the software database 31 may also be part of the fault analyser system 1.

[0021] The processor 13 may be configured to access the software database 31 and event storage unit 21 and process information from the event storage unit 21 and the software database 31, and / or store relevant information in the historic database of events 212 of the storage unit 21. The processor 13 may also be configured to access the storage unit 12 and process event data stored therein. The processor 13 may output results to a terminal T for display or further analysis, for example in a form of a report for a user / operator. The terminal T may be equipped with a display, allowing for visualization of the results. The display can provide a user interface for configuring detection parameters and viewing results.

[0022] In an example, the fault analyser system 1 may be implemented as a cloud / edge based solution. This implementation allows for distributed processing and storage of fault event data, potentially improving system responsiveness and scalability.

[0023] In an example, the fault analyser system 1 is triggered automatically when an event is detected by an analytic software, such as a software component or algorithm designed to monitor operational status of the one or more machinery units M and detect anomalies or events that may indicate a fault condition. When the analytic software detects an event, it may signal the fault analyser system 1 to initiate the fault analysis method. The automatic triggering of the fault analyser system 1 enables rapid response to potential fault conditions, allowing for timely analysis and intervention. In some examples, the fault analyser system 1 itself may be configured to monitor operational status of the one or more machinery units M and detect anomalies or events that may indicate a fault condition.

[0024] The fault analysis method may involve retrieving event data, analysing the data using the logical structure stored in the software database 31, and storing results in the historic database of events 212. The processor 13 may execute various steps which may beimplemented as software routines or algorithms that the processor 13 executes to analyse the detected event and determine its root cause or potential implications for the one or more machinery units M.

[0025] FIG. 2 illustrates a block diagram of the method for performing a fault analysis of one or more machinery units M, according to an embodiment of the present disclosure. The method may be implemented at a processor 13 of the fault analyser system 1. The method comprises the following steps: A) obtaining event data associated with an event in the one or more machinery units M; B) identifying fault indicators from the event data; C) obtaining a logical structure 311 of the one or more machinery units M comprising interconnected signal nodes; D) identifying a first node 314 associated with a first detected failure signal and a root node 312; E) performing a root search process to identify a path between the root node 312 and the first node 314; F) identifying associated hardware signal nodes; and G) forming a modified path representative of a sequence of signals associated with the event. The method enables automated fault analysis by traversing the logical structure of the one or more machinery units M to trace the propagation of fault signals.

[0026] More specifically, at step A of the method, the processor 13 obtains event data being associated to an event that has occurred in the one or more machinery units M. Step A may comprise identifying the one or more machinery units M by accessing the software database 31. Such identification may be based on corresponding machine serial number(s) retrieved from the event data. Since the software database 31 stores the logical structure 311 of the respective one or more machinery units M, this can also be selected accordingly to the corresponding machine serial number(s).

[0027] Upon obtaining the event data, at step B the processor 13 identifies one or more fault indicators from the event data. Each fault indicator comprises a respective first detected failure signal. These fault indicators serve as initial points of investigation in the fault analysis process.

[0028] At step C, the fault analyser system 1 obtains a logical structure 311 of the one or more machinery units M. The logical structure 311 comprises a plurality of signal nodes, each node being representative of either a hardware signal or logical signal of the one or more machinery units M. Each node in the logical structure 311 is logically associated with at least another node of the plurality of signal nodes, forming an interconnected tree of signal nodes. An example of the interconnected tree of signal nodes is illustrated in FIG. 5.

[0029] In an embodiment, upon detection of an event, the fault analyser system 1 is configuredto dynamically generate the logical structure 311. This real-time generation process is initiated by the processor 13 which, using the first detected failure signal associated with the first node 314 as the starting target signal, performs an automated backward traversal through the machinery unit's control logic.

[0030] The building blocks for this dynamic and automated generation are derived from the constituent logical elements present in the control system of the machinery unit (M), including logic functional blocks, interlocks, sequencing logic, and intermediate logical signals. The traversal proceeds recursively from the target signal, expanding each logical dependency to identify the antecedent signals and conditions required for its state.

