Valve internal leakage detection method and device, storage medium and electronic equipment

Abstract

The present disclosure relates to a valve leakage detection method and device, a storage medium and an electronic device. The method comprises: acquiring a temperature value corresponding to a valve outlet; in the case that the temperature value is less than a preset temperature threshold, acquiring an acoustic emission signal corresponding to the valve outlet; and determining whether the valve has a leakage according to the acoustic emission signal and a valve leakage identification model. Thus, the leakage of the valve can be accurately and effectively detected, and the safety monitoring of the valve and the pipeline is ensured.

Description

Technical Field

[0001] This disclosure relates to the field of valve internal leakage detection technology, specifically to a valve internal leakage detection method, apparatus, storage medium, and electronic equipment. Background Technology

[0002] Currently, valves, as control devices in fluid pipelines, play a crucial role in pipeline transportation. Internal leakage in valves, a common problem in industries such as petrochemicals, thermal power, and nuclear power, can affect the safety of unit operation and the economics of the unit system.

[0003] In the existing technology, whether a valve has internal leakage is detected by measuring the relevant temperature at the valve. However, since some valves are under negative pressure, if leakage occurs, the steam will spread rapidly. In this case, it is difficult to accurately detect the leakage of the valve by measuring the temperature. Summary of the Invention

[0004] The purpose of this disclosure is to provide a valve internal leakage detection method, device, storage medium, and electronic equipment to accurately and effectively detect valve leakage and ensure the safety monitoring of valves and pipelines.

[0005] To achieve the above objectives, in a first aspect, this disclosure provides a valve internal leakage detection method, comprising: acquiring a temperature value corresponding to the valve outlet; acquiring an acoustic emission signal corresponding to the valve outlet when the temperature value is less than a preset temperature threshold; and determining whether the valve has internal leakage based on the acoustic emission signal and a valve internal leakage identification model.

[0006] Optionally, determining whether the valve has internal leakage based on the acoustic emission signal and the valve internal leakage identification model includes: determining the leakage characteristic parameters corresponding to the valve based on the acoustic emission signal; inputting the leakage characteristic parameters into the valve internal leakage identification model to obtain the target level output by the valve internal leakage identification model, wherein the valve internal leakage identification model includes a non-leakage level and multiple leakage levels, the target level is any one of the non-leakage level and multiple leakage levels, each leakage level is used to characterize the leakage amount corresponding to the valve internal leakage, and the higher the leakage level, the greater the leakage amount; if the target level is a leakage level, then it is determined that the valve has internal leakage, and the target level is used as the leakage level of the valve internal leakage.

[0007] Optionally, determining the leakage characteristic parameters corresponding to the valve based on the acoustic emission signal includes: decomposing the acoustic emission signal based on wavelet packet transform to obtain multiple frequency bands corresponding to the acoustic emission signal; determining the energy characteristics corresponding to each frequency band based on the acoustic emission signal, and using the energy characteristics corresponding to each frequency band as the leakage characteristic parameters.

[0008] Optionally, the leakage characteristic parameters further include at least one of the following: the amplitude corresponding to the acoustic emission signal, the ring count corresponding to the acoustic emission signal, the average signal level corresponding to the acoustic emission signal, and the root mean square value corresponding to the acoustic emission signal.

[0009] Optionally, the method further includes: if the temperature value is greater than or equal to the temperature threshold, determining that the valve has internal leakage, and determining that the leakage level of the valve is the highest level, wherein the leakage amount represented by the highest level is greater than or equal to the leakage amount represented by each leakage level output by the valve internal leakage identification model.

[0010] Optionally, the valve internal leakage identification model is determined by: obtaining a training sample set, wherein each training sample in the training sample set includes training leakage feature parameters and a labeling level corresponding to the training leakage feature parameters; training the model using the training leakage feature parameters as the input of the model and the labeling level as the target output of the model; and determining the trained model as the valve internal leakage identification model.

[0011] Optionally, the method further includes: displaying a graph corresponding to the temperature value; and when it is determined that the valve has internal leakage, displaying a prompt message and / or outputting an audible prompt message on the graph.

