Fault diagnosis method, system and device for steam turbine generator
By fusing the shaft voltage and vibration signals of the steam turbine generator and building a fault diagnosis model using deep learning, the subjectivity and complexity of fault diagnosis in the existing technology are solved, and more accurate and real-time fault monitoring and early warning are achieved.
Patent Information
- Application Number
- CN202510166144.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-02-14
- Publication Date
- 2025-06-06
AI Technical Summary
The existing steam turbine generator fault diagnosis methods rely on a single monitoring indicator and traditional signal processing technology, which have subjectivity and operational complexity, and cannot achieve real-time monitoring and early warning, and it is especially difficult to judge hidden faults and multiple faults.
By obtaining the shaft voltage signals and vibration signals of the steam turbine generator under the defects of different bodies and excitation systems, a map is generated, and the map is fused in the feature layer to form the spliced feature vector. The deep learning neural network is used to classify the labeled feature vectors to build a steam turbine generator fault diagnosis model.
The integration of the shaft voltage and vibration information of the turbine equipment is achieved, the comprehensiveness and accuracy of fault diagnosis is improved, real-time monitoring and early warning is achieved, and the safe and stable operation level of the generator is improved.
Smart Images
Figure CN120103136A_ABST
Abstract
Description
Technical Field
[0001] The invention belongs to the technical field of nuclear power, and in particular relates to a method, system and device for diagnosing faults of a steam turbine generator. Background Art
[0002] As an important power generation equipment, steam turbine generators are widely used in various fields, including power systems, industrial production, and aerospace, because of their advantages such as high-efficiency conversion, high-power output, good stability, and strong controllability. The shaft voltage is the result of the rotating parts (rotor) of the steam turbine generator being charged. It reflects the electromagnetic conditions inside the generator. If the generator suffers from a fault or abnormality, such as insulation damage, winding grounding, or excitation system problems, it will cause abnormal shaft voltage. At the same time, the vibration signal reflects the mechanical state of the rotating parts of the generator, including the vibration of the rotor, bearings, gears, etc. When the generator fails or parts wear, it will cause abnormal changes in vibration. For example, bearing wear will lead to an increase in high-frequency vibration, and gear failure may cause impact vibration. Therefore, the shaft voltage and vibration signal can be used as a basis for diagnosing the operating status of the steam turbine generator.
[0003] At present, the diagnosis method of steam turbine generator faults mainly relies on a single monitoring indicator or traditional signal processing technology, such as the analysis of shaft voltage and vibration signals. It usually needs to rely on professional operators to make judgments and diagnoses, which has problems of subjectivity and operational complexity. At the same time, it is also impossible to achieve real-time monitoring and early warning. There are certain difficulties in judging some hidden faults or multiple faults. Summary of the invention
[0004] In order to overcome the problems existing in the related art, a method, system and device for diagnosing faults of a steam turbine generator are provided.
[0005] According to one aspect of an embodiment of the present disclosure, a method for diagnosing a fault of a steam turbine generator is provided, the method comprising:
[0006] Step 1, obtaining shaft voltage signals and vibration signals of the steam turbine generator under different body and excitation system defects, and generating shaft voltage spectra and vibration spectra of the steam turbine generator under different body and excitation system defects;
[0007] Step 2: fuse the shaft voltage spectrum and vibration spectrum of the steam turbine generator at the feature layer to form a spliced feature vector;
[0008] Step 3: Mark the equipment status under different motor body and excitation system defects in the feature vector to form a marked feature vector; and use a deep learning neural network to perform classification training on the marked feature vector to build a steam turbine generator fault diagnosis model.
[0009] In a possible implementation, in step 2, the obtained shaft voltage signal x e and vibration signal x v The multi-layer perceptron is used to extract feature vectors respectively, and then the extracted shaft voltage feature vector and vibration feature vector are weighted superimposed to obtain the concatenated feature vector y, as shown in the following formula:
[0010] y=λ 1 f(w 1 x e +b 1 )+λ 2 f(w 2 x v +b 2 )
[0011] Among them, λ 1 is the inter-modal weight of the voltage signal, λ 2 is the inter-modal weight of the vibration signal, w 1 is the modal intra-weight of the voltage signal, w 2 is the modal intra-weight of the vibration signal, b 1 is the intramodal bias of the voltage signal, b 2 is the intra-modal bias of the vibration signal, and f() is the activation function.
[0012] In a possible implementation, in step 3, the data set of steam turbine generator fault samples is expanded using data enhancement technology.
