Pipeline identification method and device, air conditioner, storage medium and computer program product

Abstract

The application discloses a pipeline identification method and device, an air conditioner, a storage medium and a computer program product. The method is applied to identifying whether a to-be-tested pipeline of an equipment is cracked. The pipeline identification method comprises the following steps: acquiring an acoustic emission signal of a to-be-tested pipeline in a pipeline of the equipment; extracting a feature parameter from the acoustic emission signal of the to-be-tested pipeline as an acoustic emission feature parameter of the to-be-tested pipeline; identifying whether the to-be-tested pipeline is cracked by using a pipeline identification model which is obtained by pre-training based on the acoustic emission feature parameter of the to-be-tested pipeline, so as to initiate a prompt message of the to-be-tested pipeline cracking in the case of identifying that the to-be-tested pipeline is cracked. According to the scheme, the acoustic emission technology and the neural network technology are adopted, the pipeline is identified based on the acoustic emission signal of the pipeline of the equipment (such as an air conditioner), whether the pipeline is cracked is identified, and the prompt message is initiated when the pipeline is identified to be cracked, so that measures can be taken, the service life of the pipeline is prolonged, and the normal use of the equipment is ensured.

Description

Technical Field

[0001] This invention belongs to the field of pipeline identification technology, specifically relating to a pipeline identification method, device, air conditioner, storage medium, and computer program product, and particularly to a fatigue crack identification method, device, air conditioner, storage medium, and computer program product for air conditioning pipelines based on acoustic emission technology. Background Technology

[0002] Vibration in equipment (such as air conditioning) piping significantly impacts the reliability and noise level of the unit. Air conditioning piping vibration is typically caused by compressor vibration. During long-term operation, the piping material gradually fatigues due to multiple factors, including compressor vibration, temperature changes, and pressure fluctuations. This increases stress on the piping, leading to cracks at weld points and potentially causing rupture or damage. However, current systems often fail to detect cracks until they occur, impacting both the lifespan of the piping and the normal operation of the air conditioner.

[0003] The above content is only used to help understand the technical solution of the present invention and does not represent an admission that the above content is prior art. Summary of the Invention

[0004] The purpose of this invention is to provide a pipeline identification method, device, air conditioner, storage medium, and computer program product to solve the problem that fatigue cracks in pipelines caused by excessive stress in equipment (such as air conditioners) cannot be detected, affecting the service life of the pipelines and the normal use of the equipment. This invention achieves the effect of identifying whether a pipeline is cracked based on the acoustic emission signal of the equipment (such as air conditioners) pipeline by employing acoustic emission technology and neural network technology, and issuing an alert message when a crack is detected, so that measures can be taken to extend the service life of the pipeline and ensure the normal use of the equipment.

[0005] This invention provides a pipeline identification method for identifying whether a pipeline under test in a device is cracked. The pipeline identification method includes: acquiring the acoustic emission signal of the pipeline under test in the pipeline of the device; extracting feature parameters from the acoustic emission signal of the pipeline under test as acoustic emission feature parameters of the pipeline under test; and identifying whether the pipeline under test is cracked based on the acoustic emission feature parameters of the pipeline under test using a pre-trained pipeline identification model, so as to initiate a cracked pipeline under test alert message when the crack is detected.

[0006] In some implementations, the training process of the pre-trained pipeline identification model includes: during an experiment to detect cracks in the experimental pipeline, collecting acoustic emission signals of the experimental pipeline and collecting crack parameters of the experimental pipeline; extracting feature parameters from the acoustic emission signals of the experimental pipeline as acoustic emission feature parameters of the experimental pipeline; using the acoustic emission feature parameters and crack parameters of the experimental pipeline as training samples, and using a preset neural network model as the base model; using the acoustic emission feature parameters of the experimental pipeline as input parameters of the base model, and using the crack parameters of the experimental pipeline as output parameters of the base model, performing neural network training to obtain the required pipeline identification model.

[0007] In some embodiments, extracting feature parameters from the acoustic emission signal of the pipeline under test as acoustic emission feature parameters of the pipeline under test includes: converting the acoustic emission signal of the pipeline under test into an electrical signal to obtain an acoustic emission electrical signal of the pipeline under test; using wavelet packet analysis to extract features from the acoustic emission electrical signal of the pipeline under test to obtain feature parameters, which are denoted as acoustic emission feature parameters of the pipeline under test; and / or, if the training process of the pre-trained pipeline identification model includes extracting feature parameters from the acoustic emission signal of the experimental pipeline, extracting feature parameters from the acoustic emission signal of the experimental pipeline as acoustic emission feature parameters of the experimental pipeline includes: converting the acoustic emission signal of the experimental pipeline into an electrical signal to obtain an acoustic emission electrical signal of the experimental pipeline; using wavelet packet analysis to extract features from the acoustic emission electrical signal of the experimental pipeline to obtain feature parameters, which are denoted as acoustic emission feature parameters of the experimental pipeline.

[0008] In some embodiments, the experimental process for detecting cracks in experimental pipelines includes: building a finite element model of the experimental pipeline in the equipment; using the finite element model to perform simulation analysis on the experimental pipeline to determine the location in the experimental pipeline where a predetermined degree of fracture or slippage occurs, which is recorded as the dangerous location of the experimental pipeline; collecting acoustic emission signals from the dangerous location of the experimental pipeline and within the set area of ​​the dangerous location of the experimental pipeline, and collecting cracking parameters of the experimental pipeline.

[0009] In some embodiments, acquiring the acoustic emission signal of the test pipeline in the pipeline of the device includes: acquiring the acoustic emission signal of the test pipeline collected by a pre-set first acoustic emission signal acquisition system; wherein the first acoustic emission signal acquisition system is pre-set at a preset crack point on the test pipeline; and / or, collecting the acoustic emission signal of the test pipeline from a dangerous location of the test pipeline and a set area of ​​the dangerous location of the test pipeline includes: collecting the acoustic emission signal of the test pipeline collected by a pre-set second acoustic emission signal acquisition system; wherein the second acoustic emission signal acquisition system is pre-set at a dangerous location of the test pipeline and a set area of ​​the dangerous location of the test pipeline.

[0010] In some implementations, when the training process of the pre-trained pipeline identification model includes extracting feature parameters from the acoustic emission signals of the experimental pipeline, the acoustic emission feature parameters of the pipeline under test and the acoustic emission feature parameters of the experimental pipeline include: time-domain parameters of the acoustic emission electrical signal of the corresponding pipeline, frequency-domain parameters of the acoustic emission electrical signal of the corresponding pipeline, and energy parameters of the acoustic emission electrical signal of the corresponding pipeline; wherein, the time-domain parameters of the acoustic emission electrical signal of the corresponding pipeline include at least one of the following: voltage amplitude of the acoustic emission electrical signal of the corresponding pipeline, voltage rise time of the acoustic emission electrical signal of the corresponding pipeline, voltage duration of the acoustic emission electrical signal of the corresponding pipeline, and vibration within the voltage duration of the acoustic emission electrical signal of the corresponding pipeline. The count value of the bell; the energy parameters of the acoustic emission signal of the corresponding pipeline, including at least one of the following: the total energy of the acoustic emission signal of the corresponding pipeline, the frequency band energy of the acoustic emission signal of the corresponding pipeline in the preset frequency band, and the proportion of the frequency band energy of the acoustic emission signal of the corresponding pipeline in the preset frequency band to the total energy; the frequency domain parameters of the acoustic emission signal of the corresponding pipeline, including at least one of the following: the frequency of the acoustic emission signal of the corresponding pipeline, and the pulse factor of the acoustic emission signal of the corresponding pipeline; wherein, the frequency of the acoustic emission signal of the corresponding pipeline includes at least one of the following: the initial frequency of the acoustic emission signal of the corresponding pipeline, the peak frequency of the acoustic emission signal of the corresponding pipeline, the average frequency of the acoustic emission signal of the corresponding pipeline, and the inverse frequency of the acoustic emission signal of the corresponding pipeline.

[0011] In conjunction with the above method, another aspect of the present invention provides a pipeline identification device for identifying whether a pipeline under test in a device is cracked; the pipeline identification device includes: an acquisition unit configured to acquire an acoustic emission signal of the pipeline under test in the pipeline of the device; a control unit configured to extract feature parameters from the acoustic emission signal of the pipeline under test as acoustic emission feature parameters of the pipeline under test; the control unit is further configured to identify whether the pipeline under test is cracked based on the acoustic emission feature parameters of the pipeline under test and using a pre-trained pipeline identification model, so as to initiate a cracked pipeline under test reminder message when the cracked pipeline under test is detected.

[0012] In some embodiments, the training process of the pre-trained pipeline identification model in the control unit includes: collecting acoustic emission signals and cracking parameters of the experimental pipeline during an experiment to detect cracks in the experimental pipeline; extracting feature parameters from the acoustic emission signals of the experimental pipeline as acoustic emission feature parameters of the experimental pipeline; using the acoustic emission feature parameters and cracking parameters of the experimental pipeline as training samples, and using a preset neural network model as the base model; using the acoustic emission feature parameters of the experimental pipeline as input parameters of the base model, and using the cracking parameters of the experimental pipeline as output parameters of the base model, performing neural network training to obtain the required pipeline identification model.

[0013] In some embodiments, the control unit extracts feature parameters from the acoustic emission signal of the pipeline under test as acoustic emission feature parameters of the pipeline under test, including: converting the acoustic emission signal of the pipeline under test into an electrical signal to obtain an acoustic emission electrical signal of the pipeline under test; using wavelet packet analysis to extract features from the acoustic emission electrical signal of the pipeline under test to obtain feature parameters, which are denoted as acoustic emission feature parameters of the pipeline under test; and / or, if the training process of the pre-trained pipeline identification model includes extracting feature parameters from the acoustic emission signal of the experimental pipeline, the control unit extracts feature parameters from the acoustic emission signal of the experimental pipeline as acoustic emission feature parameters of the experimental pipeline, including: converting the acoustic emission signal of the experimental pipeline into an electrical signal to obtain an acoustic emission electrical signal of the experimental pipeline; using wavelet packet analysis to extract features from the acoustic emission electrical signal of the experimental pipeline to obtain feature parameters, which are denoted as acoustic emission feature parameters of the experimental pipeline.