[0012] In a second aspect, this disclosure provides a valve internal leakage detection device, comprising: a first acquisition module for acquiring a temperature value corresponding to the valve outlet; a second acquisition module for acquiring an acoustic emission signal corresponding to the valve outlet when the temperature value is less than a preset temperature threshold; and a first determination module for determining whether the valve has internal leakage based on the acoustic emission signal and a valve internal leakage identification model.

[0013] Thirdly, this disclosure provides a computer-readable medium having a computer program stored thereon that, when executed by a processor, implements the steps of any of the methods described in the first aspect.

[0014] Fourth aspect: This disclosure provides an electronic device, comprising: a memory having a computer program stored thereon; and a processor for executing the computer program in the memory to implement the steps of any of the methods described in the first aspect.

[0015] In the above technical solution, when detecting internal leakage in a valve, the temperature value at the valve outlet is first determined. When the temperature value is insufficient for accurate internal leakage identification, the acoustic emission signal at the valve outlet is acquired for internal leakage identification. This improves the accuracy of internal leakage identification, avoiding errors caused by rapid steam diffusion, thus enabling accurate and effective monitoring of valve and pipeline operation. Furthermore, based on the acoustic emission signal and the internal leakage identification model, the identification result can be obtained directly and quickly, simplifying the data processing flow, improving the efficiency and real-time nature of internal leakage identification, and providing data support for users to promptly detect leaks and formulate corresponding measures.

[0016] Other features and advantages of this disclosure will be described in detail in the following detailed description section. Attached Figure Description

[0017] The accompanying drawings are provided to further illustrate the present disclosure and form part of the specification. They are used together with the following detailed description to explain the present disclosure, but do not constitute a limitation thereof. In the drawings:

[0018] Figure 1 This is a flowchart of a valve internal leakage detection method provided in an exemplary embodiment of this disclosure;

[0019] Figure 2 This is a block diagram of a valve internal leakage detection device provided in an exemplary embodiment of this disclosure;

[0020] Figure 3 This is a schematic diagram of the structure of an electronic device provided in an exemplary embodiment of the present disclosure;

[0021] Figure 4 This is a schematic diagram of the structure of an electronic device provided in an exemplary embodiment of the present disclosure. Detailed Implementation

[0022] The specific embodiments of this disclosure will be described in detail below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are for illustration and explanation only and are not intended to limit this disclosure.

[0023] It should be noted that all actions involving the acquisition of signals, information, or data in this disclosure are carried out in compliance with the relevant data protection laws and policies of the country where the location is situated, and with authorization from the owner of the relevant device.

[0024] This embodiment provides a method for detecting internal leakage in valves. Figure 1 A flowchart of a valve internal leakage detection method provided in an exemplary embodiment, such as... Figure 1The method may include the following steps:

[0025] Step S101: Obtain the temperature value corresponding to the valve outlet.

[0026] For example, valves on high-temperature, high-pressure steam pipelines, such as steam traps, are more prone to internal leakage due to the harsh working environment. For instance, a steam trap used in a main reheat system, if it leaks, will allow a large amount of high-quality steam to leak into the condenser, affecting the economics of the unit's thermal system. It may also increase the condenser's heat load and cold source losses, and reduce the condenser vacuum, impacting the safe operation of the unit. Therefore, in this step, a temperature sensor, such as a thermocouple temperature sensor, can be installed on the downstream pipeline to collect real-time temperature data at the valve outlet.

[0027] Step S102: When the temperature value is less than the preset temperature threshold, acquire the acoustic emission signal corresponding to the valve outlet.

[0028] The temperature threshold can be set based on actual application scenarios and empirical values, and this disclosure does not limit it. If the temperature value is lower than the preset temperature threshold, internal leakage may be difficult to detect due to the rapid diffusion of leaked vapor. Therefore, in this embodiment, the acoustic emission signal at the valve outlet can be further acquired to further determine the leakage status of the valve based on the acoustic emission signal.

[0029] For example, an acoustic emission sensor can be installed on the valve body downstream of the valve to collect acoustic emission signals at the valve outlet.

[0030] Step S103: Determine whether the valve has internal leakage based on the acoustic emission signal and the valve internal leakage identification model.

[0031] The valve internal leakage identification model can be a neural network-based model used to detect whether a valve has internal leakage. For example, the neural network can be a BP (Back Propagation) neural network. For instance, the acoustic emission signal can be input into the valve internal leakage identification model, thereby determining whether the valve has internal leakage based on the output of the model.

