Training method and device of power plant equipment fault diagnosis model, electronic equipment and storage medium

By constructing the operation data diagram of the power plant equipment failure and training the neural network model, the problem of low fault diagnosis accuracy in the existing technology is solved, and high accuracy recognition of power plant equipment failure is achieved.

CN118940040APending Publication Date: 2024-11-12润电能源科学技术有限公司
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411062084.1
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-05
Publication Date
2024-11-12

AI Technical Summary

Technical Problem

The accuracy of existing power plant equipment fault diagnosis methods is low, making it difficult to effectively identify equipment faults.

Method used

By obtaining the fault operation data of power plant equipment, a fault operation data diagram is constructed, and a training data set is constructed based on this diagram, the initial neural network model is trained, a fault diagnosis model is generated, and the real-time data is diagnosed using this model.

Benefits of technology

It improves the accuracy of fault diagnosis of power plant equipment, and can accurately extract the changing characteristics between fault operation data and the changing characteristics on the time scale, thereby improving the accuracy of fault identification.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118940040A_ABST
    Figure CN118940040A_ABST
Patent Text Reader

Abstract

The invention discloses a training method and device of a power plant equipment fault diagnosis model, electronic equipment and a storage medium. The method comprises the following steps: acquiring fault operation data of power plant equipment at a plurality of moments; performing graph construction operation in response to the fault operation data of the power plant equipment at the multiple moments to obtain a fault operation data graph of the power plant equipment; constructing and obtaining a power plant equipment fault diagnosis model training data set based on the fault operation data graph of the power plant equipment; and training an initial neural network model based on the training data set of the power plant equipment fault diagnosis model to obtain a trained power plant equipment fault diagnosis model. According to the technical scheme, through the graph construction operation, the model can accurately extract the change characteristics between the fault operation data and the change characteristics on the time scale at the same time, so that the fault recognition accuracy of the power plant equipment fault diagnosis model is improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of fault diagnosis, and in particular to a training method, device, electronic equipment and storage medium for a power plant equipment fault diagnosis model. Background Art

[0002] Existing power plant equipment fault diagnosis methods usually require experts to predict equipment failures based on equipment operating data.

[0003] In the process of implementing the present invention, it is found that there are at least the following technical problems in the prior art: the prior art solution has the problem of low fault diagnosis accuracy. Summary of the invention

[0004] The present invention provides a training method, device, electronic equipment and storage medium for a power plant equipment fault diagnosis model to improve the fault diagnosis accuracy of the power plant equipment.

[0005] According to one aspect of the present invention, a method for training a power plant equipment fault diagnosis model is provided, comprising:

[0006] Acquire fault operation data of power plant equipment at multiple moments, wherein the fault operation data of power plant equipment includes inlet working fluid parameters of power plant equipment, outlet working fluid parameters of power plant equipment and control operation parameters of power plant equipment;

[0007] In response to performing a graph construction operation on the fault operation data of the power plant equipment at the multiple moments, a fault operation data graph of the power plant equipment is obtained, wherein the fault operation data graph of the power plant equipment comprises a plurality of columns of data, each column represents the fault operation data of the power plant equipment at the same moment, and the order of the inlet working fluid parameter of the power plant equipment, the control operation parameter of the power plant equipment and the outlet working fluid parameter of the power plant equipment in each column of data is arranged in sequence from top to bottom;

[0008] A training data set of a power plant equipment fault diagnosis model is obtained based on the fault operation data graph of the power plant equipment;

[0009] The initial neural network model is trained based on the power plant equipment fault diagnosis model training data set to obtain a trained power plant equipment fault diagnosis model.

[0010] According to another aspect of the present invention, there is provided a method for diagnosing faults of power plant equipment, comprising:

[0011] Obtain real-time fault operation data of power plant equipment;

[0012] In response to performing a graph construction operation on the real-time fault operation data of the power plant equipment, a real-time fault operation data graph of the power plant equipment is obtained;

[0013] The real-time fault operation data graph of the power plant equipment is input into a pre-trained power plant equipment fault diagnosis model to obtain a fault diagnosis result, wherein the power plant equipment fault diagnosis model is trained based on the training method of the power plant equipment fault diagnosis model described in any one of the embodiments of the present invention.

