Carrier roller fault detection method, computer equipment and storage medium

Abstract

The invention discloses a carrier roller fault detection method, computer equipment and a storage medium. The method comprises the following steps: acquiring a channel signal acquired in the operation process of the belt conveyor; wherein the running process of the belt conveyor is driven by the rotation of the carrier rollers; separating the channel signal to obtain a target signal of the carrier roller; and performing fault detection by using the target signal of the carrier roller to obtain a fault detection result of the carrier roller. According to the scheme, the accuracy of carrier roller fault detection can be improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of fault detection, in particular to a fault detection method of a carrier roller, a computer device and a storage medium. BACKGROUND

[0002] In many fields, more and more belt conveyors are applied to material conveying. As a core component of the belt conveyor, the carrier roller is prone to failure due to factors such as dust erosion, lubrication failure, bearing wear and seal damage during long-term operation.

[0003] At present, the detection methods of the carrier roller failure mainly include user inspection and traditional sensors. The user inspection is low in efficiency and is prone to missed judgment and misjudgment. Although the traditional sensor detection can collect related signals of the belt conveyor for fault detection, the fault detection accuracy is not high.

[0004] Therefore, the accuracy of the current fault detection of the carrier roller is low. SUMMARY

[0005] The technical problem solved by the present application is to provide a fault detection method of a carrier roller, a computer device and a storage medium, which can improve the accuracy of the fault detection of the carrier roller.

[0006] The first aspect of the present application provides a fault detection method of a carrier roller, which comprises: acquiring a channel signal collected in the operation process of a belt conveyor; wherein the operation process of the belt conveyor is driven by the rotation of the carrier roller; separating the channel signal to obtain a target signal of the carrier roller; and performing fault detection by using the target signal of the carrier roller to obtain a fault detection result of the carrier roller.

[0007] The second aspect of the present application provides a computer device, which comprises a memory and a processor coupled to each other, the memory stores program data, and the processor is used to execute the program data to realize any step of the above-mentioned fault detection method of the carrier roller.

[0008] The third aspect of the present application provides a computer readable storage medium, which stores program data capable of being executed by a processor, and the program data is used to realize any step of the above-mentioned fault detection method of the carrier roller.

[0009] The scheme can be used for obtaining the channel signal collected in the running process of the belt conveyor, the running process of the belt conveyor is driven by the rotation of the carrier roller, the channel signal is separated to obtain the target signal of the carrier roller, the target signal of the carrier roller can be more accurately extracted, the interference of other irrelevant signals in the running process of the belt conveyor is reduced, the target signal of the carrier roller is used for fault detection to obtain the fault detection result of the carrier roller, the fault detection can be focused on the running state of the carrier roller of the belt conveyor, and therefore the accuracy of the fault detection of the carrier roller is significantly improved.

[0010] It should be understood that the foregoing general description and the following detailed description are only exemplary and explanatory, rather than limiting the present application. BRIEF DESCRIPTION OF DRAWINGS

[0011] In order to more clearly illustrate the technical solutions in the present application, the drawings needed in the embodiments will be briefly introduced as follows. Obviously, the drawings described below are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor on the basis of these drawings. Among them: Figure 1 is a flowchart of an embodiment of the fault detection method of the carrier roller of the present application; Figure 2 is an example schematic diagram of an embodiment of the fault detection method of the carrier roller of the present application; Figure 3 is a flowchart of an embodiment of step S12 in the present application; Figure 1 Figure 4 is a structural schematic diagram of an embodiment of the fault detection device of the carrier roller of the present application; Figure 5 is a structural schematic diagram of an embodiment of the computer device of the present application; Figure 6 is a structural schematic diagram of an embodiment of the computer readable storage medium of the present application. DETAILED DESCRIPTION

[0012] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0013] ​The terms "first" and "second" in this application 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, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, "multiple" means at least two, such as two, three, etc., unless otherwise explicitly specified. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or apparatus that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to such processes, methods, products, or apparatus.

