A Substation Equipment Fault Diagnosis Method and Related Devices Based on Voiceprint Recognition

Abstract

The present application discloses a substation equipment fault diagnosis method and related devices based on voiceprint recognition. The method includes: obtaining the operation sound data and equipment-related information of each device in the target substation area according to a preset basic data acquisition underlying framework, where the preset basic data acquisition underlying framework includes multiple data transmission nodes; using a preset voice recognition model to perform abnormality determination based on the operation sound data to obtain an abnormality recognition result; in the case where the abnormality recognition result is abnormal, generating an equipment fault information group according to the equipment-related information; based on a preset fault analysis model, performing fault analysis according to the equipment fault information group and preset historical experience data to obtain a fault analysis result, where the fault analysis result includes a fault cause and a fault response measure. The present application can solve the technical problems in the prior art that the data acquisition and transmission process in the early stage is unreliable, and the abnormality detection granularity is large and the accuracy is low, resulting in an unsatisfactory actual fault diagnosis effect.

Description

Technical Field

[0001] The present application relates to the technical field of substation equipment, and in particular to a substation equipment fault diagnosis method based on voiceprint recognition and related devices. Background Art

[0002] With the development of power grid construction and the improvement of safety requirements, substation construction is moving towards unmanned or less-manned operation. At present, unmanned substations mainly tend to develop in the direction of "five remotes" (telemetry, telesignaling, remote control, remote adjustment, and remote viewing). Using video monitoring systems, the "remote viewing" function has been gradually realized in substations, but the monitoring of the internal sound of the running equipment has not been taken seriously, and very few complete sets of equipment have been developed, and even fewer intelligent audio recognition systems for the operating status of power equipment.

[0003] When the power equipment is running with power, it will produce unique sound and vibration that can characterize the state of the equipment itself. This sound is unique to the equipment and can be measured and analyzed by electroacoustic instruments. Therefore, we call the characteristics of the power equipment running state carried by the sound as soundprint and vibration. By using this characteristic, abnormal detection of the detection soundprint information of the detected equipment can predict the working condition of the equipment, realize early prediction and elimination before the equipment fails, and avoid losses caused by abnormal power outages caused by sudden failures of power equipment.

[0004] Although the existing technology can determine whether there is an abnormality by collecting the sound of the target device and pre-processing it, it cannot guarantee the accuracy of the data collection process, and requires targeted processing of the data at a later stage, which is cumbersome; and the data transmission process is not guaranteed, which is also an important factor affecting data quality and judgment results; in addition, simply determining the existence of an abnormality cannot effectively solve the actual problem, that is, the granularity and accuracy of anomaly detection are poor, and the monitoring effect is not ideal. Summary of the invention

[0005] The present application provides a substation equipment fault diagnosis method and related devices based on voiceprint recognition, which are used to solve the technical problems that the data collection and transmission process in the early stage of the prior art is unreliable, and the anomaly detection granularity is large and the accuracy is low, resulting in unsatisfactory actual fault diagnosis effect.

[0006] In view of this, the first aspect of the present application provides a substation equipment fault diagnosis method based on voiceprint recognition, comprising:

[0007] Obtain the operating sound data and device-related information of each device in the target substation area according to the preset basic data acquisition underlying framework, where the preset basic data acquisition underlying framework includes multiple data transmission nodes, and the device-related information includes device structure information, device images, and device environment information;

[0008] Use the preset sound recognition model to perform anomaly determination based on the operating sound data to obtain an anomaly recognition result;

[0009] In the case where the anomaly recognition result is an anomaly, generate a device fault information group according to the device-related information;

[0010] Based on the preset fault analysis model, perform fault analysis according to the device fault information group and the preset historical experience data to obtain a fault analysis result, where the fault analysis result includes the fault cause and the fault response measure.

[0011] Preferably, before obtaining the operating sound data and device-related information of each device in the target substation area according to the preset basic data acquisition underlying framework, it further includes:

[0012] Divide the original power grid area into multiple target power grid areas;

[0013] Obtain the basic information of all substations in the target power grid area, where the basic information includes the number of substations and the location of the substations.

[0014] Preferably, before obtaining the operating sound data and device-related information of each device in the target substation area according to the preset basic data acquisition underlying framework, it further includes:

[0015] Build an initial data transmission network framework based on the basic information of each substation, where the initial data transmission network framework includes multiple data transmission nodes;

[0016] Establish an association between the preset device basic information of each device in the substation and the data transmission nodes to obtain a preset basic data acquisition underlying framework, where the preset device basic information includes the device model, device name, and device type.