[0032] In the above technical solution, when detecting internal leakage in a valve, the temperature value at the valve outlet is first determined. When the temperature value is insufficient for accurate internal leakage identification, the acoustic emission signal at the valve outlet is acquired for internal leakage identification. This improves the accuracy of internal leakage identification, avoiding errors caused by rapid steam diffusion, thus enabling accurate and effective monitoring of valve and pipeline operation. Furthermore, based on the acoustic emission signal and the internal leakage identification model, the identification result can be obtained directly and quickly, simplifying the data processing flow, improving the efficiency and real-time nature of internal leakage identification, and providing data support for users to promptly detect leaks and formulate corresponding measures.

[0033] In one possible embodiment, an exemplary implementation of determining whether a valve has internal leakage based on acoustic emission signals and a valve internal leakage identification model includes the following steps:

[0034] Based on the acoustic emission signal, the leakage characteristic parameters corresponding to the valve are determined. These leakage characteristic parameters can be feature parameters related to internal leakage of the valve obtained through feature analysis and extraction of the acoustic emission information.

[0035] Then, the leakage characteristic parameters are input into the valve internal leakage identification model to obtain the target level output by the valve internal leakage identification model. The valve internal leakage identification model includes a non-leakage level and multiple leakage levels. The target level is any one of the non-leakage level and multiple leakage levels. Each leakage level is used to characterize the leakage amount corresponding to the valve internal leakage. The higher the leakage level, the greater the leakage amount.

[0036] For example, leakage levels can include multiple types such as large, medium, small, and micro, and this classification can be set based on actual applications. The leakage levels are ordered from highest to lowest as large, medium, small, and micro, with the corresponding leakage amounts decreasing progressively.

[0037] If the target level is a non-leakage level, then the valve is determined to be free of internal leakage and its operation is safe. If the target level is a leakage level, then the valve is determined to have internal leakage, and the target level is used as the leakage level for the internal leakage of the valve.

[0038] For example, if the target level output by the valve internal leakage identification model is medium, it can be determined that the valve has internal leakage and the leakage level is medium. Thus, while alerting the user to the valve internal leakage, the user can also be informed of the leakage level, so that the user can formulate a response based on the leakage situation and resolve the internal leakage in a timely manner. This allows for accurate detection and classification of internal leakage, further improving the accuracy and precision of valve internal leakage detection results and enhancing the user experience.

[0039] Optionally, an exemplary implementation of determining the leakage characteristic parameters corresponding to the valve based on the acoustic emission signal is as follows, which may include:

[0040] The acoustic emission signal is decomposed based on wavelet packet transform to obtain multiple frequency bands corresponding to the acoustic emission signal.

[0041] In this process, a continuous periodic signal can be decomposed into a linear combination of trigonometric function signals with different frequencies. Wavelet packet transform can then be used to project the acoustic emission signal from the time domain onto different frequency bands in the frequency domain to achieve this decomposition, obtaining multiple corresponding frequency bands. Wavelet packet transform uses a set of orthogonal, rapidly decaying wavelet function bases for signal fitting.

[0042] Based on the acoustic emission signal, the energy characteristics corresponding to each frequency band are determined, and the energy characteristics corresponding to each frequency band are used as the leakage characteristic parameters.

[0043] When internal leakage occurs in a valve, the energy of the acoustic emission signal changes in each frequency band. Therefore, the energy characteristics of each frequency band can be used as leakage characteristic parameters to ensure that the leakage characteristic parameters match the valve state, so as to accurately determine whether the valve has internal leakage based on the leakage characteristic parameters.

[0044] The above scheme can decompose the acoustic emission signal into multiple frequency bands based on wavelet packet transform, and use the energy characteristics of each frequency band as leakage characteristic parameters. This allows the features of abrupt change points in the acoustic emission signal to be extracted, effectively distinguishing between valve internal leakage related signals and external interference signals in the acoustic emission signal. This provides accurate data support for the analysis of valve internal leakage and improves the sensitivity and accuracy of valve internal leakage detection.

