Tunnel fan state detection method and system, computer device and storage medium

Abstract

The application provides a tunnel fan state detection method and system, computer equipment and a storage medium. The method comprises the following steps: obtaining a first target vibration signal sent by a first laser vibration tester; the first target vibration signal is obtained by interference processing and demodulation processing of a first echo light beam fed back by the fan by the first laser vibration tester; separating the first target vibration signal according to a preset signal mapping model to obtain a mechanical vibration signal and an acoustic vibration signal corresponding to the first target vibration signal; and performing state detection on the fan according to the mechanical vibration signal and the acoustic vibration signal corresponding to the first target vibration signal to obtain a detection result. Based on the signal separation mode, only the vibration signal needs to be collected by the laser vibration tester, the laser vibration tester can non-contact vibration detection, is not affected by the driving vehicles in the tunnel, the detection accuracy is improved, and false positives and false negatives are less likely to occur. In addition, a large number of detection costs are not required to arrange multiple sensors.

Description

Technical Field

[0001] This invention relates to the field of ventilation technology, specifically to a method, system, computer equipment, and storage medium for detecting the condition of a tunnel ventilation fan. Background Technology

[0002] In order to improve airflow and ensure ventilation, tunnels on highways are usually equipped with fans. However, fans can malfunction during use, resulting in abnormal vibrations and noises. Current fan condition monitoring focuses on these two aspects: abnormal vibrations and abnormal noises. Specifically, existing technologies use noise sensors and vibration sensors to detect abnormal noises and vibrations respectively. The detected vibration and noise data are then analyzed to determine whether the fan is in an abnormal state.

[0003] However, the detection performance of noise and vibration sensors is easily affected by vehicles traveling in the tunnel, resulting in the detected data including the vibration and noise of the vehicles, which reduces the detection accuracy and makes it easy for false alarms and missed alarms to occur. Summary of the Invention

[0004] To address the shortcomings of existing technologies, this invention provides a method, system, computer equipment, and storage medium for detecting the condition of tunnel ventilation fans.

[0005] In one embodiment, the present invention provides a method for detecting the status of a tunnel ventilation fan, comprising:

[0006] The vibration signal of the first target sent by the first laser vibration meter is acquired; the vibration signal of the first target is obtained by the first laser vibration meter through interference processing and demodulation processing based on the first echo beam fed back by the fan.

[0007] According to the preset signal mapping model, the vibration signal of the first target is separated to obtain the mechanical vibration signal and the acoustic vibration signal corresponding to the vibration signal of the first target.

[0008] Based on the mechanical vibration signal and acoustic vibration signal corresponding to the first target vibration signal, the condition of the fan is detected, and the detection results are obtained.

[0009] In one embodiment, the signal mapping model includes a signal mapping table, which includes multiple sample vibration signals and corresponding sample mechanical vibration signals and sample acoustic vibration signals. According to the preset signal mapping model, the first target vibration signal is separated to obtain the corresponding mechanical vibration signal and acoustic vibration signal, including:

[0010] Obtain the signal mapping table;

[0011] Based on the first target vibration signal, the corresponding sample vibration signal is matched in the signal mapping table, and the sample mechanical vibration signal and sample acoustic vibration signal corresponding to the matched sample vibration signal are respectively determined as the mechanical vibration signal and acoustic vibration signal corresponding to the first target vibration signal.

[0012] In one embodiment, prior to the step of obtaining the signal mapping table, the tunnel ventilation fan status detection method further includes:

[0013] Model the wind turbine to obtain the wind turbine model;

[0014] Acquire multiple sample mechanical vibration signals and the corresponding sample acoustic vibration signals;

[0015] For each sample mechanical vibration signal, the fan model is simulated based on the sample mechanical vibration signal and the corresponding sample sound vibration signal to obtain the sample vibration signal corresponding to the sample mechanical vibration signal;

[0016] A signal mapping table is obtained based on each sample vibration signal, the corresponding sample mechanical vibration signal, and the sample acoustic vibration signal.

[0017] In one embodiment, the signal mapping model includes a trained signal separation model; according to the preset signal mapping model, the first target vibration signal is separated to obtain the mechanical vibration signal and acoustic vibration signal corresponding to the first target vibration signal, including:

[0018] Obtain the signal separation model;

[0019] The first target vibration signal is input into the signal separation model to obtain the mechanical vibration signal and acoustic vibration signal corresponding to the first target vibration signal output by the signal separation model.

[0020] In one embodiment, the first target vibration signal is the vibration signal of the wind turbine in the vibration direction of the first plane; according to a preset signal mapping model, the first target vibration signal is separated to obtain the mechanical vibration signal and acoustic vibration signal corresponding to the first target vibration signal, including:

[0021] Based on the signal mapping model and the vibration direction of the first plane, the vibration signal of the first target is separated to obtain the mechanical vibration signal and the acoustic vibration signal corresponding to the vibration signal of the first target.

[0022] In one embodiment, the first target vibration signal is separated according to the signal mapping model and the vibration direction of the first plane to obtain the mechanical vibration signal and the acoustic vibration signal corresponding to the first target vibration signal, including:

[0023] Based on the vibration direction of the first plane, the vibration signal of the first target is decomposed to obtain the first decomposed vibration signal in the first decomposed vibration direction and the second decomposed vibration signal in the second decomposed vibration direction.

[0024] Based on the signal mapping model, the first decomposed vibration signal and the second decomposed vibration signal are separated to obtain the mechanical vibration signal and acoustic vibration signal corresponding to the first decomposed vibration signal and the mechanical vibration signal and acoustic vibration signal corresponding to the second decomposed vibration signal.

[0025] Based on the mechanical vibration signal and acoustic vibration signal corresponding to the first target vibration signal, the condition of the fan is monitored, including:

[0026] The condition of the fan is detected based on the mechanical vibration signal and acoustic vibration signal corresponding to the first decomposed vibration signal and the mechanical vibration signal and acoustic vibration signal corresponding to the second decomposed vibration signal.

[0027] In one embodiment, the first target vibration signal is the vibration signal of the fan in the first plane vibration direction; after the step of acquiring the first target vibration signal sent by the first laser vibration meter, the above-mentioned tunnel fan status detection method further includes:

[0028] The vibration signal of the second target sent by the second laser vibration meter is acquired; the vibration signal of the second target is obtained by the second laser vibration meter through interference processing and demodulation processing based on the second echo beam fed back by the fan; the vibration signal of the second target is the vibration signal of the fan in the second plane vibration direction;

[0029] Based on the vibration directions of the first and second planes, the vibration signals of the first and second targets are integrated to obtain a third vibration signal; the third vibration signal is the vibration signal of the fan in the three-dimensional vibration direction.