[0017] Preferably, before using the preset sound recognition model to perform anomaly determination based on the operating sound data to obtain an anomaly recognition result, it further includes:

[0018] Perform preprocessing operations on the obtained large amount of device sound sample data to obtain a sound sample training set;

[0019] Perform anomaly determination pre-training operations on the constructed initial sound recognition model through the sound sample training set to obtain a preset sound recognition model.

[0020] The second aspect of the present application provides a substation equipment fault diagnosis device based on voiceprint recognition, including:

[0021] A first acquisition module, configured to obtain the operation sound data and equipment-related information of each device in the target substation area according to a preset basic data acquisition underlying framework, where the preset basic data acquisition underlying framework includes a plurality of data transmission nodes, and the equipment-related information includes equipment structure information, equipment images, and equipment environment information;

[0022] An abnormal determination module, configured to perform abnormal determination according to the operation sound data by using a preset voice recognition model to obtain an abnormal recognition result;

[0023] An information generation module, configured to generate a device fault information group according to the equipment-related information when the abnormal recognition result is abnormal;

[0024] A fault diagnosis module, configured to perform fault analysis based on a preset fault analysis model according to the equipment fault information group and preset historical experience data to obtain a fault analysis result, where the fault analysis result includes a fault cause and a fault response measure.

[0025] Preferably, it further includes:

[0026] A region division module, configured to divide the original power grid region to obtain a plurality of target power grid regions;

[0027] A second acquisition module, configured to obtain the basic information of all substations in the target power grid region, where the basic information includes the number of substations and the positions of substations.

[0028] Preferably, it further includes:

[0029] A framework construction module, configured to build an initial data transmission network framework based on the basic information of each substation, where the initial data transmission network framework includes a plurality of data transmission nodes;

[0030] An information association module, configured to establish an association between the preset equipment basic information of each device in the substation and the data transmission nodes to obtain a preset basic data acquisition underlying framework, where the preset equipment basic information includes equipment model, equipment name, and equipment type.

[0031] Preferably, it further includes:

[0032] A sample acquisition module, configured to perform preprocessing operations on a large amount of acquired equipment sound sample data to obtain a sound sample training set;

[0033] The model training module is used to perform an abnormality determination pre-training operation on the constructed initial sound recognition model through the sound sample training set to obtain a preset sound recognition model.

[0034] A third aspect of the present application provides a substation equipment fault diagnosis device based on voiceprint recognition, the device comprising a processor and a memory;

[0035] The memory is used to store program codes and transmit the program codes to the processor;

[0036] The processor is used to execute the substation equipment fault diagnosis method based on voiceprint recognition described in the first aspect according to the instructions in the program code.

[0037] A fourth aspect of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium is used to store program code, and the program code is used to execute the substation equipment fault diagnosis method based on voiceprint recognition described in the first aspect.

[0038] It can be seen from the above technical solutions that the embodiments of the present application have the following advantages:

[0039] In the present application, a method for diagnosing substation equipment faults based on voiceprint recognition is provided, including: obtaining operating sound data and equipment-related information of each device in the target substation area according to a preset basic data acquisition underlying framework, the preset basic data acquisition underlying framework includes multiple data transmission nodes, and the equipment-related information includes equipment construction information, equipment image and equipment environment information; using a preset sound recognition model to perform abnormality judgment based on the operating sound data to obtain an abnormality recognition result; when the abnormality recognition result is abnormal, generating an equipment fault information group according to the equipment-related information; based on a preset fault analysis model, performing fault analysis according to the equipment fault information group and preset historical experience data to obtain a fault analysis result, and the fault analysis result includes the cause of the fault and the fault response measures.

[0040] The substation equipment fault diagnosis method based on voiceprint recognition provided by the present application adopts a preset basic data acquisition underlying framework to acquire and transmit information such as operating sound data, ensures the accuracy of acquired data through the acquisition framework, and ensures the reliability of data transmission through data transmission nodes; after determining the abnormal result through the sound recognition model, the cause of the fault is analyzed based on the equipment information and the abnormal determination result, accurately diagnoses the equipment fault, and provides corresponding fault response measures for specific faults, which can provide accurate fault diagnosis solutions and ensure the reliability of early data processing. Therefore, the present application can solve the technical problems that the data acquisition and transmission process in the early stage of the prior art is unreliable, and the abnormal detection granularity is large and the accuracy is low, resulting in unsatisfactory actual fault diagnosis effect. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 It is a schematic flow chart of a substation equipment fault diagnosis method based on voiceprint recognition provided by an embodiment of the present application;

[0042] Figure 2 It is a schematic structural diagram of a substation equipment fault diagnosis device based on voiceprint recognition provided by an embodiment of the present application. Specific embodiments

[0043] In order to enable those skilled in the art to better understand the solution of the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative work shall fall within the protection scope of the present application.