[0014] According to another aspect of the present invention, there is provided a training device for a power plant equipment fault diagnosis model, comprising:

[0015] A fault operation data acquisition module for power plant equipment, used to acquire fault operation data of power plant equipment, wherein the fault operation data of power plant equipment includes inlet working fluid parameters of power plant equipment, outlet working fluid parameters of power plant equipment and control operation parameters of power plant equipment;

[0016] A fault operation data graph construction module for power plant equipment, configured to obtain a fault operation data graph of the power plant equipment in response to a graph construction operation on the fault operation data of the power plant equipment, wherein the fault operation data graph of the power plant equipment comprises a plurality of columns of data, each column representing the fault operation data of the power plant equipment at the same time, and the order of the inlet working fluid parameters of the power plant equipment, the control operation parameters of the power plant equipment and the outlet working fluid parameters of the power plant equipment in each column of data is arranged from top to bottom;

[0017] A power plant equipment fault diagnosis model training data set construction module, used to construct a power plant equipment fault diagnosis model training data set based on the fault operation data graph of the power plant equipment;

[0018] The power plant equipment fault diagnosis model training module is used to train the initial neural network model based on the power plant equipment fault diagnosis model training data set to obtain a trained power plant equipment fault diagnosis model.

[0019] According to another aspect of the present invention, there is provided a method for diagnosing faults of power plant equipment, comprising:

[0020] A real-time fault operation data acquisition module is used to acquire real-time fault operation data of power plant equipment;

[0021] A real-time fault operation data graph construction module, configured to obtain a real-time fault operation data graph of the power plant equipment in response to performing a graph construction operation on the real-time fault operation data of the power plant equipment;

[0022] A fault diagnosis result prediction module is used to input the real-time fault operation data graph of the power plant equipment into a pre-trained power plant equipment fault diagnosis model to obtain a fault diagnosis result, wherein the power plant equipment fault diagnosis model is trained based on the training method of the power plant equipment fault diagnosis model described in any one of the embodiments of the present invention.

[0023] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0024] at least one processor;

[0025] and a memory communicatively coupled to the at least one processor;

[0026] Wherein, the memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the training method of the power plant equipment fault diagnosis model described in any embodiment of the present invention.

[0027] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to implement the training method of the power plant equipment fault diagnosis model described in any embodiment of the present invention when executed by a processor.

[0028] The technical solution of the embodiment of the present invention is to obtain the fault operation data of the power plant equipment at multiple moments, wherein the fault operation data of the power plant equipment includes the inlet working fluid parameters of the power plant equipment, the outlet working fluid parameters of the power plant equipment and the control operation parameters of the power plant equipment; in response to the graph construction operation of the fault operation data of the power plant equipment at multiple moments, obtain the fault operation data graph of the power plant equipment, wherein the fault operation data graph of the power plant equipment includes multiple columns of data, each column represents the fault operation data of the power plant equipment at the same moment, and the order of the inlet working fluid parameters of the power plant equipment, the control operation parameters of the power plant equipment and the outlet working fluid parameters of the power plant equipment in each column of data is arranged from top to bottom; obtain the training data set of the fault diagnosis model of the power plant equipment based on the fault operation data graph of the power plant equipment; train the initial neural network model based on the training data set of the fault diagnosis model of the power plant equipment to obtain the trained fault diagnosis model of the power plant equipment. The above technical solution, through the graph construction operation, can enable the model to accurately extract the change characteristics between the fault operation data and the change characteristics on the time scale at the same time, thereby improving the fault recognition accuracy of the fault diagnosis model of the power plant equipment.

[0029] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0031] Figure 1 is a flow chart of a method for training a power plant equipment fault diagnosis model according to Embodiment 1 of the present invention;

[0032] Figure 2 is a flow chart of a method for training a power plant equipment fault diagnosis model according to Embodiment 2 of the present invention;

[0033] Figure 3 is a flow chart of a method for training a power plant equipment fault diagnosis model according to Embodiment 3 of the present invention;

[0034] Figure 4 is a flow chart of a method for diagnosing power plant equipment faults according to a fourth embodiment of the present invention;

[0035] Figure 5 It is a structural schematic diagram of a training device for a power plant equipment fault diagnosis model provided in accordance with a fifth embodiment of the present invention;

[0036] Figure 6 is a structural schematic diagram of a power plant equipment fault diagnosis device provided according to Embodiment 6 of the present invention;

[0037] Figure 7 It is a structural schematic diagram of an electronic device for implementing the training method of the power plant equipment fault diagnosis model according to an embodiment of the present invention. DETAILED DESCRIPTION

[0038] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0039] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices. The acquisition, storage, use, processing, etc. of data in the technical solution of this application comply with the relevant provisions of national laws and regulations.

[0040] Embodiment 1

[0041] Figure 1 This is a flowchart of a method for training a power plant equipment fault diagnosis model provided in the first embodiment of the present invention. This embodiment is applicable to the case of fault diagnosis of power plant equipment. The method can be executed by a training device for a power plant equipment fault diagnosis model. The training device for a power plant equipment fault diagnosis model can be implemented in the form of hardware and / or software. The training device for a power plant equipment fault diagnosis model can be configured in a terminal and / or a server. Figure 1 As shown, the method includes:

[0042] S110. Acquire fault operation data of power plant equipment at multiple moments, wherein the fault operation data of power plant equipment includes inlet working fluid parameters of power plant equipment, outlet working fluid parameters of power plant equipment and control operation parameters of power plant equipment.

