Conveying belt tearing detection method, device and system and computer equipment

Abstract

The invention relates to a conveyor belt tearing detection method, device and system and computer equipment. The method comprises the following steps: acquiring a vibration signal of a conveying belt, performing time-frequency domain analysis and feature extraction on the vibration signal to obtain time-frequency domain feature data of the vibration signal, performing power spectrum analysis on the vibration signal to obtain power spectrum data of the vibration signal, and detecting whether the conveying belt is torn or not based on the time-frequency domain feature data and the power spectrum data. By adopting the method, the tearing detection precision of the conveying belt can be improved.

Description

Technical Field

[0001] This application relates to the technical field of belt conveyor system monitoring, and particularly to a conveyor belt tear detection method, device, system, computer device, computer-readable storage medium, and computer program product. Background Art

[0002] With the development of industrial intelligence, belt conveyors are favored in multiple industries due to their high-efficient material conveying capacity, ability to perform long-distance continuous operations, and high stability. As the core component of the belt conveyor, it is necessary to detect the tear of the conveyor belt in a timely manner.

[0003] In traditional solutions, protective devices are usually installed on the belt conveyor to detect the conveyor belt in real time. Most of these installed protective devices are based on piezoresistive or infrared blocking technologies, which can detect whether a tear event has occurred on the conveyor belt.

[0004] However, traditional tear detection methods are easily affected by electrical signal attenuation and electromagnetic interference. And for the transverse tear of the conveyor belt, since the conveyor belt is completely broken, it is relatively easy to detect. But the longitudinal tear situation of the conveyor belt is more complex, and traditional solutions are difficult to identify. That is, traditional tear detection solutions have the problem of low accuracy. Summary of the Invention

[0005] Based on this, in view of the above technical problems, it is necessary to provide a conveyor belt tear detection method, device, system, computer device, computer-readable storage medium, and computer program product that can improve the accuracy of conveyor belt tear detection.

[0006] In a first aspect, this application provides a conveyor belt tear detection method, including:

[0007] Obtain the vibration signal of the conveyor belt;

[0008] Perform time-frequency domain analysis and feature extraction on the vibration signal to obtain the time-frequency domain feature data of the vibration signal;

[0009] Perform power spectrum analysis on the vibration signal to obtain the power spectrum data of the vibration signal;

[0010] Based on the time-frequency domain feature data and the power spectrum data, detect whether the conveyor belt has a tear.

[0011] In a second aspect, this application also provides a conveyor belt tear detection device, including:

[0012] A signal acquisition module, configured to obtain the vibration signal of the conveyor belt;

[0013] A first signal analysis module, configured to perform time-frequency domain analysis and feature extraction on the vibration signal to obtain time-frequency domain feature data of the vibration signal;

[0014] A second signal analysis module, configured to perform power spectrum analysis on the vibration signal to obtain power spectrum data of the vibration signal;

[0015] A tear detection module, configured to detect whether the conveyor belt is torn based on the time-frequency domain feature data and the power spectrum data.

[0016] In a third aspect, the present application further provides a conveyor belt tear detection system, which includes a fiber optic sensing device, a distributed fiber optic monitoring host, an industrial intelligent analysis gateway, and a voiceprint engine server that are connected in sequence. The fiber optic sensing device is arranged on the conveyor belt;

[0017] The distributed fiber optic monitoring host is configured to receive the optical signal collected by the fiber optic sensing device based on the Rayleigh scattering effect, perform signal conversion and data demodulation processing on the optical signal, and obtain and send the initial vibration signal of the conveyor belt to the industrial intelligent analysis gateway;

[0018] The industrial intelligent analysis gateway is configured to receive the initial vibration signal, perform preprocessing on the initial vibration signal, and obtain and feedback the vibration signal to the voiceprint engine server;

[0019] The voiceprint engine server is configured to detect whether the conveyor belt is torn based on the steps in any one of the embodiments of the conveyor belt tear detection method.

[0020] In a fourth aspect, the present application further provides a computer device, which includes a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, the steps in the embodiments of the above conveyor belt tear detection method are implemented.

[0021] In a fifth aspect, the present application further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps in the embodiments of the above conveyor belt tear detection method are implemented.

[0022] In a sixth aspect, the present application further provides a computer program product, which includes a computer program. When the computer program is executed by a processor, the steps in the embodiments of the above conveyor belt tear detection method are implemented.

[0023] The above conveyor belt tear detection method, device, system, computer device, computer-readable storage medium, and computer program product are different from traditional solutions that are susceptible to the influence of electrical signal attenuation and electromagnetic interference when using piezoresistors or infrared blocking technologies. In this solution, by acquiring the vibration signal of the conveyor belt, which belongs to mechanical signals, reliable data support can be provided for subsequent tear detection even in an industrial environment with strong electromagnetic interference. Then, time-frequency domain analysis and feature extraction are performed on the vibration signal to obtain the time-frequency domain feature data of the vibration signal, and power spectrum analysis is performed on the vibration signal to obtain the power spectrum data of the vibration signal. Even when the conveyor belt experiences longitudinal tears, minor tears, etc., the vibration frequency, vibration mode, and the distribution of signal power at different frequencies of the vibration signal will change, that is, the time-frequency domain feature data and power spectrum data will change. Therefore, by combining the time-frequency domain feature data and power spectrum data, the tear situation of the conveyor belt can be identified more comprehensively and accurately, improving the tear detection accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] To more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the following will briefly introduce the drawings required for use in the description of the embodiments of the present application or related technologies. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, other related drawings can be obtained based on these drawings without creative efforts.