[0031] Logic functional blocks may include computational elements that perform specific operations, such as Boolean operators or comparison blocks. Interlocks may refer to the critical safety and operational logic designed to enforce specific conditions. The sequencing logic defines the required order of operations and the conditions for transitioning from one state to the next. Intermediate logical signals are internal signals or flags that are not directly tied to a physical hardware input or output, serving as the result of an upstream logical calculation and as an input to a downstream calculation. The fault analyser system 1 is configured to parse these varied logical elements from the machinery unit's control system at the time of the analysis to dynamically construct the interconnected tree of signal nodes.

[0032] The recursive traversal continues until termination points are reached. These termination points may comprise, for example, control constants, such as those stored in the control constant database 104, or hardware signal nodes 313 i-nrepresenting physical hardware interfaces. This correlation effectively binds the software logic elements of the control system to physical components such as sensors, actuators, and hardware input / output channels.

[0033] The resulting logical structure 311 forms a hierarchical and causal interconnected tree of signal nodes. This tree provides a complete mapping that links the hardware signal nodes 313i-n at the lowest level, through a series of logical transformations, up to the target signal at the first node 314. As defined in the method, each node within this structure represents either a logical construct or a physical hardware signal, and each edge connecting the nodes represents a direct dependency relationship required for the evaluation of the downstream logic.

[0034] By dynamically synthesizing this structure at the time of the event directly from the machinery unit's control logic and associated hardware data, the fault analyser system 1 enables detailed, signal-level diagnostics and fault analysis without requiring any manual modelling orreliance on pre-configured, static fault logic.

[0035] Subsequently, the processor 13 of the fault analyser system 1, identifies, at step D, a plurality of signal nodes within the logical structure 311. This plurality of identified nodes includes a root node 312 and a first node 314. The root node 312 represents the highest signal node in the interconnected tree, while the first node 314 corresponds to the first detected failure signal. In other words, the root node 312 is the topmost node in the tree structure from which all other nodes descend. It serves as the starting point of the tree.

[0036] At step E, the fault analyser system 1 then performs a root search process of the interconnected tree to identify a path between the root node 312 and the first node 314. This path traverses a sequence of the plurality of signal nodes in the interconnected tree, comprising at least one branch. Each branch connects a higher signal node with a lower signal node.

[0037] As part of the fault analysis, the fault analyser system 1 identifies, at step F, one or more associated hardware signal nodes connected to the sequence of signal nodes. In the example shown in FIG. 5, these hardware signal nodes include a first hardware signal node 3131 (a63sg_a), a second hardware signal node 313? (a63sg_b) and a third hardware signal node 313s (a63sg_c). These hardware signal nodes are representative of input signals of the one or more machinery units M.

[0038] Finally, at step G, the fault analyser system 1 continues the path to reach the identified hardware signal nodes, forming a modified path. This modified path represents the sequence of signals associated with the fault event. In this way the method reconstructs the sequence of events leading to the trip or failure.

[0039] Upon completing the fault analysis, the fault analyser system 1 may outputs the sequence of signal nodes of the modified path for display on a terminal T, for example in the form of a report. This output provides a visual representation of the fault propagation path, aiding in the understanding and diagnosis of the fault event.

[0040] By traversing the logical structure 311 and identifying the relevant hardware and logical signals involved in a fault event, the fault analyser system 1 can provide a comprehensive analysis of the fault's root cause and its propagation through the one or more machinery units’ control system.

[0041] Steps A-G may be performed in response of detecting the event or at any time, in response to obtaining event data from an event log 121. The former allows for near to real time analysis.

[0042] The method may also comprise executing a correlation cycle H that may be repeated for each of the plurality of the event entries. The correlation cycle H includes the following steps: Hl) obtaining an event entry from the event log 121 storing a plurality of event entries; H2) obtaining a dataset from an historic database of events 212; and H3) determining a correlation between the first detected failure signal of the dataset and the event entry. In some embodiment the event entry may be retrieved at step A, in this case the correlation cycle H will comprise steps H2-H3.

[0043] In response of determining a correlation, the method may comprise outputting an indicator that the at least one event entry is correlated to the obtained dataset.