[0014] In some embodiments, the control unit's experimental process for detecting cracks in the experimental pipeline includes: building a finite element model of the experimental pipeline in the equipment's pipeline; using the finite element model to perform simulation analysis on the experimental pipeline to determine the location in the experimental pipeline where a preset degree of fracture or slippage occurs, which is recorded as the dangerous location of the experimental pipeline; collecting acoustic emission signals from the dangerous location of the experimental pipeline and within a set area of ​​the dangerous location of the experimental pipeline, and collecting cracking parameters of the experimental pipeline.

[0015] In some embodiments, the acquisition unit acquires the acoustic emission signal of the test pipeline in the pipeline of the device, including: acquiring the acoustic emission signal of the test pipeline collected by a pre-set first acoustic emission signal acquisition system; wherein the first acoustic emission signal acquisition system is pre-set at a preset crack point on the test pipeline; and / or, the control unit collects the acoustic emission signal of the test pipeline from a dangerous location of the test pipeline and a set area of ​​the dangerous location of the test pipeline, including: collecting the acoustic emission signal of the test pipeline collected by a pre-set second acoustic emission signal acquisition system; wherein the second acoustic emission signal acquisition system is pre-set at a dangerous location of the test pipeline and a set area of ​​the dangerous location of the test pipeline.

[0016] In some embodiments, when the training process of the pre-trained pipeline identification model includes extracting feature parameters from the acoustic emission signals of the experimental pipeline, the acoustic emission feature parameters of the pipeline under test and the acoustic emission feature parameters of the experimental pipeline include the time-domain parameters of the acoustic emission electrical signal of the corresponding pipeline, the frequency-domain parameters of the acoustic emission electrical signal of the corresponding pipeline, and the energy parameters of the acoustic emission electrical signal of the corresponding pipeline; wherein, the time-domain parameters of the acoustic emission electrical signal of the corresponding pipeline include at least one of the following: the voltage amplitude of the acoustic emission electrical signal of the corresponding pipeline, the voltage rise time of the acoustic emission electrical signal of the corresponding pipeline, the voltage duration of the acoustic emission electrical signal of the corresponding pipeline, and the voltage duration of the acoustic emission electrical signal of the corresponding pipeline. The count value of ringing within the interval; the energy parameters of the acoustic emission signal of the corresponding pipeline, including at least one of the following: the total energy of the acoustic emission signal of the corresponding pipeline, the frequency band energy of the acoustic emission signal of the corresponding pipeline in the preset frequency band, and the proportion of the frequency band energy of the acoustic emission signal of the corresponding pipeline in the preset frequency band to the total energy; the frequency domain parameters of the acoustic emission signal of the corresponding pipeline, including at least one of the following: the frequency of the acoustic emission signal of the corresponding pipeline, and the pulse factor of the acoustic emission signal of the corresponding pipeline; wherein, the frequency of the acoustic emission signal of the corresponding pipeline includes at least one of the following: the initial frequency of the acoustic emission signal of the corresponding pipeline, the peak frequency of the acoustic emission signal of the corresponding pipeline, the average frequency of the acoustic emission signal of the corresponding pipeline, and the inverse frequency of the acoustic emission signal of the corresponding pipeline.

[0017] In conjunction with the above-described device, the present invention further provides an air conditioner, comprising: the pipeline identification device described above.

[0018] In conjunction with the above method, the present invention further provides a storage medium comprising a stored program, wherein, when the program is executed, the device on which the storage medium is located executes the steps of the pipeline identification method described above.

[0019] In conjunction with the above method, the present invention further provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the pipeline identification method described above.

[0020] Therefore, the solution of this invention involves constructing an air conditioning pipeline model (e.g., an air conditioning pipeline finite element model) for simulation analysis, selecting areas in the air conditioning pipeline where cracks (minor fractures or slippage) occur, and deploying an acoustic emission signal acquisition system (e.g., an acoustic emission sensor) in the selected areas to acquire the acoustic emission signals of the air conditioning pipeline. Using wavelet packet analysis, characteristic parameters (e.g., eigenvalues) of the acoustic emission signals are extracted. These characteristic parameters, along with air conditioning pipeline parameters (e.g., parameters indicating whether the air conditioning pipeline is cracked), are used as samples. Using this sample (with the characteristic parameters of the acoustic emission signal as input and the air conditioning pipe parameters as output), a BP neural network is used for neural network training to obtain an air conditioning pipe identification model, which is used to identify whether the air conditioning pipe is cracked. Then, using the air conditioning pipe identification model, the air conditioning pipe is identified as cracked based on the acoustic emission signal of the air conditioning pipe. Thus, by using acoustic emission technology and neural network technology, the air conditioning pipe is identified as cracked based on the acoustic emission signal of the equipment pipe (such as the air conditioning pipe), and an alert message is sent when the air conditioning pipe is cracked, so that measures can be taken to extend the service life of the air conditioning pipe and ensure the normal use of the air conditioner.

[0021] Other features and advantages of the invention will be set forth in the description which follows, and will be apparent in part from the description, or may be learned by practicing the invention.

[0022] The technical solution of the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. Attached Figure Description

[0023] Figure 1 This is a schematic flowchart of an embodiment of the pipeline identification method of the present invention;

[0024] Figure 2 This is a flowchart illustrating an embodiment of the training process of the pre-trained pipeline identification model in the method of the present invention.

[0025] Figure 3 This is a schematic flowchart of an embodiment of the method of the present invention for extracting characteristic parameters from the acoustic emission signal of the pipeline under test;

[0026] Figure 4 This is a schematic flowchart of an embodiment of the method of the present invention for extracting characteristic parameters from the acoustic emission signal of an experimental pipeline;

[0027] Figure 5 This is a schematic flowchart of an embodiment of the experimental process for detecting cracks in experimental pipelines in the method of the present invention;

[0028] Figure 6 This is a schematic diagram of the structure of an embodiment of the pipeline identification device of the present invention;

[0029] Figure 7 This is a schematic diagram of the process for identifying cracks in air conditioning pipes based on acoustic emission technology and neural network technology.

[0030] Figure 8 This is a stress cloud diagram of the air conditioning piping.

[0031] Figure 9 This is a displacement cloud map of the air conditioning ducts;

[0032] Figure 10 A schematic diagram of the energy curves for each frequency band, numbered accordingly;

[0033] Figure 11 A diagram showing the ratio of energy in each frequency band to the total energy;

[0034] Figure 12 This is a schematic diagram of the acoustic emission parameters.

[0035] Figure 13 This diagram illustrates the distribution of pulse damage factors at different stages (such as the initiation stage, propagation stage, and cracking stage).

[0036] Referring to the accompanying drawings, the reference numerals in the embodiments of the present invention are as follows:

[0037] 102 - Acquisition unit; 104 - Control unit. Detailed Implementation

[0038] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below in conjunction with specific embodiments and corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of this invention, and not all of them. Based on the embodiments of this invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this invention.

[0039] According to embodiments of the present invention, a pipeline identification method is provided, such as... Figure 1 The diagram shows a flowchart of an embodiment of the method of the present invention. This pipe identification method is applied to identify whether the pipe under test in a device (such as an air conditioner) is cracked. In the solution of the present invention, as... Figure 1 As shown, the pipeline identification method includes steps S110 to S130.

[0040] In step S110, the acoustic emission signal of the pipeline under test in the pipeline of the device is acquired.

[0041] In step S120, characteristic parameters are extracted from the acoustic emission signal of the pipeline under test and used as the acoustic emission characteristic parameters of the pipeline under test.

[0042] In step S130, based on the acoustic emission characteristic parameters of the pipeline under test, a pre-trained pipeline identification model is used to identify whether the pipeline under test is cracked. If a crack is detected, a reminder message is sent to alert relevant personnel to take timely measures to prevent the pipeline under test from breaking or being damaged and unable to function properly. This helps extend the service life of the pipeline under test and ensures the normal use of the equipment. The pre-trained pipeline identification model is a pipeline identification model pre-trained based on acoustic emission technology, wavelet packet analysis, and neural network technology.

[0043] To address the problem of fatigue cracks in air conditioning ducts caused by excessive stress, this invention applies acoustic emission technology and neural network technology to the preventative maintenance of air conditioning ducts. By detecting fatigue damage in the ducts early and identifying cracks in real time, it can identify and detect cracks, allowing for timely intervention to extend the service life of the air conditioning ducts. For example, smaller cracks can be repaired by welding or sealant, while larger cracks can be addressed by replacing the ductwork, thus extending the overall lifespan of the air conditioning ducts.

[0044] In some implementations, the specific process of training the pre-trained pipeline identification model in step S130 is described in the following exemplary description.

[0045] The following is combined with Figure 2 The diagram shows an embodiment of the training process of the pre-trained pipeline identification model in the method of the present invention. It further illustrates the specific process of the training process of the pre-trained pipeline identification model in step S130, including steps S210 to S240.

[0046] Step S210: During the experiment to detect cracking in the experimental pipeline, acoustic emission signals from the experimental pipeline are collected, and cracking parameters of the experimental pipeline are also collected. The experimental pipeline refers to the pipeline used in the experiment within the equipment. The cracking parameters of the experimental pipeline characterize whether the experimental pipeline has actually cracked; for example, if the experimental pipeline is not cracked, the cracking parameters are within a set range; if the experimental pipeline is not cracked, the cracking parameters are outside the set range.

[0047] Step S220: Extract characteristic parameters from the acoustic emission signal of the experimental pipeline and use them as the acoustic emission characteristic parameters of the experimental pipeline.