[0025] Figure 1 It is an application environment diagram of the conveyor belt tear detection method in an embodiment;

[0026] Figure 2 It is a flowchart of the conveyor belt tear detection method in an embodiment;

[0027] Figure 3 It is a flowchart of the conveyor belt tear detection method in another embodiment;

[0028] Figure 4 It is a flowchart of the step of determining whether the conveyor belt is torn in an embodiment;

[0029] Figure 5 It is a flowchart of the step of determining whether the conveyor belt is torn in another embodiment;

[0030] Figure 6 It is a flowchart of the conveyor belt tear detection method in a detailed embodiment;

[0031] Figure 7 It is a structural block diagram of the conveyor belt tear detection device in an embodiment;

[0032] Figure 8It is a structural block diagram of a conveyor belt tear detection system in an embodiment;

[0033] Figure 9 It is a structural block diagram of a conveyor belt tear detection system in another embodiment;

[0034] Figure 10 It is a structural block diagram of an optical fiber sensing device in an embodiment;

[0035] Figure 11 It is a schematic structural diagram of an optical fiber sensing device in an embodiment;

[0036] Figure 12 It is a schematic structural diagram of an optical fiber fixing fixture in an embodiment;

[0037] Figure 13 It is an internal structural diagram of a computer device in an embodiment.

[0038] Explanation of reference numerals: 1, channel steel; 811, vibration measuring optical fiber; 812, optical fiber fixing fixture; 812(1), the first part of the optical fiber fixing fixture; 812(2), the second part of the optical fiber fixing fixture. Detailed implementation manners

[0039] In order to make the objectives, technical solutions and advantages of the present application clearer, the present application will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0040] The conveyor belt tear detection method provided by the embodiments of the present application can be applied to an application environment as shown in Figure 1 . Among them, the terminal 102 communicates with the server 104 through the network. The data storage system can store the data that the server 104 needs to process. The data storage system can be integrated on the server 104, or placed in the cloud or other network servers.

[0041] Specifically, it can be that an operator uploads the vibration signal of the conveyor belt to the server 104 through the terminal 102. The server performs time-frequency domain analysis and feature extraction on the vibration signal to obtain the time-frequency domain feature data of the vibration signal, and performs power spectrum analysis on the vibration signal to obtain the power spectrum data of the vibration signal. Finally, the server 104 detects whether the conveyor belt is torn based on the time-frequency domain feature data and the power spectrum data.

[0042] Among them, the terminal 102 can be, but is not limited to, various personal computers, laptop computers, smart phones, tablet computers, Internet of Things devices, and portable wearable devices. The Internet of Things devices can be smart speakers, smart TVs, smart air conditioners, smart in-vehicle devices, projection devices, etc. The portable wearable devices can be smart watches, smart bracelets, head-mounted devices, etc. The head-mounted devices can be virtual reality (VR) devices, augmented reality (AR) devices, smart glasses, etc. The server 104 can be an independent physical server, a server cluster or a distributed system composed of multiple physical servers, or a cloud server providing cloud computing services.

[0043] In an exemplary embodiment, as Figure 2 shown, a conveyor belt tearing detection method is provided. Taking the method applied to Figure 1 the server 104 (which can be a voiceprint engine server) in

[0044] S100, obtain the vibration signal of the conveyor belt.

[0045] Among them, the conveyor belt will generate vibrations during operation, thereby generating vibration signals. The vibration signals can be obtained by the vibration measurement optical fiber (such as the sensitized optical fiber) collecting the Rayleigh scattered light based on the Rayleigh scattering principle, and then performing photoelectric signal conversion, signal demodulation, noise processing, etc. on the Rayleigh scattered light.

[0046] Specifically, the Rayleigh scattering principle is an inherent property of the optical fiber material. When a narrow optical pulse is injected into the optical fiber, it will propagate forward along the optical fiber. During this process, Rayleigh scattering will occur wherever the optical pulse reaches. The Rayleigh scattered light will scatter in all directions, and a part of it will return to the light source end. Moreover, the intensity of the Rayleigh scattered light is inversely proportional to the fourth power of the wavelength of the incident light, which means that the shorter the wavelength, the stronger the scattering. It can be to set the sensitized optical fiber at the channel steel of the conveyor belt. The laser light source emits narrowband pulsed light into the sensitized optical fiber. The conveyor belt will generate vibrations during operation, which will cause the phase of the Rayleigh scattered light in the sensitized optical fiber to change. The phase-sensitive optical time domain reflectometry technology can utilize the phase change of the Rayleigh scattered light to sense the external vibration, that is, the Rayleigh scattered light carries the vibration information of the conveyor belt.

[0047] Furthermore, through coherent detection technology, the backward Rayleigh scattered light carrying the vibration information of the conveyor belt can be coherently mixed with the reference light. During the mixing process, the two beams of light interfere with each other. According to the interference principle, information such as their phase difference will be reflected in the interference result, thus generating a beat frequency signal, which contains the vibration information. Then, the generated beat frequency signal is demodulated, that is, the original vibration information is extracted from the complex beat frequency signal, and the information such as the amplitude, frequency, and phase of the conveyor belt vibration carried in the optical signal is restored, and finally a vibration signal that can directly reflect the vibration condition of the conveyor belt is obtained.

[0048] S200. Perform time-frequency domain analysis and feature extraction on the vibration signal to obtain the time-frequency domain feature data of the vibration signal.

[0049] Specifically, time domain analysis, frequency domain analysis, and time-frequency analysis can be performed on the vibration signal, and time-frequency domain feature data is extracted from the vibration signal. The time-frequency domain feature data includes, but is not limited to, time domain feature data, frequency domain feature data, time-frequency feature data, etc. Among them, the time domain feature data includes maximum value, minimum value, mean value, peak-to-peak value, root mean square value, kurtosis, skewness, etc. The frequency domain feature data includes center frequency, average frequency, root mean square frequency, frequency variance, etc. For the time-frequency feature data, the wavelet packet analysis technology can be used to decompose the vibration signal into multiple sub-bands, and the energy percentage of each sub-band is calculated as the time-frequency domain feature data.

