Gas turbine unit equipment fault early warning method and system and medium

Abstract

The invention relates to a gas turbine unit equipment fault early warning method and system and a medium, and the method comprises the following steps: S1, data collection; step S3, data processing; step S5, data management and storage; step S7, grading the measuring points; step S9, making a feature model according to the data; step S11, calculating the health degree; step S13, performing fault early warning; the invention provides the gas turbine unit equipment fault early-warning method which only utilizes the positive sample of the operation data and has the characteristics of strong generalization ability, relatively high precision and the like, the fault early-warning model of the gas turbine is constructed without depending on the negative sample, the equipment operation abnormity can be found in the early stage of fault germination, the abnormity main cause measuring point is given, and the fault early-warning method has the advantages of high accuracy and the like. Operation and maintenance personnel are assisted to quickly position faults, the initiative of the operation and maintenance personnel is improved, and the reliability of the unit is improved.

Description

Technical Field

[0001] The present application relates to the field of gas turbines, and in particular to a method, system and medium for early warning of equipment failure of a gas turbine unit. Background Art

[0002] In the field of power generation, gas turbines have many advantages. They are important core equipment for my country's energy development, and are major power equipment that integrates many high-end design, material, manufacturing and other technologies. They are an important symbol of a country's scientific and technological level, military strength, and even comprehensive national strength. However, the strong coupling between gas turbine power generation equipment and process systems, the complexity of the system, and the particularity of the equipment working environment (high temperature, high pressure, high-speed rotation) determine that gas turbine units are a production site with a high failure rate and high failure hazards. Any downtime caused by failures will cause significant economic losses and social consequences.

[0003] Therefore, it is of great significance to ensure the safe production and efficient operation of gas turbine units, among which the fault warning system plays a vital role. However, most of the existing technologies only issue warnings after a fault occurs to prevent the accident from further expanding, and lack a means to issue warnings in the early stages of an accident. Summary of the invention

[0004] The embodiments of the present application provide a method, system and medium for early warning of a gas turbine unit equipment failure, so as to at least solve the problem in the related art of lacking a means for early warning at the early stage of an accident.

[0005] In a first aspect, an embodiment of the present application provides a method for early warning of a gas turbine unit equipment failure, characterized by comprising:

[0006] According to the pre-processed data, the measuring points are classified based on the process flow of the gas turbine equipment to obtain the measuring point classification data;

[0007] According to the measuring point classification data, a characteristic probability model is constructed, wherein the characteristic probability model is used to input the measuring point classification data and output the fault probability corresponding to the measuring point classification data;

[0008] According to the current operation stage of the gas turbine equipment, based on the failure probability corresponding to the measurement point classification data, obtaining the health value of the current state of the gas turbine equipment;

[0009] Based on the health value, the current state of the gas turbine equipment is determined, and when the equipment state is abnormal, an early warning of the current fault measurement point is issued.

[0010] In one embodiment, before performing measurement point classification based on the process flow of the combustion engine equipment according to the preprocessed data and obtaining the measurement point classification data, the method further includes:

[0011] By exchanging data with the gas turbine control system, the operating data of the gas turbine is collected.

[0012] In one embodiment, after collecting the operating condition data of the gas engine, the method further includes:

[0013] Based on the working condition data, a multi-sampling rate data preprocessor is used to search from a data set with a low sampling frequency to a data set with a higher sampling frequency, and the searched data is reorganized into data with the same resolution;

[0014] The multi-sampling rate data are converted into multi-resolution data sets with different sample sizes and different variables by sequentially increasing the lowest sampling frequency, and the multi-resolution data sets with different sample sizes and different variables are used as preprocessed data.

[0015] In one embodiment, the step of performing measurement point classification based on the preprocessed data and the process flow of the gas turbine equipment to obtain measurement point classification data includes:

[0016] According to the process technology of the gas turbine equipment, set the J-level alarm catalog, where J∈(1,+∞);

[0017] When J=1, it is the gas turbine system, steam turbine system, and waste heat boiler system;

[0018] When J=2, it is the intake system, starting system, and compressor system.

