Tempering fault identification method and device, equipment, storage medium and program product

Abstract

The invention provides a tempering fault recognition method, device and equipment, a storage medium and a program product, and relates to the technical field of gas turbines. In some embodiments of the present disclosure, an original combustion chamber image of a combustion chamber within a gas turbine is acquired; performing edge detection on the original combustion chamber image to obtain a tempering area image; generating a mask image according to the tempering area image; synthesizing the mask image and the original combustion chamber image to obtain a synthesized image after image enhancement; inputting the synthesized image into a tempering fault recognition model to quickly obtain a tempering recognition result; according to the method, the edge detection technology and the neural network model are combined, the tempering fault is quickly identified based on the original combustion chamber image, the tempering fault detection efficiency is improved, and the tempering fault identification precision is improved.

Description

Technical Field

[0001] The present disclosure relates to the technical field of gas turbines, and in particular to a flashback fault identification method, apparatus, device, storage medium, and program product. Background Art

[0002] Combustion chamber flashback is a common fault during gas turbine operation. Flashback refers to the propagation of flames upstream within the combustion chamber, potentially causing equipment damage or serious safety incidents.

[0003] At present, the detection of backfire faults mainly relies on physical monitoring methods such as temperature sensors and pressure sensors. However, these methods have delayed detection results, resulting in low backfire fault detection efficiency and low backfire fault identification accuracy. Summary of the Invention

[0004] The present disclosure provides a flashback fault identification method, apparatus, device, storage medium, and program product to at least solve the problems of low flashback fault detection efficiency and low flashback fault identification accuracy in the prior art.

[0005] The technical solutions disclosed in this disclosure are as follows:

[0006] The present disclosure provides a method for identifying a flashback fault, including:

[0007] Acquire a raw combustion chamber image of a combustion chamber within a gas turbine;

[0008] Performing edge detection on the original combustion chamber image to obtain a tempering area image;

[0009] generating a mask image according to the tempering area image;

[0010] synthesizing the mask image and the original combustion chamber image to obtain a synthesized image;

[0011] The synthesized image is input into a tempering fault recognition model to obtain a tempering recognition result.

[0012] Optionally, performing edge detection on the original combustion chamber image to obtain a tempering area image includes:

[0013] Performing filtering on the original combustion chamber image to obtain a filtered combustion chamber image;

[0014] Converting the filtered combustion chamber image into an initial grayscale image;

[0015] Adjusting the resolution of the initial grayscale image from a first resolution to a second resolution to obtain a super-resolution grayscale image, wherein the second resolution is greater than the first resolution;

[0016] An edge detection algorithm is used to perform edge detection on the super-resolution grayscale image to obtain a tempering area image.

[0017] Optionally, the edge detection algorithm is a Canny edge detection algorithm, and the edge detection is performed on the super-resolution grayscale image using the edge detection algorithm to obtain the tempering area image, including:

[0018] The Canny edge detection algorithm is used to perform edge detection on the super-resolution grayscale image to obtain the tempering area image.

[0019] Optionally, generating a mask image according to the tempering area image includes:

[0020] performing binarization processing on the tempering area image to obtain a binarized image;

[0021] The resolution of the binarized image is adjusted from a second resolution to a first resolution to obtain a mask image, wherein the second resolution is greater than the first resolution.

[0022] Optionally, synthesizing the mask image and the original combustion chamber image to obtain a synthesized image includes:

[0023] Covering the area of ​​the original combustion chamber image corresponding to the mask image with the mask image to obtain a composite image;

[0024] converting the mask image into a pseudo-color thermal map, and superimposing the pseudo-color thermal map onto the original combustion chamber image according to weights to obtain the composite image; or

[0025] A tempering area is extracted from the original combustion chamber image according to the mask image; image enhancement is performed on the tempering area to obtain a tempering enhanced image; and the tempering area in the original combustion chamber image is covered with the tempering enhanced image to obtain a composite image.