[0030] Based on the signal mapping model and the three-dimensional vibration direction, the third vibration signal is separated to obtain the mechanical vibration signal and the acoustic vibration signal corresponding to the third vibration signal.

[0031] Based on the mechanical vibration signal and acoustic vibration signal corresponding to the third vibration signal, the condition of the fan is detected, and the detection results are obtained.

[0032] Secondly, the present invention provides a tunnel ventilation fan status detection system, comprising:

[0033] The first laser vibration meter and computer equipment are interconnected;

[0034] The first laser vibration meter is used to send a first transmitted beam to the wind turbine, receive the first echo beam fed back by the wind turbine according to the first transmitted beam, and perform interference processing on the first echo beam to obtain a first laser signal. The first laser signal is demodulated to obtain a first target vibration signal, and the first target vibration signal is sent to the computer equipment.

[0035] The computer equipment is used to separate the first target vibration signal according to a preset signal mapping model to obtain the mechanical vibration signal and sound vibration signal corresponding to the first target vibration signal; and to perform state detection on the fan according to the mechanical vibration signal and sound vibration signal corresponding to the first target vibration signal to obtain the detection result.

[0036] Thirdly, in one embodiment, the present invention provides a computer device including a memory and a processor; the memory stores a computer program, and the processor is used to run the computer program in the memory to perform the steps in the tunnel ventilation fan status detection method of any of the above embodiments.

[0037] Fourthly, in one embodiment, the present invention provides a storage medium storing a computer program that is loaded by a processor to perform the steps in the tunnel ventilation fan status detection method of any of the above embodiments.

[0038] The aforementioned tunnel ventilation fan status detection method, system, computer equipment, and storage medium acquire and process target vibration signals obtained from a laser vibration meter. Since sound is essentially vibration, the target vibration signal simultaneously includes the mechanical vibration corresponding to abnormal vibration and the acoustic vibration corresponding to abnormal noise. Subsequently, the vibration signal can be separated using a preset signal mapping model to obtain the required mechanical vibration signal and acoustic vibration signal. Finally, the ventilation fan status is detected based on the mechanical vibration signal and acoustic vibration signal. Based on the signal separation method, only a laser vibration meter is needed to acquire the vibration signal. The laser vibration meter can achieve non-contact vibration measurement of the ventilation fan itself, which is not affected by vehicles traveling in the tunnel, improving detection accuracy and reducing the likelihood of false alarms and missed alarms. In addition, it eliminates the need to spend a lot of detection costs to deploy multiple sensors. Attached Figure Description

[0039] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0040] Figure 1This is a schematic diagram illustrating an application scenario of the tunnel ventilation fan status detection method in one embodiment of the present invention;

[0041] Figure 2 This is a flowchart illustrating a tunnel ventilation fan status detection method in one embodiment of the present invention;

[0042] Figure 3 This is a schematic diagram illustrating the separation of a first target vibration signal into a mechanical vibration signal and an acoustic vibration signal in one embodiment of the present invention;

[0043] Figure 4 This is a schematic diagram of the tunnel ventilation fan status detection device in one embodiment of the present invention;

[0044] Figure 5 This is a schematic diagram of the internal structure of a computer device according to one embodiment of the present invention. Detailed Implementation

[0045] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0046] In the description of this invention, it should be understood that the terms "center," "longitudinal," "lateral," "length," "width," "thickness," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," and "outer," etc., indicating orientation or positional relationships based on the orientation or positional relationships shown in the accompanying drawings, are only for the convenience of describing the invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of the invention. Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, features defined with "first" and "second" may explicitly or implicitly include one or more of the stated features. In the description of this application, "a plurality of" means two or more, unless otherwise explicitly specified. In this application, the term "exemplary" is used to mean "used as an example, illustration, or description." Any embodiment described as "exemplary" in this application is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is provided to enable any person skilled in the art to implement and use the invention. In the following description, details are set forth for purposes of explanation. It should be understood that those skilled in the art will recognize that the invention can be implemented without using these specific details. In other instances, well-known structures and processes will not be described in detail to avoid obscuring the description of the invention with unnecessary detail. Therefore, the invention is not intended to be limited to the embodiments shown, but is consistent with the broadest scope of the principles and features disclosed herein.

[0047] The tunnel ventilation fan status detection method in this embodiment of the invention is applied to a tunnel ventilation fan status detection device, which is set on a computer device. The computer device can be a terminal, such as a mobile phone or a tablet computer, or it can be a server or a service cluster composed of multiple servers.

[0048] like Figure 1 As shown, Figure 1 This is a schematic diagram of an application scenario for the tunnel ventilation fan status detection method according to an embodiment of the present invention. The application scenario of the tunnel ventilation fan status detection method in this embodiment includes a computer device 100 (the computer device 100 integrates a tunnel ventilation fan status detection device), and a computer-readable storage medium corresponding to the tunnel ventilation fan status detection method is run in the computer device 100 to execute the steps of the tunnel ventilation fan status detection method.

[0049] Understandable Figure 1The computer equipment in the application scenario of the tunnel ventilation fan status detection method, or the devices contained in the computer equipment, do not constitute a limitation on the embodiments of the present invention. That is, the number or type of equipment in the application scenario of the tunnel ventilation fan status detection method, or the number or type of devices contained in each equipment, do not affect the overall implementation of the technical solution in the embodiments of the present invention, and can all be considered as equivalent substitutions or derivatives of the technical solutions claimed in the embodiments of the present invention.

[0050] In this embodiment of the invention, the computer device 100 can be an independent device, or a network of devices or a cluster of devices. For example, the computer device 100 described in this embodiment of the invention includes, but is not limited to, a computer, a network host, a single network device, a set of multiple network devices, or a cloud device composed of multiple devices. The cloud device consists of a large number of computers or network devices based on cloud computing.

[0051] Those skilled in the art will understand that Figure 1 The application scenarios shown are merely one example corresponding to the technical solution of this invention and do not constitute a limitation on the application scenarios of the technical solution of this invention. Other application scenarios may include more than one example. Figure 1 The more or fewer computer devices shown, or the network connections of the computer devices, for example Figure 1 Only one computer device is shown in the diagram. It is understood that the scenario of the tunnel ventilation fan status detection method may also include one or more other computer devices, which are not specifically limited here. The computer device 100 may also include a memory for storing information related to the tunnel ventilation fan status detection method.

[0052] Furthermore, in the application scenario of the tunnel ventilation fan status detection method in this embodiment of the invention, the computer device 100 may be equipped with a display device, or the computer device 100 may not have a display device but may be communicatively connected to an external display device 200. The display device 200 is used to output the results of the tunnel ventilation fan status detection method executed in the computer device. The computer device 100 may access a background database 300 (the background database 300 may be the local storage of the computer device 100, or it may be located in the cloud), and the background database 300 stores information related to the tunnel ventilation fan status detection method.