[0050] S300. Perform power spectrum analysis on the vibration signal to obtain the power spectrum data of the vibration signal.

[0051] Among them, the power spectrum data is used to describe the distribution of signal power at different frequencies. For the vibration signal, the power spectrum data reflects the energy magnitude carried by the vibration signal at each frequency component.

[0052] Specifically, power spectrum analysis is usually based on Fourier transform. The vibration signal can be divided into multiple short-time frames, and Fourier transform is performed on each short-time frame, so as to obtain the spectrum of each short-time frame, which can be represented in the form of a complex matrix. The complex matrix contains the frequency components and phase information of each short-time frame. Taking the modulus square of the complex matrix can obtain the power spectrum data.

[0053] S400. Based on the time-frequency domain feature data and the power spectrum data, detect whether the conveyor belt is torn.

[0054] Continuing from the above embodiments, the time-frequency domain feature data reflects the energy distribution of the vibration signal at different time and frequency scales. For the conveyor belt, when it is operating normally and when it is torn, there will be significant differences in the time-frequency domain feature data and the power spectrum data of its vibration signal.

[0055] Specifically, for the time-frequency domain feature data, the normal vibration signals of the conveyor belt during normal operation and the abnormal vibration signals during conveyor belt tearing can be collected in advance, and the time-frequency domain feature data can be extracted from the normal vibration signals and the abnormal vibration signals respectively. Based on this, a threshold range for the time-frequency domain feature data is set. If the time-frequency domain feature data of the conveyor belt exceeds the set threshold range, it can be considered that the conveyor belt is torn.

[0056] For the power spectrum data, feature extraction can be performed on the power spectrum data first to obtain feature data such as spectral peak value, spectral center, spectral bandwidth, and spectral flatness. Then, through a neural network method, such as through a trained neural network model, the above feature data is processed. The trained neural network model can be trained based on historical power spectrum data with tearing labels. During the training process, the neural network model has learned the correlation between the power spectrum data and the tearing result. Therefore, the neural network model can output the tearing result, thereby detecting whether the conveyor belt is torn. In addition, similar to the time-frequency domain feature data, the conveyor belt can also be detected for tearing by setting a threshold range for the power spectrum data. For example, when the conveyor belt is torn, the frequency peak value, frequency bandwidth, etc. on the power spectrum data may change. By monitoring the changes in the frequency peak value and frequency bandwidth and comparing them with the frequency peak value and frequency bandwidth on the power spectrum data in the normal operation state of the conveyor belt, the corresponding frequency peak value threshold range and frequency bandwidth threshold range are set. When the frequency peak value or frequency bandwidth on the collected power spectrum data exceeds the corresponding threshold range, it can be determined that the conveyor belt is torn.

[0057] It should be noted that due to possible errors in the detection process, situations may occur where it is determined that the conveyor belt is torn based on the time-frequency domain feature data but not torn based on the power spectrum data. Therefore, in this application, it is considered that the conveyor belt is torn only when it is determined that the conveyor belt is torn based on both the time-frequency domain feature data and the power spectrum data. In addition, it can also be set that when it is determined that the conveyor belt is torn based on the time-frequency domain feature data or when it is determined that the conveyor belt is torn based on the power spectrum data, it is considered that the conveyor belt is torn.

[0058] Moreover, when it is detected that the conveyor belt is torn, the server can output a tearing alarm message in a timely manner and upload it to the terminal service warning platform. The terminal service warning platform connects to the network repeater through a specific transmission protocol, such as the modbus tcp protocol, and outputs a stop signal to the belt tearing fault receiver in the PLC control cabinet through the network repeater to achieve linkage shutdown, further reducing the occurrence of tearing events. In addition, the server can also upload the tearing alarm message to the centralized control center platform to facilitate the on-site operators to handle the tearing event in a timely manner and reduce potential safety hazards.

[0059] The above conveyor belt tear detection method is different from the traditional solutions that are susceptible to the influence of electrical signal attenuation and electromagnetic interference when using piezoresistors or infrared blocking technologies. In this solution, by obtaining the vibration signal of the conveyor belt, which belongs to a mechanical signal, reliable data support can be provided for subsequent tear detection even in an industrial environment with strong electromagnetic interference. Then, time-frequency domain analysis and feature extraction are performed on the vibration signal to obtain the time-frequency domain feature data of the vibration signal, and power spectrum analysis is performed on the vibration signal to obtain the power spectrum data of the vibration signal. Even when longitudinal tears, minor tears, etc. occur in the conveyor belt, the vibration frequency, vibration mode, and the distribution of signal power at different frequencies of the vibration signal will change, that is, the time-frequency domain feature data and power spectrum data will change. Therefore, by combining the time-frequency domain feature data and power spectrum data, the tear situation of the conveyor belt can be identified more comprehensively and accurately, improving the tear detection accuracy.

[0060] In one embodiment, as Figure 3 shown, S400 includes:

[0061] S410, based on the time-frequency domain feature data, detect whether the conveyor belt has a tear to obtain a first tear detection result.

[0062] S420, based on the power spectrum data, detect whether the conveyor belt has a tear to obtain a second tear detection result.

[0063] S430, in the case where both the first tear detection result and the second tear detection result indicate that the conveyor belt has a tear, determine that the conveyor belt has a tear.

[0064] Continuing from the above embodiment, by separately detecting whether the conveyor belt has a tear based on the time-frequency domain feature data and the power spectrum feature data, a first tear detection result and a second tear detection result can be obtained. To improve the accuracy of the tear detection result and reduce the detection error that may occur in a single detection method, only when both the first tear detection result obtained based on the time-frequency domain feature data and the second tear detection result obtained based on the power spectrum data indicate that the conveyor belt has a tear, is it finally determined that the conveyor belt has a tear.