[0026] Optionally, the tempering fault recognition model includes: an input layer, an encoder, a decoder, and an output layer; inputting the synthetic image into the tempering fault recognition model to obtain a tempering recognition result includes:

[0027] Within the tempering fault recognition model, inputting the synthetic image into the input layer to perform normalization processing on the synthetic image to obtain a normalized feature image;

[0028] Inputting the normalized feature image into the encoder for feature downsampling to obtain a first image feature;

[0029] Inputting the downsampled features into the decoder for feature upsampling and feature fusion to obtain second image features;

[0030] The second image feature is input into the output layer to obtain a tempering recognition result indicating whether a tempering fault exists.

[0031] The present disclosure also provides a flashback fault identification device, comprising:

[0032] an acquisition module, for acquiring an original combustion chamber image of a combustion chamber in a gas turbine;

[0033] A detection module, configured to perform edge detection on the original combustion chamber image to obtain a tempering area image;

[0034] A generating module, configured to generate a mask image according to the tempering area image;

[0035] a synthesis module, configured to synthesize the mask image and the original combustion chamber image to obtain a synthesized image;

[0036] The recognition module is used to input the synthesized image into a tempering fault recognition model to obtain a tempering recognition result.

[0037] The present disclosure also provides an electronic device, including:

[0038] processor;

[0039] a memory for storing processor-executable instructions;

[0040] The processor is configured to execute instructions to implement each step in the above method.

[0041] The embodiment of the present disclosure further provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, each step in the above method is implemented.

[0042] The embodiments of the present disclosure further provide a computer program product, including a computer program / instruction, which implements the steps in the above method when executed by a processor.

[0043] The technical solutions provided by the embodiments of the present disclosure bring at least the following beneficial effects:

[0044] In some embodiments of the present disclosure, an original combustion chamber image of a combustion chamber in a gas turbine is obtained; edge detection is performed on the original combustion chamber image to obtain a backfire area image; a mask image is generated based on the backfire area image; the mask image and the original combustion chamber image are synthesized to obtain an image-enhanced synthesized image; the synthesized image is input into a backfire fault recognition model to quickly obtain a backfire recognition result; the present disclosure combines edge detection technology and a neural network model to quickly perform backfire fault recognition based on the original combustion chamber image, thereby improving the backfire fault detection efficiency and the backfire fault recognition accuracy.

[0045] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] The accompanying drawings herein are incorporated into and constitute a part of the specification, illustrate embodiments consistent with the present disclosure, and together with the description are used to explain the principles of the present disclosure, and do not constitute an improper limitation of the present disclosure.

[0047] Figure 1 A flowchart of a method for identifying a backfire fault provided by an exemplary embodiment of the present disclosure;

[0048] Figure 2 A schematic structural diagram of a backfire fault identification device provided by an exemplary embodiment of the present disclosure;

[0049] Figure 3 A schematic structural diagram of an electronic device provided by an exemplary embodiment of the present disclosure. DETAILED DESCRIPTION

[0050] In order to enable ordinary persons in the art to better understand the technical solutions of the present disclosure, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below with reference to the accompanying drawings.

[0051] It should be noted that the terms "first," "second," and the like in the specification and claims of the present disclosure and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or precedence. It should be understood that the numbers used in this manner are interchangeable where appropriate so that the embodiments of the present disclosure described herein can be implemented in an order other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present disclosure. Instead, they are merely examples of devices and methods consistent with some aspects of the present disclosure.

[0052] It should be noted that the user information involved in this disclosure includes but is not limited to: user device information and user personal information; the collection, storage, use, processing, transmission, provision and disclosure of user information in this disclosure comply with the relevant laws and regulations and do not violate public order and good morals.