[0053] It should be noted that, Figure 1 The application scenario of the tunnel ventilation fan status detection method shown is merely an example. The application scenario of the tunnel ventilation fan status detection method described in the embodiments of the present invention is to more clearly illustrate the technical solution of the embodiments of the present invention, and does not constitute a limitation on the technical solution provided by the embodiments of the present invention.

[0054] Based on the application scenarios of the tunnel ventilation fan condition detection method described above, an embodiment of the tunnel ventilation fan condition detection method is proposed.

[0055] Firstly, such as Figure 2 As shown, in one embodiment, the present invention provides a method for detecting the status of a tunnel ventilation fan, comprising:

[0056] Step 201: Obtain the first target vibration signal sent by the first laser vibrometer;

[0057] The vibration signal of the first target is obtained by the first laser vibration meter through interference processing and demodulation processing based on the first echo beam fed back by the fan.

[0058] Among them, the laser vibration meter is a measuring instrument that uses the laser Doppler effect, optical heterodyne interference and other principles to measure the vibration of objects. Compared with traditional sensors such as accelerometers, it has the advantages of long-distance measurement, non-contact, high spatial resolution, short measurement time, wide response bandwidth and high velocity resolution. It is widely used in modal characteristic analysis of models, quality inspection, online control, structural flaw detection, health and medical fields.

[0059] The laser vibrometer mainly consists of a high-precision laser interferometer and a signal processor. The polarized beam (with a frequency of F0) emitted by the laser in the high-precision laser interferometer is split into two paths by a beam splitter: one as the emitted beam and the other as the reference beam. The reference beam has a certain frequency shift (F) after passing through an acousto-optic modulator. The emitted beam is focused onto the surface of the object being measured. The vibration of the object causes a Doppler frequency shift (f = 2v / λ) in the emitted beam. Specifically, during wave propagation, the frequency changes with the relative motion between the wave source and the observer. When light shines on a moving object... When the object is on the surface, for the photodetector, the frequency of the light scattered from its surface changes due to the object's motion (this frequency change is related to the object's speed, direction, wavelength, and the incident direction of the light). The reflected light then contains the Doppler frequency shift, and this reflected light interferes with the previous reference beam to obtain a laser signal with a frequency of F0+F+f. This laser signal carries the vibration information of the object being measured. The signal processor demodulates the laser signal obtained from the high-precision laser interferometer and, based on the frequency change, obtains the target vibration signal of the object being measured.

[0060] In this embodiment, the high-precision laser interferometer in the first laser vibration meter sends a first emitted beam to the wind turbine under test. The first emitted beam reaches the surface of the wind turbine, and due to the vibration of the wind turbine, a Doppler frequency shift is caused, which causes the wind turbine to feed back a first echo beam containing the Doppler frequency shift. Then, the first echo beam and the first reference beam obtained by beam splitting are interfered to obtain a first laser signal. The first laser signal is sent to the signal processor in the first laser vibration meter. The signal processor in the first laser vibration meter demodulates the first laser signal to obtain the first target vibration signal of the wind turbine. Finally, the first target vibration signal is sent to the execution subject of the tunnel wind turbine state detection method in this embodiment, namely the computer equipment.

[0061] Step 202: According to the preset signal mapping model, the vibration signal of the first target is separated to obtain the mechanical vibration signal and the sound vibration signal corresponding to the vibration signal of the first target.

[0062] In the process of monitoring the condition of a wind turbine, it is necessary to make judgments based on both the mechanical vibration caused by abnormal vibration and the acoustic vibration caused by abnormal noise. The first target vibration signal contains both mechanical and acoustic vibrations; therefore, the first target vibration signal can be processed to obtain the corresponding mechanical and acoustic vibration signals. Figure 3 As shown, the waveform in the left figure is the first target vibration signal obtained, the waveform in the upper part of the right box is the separated mechanical vibration signal, and the waveform in the lower part of the right box is the separated acoustic vibration signal.

[0063] The signal mapping model contains a mapping relationship between the target vibration signal and the mechanical vibration signal and the acoustic vibration signal. Based on this mapping relationship, the separation of the first target vibration signal can be achieved, that is, the mechanical vibration signal and the acoustic vibration signal corresponding to the first target vibration signal can be determined.

[0064] In other embodiments, the vibration signal of the first target can be directly divided according to frequency. Specifically, mechanical vibration signals are usually low-frequency signals, while sound vibration signals are usually high-frequency signals. Thus, high and low frequencies can be directly determined based on frequency thresholds, and then the vibration signal of the first target can be separated based on high and low frequencies to obtain low-frequency mechanical vibration signals and high-frequency sound vibration signals. However, in this method, mechanical vibration may also be a high-frequency signal, and sound signals may also be low-frequency signals. Therefore, directly separating based on high and low frequencies results in mechanical vibration signals and sound vibration signals that do not conform to the actual situation of the fan, thereby reducing the accuracy of detection.

[0065] Step 203: Based on the mechanical vibration signal and acoustic vibration signal corresponding to the first target vibration signal, perform state detection on the fan to obtain the detection result;

[0066] Once the mechanical vibration signal and acoustic vibration signal of the fan are obtained, condition detection can be performed. For example, the first individual detection result of the fan can be determined based on the mechanical vibration signal, and the second individual detection result can be determined based on the acoustic vibration signal. Of course, the comprehensive detection result of the fan can also be determined based on both the mechanical vibration signal and the acoustic vibration signal. Based on the known mechanical vibration signal and acoustic vibration signal, the mechanical vibration signal and acoustic vibration signal can be used in any way to perform comprehensive condition detection.

[0067] The test results indicate whether the fan has a fault. If a fault exists, the test results further indicate what kind of fault it is or what the fault is.

[0068] The aforementioned tunnel ventilation fan status detection method acquires and processes target vibration signals collected by a laser vibration meter. Since sound is essentially vibration, the target vibration signal simultaneously includes the mechanical vibration corresponding to abnormal vibration and the acoustic vibration corresponding to abnormal noise. Subsequently, the vibration signal can be separated using a preset signal mapping model to obtain the required mechanical vibration signal and acoustic vibration signal. Finally, the ventilation fan status is detected based on the mechanical vibration signal and acoustic vibration signal. Based on the signal separation method, only a laser vibration meter is needed to collect vibration signals. The laser vibration meter can achieve non-contact vibration measurement of the ventilation fan itself, which is not affected by vehicles traveling in the tunnel, thus improving detection accuracy and reducing the likelihood of false alarms and missed alarms. In addition, it eliminates the need to spend a lot of detection costs to deploy multiple sensors.