[0048] Step S230: The acoustic emission characteristic parameters and cracking parameters of the experimental pipeline are used as training samples, and a preset neural network model is used as the base model. The preset neural network model is, for example, a BP neural network model.

[0049] Step S240: Using the acoustic emission characteristic parameters of the experimental pipeline as the input parameters of the basic model and the cracking parameters of the experimental pipeline as the output parameters of the basic model, perform neural network training to obtain the required pipeline identification model.

[0050] In the present invention, an artificial neural network is used to establish the relationship between air conditioning pipe cracks and acoustic emission signals by utilizing the feature parameters in the acoustic emission signals. This enables real-time detection of whether air conditioning pipes have cracks, allowing for timely measures to be taken when cracks are detected, thereby extending the service life of the air conditioning pipes.

[0051] In some embodiments, the specific process of extracting characteristic parameters from the acoustic emission signal of the pipeline under test in step S120 as the acoustic emission characteristic parameters of the pipeline under test is described in the following exemplary description.

[0052] The following is combined with Figure 3 The schematic diagram shown is a flowchart of an embodiment of the method of the present invention for extracting feature parameters from the acoustic emission signal of the pipeline under test. It further illustrates the specific process of extracting feature parameters from the acoustic emission signal of the pipeline under test in step S120, including steps S310 to S320.

[0053] Step S310: Convert the acoustic emission signal of the pipeline under test into an electrical signal to obtain the acoustic emission electrical signal of the pipeline under test.

[0054] Step S320: Using wavelet packet analysis, feature extraction is performed on the acoustic emission electrical signal of the pipeline under test to obtain feature parameters, which are denoted as the acoustic emission feature parameters of the pipeline under test, such as the feature values ​​of the acoustic emission signal of the pipeline under test. Specifically, using wavelet packet analysis, feature parameters that meet the preset parameter requirements are extracted from the acoustic emission electrical signal of the pipeline under test and used as the acoustic emission feature parameters of the pipeline under test, such as the feature values ​​of the acoustic emission signal of the pipeline under test.

[0055] In some embodiments, when the training process of the pipeline identification model pre-trained in step S130 includes extracting feature parameters from the acoustic emission signal of the experimental pipeline, the specific process of extracting feature parameters from the acoustic emission signal of the experimental pipeline in step S220 as the acoustic emission feature parameters of the experimental pipeline is described in the following exemplary description.

[0056] The following is combined with Figure 4 The diagram shows an embodiment of the method of the present invention for extracting feature parameters from the acoustic emission signal of the experimental pipeline. It further illustrates the specific process of extracting feature parameters from the acoustic emission signal of the experimental pipeline in step S220, including steps S410 to S420.

[0057] Step S410: Convert the acoustic emission signal of the experimental pipeline into an electrical signal to obtain the acoustic emission electrical signal of the experimental pipeline.

[0058] Step S420: Using wavelet packet analysis, feature extraction is performed on the acoustic emission electrical signal of the experimental pipeline to obtain feature parameters, which are denoted as the acoustic emission feature parameters of the experimental pipeline, such as the feature values ​​of the acoustic emission signal of the experimental pipeline. Specifically, using wavelet packet analysis, feature parameters that meet the preset parameter requirements are extracted from the acoustic emission electrical signal of the experimental pipeline and used as the acoustic emission feature parameters of the experimental pipeline, such as the feature values ​​of the acoustic emission signal of the experimental pipeline.

[0059] In the present invention, wavelet packet analysis is used to extract feature values ​​from the acoustic emission signals of the corresponding pipeline (such as the pipeline under test or the experimental pipeline) in both the time and frequency domains. These feature values ​​are used as acoustic emission feature parameters of the corresponding pipeline. Then, based on the acoustic emission feature parameters of the experimental pipeline, a BP neural network is trained to obtain a pipeline identification model. The pipeline identification model is used to identify whether the pipeline under test is cracked based on the acoustic emission feature parameters of the pipeline under test. This allows for timely measures to be taken when cracks are detected in the air conditioning pipeline, thereby extending the service life of the air conditioning pipeline.

[0060] In some embodiments, the specific process of detecting cracks in the experimental pipeline in step S210 is described in the following exemplary description.

[0061] The following is combined with Figure 5The diagram shows an embodiment of the experimental process for detecting cracks in the experimental pipeline in the method of the present invention. It further illustrates the specific process of detecting cracks in the experimental pipeline in step S210, including steps S510 to S530.

[0062] Step S510: For the experimental piping in the equipment, a finite element model is built. A finite element model is a model established using the finite element analysis method. It is a combination of elements that are connected only at the nodes, transmit forces only through the nodes, and are constrained only at the nodes.

[0063] Step S520: Use the finite element model to perform simulation analysis on the experimental pipeline to determine the locations in the experimental pipeline where a predetermined degree of fracture or slippage occurs, and record these locations as dangerous locations in the experimental pipeline. For example: determine the points in the experimental pipeline where a predetermined degree of fracture or slippage occurs, and record these as dangerous points in the experimental pipeline.

[0064] Step S530: Collect acoustic emission signals from the experimental pipeline at the dangerous location and within the designated area of ​​the dangerous location of the experimental pipeline, and collect cracking parameters of the experimental pipeline.

[0065] Figure 7 This is a schematic diagram illustrating the process of identifying cracks in air conditioning pipes based on acoustic emission technology and neural network technology. Figure 7 As shown, the process for identifying cracks in air conditioning pipes based on acoustic emission technology and neural network technology includes:

[0066] Step 1: Build a finite element model of the air conditioning duct system and use the finite element model to perform simulation analysis and calculations on the air conditioning duct system to obtain the dangerous points of the air conditioning duct system. Then proceed to Step 2. The dangerous points of the air conditioning duct system include points where there are minor breaks or slippage in the air conditioning duct system.

[0067] In step 1, a finite element model of the air conditioning pipeline is built and used to perform simulation analysis and calculation on the air conditioning pipeline to obtain the dangerous points of the air conditioning pipeline. Specifically, this can be done by: building a realistic three-dimensional model of the pipeline at a 1:1 scale in drawing software (such as Creo), importing the three-dimensional model of the pipeline into the finite element simulation software, constraining the pipeline according to the installation situation of the pipeline in the air conditioner, and finally obtaining the dangerous points of pipeline stress and displacement according to the power spectral density (PSD) spectrum (i.e., the vibration excitation or acceleration excitation that the pipeline is subjected to during actual operation).

[0068] Figure 8 This is a stress cloud diagram of the air conditioning piping. Figure 9 This is a displacement cloud map of the air conditioning ducts. Figure 8 and Figure 9The bottom of the image shows the scaling factor. In step 1, the air conditioning piping is simulated and analyzed using a finite element model, which yields a stress cloud diagram of the air conditioning piping (e.g., Figure 8 (as shown) and displacement cloud map of air conditioning pipes (as shown) Figure 9 As shown in the diagram, based on the stress cloud diagram and displacement cloud diagram of the air conditioning duct, the dangerous points of the air conditioning duct can be obtained through calculation. For example: in Figure 8 In the stress cloud diagram of the air conditioning duct shown, from the red area (e.g., the Max area) to the blue area (e.g., the Min area), the air conditioning duct in the blue area (e.g., the Min area) experiences less stress, while the air conditioning duct in the red area (e.g., the Max area) experiences greater stress. It can be considered that the points on the air conditioning duct corresponding to the red area are the dangerous points of the air conditioning duct.

[0069] exist Figure 9 In the displacement cloud diagram of the air conditioning duct shown, from the red area (e.g., the Max area) to the blue area (e.g., the Min area), the displacement deformation of the air conditioning duct in the blue area (e.g., the Min area) is smaller, while the displacement deformation of the air conditioning duct in the red area (e.g., the Max area) is larger. It can be considered that the points on the air conditioning duct corresponding to the red area are the danger points of the air conditioning duct.

[0070] Step 2: Select the dangerous points and the areas near the dangerous points of the air conditioning duct obtained in Step 1 as the placement points for acoustic emission sensor signals; then use the acoustic emission signal acquisition system (i.e., the acquisition system composed of acoustic emission sensors) to collect the acoustic emission signals of the air conditioning duct in the fatigue test, and then proceed to Step 3.

[0071] In this invention, fatigue cracks in air conditioning pipes are identified and detected using neural network technology via acoustic emission. Specifically, acoustic emission signals are collected from the air conditioning pipes using acoustic emission technology. Feature values ​​of the signals are selected, and the feature value parameters and energy frequency bands in the acoustic emission signals are input into a BP neural network (Backpropagation Neural Network) for neural network training. The trained pipe identification model is then used to identify whether the pipe under test is cracked, thus enabling the neural network to identify and detect cracks in the air conditioning pipes. When cracks are detected in the air conditioning pipes, timely measures are taken to extend the service life of the air conditioning pipes.

[0072] In some embodiments, step S110, which involves acquiring the acoustic emission signal of the pipeline under test (TBT) in the piping of the device, includes: acquiring the acoustic emission signal of the TBT collected by a pre-set first acoustic emission signal acquisition system; wherein the first acoustic emission signal acquisition system is pre-set at a preset crack point on the TBT. That is, the first acoustic emission signal acquisition system is pre-positioned at a preset crack point (such as a point where excessive stress may occur) on the TBT to acquire the acoustic emission signal of the TBT collected by the first acoustic emission signal acquisition system.

[0073] In some embodiments, step S530, collecting acoustic emission signals from the experimental pipeline at the hazardous location and within a designated area of ​​the hazardous location, includes: collecting acoustic emission signals from the experimental pipeline acquired by a pre-set second acoustic emission signal acquisition system; wherein the second acoustic emission signal acquisition system is pre-set at the hazardous location of the experimental pipeline and within a designated area of ​​the hazardous location. That is, the acoustic emission signal acquisition system is arranged at the hazardous location of the experimental pipeline and within the designated area of ​​the hazardous location to collect the acoustic emission signals from the experimental pipeline acquired by the acoustic emission signal acquisition system; and based on the hazardous location of the experimental pipeline, cracking parameters of the experimental pipeline are collected.