[0014] In this application, the reference to "embodiment" means that a specific feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0015] In this document, the term "and / or" is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. Additionally, the character " / " generally indicates that the preceding and following related objects have an "or" relationship. Furthermore, "many" in this document means two or more. Moreover, the term "at least one" in this document means any combination of at least two of any one or more of a plurality of objects. For example, including at least one of A, B, and C can mean including any one or more elements selected from the set consisting of A, B, and C.

[0016] This application provides the following embodiments, and each embodiment is described in detail below.

[0017] Please see Figure 1 , Figure 1 This is a flowchart illustrating an embodiment of the idler roller fault detection method of this application. The method may include the following steps: S11: Acquire channel signals collected during the operation of the belt conveyor; wherein, the operation of the belt conveyor is driven by the rotation of the idler rollers.

[0018] The belt conveyor is equipped with at least one idler roller, for example, installed below the conveyor belt. The rotation of the idler roller drives the conveyor belt to rotate cyclically. During the operation of the belt conveyor, such as during normal operation, channel signals can be collected.

[0019] In some implementations, the belt conveyor is sampled using a preset sampling method (such as a preset sampling frequency and sampling duration), and the channel signals collected from the belt conveyor are analyzed. This is a one-dimensional time series data, where F is the sampling frequency and T is the sampling duration.

[0020] In some embodiments, the distributed optical fiber sensor can sense the rotational sound emitted by the idler rollers, and can be used to collect channel signals during the operation of the belt conveyor. The distributed optical fiber sensor is a sensor that uses optical fiber as the sensing element and signal transmission medium, and can simultaneously acquire information on the spatial distribution and time-varying characteristics of the measured field. Optionally, the distributed optical fiber sensor can be a distributed optical fiber sensor based on φ-OTDR (Phase Sensitive Optical Time Domain Reflectometric). Optionally, at least a portion of the distributed optical fiber sensor is deployed at a corresponding location on the belt conveyor. For example, a heterodyne coherent detection structure can be used, with the length of the distributed optical fiber sensor deployed at the corresponding location on the belt conveyor being L meters, the spatial resolution of the distributed optical fiber sensor being set to S meters, and the number of channels being L / S. This application does not limit the type of optical fiber sensor.

[0021] In some embodiments, at least a portion of the distributed fiber optic sensor is deployed at the corresponding location on the belt conveyor, while another portion is deployed at a location outside the corresponding location on the belt conveyor, i.e., a non-belt conveyor location. Optionally, the front part of the distributed fiber optic sensor corresponds to the non-belt conveyor location; this application does not limit the specific deployment method.

[0022] Please see Figure 2The idler rollers are installed below the conveyor belt of the belt conveyor, and their rotation drives the conveyor belt to rotate cyclically. At least a portion of the distributed fiber optic sensors are deployed at corresponding positions on the belt conveyor. The sensing element of the distributed fiber optic sensor includes a sensing fiber, the front end of which is connected to a computer or network device. The sensing fiber can extend from the computer (or network) device to the belt conveyor. A portion of the sensing fiber is deployed between the computer (or network) device and the belt conveyor, i.e., outside the belt conveyor, while another portion is deployed at the corresponding position on the belt conveyor. The channel signals collected by the deployed distributed fiber optic sensors can be acquired, i.e., the channel signals collected during the operation of the belt conveyor. For example, the channel signals can be represented using a spectrum diagram, where the vertical axis can be amplitude and the horizontal axis can be time per second (Time / s).

[0023] S12: Separate the channel signal to obtain the target signal of the idler roller.

[0024] Since the channel signal is a mixture of channel signals collected from the belt conveyor and channel signals collected from non-belt conveyors, the channel signal can be separated to obtain the target signal of the idler roller.

[0025] In some implementations, considering that the aforementioned sensing fiber can sense the sound field, the channel signal can be... The sound is converted into an audio signal, and then the rotation sound of the idler roller is separated from the aliased audio signal to obtain the target signal of the idler roller.