[0013] In a possible implementation, in step 3, any deep learning classification network AlexNet, VGG, GoogleNet is used to build a turbine generator fault diagnosis model.
[0014] In one possible implementation, in step 3, the optimal parameter settings of the model are set by a grid search parameter optimization method, and then the model is trained to obtain the turbine generator operating state prediction results of different models. Finally, the performance of different diagnostic models is compared through cluster analysis or AP curve, and the model with the best performance is used as the turbine generator fault diagnosis model.
[0015] According to another aspect of the embodiment of the present disclosure, there is provided a steam turbine generator fault diagnosis system, the system comprising: a voltage sensor, a vibration sensor and a control device;
[0016] The voltage sensor and the vibration sensor are respectively installed on the rotor shaft of the steam turbine generator, and the shaft voltage signal and vibration signal of the steam turbine generator under the defects of the body and the excitation system corresponding to the defect conditions are obtained under different defect conditions;
[0017] The control device is connected to the sensor through the data acquisition unit to obtain the shaft voltage signal and vibration signal of the steam turbine generator under different body and excitation system defects, and executes the method described in any one of claims 1 to 5.
[0018] According to another aspect of the present disclosure, a steam turbine generator fault diagnosis device is provided, the device comprising:
[0019] A generation module, used to obtain shaft voltage signals and vibration signals of the steam turbine generator under different defects in the body and excitation system, and to generate shaft voltage spectra and vibration spectra of the steam turbine generator under different defects in the body and excitation system;
[0020] A fusion module is used to fuse the shaft voltage spectrum and the vibration spectrum of the steam turbine generator at the feature layer to form a spliced feature vector;
[0021] A construction module is used to mark the equipment status under different motor body and excitation system defects in the feature vector to form a marked feature vector; and a deep learning neural network is used to perform classification training on the marked feature vector to build a steam turbine generator fault diagnosis model.
[0022] According to another aspect of the present disclosure, a steam turbine generator fault diagnosis device is provided, the device comprising:
[0023] processor;
[0024] a memory for storing processor-executable instructions;
[0025] Wherein, the processor is configured to execute the above method.
[0026] According to another aspect of an embodiment of the present disclosure, a non-volatile computer-readable storage medium is provided, on which computer program instructions are stored, and the computer program instructions implement the above method when executed by a processor.
[0027] The beneficial effects of the present disclosure are as follows: the steam turbine generator fault diagnosis method provided by the present disclosure can realize the integration of the shaft voltage and vibration information of the steam turbine equipment, improve the comprehensiveness and accuracy of the steam turbine equipment fault diagnosis, have important practical and economic value, can improve the safe and stable operation level of the generator, and provide more effective technical support for the operation and maintenance of the power system. BRIEF DESCRIPTION OF THE DRAWINGS
[0028] Figure 1 It is a flow chart of a method for diagnosing faults of a steam turbine generator shown in an embodiment of the present disclosure.
[0029] Figure 2 It is a schematic diagram of a steam turbine generator fault diagnosis system shown in an embodiment of the present disclosure.
[0030] Figure 3 It is a block diagram of a steam turbine generator fault diagnosis device shown in an embodiment of the present disclosure. DETAILED DESCRIPTION
[0031] The present disclosure is further described in detail below with reference to the accompanying drawings and specific embodiments.
[0032] Unless otherwise defined, the technical and scientific terms used in the present disclosure have the same meanings as those generally understood by those skilled in the art to which the present disclosure belongs; the terms used in the present disclosure are only for the purpose of describing specific embodiments and are not intended to limit the present disclosure; the term "including" and any variations thereof in the present disclosure are intended to cover non-exclusive inclusions. Obviously, the embodiments described in the present disclosure are only part of the embodiments of the present disclosure, not all of the embodiments. Based on the embodiments in the present disclosure, all other embodiments obtained by ordinary technicians in the field without making creative efforts are within the scope of protection of the present disclosure.
[0033] Reference to "embodiments" in this disclosure means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the disclosure. The appearance of the phrase in various places 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 skilled in the art that the embodiments described herein may be combined with other embodiments.
[0034] Figure 1 is a flow chart of a method for diagnosing a fault of a steam turbine generator shown in an embodiment of the present disclosure. The method can be executed by a terminal device, wherein the terminal device can be a server, a desktop computer, a laptop computer, etc. The embodiment of the present disclosure does not limit the type of the terminal device. Figure 1 As shown, the method includes:
[0035] Step 1: Acquire the shaft voltage signal and vibration signal of the steam turbine generator under different body and excitation system defects, and generate the shaft voltage spectrum and vibration spectrum of the steam turbine generator under different body and excitation system defects.