[0019] In one embodiment, constructing a feature probability model according to the measurement point classification data includes:

[0020] According to the measuring point classification data, a multivariate normal distribution algorithm is used to construct an operation characteristic probability model of the classification system.

[0021] In one embodiment, the operation characteristic probability model of the grading system is constructed based on the measurement point grading data using a multivariate normal distribution algorithm, including:

[0022] X is the historical measurement point data of the grading system, the number of data points is m, the number of samples is n, where m∈(1, +∞), n∈(3, +∞);

[0023] The Mahalanobis distance of X

[0024] The mean vector of X

[0025] The covariance matrix of X The elements in the covariance are defined as x ijis the observed value of the jth element in the i-th sample, is the average value of the observed values ​​of the jth element of all samples;

[0026] The characteristic probability model is in ∑=S.

[0027] In one embodiment, according to the current operation stage of the gas turbine equipment and based on the failure probability corresponding to the measurement point classification data, obtaining the health value of the current state of the gas turbine equipment includes:

[0028] Determine the current operation stage of the gas turbine device according to the load of the gas turbine device, the fuel amount of the gas turbine device and the speed of the gas turbine device, wherein the operation stage includes a stop stage, a start-stop stage and an operation stage;

[0029] When the unit is in the stopping stage, the health value is 100;

[0030] When the unit is in the start-up and shutdown stage, the health value = (P + A) / B, where A, B∈(500, 600);

[0031] When the unit is in the operation stage, the health value = (P + A) / B, where A, B∈(300, 400).

[0032] In one embodiment, determining the current state of the gas turbine equipment based on the health value, and issuing an early warning of the current fault measurement point when the equipment state is abnormal, includes:

[0033] When the health value is less than the health threshold F of the gas turbine equipment, F∈(0,100), it is determined that the current state of the gas turbine equipment is abnormal, and an early warning of the current fault measurement point is issued;

[0034] When the health value is greater than or equal to the health threshold F of the gas turbine equipment, F∈(0, 100), it is determined that the current state of the gas turbine equipment is a normal state.

[0035] In a second aspect, an embodiment of the present application provides a gas turbine unit equipment fault warning system, the system comprising a measurement point classification data module, a feature probability model construction module, a health value module and a gas turbine equipment status determination module, wherein:

[0036] The measuring point classification data module is used to classify the measuring points based on the preprocessed data and the process flow of the gas turbine equipment, and obtain the measuring point classification data;

[0037] A feature probability model building module is used to build a feature probability model according to the measuring point classification data, wherein the feature probability model is used to input the measuring point classification data and output the fault probability corresponding to the measuring point classification data;

[0038] A health value module, used to obtain the health value of the current state of the gas turbine equipment based on the failure probability corresponding to the measurement point classification data according to the current operation stage of the gas turbine equipment;

[0039] The combustion engine equipment state determination module is used to determine the current state of the combustion engine equipment based on the health value, and to issue an early warning of the current fault measurement point when the equipment state is abnormal.

[0040] In a third aspect, an embodiment of the present application provides a computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, a gas turbine unit equipment fault warning method as described in the first aspect above is implemented.

[0041] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements a gas turbine unit equipment fault warning method as described in the first aspect above.

[0042] A gas turbine unit equipment fault warning method, system and medium provided in the embodiments of the present application have at least the following technical effects.

[0043] The present invention provides a method for early warning of gas turbine unit equipment faults which utilizes only positive samples of operating data and has the characteristics of strong generalization ability and high precision. It realizes the construction of a fault early warning model for the gas turbine without relying on negative samples, can detect equipment operation abnormalities at the early stage of fault initiation, and provides the main cause measurement points of the abnormalities, thereby assisting operation and maintenance personnel to quickly locate faults, improve the initiative of operation and maintenance personnel, and enhance the reliability of the unit.