[0065] In addition, specific weights can be assigned to the first tear detection result obtained based on the time-frequency domain feature data and the second tear detection result obtained based on the power spectrum data according to the importance of the time-frequency domain feature data and the power spectrum data in detecting the tear of the conveyor belt. The time-frequency domain feature data can capture the local transient information of the vibration signal, and the power spectrum data can reflect the overall frequency characteristics of the vibration signal. Different weights can be set according to the actual situation.

[0066] In this embodiment, through a comprehensive determination method, the advantages of time-frequency domain feature data and power spectrum data are utilized. The time-frequency domain feature data can better reflect the dynamic changes of vibration signals in terms of time and frequency and is sensitive to local and instantaneous abnormalities. The power spectrum data focuses on the energy distribution of the overall frequency components and can reflect the overall frequency characteristics of vibration signals. When it is determined that the conveyor belt is torn based on both of them, it is considered that the conveyor belt has torn, effectively reducing the probabilities of false judgment and missed judgment and improving the detection accuracy of conveyor belt tearing.

[0067] In one embodiment, the time-frequency domain feature data includes time domain feature values, frequency domain feature values, and time-frequency feature values. S410 includes: when at least two of the following are satisfied, determining that the conveyor belt has torn to obtain a first tearing detection result:

[0068] The first item is that the time domain feature value exceeds a preset time domain feature value range;

[0069] The second item is that the frequency domain feature value exceeds a preset frequency domain feature value range;

[0070] The third item is that the time-frequency feature value exceeds a preset time-frequency feature value range.

[0071] Specifically, the time-frequency domain feature data includes time domain feature values, frequency domain feature values, and time-frequency feature values. Among them, the time domain feature value is a feature obtained by analyzing the vibration signal in the time dimension, such as the maximum value, minimum value, mean value, peak-to-peak value, root mean square value, kurtosis, skewness, etc. mentioned above. The time domain feature value reflects the characteristics of the vibration signal changing with time. When these time domain feature values exceed the corresponding preset time domain feature value range, it can be considered that the first item is satisfied. For example, the maximum value exceeds the preset maximum value threshold range, the minimum value exceeds the preset minimum value threshold range, etc.

[0072] The frequency domain feature value is obtained by performing spectrum analysis on the vibration signal and includes the center frequency, average frequency, root mean square frequency, frequency variance, etc., reflecting the characteristics of the vibration signal in different frequency components. Similarly, when the frequency domain feature value exceeds the corresponding preset frequency domain feature value range, it can be considered that the second item is satisfied. For example, the center frequency exceeds the preset center frequency threshold range, the average frequency exceeds the preset average frequency threshold range, etc.

[0073] The time-frequency feature value is obtained by decomposing the vibration signal into multiple sub-bands through a method such as wavelet packet analysis and extracting the energy percentage of each sub-band, reflecting the characteristics of the vibration signal in terms of time and frequency. Similarly, when the time-frequency feature value exceeds the corresponding preset time-frequency feature value range, it can be considered that the third item is satisfied. For example, the time-frequency feature value of a specific sub-band exceeds the time-frequency feature value threshold range of that sub-band, etc.

[0074] Finally, when at least two of the above three judgment conditions are satisfied, it can be considered that the first tear detection result indicates that the conveyor belt is torn.

[0075] In this embodiment, the method of determining that the conveyor belt is torn only when at least two judgment conditions are satisfied can reduce the misjudgment caused by a single eigenvalue and improve the accuracy and reliability of conveyor belt tear detection. For example, at a certain moment, due to the short-term interference of nearby equipment, the peak-to-peak value in the time-domain eigenvalue may suddenly increase and exceed the preset threshold range, but this does not necessarily mean that the conveyor belt is torn. When at least two judgment conditions are satisfied simultaneously, it indicates a greater possibility that the conveyor belt is torn, thereby reducing the misjudgment probability and more accurately detecting whether the conveyor belt is truly torn.

[0076] In one embodiment, the number of time-domain eigenvalues, frequency-domain eigenvalues, and time-frequency eigenvalues is multiple. The time-domain eigenvalues correspond one-to-one with the preset time-domain eigenvalue threshold range, the frequency-domain eigenvalues correspond one-to-one with the preset frequency-domain eigenvalue threshold range, and the time-frequency eigenvalues correspond one-to-one with the preset time-frequency eigenvalue threshold range. As Figure 4 shown, the method further includes:

[0077] S411, respectively compare each time-domain eigenvalue with the corresponding preset time-domain eigenvalue threshold range. When the number of time-domain eigenvalues exceeding the preset time-domain eigenvalue threshold range is greater than the preset number threshold, it is determined that the time-domain eigenvalue exceeds the preset time-domain eigenvalue range.

[0078] S412, respectively compare each frequency-domain eigenvalue with the corresponding preset frequency-domain eigenvalue threshold range. When the number of frequency-domain eigenvalues exceeding the preset frequency-domain eigenvalue threshold range is greater than the preset number threshold, it is determined that the frequency-domain eigenvalue exceeds the preset frequency-domain eigenvalue range.

[0079] S413, respectively compare each time-frequency eigenvalue with the corresponding preset time-frequency eigenvalue threshold range. When the number of time-frequency eigenvalues exceeding the preset time-frequency eigenvalue threshold range is greater than the preset number threshold, it is determined that the time-frequency eigenvalue exceeds the preset time-frequency eigenvalue range.

