Leakage state assessment method, device, terminal and storage medium of gas valve device
By reducing the noise reduction and extracting the soundprint feature of the audio data of the air valve device, and determining the leakage status using the identification model, the problem of air leakage in the existing technology cannot be discovered in a timely manner, and the intelligentization of the air valve device is realized and automated air leakage detection improve evaluation accuracy.
Patent Information
- Application Number
- CN202111109443.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2021-09-22
- Publication Date
- 2024-11-01
- Estimated Expiration
- 2041-09-22
AI Technical Summary
The prior art cannot detect whether the air valve device is leaking in time, resulting in the inability to detect risks and hidden dangers in time.
By acquiring the initial audio data of the air valve device, performing noise reduction processing and voiceprint feature extraction, a preset identification model is used to determine whether the air valve device is in a leaky state, and an abnormal signal is sent to the client.
The accuracy of air leakage audio data extraction and the accuracy of air leakage status evaluation of air valve device are improved, and intelligent and automated detection of air leakage status is realized, avoiding the gas valve device causing failure and affecting normal production.
Smart Images

Figure CN114018498B_ABST
Abstract
Description
Technical Field
[0001] The present invention belongs to the technical field of gas valve fault detection, and in particular relates to a gas leakage state assessment method, device, terminal and storage medium of a gas valve device. Background Art
[0002] The power metering production infrastructure mainly includes automated calibration lines and intelligent three-dimensional warehouses. These two types of infrastructure are mainly divided into pneumatic and electric types. Pneumatic automated calibration lines and intelligent three-dimensional warehouses are mainly driven by compressed gas, so each action unit needs to be equipped with one or more gas valve devices. The gas valve may leak due to manufacturing process, usage time, aging, and untimely maintenance.
[0003] At present, whether there is leakage in the gas valve device is generally detected by manual inspection, that is, after a period of time, maintenance personnel go to the operation site to conduct unified inspection and troubleshooting of the gas valve device.
[0004] However, the aging of the gas valve device is a gradual process. When the leakage reaches a certain level, it is difficult to detect potential risks through manual inspections, resulting in the inability to promptly detect whether the gas valve device is leaking. Summary of the invention
[0005] In view of this, an embodiment of the present invention provides a method, device, terminal and storage medium for evaluating the leakage status of a gas valve device to solve the problem in the prior art that it is impossible to timely detect whether the gas valve device is leaking.
[0006] A first aspect of an embodiment of the present invention provides a method for evaluating a gas leakage state of a gas valve device, comprising:
[0007] Acquiring initial audio data within a preset range of the air valve device;
[0008] Performing noise reduction processing on the initial audio data to obtain air leakage audio data;
[0009] According to the preset recognition model and the air leakage audio data, the voiceprint feature corresponding to the air leakage audio data is obtained;
[0010] Based on the voiceprint features and preset voiceprint features, it is determined that the air valve device is in a leaking state.
[0011] In a possible implementation, performing noise reduction processing on the initial audio data to obtain air leakage audio data includes:
[0012] Removing environmental noise data from the initial audio data to obtain air leakage audio data;
[0013] or,
[0014] Performing software filtering and noise reduction on the initial audio data to obtain the noise-reduced initial audio data;
[0015] If the amplitude corresponding to the initial audio data after noise reduction meets the preset amplitude, the initial audio data after noise reduction is used as the air leakage audio data.
[0016] In a possible implementation, obtaining a voiceprint feature corresponding to the air leakage audio data according to a preset recognition model and the air leakage audio data includes:
[0017] Determine the preset recognition model;
[0018] The preset recognition model is used to extract the voiceprint features of the air leakage audio data to obtain the voiceprint features corresponding to the air leakage audio data.
[0019] In a possible implementation, determining a preset recognition model includes:
[0020] Obtaining an initial recognition model and training sample data;
[0021] The training sample data is input into the initial recognition model, and when the number of iterations meets the preset number, the preset recognition model is obtained.
[0022] In a possible implementation, the training sample data is input into the initial recognition model, and when the number of iterations meets the preset number, a preset recognition model is obtained, including:
[0023] Input the training sample data into the initial recognition model to determine the classification probability corresponding to the training sample data;
[0024] Calculate the difference between the classification probability and the preset classification probability, and determine the loss value of the initial recognition model based on the difference;
[0025] The initial recognition model is reversely trained according to the loss value until the number of iterations meets the preset number, and the preset recognition model is determined.