[0045] As another example, the leakage characteristic parameters also include at least one of the following: the amplitude corresponding to the acoustic emission signal, the ring count corresponding to the acoustic emission signal, the average signal level corresponding to the acoustic emission signal, and the root mean square value corresponding to the acoustic emission signal. These parameters can be determined through statistical analysis of the acoustic emission signal, such as obtaining the amplitude and ring count corresponding to the acoustic emission signal based on signal analysis, and determining the average signal level and root mean square value through statistical analysis of the acoustic emission signal, thereby identifying auxiliary characteristics for judging internal leakage in the valve.

[0046] The above scheme can further determine more dimensional leakage characteristic parameters from acoustic emission signals, increase the input features of the valve internal leakage identification model, and take into account the influence of leakage characteristic parameters on valve internal leakage from multiple perspectives. This avoids the occurrence of accidental results to a certain extent and improves the accuracy of the output results of the valve internal leakage identification model.

[0047] In one possible embodiment, the method may further include:

[0048] If the temperature value is greater than or equal to the temperature threshold, it is determined that the valve has internal leakage, and the leakage level of the valve is determined to be the highest level, wherein the leakage amount represented by the highest level is greater than or equal to the leakage amount represented by each leakage level output by the valve internal leakage identification model.

[0049] As mentioned above, if an internal leak occurs in a valve, the leaking steam will diffuse rapidly. If the temperature value obtained is greater than or equal to the temperature threshold, it indicates that the valve has an internal leak, and the leakage is significant. In this case, the valve can be directly identified as having an internal leak and the leak level can be determined as the highest level. Only temperature detection is required in this situation; there is no need to analyze or detect the acoustic emission signal to obtain the leak result and leak level, ensuring the accuracy of valve internal leak detection and improving detection efficiency.

[0050] In one possible embodiment, the valve internal leakage identification model is determined in the following manner:

[0051] Obtain a training sample set, wherein each training sample in the training sample set includes training leakage feature parameters and a corresponding labeling level for the training leakage feature parameters. The labeling level can be a non-leaking level or any of multiple leakage levels.

[0052] As an example, acoustic emission signals of the valve can be collected in advance under various opening conditions and non-leakage conditions by adjusting the valve opening. Leakage feature parameters corresponding to these acoustic emission signals can then be extracted as training leakage feature parameters. The labeling level is determined based on the operating condition corresponding to the acoustic emission signal. If the acoustic emission signal is collected under non-leakage conditions, the labeling level of the training leakage feature parameter corresponding to that acoustic emission signal is determined to be the non-leakage level. Leakage levels can be pre-classified based on valve opening. For example, if the valve opening is in the first range, the leakage level is determined to be a high level; if the valve opening is in the second range, the leakage level is determined to be a medium level. Correspondingly, if the valve opening corresponding to the acoustic emission signal collection is in the first range, the labeling level of the training leakage feature parameter corresponding to that acoustic emission signal can be determined to be a high level, thereby establishing the training sample set required for model training.

[0053] Then, the model is trained using the training leakage feature parameters as input and the labeling level as the target output.

[0054] For example, the model structure can be set according to the actual application scenario. For instance, a backpropagation (BP) neural network with 5 input nodes, 1 output node, and 10 hidden layer nodes can be used as the model. Correspondingly, the training leakage feature parameters can include the five features mentioned above, which are then input into the model to obtain its output. The loss is calculated based on the labeling level corresponding to the output and the training leakage feature parameters, and the model parameters are adjusted using gradient descent based on the loss. During training, the model's learning rate can be optimized, and the above steps are repeated until the loss is within a preset error range.

[0055] The trained model is then designated as the valve internal leakage identification model.

[0056] The above technical solution can be used to collect acoustic emission signals of valves under various operating conditions and label them to obtain training samples for quantitative characterization of valve leakage. Based on these training samples, a valve internal leakage identification model can be obtained to accurately identify valve internal leakage, thereby improving the efficiency and accuracy of valve internal leakage identification.

[0057] In one possible embodiment, the method may further include:

[0058] The graph corresponding to the temperature value can be displayed. For example, the graphs formed by the collected temperature values ​​can be displayed on the screen to allow users to intuitively understand the temperature changes of the valve.

[0059] When it is determined that the valve has internal leakage, a prompt message is displayed on the graph and / or an audible prompt message is output.

[0060] As an example, the audible prompt can be an alarm signal or a voice prompt. The prompt can be displayed on the graph as a marker point. When an internal leak is determined based on a temperature value, the marker point can be displayed directly at the location of that temperature value. When an internal leak is determined based on an acoustic emission signal, the marker point can be displayed at the location of the temperature value closest to the time the acoustic emission signal was collected.