[0069] In one embodiment, the signal mapping model includes a signal mapping table, which includes multiple sample vibration signals and corresponding sample mechanical vibration signals and sample acoustic vibration signals. According to the preset signal mapping model, the first target vibration signal is separated to obtain the corresponding mechanical vibration signal and acoustic vibration signal, including:

[0070] Obtain the signal mapping table;

[0071] Among them, the signal mapping table method requires the pre-construction of multiple samples. The sample range needs to cover all possible vibration situations of the wind turbine as much as possible, that is, to ensure that each detected target vibration signal can be matched with the corresponding sample mechanical vibration signal and sample sound vibration signal in the signal mapping table.

[0072] Among them, the samples can be historical big data, that is, the target vibration signals that have appeared in the past as well as the actual detected mechanical vibration signals and sound vibration signals; historical big data can include all the same type of fans in the tunnel, so as to expand the number of samples, that is, expand the sample coverage, while ensuring the validity of the samples.

[0073] Based on the first target vibration signal, the corresponding sample vibration signal is matched in the signal mapping table, and the sample mechanical vibration signal and sample acoustic vibration signal corresponding to the matched sample vibration signal are respectively determined as the mechanical vibration signal and acoustic vibration signal corresponding to the first target vibration signal.

[0074] In the matching process in the signal mapping table, the similarity between the first target vibration signal and each sample vibration signal in the signal mapping table is determined. The sample vibration signal with the highest similarity and greater than the similarity threshold is determined. The sample mechanical vibration signal and sample sound vibration signal corresponding to the sample vibration signal are respectively determined as the mechanical vibration signal and sound vibration signal corresponding to the first target vibration signal.

[0075] If the matched sample vibration signal has the highest similarity but the similarity is not greater than the similarity threshold, the match is considered to have failed.

[0076] By using a mapping table based on a large number of pre-built samples, the separation of target vibration signals can be completed more quickly and accurately. However, the drawback is that the success rate of matching depends on the coverage of the samples. To achieve complete coverage, a large number of samples need to be built.

[0077] In one embodiment, prior to the step of obtaining the signal mapping table, the tunnel ventilation fan status detection method further includes:

[0078] Model the wind turbine to obtain the wind turbine model;

[0079] As mentioned in the above embodiments, the samples in the signal mapping table can be obtained through historical big data. However, due to storage or other reasons, the number of samples that can be obtained from historical big data is small, which cannot meet the needs of the signal mapping table. Therefore, in this embodiment, samples can be obtained through simulation. First, a three-dimensional model of the wind turbine can be performed to obtain the corresponding wind turbine model.

[0080] Acquire multiple sample mechanical vibration signals and the corresponding sample acoustic vibration signals;

[0081] Among them, the sample mechanical vibration signal and the sample sound vibration signal can be generated randomly, or they can be generated in a targeted manner for various types of faults of the fan;

[0082] For each sample mechanical vibration signal, the fan model is simulated based on the sample mechanical vibration signal and the corresponding sample sound vibration signal to obtain the sample vibration signal corresponding to the sample mechanical vibration signal;

[0083] Each sample mechanical vibration signal and its corresponding sample acoustic vibration signal constitute a set of simulation parameters. Each set of simulation parameters is added to the constructed wind turbine model to detect the simulated vibration signal exhibited by the wind turbine model for each set of simulation parameters. Each simulated vibration signal is used as a sample vibration signal for each set of simulation parameters.

[0084] Based on each sample vibration signal, the corresponding sample mechanical vibration signal, and the sample acoustic vibration signal, a signal mapping table is obtained;

[0085] By associating each set of simulated parameters (i.e., a sample mechanical vibration signal and a sample acoustic vibration signal) with the corresponding simulated vibration signal (i.e., the sample vibration signal), a signal mapping table can be obtained, which can then be stored as a template library.

[0086] By constructing and simulating wind turbine models to obtain samples, a larger number of samples can be obtained compared to obtaining samples from historical big data, thus ensuring the coverage of the samples. In addition, 3D modeling can completely follow the structure of the actual wind turbine, thereby improving the quality of the samples and improving the accuracy of subsequent condition detection of the actual wind turbine being modeled.

[0087] In one embodiment, the signal mapping model includes a trained signal separation model; according to the preset signal mapping model, the first target vibration signal is separated to obtain the mechanical vibration signal and acoustic vibration signal corresponding to the first target vibration signal, including:

[0088] Obtain the signal separation model;

[0089] As mentioned in the above embodiments, the vibration signal of the first target can be separated by a signal mapping table. However, the success rate of the separation depends on the coverage of the samples in the signal mapping table. To ensure the success rate, a large number of samples need to be pre-configured. Therefore, in this embodiment, an AI (Artificial Intelligence) model can be used, employing various typical high-performance machine learning algorithms for efficient processing. The signal separation model can be trained with non-exhaustive samples to learn the ability to separate signals. After training, it can automatically separate the vibration signal of the first target, and there is no need to open a database to store the signal mapping table, saving storage space.

[0090] The first target vibration signal is input into the signal separation model to obtain the mechanical vibration signal and acoustic vibration signal corresponding to the first target vibration signal output by the signal separation model.

[0091] The first target vibration signal is input into the signal separation model. Since the signal separation model has learned the separation capability through the training process, it can automatically separate the first target vibration signal according to the learned separation capability, and then output the separated mechanical vibration signal and sound vibration signal. Furthermore, based on unsupervised learning, the signal separation model can be trained again according to the input and output in the actual process to improve the separation capability.

[0092] By leveraging the advantages of AI algorithms and training and learning with a large amount of data, the signal separation model can automatically avoid some errors, thereby improving the efficiency and applicability of signal separation. In addition, the signal separation model can handle various types of target vibration signals and is not limited by the coverage area, unlike signal mapping tables.

[0093] In one embodiment, the training steps of the signal separation model include:

[0094] A training sample set is obtained, which includes multiple training samples. Each training sample includes a training vibration signal and a corresponding training mechanical vibration signal and a training sound vibration signal. The training mechanical vibration signal and the training sound vibration signal are obtained through manual processing. That is, a supervised learning method is used for training. In other embodiments, an unsupervised learning method can also be used for training.

[0095] The training vibration signals in the training sample set are used as inputs to the signal separation model, and the corresponding training mechanical vibration signals and training acoustic vibration signals are used as the expected outputs of the signal separation model to train the signal separation model.

[0096] Determine the comparison result between the actual output and the expected output of the signal separation model. If the comparison result does not meet the requirements, update the model parameters of the signal separation model based on the comparison result.

[0097] Obtain the next training sample set until the alignment results meet the requirements.