[0026] Since the aliased audio signal is a single-channel under-aliased signal, the rotation sound of the idler roller can be separated from the single-channel under-aliased audio signal. In order to effectively extract the audio signal of the idler roller rotation from the aliased audio signal, the channel signal collected at the location of the belt conveyor and the channel signal collected at the location of the non-belt conveyor can be acquired separately, and then the target signal of the idler roller can be obtained by spectral subtraction.

[0027] In some embodiments, please refer to Figure 3 This embodiment can further extend step S12 of the above embodiment. Separating the channel signal to obtain the target signal of the idler roller can include the following steps: S121: Extract the first channel signal and the second channel signal from the channel signals, wherein the first channel signal is collected at the position corresponding to the non-belt conveyor, and the second channel signal is collected at the position corresponding to the belt conveyor.

[0028] Continue reading Figure 2 It can be obtained from the channel signals. In the process, the first channel signal and the second channel signal are extracted. The first channel signal is collected at a location other than the corresponding position of the belt conveyor, that is, the channel signal not deployed at the position of the belt conveyor is extracted. The second channel signal is collected at the corresponding position of the belt conveyor, that is, the sensor channel signal deployed at the position of the belt conveyor is extracted.

[0029] In some implementations, the first channel signal corresponds to a first duration, and the second channel signal corresponds to a second duration, where the first duration is shorter than the second duration. Therefore, it is possible to determine the duration from the channel signals. In this process, the first channel signal of the first duration and the second channel signal of the second duration are extracted. For example, the first duration is extracted. The first duration is obtained from the channel signal at the location where the second-sensing fiber optic cable is not deployed at the conveyor belt position. Extract the second duration from the first channel signal. The second duration is obtained by detecting the sensor channel signal deployed at the location of the belt conveyor. The second channel signal, and .

[0030] Optionally, it can be from the channel signal In this application, at least a portion of the channel signals collected at locations other than those on the belt conveyor are extracted as the first channel signal, and at least a portion of the channel signals collected at locations on the belt conveyor are extracted as the second channel signal. This application does not limit the extraction method.

[0031] Optionally, channel signal Includes channel signals collected at locations other than the belt conveyor. and the channel signal collected at the corresponding position on the belt conveyor Extract the first duration Seconds (e.g., truncating any consecutive seconds) Channel signals collected at non-belt conveyor locations (seconds) The first channel signal is obtained. Extract the second duration Seconds (e.g., truncating any consecutive seconds) Channel signal collected at the corresponding position on the belt conveyor (seconds) The second channel signal is obtained. Optionally, the first duration can be determined based on the channel signal. The corresponding acquisition duration is determined, such as by a preset ratio or a set duration, and the second duration can be determined based on the channel signal. The corresponding data collection duration is determined, such as by a preset ratio or a set duration. It is understood that the first and second durations can be determined based on the application scenario (such as the size of the belt conveyor), and this application does not impose any restrictions on the duration.

[0032] S122: The first channel signal and the second channel signal are spliced ​​together to obtain the spliced ​​channel signal.

[0033] The first channel signal extracted above can be used. Second channel signal By splicing the data, such as horizontally splicing, the spliced ​​channel signal is obtained. ; .

[0034] S123: Use the splicing channel signal to determine the target signal of the idler roller.

[0035] The splicing channel signal is a single-channel aliased channel signal. It can be processed, such as separating the splicing channel signal to determine the target signal of the idler roller.

[0036] In some implementations, the splicing channel signals can be... As input to the spectral subtraction method, the splicing channel signal is processed using the spectral subtraction method to obtain the target signal of the idler roller.

[0037] The parameters of spectral subtraction can be set first, such as setting the frame length to fl, the frame shift to fs, the preset number of frames (such as the number of frames without a preceding voice segment or the number of frames of noise frames) to N, the over-subtraction factor to a, the gain compensation factor to b, etc. This application does not impose any restrictions on these.