[0044] Details of one or more embodiments of the present application are set forth in the following drawings and description to make other features, objects, and advantages of the present application more readily apparent. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0046] Figure 1 It is a flow chart of a gas turbine unit equipment failure warning method according to an embodiment of the present application.

[0047] Figure 2 It is a block diagram of a data processing module in a gas turbine unit equipment fault early warning system provided according to the relevant technology;

[0048] Figure 3 It is a block diagram of a health calculation module in a gas turbine unit equipment fault early warning system provided according to the relevant technology;

[0049] Figure 4 is a block diagram of an electronic device according to an exemplary embodiment. DETAILED DESCRIPTION

[0050] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application is described and illustrated below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not intended to limit the present application. Based on the embodiments provided in the present application, all other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of the present application.

[0051] Obviously, the drawings described below are only some examples or embodiments of the present application. For ordinary technicians in this field, the present application can also be applied to other similar scenarios based on these drawings without creative work. In addition, it can also be understood that although the efforts made in this development process may be complicated and lengthy, for ordinary technicians in this field related to the content disclosed in this application, some changes in design, manufacturing or production based on the technical content disclosed in this application are just conventional technical means, and should not be understood as insufficient content disclosed in this application.

[0052] Reference to "embodiments" in this application means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those of ordinary skill in the art that the embodiments described in this application may be combined with other embodiments without conflict.

[0053] Unless otherwise defined, the technical terms or scientific terms involved in this application should be understood by people with ordinary skills in the technical field to which this application belongs. The words "one", "a", "a", "the" and the like involved in this application do not indicate a quantitative limitation, and may represent the singular or plural. The terms "include", "comprise", "have" and any of their variations involved in this application are intended to cover non-exclusive inclusions; for example, a process, method, system, product or device that includes a series of steps or modules (units) is not limited to the listed steps or units, but may also include steps or units that are not listed, or may also include other steps or units inherent to these processes, methods, products or devices. The words "connect", "connected", "coupled" and the like involved in this application are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. The "multiple" involved in this application refers to two or more. "And / or" describes the association relationship of associated objects, indicating that there may be three relationships, for example, "A and / or B" can represent: A exists alone, A and B exist at the same time, and B exists alone. The character " / " generally indicates that the objects before and after are in an "or" relationship. The terms "first", "second", "third", etc. involved in this application are only used to distinguish similar objects and do not represent a specific ordering of the objects.

[0054] In the prior art, a series of mechanism-based, data-driven fault warning methods have been proposed. Such methods usually calculate the residuals between the baseline value and the actual value of the equipment operation, and characterize whether the equipment has a fault by calculating the residuals. Such methods have very high requirements for the accuracy of the identification model, and the structure of the multi-output baseline value model is complex and has poor generalization ability. Another commonly used method is a classification method, but this method relies on negative samples of the data. There are often relatively few negative samples in gas turbine units, which are seriously unbalanced compared with positive samples, making classification difficult and the fault warning accuracy low.

[0055] Based on the above situation, the embodiments of the present application provide a gas turbine unit equipment fault warning method, system and medium.

[0056] Figure 1 FIG. 1 is a flow chart showing a method for early warning of a gas turbine unit equipment failure according to another exemplary embodiment. Figure 1 As shown, a gas turbine unit equipment failure early warning method provided by the present application also includes the following steps:

[0057] Step S1, data collection;

[0058] Step S101, collect various types of gas turbine operation data by interacting with the gas turbine control system, and support OPC and Modbus protocols, API interfaces and other methods to interact with the gas turbine control system. The various types of gas turbine operation data include mechanism physical data, operation management data, internal and external production environment data and other status feedback data.