[0074] In the present invention, considering that when air conditioning pipes develop cracks or other damage, the internal stress state of the material changes, leading to micro-fractures or slippages in local areas, and these micro-fractures or slippages release characteristic acoustic signals, acoustic emission technology is used to convert acoustic signals into electrical signals. The electrical signals are collected and processed to obtain characteristic values ​​of the classified signals. The parameter list analysis method is used to determine whether the air conditioning pipes have developed cracks, so that measures can be taken in a timely manner when cracks are detected in the air conditioning pipes to extend the service life of the air conditioning pipes.

[0075] In some embodiments, the training process of the pipeline identification model pre-trained in step S130 includes extracting feature parameters from the acoustic emission signal of the experimental pipeline. In step S120, the acoustic emission feature parameters of the pipeline under test and the acoustic emission feature parameters of the experimental pipeline in step S220 are the feature parameters obtained by feature extraction of the acoustic emission electrical signal of the corresponding pipeline. These feature parameters include: the time domain parameters of the acoustic emission electrical signal of the corresponding pipeline, the frequency domain parameters of the acoustic emission electrical signal of the corresponding pipeline, and the energy parameters of the acoustic emission electrical signal of the corresponding pipeline.

[0076] The time-domain parameters of the acoustic emission signal of the corresponding pipeline include at least one of the following: the voltage amplitude of the acoustic emission signal of the corresponding pipeline, the voltage rise time of the acoustic emission signal of the corresponding pipeline, the voltage duration of the acoustic emission signal of the corresponding pipeline, and the ringing count value within the voltage duration of the acoustic emission signal of the corresponding pipeline.

[0077] The energy parameters of the acoustic emission signal of the corresponding pipeline include at least one of the following: the total energy of the acoustic emission signal of the corresponding pipeline, the frequency band energy of the acoustic emission signal of the corresponding pipeline in the preset frequency band, and the proportion of the frequency band energy of the acoustic emission signal of the corresponding pipeline in the preset frequency band to the total energy.

[0078] The frequency domain parameters of the acoustic emission signal of the corresponding pipeline include at least one of the following: the frequency of the acoustic emission signal of the corresponding pipeline, and the pulse factor of the acoustic emission signal of the corresponding pipeline; wherein, the frequency of the acoustic emission signal of the corresponding pipeline includes at least one of the following: the initial frequency of the acoustic emission signal of the corresponding pipeline, the peak frequency of the acoustic emission signal of the corresponding pipeline, the average frequency of the acoustic emission signal of the corresponding pipeline, and the inverse calculated frequency of the acoustic emission signal of the corresponding pipeline.

[0079] Specifically, the feature parameters obtained by feature extraction of the acoustic emission signal of the pipeline under test include: time-domain parameters of the acoustic emission signal of the pipeline under test, and frequency-domain parameters of the acoustic emission signal of the pipeline under test; wherein, the time-domain parameters of the acoustic emission signal of the pipeline under test include at least one of the following: voltage amplitude of the acoustic emission signal of the pipeline under test, voltage rise time of the acoustic emission signal of the pipeline under test, voltage duration of the acoustic emission signal of the pipeline under test, and ringing count during the voltage duration of the acoustic emission signal of the pipeline under test; the frequency-domain parameters of the acoustic emission signal of the pipeline under test include the following At least one of the following: the total energy of the acoustic emission signal of the pipeline under test, the frequency of the acoustic emission signal of the pipeline under test, the pulse factor of the acoustic emission signal of the pipeline under test, the band energy of the acoustic emission signal of the pipeline under test in a preset frequency band, and the proportion of the band energy of the acoustic emission signal of the corresponding pipeline in the preset frequency band to the total energy; wherein, the frequency of the acoustic emission signal of the pipeline under test includes at least one of the following: the initial frequency of the acoustic emission signal of the pipeline under test, the peak frequency of the acoustic emission signal of the pipeline under test, the average frequency of the acoustic emission signal of the pipeline under test, and the inverse calculated frequency of the acoustic emission signal of the pipeline under test.

[0080] The feature parameters obtained by feature extraction of the acoustic emission signal from the experimental pipeline include: time-domain parameters and frequency-domain parameters of the acoustic emission signal from the experimental pipeline; wherein, the time-domain parameters of the acoustic emission signal from the experimental pipeline include at least one of the following: voltage amplitude, voltage rise time, voltage duration, and ring count during the voltage duration; the frequency-domain parameters of the acoustic emission signal from the experimental pipeline include at least one of the following. One of the following: the total energy of the acoustic emission signal in the experimental pipeline, the frequency of the acoustic emission signal in the experimental pipeline, the pulse factor of the acoustic emission signal in the experimental pipeline, the band energy of the acoustic emission signal in the experimental pipeline in the preset frequency band, and the proportion of the band energy of the acoustic emission signal in the preset frequency band of the corresponding pipeline in the total energy; wherein, the frequency of the acoustic emission signal in the experimental pipeline includes at least one of the following: the initial frequency of the acoustic emission signal in the experimental pipeline, the peak frequency of the acoustic emission signal in the experimental pipeline, the average frequency of the acoustic emission signal in the experimental pipeline, and the inverse calculated frequency of the acoustic emission signal in the experimental pipeline.

[0081] like Figure 7 As shown, the process for identifying cracks in air conditioning pipes based on acoustic emission technology and neural network technology also includes:

[0082] Step 3: Select acoustic emission characteristic values ​​based on the acoustic emission signals of the air conditioning duct in the fatigue test: Select characteristic values ​​of the acoustic emission signals through two different dimensions, time-energy and frequency-energy, to obtain the characteristic values ​​of the acoustic emission signals of the air conditioning duct, and then proceed to step 4.

[0083] In step 3, the eigenvalues ​​of the acoustic emission signal are selected using two different dimensions: time-energy and frequency-energy. Specifically, wavelet packet transform can be used to characterize the acoustic emission signal and obtain its eigenvalues. Wavelet packet transform (WPT) is a signal processing technique that inherits the time-frequency analysis characteristics of wavelet transform and further decomposes undecomposed high-frequency band signals, thereby improving frequency resolution.

[0084] The acoustic emission signal acquired is a set of voltage amplitudes at equal time intervals. Direct analysis would be extremely complex, requiring description using various characteristic values. Parameters describing the acoustic emission waveform include amplitude, rise time, duration, and ring count; parameters describing frequency characteristics include initial frequency, peak frequency, inverse frequency, and average frequency; parameters describing energy characteristics include energy, signal strength, and ASL (Average Saturation Level). Using these parameters allows for the description and analysis of the acoustic emission signal. Simultaneous description using time-energy and frequency-energy parameters yields a more complete and accurate acoustic emission signal.

[0085] Specifically, the process of characterizing the acoustic emission signal using wavelet packet transform can include: first, determining the spectral characteristics of the acoustic emission signal, selecting an appropriate decomposition level n (n is a positive integer), and decomposing the original signal into 2n... n In each of the nodes, the bandwidth of each node is 1 / 2 of the original signal bandwidth. n Finally, the wavelet coefficients of each node are inversely transformed, and the signal energy of the node is calculated from the signal components corresponding to the node. The energy of different frequency bands is selected from the calculated signal energy as the characteristic values ​​of the acoustic emission signal.

[0086] For example, the acoustic emission signal from one of the air conditioning ducts is selected and subjected to wavelet packet transform. A db4-series wavelet function is chosen, and a three-level wavelet packet decomposition is performed to obtain the energy values ​​of eight frequency bands in the signal. This allows for the selection of energy values ​​for different frequency bands in the acoustic emission signal. The db4-series wavelet function is a discrete wavelet transform function. In the process of selecting the characteristic values ​​of the acoustic emission signal, the energy frequency bands need to be extracted using wavelet packet transform, enabling the deriving of the characteristic values ​​of energy for each frequency band based on the acoustic emission signal.

[0087] When using wavelet packet transform to characterize acoustic emission signals, the energy of the signal and the energy of each frequency component can be calculated using equations (1) and (2):

[0088]

[0089]

[0090] Formula (1) can be used to calculate the energy in the signal, where: E i Indicates the energy of the i-band; Let A represent the signal component in frequency band i, and A be the conversion coefficient, which depends on the model of the acoustic emission sensor. Formula (2) can be used to calculate the energy of the signal components in each frequency band. The calculated frequency band energy distribution is as follows: Figure 10 and Figure 11 As shown. Figure 10A schematic diagram of the energy curves for each frequency band, numbered accordingly. Figure 11 A diagram illustrating the ratio of energy in each frequency band to the total energy, numbered by [the relevant authority]. Figure 10 and Figure 11 It can be seen that the frequency band with the highest frequency band number 2 has the highest energy. Both formula (1) and formula (2) are used to calculate the energy of the acoustic emission signal in each frequency band. The difference between the two lies in A (conversion coefficient). The coefficient of A is related to the sensor type. Since the acoustic emission sensor used in the experiment is the same, A can be omitted, that is, formula (2) is used.

[0091] Step 4: Using the feature values ​​of the acoustic emission signal of the air conditioning pipes obtained in Step 3 as samples, a BP neural network is used for neural network training to obtain an air conditioning pipe identification model. Then, the feature values ​​of the acoustic emission signal of the air conditioning pipes obtained on site are identified using the air conditioning pipe identification model to identify whether the air conditioning pipes on site are cracked.