[0038] The splicing channel signal is processed into frames according to a preset framing method, resulting in several frames of frame signals. Specifically, the splicing channel signal... It can represent a channel signal containing the target signal plus noise, and can splice the channel signals according to a frame length of fl and a frame shift of fs. Framing is performed to obtain several frames M (M is an integer) of frame signals, where the overlap length between adjacent frames is fs, so that each frame overlaps by fl-fs, which can reduce inter-frame distortion and improve signal continuity.

[0039] Several frames (M frames) contain noise frames and target frames. The noise frames correspond to the first channel signal, that is, the noise frames correspond to the non-belt conveyor positions. The target frames correspond to the second channel signal, that is, the belt conveyor positions. The target frames can correspond to the target signals. The number of preamble frames without voice segments can represent the extracted noise frames, which are used to estimate the power spectrum of the noise frames. It is necessary to ensure that there are no target signals in the preamble and that it only contains noise. A preset number of extracted frames can be used as the noise frames.

[0040] Take from the frame signal of frame M The frame signal serves as pre-noise, i.e., a preset number of noise frames N. A preset estimate (such as averaging or squaring) can be performed on the preset number of noise frames to obtain the power spectrum P of the noise frames. Specifically, the noise spectrum of a single frame can be calculated first: perform a Fourier transform on each noise frame to obtain its complex spectrum (e.g., amplitude spectrum + phase spectrum). The power spectra (squared amplitude spectra) of the N noise frames are averaged to obtain the estimated power spectrum of the noise frame, which is then used as the power spectrum P of the noise frame. Here, the power spectrum of each frame is the square of the amplitude spectrum; averaging over N frames reduces the randomness of the noise spectrum.

[0041] The power spectrum of the noisy frame is used to process the frame signal of each frame to obtain the processing result of each frame. For each frame signal, the estimated power spectrum P of the noisy frame is used for spectral subtraction to obtain the processing result of each frame, thus removing the power spectrum of the noisy frame. Specifically, a first transform can be performed on the frame signal of each frame to obtain the corresponding amplitude value Mag and phase value Phase of each frame. The first transform can be Fourier transform or fast Fourier transform, etc. Then, over-subtraction processing is performed using the power spectrum P of the noisy frame and the amplitude value Mag of each frame to obtain the power spectrum of the target signal. Optionally, over-subtraction processing can be performed directly using the power spectrum P of the noisy frame and the amplitude value Mag of each frame. Since there may be residual noise due to errors in the noise spectrum estimation, an over-subtraction factor a and a gain compensation factor b can be introduced to over-subtract the power spectrum P of the noisy frame and the amplitude value Mag of each frame. Introducing an over-subtraction factor a can enhance the noise suppression effect. After over-subtraction, the amplitude value of the target signal may be attenuated. Introducing a gain compensation factor b can restore the energy and obtain the amplitude value (amplitude spectrum) of the target signal in each frame, which is also the power spectrum S of the target signal in each frame.

[0042] For example, for each frame, the power spectrum of that frame (the square of the amplitude value Mag) and the power spectrum P of the processed noise frame (multiplied by the over-subtraction factor a) can be obtained, followed by an over-subtraction of the first power spectrum. Then, the second power spectrum is obtained by processing the power spectrum of that frame using the gain compensation factor b (e.g., multiplying). The maximum value between the first and second power spectra is obtained to obtain the power spectrum S of the target signal in that frame. It is understood that the power spectrum of each frame can also be represented using the amplitude value Mag, in which case the square root of the power spectrum P of the noise frame can be taken for calculation. This application does not limit this.

[0043] For example, for each frame, {Mag-a} can be obtained. The maximum value in the set is used to obtain the power spectrum S of the target signal in each frame.

[0044] By using the phase value (Phase) of each frame, the power spectrum (S) of the corresponding target signal is processed to obtain the processed signal for each frame. For example, it is possible to obtain each frame. To obtain the processing signal corresponding to each frame. , where j is the imaginary unit.

[0045] Then, the processing signals for each frame. A second transformation is performed to obtain the processing results for each frame. This second transformation is the inverse of the first transformation; for example, it may be an inverse Fourier transform or an inverse fast Fourier transform. For instance, the processing signals for each frame can be... Perform an inverse fast Fourier transform and take the real part of the result to obtain the processing results for each frame.