[0061] As another example, a text message such as "The valve has an internal leak!!! The leak level is medium" can be displayed on the page to further alert the user.

[0062] The above technical solution allows the temperature value at the valve outlet to be displayed and monitored via a curve graph. This enables real-time monitoring of the valve's temperature and displays alerts on the graph. It also allows users to understand the leakage situation and its relationship with temperature, further enhancing the user experience.

[0063] Figure 2 This is a block diagram of a valve internal leakage detection device provided in an exemplary embodiment of the present disclosure. The device includes:

[0064] The first acquisition module 201 is used to acquire the temperature value corresponding to the valve outlet.

[0065] The second acquisition module 202 is used to acquire the acoustic emission signal corresponding to the valve outlet when the temperature value is less than a preset temperature threshold.

[0066] The first determining module 203 is used to determine whether the valve has internal leakage based on the acoustic emission signal and the valve internal leakage identification model.

[0067] Optionally, the first determining module 203 includes:

[0068] The first determining submodule is used to determine the leakage characteristic parameters corresponding to the valve based on the acoustic emission signal;

[0069] The first acquisition submodule is used to input the leakage characteristic parameters into the valve internal leakage identification model to obtain the target level output by the valve internal leakage identification model. The valve internal leakage identification model includes a non-leakage level and multiple leakage levels. The target level is any one of the non-leakage level and multiple leakage levels. Each leakage level is used to characterize the leakage amount corresponding to the valve internal leakage. The higher the leakage level, the greater the leakage amount.

[0070] The second determining submodule is used to determine that the valve has internal leakage if the target level is a leakage level, and to use the target level as the leakage level of the valve having internal leakage.

[0071] Optionally, the first determining submodule includes:

[0072] The decomposition submodule is used to decompose the acoustic emission signal based on wavelet packet transform to obtain multiple frequency bands corresponding to the acoustic emission signal;

[0073] The third determining submodule is used to determine the energy characteristics corresponding to each frequency band based on the acoustic emission signal, and to use the energy characteristics corresponding to each frequency band as the leakage characteristic parameters.

[0074] Optionally, the leakage characteristic parameters further include at least one of the following:

[0075] The amplitude corresponding to the acoustic emission signal, the ring count corresponding to the acoustic emission signal, the average signal level corresponding to the acoustic emission signal, and the root mean square value corresponding to the acoustic emission signal.

[0076] Optionally, the device further includes:

[0077] The second determining module is used to determine that the valve has internal leakage when the temperature value is greater than or equal to the temperature threshold, and to determine that the leakage level of the valve is the highest level, wherein the leakage amount represented by the highest level is greater than or equal to the leakage amount represented by each leakage level output by the valve internal leakage identification model.

[0078] Optionally, the valve internal leakage identification model is determined by a training module, which includes:

[0079] The second acquisition submodule acquires a training sample set, wherein each training sample in the training sample set includes training leakage feature parameters and the labeling level corresponding to the training leakage feature parameters;

[0080] The processing submodule is used to train the model by taking the training leakage feature parameters as input to the model and the labeling level as the target output of the model.

[0081] The fourth determination submodule is used to determine the trained model as the valve internal leakage identification model.

[0082] Optionally, the device further includes:

[0083] The first display module is used to display a graph corresponding to the temperature value;

[0084] The second display module is used to display prompt information and / or output audible prompt information on the curve graph when it is determined that the valve has internal leakage.

[0085] Regarding the apparatus in the above embodiments, the specific manner in which each module performs its operation has been described in detail in the embodiments related to the method, and will not be elaborated upon here.

[0086] Figure 3 This is a block diagram illustrating an electronic device 700 according to an exemplary embodiment. Figure 3 As shown, the electronic device 700 may include a processor 701 and a memory 702. The electronic device 700 may also include one or more of a multimedia component 703, an input / output (I / O) interface 704, and a communication component 705.