[0092] The waveform of the acoustic emission signal from air conditioning ducts contains four characteristic values: amplitude, rise time, duration, and ring count. It is particularly useful for detecting fatigue cracks in their early stages. The frequency characteristic value represents the frequency at different stages of the acoustic emission signal: the initial frequency is the average frequency before the signal reaches its peak; the peak frequency is the frequency corresponding to the maximum peak in the power spectrum; the inverse frequency is the average frequency after the peak; and the average frequency is the average frequency of the entire acoustic emission signal. These represent the frequencies at different stages of the acoustic emission signal. The acquired acoustic emission signal is quite complex and requires description using various characteristic values, including time, frequency, and energy. For time and frequency, time-domain and frequency-domain graphs can be directly observed and recorded on the system as needed. The energy of each frequency band needs to be calculated using wavelet packet transform. Finally, amplitude, rise time, duration, ring count, initial frequency, peak frequency, inverse frequency, average frequency, signal strength, impulse factor, and the energy percentage of the first four frequency bands are selected as the characteristic value inputs for neural network training. Among them, the characteristic values ​​of the acoustic emission signal (such as amplitude, rise time, duration, and ring count) and the frequency band energy (i.e., the energy of the first four frequency bands) are as follows: Figure 12 As shown. Figure 12This is a schematic diagram of the acoustic emission parameters. Amplitude: refers to the size of the maximum peak value in the signal. Rise time: refers to the time required for the acoustic emission signal to rise from above the threshold to the maximum peak value. Duration: refers to the duration of the entire acoustic emission signal above the threshold value. Ring count: refers to the number of oscillations after exceeding the threshold value. The characteristic values ​​of the acoustic emission signal (such as amplitude, rise time, duration, and ring count) can completely describe the set of morphological characteristics of a waveform in the acoustic emission signal. The threshold value is a set critical value; only when the acoustic emission signal exceeds the threshold value will it be recorded.

[0093] Determining the presence of fatigue cracks based on acoustic emission signals of air conditioning pipelines: When a crack occurs at a certain location in an air conditioning pipeline, various acoustic emission parameters also undergo drastic changes; for example, at the location of the crack, the acoustic emission spectrum signal increases, the energy is enhanced, and the impulse factor decreases. By inputting the characteristic values ​​and energy frequency bands of the acoustic emission signal into a BP neural network model, the acoustic emission signal can be automatically identified after training. When the acoustic emission signal exhibits the above characteristics during the detection process, it indicates that fatigue cracks have occurred in the air conditioning pipeline. Among them, the energy frequency band is obtained by performing wavelet packet transform on the acoustic emission signal and then calculating it using formula (2). The energy frequency band is part of the characteristic value; the energy frequency band is obtained by extracting the energy of each frequency band in the acoustic emission signal after obtaining the acoustic emission signal using the wavelet packet transform method. The input of the BP neural network model is the various characteristic value parameters, and the output of the BP neural network model is the occurrence of cracks in the air conditioning pipeline. Figure 13 The figure shows the distribution of pulse factors in acoustic emission signals at different stages. Figure 13 This diagram illustrates the distribution of pulse damage factors at different stages (e.g., initiation, propagation, and cracking). The initiation stage refers to the appearance of a very small crack on the structural surface, with stress concentration areas exhibiting minute crack formation; this is the initial stage of crack formation. The propagation stage refers to the slow, gradually increasing crack growth, with stress concentration at the crack tip leading to localized plastic deformation. The cracking stage refers to the rapid propagation of the crack after it reaches a critical size until material fracture occurs; the crack propagation rate increases dramatically, reaching the macroscopic crack propagation stage.

[0094] In step 4, a neural network is used to detect cracks in the air conditioning pipes: a BP neural network model is selected to establish the relationship between the air conditioning pipes and acoustic emission signals, enabling real-time identification of cracks in the air conditioning pipes. The training of the neural network involves: X... i As a sample, the sample contains training feature values. These feature values ​​include amplitude, initial frequency, and energy of the first four frequency bands. A large number of training samples are input into a BP neural network to establish a nonlinear functional relationship f between the feature values ​​and whether cracking has occurred in the air conditioning pipes.j The feature vector for testing is input into a nonlinear function f to identify whether cracks have occurred in the air conditioning pipes. The input amplitude, rise time, duration, ring count, initial frequency, peak frequency, inverse frequency, average frequency, signal strength, ASL, and energy of the first four frequency bands from the acoustic emission data are used as the input data for the initial nodes of the 14 input layers of the neural network. The output node [1, 0] indicates the presence of a crack. Training samples are randomly selected, accounting for 80% of the total samples. During training, the Levenberg-Marquardt optimization algorithm (LM algorithm) is used, with a maximum iteration count of 2000, a training rate of 0.01, and a minimum training error of 10. -6 The Levenberg-Marquardt algorithm is a numerical optimization method widely used in nonlinear least squares problems. The remaining 20% ​​of the acoustic emission data is a test sample set. Rise time refers to the time required for the acoustic emission signal to rise from above a threshold value to its maximum peak value. Duration refers to the duration of the entire acoustic emission signal above the threshold value. Ring count refers to the number of oscillations after exceeding the threshold value. Initial frequency refers to the average frequency of the acoustic emission signal before reaching its peak value. Peak frequency refers to the frequency corresponding to the maximum peak value in the power spectrum. Inverse frequency refers to the average frequency after the peak value of the acoustic emission signal. Average frequency refers to the average frequency of the entire acoustic emission signal. ASL (Average signal level) refers to a physical quantity that describes the average value of a signal in decibels.

[0095] In this invention, the acoustic emission signals from fatigue cracks in air conditioning pipes are characterized and then imported into a BP neural network for training and testing. Finally, the neural network is used to identify and detect cracks in the air conditioning pipes online. The results of training and testing the neural network on the air conditioning pipes are shown in Table 1. Table 1 shows that the error rate is 3.56%, indicating that the neural network has high accuracy in identifying cracks in the air conditioning pipes.

[0096] Table 1

[0097] Operating conditions Training data volume Training error percentage Test data volume Test error percentage Air conditioning ducts 100000 3.56％ 30000 3.96％

[0098] In the present invention, fatigue cracks in air conditioning pipes are identified and detected by using neural network technology through acoustic emission. The fatigue cracks in the air conditioning pipes are identified and detected in real time so that timely measures can be taken to extend the service life of the air conditioning pipes.

[0099] The technical solution of this embodiment involves constructing an air conditioning duct model (such as a finite element model) for simulation analysis. Areas in the air conditioning duct where cracks (minor fractures or slippage) occur are selected. An acoustic emission signal acquisition system (such as an acoustic emission sensor) is deployed in these selected areas to collect the acoustic emission signals from the air conditioning duct. Wavelet packet analysis is used to extract the characteristic parameters (such as eigenvalues) of the acoustic emission signals. These characteristic parameters, along with the air conditioning duct parameters (such as parameters indicating whether the air conditioning duct is cracked), are used as samples. Based on this sample (using the characteristic parameters of the acoustic emission signal as input and the air conditioning pipe parameters as output), a BP neural network is used for neural network training to obtain an air conditioning pipe identification model, which is used to identify whether the air conditioning pipe is cracked. Then, the air conditioning pipe identification model is used to identify whether the air conditioning pipe is cracked based on the acoustic emission signal of the air conditioning pipe. Thus, by using acoustic emission technology and neural network technology, the air conditioning pipe is identified as cracked based on the acoustic emission signal of the air conditioning pipe, and an alert message is sent when the air conditioning pipe is cracked, so that measures can be taken to extend the service life of the air conditioning pipe and ensure the normal use of the air conditioner.

[0100] According to an embodiment of the present invention, a pipe identification device corresponding to the pipe identification method is also provided. See also Figure 6 The diagram shows a structural schematic of an embodiment of the device of the present invention. This pipe identification device is used to identify whether the pipe under test in a device (such as an air conditioner) is cracked. In the solution of the present invention, as... Figure 6 As shown, the pipeline identification device includes: an acquisition unit 102 and a control unit 104.

[0101] The acquisition unit 102 is configured to acquire the acoustic emission signal of the pipeline under test in the pipeline of the device. The specific functions and processing of the acquisition unit 102 are described in step S110.

[0102] The control unit 104 is configured to extract characteristic parameters from the acoustic emission signal of the pipeline under test, and use them as the acoustic emission characteristic parameters of the pipeline under test. The specific functions and processing of the control unit 104 are described in step S120.

[0103] The control unit 104 is further configured to identify whether the pipeline under test is cracked based on the acoustic emission characteristic parameters of the pipeline under test and using a pre-trained pipeline identification model. If a crack is detected, the control unit will send a crack alert message to remind relevant personnel to take timely measures to prevent the pipeline from breaking or being damaged, thus extending its service life and ensuring the normal operation of the equipment. The pre-trained pipeline identification model is a pipeline identification model pre-trained based on acoustic emission technology, wavelet packet analysis, and neural network technology. The specific functions and processing of the control unit 104 are further described in step S130.

[0104] To address the problem of fatigue cracks in air conditioning pipes caused by excessive stress, this invention applies acoustic emission technology and neural network technology to the preventive maintenance of air conditioning pipes. By detecting fatigue damage in the air conditioning pipes at an early stage and identifying cracks in real time, it can identify and detect cracks in the air conditioning pipes, and take timely measures to extend the service life of the air conditioning pipes.

[0105] In some embodiments, the training process of the pre-trained pipeline identification model of the control unit 104 includes:

[0106] The control unit 104 is further configured to collect acoustic emission signals from the experimental pipeline and collect cracking parameters of the experimental pipeline during the experiment to detect cracking of the experimental pipeline. The cracking parameters of the experimental pipeline are used to characterize whether the experimental pipeline has actually cracked. The specific functions and processing of the control unit 104 are further described in step S210.

[0107] The control unit 104 is further configured to extract characteristic parameters from the acoustic emission signal of the experimental pipeline, and use these parameters as the acoustic emission characteristic parameters of the experimental pipeline. The specific functions and processing of the control unit 104 are further described in step S220.