[0046] Then, the frame signals and processing results of each frame are used for enhancement to obtain the enhanced signals for each frame. For example, for each frame (such as the i-th frame), the frame signal can be... and processing results The signals are added together to obtain the enhanced signal for that frame. The enhanced signal for each frame can be represented as follows: That is, we obtain the noise-removed channel signal.

[0047] Finally, by combining the enhanced signals from each frame, the target signal y of the idler roller can be obtained, which is the sound of the idler roller rotating.

[0048] In some embodiments, after separating the channel signal to obtain the target signal of the idler roller, noise in the target signal y can be further filtered out. Specifically, a preset filter can be used to perform noise filtering on the target signal to obtain the filtered target signal. Optionally, the preset filter can be a Butterworth filter, Chebyshev filter, Kalman filter, etc., such as an nth-order Butterworth filter. For example, the target signal can be... The frame signals of subsequent sequence frames (such as frames after a preset number of frames N of noise) are used as the frame signals of the target frame. The frame signals of the target frame are normalized to obtain a normalized result. Then, a Butterworth low-pass filter is used to further filter out noise from the normalized result, resulting in the filtered target signal. .

[0049] Continue reading Figure 1 Following step S12 above, the following steps are also included: S13: Use the target signal of the idler roller to perform fault detection and obtain the fault detection result of the idler roller.

[0050] A fault detection model can be used to detect faults in the target signal of the idler roller, and the fault detection result of the idler roller can be obtained. The fault detection model can include a ResNet152 network with an OpenMax layer. It is understood that the fault detection model can be other networks, and this application does not limit the fault detection model.

[0051] Optionally, the target signal for the idler roller can be a filtered target signal. .

[0052] Optionally, the target signal (y or Voiceprint recognition is performed to obtain the target decibel spectrum. Specifically, the target signal can be processed by framing, adding a Hamming window, performing Fourier transform, etc., and then converted into a decibel spectrum to obtain the target decibel spectrum. The window length of the Hamming window and the frame shift of the framing can be set. After the Fourier transform, the amplitude spectrum in the transform result can be converted into a decibel spectrum to obtain the target decibel spectrum. It is understood that the processing procedures for framing, adding a Hamming window, and Fourier transform can be referenced here, and this application does not impose any limitations on them.

[0053] Optionally, after performing voiceprint recognition on the target signal to obtain the target decibel spectrum, preset data enhancement can be applied to the target decibel spectrum to obtain an enhanced target decibel spectrum. For example, preset data enhancement includes random rotation, cropping, etc., which can enhance the target decibel spectrum to obtain an enhanced target decibel spectrum.

[0054] Finally, a fault detection model is used to detect faults in the target decibel spectrum to obtain the fault detection results of the idler roller, thereby detecting whether the current idler roller is faulty. Optionally, the fault detection results may include fault or normal status. Alternatively, the fault detection results may include fault type, fault area, etc., and this application does not limit the fault detection results. For example, the types of fault detection results may include jamming, abnormal noise, eccentricity, breakage, etc., and this application does not limit these.

[0055] Alternatively, in order to enable the fault detection model to effectively detect untrained voiceprint signals in an open environment, the enhanced target decibel spectrum can be used as the input to a ResNet152 network (i.e., the fault detection model) with an Openmax layer. The Openmax layer can be used to replace the traditional softmax activation function to obtain the probability score of signals that do not belong to normal voiceprint signals.

[0056] The above solution acquires channel signals collected during the operation of the belt conveyor, which is driven by the rotation of idlers. The channel signals are then separated to obtain the target signals of the idlers, which can be extracted more accurately. This reduces interference from other irrelevant signals during the operation of the belt conveyor. The target signals of the idlers are then used for fault detection to obtain fault detection results. This allows fault detection to focus on the operating status of the idlers themselves, thereby significantly improving the accuracy of idler fault detection.