[0026] In a possible implementation, determining that the air valve device is in a leaking state based on the voiceprint feature and the preset voiceprint feature includes:
[0027] Determine whether the voiceprint feature is consistent with the preset voiceprint feature;
[0028] If the voiceprint feature is inconsistent with the preset voiceprint feature, the air valve device is in a leaking state.
[0029] In a possible implementation, the method further includes:
[0030] Determine a status score corresponding to the air leakage audio data;
[0031] If the leaking audio data is inconsistent with the preset audio data and the status score exceeds the preset score, an abnormal signal is sent to the client.
[0032] A second aspect of an embodiment of the present invention provides a device for evaluating the leakage state of a gas valve device, the device comprising:
[0033] A data acquisition module, used to acquire initial audio data within a preset range of the air valve device;
[0034] A noise reduction processing module is used to perform noise reduction processing on the initial audio data to obtain air leakage audio data;
[0035] A feature extraction module, used to obtain the voiceprint features corresponding to the air leakage audio data according to a preset recognition model and the air leakage audio data;
[0036] The state determination module is used to determine whether the air valve device is in a leaking state based on the voiceprint feature and the preset voiceprint feature.
[0037] In a possible implementation, the noise reduction processing module includes:
[0038] A first noise reduction processing submodule is used to remove environmental noise data from the initial audio data to obtain air leakage audio data;
[0039] or,
[0040] The second noise reduction processing submodule is used to perform software filtering and noise reduction on the initial audio data to obtain the noise-reduced initial audio data;
[0041] The air leakage audio determination submodule is used to use the initial audio data after noise reduction as the air leakage audio data if the amplitude corresponding to the initial audio data after noise reduction meets the preset amplitude.
[0042] In a possible implementation, the feature extraction module includes:
[0043] A model determination submodule is used to determine a preset recognition model;
[0044] The feature extraction submodule is used to extract voiceprint features from the air leakage audio data using a preset recognition model to obtain the voiceprint features corresponding to the air leakage audio data.
[0045] In a possible implementation, the model determination submodule includes:
[0046] A data acquisition unit, used to acquire an initial recognition model and training sample data;
[0047] The model training unit is used to input the training sample data into the initial recognition model, and obtain the preset recognition model when the number of iterations meets the preset number.
[0048] In a possible implementation, the model training unit includes:
[0049] The classification probability determination subunit is used to input the training sample data into the initial recognition model to determine the classification probability corresponding to the training sample data;
[0050] The loss value calculation subunit is used to calculate the difference between the classification probability and the preset classification probability, and determine the loss value of the initial recognition model according to the difference;
[0051] The model determination subunit is used to reversely train the initial recognition model according to the loss value until the number of iterations meets the preset number, and determine the preset recognition model.
[0052] In a possible implementation, the state determination module includes:
[0053] A judgment submodule is used to judge whether the voiceprint feature is consistent with the preset voiceprint feature;
[0054] The state determination submodule is used to determine that the air valve device is in a leaking state if the voiceprint feature is inconsistent with the preset voiceprint feature.
[0055] In a possible implementation, the method further includes:
[0056] A score determination module, used to determine a status score corresponding to the air leakage audio data;
[0057] The abnormality judgment module is used to send an abnormality signal to the client if the air leakage audio data is inconsistent with the preset audio data and the status score exceeds the preset score.
[0058] A third aspect of an embodiment of the present invention provides a terminal, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the steps of a method for evaluating the leakage status of a gas valve device as described in any one of the above items are implemented.
[0059] A fourth aspect of an embodiment of the present invention provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the steps of the method for evaluating the leakage state of a gas valve device as described in any one of the above items are implemented.
[0060] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:
[0061] The embodiment of the present invention first obtains the initial audio data within a preset range of the air valve device, then performs noise reduction processing on the initial audio data to obtain leakage audio data, and then obtains the voiceprint features corresponding to the leakage audio data based on the preset recognition model and the leakage audio data, and finally compares the voiceprint features with the preset voiceprint features to determine that the air valve device is in a leakage state. The present invention extracts features from the leakage audio data through a preset recognition model, thereby improving the accuracy of the leakage audio data extraction, and can obtain more accurate voiceprint features, and then compares the voiceprint features with the preset voiceprint features, further improving the accuracy of the leakage state assessment of the air valve device. In addition, the present invention uses an artificial intelligence model to assess the leakage state of the air valve device, which not only improves the assessment accuracy, but also realizes the intelligence and automation of the leakage state assessment, thereby avoiding the air valve device causing failures and affecting normal production. BRIEF DESCRIPTION OF THE DRAWINGS
[0062] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. 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 paying creative labor.