[0108] The control unit 104 is further configured to use the acoustic emission characteristic parameters and cracking parameters of the experimental pipeline as training samples, and a preset neural network model as the base model. The specific functions and processing of the control unit 104 are further described in step S230.

[0109] The control unit 104 is further configured to use the acoustic emission characteristic parameters of the experimental pipeline as input parameters of the basic model and the cracking parameters of the experimental pipeline as output parameters of the basic model to perform neural network training, thereby obtaining the required pipeline identification model. The specific functions and processing of this control unit 104 are further described in step S240.

[0110] In the present invention, an artificial neural network is used to establish the relationship between air conditioning pipe cracks and acoustic emission signals by utilizing the feature parameters in the acoustic emission signals. This enables real-time detection of whether air conditioning pipes have cracks, allowing for timely measures to be taken when cracks are detected, thereby extending the service life of the air conditioning pipes.

[0111] In some embodiments, the control unit 104 extracts characteristic parameters from the acoustic emission signal of the pipeline under test as acoustic emission characteristic parameters of the pipeline under test, including:

[0112] The control unit 104 is further configured to convert the acoustic emission signal of the pipeline under test into an electrical signal to obtain the acoustic emission electrical signal of the pipeline under test. The specific functions and processing of the control unit 104 are further described in step S310.

[0113] The control unit 104 is further configured to use wavelet packet analysis to extract features from the acoustic emission electrical signal of the pipeline under test, obtaining feature parameters, which are denoted as the acoustic emission feature parameters of the pipeline under test, such as the feature values ​​of the acoustic emission signal of the pipeline under test. Specifically, wavelet packet analysis is used to extract feature parameters that meet preset parameter requirements from the acoustic emission electrical signal of the pipeline under test, which are then used as the acoustic emission feature parameters of the pipeline under test, such as the feature values ​​of the acoustic emission signal of the pipeline under test. The specific functions and processing of this control unit 104 are further described in step S320.

[0114] In some embodiments, the control unit 104, when the training process of the pre-trained pipeline identification model includes extracting feature parameters from the acoustic emission signal of the experimental pipeline, extracts feature parameters as acoustic emission feature parameters of the experimental pipeline, including:

[0115] The control unit 104 is further configured to convert the acoustic emission signal of the experimental pipeline into an electrical signal to obtain the acoustic emission electrical signal of the experimental pipeline. The specific functions and processing of the control unit 104 are further described in step S410.

[0116] The control unit 104 is further configured to use wavelet packet analysis to extract features from the acoustic emission electrical signal of the experimental pipeline, obtaining feature parameters, which are denoted as the acoustic emission feature parameters of the experimental pipeline, such as the feature values ​​of the acoustic emission signal of the experimental pipeline. Specifically, wavelet packet analysis is used to extract feature parameters that meet preset parameter requirements from the acoustic emission electrical signal of the experimental pipeline, which are then used as the acoustic emission feature parameters of the experimental pipeline, such as the feature values ​​of the acoustic emission signal of the experimental pipeline. The specific functions and processing of this control unit 104 are further described in step S420.

[0117] In the present invention, wavelet packet analysis is used to extract feature values ​​from the acoustic emission signals of the corresponding pipeline (such as the pipeline under test or the experimental pipeline) in both the time and frequency domains. These feature values ​​are used as acoustic emission feature parameters of the corresponding pipeline. Then, based on the acoustic emission feature parameters of the experimental pipeline, a BP neural network is trained to obtain a pipeline identification model. The pipeline identification model is used to identify whether the pipeline under test is cracked based on the acoustic emission feature parameters of the pipeline under test. This allows for timely measures to be taken when cracks are detected in the air conditioning pipeline, thereby extending the service life of the air conditioning pipeline.

[0118] In some embodiments, the control unit 104 performs an experimental process for detecting cracks in the experimental pipeline, including:

[0119] The control unit 104 is further configured to build a finite element model for the experimental piping in the equipment's piping. The specific functions and processing of the control unit 104 are further described in step S510.

[0120] The control unit 104 is further configured to use the finite element model to perform simulation analysis on the experimental pipeline, determine the locations in the experimental pipeline where a preset degree of fracture or slippage occurs, and record these locations as dangerous locations in the experimental pipeline. The specific functions and processing of this control unit 104 are further described in step S520.

[0121] The control unit 104 is further configured to collect acoustic emission signals from the experimental pipeline at dangerous locations and within a defined area of ​​the dangerous locations, and to collect cracking parameters of the experimental pipeline. The specific functions and processing of the control unit 104 are further described in step S530.

[0122] Figure 7 This is a schematic diagram illustrating the process of identifying cracks in air conditioning pipes based on acoustic emission technology and neural network technology. Figure 7 As shown, the process for identifying cracks in air conditioning pipes based on acoustic emission technology and neural network technology includes:

[0123] Step 1: Build a finite element model of the air conditioning duct system and use the finite element model to perform simulation analysis and calculations on the air conditioning duct system to obtain the dangerous points of the air conditioning duct system. Then proceed to Step 2. The dangerous points of the air conditioning duct system include points where there are minor breaks or slippage in the air conditioning duct system.

[0124] Figure 8 This is a stress cloud diagram of the air conditioning piping. Figure 9 This is a displacement cloud map of the air conditioning ducts. Figure 8 and Figure 9 The bottom of the image shows the scaling factor. In step 1, the air conditioning piping is simulated and analyzed using a finite element model, which yields a stress cloud diagram of the air conditioning piping (e.g., Figure 8(as shown) and displacement cloud map of air conditioning pipes (as shown) Figure 9 As shown in the diagram, based on the stress cloud diagram and displacement cloud diagram of the air conditioning duct, the dangerous points of the air conditioning duct can be obtained through calculation. For example: in Figure 8 In the stress cloud diagram of the air conditioning duct shown, from the red area (e.g., the Max area) to the blue area (e.g., the Min area), the air conditioning duct in the blue area (e.g., the Min area) experiences less stress, while the air conditioning duct in the red area (e.g., the Max area) experiences greater stress. It can be considered that the points on the air conditioning duct corresponding to the red area are the dangerous points of the air conditioning duct.

[0125] exist Figure 9 In the displacement cloud diagram of the air conditioning duct shown, from the red area (e.g., the Max area) to the blue area (e.g., the Min area), the displacement deformation of the air conditioning duct in the blue area (e.g., the Min area) is smaller, while the displacement deformation of the air conditioning duct in the red area (e.g., the Max area) is larger. It can be considered that the points on the air conditioning duct corresponding to the red area are the danger points of the air conditioning duct.

[0126] Step 2: Select the dangerous points and the areas near the dangerous points of the air conditioning duct obtained in Step 1 as the placement points for acoustic emission sensor signals; then use the acoustic emission signal acquisition system (i.e., the acquisition system composed of acoustic emission sensors) to collect the acoustic emission signals of the air conditioning duct in the fatigue test, and then proceed to Step 3.

[0127] In this invention, fatigue cracks in air conditioning pipes are identified and detected using neural network technology via acoustic emission. Specifically, acoustic emission signals are collected from the air conditioning pipes using acoustic emission technology. Feature values ​​of the signals are selected, and the feature value parameters and energy frequency bands in the acoustic emission signals are input into a BP neural network (Backpropagation Neural Network) for neural network training. The trained pipe identification model is then used to identify whether the pipe under test is cracked, thus enabling the neural network to identify and detect cracks in the air conditioning pipes. When cracks are detected in the air conditioning pipes, timely measures are taken to extend the service life of the air conditioning pipes.

[0128] In some embodiments, the acquisition unit 102 acquires the acoustic emission signal of the pipeline under test in the pipeline of the device, including: the acquisition unit 102 is further configured to acquire the acoustic emission signal of the pipeline under test collected by a pre-set first acoustic emission signal acquisition system; wherein, the first acoustic emission signal acquisition system is pre-set at a preset crack point on the pipeline under test. That is, the first acoustic emission signal acquisition system is pre-arranged at the preset crack point (such as a point where excessive stress may occur) of the pipeline under test to acquire the acoustic emission signal of the pipeline under test collected by the first acoustic emission signal acquisition system.

[0129] In some embodiments, the control unit 104 collects acoustic emission signals from the experimental pipeline at the dangerous location and within a designated area of ​​the dangerous location. Specifically, the control unit 104 is further configured to collect acoustic emission signals from the experimental pipeline acquired by a pre-set second acoustic emission signal acquisition system. This second acoustic emission signal acquisition system is pre-set at the dangerous location of the experimental pipeline and within a designated area of ​​the dangerous location. In other words, the acoustic emission signal acquisition system is deployed at the dangerous location of the experimental pipeline and within the designated area of ​​the dangerous location to collect the acoustic emission signals from the experimental pipeline acquired by the acoustic emission signal acquisition system; and based on the dangerous location of the experimental pipeline, it collects cracking parameters of the experimental pipeline.

[0130] In the present invention, considering that when air conditioning pipes develop cracks or other damage, the internal stress state of the material changes, leading to micro-fractures or slippages in local areas, and these micro-fractures or slippages release characteristic acoustic signals, acoustic emission technology is used to convert acoustic signals into electrical signals. The electrical signals are collected and processed to obtain characteristic values ​​of the classified signals. The parameter list analysis method is used to determine whether the air conditioning pipes have developed cracks, so that measures can be taken in a timely manner when cracks are detected in the air conditioning pipes to extend the service life of the air conditioning pipes.

[0131] In some embodiments, the control unit 104, when the training process of the pre-trained pipeline identification model includes extracting feature parameters from the acoustic emission signal of the experimental pipeline, the acoustic emission feature parameters of the pipeline under test and the acoustic emission feature parameters of the experimental pipeline, that is, the feature parameters obtained by feature extraction of the acoustic emission electrical signal of the corresponding pipeline, include: the time domain parameters of the acoustic emission electrical signal of the corresponding pipeline, the frequency domain parameters of the acoustic emission electrical signal of the corresponding pipeline, and the energy parameters of the acoustic emission electrical signal of the corresponding pipeline.