[0057] It is understood that in the above method of specific implementation, the order in which each step is written does not mean a strict execution order and does not constitute any limitation on the implementation process. The specific execution order of each step should be determined by its function and possible internal logic.

[0058] In some embodiments, this application also provides a fault detection device for idlers, used to implement the fault detection method for idlers in any of the above embodiments.

[0059] Please see Figure 4 , Figure 4 This is a schematic diagram of an embodiment of the idler roller fault detection device of this application. The idler roller fault detection device 20 includes a data acquisition module 21, a separation module 22, and a detection module 23. All modules are interconnected.

[0060] The acquisition module 21 is used to acquire channel signals collected during the operation of the belt conveyor; wherein the operation of the belt conveyor is driven by the rotation of the idler rollers.

[0061] The separation module 22 is used to separate the channel signal to obtain the target signal of the idler roller.

[0062] The detection module 23 is used to perform fault detection using the target signal of the idler roller and obtain the fault detection result of the idler roller.

[0063] It should be noted that the idler roller fault detection device and the idler roller fault detection method provided in the above embodiments belong to the same concept. The specific operation methods of each module and unit have been described in detail in the method embodiments and will not be repeated here. In practical applications, the idler roller fault detection device provided in the above embodiments can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. This application does not impose any limitations on this.

[0064] It is understood that the idler roller fault detection method in this application can be executed by a computer device, which can be any device with processing capabilities, such as a mobile device, computer, server, etc., and this application does not impose any restrictions on it. In some possible implementations, the idler roller fault detection method can be implemented by the processor calling program data stored in memory.

[0065] Regarding the above embodiments, this application provides a computer device; please refer to [link / reference]. Figure 5 , Figure 5This is a schematic diagram of the structure of a computer device according to an embodiment of the present application. The computer device 30 includes a memory 31 and a processor 32, wherein the memory 31 and the processor 32 are coupled to each other. The memory 31 stores program data, and the processor 32 is used to execute the program data to implement the steps of any embodiment of the above-described idler roller fault detection method.

[0066] In this embodiment, processor 32 can also be referred to as a CPU (Central Processing Unit). Processor 32 may be an integrated circuit chip with signal processing capabilities. Processor 32 can also be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. The general-purpose processor can be a microprocessor, or processor 32 can be any conventional processor.

[0067] The methods described in the above embodiments can be implemented as computer programs; therefore, this application proposes a computer-readable storage medium. Please refer to [link to relevant documentation]. Figure 6 , Figure 6 This is a schematic diagram of a computer-readable storage medium according to an embodiment of the present application. The computer-readable storage medium 40 stores program data 41 that can be executed by a processor. The program data 41 can be executed by the processor to implement the steps of any embodiment of the above-described idler roller fault detection method.

[0068] In this embodiment, the computer-readable storage medium 40 can be a USB flash drive, a portable hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk, or a medium that can store program data 41. Alternatively, it can be a server that stores the program data 41. The server can send the stored program data 41 to other devices for execution, or it can run the stored program data 41 itself.

[0069] In some embodiments, the functions or modules of the apparatus provided in the above embodiments of this application can be used to perform the methods described in the above method embodiments. The specific implementation can be referred to the description of the above method embodiments. For the sake of brevity, this application will not repeat the details here.

[0070] The description of the various embodiments above tends to emphasize the differences between the various embodiments. The similarities or similarities between them can be referred to. For the sake of brevity, the present application will not repeat them here.

[0071] In the several embodiments provided in this application, it should be understood that the disclosed methods and apparatus can be implemented in other ways. For example, the apparatus implementations described above are merely illustrative. For instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed may be through some interfaces, and the indirect coupling or communication connection of devices or units may be electrical, mechanical, or other forms.

[0072] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment, depending on actual needs.

[0073] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0074] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a computer, server, or network device, etc.) or processor to execute all or part of the steps of the methods of the various embodiments of this application.