[0080] Continuing with the above embodiments, it can be seen that the number of time-domain eigenvalues, frequency-domain eigenvalues, and time-frequency eigenvalues is multiple. The time-domain eigenvalues include the maximum value, minimum value, mean value, peak-to-peak value, root mean square value, kurtosis, skewness, etc. The frequency-domain eigenvalues include the center frequency, average frequency, root mean square frequency, frequency variance, etc. The time-frequency eigenvalues include the time-frequency eigenvalues of multiple sub-bands. When the conveyor belt tears, it is possible that not all of the above time-domain eigenvalues, frequency-domain eigenvalues, and time-frequency eigenvalues exceed the corresponding threshold ranges. Therefore, when it is recognized that a part of the data exceeds the corresponding threshold range, it can be considered that the corresponding judgment condition in the above embodiments is established.

[0081] Specifically, the time-domain eigenvalues include multiple values such as the maximum value, minimum value, mean value, peak-to-peak value, root mean square value, kurtosis, skewness, etc., and each value has a corresponding preset time-domain eigenvalue threshold range. For example, the maximum value corresponds to a preset maximum value threshold range, the mean value corresponds to a preset mean value threshold range, etc. For each time-domain eigenvalue, it is compared with the corresponding threshold range. Taking the preset number threshold as 3 as an example, when the number of time-domain eigenvalues exceeding the corresponding threshold range is greater than 3 (for example, the maximum value, minimum value, and mean value all exceed the corresponding threshold ranges), it can be considered that the first judgment condition is established.

[0082] Similarly, the center frequency, average frequency, root mean square frequency, frequency variance, etc. in the frequency-domain eigenvalues also have corresponding preset frequency-domain eigenvalue threshold ranges. Each frequency-domain eigenvalue is respectively compared with its corresponding frequency-domain eigenvalue threshold range. Taking the preset number threshold as 3 as an example, when the number of frequency-domain eigenvalues exceeding the corresponding threshold range is greater than 3 (for example, the center frequency, average frequency, and root mean square frequency all exceed the corresponding threshold ranges), it can be considered that the second judgment condition is established.

[0083] Similarly, the time-frequency eigenvalues include the time-frequency eigenvalues of multiple sub-bands, and each time-frequency eigenvalue of each sub-band has a corresponding preset time-frequency eigenvalue preset range. Each time-frequency eigenvalue is respectively compared with its corresponding time-frequency eigenvalue threshold range. Taking the preset number threshold as 3 as an example, when the number of time-frequency eigenvalues exceeding the corresponding threshold range is greater than 3, it can be considered that the third judgment condition is established.

[0084] In this embodiment, the provided determination method further improves the accuracy and reliability of conveyor belt tear detection. Because in the actual conveyor belt operating environment, the occasional exceeding of the threshold range by a single eigenvalue may be caused by non-tear fault reasons such as noise interference and transient external factors. By setting a number threshold, when multiple eigenvalues exceed the range at the same time, it is determined that the category of eigenvalues exceeds the range, which can effectively reduce the influence of accidental factors and thus more accurately judge whether the conveyor belt tears.

[0085] In one embodiment, asFigure 5 As shown in Figure 5 , S420 includes:

[0086] S421 extracts features from the power spectrum data to obtain power spectrum feature data. Using the power spectrum feature data as input, a trained error backpropagation neural network is called to obtain a second tear detection result.

[0087] Among them, the power spectrum feature data includes spectral peak value, spectral center, spectral bandwidth, spectral flatness, etc. After extracting the above power spectrum feature data, it can be normalized to adjust the power spectrum feature data to a unified range, such as between [0, 1].

[0088] Specifically, the framework of the error backpropagation neural network can be pre-constructed, including an input layer, a hidden layer, and an output layer. The number of nodes in the input layer is equal to the number of power spectrum feature data, and the number of nodes in the output layer is equal to the tear time. When training the constructed backpropagation neural network, historical power spectrum feature data can be extracted from historical power spectrum data, and the tear labels corresponding to the historical power spectrum feature data are combined as training data. Then, the gradient descent algorithm can be used to train the error backpropagation neural network. By calculating the output of the neural network through forward propagation and then adjusting the weights of the neural network through backpropagation to minimize the preset loss function, the trained error backpropagation neural network can be obtained.

[0089] Then, the extracted power spectrum feature data is used as the input of the trained error backpropagation neural network. The number of nodes in its input layer is equal to the number of power spectrum feature data, so that each power spectrum feature data can correspond to an input node of the neural network, thereby completely transmitting the power spectrum feature data to the neural network for processing. Since the error backpropagation neural network has been fully trained, when new power spectrum feature data is input into the error backpropagation neural network, the error backpropagation neural network will calculate and judge according to the patterns it has learned, and finally output a second tear detection result.

[0090] In this embodiment, through training with a large number of historical power spectrum feature data and corresponding tear labels, the error backpropagation neural network can learn the differences in power spectrum feature data in normal and torn states, so as to analyze and obtain an accurate second tear detection result, improving the accuracy of conveyor belt tear detection.

[0091] To make the conveyor belt tear detection method provided in this application clearer, the following combines Figure 6 and One two detailed embodiments for explanation. The detailed embodiments include the following steps:

[0092] S610, obtain the vibration signal of the conveyor belt.

[0093] S620, perform time-frequency domain analysis and feature extraction on the vibration signal to obtain time-frequency domain feature data of the vibration signal.

[0094] S630, perform power spectrum analysis on the vibration signal to obtain power spectrum data of the vibration signal.

[0095] S640, when at least two of the following are established, determine that the conveyor belt is torn to obtain a first tear detection result: the first item, the time domain eigenvalue exceeds the preset time domain eigenvalue range; the second item, the frequency domain eigenvalue exceeds the preset frequency domain eigenvalue range; the third item, the time-frequency eigenvalue exceeds the preset time-frequency eigenvalue range.

[0096] S650, perform feature extraction on the power spectrum data to obtain power spectrum feature data, and use the power spectrum feature data as input to call the trained error backpropagation neural network to obtain a second tear detection result.