[0087] The processor 701 controls the overall operation of the electronic device 700 to complete all or part of the steps in the valve internal leakage detection method described above. The memory 702 stores various types of data to support the operation of the electronic device 700. This data may include, for example, instructions for any application or method operating on the electronic device 700, and application-related data such as contact data, sent and received messages, pictures, audio, video, etc. The memory 702 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read-Only Memory (EPROM), Programmable Read-Only Memory (PROM), Read-Only Memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. Multimedia component 703 may include a screen and an audio component. The screen may be, for example, a touchscreen, and the audio component is used to output and / or input audio signals. For example, the audio component may include a microphone for receiving external audio signals. The received audio signals may be further stored in memory 702 or transmitted via communication component 705. The audio component also includes at least one speaker for outputting audio signals. I / O interface 704 provides an interface between processor 701 and other interface modules, such as a keyboard, mouse, buttons, etc. These buttons may be virtual or physical buttons. Communication component 705 is used for wired or wireless communication between the electronic device 700 and other devices. Wireless communication, such as Wi-Fi, Bluetooth, Near Field Communication (NFC), 2G, 3G, 4G, NB-IoT, eMTC, or other 5G technologies, or combinations thereof, is not limited here. Therefore, the corresponding communication component 705 may include: a Wi-Fi module, a Bluetooth module, an NFC module, etc.

[0088] In an exemplary embodiment, the electronic device 700 may be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the valve internal leakage detection method described above.

[0089] In another exemplary embodiment, a computer-readable storage medium including program instructions is also provided, which, when executed by a processor, implement the steps of the valve internal leakage detection method described above. For example, the computer-readable storage medium may be the memory 702 including program instructions described above, which may be executed by the processor 701 of the electronic device 700 to complete the valve internal leakage detection method described above.

[0090] Figure 4 This is a block diagram illustrating an electronic device 1900 according to an exemplary embodiment. For example, the electronic device 1900 may be provided as a server. (Refer to...) Figure 4 The electronic device 1900 includes a processor 1922, which may be one or more, and a memory 1932 for storing computer programs executable by the processor 1922. The computer program stored in the memory 1932 may include one or more modules, each corresponding to a set of instructions. Furthermore, the processor 1922 may be configured to execute the computer program to perform the valve internal leakage detection method described above.

[0091] Additionally, the electronic device 1900 may also include a power supply component 1926 and a communication component 1950. The power supply component 1926 can be configured to perform power management of the electronic device 1900, and the communication component 1950 can be configured to enable communication of the electronic device 1900, such as wired or wireless communication. Furthermore, the electronic device 1900 may also include an input / output (I / O) interface 1958. The electronic device 1900 can operate on an operating system, such as Windows Server, stored in memory 1932. TM Mac OS X TM Unix TM Linux TM etc.

[0092] In another exemplary embodiment, a computer-readable storage medium including program instructions is also provided, which, when executed by a processor, implement the steps of the valve internal leakage detection method described above. For example, the non-transitory computer-readable storage medium may be the memory 1932 including the program instructions described above, which may be executed by the processor 1922 of the electronic device 1900 to complete the valve internal leakage detection method described above.

[0093] In another exemplary embodiment, a computer program product is also provided, comprising a computer program executable by a programmable device, the computer program having a code portion for performing the valve internal leakage detection method described above when executed by the programmable device.

[0094] The preferred embodiments of this disclosure have been described in detail above with reference to the accompanying drawings. However, this disclosure is not limited to the specific details of the above embodiments. Within the scope of the technical concept of this disclosure, various simple modifications can be made to the technical solutions of this disclosure, and these simple modifications all fall within the protection scope of this disclosure.

[0095] It should also be noted that the various specific technical features described in the above specific embodiments can be combined in any suitable manner without contradiction. In order to avoid unnecessary repetition, this disclosure will not describe the various possible combinations separately.

[0096] Furthermore, various different embodiments of this disclosure can be combined in any way, as long as they do not violate the spirit of this disclosure, they should also be regarded as the content disclosed in this disclosure.