[0132] The time-domain parameters of the acoustic emission signal of the corresponding pipeline include at least one of the following: the voltage amplitude of the acoustic emission signal of the corresponding pipeline, the voltage rise time of the acoustic emission signal of the corresponding pipeline, the voltage duration of the acoustic emission signal of the corresponding pipeline, and the ringing count value within the voltage duration of the acoustic emission signal of the corresponding pipeline.

[0133] The energy parameters of the acoustic emission signal of the corresponding pipeline include at least one of the following: the total energy of the acoustic emission signal of the corresponding pipeline, the frequency band energy of the acoustic emission signal of the corresponding pipeline in the preset frequency band, and the proportion of the frequency band energy of the acoustic emission signal of the corresponding pipeline in the preset frequency band to the total energy.

[0134] The frequency domain parameters of the acoustic emission signal of the corresponding pipeline include at least one of the following: the frequency of the acoustic emission signal of the corresponding pipeline, and the pulse factor of the acoustic emission signal of the corresponding pipeline; wherein, the frequency of the acoustic emission signal of the corresponding pipeline includes at least one of the following: the initial frequency of the acoustic emission signal of the corresponding pipeline, the peak frequency of the acoustic emission signal of the corresponding pipeline, the average frequency of the acoustic emission signal of the corresponding pipeline, and the inverse calculated frequency of the acoustic emission signal of the corresponding pipeline.

[0135] Specifically, the feature parameters obtained by feature extraction of the acoustic emission signal of the pipeline under test include: time-domain parameters of the acoustic emission signal of the pipeline under test, and frequency-domain parameters of the acoustic emission signal of the pipeline under test; wherein, the time-domain parameters of the acoustic emission signal of the pipeline under test include at least one of the following: voltage amplitude of the acoustic emission signal of the pipeline under test, voltage rise time of the acoustic emission signal of the pipeline under test, voltage duration of the acoustic emission signal of the pipeline under test, and ringing count during the voltage duration of the acoustic emission signal of the pipeline under test; the frequency-domain parameters of the acoustic emission signal of the pipeline under test include the following At least one of the following: the total energy of the acoustic emission signal of the pipeline under test, the frequency of the acoustic emission signal of the pipeline under test, the pulse factor of the acoustic emission signal of the pipeline under test, the band energy of the acoustic emission signal of the pipeline under test in a preset frequency band, and the proportion of the band energy of the acoustic emission signal of the corresponding pipeline in the preset frequency band to the total energy; wherein, the frequency of the acoustic emission signal of the pipeline under test includes at least one of the following: the initial frequency of the acoustic emission signal of the pipeline under test, the peak frequency of the acoustic emission signal of the pipeline under test, the average frequency of the acoustic emission signal of the pipeline under test, and the inverse calculated frequency of the acoustic emission signal of the pipeline under test.

[0136] The feature parameters obtained by feature extraction of the acoustic emission signal from the experimental pipeline include: time-domain parameters and frequency-domain parameters of the acoustic emission signal from the experimental pipeline; wherein, the time-domain parameters of the acoustic emission signal from the experimental pipeline include at least one of the following: voltage amplitude, voltage rise time, voltage duration, and ring count during the voltage duration; the frequency-domain parameters of the acoustic emission signal from the experimental pipeline include at least one of the following. One of the following: the total energy of the acoustic emission signal in the experimental pipeline, the frequency of the acoustic emission signal in the experimental pipeline, the pulse factor of the acoustic emission signal in the experimental pipeline, the band energy of the acoustic emission signal in the experimental pipeline in the preset frequency band, and the proportion of the band energy of the acoustic emission signal in the preset frequency band of the corresponding pipeline in the total energy; wherein, the frequency of the acoustic emission signal in the experimental pipeline includes at least one of the following: the initial frequency of the acoustic emission signal in the experimental pipeline, the peak frequency of the acoustic emission signal in the experimental pipeline, the average frequency of the acoustic emission signal in the experimental pipeline, and the inverse calculated frequency of the acoustic emission signal in the experimental pipeline.

[0137] like Figure 7 As shown, the process for identifying cracks in air conditioning pipes based on acoustic emission technology and neural network technology also includes:

[0138] Step 3: Select acoustic emission characteristic values ​​based on the acoustic emission signals of the air conditioning duct in the fatigue test: Select characteristic values ​​of the acoustic emission signals through two different dimensions, time-energy and frequency-energy, to obtain the characteristic values ​​of the acoustic emission signals of the air conditioning duct, and then proceed to step 4.

[0139] In step 3, the eigenvalues ​​of the acoustic emission signal are selected using two different dimensions: time-energy and frequency-energy. Specifically, wavelet packet transform can be used to characterize the acoustic emission signal and obtain its eigenvalues. Wavelet packet transform (WPT) is a signal processing technique that inherits the time-frequency analysis characteristics of wavelet transform and further decomposes undecomposed high-frequency band signals, thereby improving frequency resolution.

[0140] Specifically, the process of characterizing the acoustic emission signal using wavelet packet transform can include: first, determining the spectral characteristics of the acoustic emission signal, selecting an appropriate decomposition level n (n is a positive integer), and decomposing the original signal into 2n... n In each of the nodes, the bandwidth of each node is 1 / 2 of the original signal bandwidth. n Finally, the wavelet coefficients of each node are inversely transformed, and the signal energy of the node is calculated from the signal components corresponding to the node. The energy of different frequency bands is selected from the calculated signal energy as the characteristic values ​​of the acoustic emission signal.

[0141] For example, the acoustic emission signal from one of the air conditioning ducts is selected and subjected to wavelet packet transform. A db4-series wavelet function is chosen, and a three-level wavelet packet decomposition is performed to obtain the energy values ​​of eight frequency bands of the signal. This allows for the selection of energy values ​​for different frequency bands in the acoustic emission signal. The db4-series wavelet function is a discrete wavelet transform function.

[0142] When using wavelet packet transform to characterize acoustic emission signals, the energy of the signal and the energy of each frequency component can be calculated using equations (1) and (2):

[0143]

[0144] Formula (1) can be used to calculate the energy in the signal, where: E i Indicates the energy of the i-band; Let A represent the signal component in frequency band i, and A be the conversion coefficient, which depends on the model of the acoustic emission sensor. Formula (2) can be used to calculate the energy of the signal components in each frequency band. The calculated frequency band energy distribution is as follows: Figure 10 and Figure 11 As shown. Figure 10 A schematic diagram of the energy curves for each frequency band, numbered accordingly. Figure 11 A diagram illustrating the ratio of energy in each frequency band to the total energy, numbered by [the relevant authority]. Figure 10 and Figure 11 It can be seen that the frequency band with the highest energy is band number 2.

[0145] Step 4: Using the feature values ​​of the acoustic emission signal of the air conditioning pipes obtained in Step 3 as samples, a BP neural network is used for neural network training to obtain an air conditioning pipe identification model. Then, the feature values ​​of the acoustic emission signal of the air conditioning pipes obtained on site are identified using the air conditioning pipe identification model to identify whether the air conditioning pipes on site are cracked.

[0146] The waveform of the acoustic emission signal from air conditioning ducts contains four characteristic values: amplitude, rise time, duration, and ring count. These are particularly useful for detecting fatigue cracks in their early stages. The frequency characteristic value represents the frequency at different stages of the acoustic emission signal: the initial frequency is the average frequency before the signal reaches its peak; the peak frequency is the frequency corresponding to the maximum peak in the power spectrum; the inverse frequency is the average frequency after the peak; and the average frequency is the average frequency of the entire acoustic emission signal. These represent the frequencies at different stages of the acoustic emission signal. Ultimately, amplitude, rise time, duration, ring count, initial frequency, peak frequency, inverse frequency, average frequency, signal strength, impulse factor, and the energy percentage of the first four frequency bands are selected as the feature values ​​for neural network training. The acoustic emission signal's characteristic values ​​(such as amplitude, rise time, duration, and ring count) and the frequency band energy (i.e., the energy of the first four frequency bands) are as follows: Figure 12 As shown. Figure 12 This is a schematic diagram of the acoustic emission parameters.

[0147] Determining the presence of fatigue cracks based on acoustic emission signals from air conditioning ducts: When a crack occurs at a location in an air conditioning duct, various acoustic emission parameters change drastically. For example, at the location of the crack, the acoustic emission spectrum increases, the energy is enhanced, and the impulse factor decreases. By inputting the characteristic values ​​and energy frequency bands of the acoustic emission signal into a BP neural network model, the model can be trained to automatically identify the acoustic emission signal. When the acoustic emission signal exhibits the above characteristics during detection, it indicates that fatigue cracks have formed in the air conditioning duct. Figure 13 The figure shows the distribution of pulse factors in acoustic emission signals at different stages. Figure 13This diagram illustrates the distribution of pulse damage factors at different stages (such as the initiation stage, propagation stage, and cracking stage).

[0148] In step 4, a neural network is used to detect cracks in the air conditioning pipes: a BP neural network model is selected to establish the relationship between the air conditioning pipes and acoustic emission signals, enabling real-time identification of cracks in the air conditioning pipes. The training of the neural network involves: X... i As a sample, the sample contains training feature values. A large number of training samples are input into a backpropagation (BP) neural network to establish a nonlinear functional relationship f between the feature values ​​and whether cracks have occurred in the air conditioning pipes. j The feature vector for testing is input into a nonlinear function f to identify whether cracks have occurred in the air conditioning pipes. The input amplitude, rise time, duration, ring count, initial frequency, peak frequency, inverse frequency, average frequency, signal strength, ASL, and energy of the first four frequency bands from the acoustic emission data are used as the input data for the initial nodes of the 14 input layers of the neural network. The output node [1, 0] indicates the presence of a crack. Training samples are randomly selected, accounting for 80% of the total samples. During training, the Levenberg-Marquardt optimization algorithm (LM algorithm) is used, with a maximum iteration count of 2000, a training rate of 0.01, and a minimum training error of 10. -6 Among them, the Levenberg-Marquardt algorithm is a numerical optimization method widely used in nonlinear least squares problems. The remaining 20% ​​of the acoustic emission data is a test sample set.