[0097] S660, when both the first tear detection result and the second tear detection result indicate that the conveyor belt is torn, determine that the conveyor belt is torn.

[0098] It should be understood that although the steps in the flowcharts involved in the above-described embodiments are sequentially shown according to the indications of the arrows, these steps do not necessarily have to be executed in the order indicated by the arrows. Unless there is a clear indication in this article, the execution of these steps does not have a strict order limit, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-described embodiments may include multiple steps or multiple stages. These steps or stages do not necessarily have to be executed at the same time, but can be executed at different times. The execution order of these steps or stages does not necessarily have to be sequential, but can be executed alternately or alternately with at least a part of other steps or steps or stages in other steps.

[0099] Based on the same inventive concept, the embodiments of the present application also provide a conveyor belt tear detection device for implementing the conveyor belt tear detection method described above. The implementation solutions provided by this device to solve problems are similar to the implementation solutions described in the above method. Therefore, the specific limitations in one or more conveyor belt tear detection device embodiments provided below can refer to the limitations on the conveyor belt tear detection method in the above text, and will not be repeated here.

[0100] In an exemplary embodiment, as Figure 7 shown, a conveyor belt tear detection device 700 is provided, including: a signal acquisition module 710, a first signal analysis module 720, a second signal analysis module 730, and a tear detection module 740, where:

[0101] A signal acquisition module 710, configured to acquire vibration signals of the conveyor belt;

[0102] A first signal analysis module 720, configured to perform time-frequency domain analysis and feature extraction on the vibration signals to obtain time-frequency domain feature data of the vibration signals;

[0103] A second signal analysis module 730, configured to perform power spectrum analysis on the vibration signals to obtain power spectrum data of the vibration signals;

[0104] A tear detection module 740, configured to detect whether the conveyor belt is torn based on the time-frequency domain feature data and the power spectrum data.

[0105] In one embodiment, the tear detection module 740 is configured to detect whether the conveyor belt is torn based on the time-frequency domain feature data to obtain a first tear detection result, detect whether the conveyor belt is torn based on the power spectrum data to obtain a second tear detection result, and determine that the conveyor belt is torn when both the first tear detection result and the second tear detection result indicate that the conveyor belt is torn.

[0106] In one embodiment, the first signal analysis module 720 is configured to determine that the conveyor belt is torn to obtain a first tear detection result when at least two of the following conditions are met: the first item, the time domain feature value exceeds a preset time domain feature value range; the second item, the frequency domain feature value exceeds a preset frequency domain feature value range; the third item, the time-frequency feature value exceeds a preset time-frequency feature value range.

[0107] In one embodiment, the number of time domain feature values, frequency domain feature values, and time-frequency feature values is multiple. The time domain feature values correspond one-to-one to a preset time domain feature value threshold range, the frequency domain feature values correspond one-to-one to a preset frequency domain feature value threshold range, and the time-frequency feature values correspond one-to-one to a preset time-frequency feature value threshold range. The conveyor belt tear detection device 700 is further configured to compare each time domain feature value with the corresponding preset time domain feature value threshold range respectively, and determine that the time domain feature value exceeds the preset time domain feature value range when the number of time domain feature values exceeding the preset time domain feature value threshold range is greater than a preset number threshold. Compare each frequency domain feature value with the corresponding preset frequency domain feature value threshold range respectively, and determine that the frequency domain feature value exceeds the preset frequency domain feature value range when the number of frequency domain feature values exceeding the preset frequency domain feature value threshold range is greater than a preset number threshold. Compare each time-frequency feature value with the corresponding preset time-frequency feature value threshold range respectively, and determine that the time-frequency feature value exceeds the preset time-frequency feature value range when the number of time-frequency feature values exceeding the preset time-frequency feature value threshold range is greater than a preset number threshold.

[0108] In one embodiment, the second signal analysis module 730 is further configured to extract features from the power spectrum data to obtain power spectrum feature data, and use the power spectrum feature data as input to call a trained error backpropagation neural network to obtain a second tear detection result, where the trained error backpropagation neural network is trained based on historical power spectrum feature data with different tear labels, and the number of nodes in the input layer of the trained error backpropagation neural network is equal to the number of power spectrum feature data.

[0109] Each module in the above conveyor belt tear detection device can be implemented in whole or in part by software, hardware, and their combination. Each of the above modules can be embedded in the processor of the computer device in hardware form or be independent of it, or can be stored in the memory of the computer device in software form to facilitate the processor to call and execute the operations corresponding to each of the above modules.

[0110] In one embodiment, as Figure 8 shown, a conveyor belt tear detection system 800 is provided, including a fiber optic sensing device 810, a distributed fiber optic monitoring host 820, an industrial intelligent analysis gateway 830, and a voiceprint engine server 840 that are connected in sequence. The fiber optic sensing device 810 is disposed on the conveyor belt.

[0111] The distributed fiber optic monitoring host 820 is configured to receive the optical signal collected by the fiber optic sensing device 810 based on the Rayleigh scattering effect, perform signal conversion and data demodulation processing on the optical signal, and obtain and send the initial vibration signal of the conveyor belt to the industrial intelligent analysis gateway 830.

[0112] The industrial intelligent analysis gateway 830 is configured to receive the initial vibration signal, perform preprocessing on the initial vibration signal, and obtain and feedback the vibration signal to the voiceprint engine server 840.

[0113] The voiceprint engine server 840 is configured to detect whether the conveyor belt is torn based on the conveyor belt tear detection method in any of the above conveyor belt tear monitoring method embodiments.