[0044] For ease of understanding, please refer to Figure 1 , an embodiment of a substation equipment fault diagnosis method based on voiceprint recognition provided by the present application, including:

[0045] Step 101: Obtain the operation sound data and equipment-related information of each device in the target substation area according to a preset basic data acquisition underlying framework. The preset basic data acquisition underlying framework includes multiple data transmission nodes, and the equipment-related information includes equipment structure information, equipment images, and equipment environment information.

[0046] The preset basic data acquisition underlying framework is constructed to ensure the quality of data acquisition and transmission. This framework can ensure the reliability and traceability of data transmission through multiple data transmission nodes. Based on this framework, in addition to being able to obtain the operation sound data of the equipment, various other related information of the equipment can also be obtained. In addition to the equipment structure information, equipment images, and equipment environment information, other equipment-related information can also be added as needed, and specific details are not limited.

[0047] After the preset basic data acquisition underlying framework is built, the operation sound data of each device in the corresponding substation in the target area is collected in real time through the acquisition device, and then the data is transmitted to the background server through each data transmission node of the constructed data transmission framework. Then, the background server processes the real-time operation sound data of the corresponding device.

[0048] Further, before step 101, it also includes:

[0049] Divide the original power grid area into multiple target power grid areas;

[0050] Obtain the basic information of all substations in the target power grid area, where the basic information includes the number of substations and the locations of substations.

[0051] The purpose of zoning is to better manage and monitor the substation equipment in each area, making the monitoring results more reliable and reducing the total data processing volume. After the target power grid area is zoned, the basic information of the substations can be obtained, that is, to determine the number and specific locations of the substations in the target power grid area.

[0052] Furthermore, before step 101, it also includes:

[0053] Build an initial data transmission network framework based on the basic information of each substation. The initial data transmission network framework includes multiple data transmission nodes;

[0054] Establish an association between the preset equipment basic information of each device in the substation and the data transmission nodes to obtain a preset basic data acquisition underlying framework. The preset equipment basic information includes equipment model, equipment name, and equipment type.

[0055] After clarifying the number and specific locations of the substations in the target power grid area, data transmission nodes can be reasonably established based on this information to improve the data transmission efficiency and ensure the reliability of data transmission. It can be understood that each data transmission node is configured with a unique identifier, which can be traced and searched, or used for establishing associations; the data transmission nodes can include a main node and auxiliary nodes to ensure that relevant information of the corresponding substation can still be obtained in a timely manner when one or more sub-nodes fail. In addition, a reasonable number of data transmission nodes needs to be set according to the maximum amount of data transmitted by each data transmission node to ensure fast data transmission while avoiding redundant transmission nodes and saving configuration resources. In addition, the data transmission targets of each data transmission node in the initial framework can also be set.

[0056] In addition to the model, name, and type, the preset equipment basic information also includes equipment location, equipment component structure, etc. Based on this information, a classification directory can be established to store equipment information of different categories and facilitate subsequent equipment classification management. According to the equipment under the classification directory, establish an association between the preset equipment basic information of each device in the substation and the data transmission nodes, thereby obtaining a complete preset basic data acquisition underlying framework.

[0057] Step 102: Use a preset voice recognition model to perform anomaly determination based on the operating sound data to obtain an anomaly recognition result.

[0058] Input the operation sound data corresponding to each device into a preset sound recognition model for feature extraction operations. Based on multiple features, perform sound judgment to obtain an anomaly recognition result, that is, whether the operation sound data of each processed device is abnormal. The preset sound recognition model is a model that has been trained based on sound samples and can be directly used. The judgment and recognition performance of the model can be tested through a test set during training, so as to obtain a preset sound recognition model with a relatively high discrimination accuracy.

[0059] Further, step 102 also includes:

[0060] Perform preprocessing operations on the obtained large amount of device sound sample data to obtain a sound sample training set;

[0061] Perform anomaly determination pre-training operations on the constructed initial sound recognition model through the sound sample training set to obtain a preset sound recognition model.

[0062] The preprocessing operation is to improve the quality of the device sound sample data, which can be selectively set according to the actual situation and is not limited here. The purpose of the pre-training operation is to improve the recognition accuracy and rate of the model. In order to verify the performance of the model, a sound sample test set can also be used to test the trained model, and the preset sound recognition model is determined only when the test results meet the standards.

[0063] Step 103, in the case where the anomaly recognition result is abnormal, generate a device fault information group according to the device-related information.