[0044] The method may also comprise step I in which it is performed a single point of failure determination cycle comprising the step (for each of the plurality of the event entries) of retrieving, from a hardware database 103, single point of failure data of the one or more hardware input / output signals associated to the corresponding one or more hardware signal nodes 313i-n. This step may further comprise retrieving at least one thresholds or operative limits associated to the one or more hardware input / output signals. After completing the single point of failure determination cycle the method may output the single point of failure data, for displaying on a display of a terminal T. Moreover, the single point of failure data may be stored in the historic database of events 212.

[0045] In some embodiments, the fault analyser system 1 may execute an exemplary fault analysis method as illustrated in FIG. 3.

[0046] With reference to FIG. 3, the fault analysis process begins with the monitoring of machinery unit(s) operation data. When an event is detected, the fault analyser system 1 initiates the analysis process. The analysis may comprise accessing data from one or more sources, including the software database 31, the storage unit 12, a hardware database 103, and a control constant 104.

[0047] The fault analyser system 1 uses the hardware database 103 to retrieve information about the physical components and instruments of one or more machinery units M involved in the fault. The information may comprise VO configuration defining how physical components and instruments of one or more machinery units M are connected / arranged in the control system. This may include single point of failure data of the one or more hardware input / output signals associated to the corresponding one or more hardware signal nodes 313 i-n. The control constant 104 provides reference values and operational parameters for the one or moremachinery units M including, for example, thresholds or operative limits associated to the one or more hardware input / output signals.

[0048] During the analysis, the fault analyser system 1 identify the first detected failure signal (also known as first out (FO)) and the hardware Input / Output (IO) signal related to the event. The processor 13 may check for instrument faults and performs a single point of failure determination cycle using data from the hardware database 103. This cycle helps identify critical components that may have contributed to the fault.

[0049] The fault analyser system 1 may also perform a correlation cycle H to determine correlation between the detected failure signal and historic event entries. This cycle involves retrieving data from a historic database of events or event library 212. The event library 212 contains information about similar historic events, including troubleshooting steps and possible causes for the failure mode.

[0050] As part of the analysis, the fault analyser system 1 determines if a signal exceeds threshold values during a predetermined monitoring period. If a signal exceeds a threshold value, the fault analyser system 1 generates an alarm signal. This alarm signal may indicate an instrument failure or a real failure in the one or more machinery units M.

[0051] The fault analyser system 1 uses the logical structure 311 of the one or more machinery units M throughout the analysis process. This structure helps in understanding the relationships between different signals and components, allowing the system to trace the fault propagation path from the root node 312 to the first node 314 and from the first node 314 through intermediate nodes (and / or directly) to the hardware signal nodes 3131, 313?, and 313s.

[0052] Upon completing the analysis, the fault analyser system 1 generates an event analysis report. This report may include details of the fault event, the identified cause, and potential corrective actions. The report can be displayed on a mobile device or terminal for review by operators or maintenance personnel.

[0053] The exemplary fault analysis method provides a systematic approach to fault diagnosis which helps in quickly identifying the root cause of faults and facilitating timely corrective actions.

[0054] An exemplary fault analysis method implemented by the fault analyser system 1 is illustrated by the block diagram 400 (right side) shown in FIG. 4. This method described represents an improvement over a conventional method for performing fault analysis shown in the block diagram 300 (left side), which is also depicted in FIG. 4 for comparison.

[0055] The conventional method for performing fault analysis 300 typically involves a manual process of preliminary analysis for first detected failure signal, followed by alerting the customer and eventually receiving a customer request for deeper analysis. The conventional method 300 then proceeds with detailed analysis incorporating trend, logic, and design considerations, leading to deeper analysis or service request (SR) generation. The conventional method 300 concludes with site feedback collecting and analysing input from users.

[0056] In contrast, block diagram 400 provides a first detected failure signal and Input / Output (IO) signal analysis, as described with reference to FIG. 2. The automated approach may also comprise a step in which the operator is alerted. The method may also perform an analysis utilizing the historic database of events or event library 212 to identify similar events and solutions. The fault analyser system 1 may also be configured to extract trends for IO signals and validates whether the fault represents a real failure or an instrumental failure. The fault analyser system 1 may also generate of a consolidated report with event details. This report is produced automatically by the fault analyser system 1, providing a comprehensive overview of the fault event without requiring manual intervention. The process concludes with site feedback, log validation.