[0114] Among them, the distributed fiber optic monitoring host 820 is a complex system integrated with optics, electronics, mechanics, and software algorithms based on the principles of Rayleigh scattering effect and optical time domain reflectometry technology, and is used to collect and record the data generated during the operation of the conveyor belt (belt conveyor) for subsequent analysis and processing. The industrial intelligent analysis gateway 830 can store and process the received data. For example, it performs preprocessing on the initial vibration signal, screens out abnormal vibration signals from the initial vibration signal, and excludes those that are obviously normal, thereby reducing the amount of data to be processed in subsequent tear detection. In addition, the industrial intelligent analysis gateway 830 also supports remote access and control, facilitating users to monitor and analyze the operating status of the conveyor belt in real time.

[0115] It should be noted that the implementation solution provided by the conveyor belt tear detection system 800 in this embodiment is similar to the implementation solution described in the above method. Therefore, the specific limitations in one or more conveyor belt tear detection system embodiments provided below can refer to the limitations on the conveyor belt tear detection method in the above text, and will not be repeated here.

[0116] In one embodiment, as Figure 9 shown, the conveyor belt tear detection system further includes a terminal service warning platform 850, a network repeater 860, and a PLC control cabinet 870 that are connected in sequence. The terminal service warning platform 850 is connected to the voiceprint engine server 840.

[0117] The voiceprint engine server 840 is configured to generate and send a tear alarm signal to the terminal service warning platform 850 when it determines that the conveyor belt has a tear.

[0118] The terminal service warning platform 850 is configured to generate a stop signal when it receives the tear alarm signal, and send the stop signal to the PLC control cabinet 870 through the network repeater 860.

[0119] The PLC control cabinet 870 is configured to control the conveyor belt to stop when it receives the stop signal.

[0120] Among them, the network repeater 860 is used to extend the network communication example, thereby reducing the risk of loss or attenuation of the tear alarm signal and the like during transmission due to excessive distance. At the same time, the network repeater 860 can forward data packets, connect different network segments, and improve the reliability and stability of the network. The PLC control cabinet 870 is a programmable logic controller, which can realize functions such as controlling the start, stop, and speed adjustment of the conveyor belt, and improve the operation stability and production efficiency of the conveyor belt.

[0121] In one embodiment, as Figure 10 shown, the optical fiber sensing device 810 includes a vibration measuring optical fiber 811 and an optical fiber fixing fixture 812. The vibration measuring optical fiber 811 is fixed to the conveyor belt through the optical fiber fixing fixture 812.

[0122] Specifically, the optical fiber fixing fixture 812 is usually composed of two parts, respectively marked as the optical fiber fixing fixture 812(1) and the optical fiber fixing fixture 812(2). The connection relationship between the optical fiber fixing fixture 812, the vibration measuring optical fiber 811 and the conveyor belt channel steel 1 is as Figure 11 shown, and the specific structure of the optical fiber fixing fixture 812 is as Figure 12 shown.

[0123] In one embodiment, the vibration measuring optical fiber 812 includes a sensitized optical fiber and a sensitized optical fiber protective sleeve, and the sensitized optical fiber is arranged inside the sensitized optical fiber protective sleeve.

[0124] Among them, the sensitized optical fiber protection sleeve can enhance the sensitized optical fiber's ability to sense vibration signals and reduce external damage to the sensitized optical fiber. The sensitized optical fiber can be arranged along the direction parallel to the running direction of the conveyor belt and installed on the steel frame (channel steel) of the conveyor belt according to the average distribution rule, so as to be able to capture the vibration signals in the entire monitoring area as much as possible. The data of the wavelength change of the optical signal transmitted through the sensitized optical fiber (the optical signal collected based on the Rayleigh scattering effect) is transmitted to the distributed optical fiber monitoring host 820. Subsequently, the distributed optical fiber monitoring host 820 extracts the characteristic data of the vibration signal, such as the high-order spectrum characteristic, through a series of signal conversion, demodulation, and various acoustic wave spectrum recognition algorithms (such as Mel spectrum, contrast spectrum, high-order spectrum, etc.).

[0125] In an exemplary embodiment, a computer device is provided. The computer device can be a server, and its internal structure diagram can be as shown in Figure 13 the figure. The computer device includes a processor, a memory, an input / output interface (Input / Output, abbreviated as I / O), and a communication interface. Among them, the processor, the memory, and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store data such as the vibration signals of the conveyor belt. The input / output interface of the computer device is used to exchange information between the processor and external devices. The communication interface of the computer device is used to communicate with external terminals through a network connection. When the computer program is executed by the processor, it implements a conveyor belt tear detection method.

[0126] Those skilled in the art can understand that Figure 13 the structure shown in the figure is only a block diagram of some structures related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine some components, or have different component arrangements.

[0127] In an exemplary embodiment, a computer device is provided, including a memory and a processor. A computer program is stored in the memory, and when the processor executes the computer program, it implements the steps in the above-mentioned conveyor belt tear detection method embodiment.

[0128] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-described embodiment of the conveyor belt tear detection method are implemented.

[0129] In one embodiment, a computer program product is provided, including a computer program which, when executed by a processor, implements the steps in the above-described embodiment of the conveyor belt tear detection method.

[0130] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use, and processing of relevant data need to comply with relevant regulations.

[0131] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, database, or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc. The databases involved in the embodiments provided in the present application can include at least one of relational databases and non-relational databases. Non-relational databases can include distributed databases based on blockchain, etc., without limitation. The processors involved in the embodiments provided in the present application can be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, data processing logics based on quantum computing, artificial intelligence (AI) processors, etc., without limitation.

[0132] The technical features of the above embodiments can be combined arbitrarily. For the sake of concise description, 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, it should be considered as the scope recorded in the present application.

[0133] The above-described embodiments merely represent several implementation manners of the present application. The description thereof is relatively specific and detailed, but it should not be construed as a limitation to the patent scope of the present application. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present application, several modifications and improvements can still be made, and these all fall within the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the appended claims.