[0063] Figure 1 It is a schematic diagram of the implementation flow of a method for evaluating the leakage state of a gas valve device provided by an embodiment of the present invention;
[0064] Figure 2 is a schematic diagram of audio data of air valve leakage provided by an embodiment of the present invention;
[0065] Figure 3 A schematic structural diagram of a device for evaluating the leakage state of a gas valve device provided by an embodiment of the present invention;
[0066] Figure 4 is a schematic diagram of a terminal provided by an embodiment of the present invention. DETAILED DESCRIPTION
[0067] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present invention. However, it should be clear to those skilled in the art that the present invention may be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present invention.
[0068] In order to illustrate the technical solution of the present invention, specific embodiments are provided below for illustration.
[0069] Figure 1FIG. 1 is a schematic diagram of a flow chart of a method for evaluating the leakage status of a gas valve device provided by an embodiment of the present invention. Figure 1 As shown, a method for evaluating the leakage state of a gas valve device in this embodiment includes:
[0070] Step S101: Acquire initial audio data within a preset range of the air valve device;
[0071] Step S102: performing noise reduction processing on the initial audio data to obtain air leakage audio data;
[0072] Step S103: obtaining a voiceprint feature corresponding to the air leakage audio data according to a preset recognition model and the air leakage audio data;
[0073] Step S104: Based on the voiceprint feature and the preset voiceprint feature, it is determined that the air valve device is in a leaking state.
[0074] In one embodiment, a microphone array is used in the embodiment of the present application to collect initial audio data. The microphone array refers to a MEMS (micro-electromechanical system) microphone, which is a microphone array group manufactured based on MEMS technology. In the present application, the microphone array is evenly arranged in the working area where the gas valve device is installed, and is installed in the vicinity of the gas valve as much as possible, but is not connected to the production facility. The microphone array has a good signal-to-noise ratio and a relatively wide frequency domain, but it will also collect noise from the environment in which the gas valve is located.
[0075] The format of the initial audio data is pulse code modulation (PCM). Pulse code modulation is one of the coding methods of digital communication. The main process is to sample analog signals such as voice and image at regular intervals to discretize them, and at the same time round the sampled values to the nearest integer according to the hierarchical unit, and at the same time represent the amplitude of the sampled pulse according to a set of binary codes.
[0076] In the embodiment of the present application, the microphone array can collect all the sounds generated by the air valve leakage, thereby avoiding inaccurate results of air valve leakage detection and status assessment due to incomplete initial audio data collection.
[0077] In the embodiment of the present application, the initial audio data can comprehensively and real-time display the air leakage situation of the air valve, and can provide a basis for judging whether there is an air leakage fault in the air valve and the air leakage status evaluation result.
[0078] The embodiment of the present invention first obtains the initial audio data within a preset range of the air valve device, then performs noise reduction processing on the initial audio data to obtain leakage audio data, and then obtains the voiceprint features corresponding to the leakage audio data based on the preset recognition model and the leakage audio data, and finally compares the voiceprint features with the preset voiceprint features to determine that the air valve device is in a leakage state. The present invention extracts features from the leakage audio data through a preset recognition model, thereby improving the accuracy of the leakage audio data extraction, and can obtain more accurate voiceprint features, and then compares the voiceprint features with the preset voiceprint features, further improving the accuracy of the leakage state assessment of the air valve device. In addition, the present invention uses an artificial intelligence model to assess the leakage state of the air valve device, which not only improves the assessment accuracy, but also realizes the intelligence and automation of the leakage state assessment, thereby avoiding the air valve device causing failures and affecting normal production.
[0079] In one embodiment, the present application uses two noise reduction methods to process the initial audio data to determine the air leakage audio data. Specifically, they include:
[0080] The first method is to remove the environmental noise data in the initial audio data to obtain the air leakage audio data. Specifically, since there is environmental noise in the initial audio data, when using the initial audio data to determine whether there is an air valve leakage fault, it is necessary to reduce the noise of the initial audio data, thereby removing the noise in the initial audio data that interferes with the judgment of the air valve leakage fault due to environmental reasons. In the embodiment of the present application, after the initial audio data is reduced in noise, the air valve leakage audio data is obtained. The air valve leakage audio data is as follows: Figure 2 shown.
