Belt conveyor abnormity monitoring system and method based on voiceprint recognition

Abstract

The invention discloses a belt conveyor abnormity monitoring system and method based on voiceprint recognition. The system comprises a data acquisition module, a data processing module and an abnormity early warning module. Relates to the technical field of fault monitoring, and solves the technical problem that the abnormity monitoring efficiency and accuracy of a belt conveyor are not high because different areas of the belt conveyor are difficult to carry out targeted monitoring in the prior art. According to the method, the accurate data twin model is constructed by integrating the equipment drawing information, the real-time noise characteristic data and the environment data, so that the belt conveyor is reasonably divided into a plurality of monitoring areas, and the troubleshooting priority is determined according to the cargo capacity of each area, so that efficient and targeted fault detection is realized. According to the method, target voiceprint features of equipment noise in each monitoring area are analyzed and compared with a fault voiceprint feature database to obtain specific fault tags. The process not only improves the accuracy and efficiency of fault identification, but also can effectively reduce the maintenance cost.

Description

Technical Field

[0001] The present invention belongs to the technical field of fault monitoring, and particularly relates to a belt conveyor abnormal monitoring system and method based on voiceprint recognition. Background Art

[0002] As an important equipment for material transportation in industrial production, belt conveyors are widely used in industries such as mines, ports, power, and metallurgy. Their characteristics of long-term continuous operation pose high requirements for the reliability and maintenance efficiency of the equipment. However, during actual use, due to reasons such as wear, overload, and improper installation, various faults may occur in belt conveyors, such as belt deviation, slipping, and tearing. These faults not only affect production efficiency but may also cause serious safety accidents.

[0003] Existing technologies monitor the noise data generated by belt conveyors during operation in real time through sound sensors and analyze the noise data, achieving abnormal monitoring to a certain extent. However, in actual situations, the cargo loads in several areas of the belt conveyor are not the same, and it is difficult for existing technologies to conduct targeted monitoring of different areas of the belt conveyor, resulting in low efficiency and accuracy of abnormal monitoring of the belt conveyor.

[0004] The present invention proposes a belt conveyor abnormal monitoring system and method based on voiceprint recognition to solve the above technical problems. Summary of the Invention

[0005] The present invention aims to solve at least one of the technical problems existing in the prior art; for this purpose, the present invention proposes a belt conveyor abnormal monitoring system and method based on voiceprint recognition, which is used to solve the technical problems that it is difficult for existing technologies to conduct targeted monitoring of different areas of the belt conveyor, resulting in low efficiency and accuracy of abnormal monitoring of the belt conveyor.

[0006] To achieve the above object, the first aspect of the present invention provides a belt conveyor abnormal monitoring system based on voiceprint recognition, including: a data processing module, and a data acquisition module and an abnormal warning module connected thereto;

[0007] The data acquisition module: is used to obtain the equipment drawing information of the belt conveyor, as well as the noise characteristic data and environmental data of the belt conveyor during operation;

[0008] The data processing module: is used to construct a data twin model of the belt conveyor based on the equipment drawing information, noise characteristic data, and environmental data; divide the belt conveyor into several monitoring areas based on the data twin model and obtain the cargo loads of each monitoring area; and,

[0009] Determine the regional investigation priority sequence based on the cargo volume of several monitoring areas; analyze the noise characteristic data of each monitoring area in turn based on the regional investigation priority sequence to obtain the corresponding target voiceprint characteristics; input the target voiceprint characteristics of each monitoring area into the fault voiceprint characteristic database to obtain fault labels;

[0010] The abnormal warning module: used to calculate the equipment abnormal score of the belt conveyor based on the noise characteristic data; perform fault warning on the belt conveyor based on the equipment abnormal score and the fault label.

[0011] Preferably, constructing a digital twin model of the belt conveyor based on the equipment drawing information, noise characteristic data and environmental data includes:

[0012] Extract the equipment drawing information, noise characteristic data and environmental data of the belt conveyor; input the equipment drawing information into 3D model software to create a 3D geometric model of the building to be measured corresponding to the belt conveyor, synchronize the noise characteristic data and environmental data to the 3D geometric model, and mark the synchronized 3D geometric model as the digital twin model.

[0013] Preferably, dividing the belt conveyor into several monitoring areas based on the digital twin model includes:

[0014] Extract the digital twin model corresponding to the belt conveyor, divide the belt in the belt conveyor into several monitoring areas according to a preset length, and sequentially mark the numbers of each monitoring area as i; where i = 1, 2,..., n, and n is the total number of monitoring areas.