[0064] The actual operation process is that when the recognition result shows that the device is operating abnormally, the server analyzes and determines which device or devices in which substation have abnormal conditions, and then generates a data acquisition signal to the data acquisition device in the corresponding substation to collect the conditions of the corresponding device.

[0065] Transmit the device data collected by the data acquisition device and the data uploaded by the device itself through the data transmission node associated with the corresponding abnormal device in the substation to the background server, so that the background server can perform further accurate analysis. The transmitted data includes data in multiple aspects such as device images, the structures of each component of the device, and the device environment. Different data analysis operations can be performed on these data information to generate a device fault information group for specific fault analysis.

[0066] Step 104, based on the preset fault analysis model, perform fault analysis according to the device fault information group and the preset historical experience data to obtain a fault analysis result, and the fault analysis result includes the fault cause and the fault countermeasure.

[0067] The preset fault analysis model mainly compares and analyzes the preset historical experience data to determine the specific faulty equipment, the faulty parts of the faulty equipment, and the fault causes of the faulty equipment, etc. It is understandable that the preset fault analysis model can also be a trained model, and the specific process is not repeated. The preset historical experience data can be organized into materials to be used in the form of a list or a checklist. Fault response measures can be measures such as controlling the equipment to suspend operation and ensuring the safe operation of the equipment.

[0068] The substation equipment fault diagnosis method based on voiceprint recognition provided in the embodiment of the present application adopts a preset basic data acquisition underlying framework to acquire and transmit information such as operating sound data, ensures the accuracy of acquired data through the acquisition framework, and ensures the reliability of data transmission through data transmission nodes; after determining the abnormal result through the sound recognition model, continue to analyze the cause of the fault according to the equipment information and the abnormal determination result, accurately diagnose the equipment fault, and provide corresponding fault response measures for specific faults, which can not only provide an accurate fault diagnosis solution, but also ensure the reliability of early data processing. Therefore, the embodiment of the present application can solve the technical problems that the data acquisition and transmission process in the early stage of the prior art is unreliable, and the abnormal detection granularity is large and the accuracy is low, resulting in unsatisfactory actual fault diagnosis effect.

[0069] For easier understanding, see Figure 2 The present application provides an embodiment of a substation equipment fault diagnosis device based on voiceprint recognition, comprising:

[0070] The first acquisition module 201 is used to acquire the operation sound data and device related information of each device in the target substation area according to the preset basic data acquisition underlying framework, the preset basic data acquisition underlying framework includes multiple data transmission nodes, and the device related information includes device structure information, device image and device environment information;

[0071] The abnormality determination module 202 is used to use a preset sound recognition model to perform abnormality determination based on the operating sound data to obtain an abnormality recognition result;

[0072] The information generation module 203 is used to generate a device fault information group according to device related information when the abnormality identification result is abnormal;

[0073] The fault diagnosis module 204 is used to perform fault analysis based on a preset fault analysis model, according to the equipment fault information group and preset historical experience data, and obtain a fault analysis result, which includes a fault cause and a fault response measure.

[0074] Furthermore, it also includes:

[0075] The area division module 205 is used to divide the original power grid area to obtain multiple target power grid areas;

[0076] The second acquisition module 206 is used to acquire the basic information of all substations in the target power grid area, and the basic information includes the number of substations and the locations of the substations.

[0077] Furthermore, it further includes:

[0078] The framework construction module 207 is used to build an initial data transmission network framework based on the basic information of each substation. The initial data transmission network framework includes multiple data transmission nodes;

[0079] The information association module 208 is used to establish an association between the preset device basic information of each device in the substation and the data transmission nodes to obtain a preset basic data acquisition underlying framework. The preset device basic information includes the device model, device name, and device type.

[0080] Furthermore, it further includes:

[0081] The sample acquisition module 209 is used to preprocess the acquired large amount of device sound sample data to obtain a sound sample training set;

[0082] The model training module 210 is used to perform an anomaly determination pre-training operation on the constructed initial sound recognition model through the sound sample training set to obtain a preset sound recognition model.

[0083] This application also provides a substation equipment fault diagnosis device based on voiceprint recognition. The device includes a processor and a memory;

[0084] The memory is used to store program codes and transmit the program codes to the processor;

[0085] The processor is used to execute the substation equipment fault diagnosis method based on voiceprint recognition in the above method embodiments according to the instructions in the program codes.

[0086] This application also provides a computer-readable storage medium. The computer-readable storage medium is used to store program codes, and the program codes are used to execute the substation equipment fault diagnosis method based on voiceprint recognition in the above method embodiments.