[0081] The second method: perform software filtering and noise reduction on the initial audio data to obtain the initial audio data after noise reduction; if the amplitude corresponding to the initial audio data after noise reduction meets the preset amplitude, the initial audio data after noise reduction is used as the leaking audio data. Specifically, firstly, the step of software filtering and noise reduction is adopted, and the initial audio data is processed by software filtering and noise reduction to obtain the first noise-reduced audio data (i.e. the initial audio data after noise reduction). Subsequently, the audio data in the first noise-reduced audio data that is higher than the preset amplitude range is removed, and only the audio data in the first noise-reduced audio data that is within the preset amplitude range is retained.
[0082] For example, the format of the collected initial audio data is set to pcm16, but it is possible that audio data larger than the preset amplitude range is collected during the collection, which will affect the final result of determining whether there is a valve leakage fault. Therefore, the first noise reduction audio data within the preset amplitude range is retained in the embodiment of the present application, so that the initial audio data can be further denoised. Factors in the initial audio data that may affect the final determination of the valve leakage fault are eliminated, thereby improving the accuracy of the valve leakage fault detection method in the embodiment of the present application.
[0083] In one embodiment, the voiceprint features corresponding to the air leakage audio data are extracted using a preset recognition model, specifically including:
[0084] Determine a preset recognition model; use the preset recognition model to extract voiceprint features of the air leakage audio data to obtain the voiceprint features corresponding to the air leakage audio data.
[0085] Specifically, the preset recognition model can be a machine model used for data mining, including a BP neural network model, a support vector machine model, etc., which is not specifically limited here. Among them, for any of the above machine models, when in use, training samples will be used for training to obtain a trained model, and then the test samples will be input into the trained model to determine the preset prediction model. Specifically, an initial recognition model and training sample data are obtained; the training sample data is input into the initial recognition model, and the preset recognition model is obtained when the number of iterations meets the preset number. By extracting voiceprint features through the above model, the accuracy of the voiceprint features can be improved.
[0086] Furthermore, the training sample data is input into the initial recognition model, and the preset number of iterations is met to obtain the preset recognition model, including: inputting the training sample data into the initial recognition model to determine the classification probability corresponding to the training sample data; calculating the difference between the classification probability and the preset classification probability, and determining the loss value of the initial recognition model according to the difference; reversely training the initial recognition model according to the loss value until the number of iterations meets the preset number, and determining the preset recognition model.
[0087] Specifically, the loss value is determined by the difference between the classification probability and the preset classification probability and the loss function. Among them, the loss function includes the square loss function and the absolute value loss function. Among them, the square loss is the most commonly used, but its disadvantage is that it will impose a large penalty on abnormal points, so the robustness is poor. If there are more abnormal points, the absolute value loss performs better, but the disadvantage of the absolute value loss is that it is not continuously differentiable at the absolute value of zero, so it is not easy to optimize. The absolute value loss function is a combination of the two. When the lowest point is less than a pre-specified value a, it becomes a square loss. When it is greater than a, it becomes similar to the absolute value loss, so it is also a loss function with strong robustness. The present invention uses the absolute value loss function to determine the loss value, which can improve the reliability of the preset recognition model and further improve the accuracy of voiceprint feature extraction.
[0088] In one embodiment, determining whether the air valve device is in a leaking state based on the voiceprint feature and the preset voiceprint feature includes: judging whether the voiceprint feature is consistent with the preset voiceprint feature; if the voiceprint feature is inconsistent with the preset voiceprint feature, the air valve device is in a leaking state.
[0089] Specifically, the preset voiceprint feature refers to the voiceprint feature when the air valve device is not leaking. When the voiceprint feature extracted by the preset recognition model is inconsistent with the voiceprint feature when there is no leakage, it indicates that the air valve device is in a leaking state.
[0090] The present invention can determine the leakage state of the air valve device through the method of the above embodiment, but when the leakage state is relatively serious, it is necessary to send an abnormal signal to the client to notify the maintenance personnel to immediately replace the air valve device. The specific implementation method is as follows: determine the state score corresponding to the leakage audio data; if the leakage audio data is inconsistent with the preset audio data and the state score exceeds the preset score, send an abnormal signal to the client.