[0036] As an example of this embodiment, experimental schemes under different defect conditions can be formulated according to the defect types of the main body and excitation system to be studied. Figure 2As shown, a voltage sensor E-1 is installed on the rotor shaft 2 of the steam turbine generator, and multiple vibration sensors (for example, the first to eighth vibration sensors A-1 to A-8) are evenly installed circumferentially on the motor housing of the steam turbine generator, wherein the control device can obtain the shaft voltage signal and vibration signal of the steam turbine generator under the defects of the body and excitation system corresponding to the defect conditions under different defect conditions; the shaft voltage signal and vibration signal of the steam turbine generator under different defects of the body and excitation system are obtained by connecting the data acquisition unit to the sensor; based on the obtained shaft voltage signal and vibration signal, a voltage-time thermal curve and an acceleration-time thermal curve are formed with time as the horizontal axis and the shaft voltage / vibration data of each sensor as the vertical axis, thereby forming a shaft voltage and vibration spectrum of the steam turbine generator.
[0037] Step 2: fuse the shaft voltage spectrum and vibration spectrum of the steam turbine generator at the feature layer to form a spliced feature vector.
[0038] As an example of this embodiment, in step 2, the obtained shaft voltage signal x e and vibration signal x v The multi-layer perceptron is used to extract feature vectors respectively, and then the extracted shaft voltage feature vector and vibration feature vector are weighted superimposed to obtain the concatenated feature vector y, thereby forming a consistent description of the equipment state containing shaft voltage and vibration information, as shown in the following formula:
[0039] y=λ 1 f(w 1 x e +b 1 )+λ 2 f(w 2 x v +b 2 )
[0040] Among them, λ 1 is the inter-modal weight of the voltage signal, λ 2 is the inter-modal weight of the vibration signal, w 1 is the modal intra-weight of the voltage signal, w 2 is the modal intra-weight of the vibration signal, b 1 is the intramodal bias of the voltage signal, b 2 is the intra-modal bias of the vibration signal, and f() is the activation function.
[0041] Step 3: Mark the equipment status under different motor body and excitation system defects in the feature vector to form a marked feature vector; and use a deep learning neural network to perform classification training on the marked feature vector to build a steam turbine generator fault diagnosis model.
[0042] like Figure 2As shown, the control device also includes a shaft voltage data acquisition and processing unit 3 for acquiring shaft voltage signals, a vibration data acquisition and processing unit 4 for acquiring vibration signals, a shaft voltage / vibration data fusion unit 5 for fusing shaft voltage data and vibration data, and a fault diagnosis unit 6 for training and generating a steam turbine generator fault diagnosis model and performing fault diagnosis.
[0043] As an example of this embodiment, in step 3, a steam turbine generator fault sample data set can be constructed based on the spliced feature vector y, and the data before and after fusion should have a consistent description of the steam turbine generator state, that is, the steam turbine generator state before fusion is used to mark the steam turbine generator state after fusion. The steam turbine generator fault sample data set can be expanded using data enhancement technology. A classic deep learning classification network (AlexNet, VGG, GoogleNet, etc.) can be used to build a steam turbine generator fault diagnosis model, and the optimal parameter settings of the model can be set by a grid search parameter optimization method, and then the model is trained to obtain the prediction results of the steam turbine generator operating state of different models. Finally, the performance of different diagnostic models is compared by cluster analysis, AP curve and other methods, and on this basis, a steam turbine generator fault diagnosis method based on deep learning is proposed.
[0044] The steam turbine generator fault diagnosis method provided by the present invention can realize the integration of the shaft voltage and vibration information of the steam turbine equipment, improve the comprehensiveness and accuracy of the steam turbine equipment fault diagnosis, has important practical and economic value, can improve the safe and stable operation level of the generator, and provide more effective technical support for the operation and maintenance of the power system.
[0045] In a possible implementation, a steam turbine generator fault diagnosis device is provided, the device comprising:
[0046] A generation module, used to obtain shaft voltage signals and vibration signals of the steam turbine generator under different defects in the body and excitation system, and to generate shaft voltage spectra and vibration spectra of the steam turbine generator under different defects in the body and excitation system;
[0047] A fusion module is used to fuse the shaft voltage spectrum and the vibration spectrum of the steam turbine generator at the feature layer to form a spliced feature vector;
[0048] A construction module is used to mark the equipment status under different motor body and excitation system defects in the feature vector to form a marked feature vector; and a deep learning neural network is used to perform classification training on the marked feature vector to build a steam turbine generator fault diagnosis model.