[0087] In several embodiments provided by the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections to each other can be through some interfaces. The indirect couplings or communication connections of the devices or units can be in electrical, mechanical or other forms.

[0088] The units described as separate components may or may not be physically separated. The components displayed as units may or may not be physical units, that is, they can be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0089] In addition, in each embodiment of the present application, the functional units can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit. The above-mentioned integrated units can be implemented in the form of hardware or in the form of software functional units.

[0090] If the above-mentioned integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, or all or part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in each embodiment of the present application. The foregoing storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memories (English full name: Read-Only Memory, English abbreviation: ROM), random access memories (English full name: Random Access Memory, English abbreviation: RAM), magnetic disks or optical discs that can store program codes.

[0091] As described above, the above embodiments are only used to illustrate the technical solutions of the present application and are not intended to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements on some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A substation equipment fault diagnosis method based on voiceprint recognition, characterized in that Including: Dividing the area of the original power grid region to obtain multiple target power grid regions; Obtaining the basic information of all substations within the target power grid region, where the basic information includes the number of substations and the locations of the substations; Building an initial data transmission network framework based on the basic information of each substation, and the initial data transmission network framework includes multiple data transmission nodes; Associating the preset device basic information of each device in the substation with the data transmission nodes to obtain a preset basic data collection underlying framework, where the preset device basic information includes the device model, device name, and device type; Obtaining the operating sound data and device-related information of each device within the target substation region according to the preset basic data collection underlying framework, the preset basic data collection underlying framework includes multiple data transmission nodes, and the device-related information includes device structure information, device images, and device environment information; Performing anomaly determination on the operating sound data using a preset sound recognition model to obtain an anomaly recognition result; Generating a device fault information group according to the device-related information in the case where the anomaly recognition result is an anomaly; Based on a preset fault analysis model, performing fault analysis according to the device fault information group and preset historical experience data to obtain a fault analysis result, where the fault analysis result includes the fault cause and fault response measures.

2. The method for diagnosing faults of substation equipment based on voiceprint recognition according to claim 1, characterized in that, Before the step of performing anomaly determination on the operating sound data using a preset sound recognition model to obtain an anomaly recognition result, it further includes: Performing a preprocessing operation on a large amount of acquired device sound sample data to obtain a sound sample training set; Performing an anomaly determination pre-training operation on the constructed initial sound recognition model through the sound sample training set to obtain a preset sound recognition model.

3. A substation equipment fault diagnosis device based on voiceprint recognition, characterized in that, Including: An area division module for dividing the area of the original power grid region to obtain multiple target power grid regions; A second acquisition module for obtaining the basic information of all substations within the target power grid region, where the basic information includes the number of substations and the locations of the substations; A framework construction module for building an initial data transmission network framework based on the basic information of each substation, and the initial data transmission network framework includes multiple data transmission nodes; An information association module for associating the preset device basic information of each device in the substation with the data transmission nodes to obtain a preset basic data collection underlying framework, where the preset device basic information includes the device model, device name, and device type; A first acquisition module for obtaining the operating sound data and device-related information of each device within the target substation region according to the preset basic data collection underlying framework, the preset basic data collection underlying framework includes multiple data transmission nodes, and the device-related information includes device structure information, device images, and device environment information; An anomaly determination module for performing anomaly determination on the operating sound data using a preset sound recognition model to obtain an anomaly recognition result; An information generation module for generating a device fault information group according to the device-related information in the case where the anomaly recognition result is an anomaly; A fault diagnosis module, configured to perform fault analysis based on a preset fault analysis model according to the device fault information group and preset historical experience data, and obtain a fault analysis result, where the fault analysis result includes a fault cause and a fault response measure.

4. The device for diagnosing substation equipment faults based on voiceprint recognition according to claim 3, wherein It further includes: A sample acquisition module, configured to perform preprocessing operations on a large number of acquired device sound sample data to obtain a sound sample training set; A model training module, configured to perform anomaly determination pre-training operations on the constructed initial sound recognition model through the sound sample training set to obtain a preset sound recognition model.

5. A substation equipment fault diagnosis device based on voiceprint recognition, characterized in that, The device includes a processor and a memory; The memory is used to store program code and transmit the program code to the processor; The processor is configured to execute the method for diagnosing faults of substation equipment based on voiceprint recognition according to any one of claims 1-2 according to the instructions in the program code.

6. A computer-readable storage medium, characterized in that, The computer-readable storage medium is used to store program code, and the program code is used to execute the method for diagnosing faults of substation equipment based on voiceprint recognition according to any one of claims 1-2.

Images