[0053] In response to the above technical problems, in some embodiments of the present disclosure, an original combustion chamber image of a combustion chamber in a gas turbine is obtained; edge detection is performed on the original combustion chamber image to obtain a backfire area image; a mask image is generated based on the backfire area image; the mask image and the original combustion chamber image are synthesized to obtain an image-enhanced synthesized image; the synthesized image is input into a backfire fault recognition model to quickly obtain a backfire recognition result; the present disclosure combines edge detection technology and a neural network model to quickly perform backfire fault recognition based on the original combustion chamber image, thereby improving the backfire fault detection efficiency and the backfire fault recognition accuracy.

[0054] The technical solutions provided by various embodiments of the present disclosure are described in detail below with reference to the accompanying drawings.

[0055] Figure 1 The following is a flow chart of a method for identifying a backfire fault provided by an exemplary embodiment of the present disclosure. Figure 1 As shown, the method includes:

[0056] S101: Acquire an original combustion chamber image of a combustion chamber in a gas turbine;

[0057] S102: performing edge detection on the original combustion chamber image to obtain a tempering area image;

[0058] S103: generating a mask image according to the tempering area image;

[0059] S104: synthesizing the mask image and the original combustion chamber image to obtain a synthesized image;

[0060] S105: Inputting the synthesized image into a tempering fault recognition model to obtain a tempering recognition result.

[0061] In this embodiment, the execution subject of the above method may be a terminal device or a server.

[0062] Among them, terminal devices include but are not limited to mobile stations (MS), mobile terminals, mobile phones, handsets, and portable equipment. The terminal devices can communicate with one or more core networks via a radio access network (RAN). For example, the terminal devices can be mobile phones (or "cellular" phones), computers with wireless communication capabilities, etc. The terminal devices can also be computers with wireless transceiver capabilities, virtual reality (VR) terminal devices, AR terminal devices, wireless terminals in industrial control, wireless terminals in self-driving, wireless terminals in remote medical care, wireless terminals in smart grids, wireless terminals in transportation safety, wireless terminals in smart cities, wireless terminals in smart homes, etc., and the operating systems installed on the terminal devices include but are not limited to: iOS, Android, Windows, Linux, Mac OS, etc. In different networks, a terminal may be called by different names, such as user equipment, mobile station, subscriber unit, station, cellular phone, personal digital assistant, wireless modem, wireless communication device, handheld device, laptop computer, cordless phone, wireless local loop station, television, etc. For the convenience of description, the terminal is referred to as terminal equipment in this embodiment.

[0063] In this embodiment, the server implementation is not limited. For example, the server can be a conventional server, a cloud server, a cloud host, a virtual center, or other server devices. The server components primarily include a processor, a hard disk, memory, a system bus, and other common computer architecture types.

[0064] In some embodiments of the present disclosure, an original combustion chamber image of a combustion chamber in a gas turbine is obtained by extracting frames from a combustion chamber monitoring video to obtain a single-frame image dataset, and any frame in the single-frame image dataset is used as the original combustion chamber image.

[0065] In some embodiments of the present disclosure, edge detection is performed on the original combustion chamber image to obtain a tempering region image. One possible implementation method is to perform edge detection on the original combustion chamber image to obtain a tempering region image. Another possible implementation method is to filter the original combustion chamber image to obtain a filtered combustion chamber image; convert the filtered combustion chamber image into an initial grayscale image; adjust the resolution of the initial grayscale image from a first resolution to a second resolution to obtain a super-resolution grayscale image, wherein the second resolution is greater than the first resolution; and perform edge detection on the super-resolution grayscale image using an edge detection algorithm to obtain a tempering region image. For example, the original combustion chamber image is subjected to non-local mean filtering to smooth noise to obtain a filtered combustion chamber image; the filtered combustion chamber image is converted into an initial grayscale image to simplify image features and preserve edge features. The resolution of the initial grayscale image is adjusted from a first resolution to a second resolution to obtain a super-resolution grayscale image, wherein the second resolution can be 2x resolution or 4x resolution to enhance image detail information.

[0066] In an optional embodiment, the edge detection algorithm is a Canny edge detection algorithm. The Canny edge detection algorithm is used to perform edge detection on the super-resolution grayscale image to obtain a tempering area image.