[0059] Step S3, data processing, designing a multi-sampling rate data preprocessor and establishing a pyramid variational autoencoder regression model;

[0060] Step S301, the multi-sampling rate data preprocessor searches from a data set with a low sampling frequency to a data set with a higher sampling frequency, and reorganizes the searched data into data with the same resolution;

[0061] Step S302, converting the original multi-sampling rate data into multi-resolution data sets with different sample sizes and different variables by sequentially increasing the lowest sampling frequency;

[0062] Step S303: converting the original data into data of different resolutions according to different sampling rates. The data variable dimensions will change at different resolutions, thereby constructing corresponding feature extraction models based on variational autoencoders for data of different resolutions.

[0063] Step S5: data management and storage;

[0064] Step S501: standardize the data, and then effectively store and manage the data.

[0065] Step S7, measuring point classification;

[0066] S701. According to the process technology of heavy-duty gas turbine generator set, set the J-level alarm catalog, J∈(1,+∞);

[0067] S703, J=1, divided into gas turbine system, steam turbine system, and waste heat boiler system;

[0068] S705, J=2, divided into intake system, starting system and compressor system.

[0069] Step S9, making a feature model according to the data;

[0070] Step S901, extracting data from the data module after the measurement point classification function is performed;

[0071] Step S902: construct an operation characteristic model of the grading system using a multivariate normal distribution algorithm;

[0072] Step S903: Evaluate the probability density of the operating status under the current distribution in real time;

[0073] The step S902, using a multivariate normal distribution algorithm to construct an operation characteristic model of the grading system, includes the following steps:

[0074] X is the historical measurement point data of the grading system, the number of data points is m, the number of samples is n, where m∈(1, +∞), n∈(3, +∞); the Mahalanobis distance of X The mean vector of X The covariance matrix of X The elements in the covariance are defined as x ij is the observed value of the jth element in the i-th sample, is the average value of the observed values ​​of the jth element of all samples;

[0075] The characteristic probability model is in ∑=S.

[0076] Step S11, health calculation;

[0077] Step S1101, forming a method for characterizing the unit operation status through variables such as engine load, engine fuel quantity, engine speed, etc.;

[0078] Step S1102, determine the state of the unit (stop state, start-stop state, running state). When the unit is in the stop state, the health is 100; when the unit is in the start-stop state, the health = (P + A) / B, where A, B ∈ (500, 600); when the unit is in the running state, the health = (P + A) / B, where A, B ∈ (300, 400).

[0079] Step S13, fault warning;

[0080] Step S1301: According to the health status of the health system and equipment, when the health is less than F, an early warning is issued, F∈(0,100), F is the equipment health threshold, and the main cause measurement point of the fault is given.

[0081] In summary, the present invention provides a method for early warning of gas turbine unit equipment faults which utilizes only positive samples of operating data and has the characteristics of strong generalization ability and high precision. It realizes the construction of a fault early warning model for the gas turbine without relying on negative samples, can detect equipment operation abnormalities at the early stage of the fault, and give the main cause measurement points of the abnormalities, to assist operation and maintenance personnel in quickly locating faults, improve the initiative of operation and maintenance personnel, and enhance the reliability of the unit.

[0082] In a second aspect, an embodiment of the present application provides a gas turbine unit equipment failure warning system, Figure 2-Figure 3This is the system block diagram of the gas turbine unit equipment fault warning system, such as Figure 2-Figure 3 As shown, the gas turbine unit equipment failure warning system includes:

[0083] The system includes a measurement point classification data module, a feature probability model building module, a health value module and a combustion engine equipment status determination module, wherein:

[0084] The measuring point classification data module is used to classify the measuring points based on the preprocessed data and the process flow of the gas turbine equipment, and obtain the measuring point classification data;

[0085] A feature probability model building module is used to build a feature probability model according to the measuring point classification data, wherein the feature probability model is used to input the measuring point classification data and output the fault probability corresponding to the measuring point classification data;

[0086] A health value module, used to obtain the health value of the current state of the gas turbine equipment based on the failure probability corresponding to the measurement point classification data according to the current operation stage of the gas turbine equipment;

[0087] The combustion engine equipment state determination module is used to determine the current state of the combustion engine equipment based on the health value, and to issue an early warning of the current fault measurement point when the equipment state is abnormal.