[0057] The fault analyser system 1 may generate a probabilistic root cause matrix based on historic events and timeseries data and entries retrieved from the event log 121.. This matrix is created by analysing the event initiator, which may have multiple causes based on the failure mode. The fault analyser system 1 may examine historic events stored in the historic database of events or event library 212 and analyse timeseries data of related process signals from the current event. The resulting probabilistic root cause matrix may provide a probability for each potential cause and failure mode associated with the event.

[0058] Additionally, the fault analyser system 1 analyses event signatures to confirm causes and suggest troubleshooting steps. By comparing the current event signature with those of similar historic events stored in the historic database of events or event library 212, the fault analyser system 1 can identify patterns and correlations. This analysis allows the system to confirm the likely cause of the current event and propose appropriate troubleshooting measures based on successful resolutions of similar past events.

[0059] A first advantage of the present invention is that it enables fault analysis for any type of system including one or more machinery units M. In particular the method enables automated fault analysis by traversing the logical structure of the one or more machinery unitsM to trace the propagation of fault signals. The analysis may be performed near to real time or at a later stage based on event data from an historic database of events 212.

[0060] Another advantage of the present invention is that it provides fault analysis method capable of distinguishing between real failure and instrumental failures, such as failures which occurs when a measuring or monitoring device (sensor, gauge, or software) provides incorrect or misleading data, even though the actual system is working properly. This allows for more reliable monitoring and accurate monitoring.

[0061] Another advantage of the present invention is that it enables identification and diagnosis of faults or abnormal conditions in the one or more machinery units M, potentially improving the overall reliability and efficiency of a plant.

[0062] A further advantage of the present invention is that enables rapid response to potential fault conditions, allowing for timely analysis and intervention. Furthermore, the present invention reduces the time required for experts to analyse events and identify causes, enhancing overall system efficiency and responsiveness.

[0063] While aspects of the invention have been described in terms of various specific embodiments, it will be apparent to those of ordinary skill in the art that many modifications, changes, and omissions are possible without departing form the spirit and scope of the claims. In addition, unless specified otherwise herein, the order or sequence of any process or method steps may be varied or re-sequenced according to alternative embodiments.

[0064] The subject matter described herein can be implemented in digital electronic circuitry, or in computer software, firmware, or hardware, including the structural means disclosed in this specification and structural equivalents thereof, or in combinations of them. The subject matter described herein can be implemented as one or more computer program products, such as one or more computer programs tangibly embodied in an information carrier (e.g., in a machine-readable storage device), or embodied in a propagated signal, for execution by, or to control the operation of, data processing apparatus (e.g., a programmable processor, a computer, or multiple computers). A computer program (also known as a program, software, software application, or code) can be written in any form of programming language, including compiled or interpreted languages, and it can be deployed in any form, including as a standalone program or as a module, component, subroutine, or other unit suitable for use in a computing environment. A computer program does not necessarily correspond to a file. A program can be stored in a portion of a file that holds other programs or data, in a single filededicated to the program in question, or in multiple coordinated files (e.g., files that store one or more modules, sub programs, or portions of code). A computer program can be deployed to be executed on one computer or on multiple computers at one site or distributed across multiple sites and interconnected by a communication network.

[0065] The processes and logic flows described in this specification, including the method steps of the subject matter described herein, can be performed by one or more programmable processors executing one or more computer programs to perform functions of the subject matter described herein by operating on input data and generating output. The processes and logic flows can also be performed by, and apparatus of the subject matter described herein can be implemented as, special purpose logic circuitry, e.g., an FPGA (field programmable gate array) or an ASIC (application specific integrated circuit).

[0066] Processors suitable for the execution of a computer program include, by way of example, both general and special purpose microprocessors, and any one or more processor of any kind of digital computer. Generally, a processor will receive instructions and data from a read only memory or a random-access memory or both. The essential elements of a computer are a processor for executing instructions and one or more memory devices for storing instructions and data. Generally, a computer will also include, or be operatively coupled to receive data from or transfer data to, or both, one or more mass storage devices for storing data, e.g., magnetic, magneto optical disks, or optical disks. Information carriers suitable for embodying computer program instructions and data include all forms of non-volatile memory, including by way of example semiconductor memory devices, (e.g., EPROM, EEPROM, and flash memory devices); magnetic disks, (e.g., internal hard disks or removable disks); magneto optical disks; and optical disks (e.g., CD and DVD disks). The processor and the memory can be supplemented by, or incorporated in, special purpose logic circuitry.