[0098] In one embodiment, the comparison result between the actual output and the expected output of the signal separation model is determined. If the comparison result does not meet the requirements, the model parameters of the signal separation model are updated according to the comparison result, including:

[0099] Determine the comparison difference between the actual output and the expected output of the signal separation model, and calculate the loss based on the comparison difference;

[0100] If the loss does not meet the preset convergence condition, the model parameters of the signal separation model are updated according to the loss.

[0101] In one embodiment, the first target vibration signal is the vibration signal of the wind turbine in the vibration direction of the first plane; according to a preset signal mapping model, the first target vibration signal is separated to obtain the mechanical vibration signal and acoustic vibration signal corresponding to the first target vibration signal, including:

[0102] Based on the signal mapping model and the vibration direction of the first plane, the vibration signal of the first target is separated to obtain the mechanical vibration signal and the acoustic vibration signal corresponding to the vibration signal of the first target.

[0103] Among them, the laser vibrometer can not only detect the vibration displacement and vibration velocity of the object under test, but also detect the vibration direction of the object under test based on the frequency change; therefore, in this embodiment, the first laser vibrometer can simultaneously send the first target vibration signal and the corresponding first plane vibration direction to the computer device, that is, send the first target vibration signal with the first plane vibration direction.

[0104] While laser vibration meters can detect the vibration direction of the object being measured, their operation is limited to a single plane based on their principle. In other words, the vibration direction is only two-dimensional, which is the planar vibration direction in this embodiment. Therefore, when using a laser vibration meter, the usual vibration direction of the fan needs to be determined in advance during the arrangement process so that the plane detected by the laser vibration meter can cover most of the fan's vibration directions.

[0105] Since the wind turbine is not a symmetrical structure, vibration signals in different directions represent different types of faults in the wind turbine. Therefore, by combining the vibration direction of the first plane, the vibration signal of the first target can be separated more precisely according to the signal mapping model, thereby separating the directional mechanical vibration signal and the acoustic vibration signal, improving the separation accuracy. Fault judgment is made based on the directional mechanical vibration signal and the acoustic vibration signal, which improves the condition detection accuracy.

[0106] In one embodiment, the first target vibration signal is separated according to the signal mapping model and the vibration direction of the first plane to obtain the mechanical vibration signal and the acoustic vibration signal corresponding to the first target vibration signal, including:

[0107] Based on the vibration direction of the first plane, the vibration signal of the first target is decomposed to obtain the first decomposed vibration signal in the first decomposed vibration direction and the second decomposed vibration signal in the second decomposed vibration direction.

[0108] In this embodiment, separating the directional target vibration signal using a signal mapping table would significantly increase the number of samples required. Therefore, in this embodiment, the first target vibration signal can be decomposed according to direction, such as vertical and horizontal directions, to obtain a first decomposed vibration signal in the vertical direction and a second decomposed vibration signal in the horizontal direction. This results in decomposed vibration signals in two fixed directions. When performing signal separation using a signal mapping table later, it is only necessary to require that the signal mapping table contains samples in these two directions. Of course, in other embodiments, decomposition can also be performed according to other directions.

[0109] Based on the signal mapping model, the first decomposed vibration signal and the second decomposed vibration signal are separated to obtain the mechanical vibration signal and acoustic vibration signal corresponding to the first decomposed vibration signal and the mechanical vibration signal and acoustic vibration signal corresponding to the second decomposed vibration signal.

[0110] Since the vibration signal of the first target is decomposed in direction, it is necessary to separate the first decomposed vibration signal and the second decomposed vibration signal respectively to obtain two sets of mechanical vibration signals and sound vibration signals.

[0111] Based on the mechanical vibration signal and acoustic vibration signal corresponding to the first target vibration signal, the condition of the fan is monitored, including:

[0112] The condition of the fan is detected based on the mechanical vibration signal and acoustic vibration signal corresponding to the first decomposed vibration signal and the mechanical vibration signal and acoustic vibration signal corresponding to the second decomposed vibration signal.

[0113] Similar to the above embodiments, fault diagnosis can be performed based on mechanical vibration signals or sound vibration signals alone, or simultaneously based on both mechanical vibration signals and sound vibration signals. It should be noted that judging faults based solely on mechanical vibration signals means judging faults based on mechanical vibration signals in two directions after decomposition. Similarly, judging faults based solely on sound vibration signals means judging faults based on sound vibration signals in two directions after decomposition.

[0114] In one embodiment, the first target vibration signal is the vibration signal of the fan in the first plane vibration direction; after the step of acquiring the first target vibration signal sent by the first laser vibration meter, the above-mentioned tunnel fan status detection method further includes:

[0115] Acquire the vibration signal of the second target sent by the second laser vibrometer;

[0116] The second target vibration signal is obtained by the second laser vibration meter through interference processing and demodulation processing based on the second echo beam fed back by the wind turbine; the second target vibration signal is the vibration signal of the wind turbine in the second plane vibration direction;

[0117] As mentioned in the above embodiments, a laser vibrometer can determine the vibration direction on a plane, but it cannot determine the vibration direction in three dimensions; therefore, in this embodiment, a laser vibrometer can be added to determine the vibration direction on two planes.

[0118] Based on the vibration directions of the first and second planes, the vibration signals of the first and second targets are integrated to obtain a third vibration signal; the third vibration signal is the vibration signal of the fan in the three-dimensional vibration direction.

[0119] Among them, based on the vibration direction of the first plane and the vibration direction of the second plane, the corresponding three-dimensional vibration direction in the three-dimensional space can be determined, that is, the third target vibration signal corresponding to the vibration signal of the first target and the vibration signal of the second target can be integrated to obtain the vibration signal of the third target.

[0120] Based on the signal mapping model and the three-dimensional vibration direction, the third vibration signal is separated to obtain the mechanical vibration signal and the acoustic vibration signal corresponding to the third vibration signal.

[0121] In this case, after separating the third vibration signal, the above-mentioned directional decomposition method can also be used. The difference is that the third vibration signal is a vibration signal in the three-dimensional vibration direction. Therefore, the decomposition can be carried out in three directions, such as the vertical direction, the horizontal direction and the depth direction (which can be understood as the XYZ three axes). Then, the signal is separated for the three decomposed vibration signals respectively.

[0122] Based on the mechanical vibration signal and acoustic vibration signal corresponding to the third vibration signal, the condition of the fan is detected, and the detection results are obtained.

[0123] In one embodiment, such as Figure 4 As shown, the present invention provides a tunnel ventilation fan status detection device, comprising:

[0124] The signal acquisition module 301 is used to acquire the first target vibration signal sent by the first laser vibration meter; the first target vibration signal is obtained by the first laser vibration meter through interference processing and demodulation processing based on the first echo beam fed back by the fan.