[0088] In summary, the present invention provides a gas turbine unit equipment fault warning system that only uses positive samples of operating data and has the characteristics of strong generalization ability and high precision. It realizes the construction of a fault warning model for the gas turbine without relying on negative samples. It can detect equipment operation abnormalities in the early stage of fault initiation and provide the main cause measurement points of the abnormalities, assisting operation and maintenance personnel to quickly locate faults, improve the initiative of operation and maintenance personnel, and enhance the reliability of the unit.

[0089] In one embodiment, the data processing module is used for collecting, fusing, enhancing, managing and storing real-time operating data of the gas turbine control system. The module can perform real-time data interaction with the gas turbine control system;

[0090] The health calculation module calculates the operating data after the data processing module through feature extraction, calculates the health of equipment, systems and units under various working conditions, realizes the monitoring of the health status of gas turbine equipment, and timely warns;

[0091] Wherein, the data processing module also includes:

[0092] The data acquisition submodule supports data interaction with the gas turbine control system through OPC and Modbus protocols, API interfaces, etc., and collects data on the operation of various gas turbines, including mechanism physical data, operation management data, internal and external production environment data, and other status feedback data.

[0093] The multi-scale data fusion submodule converts the original multi-sampling rate data into multi-resolution data sets with different sample sizes and different variables. It designs a multi-sampling rate data preprocessor and establishes a pyramid variational autoencoder regression model to perform multi-scale data fusion.

[0094] The data management and storage submodule supports the effective storage and management of data, including data organization, indexing, query and maintenance, for subsequent data mining and analysis; standardizes data to ensure data consistency and availability, and has data quality management, security and privacy protection, access control strategies, etc.

[0095] The health calculation module also includes:

[0096] The measurement point classification submodule sets the J-level alarm catalog according to the process technology of heavy-duty gas turbine generator sets, J∈(1,+∞). J=1, divided into gas turbine, steam turbine, waste heat boiler and other systems; J=2, divided into intake system, starting system, compressor system, etc.

[0097] The feature model submodule builds the operation feature model of the hierarchical system and evaluates the probability density of the operation status under the current distribution in real time.

[0098] The health calculation submodule uses the state of the gas turbine as a variable to form a method for characterizing the unit's operating status and determine the unit's status;

[0099] The fault warning submodule uses the above calculated data as the judgment standard, issues an alarm when the data is lower than the threshold, and gives the main cause measurement point of the fault.

[0100] It should be noted that the gas turbine unit equipment fault warning system provided in this embodiment is used to implement the above-mentioned implementation mode, and the descriptions that have been made will not be repeated. As used above, the terms "module", "unit", "subunit" and the like can be a combination of software and / or hardware that implements a predetermined function. Although the device described in the above embodiment is preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0101] In a third aspect, an embodiment of the present application provides an electronic device, Figure 4 FIG. 1 is a block diagram of an electronic device according to an exemplary embodiment. Figure 4 As shown, the electronic device may include a processor 41 and a memory 42 storing computer program instructions.

[0102] Specifically, the processor 41 may include a central processing unit (CPU), or an application specific integrated circuit (ASIC), or may be configured to implement one or more integrated circuits of the embodiments of the present application.

[0103] Among them, the memory 42 may include a large-capacity memory for data or instructions. By way of example and not limitation, the memory 42 may include a hard disk drive (HDD), a floppy disk drive, a solid-state drive (SSD), a flash memory, an optical disk, a magneto-optical disk, a magnetic tape, or a universal serial bus (USB) drive, or a combination of two or more of these. Where appropriate, the memory 42 may include a removable or non-removable (or fixed) medium. Where appropriate, the memory 42 may be inside or outside the data processing device. In a specific embodiment, the memory 42 is a non-volatile memory. In a specific embodiment, the memory 42 includes a read-only memory (ROM) and a random access memory (RAM). Where appropriate, the ROM may be a mask-programmed ROM, a programmable ROM (Programmable Read-Only Memory, PROM for short), an erasable PROM (Erasable ProgrammableRead-Only Memory, EPROM for short), an electrically erasable PROM (Electrically Erasable ProgrammableRead-Only Memory, EEPROM for short), an electrically alterable ROM (Electrically Alterable Read-Only Memory, EAROM for short) or a flash memory (FLASH) or a combination of two or more of these. Under appropriate circumstances, the RAM can be a static random access memory (SRAM) or a dynamic random access memory (DRAM), wherein the DRAM can be a fast page mode dynamic random access memory (FPMDRAM), an extended data output dynamic random access memory (EDODRAM), a synchronous dynamic random access memory (SDRAM), etc.