[0067] To provide for interaction with a user, the subject matter described herein can be implemented on a computer having a display device, e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor, for displaying information to the user and a keyboard and a pointing device, (e.g., a mouse or a trackball), by which the user can provide input to the computer. Other kinds of devices can be used to provide for interaction with a user as well. For example, feedback provided to the user can be any form of sensory feedback, (e.g., visual feedback, auditory feedback, or tactile feedback), and input from the user can be received in any form, including acoustic, speech, or tactile input.

[0068] The techniques described herein can be implemented using one or more modules. As used herein, the term “module” refers to computing software, firmware, hardware, and / or various combinations thereof. At a minimum, however, modules are not to be interpreted as software that is not implemented on hardware, firmware, or recorded on a non-transitory processor readable recordable storage medium (i.e., modules are not software per se). Indeed “module” is to be interpreted to always include at least some physical, non-transitory hardware such as a part of a processor or computer. Two different modules can share the same physical hardware (e.g., two different modules can use the same processor and network interface). The modules described herein can be combined, integrated, separated, and / or duplicated to support various applications. Also, a function described herein as being performed at a particular module can be performed at one or more other modules and / or by one or more other devices instead of or in addition to the function performed at the particular module. Further, the modules can be implemented across multiple devices and / or other components local or remote to one another. Additionally, the modules can be moved from one device and added to another device, and / or can be included in both devices.

[0069] The subject matter described herein can be implemented in a computing system that includes a back end component (e.g., a data server), a middleware component (e.g., an application server), or a front end component (e.g., a client computer having a graphical user interface or a web browser through which a user can interact with an implementation of the subject matter described herein), or any combination of such back end, middleware, and front end components. The components of the system can be interconnected by any form or medium of digital data communication, e.g., a communication network. Examples of communication networks include a local area network (“LAN”) and a wide area network (“WAN”), e.g., the Internet.

[0070] Reference has been made in detail to the embodiments of the disclosure, one or more examples of which are illustrated in the drawings. Each example is provided by way of explanation of the disclosure, not 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 present disclosure without departing from the scope or spirit of the disclosure. Reference throughout the specification to "one embodiment" or "an embodiment" or “some embodiments” means that the particular feature, structure or characteristic described in connection with an embodiment is included in at least one embodiment of the subject matter disclosed. Thus, the appearance of the phrase "in one embodiment" or "in an embodiment" or "in some embodiments" in variousplaces throughout the specification is not necessarily referring to the same embodiment(s). Further, the particular features, structures or characteristics may be combined in any suitable manner in one or more embodiments.

[0071] When elements of various embodiments are introduced, the articles “a”, “an”, “the”, and “said” are intended to mean that there are one or more of the elements. The terms “comprising”, “including”, and “having” are intended to be inclusive and mean that there may be additional elements other than the listed elements.

Claims

CLAIMS1. A computer-implemented method for performing a fault analysis of one or more machinery units (M), said method comprising the following steps:A) obtaining event data, said event data being associated to an event that has occurred in the one or more machinery units (M);B) identify from the event data one or more fault indicators, each fault indicator comprising a respective first detected failure signal;C) obtaining a logical structure (311) of said the one or more machinery units (M), said logical structure comprising a plurality of signal nodes, each node being representative of either a hardware signal or logical signal of the one or more machinery units (M), each node being logically associated to at least another node of the plurality of signal nodes so as to form an interconnected tree of signal nodes;D) identify a plurality of signal nodes of the interconnected tree, said plurality of identified nodes comprising a first node (314) and a root node (312), said first node (314) being associated with the first detected failure signal and said root node (312) being the highest signal node of the plurality of signal nodes of the interconnected tree; andE) performing a root search process of the interconnected tree to identify a path between the root node (312) to the first node (314), said path traversing a sequence of the plurality of signal nodes of the interconnected tree, said path comprising at least one branch, each branch connecting a higher signal node with a lower signal node;F) identify one or more associated hardware signal nodes associated to said sequence of signal nodes, said identified one or more associated hardware signal nodes (313i-n) being representative of an input signal of the one or more machinery units (M); andG) continuing said path to reach the identified one or more associated hardware signal nodes (313i-n) so as to form a modified path, said modified path being representative of the sequence of signals associated to said event.