[0125] The signal separation module 302 is used to separate the first target vibration signal according to the preset signal mapping model to obtain the mechanical vibration signal and the sound vibration signal corresponding to the first target vibration signal;

[0126] The status detection module 303 is used to perform status detection on the fan based on the mechanical vibration signal and sound vibration signal corresponding to the first target vibration signal, and obtain the detection result.

[0127] The aforementioned tunnel ventilation fan status detection device acquires and processes the target vibration signal obtained by a laser vibration meter. Since sound is essentially vibration, the target vibration signal simultaneously includes the mechanical vibration corresponding to the abnormal vibration and the acoustic vibration corresponding to the abnormal noise. Subsequently, the vibration signal can be separated using a preset signal mapping model to obtain the required mechanical vibration signal and acoustic vibration signal. Finally, the ventilation fan status is detected based on the mechanical vibration signal and acoustic vibration signal. Based on the signal separation method, only the vibration signal needs to be acquired by a laser vibration meter. The laser vibration meter can achieve non-contact vibration measurement of the ventilation fan itself, which is not affected by vehicles traveling in the tunnel, thus improving detection accuracy and reducing the likelihood of false alarms and missed alarms. In addition, it eliminates the need to spend a lot of detection costs to deploy multiple sensors.

[0128] In one embodiment, the signal mapping model includes a signal mapping table, which includes multiple sample vibration signals and sample mechanical vibration signals and sample acoustic vibration signals corresponding to the sample vibration signals; the signal separation module is specifically used to obtain the signal mapping table; according to the first target vibration signal, the corresponding sample vibration signal is matched in the signal mapping table, and the sample mechanical vibration signal and sample acoustic vibration signal corresponding to the matched sample vibration signal are respectively determined as the mechanical vibration signal and acoustic vibration signal corresponding to the first target vibration signal.

[0129] In one embodiment, the tunnel ventilation fan status detection device further includes:

[0130] The sample acquisition module is used to model the wind turbine before obtaining the signal mapping table, thereby obtaining a wind turbine model; acquire multiple sample mechanical vibration signals and corresponding sample acoustic vibration signals; for each sample mechanical vibration signal, simulate the wind turbine model based on the sample mechanical vibration signal and the corresponding sample acoustic vibration signal to obtain the sample vibration signal corresponding to the sample mechanical vibration signal; and obtain a signal mapping table based on each sample vibration signal, the corresponding sample mechanical vibration signal, and the sample acoustic vibration signal.

[0131] In one embodiment, the signal mapping model includes a trained signal separation model; the signal separation module is specifically used to acquire the signal separation model; the first target vibration signal is input into the signal separation model to obtain the mechanical vibration signal and acoustic vibration signal corresponding to the first target vibration signal output by the signal separation model.

[0132] In one embodiment, the first target vibration signal is the vibration signal of the fan in the vibration direction of the first plane; the signal separation module is specifically used to separate the first target vibration signal according to the signal mapping model and the vibration direction of the first plane to obtain the mechanical vibration signal and the acoustic vibration signal corresponding to the first target vibration signal.

[0133] In one embodiment, the signal separation module is specifically used to decompose the first target vibration signal according to the first plane vibration direction to obtain a first decomposed vibration signal in the first decomposed vibration direction and a second decomposed vibration signal in the second decomposed vibration direction; and to separate the first decomposed vibration signal and the second decomposed vibration signal according to the signal mapping model to obtain the mechanical vibration signal and acoustic vibration signal corresponding to the first decomposed vibration signal and the mechanical vibration signal and acoustic vibration signal corresponding to the second decomposed vibration signal.

[0134] The status detection module is specifically used to detect the status of the fan based on the mechanical vibration signal and acoustic vibration signal corresponding to the first decomposed vibration signal and the mechanical vibration signal and acoustic vibration signal corresponding to the second decomposed vibration signal.

[0135] In one embodiment, the first target vibration signal is the vibration signal of the wind turbine in the first planar vibration direction; the signal acquisition module is further configured to acquire the second target vibration signal sent by the second laser vibration meter after acquiring the first target vibration signal sent by the first laser vibration meter; the second target vibration signal is obtained by the second laser vibration meter through interference processing and demodulation processing based on the second echo beam fed back by the wind turbine; the second target vibration signal is the vibration signal of the wind turbine in the second planar vibration direction; the first target vibration signal and the second target vibration signal are integrated according to the first planar vibration direction and the second planar vibration direction to obtain a third vibration signal; the third vibration signal is the vibration signal of the wind turbine in the three-dimensional vibration direction;

[0136] The signal separation module is also used to separate the third vibration signal according to the signal mapping model and the three-dimensional vibration direction to obtain the mechanical vibration signal and the sound vibration signal corresponding to the third vibration signal;

[0137] The condition detection module is also used to perform condition detection on the fan based on the mechanical vibration signal and sound vibration signal corresponding to the third vibration signal, and obtain the detection results.

[0138] Secondly, the present invention provides a tunnel ventilation fan status detection system, comprising:

[0139] The first laser vibration meter and computer equipment are interconnected;

[0140] The first laser vibration meter is used to send a first transmitted beam to the wind turbine, receive the first echo beam fed back by the wind turbine according to the first transmitted beam, and perform interference processing on the first echo beam to obtain a first laser signal. The first laser signal is demodulated to obtain a first target vibration signal, and the first target vibration signal is sent to the computer equipment.

[0141] The computer equipment is used to separate the first target vibration signal according to a preset signal mapping model to obtain the mechanical vibration signal and sound vibration signal corresponding to the first target vibration signal; and to perform state detection on the fan according to the mechanical vibration signal and sound vibration signal corresponding to the first target vibration signal to obtain the detection result.

[0142] The aforementioned tunnel ventilation fan status detection system acquires and processes target vibration signals collected by a laser vibration meter. Since sound is essentially vibration, the target vibration signal simultaneously includes the mechanical vibration corresponding to abnormal vibration and the acoustic vibration corresponding to abnormal noise. Subsequently, the vibration signal can be separated using a preset signal mapping model to obtain the required mechanical vibration signal and acoustic vibration signal. Finally, the fan status is detected based on the mechanical vibration signal and acoustic vibration signal. Based on the signal separation method, only a laser vibration meter is needed to collect vibration signals. The laser vibration meter can achieve non-contact vibration measurement of the fan itself, which is not affected by vehicles traveling in the tunnel, improving detection accuracy and reducing the likelihood of false alarms and missed alarms. In addition, it eliminates the need to spend a lot of detection costs to deploy multiple sensors.

[0143] In one embodiment, the first target vibration signal is the vibration signal of the fan in the first plane vibration direction; the tunnel fan condition detection system further includes a second laser vibration meter connected to computer equipment.