[0043] In this embodiment, the fault operation data refers to the equipment operation parameters before and after the power plant equipment fails, including but not limited to the inlet working fluid parameters of the power plant equipment, the outlet working fluid parameters of the power plant equipment, and the control operation parameters of the power plant equipment. The power plant equipment may include one or more of a boiler, a steam turbine, a condenser, a high- and low-pressure heater, a condensate pump, and a feed water pump, etc., which are not specifically limited here. The inlet working fluid parameters may be the pressure and / or temperature of the water vapor at the inlet of the power plant equipment; the outlet working fluid parameters may be the pressure and / or temperature of the water vapor at the outlet of the power plant equipment; the control operation parameters of the power plant equipment may include but are not limited to the real-time water level value, the preset water level value, the motor speed, the equipment voltage and / or current, etc., which are not specifically limited here.

[0044] Exemplarily, the user can export the fault operation data of the power plant equipment at multiple times from the power plant database according to the maintenance log. The fault operation data can be in the form of a point table: P = (p1, p2, p3, ..., pm), where pm represents the fault operation data of the mth power plant equipment, that is, the point table P contains the continuous operation data of the power plant equipment at m times.

[0045] S120. In response to a graph construction operation being performed on the fault operation data of the power plant equipment at the multiple moments, a fault operation data graph of the power plant equipment is obtained, wherein the fault operation data graph of the power plant equipment comprises a plurality of columns of data, each column representing the fault operation data of the power plant equipment at the same moment, and the order of the inlet working fluid parameters of the power plant equipment, the control operation parameters of the power plant equipment and the outlet working fluid parameters of the power plant equipment in each column of data is arranged from top to bottom.

[0046] It should be noted that, through the graph construction operation, the model can accurately extract the change characteristics between fault operation data and the change characteristics on the time scale at the same time.

[0047] In some embodiments, data within a preset time period can be extracted from the fault operation data graph of the power plant equipment in a sliding time window manner, and the extracted fault operation data can be used to construct a training data set for the fault diagnosis model of the power plant equipment. The sliding window size can be W, and W can be 2×T / s, where T represents the equipment inertia time, and s represents the data sampling period; the sliding step size is the data sampling period.

[0048] S130. Constructing a training data set of a power plant equipment fault diagnosis model based on the fault operation data graph of the power plant equipment.

[0049] Specifically, the fault operation data graph of the power plant equipment can be labeled, proportionally divided, stored, and other operations can be performed to obtain a training data set for the power plant equipment fault diagnosis model.

[0050] S140, training the initial neural network model based on the power plant equipment fault diagnosis model training data set to obtain a trained power plant equipment fault diagnosis model.

[0051] In this embodiment, the initial neural network model can be trained in advance with the power plant equipment fault diagnosis model training data set to obtain the power plant equipment fault diagnosis model. In the trained neural network model, the change characteristics between the fault operation data and the change characteristics on the time scale in the fault operation data graph of the power plant equipment are extracted in advance, and the model parameters in the initial neural network model are trained based on the extracted change characteristics between the fault operation data and the change characteristics on the time scale, and by continuously adjusting the model parameters, the distance deviation between the output result of the model and the label is gradually reduced and stabilized, thereby obtaining the power plant equipment fault diagnosis model.

[0052] Exemplarily, the initial neural network model can be a convolutional neural network or a target detection model such as YoloV4, which is not specifically limited here.

[0053] In some optional embodiments, the configuration file for model training may also be modified according to the power plant equipment fault diagnosis model training data set. For example, the input image size parameters of YoloV4, the classes parameters of the Yolo layer, and the filters parameters of the Yolo layer may be modified.

[0054] The technical solution of the embodiment of the present invention is to obtain the fault operation data of the power plant equipment at multiple moments, wherein the fault operation data of the power plant equipment includes the inlet working fluid parameters of the power plant equipment, the outlet working fluid parameters of the power plant equipment and the control operation parameters of the power plant equipment; in response to the graph construction operation of the fault operation data of the power plant equipment at multiple moments, obtain the fault operation data graph of the power plant equipment, wherein the fault operation data graph of the power plant equipment includes multiple columns of data, each column represents the fault operation data of the power plant equipment at the same moment, and the order of the inlet working fluid parameters of the power plant equipment, the control operation parameters of the power plant equipment and the outlet working fluid parameters of the power plant equipment in each column of data is arranged from top to bottom; obtain the training data set of the fault diagnosis model of the power plant equipment based on the fault operation data graph of the power plant equipment; train the initial neural network model based on the training data set of the fault diagnosis model of the power plant equipment to obtain the trained fault diagnosis model of the power plant equipment. The above technical solution, through the graph construction operation, can enable the model to accurately extract the change characteristics between the fault operation data and the change characteristics on the time scale at the same time, thereby improving the fault recognition accuracy of the fault diagnosis model of the power plant equipment.