[0067] This paper effectively removes noise and background interference through filtering and grayscale conversion; uses super-resolution enhancement technology to enhance image details and make the tempering area clearer; and uses Canny edge detection to accurately extract the contour of the tempering area, avoiding false detection and missed detection of traditional methods.

[0068] In some embodiments of the present disclosure, a mask image is generated based on a tempered region image. One possible implementation involves binarizing the tempered region image to obtain a binarized image; then adjusting the resolution of the binarized image from a second resolution to a first resolution to obtain a mask image, where the second resolution is greater than the first resolution. After obtaining the mask image, the mask image is overlaid on the tempered region image, and the resolution is adjusted from the second resolution to the first resolution to ensure the efficiency of subsequent neural network training.

[0069] In some embodiments of the present disclosure, the mask image and the original combustion chamber image are synthesized to obtain a synthesized image. The synthesized image may be obtained by the following methods, but is not limited to:

[0070] Synthesis method 1: Cover the area of ​​the original combustion chamber image corresponding to the mask image with the mask image to obtain a synthesized image.

[0071] Synthesis method 2: Convert the mask image into a pseudo-color heat map, and then overlay the pseudo-color heat map onto the original combustion chamber image according to the weights to obtain a synthesized image. For example, convert the mask image into a pseudo-color heat map, and then overlay the pseudo-color heat map onto the original combustion chamber image according to the weights.

[0072] Synthesis method three: Extract the tempered area from the original combustion chamber image based on the mask image; perform image enhancement on the tempered area to obtain a tempered enhanced image; and overlay the tempered area in the original combustion chamber image with the tempered enhanced image to obtain a synthesized image. For example, perform brightness and contrast enhancement on the tempered area to obtain a tempered enhanced image; and overlay the tempered area in the original combustion chamber image with the tempered enhanced image to obtain a synthesized image.

[0073] The present disclosure utilizes mask covering and image synthesis technology to significantly enhance the tempered area in the original image; the generated enhanced image highlights the fault features while retaining background information, providing more intuitive input for subsequent CNN classification.

[0074] It should be noted that the flashback fault recognition model is a convolutional neural network model. Before using the flashback fault recognition model, it must be trained. The following describes the training process for the flashback fault recognition model. Sample combustion chamber images are collected and edge detection is performed on the sample combustion chamber images to obtain sample images of the flashback region. A mask sample image is generated based on the sample flashback region images. The mask sample image and the combustion chamber sample image are synthesized to obtain a synthesized sample image. A training sample set is selected from the synthesized sample image, annotated, and used to train the initial model, resulting in a trained flashback fault recognition model.

[0075] In one embodiment, the flashback fault identification model includes an input layer, an encoder, a decoder, and an output layer.

[0076] In some embodiments of the present disclosure, a composite image is input into a flashback fault recognition model to obtain a flashback recognition result. One achievable method is to input the composite image into the input layer within the flashback fault recognition model, normalize the composite image, and obtain a normalized feature image; input the normalized feature image into the encoder for feature downsampling to obtain first image features; input the downsampled features into the decoder for feature upsampling and feature fusion to obtain second image features; and input the second image features into the output layer to obtain a flashback recognition result indicating whether a flashback fault exists. The flashback fault recognition model disclosed herein improves classification accuracy and recognition rate by learning enhanced image features. This method has good adaptability under different operating conditions and effectively reduces false positives and false negatives.

[0077] The present invention has high computational efficiency and good real-time performance, and can promptly identify the tempering phenomenon at the early stage of a fault. Compared with the traditional physical sensor detection method, it has a shorter response time and improves the safety of equipment operation. The image detection method reduces the dependence on sensors and reduces the cost of equipment maintenance and replacement. The system can realize automatic fault diagnosis through remote monitoring, reducing the workload of manual inspection and maintenance.