2. The method of claim 1, further comprising: performing step A-G in response of detecting the event.

3. The method of claim 1, wherein the event data comprises a plurality of event entries stored in an event log (121).

4. The method of any one of the preceding claims, further comprising outputting the sequence of the plurality of signal nodes of the modified path, for displaying on a display of a terminal (T).

5. The method of any one of the preceding claims, further comprising:I) transmitting a dataset for storage on a historic database of events (212), said dataset comprising the first detected failure signal, the modified path and the one or more hardware input / output signals associated to the corresponding one or more hardware signal nodes (313i-n).

6. The method of claims 3 and 5, further comprising:H) performing a correlation cycle, said correlation cycle including:Hl) obtaining an event entry from the event log (121);H2) obtaining a dataset from the historic database of events (212); andH3) determining a correlation between said first detected failure signal of the dataset and said event entry.

7. The method of the preceding claim, wherein step H further comprises:in response of determining a correlation, outputting an indicator that the at least one event entry is correlated to the obtained dataset.

8. The method of claim 6 or 7, further comprising:repeating the correlation cycle H for each of the plurality of the event entries.

9. The method of any one of claims 6-8, wherein said event entry comprises one or more corresponding corrective actions, and wherein step H further comprises:in response of determining a correlation, outputting the one or more corresponding corrective actions.

10. The method of any one of claims 6-9, further comprisingI) performing a single point of failure determination cycle comprising the following steps, for each of the plurality of the event entries:retrieving, from a hardware database (103), single point of failure data of the one or more hardware input / output signals associated to the corresponding one or more hardware signal nodes (313i-n).

11. The method of the preceding claim, wherein retrieving single point of failure data comprises retrieving at least one thresholds or operative limits associated to said one or more hardware input / output signals.

12. The method of claim 10 or 11, further comprising outputting the single point of failure data, for displaying on a display of a terminal (T).

13. The method of any one of claims 10-12, further comprising storing the single point of failure data.

14. The method of claim 11, further comprising:determining whether the signal exceeds the threshold values during the predetermined monitoring period; andgenerating an alarm signal if the signal exceeds the threshold value, said alarm signal being indicative that an instrument failure is determined.

15. The method of any one of the preceding claims, wherein said one or more associated hardware signal nodes comprise descendant nodes that can be reached by traversing the modified path in a downward direction starting from the first node, said descendant nodes being directly connectable to the sequence of signal nodes or being connectable to the sequence of signal nodes through intermediate nodes.

16. The method of claim 1, wherein the step of obtaining a logical structure (C) comprises dynamically generating said logical structure upon detection of the event by:performing an automated backward traversal through the machinery unit's control logic, said traversal initiating from the first detected failure signal; andrecursively expanding each logical dependency of said traversal until one or more termination points are reached, said termination points comprising at least one of a control constant or one of the hardware signal nodes.

17. A fault event analyser system (1) comprising:a storage unit (21) comprising an historic database of events (212) being configured to store one or more datasets comprising the first detected failure, the modified path and the one or more associated hardware input / output signals associated to the corresponding one or more hardware signal nodes (313 i-n); andat least one processor (13) communicatively connected with said storage unit (21) and-18-configured to perform the method of any one of the preceding claims.

18. A plant comprising a machinery unit and a fault event analyser system of the preceding claim.

19. The plant of the preceding claim, wherein the machinery unit comprises a turbomachinery unit.

20. The plant of the preceding claim, wherein the turbomachinery unit is a gas turbine comprising:a compressor, for compressing air from an intake;a turbine, to convert thermal energy to mechanical energy; anda combustor.

21. The plant of claim 19, wherein the plant comprises a power plant or a waste heat recovery system, and wherein the machinery unit comprises an expander for performing a supercritical CO2 cycle.

22. A computer program product comprising instructions which, when the program is executed by at least one processor (13) of the fault event analyser system (1), cause the at least one processor (13) to carry out steps of the method of any one of claims 1-16.

23. A computer-readable storage medium having stored thereon the computer program product of claim 22.-19-

Images