[0104] The memory 42 may be used to store or cache various data files required for processing and / or communication, as well as possible computer program instructions executed by the processor 41 .

[0105] The processor 41 implements any one of the gas turbine unit equipment failure early warning methods in the above embodiments by reading and executing computer program instructions stored in the memory 42 .

[0106] In one embodiment, a gas turbine unit equipment failure warning device may further include a communication interface 43 and a bus 40. Figure 4 As shown, the processor 41, the memory 42, and the communication interface 43 are connected via a bus 40 and communicate with each other.

[0107] The communication interface 43 is used to implement communication between the modules, devices, units and / or equipment in the embodiment of the present application. The communication port 43 can also implement data communication with other components such as: external devices, image / data acquisition equipment, databases, external storage, and image / data processing workstations.

[0108] The bus 40 includes hardware, software or both, and couples the components of a gas turbine unit equipment fault warning device to each other. The bus 40 includes but is not limited to at least one of the following: a data bus, an address bus, a control bus, an expansion bus, and a local bus. By way of example and not limitation, bus 40 may include an Accelerated Graphics Port (AGP) or other graphics bus, an Extended Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), a HyperTransport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an InfiniBand interconnect, a Low Pin Count (LPC) bus, a memory bus, a Micro Channel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local Bus (VLB) bus, or other suitable buses or a combination of two or more of the above. Where appropriate, bus 40 may include one or more buses. Although embodiments of the present application describe and illustrate a particular bus, the present application contemplates any suitable bus or interconnect.

[0109] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium having a program stored thereon, and when the program is executed by a processor, a gas turbine unit equipment fault warning method provided in the first aspect is implemented.

[0110] The readable storage medium may include but is not limited to: a portable disk, a hard disk, a random access memory, a read-only memory, an erasable programmable read-only memory, an optical storage device, a magnetic storage device or any suitable combination of the above.

[0111] In a possible implementation, the present invention can also be implemented in the form of a program product, which includes program code. When the program product is run on a terminal device, the program code is used to enable the terminal device to execute the steps of a gas turbine unit equipment fault warning method provided in the first aspect.

[0112] Among them, the program code for executing the present invention can be written in any combination of one or more programming languages, and the program code can be executed completely on the user device, partially on the user device, as an independent software package, partially on the user device and partially on a remote device, or completely on the remote device.

[0113] The technical features of the above-described embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above-described embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0114] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the attached claims.

Claims

1. A method for early warning of gas turbine unit equipment failure, characterized in that: include: According to the pre-processed data, the measuring points are classified based on the process flow of the gas turbine equipment to obtain the measuring point classification data; According to the measuring point classification data, a characteristic probability model is constructed, wherein the characteristic probability model is used to input the measuring point classification data and output the fault probability corresponding to the measuring point classification data; According to the current operation stage of the gas turbine equipment, based on the failure probability corresponding to the measurement point classification data, obtaining the health value of the current state of the gas turbine equipment; Based on the health value, the current state of the gas turbine equipment is determined, and when the equipment state is abnormal, an early warning of the current fault measurement point is issued.