[0078] In the above method embodiment, an original combustion chamber image of a combustion chamber in a gas turbine is obtained; edge detection is performed on the original combustion chamber image to obtain a backfire area image; a mask image is generated based on the backfire area image; the mask image and the original combustion chamber image are synthesized to obtain an image-enhanced synthesized image; the synthesized image is input into a backfire fault recognition model to quickly obtain a backfire recognition result; the present disclosure combines edge detection technology and a neural network model to quickly perform backfire fault recognition based on the original combustion chamber image, thereby improving the backfire fault detection efficiency and the backfire fault recognition accuracy.

[0079] Figure 2 FIG. 2 is a schematic structural diagram of a backfire fault identification device 20 provided by an exemplary embodiment of the present disclosure. Figure 2 As shown, the backfire fault identification device 20 includes: an acquisition module 21 , a detection module 22 , a generation module 23 , a synthesis module 24 and an identification module 25 .

[0080] The acquisition module 21 is used to acquire an original combustion chamber image of the combustion chamber in the gas turbine;

[0081] Detection module 22, used to perform edge detection on the original combustion chamber image to obtain a tempering area image;

[0082] A generating module 23 is used to generate a mask image according to the tempering area image;

[0083] A synthesis module 24 is used to synthesize the mask image and the original combustion chamber image to obtain a synthesized image;

[0084] The recognition module 25 is used to input the synthesized image into the tempering fault recognition model to obtain the tempering recognition result.

[0085] Optionally, when performing edge detection on the original combustion chamber image to obtain the tempering area image, the detection module 22 is configured to:

[0086] Performing filtering on the original combustion chamber image to obtain a filtered combustion chamber image;

[0087] Convert the filtered combustion chamber image into an initial grayscale image;

[0088] Adjusting the resolution of the initial grayscale image from a first resolution to a second resolution to obtain a super-resolution grayscale image, wherein the second resolution is greater than the first resolution;

[0089] The edge detection algorithm is used to perform edge detection on the super-resolution grayscale image to obtain the tempering area image.

[0090] Optionally, the edge detection algorithm is a Canny edge detection algorithm. When the detection module 22 uses the edge detection algorithm to perform edge detection on the super-resolution grayscale image to obtain the tempering area image, it is used to:

[0091] The Canny edge detection algorithm is used to perform edge detection on the super-resolution grayscale image to obtain the tempering area image.

[0092] Optionally, when generating the mask image according to the tempering area image, the generating module 23 is configured to:

[0093] Performing binarization processing on the tempering area image to obtain a binarized image;

[0094] The resolution of the binarized image is adjusted from the second resolution to the first resolution to obtain a mask image, wherein the second resolution is greater than the first resolution.

[0095] Optionally, when synthesizing the mask image and the original combustion chamber image to obtain a synthesized image, the synthesis module 24 is configured to:

[0096] Cover the area of ​​the original combustion chamber image corresponding to the mask image with the mask image to obtain a composite image; or

[0097] Convert the mask image into a pseudo-color thermal map, and superimpose the pseudo-color thermal map onto the original combustion chamber image according to the weight to obtain a composite image; or

[0098] A tempering area is extracted from the original combustion chamber image according to the mask image; image enhancement is performed on the tempering area to obtain a tempering enhanced image; and the tempering area in the original combustion chamber image is overlaid with the tempering enhanced image to obtain a composite image.

[0099] Optionally, the tempering fault recognition model includes an input layer, an encoder, a decoder, and an output layer. When the recognition module 25 inputs the synthesized image into the tempering fault recognition model and obtains the tempering recognition result, it is configured to:

[0100] In the tempering fault recognition model, the synthetic image is input into the input layer and normalized to obtain a normalized feature image.

[0101] Inputting the normalized feature image into the encoder for feature downsampling to obtain a first image feature;

[0102] The downsampled features are input into the decoder for feature upsampling and feature fusion to obtain the second image features;

[0103] The second image feature is input into the output layer to obtain a tempering recognition result indicating whether there is a tempering fault.