[0144] The second laser vibration meter is used to emit a second transmitted beam to the wind turbine, receive the second echo beam fed back by the wind turbine according to the second transmitted beam, and perform interference processing on the second echo beam to obtain a second laser signal. The second laser signal is then demodulated to obtain a second target vibration signal, which is then sent to a computer device. The second target vibration signal is the vibration signal of the wind turbine in the second plane vibration direction.

[0145] The computer equipment is also used to separate the first target vibration signal and the second target vibration signal according to the signal mapping model, the vibration direction of the first plane and the vibration direction of the second plane, to obtain the mechanical vibration signal and the acoustic vibration signal corresponding to the first target vibration signal and the second target vibration signal; and to perform state detection on the fan according to the mechanical vibration signal and the acoustic vibration signal corresponding to the first target vibration signal and the second target vibration signal, and to obtain the detection result.

[0146] Thirdly, in one embodiment, the present invention provides a computer device, such as... Figure 5 As shown, it illustrates the structure of the computer device involved in this invention, specifically:

[0147] The computer device may include components such as a processor 401 with one or more processing cores, a memory 402 with one or more computer-readable storage media, a power supply 403, and an input unit 404. Those skilled in the art will understand that... Figure 5 The structure of the computer device shown does not constitute a limitation on the computer device and may include more or fewer components than shown, or combine certain components, or have different component arrangements. Wherein:

[0148] The processor 401 is the control center of the computer device. It connects various parts of the computer device via various interfaces and lines, and performs various functions and processes data by running or executing software programs and / or modules stored in the memory 402, and by calling data stored in the memory 402, thereby providing overall monitoring of the computer device. Optionally, the processor 401 may include one or more processing cores; preferably, the processor 401 may integrate an application processor and a modem processor, wherein the application processor mainly handles the operating system, user interface, and computer programs, and the modem processor mainly handles wireless communication. It is understood that the modem processor may not be integrated into the processor 401.

[0149] The memory 402 can be used to store software programs and modules. The processor 401 executes various functional applications and data processing by running the software programs and modules stored in the memory 402. The memory 402 may mainly include a program storage area and a data storage area. The program storage area may store the operating system, computer programs required for at least one function (such as sound playback function, image playback function, etc.), etc.; the data storage area may store data created according to the use of the server, etc. In addition, the memory 402 may include high-speed random access memory, and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other volatile solid-state storage device. Accordingly, the memory 402 may also include a memory controller to provide the processor 401 with access to the memory 402.

[0150] The computer device also includes a power supply 403 that supplies power to the various components. Preferably, the power supply 403 can be logically connected to the processor 401 through a power management system, thereby enabling functions such as charging, discharging, and power consumption management through the power management system. The power supply 403 may also include one or more DC or AC power supplies, recharging systems, power fault detection circuits, power converters or inverters, power status indicators, and other arbitrary components.

[0151] The computer device may also include an input unit 404, which can be used to receive input digital or character information and generate keyboard, mouse, joystick, optical or trackball signal inputs related to user settings and function control.

[0152] Although not shown, the computer device may also include a display unit, etc., which will not be described in detail here. Specifically, in this embodiment, the processor 401 in the computer device loads the executable files corresponding to the processes of one or more computer programs into the memory 402 according to the following instructions, and the processor 401 runs the computer programs stored in the memory 402 to perform the following steps:

[0153] The vibration signal of the first target sent by the first laser vibration meter is acquired; the vibration signal of the first target is obtained by the first laser vibration meter through interference processing and demodulation processing based on the first echo beam fed back by the fan.

[0154] According to the preset signal mapping model, the vibration signal of the first target is separated to obtain the mechanical vibration signal and the acoustic vibration signal corresponding to the vibration signal of the first target.

[0155] Based on the mechanical vibration signal and acoustic vibration signal corresponding to the first target vibration signal, the condition of the fan is detected, and the detection results are obtained.

[0156] Using the aforementioned computer equipment, the target vibration signal is acquired and processed by the laser vibration meter. Since sound is essentially vibration, the target vibration signal simultaneously includes the mechanical vibration corresponding to the abnormal vibration and the acoustic vibration corresponding to the abnormal noise. Subsequently, the vibration signal can be separated using a preset signal mapping model to obtain the required mechanical vibration signal and acoustic vibration signal. Finally, the condition of the wind turbine is detected based on the mechanical vibration signal and acoustic vibration signal. Based on the signal separation method, only the vibration signal needs to be acquired by the laser vibration meter. The laser vibration meter can achieve non-contact vibration measurement of the wind turbine itself, which is not affected by vehicles traveling in the tunnel, thus improving the detection accuracy and reducing the likelihood of false alarms and missed alarms. In addition, it does not require the expenditure of a lot of detection costs to deploy multiple sensors.

[0157] Those skilled in the art will understand that all or part of the steps in any of the methods in the above embodiments can be performed by a computer program or by a computer program controlling related hardware. The computer program can be stored in a computer-readable storage medium and loaded and executed by a processor.

[0158] Fourthly, in one embodiment, the present invention provides a storage medium storing a plurality of computer programs that can be loaded by a processor to perform the following steps:

[0159] The vibration signal of the first target sent by the first laser vibration meter is acquired; the vibration signal of the first target is obtained by the first laser vibration meter through interference processing and demodulation processing based on the first echo beam fed back by the fan.

[0160] According to the preset signal mapping model, the vibration signal of the first target is separated to obtain the mechanical vibration signal and the acoustic vibration signal corresponding to the vibration signal of the first target.

[0161] Based on the mechanical vibration signal and acoustic vibration signal corresponding to the first target vibration signal, the condition of the fan is detected, and the detection results are obtained.

[0162] The target vibration signal, acquired and processed by the laser vibration meter, is obtained through the aforementioned storage medium. Since sound is also essentially vibration, the target vibration signal simultaneously contains the mechanical vibration corresponding to the abnormal vibration and the acoustic vibration corresponding to the abnormal noise. Subsequently, the vibration signal can be separated using a preset signal mapping model to obtain the required mechanical vibration signal and acoustic vibration signal. Finally, the condition of the wind turbine is detected based on the mechanical vibration signal and acoustic vibration signal. Based on the signal separation method, only the vibration signal needs to be acquired through the laser vibration meter. The laser vibration meter can achieve non-contact vibration measurement of the wind turbine itself, which is not affected by vehicles traveling in the tunnel, thus improving detection accuracy and reducing the likelihood of false alarms and missed alarms. In addition, it eliminates the need to spend a lot of detection costs to deploy multiple sensors.