[0075] Obviously, those skilled in the art should understand that the modules or steps of this application described above can be implemented using general-purpose computing devices. They can be centralized on a single computing device or distributed across a network of multiple computing devices. Optionally, they can be implemented using computer-executable program code, and thus stored in a computer-readable storage medium for execution by a computing device, or they can be fabricated as separate integrated circuit modules, or multiple modules or steps can be fabricated as a single integrated circuit module. Therefore, this application is not limited to any particular hardware and software combination.

[0076] The above description is merely an embodiment of this application and does not limit the patent scope of this application. Any equivalent structural or procedural transformations made using the content of this application's specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the patent protection scope of this application.

Claims

1. A method for detecting a failure of an idler, characterized by, The method comprises the following steps: acquiring a channel signal collected in the operation process of the belt conveyor; wherein the operation process of the belt conveyor is driven by the rotation of the carrier roller; separating the channel signal to obtain a target signal of the carrier roller; performing fault detection on the target signal of the carrier roller to obtain a fault detection result of the carrier roller.

2. The method of claim 1, wherein, The acquisition of the channel signal collected in the operation process of the belt conveyor comprises: acquiring the channel signal collected in the operation process of the belt conveyor by using a distributed optical fiber sensor; wherein at least part of the distributed optical fiber sensor is deployed at a corresponding position of the belt conveyor.

3. The method of claim 1, wherein, The separation of the channel signal to obtain the target signal of the carrier roller comprises: extracting a first channel signal and a second channel signal from the channel signal, wherein the first channel signal is collected at a non-belt conveyor corresponding position, and the second channel signal is collected at a belt conveyor corresponding position; splicing the first channel signal and the second channel signal to obtain a spliced channel signal; determining the target signal of the carrier roller by using the spliced channel signal.

4. The method of claim 3, wherein: the first channel signal corresponds to a first time length, and the second channel signal corresponds to a second time length, and the first time length is less than the second time length.

5. The method of claim 3, wherein, The determination of the target signal of the carrier roller by using the spliced channel signal comprises: performing frame processing on the spliced channel signal according to a preset frame division mode to obtain a plurality of frame signals; performing a preset estimation on a preset number of noise frames to obtain a power spectrum of the noise frames; wherein the plurality of frames contain noise frames, and the noise frames correspond to the first channel signal; processing each frame signal by using the power spectrum of the noise frames to obtain a processing result of each frame; obtaining an enhanced signal of each frame by using the frame signal of each frame and the processing result; integrating the enhanced signals of the frames to obtain the target signal of the carrier roller.

6. The method of claim 5, wherein, The processing of each frame signal by using the power spectrum of the noise frames to obtain a processing result of each frame comprises: performing a first transformation on each frame signal to obtain an amplitude value and a phase value corresponding to each frame; performing a subtraction processing on the amplitude value by using the power spectrum of the noise frames to obtain a power spectrum of a target signal; processing the power spectrum of the target signal by using the phase value to obtain a processing signal; performing a second transformation on the processing signal to obtain a processing result of each frame; wherein the second transformation is an inverse transformation of the first transformation.

7. The method of claim 1, wherein, The fault detection on the target signal of the carrier roller to obtain a fault detection result of the carrier roller comprises: performing voiceprint recognition on the target signal to obtain a target decibel spectrum; detecting the target decibel spectrum by using a fault detection model to obtain the fault detection result of the carrier roller.

8. The method of claim 7, wherein: after the voiceprint recognition on the target signal to obtain a target decibel spectrum, the method comprises: performing a preset data enhancement on the target decibel spectrum to obtain an enhanced target decibel spectrum; and / or, before the voiceprint recognition on the target signal to obtain a target decibel spectrum, the method comprises: The target signal is filtered by using a preset filter to obtain a filtered target signal.

9. A computer device, comprising: The memory and the processor are coupled to each other, the memory stores program data, and the processor is configured to execute the program data to implement the steps of the method in any one of claims 1 to 8.

10. A computer-readable storage medium, characterized in that, The memory stores program data capable of being executed by the processor, and the program data is configured to implement the steps of the method in any one of claims 1 to 8.

Images