[0049] The description of the above-mentioned device has been explained in detail in the description of the above-mentioned method, and will not be repeated here.
[0050] Figure 3 1900 is a block diagram of a steam turbine generator fault diagnosis device shown in an embodiment of the present disclosure. For example, the device 1900 can be provided as a server. Figure 3 , the apparatus 1900 includes a processing component 1922, which further includes one or more processors, and a memory resource represented by a memory 1932 for storing instructions, such as an application, that can be executed by the processing component 1922. The application stored in the memory 1932 may include one or more modules, each corresponding to a set of instructions. In addition, the processing component 1922 is configured to execute instructions to perform the above method.
[0051] The device 1900 may also include a power supply component 1926 configured to perform power management of the device 1900, a wired or wireless network interface 1950 configured to connect the device 1900 to a network, and an input / output (I / O) interface 1958. The device 1900 may operate based on an operating system stored in the memory 1932, such as Windows Server™, MacOS X™, Unix™, Linux™, FreeBSD™, or the like.
[0052] In an exemplary embodiment, a non-volatile computer-readable storage medium is also provided, such as a memory 1932 including computer program instructions, which can be executed by the processing component 1922 of the device 1900 to perform the above method.
[0053] The present disclosure may be a system, a method and / or a computer program product. The computer program product may include a computer-readable storage medium carrying computer-readable program instructions for causing a processor to implement various aspects of the present disclosure.
[0054] A computer-readable storage medium may be a tangible device that can hold and store instructions used by an instruction execution device. A computer-readable storage medium may be, for example, but not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing. More specific examples of computer-readable storage media (a non-exhaustive list) include: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a static random access memory (SRAM), a portable compact disk read-only memory (CD-ROM), a digital versatile disk (DVD), a memory stick, a floppy disk, a mechanical encoding device, such as a punch card or a raised structure in a groove on which instructions are stored, and any suitable combination of the foregoing. As used herein, a computer-readable storage medium is not to be interpreted as a transient signal per se, such as a radio wave or other freely propagating electromagnetic wave, an electromagnetic wave propagating through a waveguide or other transmission medium (e.g., a light pulse through a fiber optic cable), or an electrical signal transmitted through a wire.
[0055] The computer-readable program instructions described herein can be downloaded from a computer-readable storage medium to each computing / processing device, or downloaded to an external computer or external storage device via a network, such as the Internet, a local area network, a wide area network, and / or a wireless network. The network can include copper transmission cables, optical fiber transmissions, wireless transmissions, routers, firewalls, switches, gateway computers, and / or edge servers. The network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards the computer-readable program instructions for storage in the computer-readable storage medium in each computing / processing device.
[0056] The computer program instructions for performing the operation of the present disclosure may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-related instructions, microcode, firmware instructions, state setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages, such as Smalltalk, C++, etc., and conventional procedural programming languages, such as "C" language or similar programming languages. Computer-readable program instructions may be executed completely on a user's computer, partially on a user's computer, as an independent software package, partially on a user's computer, partially on a remote computer, or completely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., using an Internet service provider to connect via the Internet). In some embodiments, an electronic circuit, such as a programmable logic circuit, a field programmable gate array (FPGA), or a programmable logic array (PLA), may be customized by utilizing the state information of the computer-readable program instructions, and the electronic circuit may execute the computer-readable program instructions, thereby realizing various aspects of the present disclosure.
[0057] Various aspects of the present disclosure are described herein with reference to the flowcharts and / or block diagrams of the methods, devices (systems) and computer program products according to the embodiments of the present disclosure. It should be understood that each box in the flowchart and / or block diagram and the combination of each box in the flowchart and / or block diagram can be implemented by computer-readable program instructions.
[0058] These computer-readable program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, thereby producing a machine, so that when these instructions are executed by the processor of the computer or other programmable data processing device, a device that implements the functions / actions specified in one or more boxes in the flowchart and / or block diagram is generated. These computer-readable program instructions can also be stored in a computer-readable storage medium, and these instructions cause the computer, programmable data processing device, and / or other equipment to work in a specific manner, so that the computer-readable medium storing the instructions includes a manufactured product, which includes instructions for implementing various aspects of the functions / actions specified in one or more boxes in the flowchart and / or block diagram.
[0059] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device so that a series of operating steps are performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions executed on the computer, other programmable data processing apparatus, or other device to implement the functions / actions specified in one or more boxes in the flowchart and / or block diagram.