[0091] Specifically, when the audio data of the valve leakage is inconsistent with the preset audio data of the valve not leaking (preset audio data) and the status score exceeds the preset value (preset score), it means that the audio data generated by the valve leakage is different from the audio data of the valve not failing and the valve must be replaced. In order to enable maintenance personnel to obtain the fault status of the valve leakage, an abnormal signal is sent to the user's client, so that maintenance personnel can handle the valve leakage fault as soon as possible to ensure the normal operation of the automation equipment.
[0092] It should be understood that the order of execution of the steps in the above embodiment does not necessarily mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present invention.
[0093] In one embodiment, Figure 3 As shown, a leakage state assessment device for a gas valve device is provided, comprising: a data acquisition module 31, a noise reduction processing module 32, a feature extraction module 33 and a state determination module 34, wherein:
[0094] The data acquisition module 31 is used to acquire the initial audio data within a preset range of the air valve device;
[0095] A noise reduction processing module 32 is used to perform noise reduction processing on the initial audio data to obtain air leakage audio data;
[0096] A feature extraction module 33, used to obtain a voiceprint feature corresponding to the air leakage audio data according to a preset recognition model and the air leakage audio data;
[0097] The state determination module 34 is used to determine whether the air valve device is in a leaking state based on the voiceprint feature and the preset voiceprint feature.
[0098] In a possible implementation, the noise reduction processing module 32 includes:
[0099] A first noise reduction processing submodule is used to remove environmental noise data from the initial audio data to obtain air leakage audio data;
[0100] or,
[0101] The second noise reduction processing submodule is used to perform software filtering and noise reduction on the initial audio data to obtain the noise-reduced initial audio data;
[0102] The air leakage audio determination submodule is used to use the initial audio data after noise reduction as the air leakage audio data if the amplitude corresponding to the initial audio data after noise reduction meets the preset amplitude.
[0103] In a possible implementation, the feature extraction module 33 includes:
[0104] A model determination submodule is used to determine a preset recognition model;
[0105] The feature extraction submodule is used to extract voiceprint features from the air leakage audio data using a preset recognition model to obtain the voiceprint features corresponding to the air leakage audio data.
[0106] In a possible implementation, the model determination submodule includes:
[0107] A data acquisition unit, used to acquire an initial recognition model and training sample data;
[0108] The model training unit is used to input the training sample data into the initial recognition model, and obtain the preset recognition model when the number of iterations meets the preset number.
[0109] In a possible implementation, the model training unit includes:
[0110] The classification probability determination subunit is used to input the training sample data into the initial recognition model to determine the classification probability corresponding to the training sample data;
[0111] The loss value calculation subunit is used to calculate the difference between the classification probability and the preset classification probability, and determine the loss value of the initial recognition model according to the difference;
[0112] The model determination subunit is used to reversely train the initial recognition model according to the loss value until the number of iterations meets the preset number, and determine the preset recognition model.
[0113] In a possible implementation, the state determination module 34 includes:
[0114] A judgment submodule is used to judge whether the voiceprint feature is consistent with the preset voiceprint feature;
[0115] The state determination submodule is used to determine that the air valve device is in a leaking state if the voiceprint feature is inconsistent with the preset voiceprint feature.
[0116] In a possible implementation, the method further includes:
[0117] A score determination module, used to determine a status score corresponding to the air leakage audio data;
[0118] The abnormality judgment module is used to send an abnormality signal to the client if the air leakage audio data is inconsistent with the preset audio data and the status score exceeds the preset score.
[0119] Figure 4 is a schematic diagram of a terminal provided by an embodiment of the present invention. Figure 4 As shown, the terminal 4 of this embodiment includes: a processor 40, a memory 41, and a computer program 42 stored in the memory 41 and executable on the processor 40. When the processor 40 executes the computer program 42, the steps in the above-mentioned gas valve device leakage state assessment method embodiments are implemented, for example Figure 1 Alternatively, when the processor 40 executes the computer program 42, the functions of each module / unit in the above-mentioned device embodiments are implemented, for example Figure 3 Functionality of the modules / units 31 to 34 shown.
[0120] Exemplarily, the computer program 42 may be divided into one or more modules / units, one or more modules / units are stored in the memory 41 and executed by the processor 40 to implement the present invention. One or more modules / units may be a series of computer program instruction segments capable of implementing specific functions, and the instruction segments are used to describe the execution process of the computer program 42 in the terminal 4. For example, the computer program 42 may be divided into Figure 3 Modules / units 31 to 34 are shown.