[0055] Embodiment 2

[0056] Figure 2A flowchart of a method for training a power plant equipment fault diagnosis model provided in the second embodiment of the present invention, the method of this embodiment can be combined with the various optional schemes in the method for training a power plant equipment fault diagnosis model provided in the above embodiments. The method for training a power plant equipment fault diagnosis model provided in this embodiment is further optimized. Optionally, after the acquisition of the fault operation data of the power plant equipment, the method further includes: normalizing the fault operation data of the power plant equipment at the multiple moments to obtain the normalized fault operation data of the power plant equipment; correspondingly, in response to performing a graph construction operation on the fault operation data of the power plant equipment at the multiple moments, obtaining a fault operation data graph of the power plant equipment, including: in response to performing a graph construction operation on the normalized fault operation data of the power plant equipment, obtaining a fault operation data graph of the power plant equipment.

[0057] like Figure 2 As shown, the method includes:

[0058] S210. Acquire fault operation data of power plant equipment at multiple moments, wherein the fault operation data of power plant equipment includes inlet working fluid parameters of power plant equipment, outlet working fluid parameters of power plant equipment and control operation parameters of power plant equipment.

[0059] S220 , normalizing the fault operation data of the power plant equipment at the multiple moments to obtain normalized fault operation data of the power plant equipment.

[0060] S230. In response to a graph construction operation being performed on the normalized fault operation data of the power plant equipment, a fault operation data graph of the power plant equipment is obtained, wherein the fault operation data graph of the power plant equipment comprises a plurality of columns of data, each column representing the fault operation data of the power plant equipment at the same moment, and the order of the inlet working fluid parameters of the power plant equipment, the control operation parameters of the power plant equipment and the outlet working fluid parameters of the power plant equipment in each column of data is arranged from top to bottom.

[0061] S240. Constructing a training data set for a power plant equipment fault diagnosis model based on the fault operation data graph of the power plant equipment.

[0062] S250: Training the initial neural network model based on the power plant equipment fault diagnosis model training data set to obtain a trained power plant equipment fault diagnosis model.

[0063] Exemplarily, the fault operation data of the power plant equipment at multiple moments may be normalized to 0-255, and then a graph construction operation may be performed on the normalized fault operation data of the power plant equipment to obtain a fault operation data graph of the power plant equipment.

[0064] The technical solution of the embodiment of the present invention normalizes the fault operation data of the power plant equipment at multiple moments to eliminate the differences between the fault operation data of the power plant equipment, thereby making the fault identification of the trained power plant equipment fault diagnosis model more accurate.

[0065] Embodiment 3

[0066] Figure 3 A flowchart of a method for training a power plant equipment fault diagnosis model provided in the third embodiment of the present invention, the method of this embodiment can be combined with the various optional schemes in the method for training a power plant equipment fault diagnosis model provided in the above embodiments. The training method for a power plant equipment fault diagnosis model provided in this embodiment is further optimized. Optionally, the construction of a training data set for a power plant equipment fault diagnosis model based on the fault operation data graph of the power plant equipment includes: obtaining labeled data of the fault operation data graph of the power plant equipment in response to a fault data labeling operation on the fault operation data graph of the power plant equipment, and constructing a training data set for a power plant equipment fault diagnosis model based on the fault operation data graph of the power plant equipment and the labeled data of the fault operation data graph of the power plant equipment.

[0067] like Figure 3 As shown, the method includes:

[0068] S310. Acquire fault operation data of power plant equipment at multiple moments, wherein the fault operation data of power plant equipment includes inlet working fluid parameters of power plant equipment, outlet working fluid parameters of power plant equipment and control operation parameters of power plant equipment.

[0069] S320. In response to a graph construction operation being performed on the fault operation data of the power plant equipment at the multiple moments, a fault operation data graph of the power plant equipment is obtained, wherein the fault operation data graph of the power plant equipment comprises a plurality of columns of data, each column representing the fault operation data of the power plant equipment at the same moment, and the order of the inlet working fluid parameters of the power plant equipment, the control operation parameters of the power plant equipment and the outlet working fluid parameters of the power plant equipment in each column of data is arranged from top to bottom.

[0070] S330. In response to the fault data labeling operation on the fault operation data graph of the power plant equipment, labeling data of the fault operation data graph of the power plant equipment is obtained, and a training data set of a fault diagnosis model for the power plant equipment is constructed based on the fault operation data graph of the power plant equipment and the labeling data of the fault operation data graph of the power plant equipment.