[0149] In this invention, the acoustic emission signals from fatigue cracks in air conditioning pipes are characterized and then imported into a BP neural network for training and testing. Finally, the neural network is used to identify and detect cracks in the air conditioning pipes online. The results of training and testing the neural network on the air conditioning pipes are shown in Table 1. Table 1 shows that the error rate is 3.56%, indicating that the neural network has high accuracy in identifying cracks in the air conditioning pipes.

[0150] Table 1

[0151] Operating conditions Training data volume Training error percentage Test data volume Test error percentage Air conditioning ducts 100000 3.56％ 30000 3.96％

[0152] In the present invention, fatigue cracks in air conditioning pipes are identified and detected by using neural network technology through acoustic emission. The fatigue cracks in the air conditioning pipes are identified and detected in real time so that timely measures can be taken to extend the service life of the air conditioning pipes.

[0153] Since the processing and functions implemented by the device in this embodiment are basically the same as the embodiments, principles and examples of the aforementioned methods, any details not covered in the description of this embodiment can be found in the relevant descriptions in the aforementioned embodiments, and will not be repeated here.

[0154] According to an embodiment of the present invention, an air conditioner corresponding to a pipe identification device is also provided. This air conditioner may include the pipe identification device described above.

[0155] Since the processing and functions implemented by the air conditioner in this embodiment are basically the same as the embodiments, principles and examples of the aforementioned device, any details not covered in the description of this embodiment can be found in the relevant descriptions in the aforementioned embodiments, and will not be repeated here.

[0156] According to an embodiment of the present invention, a computer program product corresponding to an air conditioner is also provided, including a computer program that, when executed by a processor, implements the steps of the pipeline identification method described above.

[0157] Since the processing and functions implemented by the product in this embodiment are basically the same as those of the aforementioned air conditioner embodiments, principles and examples, any details not covered in this embodiment can be found in the relevant descriptions in the aforementioned embodiments, and will not be repeated here.

[0158] According to an embodiment of the present invention, a storage medium corresponding to the pipeline identification method is also provided, the storage medium including a stored program, wherein, when the program is executed, the device where the storage medium is located controls the execution of the steps of the pipeline identification method described above.

[0159] Since the processing and functions implemented by the storage medium in this embodiment are basically the same as the embodiments, principles and examples of the aforementioned methods, any details not covered in this embodiment can be found in the relevant descriptions in the aforementioned embodiments, and will not be repeated here.

[0160] In summary, it is readily understood by those skilled in the art that, without conflict, the aforementioned advantageous methods can be freely combined and superimposed.

[0161] The above description is merely an embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of the claims of the present invention.

Claims

1. A pipeline identification method, characterized in that, This device is used to identify whether the pipeline under test of a device is cracked; the device includes an air conditioner, and the pipeline under test of the device includes the air conditioner pipeline. The pipeline identification method includes: A finite element model of the air conditioning pipeline was built for simulation analysis. Areas in the air conditioning pipeline where cracks, such as minor fractures or slippage, were selected. An acoustic emission signal acquisition system, such as an acoustic emission sensor, was deployed in the selected area to collect the acoustic emission signals of the air conditioning pipeline. The characteristic parameters of the acoustic emission signals and the parameters indicating whether the air conditioning pipeline is cracked were used as samples. A BP neural network was used to train the neural network to obtain an air conditioning pipeline identification model, which is used to identify whether the air conditioning pipeline is cracked. Acoustic emission signals of the pipeline under test in the pipeline of the device are acquired. Extracting feature parameters from the acoustic emission signal of the pipeline under test, as the acoustic emission feature parameters of the pipeline under test, includes: converting the acoustic emission signal of the pipeline under test into an electrical signal to obtain the acoustic emission electrical signal of the pipeline under test; using wavelet packet analysis to extract features from the acoustic emission electrical signal of the pipeline under test to obtain feature parameters, which are denoted as the acoustic emission feature parameters of the pipeline under test. Based on the acoustic emission characteristic parameters of the pipeline under test, a pre-trained pipeline identification model is used to identify whether the pipeline under test is cracked. If a crack is detected, an alert message is sent. The training process of the pre-trained pipeline identification model includes extracting characteristic parameters from the acoustic emission signals of the experimental pipeline. The acoustic emission characteristic parameters of the pipeline under test and the acoustic emission characteristic parameters of the experimental pipeline include the time-domain parameters, frequency-domain parameters, and energy parameters of the acoustic emission electrical signals of the corresponding pipeline.

2. The pipeline identification method according to claim 1, characterized in that, The training process of the pre-trained pipeline identification model includes: During the experiment to detect cracks in the experimental pipeline, acoustic emission signals from the experimental pipeline were collected, as well as cracking parameters of the experimental pipeline. Feature parameters are extracted from the acoustic emission signal of the experimental pipeline and used as the acoustic emission feature parameters of the experimental pipeline. The acoustic emission characteristic parameters and cracking parameters of the experimental pipeline were used as training samples, and a pre-set neural network model was used as the base model. Using the acoustic emission characteristic parameters of the experimental pipeline as the input parameters of the basic model and the cracking parameters of the experimental pipeline as the output parameters of the basic model, a neural network is trained to obtain the required pipeline identification model.

3. The pipeline identification method according to claim 1 or 2, characterized in that, in, In the case where the training process of the pre-trained pipeline identification model includes extracting feature parameters from the acoustic emission signal of the experimental pipeline, the feature parameters extracted from the acoustic emission signal of the experimental pipeline, as the acoustic emission feature parameters of the experimental pipeline, include: The acoustic emission signal of the experimental pipeline is converted into an electrical signal to obtain the acoustic emission electrical signal of the experimental pipeline. The acoustic emission electrical signal of the experimental pipeline was feature extracted using wavelet packet analysis, and the feature parameters were obtained, which are denoted as the acoustic emission feature parameters of the experimental pipeline.

4. The pipeline identification method according to claim 2, characterized in that, The experimental procedure for detecting cracks in experimental pipelines includes: A finite element model was built for the experimental piping in the equipment. The experimental pipeline is simulated and analyzed using the finite element model to determine the locations in the experimental pipeline where a predetermined degree of fracture or slippage occurs, which are recorded as the dangerous locations of the experimental pipeline. Acoustic emission signals from the experimental pipeline are collected at dangerous locations and within a defined area of ​​the dangerous locations, and cracking parameters of the experimental pipeline are also collected.

5. The pipeline identification method according to claim 4, characterized in that, in, For the pipeline under test in the equipment, the acoustic emission signal of the pipeline under test is acquired, including: Acquire the acoustic emission signal of the pipeline under test, which is collected by a pre-set first acoustic emission signal acquisition system; wherein, the first acoustic emission signal acquisition system is pre-set at a preset crack point on the pipeline under test; And / or, Acoustic emission signals from the experimental pipeline are collected from hazardous locations within the experimental pipeline and from designated areas around those hazardous locations, including: Acoustic emission signals from the experimental pipeline are collected by a pre-set second acoustic emission signal acquisition system; wherein the second acoustic emission signal acquisition system is pre-set at a dangerous location on the experimental pipeline and within a designated area of ​​the dangerous location on the experimental pipeline.

6. The pipeline identification method according to claim 1 or 2, characterized in that, in, The time-domain parameters of the acoustic emission signal of the corresponding pipeline include at least one of the following: the voltage amplitude of the acoustic emission signal of the corresponding pipeline, the voltage rise time of the acoustic emission signal of the corresponding pipeline, the voltage duration of the acoustic emission signal of the corresponding pipeline, and the ringing count value within the voltage duration of the acoustic emission signal of the corresponding pipeline. The energy parameters of the acoustic emission signal of the corresponding pipeline include at least one of the following: the total energy of the acoustic emission signal of the corresponding pipeline, the frequency band energy of the acoustic emission signal of the corresponding pipeline in the preset frequency band, and the proportion of the frequency band energy of the acoustic emission signal of the corresponding pipeline in the preset frequency band to the total energy. The frequency domain parameters of the acoustic emission signal of the corresponding pipeline include at least one of the following: the frequency of the acoustic emission signal of the corresponding pipeline, and the pulse factor of the acoustic emission signal of the corresponding pipeline; wherein, the frequency of the acoustic emission signal of the corresponding pipeline includes at least one of the following: the initial frequency of the acoustic emission signal of the corresponding pipeline, the peak frequency of the acoustic emission signal of the corresponding pipeline, the average frequency of the acoustic emission signal of the corresponding pipeline, and the inverse calculated frequency of the acoustic emission signal of the corresponding pipeline.

7. A pipeline identification device that uses the pipeline identification method as described in any one of claims 1 to 6 to achieve pipeline identification, characterized in that, An instrument for identifying whether a pipeline under test is cracked; the pipeline identification device includes: The acquisition unit is configured to acquire the acoustic emission signal of the pipeline under test in the pipeline of the device. The control unit is configured to extract characteristic parameters from the acoustic emission signal of the pipeline under test, and use them as the acoustic emission characteristic parameters of the pipeline under test. The control unit is also configured to identify whether the pipeline under test is cracked based on the acoustic emission characteristic parameters of the pipeline under test and using a pre-trained pipeline identification model, so as to initiate a reminder message for cracked pipeline under test if cracked pipeline under test is detected.

8. An air conditioner, characterized in that, include: The pipeline identification device as described in claim 7.

9. A storage medium, characterized in that, The storage medium includes a stored program, wherein, when the program is executed, it controls the device containing the storage medium to perform the pipeline identification method according to any one of claims 1 to 6.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the pipeline identification method according to any one of claims 1 to 6.

Images