[0104] Regarding the apparatus in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0105] Figure 3 FIG. 1 is a structural diagram of an electronic device provided by an exemplary embodiment of the present disclosure. Figure 3 As shown, the electronic device includes: a memory 31 and a processor 32. In addition, the electronic device also includes a power supply component 33 and a communication component 34.

[0106] The memory 31 is used to store computer programs and can be configured to store various other data to support operations on the electronic device. Examples of such data include instructions for any application or method operating on the electronic device.

[0107] The memory 31 can be implemented by any type of volatile or non-volatile memory device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0108] The communication component 34 is used for data transmission with other devices.

[0109] The processor 32 can execute computer instructions stored in the memory 31 to: obtain an original combustion chamber image of the combustion chamber in the gas turbine; perform edge detection on the original combustion chamber image to obtain a backfire area image; generate a mask image based on the backfire area image; synthesize the mask image and the original combustion chamber image to obtain a synthesized image; and input the synthesized image into a backfire fault recognition model to obtain a backfire recognition result.

[0110] Accordingly, the embodiment of the present disclosure further provides a computer-readable storage medium storing a computer program. When the computer-readable storage medium stores the computer program and the computer program is executed by one or more processors, the one or more processors are caused to execute Figure 1 Each step in the method embodiment.

[0111] Accordingly, the present disclosure also provides a computer program product, which includes a computer program / instruction, and the computer program / instruction is executed by a processor. Figure 1 Each step in the method embodiment.

[0112] above Figure 3 The communication component is configured to facilitate wired or wireless communication between the device where the communication component is located and other devices. The device where the communication component is located can access a wireless network based on a communication standard, such as WiFi, 2G, 3G, 4G / LTE, 5G and other mobile communication networks, or a combination thereof. In an exemplary embodiment, the communication component receives a broadcast signal or broadcast-related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component also includes a near field communication (NFC) module to facilitate short-range communication. For example, the NFC module can be implemented based on radio frequency identification (RFID) technology, infrared data association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology and other technologies.

[0113] above Figure 3 The power supply component in a device provides power to various components of the device in which the power supply component is located. The power supply component may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power to the device in which the power supply component is located.

[0114] The electronic device also includes a display screen and an audio component.

[0115] The display screen includes a screen, which may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from a user. The touch panel includes one or more touch sensors to sense touches, slides, and gestures on the touch panel. The touch sensor can not only sense the boundaries of a touch or slide action, but also detect the duration and pressure associated with the touch or slide operation.

[0116] The audio component can be configured to output and / or input audio signals. For example, the audio component includes a microphone (MIC), and when the device where the audio component is located is in an operating mode, such as call mode, recording mode, and voice recognition mode, the microphone is configured to receive external audio signals. The received audio signal can be further stored in a memory or sent via a communication component. In some embodiments, the audio component also includes a speaker for outputting audio signals.

[0117] In the embodiments of the above-mentioned apparatus, device, storage medium and computer program product disclosed herein, an original combustion chamber image of a combustion chamber in a gas turbine is obtained; edge detection is performed on the original combustion chamber image to obtain a backfire area image; a mask image is generated based on the backfire area image; the mask image and the original combustion chamber image are synthesized to obtain an image-enhanced synthesized image; the synthesized image is input into a backfire fault recognition model to quickly obtain a backfire recognition result; the present disclosure combines edge detection technology and a neural network model to quickly perform backfire fault recognition based on the original combustion chamber image, thereby improving the efficiency of backfire fault detection and improving the accuracy of backfire fault recognition.

[0118] Those skilled in the art will appreciate that the embodiments of the present disclosure may be provided as methods, systems, or computer program products. Therefore, the present disclosure may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present disclosure may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0119] The present disclosure is described 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 process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0120] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0121] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0122] In a typical configuration, a computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory.

[0123] Memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. Memory is an example of a computer-readable medium.