2. The method according to claim 1, characterized in that According to the current operation stage of the gas turbine equipment and based on the failure probability corresponding to the measurement point classification data, the health value of the current state of the gas turbine equipment is obtained, including: Determine the current operation stage of the gas turbine device according to the load of the gas turbine device, the fuel amount of the gas turbine device and the speed of the gas turbine device, wherein the operation stage includes a stop stage, a start-stop stage and an operation stage; When the unit is in the stopping stage, the health value is 100; When the unit is in the start-up and shutdown stage, the health value = (P + A) / B, where P represents the failure probability, A, B∈(500, 600); When the unit is in the operation stage, the health value = (P + A) / B, where P represents the failure probability, and A, B∈(300, 400).

3. The method according to claim 2, characterized in that The determining the current state of the gas turbine equipment based on the health value, and issuing an early warning of the current fault measurement point when the equipment state is abnormal, includes: When the health value is less than the health threshold F of the gas turbine equipment, F∈(0,100), it is determined that the current state of the gas turbine equipment is abnormal, and an early warning of the current fault measurement point is issued; When the health value is greater than or equal to the health threshold F of the gas turbine equipment, F∈(0, 100), it is determined that the current state of the gas turbine equipment is a normal state.

4. The method according to claim 1, characterized in that The step of constructing a feature probability model according to the measurement point classification data includes: According to the measuring point classification data, a multivariate normal distribution algorithm is used to construct an operation characteristic probability model of the classification system.

5. The method according to claim 4, characterized in that The method of constructing an operation characteristic probability model of a grading system based on the measurement point grading data using a multivariate normal distribution algorithm includes: X is the historical measurement point data of the grading system, the number of data points is m, the number of samples is n, where m∈(1, +∞), n∈(3, +∞); The Mahalanobis distance of X The mean vector of X The covariance matrix of X The elements in the covariance are defined as x ij is the observed value of the jth element in the i-th sample, is the average value of the observed values ​​of the jth element of all samples; The characteristic probability model is in ∑=S.

6. The method according to claim 1, characterized in that Before performing measurement point classification based on the process flow of the gas turbine equipment according to the preprocessed data and obtaining measurement point classification data, the method further includes: By exchanging data with the gas turbine control system, the operating data of the gas turbine is collected.

7. The method according to claim 6, characterized in that After collecting the operating condition data of the gas turbine, the method further includes: Based on the working condition data, a multi-sampling rate data preprocessor is used to search from a data set with a low sampling frequency to a data set with a higher sampling frequency, and the searched data is reorganized into data with the same resolution; The multi-sampling rate data are converted into multi-resolution data sets with different sample sizes and different variables by sequentially increasing the lowest sampling frequency, and the multi-resolution data sets with different sample sizes and different variables are used as preprocessed data.

8. The method according to claim 1, characterized in that: The method of performing measurement point classification based on the preprocessed data and the process flow of the gas turbine equipment to obtain measurement point classification data includes: According to the process technology of the gas turbine equipment, set the J-level alarm catalog, where J∈(1,+∞); When J=1, it is the gas turbine system, steam turbine system, and waste heat boiler system; When J=2, it is the intake system, starting system, and compressor system.

9. A gas turbine unit equipment failure early warning system, characterized in that: The system includes a measurement point classification data module, a feature probability model building module, a health value module and a combustion engine equipment status determination module, wherein: The measuring point classification data module is used to classify the measuring points based on the preprocessed data and the process flow of the gas turbine equipment, and obtain the measuring point classification data; A feature probability model building module is used to build a feature probability model according to the measuring point classification data, wherein the feature probability model is used to input the measuring point classification data and output the fault probability corresponding to the measuring point classification data; A health value module, used to obtain the health value of the current state of the gas turbine equipment based on the failure probability corresponding to the measurement point classification data according to the current operation stage of the gas turbine equipment; The combustion engine equipment state determination module is used to determine the current state of the combustion engine equipment based on the health value, and to issue an early warning of the current fault measurement point when the equipment state is abnormal.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, a gas turbine unit equipment failure early warning method according to any one of claims 1 to 8 is implemented.

Images