[0015] Preferably, determining the regional investigation priority sequence based on the cargo volume of several monitoring areas includes:

[0016] Extract the cargo volume of each monitoring area, perform linear fitting on the cargo volume of each monitoring area to obtain the cargo volume curves of several monitoring areas; calculate the first derivative function of the cargo volume curve to obtain the cargo volume change function; calculate the difference between the function maximum value and the function minimum value of the cargo volume change function, and mark the difference as the cargo volume change value; sort the cargo volume change values in descending order to obtain the regional investigation priority sequence.

[0017] Preferably, analyzing the noise characteristic data of each monitoring area in turn based on the regional investigation priority sequence includes:

[0018] Extract the regional investigation priority sequence; analyze the noise characteristic data of each monitoring area in turn according to the regional investigation priority sequence to obtain the target voiceprint characteristics of the corresponding monitoring area.

[0019] Preferably, inputting the target voiceprint characteristics of each monitoring area into the fault voiceprint characteristic database includes:

[0020] Extract the target voiceprint features of each monitoring area, input the target voiceprint features into the fault voiceprint feature database for matching, and obtain the matching result; determine whether the target voiceprint features are successfully matched; if so, mark the matching result as a fault label; if not, mark the fault label as no fault.

[0021] Preferably, the fault voiceprint feature database is constructed in the following manner:

[0022] Simulate the operation of the belt conveyor through a digital twin model to obtain several groups of simulated fault features and corresponding simulated sound data; analyze the simulated sound data based on the voiceprint recognition algorithm to obtain fault voiceprint features; save the mapping relationship between several groups of simulated fault features and fault voiceprint features to the fault voiceprint feature database.

[0023] Preferably, calculating the equipment abnormality score of the belt conveyor based on the noise feature data includes:

[0024] Extract the noise feature data of each monitoring area; wherein, the noise feature data includes a decibel feature value and a frequency feature value;

[0025] Through the formula Calculate the equipment abnormality score SYP of the belt conveyor; wherein, FBi is the decibel feature value of monitoring area i, and PLi is the frequency feature value of monitoring area i; both a and b are proportionality coefficients greater than 0.

[0026] Preferably, performing fault early warning on the belt conveyor based on the equipment abnormality score and the fault label includes:

[0027] Extract the equipment abnormality score and the fault label; determine whether the equipment abnormality score is greater than a preset abnormality score threshold; if so, integrate the equipment abnormality score and the fault label into a fault early warning message, and send the fault early warning message to the intelligent terminal of the equipment maintenance personnel; if not, continue to monitor the belt conveyor.

[0028] The second aspect of the present invention provides a method for abnormal monitoring of a belt conveyor based on voiceprint recognition, including:

[0029] S1: Obtain the equipment drawing information of the belt conveyor, as well as the noise feature data and environmental data during the operation of the belt conveyor;

[0030] S2: Construct a digital twin model of the belt conveyor based on the equipment drawing information, noise feature data, and environmental data;

[0031] S3: Divide the belt conveyor into several monitoring areas based on the digital twin model, and obtain the load capacity of each monitoring area;

[0032] S4: Determine the regional investigation priority sequence based on the cargo capacity of several monitoring regions;

[0033] S5: Analyze the noise feature data of each monitoring region in turn based on the regional investigation priority sequence to obtain the target voiceprint features of the corresponding monitoring region;

[0034] S6: Input the target voiceprint features of each monitoring region into the fault voiceprint feature database to obtain the corresponding fault labels;

[0035] S7: Calculate the equipment anomaly score of the belt conveyor based on the noise feature data;

[0036] S8: Conduct fault early warning for the belt conveyor based on the equipment anomaly score and the fault labels.