[0124] Computer-readable media includes permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. The information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices, or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include transitory media such as modulated data signals and carrier waves.

[0125] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article, or device that includes a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or device. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, method, article, or device that includes the element.

[0126] The above are merely specific embodiments of the present disclosure, intended to enable those skilled in the art to understand and implement the present disclosure. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present disclosure. Therefore, the present disclosure is not limited to these embodiments, but is to be construed in the broadest manner consistent with the principles and novel features disclosed herein.

Claims

1. A method for identifying a tempering fault, characterized in that: include: Acquire a raw combustion chamber image of a combustion chamber within a gas turbine; Performing edge detection on the original combustion chamber image to obtain a tempering area image; generating a mask image according to the tempering area image; synthesizing the mask image and the original combustion chamber image to obtain a synthesized image; The synthesized image is input into a tempering fault recognition model to obtain a tempering recognition result.

2. The method according to claim 1, characterized in that The performing edge detection on the original combustion chamber image to obtain a tempering area image includes: Performing filtering on the original combustion chamber image to obtain a filtered combustion chamber image; Converting the filtered combustion chamber image into an initial grayscale image; Adjusting the resolution of the initial grayscale image from a first resolution to a second resolution to obtain a super-resolution grayscale image, wherein the second resolution is greater than the first resolution; An edge detection algorithm is used to perform edge detection on the super-resolution grayscale image to obtain a tempering area image.

3. The method according to claim 2, characterized in that The edge detection algorithm is a Canny edge detection algorithm. The edge detection algorithm is used to perform edge detection on the super-resolution grayscale image to obtain a tempering area image, including: The Canny edge detection algorithm is used to perform edge detection on the super-resolution grayscale image to obtain the tempering area image.

4. The method according to claim 1, wherein Generating a mask image according to the tempering area image includes: performing binarization processing on the tempering area image to obtain a binarized image; The resolution of the binarized image is adjusted from a second resolution to a first resolution to obtain a mask image, wherein the second resolution is greater than the first resolution.

5. The method according to claim 1, wherein The step of synthesizing the mask image and the original combustion chamber image to obtain a synthesized image includes: Covering the area of ​​the original combustion chamber image corresponding to the mask image with the mask image to obtain a composite image; or, converting the mask image into a pseudo-color thermal map, and superimposing the pseudo-color thermal map onto the original combustion chamber image according to weights to obtain the composite image; or A tempering area is extracted from the original combustion chamber image according to the mask image; image enhancement is performed on the tempering area to obtain a tempering enhanced image; and the tempering area in the original combustion chamber image is covered with the tempering enhanced image to obtain a composite image.

6. The method according to claim 1, characterized in that The tempering fault recognition model includes: an input layer, an encoder, a decoder, and an output layer. Inputting the synthetic image into the tempering fault recognition model to obtain a tempering recognition result includes: Within the tempering fault recognition model, inputting the synthetic image into the input layer to perform normalization processing on the synthetic image to obtain a normalized feature image; Inputting the normalized feature image into the encoder for feature downsampling to obtain a first image feature; Inputting the downsampled features into the decoder for feature upsampling and feature fusion to obtain second image features; The second image feature is input into the output layer to obtain a tempering recognition result indicating whether a tempering fault exists.

7. A tempering fault identification device, characterized in that: include: an acquisition module, for acquiring an original combustion chamber image of a combustion chamber in a gas turbine; A detection module, configured to perform edge detection on the original combustion chamber image to obtain a tempering area image; A generating module, configured to generate a mask image according to the tempering area image; a synthesis module, configured to synthesize the mask image and the original combustion chamber image to obtain a synthesized image; The recognition module is used to input the synthesized image into a tempering fault recognition model to obtain a tempering recognition result.

8. An electronic device, characterized in that: include: processor; a memory for storing processor-executable instructions; The processor is configured to execute instructions to implement each step in the method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product comprising a computer program / instructions, characterized in that When the computer program / instructions are executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images