[0163] It will be understood by those skilled in the art that any references to memory, storage, database, or other media used in the embodiments provided in this invention may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), Synchlink, DRAM (SLDRAM), RAMbus, direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0164] Since the computer program stored in the storage medium can execute the steps in the tunnel ventilation fan status detection method in any embodiment of the present invention, the beneficial effects that the tunnel ventilation fan status detection method in any embodiment of the present invention can achieve can be realized. For details, please refer to the previous embodiments, which will not be repeated here.

[0165] For details on the implementation of each of the above operations, please refer to the previous examples, which will not be repeated here.

[0166] In the above embodiments, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the detailed descriptions of other embodiments above, which will not be repeated here.

[0167] The present invention provides a detailed description of a tunnel ventilation fan status detection method, system, computer equipment, and storage medium. Specific examples have been used to illustrate the principles and implementation methods of the present invention. The descriptions of the above embodiments are only for the purpose of helping to understand the method and core ideas of the present invention. At the same time, those skilled in the art will recognize that there will be changes in the specific implementation methods and application scope based on the ideas of the present invention. Therefore, the content of this specification should not be construed as a limitation of the present invention.

[0168] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

Claims

1. A method of detecting the state of a tunnel fan, characterized by, include: Acquire the first target vibration signal sent by the first laser vibrometer; The first target vibration signal is obtained by the first laser vibration meter through interference processing and demodulation processing based on the first echo beam fed back by the fan; According to the preset signal mapping model, the first target vibration signal is separated to obtain the mechanical vibration signal and the sound vibration signal corresponding to the first target vibration signal; Based on the mechanical vibration signal and acoustic vibration signal corresponding to the first target vibration signal, the state of the fan is detected to obtain the detection result; The signal mapping model includes a signal mapping table, and the first target vibration signal is the vibration signal of the wind turbine in the first plane vibration direction; the step of separating the first target vibration signal according to the preset signal mapping model to obtain the mechanical vibration signal and acoustic vibration signal corresponding to the first target vibration signal includes: Based on the first plane vibration direction, the first target vibration signal is decomposed to obtain a first decomposed vibration signal in the first decomposed vibration direction and a second decomposed vibration signal in the second decomposed vibration direction. According to the signal mapping model, the first decomposed vibration signal and the second decomposed vibration signal are separated to obtain the mechanical vibration signal and sound vibration signal corresponding to the first decomposed vibration signal and the mechanical vibration signal and sound vibration signal corresponding to the second decomposed vibration signal. The step of detecting the state of the fan based on the mechanical vibration signal and acoustic vibration signal corresponding to the first target vibration signal includes: The fan is state-detected based on the mechanical vibration signal and acoustic vibration signal corresponding to the first decomposed vibration signal and the mechanical vibration signal and acoustic vibration signal corresponding to the second decomposed vibration signal. Also includes: The wind turbine is modeled to obtain a wind turbine model; Acquire multiple sample mechanical vibration signals and the corresponding sample acoustic vibration signals; For each of the sample mechanical vibration signals, the wind turbine model is simulated based on the sample mechanical vibration signal and the sample sound vibration signal corresponding to the sample mechanical vibration signal to obtain the sample vibration signal corresponding to the sample mechanical vibration signal; The signal mapping table is obtained based on each sample vibration signal, the corresponding sample mechanical vibration signal, and the sample acoustic vibration signal.

2. The tunnel fan status detection method of claim 1, wherein, After the step of acquiring the first target vibration signal sent by the first laser vibrometer, the method further includes: The second target vibration signal sent by the second laser vibration meter is acquired; the second target vibration signal is obtained by the second laser vibration meter through interference processing and demodulation processing based on the second echo beam fed back by the fan; the second target vibration signal is the vibration signal of the fan in the second plane vibration direction; Based on the first planar vibration direction and the second planar vibration direction, the first target vibration signal and the second target vibration signal are integrated to obtain a third vibration signal; the third vibration signal is the vibration signal of the wind turbine in the three-dimensional vibration direction; Based on the signal mapping model and the three-dimensional vibration direction, the third vibration signal is separated to obtain the mechanical vibration signal and the acoustic vibration signal corresponding to the third vibration signal; Based on the mechanical vibration signal and acoustic vibration signal corresponding to the third vibration signal, the state of the fan is detected, and the detection result is obtained.

3. A tunnel fan status detection system, characterized by, include: The first laser vibration meter and computer equipment are interconnected; The first laser vibration meter is used to emit a first transmitted beam to the wind turbine, receive a first echo beam fed back by the wind turbine according to the first transmitted beam, and perform interference processing on the first echo beam to obtain a first laser signal. The first laser signal is demodulated to obtain a first target vibration signal, and the first target vibration signal is sent to the computer device. The computer device is used to separate the first target vibration signal according to a preset signal mapping model to obtain the mechanical vibration signal and the acoustic vibration signal corresponding to the first target vibration signal; and to perform state detection on the fan according to the mechanical vibration signal and the acoustic vibration signal corresponding to the first target vibration signal to obtain the detection result. The signal mapping model includes a signal mapping table. The first target vibration signal is the vibration signal of the wind turbine in the first plane vibration direction. Specifically, the computer device is used to decompose the first target vibration signal according to the first plane vibration direction to obtain a first decomposed vibration signal in the first decomposed vibration direction and a second decomposed vibration signal in the second decomposed vibration direction. According to the signal mapping model, the first decomposed vibration signal and the second decomposed vibration signal are separated to obtain the mechanical vibration signal and acoustic vibration signal corresponding to the first decomposed vibration signal and the mechanical vibration signal and acoustic vibration signal corresponding to the second decomposed vibration signal. Based on the first decomposed vibration signal... The mechanical vibration signal, acoustic vibration signal, and the mechanical vibration signal and acoustic vibration signal corresponding to the second decomposed vibration signal are used to perform state detection on the fan; it is also used to model the fan to obtain a fan model; multiple sample mechanical vibration signals and sample acoustic vibration signals corresponding to the sample mechanical vibration signals are acquired; for each sample mechanical vibration signal, the fan model is simulated according to the sample mechanical vibration signal and the sample acoustic vibration signal corresponding to the sample mechanical vibration signal to obtain the sample vibration signal corresponding to the sample mechanical vibration signal; the signal mapping table is obtained according to each sample vibration signal, the sample mechanical vibration signal and the sample acoustic vibration signal corresponding to each sample vibration signal.

4. A computer device, comprising: It includes a memory and a processor; the memory stores a computer program, and the processor is used to run the computer program in the memory to perform the steps in the tunnel ventilation fan condition detection method according to claim 1 or 2.

5. A storage medium, characterized by The storage medium stores a computer program, which is loaded by a processor to execute the steps in the tunnel ventilation fan status detection method according to claim 1 or 2.

Images