[0037] Compared with the prior art, the beneficial effects of the present invention are:

[0038] By integrating equipment drawing information, real-time noise feature data, and environmental data, the present invention constructs an accurate digital twin model, reasonably divides the belt conveyor into multiple monitoring regions, and determines the investigation priority based on the cargo capacity of each region, thereby realizing efficient and targeted fault detection. This method analyzes the target voiceprint features of the equipment noise in each monitoring region and compares them with the fault voiceprint feature database to obtain specific fault labels. At the same time, it calculates the equipment anomaly score, providing a quantitative basis for fault early warning. This process not only improves the accuracy and efficiency of fault identification, but also can effectively reduce maintenance costs, extend the service life of the equipment, and enhance the safety and stability of equipment operation, which is of great significance for the maintenance and management of belt conveyors. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0040] Figure 1 It is the overall flowchart of the abnormal monitoring method for belt conveyors based on voiceprint recognition of the present invention;

[0041] Figure 2 It is the schematic diagram of the principle of the abnormal monitoring system for belt conveyors based on voiceprint recognition of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0042] The technical solution of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0043] Please refer to Figure 1 - Figure 2 , an embodiment of the first aspect of the present invention provides an abnormal monitoring system for a belt conveyor based on voiceprint recognition, including: a data processing module, and a data acquisition module and an abnormal warning module connected thereto;

[0044] The data acquisition module: is used to obtain the equipment drawing information of the belt conveyor, as well as the noise characteristic data and environmental data of the belt conveyor during operation;

[0045] The data processing module: is used to construct a digital twin model of the belt conveyor based on the equipment drawing information, noise characteristic data and environmental data; divide the belt conveyor into several monitoring areas based on the digital twin model, and obtain the load capacity of each monitoring area; and,

[0046] Determine the area investigation priority sequence based on the load capacity of several monitoring areas; analyze the noise characteristic data of each monitoring area in turn based on the area investigation priority sequence to obtain the corresponding target voiceprint characteristics; input the target voiceprint characteristics of each monitoring area into the fault voiceprint characteristic database to obtain fault labels;

[0047] The abnormal warning module: is used to calculate the equipment abnormal score of the belt conveyor based on the noise characteristic data; perform fault warning on the belt conveyor based on the equipment abnormal score and the fault label.

[0048] In this embodiment, constructing a digital twin model of the belt conveyor based on the equipment drawing information, noise characteristic data and environmental data includes:

[0049] Extract the equipment drawing information, noise characteristic data and environmental data of the belt conveyor; input the equipment drawing information into 3D model software to create a 3D geometric model of the building to be measured corresponding to the building, synchronize the noise characteristic data and environmental data to the 3D geometric model, and mark the synchronized 3D geometric model as a digital twin model.

[0050] In this embodiment, dividing the belt conveyor into several monitoring areas based on the digital twin model includes:

[0051] Extract the digital twin model corresponding to the belt conveyor, divide the belt in the belt conveyor into several monitoring areas according to a preset length, and sequentially mark the numbers of each monitoring area as i; where i = 1, 2,..., n, and n is the total number of monitoring areas.

[0052] In this embodiment, the regional screening priority sequence is determined based on the cargo volume of several monitoring areas, including:

[0053] The cargo capacity of each monitoring area is extracted, and a linear fit is performed on the cargo capacity of each monitoring area to obtain cargo capacity curves of several monitoring areas; the first-order derivative function of the cargo capacity curve is calculated to obtain the cargo capacity change function; the difference between the maximum value and the minimum value of the cargo capacity change function is calculated, and the difference is marked as the cargo capacity change value; the cargo capacity change values are sorted in order from large to small to obtain the regional inspection priority sequence.

[0054] It should be noted that the more drastic the change in the cargo load in the monitoring area, the higher the frequency of the belt in the corresponding monitoring area being impacted by the cargo, which leads to a greater probability of abnormality in the belt conveyor.

[0055] The present invention determines the change value of cargo volume by linear fitting and first-order derivative calculation of the cargo volume in each monitoring area, and sorts and generates a regional inspection priority sequence. This method effectively identifies areas with drastic changes in cargo volume, provides a basis for precise maintenance, and improves the pertinence and efficiency of fault detection. By quantifying the changes in cargo volume in each area, it not only optimizes the maintenance strategy and reduces resource waste, but also reduces the risk of equipment failure, enhances the safety and stability of belt conveyor operation, and helps reduce long-term maintenance costs.

[0056] In this embodiment, the noise characteristic data of each monitoring area is analyzed in sequence based on the area screening priority sequence, including:

[0057] Extract the regional screening priority sequence; analyze the noise characteristic data of each monitoring area in turn according to the regional screening priority sequence to obtain the target voiceprint characteristics of the corresponding monitoring area.

[0058] In this embodiment, the target voiceprint features of each monitoring area are input into the fault voiceprint feature database, including:

[0059] Extract the target voiceprint features of each monitoring area, input the target voiceprint features into the fault voiceprint feature database for matching, and obtain the matching results; determine whether the target voiceprint features are successfully matched; if yes, mark the matching result as a fault label; if not, mark the fault label as no fault.