[0060] The flow chart and block diagram in the accompanying drawings show the possible architecture, function and operation of the system, method and computer program product according to multiple embodiments of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a part of a module, program segment or instruction, and a part of the module, program segment or instruction includes one or more executable instructions for realizing the specified logical function. In some alternative implementations, the function marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two continuous square boxes can actually be executed substantially in parallel, and they can sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs the specified function or action, or can be implemented with a combination of special hardware and computer instructions.
[0061] The embodiments of the present disclosure have been described above, and the above description is exemplary, not exhaustive, and is not limited to the disclosed embodiments. Many modifications and changes will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The selection of terms used herein is intended to best explain the principles of the embodiments, practical applications, or improvements to the technology in the market, or to enable other persons of ordinary skill in the art to understand the embodiments disclosed herein.
Claims
1. A method for diagnosing faults of a steam turbine generator, characterized in that: The method comprises: Step 1, obtaining shaft voltage signals and vibration signals of the steam turbine generator under different body and excitation system defects, and generating shaft voltage spectra and vibration spectra of the steam turbine generator under different body and excitation system defects; Step 2: fuse the shaft voltage spectrum and vibration spectrum of the steam turbine generator at the feature layer to form a spliced feature vector; Step 3: Mark the equipment status under different motor body and excitation system defects in the feature vector to form a marked feature vector; and use a deep learning neural network to perform classification training on the marked feature vector to build a steam turbine generator fault diagnosis model.
2. The method according to claim 1, characterized in that In step 2, the shaft voltage signal x is obtained e and vibration signal x v The multi-layer perceptron is used to extract feature vectors respectively, and then the extracted shaft voltage feature vector and vibration feature vector are weighted superimposed to obtain the concatenated feature vector y, as shown in the following formula: y=λ1f(w1x e +b1)+λ2f(w2x v +b2) Among them, λ1 is the inter-modal weight of the voltage signal, λ2 is the inter-modal weight of the vibration signal, w1 is the intra-modal weight of the voltage signal, w2 is the intra-modal weight of the vibration signal, b1 is the intra-modal bias of the voltage signal, b2 is the intra-modal bias of the vibration signal, and f() is the activation function.
3. The method according to claim 1, characterized in that In step 3, data enhancement technology is used to expand the steam turbine generator fault sample dataset.
4. The method according to claim 1, characterized in that: In step 3, any deep learning classification network AlexNet, VGG, GoogleNet is used to build a turbine generator fault diagnosis model.
5. The method according to claim 1, characterized in that: In step 3, the optimal parameter settings of the model are set through the parameter optimization method of grid search, and then the model is trained to obtain the prediction results of the steam turbine generator operation status of different models. Finally, the performance of different diagnosis models is compared through cluster analysis or AP curve, and the model with the best performance is used as the steam turbine generator fault diagnosis model.
6. A steam turbine generator fault diagnosis system, characterized in that: The system comprises: a voltage sensor, a vibration sensor and a control device; The voltage sensor and the vibration sensor are respectively installed on the rotor shaft of the steam turbine generator, and the shaft voltage signal and vibration signal of the steam turbine generator under the defects of the body and the excitation system corresponding to the defect conditions are obtained under different defect conditions; The control device is connected to the sensor through the data acquisition unit to obtain the shaft voltage signal and vibration signal of the steam turbine generator under different body and excitation system defects, and executes the method described in any one of claims 1 to 5.
7. A steam turbine generator fault diagnosis device, characterized in that: The device comprises: A generation module, used to obtain shaft voltage signals and vibration signals of the steam turbine generator under different defects in the body and excitation system, and to generate shaft voltage spectra and vibration spectra of the steam turbine generator under different defects in the body and excitation system; A fusion module is used to fuse the shaft voltage spectrum and the vibration spectrum of the steam turbine generator at the feature layer to form a spliced feature vector; A construction module is used to mark the equipment status under different motor body and excitation system defects in the feature vector to form a marked feature vector; and a deep learning neural network is used to perform classification training on the marked feature vector to build a steam turbine generator fault diagnosis model.
8. A steam turbine generator fault diagnosis device, characterized in that: The device comprises: processor; a memory for storing processor-executable instructions; The processor is configured to execute the method according to any one of claims 1 to 5.
9. A non-volatile computer-readable storage medium having computer program instructions stored thereon, characterized in that: When the computer program instructions are executed by a processor, the method according to any one of claims 1 to 5 is implemented.