Claims

1. A method of detecting valve internal leakage, the method comprising: The method comprises: acquiring a temperature value corresponding to the valve outlet; in the case where the temperature value is less than a preset temperature threshold, acquiring an acoustic emission signal corresponding to the valve outlet; determining whether the valve has internal leakage according to the acoustic emission signal and a valve internal leakage identification model; in the case where the temperature value is greater than or equal to the temperature threshold, determining that the valve has internal leakage and determining that the leakage level of the valve is the highest level, wherein the highest level represents a leakage amount greater than or equal to the leakage amount represented by each leakage level output by the valve internal leakage identification model; wherein the determination of whether the valve has internal leakage according to the acoustic emission signal and the valve internal leakage identification model comprises: determining a leakage characteristic parameter corresponding to the valve according to the acoustic emission signal; inputting the leakage characteristic parameter into the valve internal leakage identification model to obtain a target level output by the valve internal leakage identification model, wherein the valve internal leakage identification model comprises a non-leakage level and a plurality of leakage levels, the target level is any one of the non-leakage level and the plurality of leakage levels, each leakage level is used to represent a leakage amount corresponding to the internal leakage of the valve, and a higher leakage level represents a larger leakage amount; if the target level is a leakage level, it is determined that the valve has internal leakage, and the target level is taken as the leakage level of the internal leakage of the valve; wherein the determination of the leakage characteristic parameter corresponding to the valve according to the acoustic emission signal comprises: decomposing the acoustic emission signal based on wavelet packet transform to obtain a plurality of frequency bands corresponding to the acoustic emission signal; determining an energy characteristic corresponding to each frequency band according to the acoustic emission signal, and taking the energy characteristic corresponding to each frequency band as the leakage characteristic parameter.

2. The method of claim 1, wherein, The leakage characteristic parameter further comprises at least one of the following: an amplitude corresponding to the acoustic emission signal, a ring count corresponding to the acoustic emission signal, an average signal level corresponding to the acoustic emission signal, and a root mean square value corresponding to the acoustic emission signal.

3. The method of claim 1, wherein, The valve internal leakage identification model is determined by the following method: acquiring a training sample set, wherein each training sample in the training sample set comprises training leakage characteristic parameters and a labeled level corresponding to the training leakage characteristic parameters; training the model by taking the training leakage characteristic parameters as the input of the model and taking the labeled level as the target output of the model; determining the trained model as the valve internal leakage identification model.

4. The method of claim 1, wherein, The method further comprises: displaying a curve graph corresponding to the temperature value; when it is determined that the valve has internal leakage, displaying prompt information and / or outputting sound prompt information in the curve graph.

5. A valve leakage detection apparatus, characterized by, The device comprises: a first acquisition module for acquiring a temperature value corresponding to the valve outlet; a second acquisition module for acquiring an acoustic emission signal corresponding to the valve outlet in the case where the temperature value is less than a preset temperature threshold; a first determination module for determining whether the valve has internal leakage according to the acoustic emission signal and a valve internal leakage identification model; The second determining module is configured to determine that the valve has internal leakage and determine that a leakage level of the valve is a highest level when the temperature value is greater than or equal to the temperature threshold, wherein the highest level represents a leakage amount greater than or equal to leakage amounts represented by each of the leakage levels output by the valve internal leakage identification model. The first determining module comprises: The first determining sub-module is configured to determine a leakage characteristic parameter corresponding to the valve according to the acoustic emission signal. The first obtaining sub-module is configured to input the leakage characteristic parameter into the valve internal leakage identification model to obtain a target level output by the valve internal leakage identification model, wherein the valve internal leakage identification model comprises a non-leakage level and a plurality of leakage levels, the target level is any one of the non-leakage level and the plurality of leakage levels, each of the leakage levels is used to represent a leakage amount corresponding to the valve internal leakage, and a higher leakage level represents a larger leakage amount. The second determining sub-module is configured to determine that the valve has internal leakage if the target level is a leakage level, and determine the target level as the leakage level of the valve internal leakage. The first determining sub-module comprises: The decomposition sub-module is configured to decompose the acoustic emission signal based on wavelet packet transform to obtain a plurality of frequency bands corresponding to the acoustic emission signal. The third determining sub-module is configured to determine an energy feature corresponding to each of the frequency bands according to the acoustic emission signal, and determine the energy feature corresponding to each of the frequency bands as the leakage characteristic parameter.

6. A computer readable medium having stored thereon a computer program, characterized in that, The program is executed by the processor to implement the steps of the method of any one of claims 1-4.

7. An electronic device, comprising: The program is executed by the processor to implement the steps of the method of any one of claims 1-4. The memory has a computer program stored thereon; The processor is configured to execute the computer program in the memory to implement the steps of the method of any one of claims 1-4.

Images