[0071] The annotation data of the fault operation data graph of the power plant equipment includes a rectangular anchor frame and a label, wherein the rectangular anchor frame contains the fault occurrence time, the fault duration and the fault operation data in the frame; the label represents the fault type number.

[0072] Exemplarily, if there are F types of faults in the power plant equipment, the value range of the label is [0, F-1]. After each fault operation data graph is annotated, a txt format file can be generated. The file name of the txt format file is consistent with the name of the fault operation data graph. The file content of the txt format file can be: (object_id x_topleft / W y_topleft / H anchor_width / Wanchor_height / H); where object_id represents the fault type number, x_topleft represents the x coordinate of the upper left corner of the rectangular anchor box, y_topleft represents the y coordinate of the upper left corner of the rectangular anchor box, anchor_width represents the width of the rectangular anchor box, and the width of the anchor box can be used to characterize the fault duration. Anchor_height represents the height of the rectangular anchor box.

[0073] S340: Training the initial neural network model based on the power plant equipment fault diagnosis model training data set to obtain a trained power plant equipment fault diagnosis model.

[0074] Optionally, before responding to a fault data labeling operation on a fault operation data graph of a power plant equipment, the method further includes: upsampling the fault operation data graph of the power plant equipment to obtain an upsampled fault operation data graph of the power plant equipment; correspondingly, in response to the fault data labeling operation on the fault operation data graph of the power plant equipment, obtaining labeling data of the fault operation data graph of the power plant equipment, and constructing a training data set of a fault diagnosis model for the power plant equipment based on the fault operation data graph of the power plant equipment and the labeling data of the fault operation data graph of the power plant equipment, including: in response to a fault data labeling operation on the upsampled fault operation data graph of the power plant equipment, obtaining labeling data of the upsampled fault operation data graph of the power plant equipment, and constructing a training data set of a fault diagnosis model for the power plant equipment based on the upsampled fault operation data graph of the power plant equipment and the labeling data of the upsampled fault operation data graph of the power plant equipment.

[0075] It should be noted that by upsampling the fault operation data graph of the power plant equipment, the fault operation data can better reflect the overall characteristics of the fault operation data graph, thereby improving the fault recognition accuracy of the trained model prediction.

[0076] Exemplarily, the upsampling target size is (W, H), W is 2×T / s, where T represents the equipment inertia time, s represents the data sampling period; H=m, m represents the amount of fault operation data of the power plant equipment.

[0077] Embodiment 4

[0078] Figure 4 This is a flowchart of a method for diagnosing a power plant equipment fault provided by the fourth embodiment of the present invention. This embodiment is applicable to the case of diagnosing a power plant equipment fault. The method can be executed by a power plant equipment fault diagnosis device. The power plant equipment fault diagnosis device can be implemented in the form of hardware and / or software. The power plant equipment fault diagnosis device can be configured in a terminal and / or a server. Figure 4 As shown, the method includes:

[0079] S410. Acquire real-time fault operation data of power plant equipment.

[0080] In this embodiment, the real-time fault operation data refers to the equipment operation parameters of the power plant equipment in the current time period, including but not limited to the inlet real-time working fluid parameters of the power plant equipment, the outlet real-time working fluid parameters of the power plant equipment, and the real-time control operation parameters of the power plant equipment. Exemplarily, the current time period may be (Tnow-W, Tnow), where Tnow is the current time.

[0081] S420: In response to performing a graph construction operation on the real-time fault operation data of the power plant equipment, a real-time fault operation data graph of the power plant equipment is obtained.

[0082] Exemplarily, the real-time fault operation data of the power plant equipment can be normalized to 0-255, and then the normalized real-time fault operation data can be arranged in sequence from top to bottom based on the inlet real-time working fluid parameters of the power plant equipment, the real-time control operation parameters of the power plant equipment, and the outlet real-time working fluid parameters of the power plant equipment to obtain a real-time fault operation data graph, and then the real-time fault operation data graph is upsampled to obtain an upsampled real-time fault operation data graph, wherein the upsampling target size is (W, H), W is 2×T / s, wherein T represents the equipment inertia time, s represents the data sampling period; H=m, m represents the number of fault operation data of the power plant equipment.

[0083] S430, inputting the real-time fault operation data graph of the power plant equipment into a pre-trained power plant equipment fault diagnosis model to obtain a fault diagnosis result.

[0084] The power plant equipment fault diagnosis model is trained based on the training method of the power plant equipment fault diagnosis model in any embodiment of the present invention.