Claims

1. A conveyor belt tear detection method, characterized in that: The method comprises: Obtain the vibration signal of the conveyor belt; Performing time-frequency domain analysis and feature extraction on the vibration signal to obtain time-frequency domain feature data of the vibration signal; Performing power spectrum analysis on the vibration signal to obtain power spectrum data of the vibration signal; Based on the time-frequency domain feature data and the power spectrum data, it is detected whether the conveyor belt is torn.

2. The method according to claim 1, characterized in that The detecting whether the conveyor belt is torn based on the time-frequency domain feature data and the power spectrum data comprises: Based on the time-frequency domain feature data, detecting whether the conveyor belt is torn, and obtaining a first tear detection result; Based on the power spectrum data, detecting whether the conveyor belt is torn, and obtaining a second tear detection result; When both the first tear detection result and the second tear detection result indicate that the conveyor belt is torn, it is determined that the conveyor belt is torn.

3. The method according to claim 2, characterized in that The time-frequency domain feature data includes a time-domain feature value, a frequency-domain feature value, and a time-frequency feature value. Based on the time-frequency domain feature data, detecting whether the conveyor belt is torn to obtain a first tear detection result includes: When at least two of the following conditions are met, it is determined that the conveyor belt is torn, and a first tear detection result is obtained: The first item is that the time domain characteristic value exceeds a preset time domain characteristic value range; The second item is that the frequency domain eigenvalue exceeds a preset frequency domain eigenvalue range; The third item is that the time-frequency characteristic value exceeds a preset time-frequency characteristic value range.

4. The method according to claim 3, characterized in that: The number of the time domain eigenvalues, the frequency domain eigenvalues, and the time-frequency eigenvalues ​​is multiple, the time domain eigenvalues ​​correspond to a preset time domain eigenvalue threshold range one-to-one, the frequency domain eigenvalues ​​correspond to a preset frequency domain eigenvalue threshold range one-to-one, and the time-frequency eigenvalues ​​correspond to a preset time-frequency eigenvalue threshold range one-to-one, and the method further includes: Comparing each of the time domain feature values ​​with a corresponding preset time domain feature value threshold range, respectively, and determining that the time domain feature value exceeds the preset time domain feature value threshold range when the number of time domain feature values ​​exceeding the preset time domain feature value threshold range is greater than a preset number threshold; Comparing each of the frequency domain eigenvalues ​​with the corresponding preset frequency domain eigenvalue threshold range respectively, and determining that the frequency domain eigenvalue exceeds the preset frequency domain eigenvalue threshold range when the number of frequency domain eigenvalues ​​exceeding the preset frequency domain eigenvalue threshold range is greater than the preset number threshold; Each of the time-frequency feature values ​​is compared with the corresponding preset time-frequency feature value threshold range. When the number of time-frequency feature values ​​exceeding the preset time-frequency feature value threshold range is greater than the preset number threshold, it is determined that the time-frequency feature value exceeds the preset time-frequency feature value range.

5. The method according to any one of claims 2 to 4, characterized in that: The detecting whether the conveyor belt is torn based on the power spectrum data to obtain a second tear detection result includes: Performing feature extraction on the power spectrum data to obtain power spectrum feature data; Taking the power spectrum feature data as input, calling the trained error back propagation neural network to obtain a second tear detection result; The trained error back propagation neural network is trained based on historical power spectrum feature data carrying different tearing labels, and the number of nodes in the input layer of the trained error back propagation neural network is equal to the number of the power spectrum feature data.

6. A conveyor belt tear detection device, characterized in that: The device comprises: A signal acquisition module is used to obtain the vibration signal of the conveyor belt; A first signal analysis module, used for performing time-frequency domain analysis and feature extraction on the vibration signal to obtain time-frequency domain feature data of the vibration signal; A second signal analysis module, used for performing power spectrum analysis on the vibration signal to obtain power spectrum data of the vibration signal; The tear detection module is used to detect whether the conveyor belt is torn based on the time-frequency domain feature data and the power spectrum data.

7. A conveyor belt tear detection system, characterized in that: The system includes a fiber optic sensing device and a distributed fiber optic monitoring host, an industrial intelligent analysis gateway and a voiceprint engine server connected in sequence, wherein the fiber optic sensing device is arranged on a conveyor belt; The distributed optical fiber monitoring host is used to receive the optical signal collected by the optical fiber sensing device based on the Rayleigh scattering effect, perform signal conversion and data demodulation processing on the optical signal, obtain and send the initial vibration signal of the conveyor belt to the industrial intelligent analysis gateway; The industrial intelligent analysis gateway is used to receive the initial vibration signal, pre-process the initial vibration signal, obtain and feed back the vibration signal to the voiceprint engine server; The voiceprint engine server is used to detect whether the conveyor belt is torn based on the conveyor belt tear detection method according to any one of claims 1 to 5.

8. The system according to claim 7, characterized in that The system also includes a terminal service warning platform, a network repeater and a PLC control cabinet connected in sequence, and the terminal service warning platform is connected to the voiceprint engine server; The voiceprint engine server is used to generate and send a tear alarm signal to the terminal service early warning platform when it is determined that the conveyor belt is torn; The terminal service early warning platform is used to generate a shutdown signal when receiving a tear alarm signal, and send the shutdown signal to the PLC control cabinet through the network repeater; The PLC control cabinet is used to control the conveyor belt to stop when receiving the stop signal.

9. The system according to claim 7, characterized in that The optical fiber sensing device comprises a vibration measuring optical fiber and an optical fiber fixing fixture, and the vibration measuring optical fiber is fixed to the conveyor belt by the optical fiber fixing fixture.

10. The system according to claim 9, characterized in that The vibration-measuring optical fiber comprises a sensitizing optical fiber and a sensitizing optical fiber protective cover, and the sensitizing optical fiber is arranged inside the sensitizing optical fiber protective cover.

Images