[0121] The terminal 4 may be a computing device such as a desktop computer, a notebook, a PDA, or a cloud server. The terminal 4 may include, but is not limited to, a processor 40 and a memory 41. Those skilled in the art will appreciate that Figure 4 It is only an example of terminal 4 and does not constitute a limitation on terminal 4. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, the terminal may also include input and output devices, network access devices, buses, etc.
[0122] The processor 40 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.
[0123] The memory 41 may be an internal storage unit of the terminal 4, such as a hard disk or memory of the terminal 4. The memory 41 may also be an external storage device of the terminal 4, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the terminal 4. Further, the memory 41 may also include both an internal storage unit of the terminal 4 and an external storage device. The memory 41 is used to store computer programs and other programs and data required by the terminal. The memory 41 may also be used to temporarily store data that has been output or is to be output.
[0124] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.
[0125] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.
[0126] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.
[0127] In the embodiments provided by the present invention, it should be understood that the disclosed devices / terminals and methods can be implemented in other ways. For example, the device / terminal embodiments described above are only schematic, for example, the division of modules or units is only a logical function division, and there may be other division methods in actual implementation, such as 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 mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.
[0128] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
[0129] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.
[0130] If the integrated module / 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 this understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned data cleaning method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, the computer-readable medium does not include electric carrier signals and telecommunication signals.
[0131] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention, and should be included in the protection scope of the present invention.
Claims
1. A method for evaluating the leakage state of a gas valve device, characterized in that: include: Acquire initial audio data within a preset range of the gas valve device; wherein the format of the initial audio data is a pulse code modulation format, and the initial audio data is acquired based on a MEMS microphone; The initial audio data is subjected to noise reduction processing to obtain air leakage audio data; specifically comprising: performing software filtering and noise reduction on the initial audio data to obtain noise-reduced initial audio data; removing audio data higher than a preset amplitude range from the noise-reduced initial audio data to obtain the air leakage audio data; Acquire an initial recognition model and training sample data; input the training sample data into the initial recognition model to determine the classification probability corresponding to the training sample data; calculate the difference between the classification probability and the preset classification probability, and determine the loss value of the initial recognition model according to the difference; reversely train the initial recognition model according to the loss value until the number of iterations to be completed meets the preset number, and determine the preset recognition model; Using the preset recognition model to extract voiceprint features from the air leakage audio data, to obtain voiceprint features corresponding to the air leakage audio data; Based on the voiceprint feature and a preset voiceprint feature, determining that the air valve device is in a leaking state; Determine a status score corresponding to the air leakage audio data; If the air leakage audio data is inconsistent with the preset audio data and the status score exceeds the preset score, an abnormal signal is sent to the client.
2. The method for evaluating the leakage state of a gas valve device according to claim 1, characterized in that: The determining that the air valve device is in a leaking state based on the voiceprint feature and a preset voiceprint feature includes: Determining whether the voiceprint feature is consistent with a preset voiceprint feature; If the voiceprint feature is inconsistent with the preset voiceprint feature, the air valve device is in a leaking state.
3. A device for evaluating the leakage state of a gas valve device, characterized in that: The device comprises: A data acquisition module, used to acquire initial audio data within a preset range of the air valve device; A noise reduction processing module is used to perform noise reduction processing on the initial audio data to obtain air leakage audio data; specifically comprising: performing software filtering and noise reduction on the initial audio data to obtain noise-reduced initial audio data; removing audio data above a preset amplitude range from the noise-reduced initial audio data to obtain the air leakage audio data; A feature extraction module is used to obtain an initial recognition model and training sample data; input the training sample data into the initial recognition model to determine the classification probability corresponding to the training sample data; calculate the difference between the classification probability and the preset classification probability, and determine the loss value of the initial recognition model according to the difference; reversely train the initial recognition model according to the loss value until the number of iterations to be completed meets the preset number of iterations, and determine the preset recognition model; The feature extraction module is further used to extract voiceprint features from the air leakage audio data using the preset recognition model to obtain voiceprint features corresponding to the air leakage audio data; a state determination module, configured to determine that the air valve device is in a leaking state based on the voiceprint feature and a preset voiceprint feature; The status determination module is further used to determine the status score corresponding to the air leakage audio data; if the air leakage audio data is inconsistent with the preset audio data and the status score exceeds the preset score, an abnormal signal is sent to the client.
4. A terminal comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the computer program, the steps of the method for evaluating the leakage state of the gas valve device according to claim 1 or 2 are implemented.
5. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method for evaluating the leakage state of the gas valve device according to claim 1 or 2 are implemented.