[0085] Exemplarily, the upsampled real-time fault operation data graph is sent to the trained power plant equipment fault diagnosis model for forward deduction to obtain the fault diagnosis result, fault diagnosis result = (classes, boxes, score). If classes is None, it means that the power plant equipment is normal. If classes is not None, the fault can be diagnosed according to the fault type number corresponding to the classes and the width of the anchor box in the boxes to prompt the user to pay attention to the status of the power plant equipment. Score represents the score.

[0086] The technical solution of the embodiment of the present invention obtains the real-time fault operation data of the power plant equipment; in response to the graph construction operation on the real-time fault operation data of the power plant equipment, obtains the real-time fault operation data graph of the power plant equipment; inputs the real-time fault operation data graph of the power plant equipment into the pre-trained power plant equipment fault diagnosis model to obtain the fault diagnosis result. The above technical solution, through the graph construction operation, enables the model to accurately extract the change characteristics between the fault operation data and the change characteristics on the time scale at the same time, thereby improving the fault recognition accuracy of the power plant equipment fault diagnosis model.

[0087] Embodiment 5

[0088] Figure 5 This is a schematic diagram of the structure of a training device for a power plant equipment fault diagnosis model provided by Embodiment 5 of the present invention. Figure 5 As shown, the device comprises:

[0089] The fault operation data acquisition module 510 of the power plant equipment is used to acquire the fault operation data of the power plant equipment, wherein the fault operation data of the power plant equipment includes the inlet working fluid parameters of the power plant equipment, the outlet working fluid parameters of the power plant equipment and the control operation parameters of the power plant equipment;

[0090] A fault operation data graph construction module 520 for power plant equipment is used to obtain a fault operation data graph of the power plant equipment in response to a graph construction operation on the fault operation data of the power plant equipment, wherein the fault operation data graph of the power plant equipment comprises a plurality of columns of data, each column representing the fault operation data of the power plant equipment at the same time, and the order of the inlet working fluid parameters of the power plant equipment, the control operation parameters of the power plant equipment and the outlet working fluid parameters of the power plant equipment in each column of data is arranged in sequence from top to bottom;

[0091] A power plant equipment fault diagnosis model training data set construction module 530, used to construct a power plant equipment fault diagnosis model training data set based on the fault operation data graph of the power plant equipment;

[0092] The power plant equipment fault diagnosis model training module 540 is used to train the initial neural network model based on the power plant equipment fault diagnosis model training data set to obtain a trained power plant equipment fault diagnosis model.

[0093] The technical solution of the embodiment of the present invention is to obtain the fault operation data of the power plant equipment at multiple moments, wherein the fault operation data of the power plant equipment includes the inlet working fluid parameters of the power plant equipment, the outlet working fluid parameters of the power plant equipment and the control operation parameters of the power plant equipment; in response to the graph construction operation of the fault operation data of the power plant equipment at multiple moments, obtain the fault operation data graph of the power plant equipment, wherein the fault operation data graph of the power plant equipment includes multiple columns of data, each column represents the fault operation data of the power plant equipment at the same moment, and the order of the inlet working fluid parameters of the power plant equipment, the control operation parameters of the power plant equipment and the outlet working fluid parameters of the power plant equipment in each column of data is arranged from top to bottom; obtain the training data set of the fault diagnosis model of the power plant equipment based on the fault operation data graph of the power plant equipment; train the initial neural network model based on the training data set of the fault diagnosis model of the power plant equipment to obtain the trained fault diagnosis model of the power plant equipment. The above technical solution, through the graph construction operation, can enable the model to accurately extract the change characteristics between the fault operation data and the change characteristics on the time scale at the same time, thereby improving the fault recognition accuracy of the fault diagnosis model of the power plant equipment.

[0094] In some optional implementations, the training device for the power plant equipment fault diagnosis model further includes:

[0095] A fault operation data normalization module, used to normalize the fault operation data of the power plant equipment at the multiple moments to obtain normalized fault operation data of the power plant equipment;

[0096] Accordingly, the fault operation data graph construction module 520 of the power plant equipment is specifically used for:

[0097] In response to performing a graph construction operation on the normalized fault operation data of the power plant equipment, a fault operation data graph of the power plant equipment is obtained.

[0098] In some optional implementations, the power plant equipment fault diagnosis model training data set construction module 530 includes:

[0099] A data annotation unit, configured to obtain annotation data of the fault operation data graph of the power plant equipment in response to a fault data annotation operation on the fault operation data graph of the power plant equipment;

[0100] The training data set construction unit is used to construct a training data set for a power plant equipment fault diagnosis model based on the fault operation data graph of the power plant equipment and the annotation data of the fault operation data graph of the power plant equipment.

[0101] In some optional implementations, the training device for the power plant equipment fault diagnosis model further includes:

[0102] A fault operation data graph upsampling module is used to upsample the fault operation data graph of the power plant equipment to obtain an upsampled fault operation data graph of the power plant equipment;

[0103] Accordingly, the power plant equipment fault diagnosis model training data set construction module 530 is specifically used for:

[0104] In response to the fault data labeling operation on the fault operation data graph of the upsampled power plant equipment, the labeling data of the fault operation data graph of the upsampled power plant equipment is obtained, and a training data set of the fault diagnosis model of the power plant equipment is constructed based on the fault operation data graph of the upsampled power plant equipment and the labeling data of the fault operation data graph of the upsampled power plant equipment.

[0105] In some optional implementations, the annotation data of the fault operation data graph of the power plant equipment includes a rectangular anchor frame and a label, wherein the rectangular anchor frame includes the fault occurrence time and the fault duration; and the label represents the fault type number.

[0106] The training device for the power plant equipment fault diagnosis model provided in the embodiment of the present invention can execute the training method for the power plant equipment fault diagnosis model provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0107] Embodiment 6

[0108] Figure 6 This is a schematic diagram of the structure of a power plant equipment fault diagnosis device provided by the sixth embodiment of the present invention. Figure 6 As shown, the device comprises:

[0109] A real-time fault operation data acquisition module 610 is used to acquire real-time fault operation data of power plant equipment;

[0110] A real-time fault operation data graph construction module 620 is used to obtain a real-time fault operation data graph of the power plant equipment in response to performing a graph construction operation on the real-time fault operation data of the power plant equipment;

[0111] The fault diagnosis result prediction module 630 is used to input the real-time fault operation data diagram of the power plant equipment into a pre-trained power plant equipment fault diagnosis model to obtain a fault diagnosis result, wherein the power plant equipment fault diagnosis model is trained based on the training method of the power plant equipment fault diagnosis model described in any one of the embodiments of the present invention.

[0112] The technical solution of the embodiment of the present invention is to obtain the real-time fault operation data of the power plant equipment; in response to the graph construction operation on the real-time fault operation data of the power plant equipment, obtain the real-time fault operation data graph of the power plant equipment; input the real-time fault operation data graph of the power plant equipment into the pre-trained power plant equipment fault diagnosis model to obtain the fault diagnosis result. The above technical solution, through the graph construction operation, can enable the model to accurately extract the change characteristics between the fault operation data and the change characteristics on the time scale at the same time, thereby improving the fault recognition accuracy of the power plant equipment fault diagnosis model.

[0113] The power plant equipment fault diagnosis device provided in the embodiment of the present invention can execute the power plant equipment fault diagnosis method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0114] Embodiment 7

[0115] Figure 7 A schematic diagram of the structure of an electronic device 10 that can be used to implement an embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0116] like Figure 7As shown, the electronic device 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. The I / O interface 15 is also connected to the bus 14.

[0117] A number of components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0118] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The processor 11 executes the various methods and processes described above, such as a training method for a power plant equipment fault diagnosis model and / or a power plant equipment fault diagnosis method.

[0119] In some embodiments, the training method of the power plant equipment fault diagnosis model and / or the power plant equipment fault diagnosis method may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the training method of the power plant equipment fault diagnosis model and / or the power plant equipment fault diagnosis method described above may be executed. Alternatively, in other embodiments, the processor 11 may be configured to execute the training method of the power plant equipment fault diagnosis model and / or the power plant equipment fault diagnosis method in any other appropriate manner (e.g., by means of firmware).

[0120] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), system-on-chips (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0121] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0122] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, 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), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0123] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0124] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0125] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0126] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0127] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A training method for a power plant equipment fault diagnosis model, characterized in that: include: Acquire fault operation data of power plant equipment at multiple moments, wherein the fault operation data of power plant equipment includes inlet working fluid parameters of power plant equipment, outlet working fluid parameters of power plant equipment and control operation parameters of power plant equipment; In response to performing a graph construction operation on the fault operation data of the power plant equipment at the multiple moments, a fault operation data graph of the power plant equipment is obtained, wherein the fault operation data graph of the power plant equipment comprises a plurality of columns of data, each column represents the fault operation data of the power plant equipment at the same moment, and the order of the inlet working fluid parameter of the power plant equipment, the control operation parameter of the power plant equipment and the outlet working fluid parameter of the power plant equipment in each column of data is arranged in sequence from top to bottom; A training data set of a power plant equipment fault diagnosis model is obtained based on the fault operation data graph of the power plant equipment; The initial neural network model is trained based on the power plant equipment fault diagnosis model training data set to obtain a trained power plant equipment fault diagnosis model.

2. The method according to claim 1, characterized in that After acquiring the fault operation data of the power plant equipment, the method further includes: Normalizing the fault operation data of the power plant equipment at the multiple moments to obtain normalized fault operation data of the power plant equipment; Accordingly, in response to performing a graph construction operation on the fault operation data of the power plant equipment at the plurality of moments, a fault operation data graph of the power plant equipment is obtained, including: In response to performing a graph construction operation on the normalized fault operation data of the power plant equipment, a fault operation data graph of the power plant equipment is obtained.

3. The method according to claim 1, characterized in that: The method of constructing a power plant equipment fault diagnosis model training data set based on the fault operation data graph of the power plant equipment includes: In response to a fault data labeling operation on the fault operation data graph of the power plant equipment, labeling data of the fault operation data graph of the power plant equipment is obtained, and a training data set of a fault diagnosis model of the power plant equipment is constructed based on the fault operation data graph of the power plant equipment and the labeling data of the fault operation data graph of the power plant equipment.

4. The method according to claim 3, characterized in that Before responding to the fault data annotation operation on the fault operation data graph of the power plant equipment, the method further includes: Upsampling the fault operation data graph of the power plant equipment to obtain an upsampled fault operation data graph of the power plant equipment; Accordingly, in response to the fault data labeling operation on the fault operation data graph of the power plant equipment, labeling data of the fault operation data graph of the power plant equipment is obtained, and a training data set of a fault diagnosis model of the power plant equipment is constructed based on the fault operation data graph of the power plant equipment and the labeling data of the fault operation data graph of the power plant equipment, including: In response to the fault data labeling operation on the fault operation data graph of the upsampled power plant equipment, the labeling data of the fault operation data graph of the upsampled power plant equipment is obtained, and a training data set of the fault diagnosis model of the power plant equipment is constructed based on the fault operation data graph of the upsampled power plant equipment and the labeling data of the fault operation data graph of the upsampled power plant equipment.

5. The method according to claim 3, characterized in that: The annotated data of the fault operation data graph of the power plant equipment includes a rectangular anchor frame and a label, wherein the rectangular anchor frame includes the fault occurrence time and the fault duration; the label represents the fault type number.

6. A method for diagnosing faults in power plant equipment, characterized in that: include: Obtain real-time fault operation data of power plant equipment; In response to performing a graph construction operation on the real-time fault operation data of the power plant equipment, a real-time fault operation data graph of the power plant equipment is obtained; The real-time fault operation data graph of the power plant equipment is input into a pre-trained power plant equipment fault diagnosis model to obtain a fault diagnosis result, wherein the power plant equipment fault diagnosis model is trained based on the training method of the power plant equipment fault diagnosis model described in any one of claims 1-5.

7. A training device for a power plant equipment fault diagnosis model, characterized in that: include: A fault operation data acquisition module for power plant equipment, used to acquire fault operation data of power plant equipment, wherein the fault operation data of power plant equipment includes inlet working fluid parameters of power plant equipment, outlet working fluid parameters of power plant equipment and control operation parameters of power plant equipment; A fault operation data graph construction module for power plant equipment, configured to obtain a fault operation data graph of the power plant equipment in response to a graph construction operation on the fault operation data of the power plant equipment, wherein the fault operation data graph of the power plant equipment comprises a plurality of columns of data, each column representing the fault operation data of the power plant equipment at the same time, and the order of the inlet working fluid parameters of the power plant equipment, the control operation parameters of the power plant equipment and the outlet working fluid parameters of the power plant equipment in each column of data is arranged from top to bottom; A power plant equipment fault diagnosis model training data set construction module, used to construct a power plant equipment fault diagnosis model training data set based on the fault operation data graph of the power plant equipment; The power plant equipment fault diagnosis model training module is used to train the initial neural network model based on the power plant equipment fault diagnosis model training data set to obtain a trained power plant equipment fault diagnosis model.

8. A power plant equipment fault diagnosis device, characterized in that: include: A real-time fault operation data acquisition module is used to acquire real-time fault operation data of power plant equipment; A real-time fault operation data graph construction module, configured to obtain a real-time fault operation data graph of the power plant equipment in response to performing a graph construction operation on the real-time fault operation data of the power plant equipment; A fault diagnosis result prediction module is used to input the real-time fault operation data graph of the power plant equipment into a pre-trained power plant equipment fault diagnosis model to obtain a fault diagnosis result, wherein the power plant equipment fault diagnosis model is trained based on the training method of the power plant equipment fault diagnosis model described in any one of claims 1-5.

9. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively coupled to the at least one processor; In which, the memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the training method of the power plant equipment fault diagnosis model described in any one of claims 1-5 and / or the power plant equipment fault diagnosis method described in claim 6.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, which are used to enable a processor to implement the training method for a power plant equipment fault diagnosis model described in any one of claims 1 to 5 and / or the power plant equipment fault diagnosis method described in claim 6 when executed.