[0060] In this embodiment, the fault voiceprint feature database is constructed in the following way:

[0061] The belt conveyor is simulated and run through a digital twin model to obtain several groups of simulated fault characteristics and corresponding simulated sound data; the simulated sound data is analyzed based on a voiceprint recognition algorithm to obtain fault voiceprint characteristics; the mapping relationship between several groups of simulated fault characteristics and fault voiceprint characteristics is saved to a fault voiceprint characteristic database; wherein, the voiceprint recognition algorithm is Mel Frequency Cepstral Coefficients.

[0062] It should be noted that the simulated fault characteristics include belt deviation, belt slipping, belt tearing and wear, idler faults, etc.

[0063] The present invention uses a digital twin model to simulate and run a belt conveyor to obtain simulated fault characteristics and their corresponding simulated sound data, analyzes these sound data through a voiceprint recognition algorithm to obtain fault voiceprint characteristics, and saves the mapping relationship between the simulated fault characteristics and the fault voiceprint characteristics to a database. This method realizes the accurate prediction and rapid identification of potential faults of equipment, not only improves the maintenance efficiency, reduces the downtime, but also reduces the maintenance cost and the fault occurrence rate, provides strong data support and technical guarantee for the predictive maintenance of industrial equipment, and significantly improves the safety and stability of the production line.

[0064] In this embodiment, calculating the equipment anomaly score of the belt conveyor based on the noise characteristic data includes:

[0065] Extracting the noise characteristic data of each monitoring area; wherein, the noise characteristic data includes a decibel characteristic value and a frequency characteristic value;

[0066] Through the formula Calculate the equipment anomaly score SYP of the belt conveyor; wherein, FBi is the decibel characteristic value of monitoring area i, and PLi is the frequency characteristic value of monitoring area i; both a and b are proportionality coefficients greater than 0.

[0067] It should be noted that the values of the proportionality coefficients a and b are related to the service life of the belt conveyor; when the service life of the belt conveyor is longer, the actual values of a and b are set correspondingly larger.

[0068] Exemplarily, set the proportionality coefficients a = 0.1 and b = 1.2; the noise characteristic data of monitoring areas 1, 2, and 3 are shown in the following table:

[0069] Monitoring area i 1 2 3 Decibel eigenvalue 80dB 75dB 93dB Frequency eigenvalue 1200Hz 1500Hz 900Hz

[0070] The equipment anomaly score SYP of the belt conveyor is calculated through the formula to be approximately 16.75.

[0071] In this embodiment, fault warning is performed on the belt conveyor based on the equipment anomaly score and fault labels, including:

[0072] Extract the device anomaly score and the fault label; determine whether the device anomaly score is greater than a preset anomaly score threshold; if so, integrate the device anomaly score and the fault label into a fault warning message, and send the fault warning message to the smart terminal of the device maintenance personnel; if not, continue to monitor the belt conveyor.

[0073] Exemplarily, set the anomaly score threshold to 12, the device anomaly score to 16.75, and the fault label to belt slipping; since the device anomaly score is greater than the preset anomaly score threshold, the device anomaly score and the fault label are integrated into a fault warning message, and the fault warning message is sent to the smart terminal of the device maintenance personnel.

[0074] An embodiment of the second aspect of the present invention provides a method for monitoring belt conveyor anomalies based on voiceprint recognition, including:

[0075] S1: Obtain the device drawing information of the belt conveyor, as well as the noise characteristic data and environmental data during the operation of the belt conveyor;

[0076] S2: Construct a digital twin model of the belt conveyor based on the device drawing information, noise characteristic data, and environmental data;

[0077] S3: Divide the belt conveyor into several monitoring areas based on the digital twin model, and obtain the cargo volume of each monitoring area;

[0078] S4: Determine the area inspection priority sequence based on the cargo volume of several monitoring areas;

[0079] S5: Analyze the noise characteristic data of each monitoring area in turn based on the area inspection priority sequence to obtain the target voiceprint characteristics of the corresponding monitoring area;

[0080] S6: Input the target voiceprint characteristics of each monitoring area into the fault voiceprint characteristic database to obtain the corresponding fault label;

[0081] S7: Calculate the device anomaly score of the belt conveyor based on the noise characteristic data;

[0082] S8: Perform fault warning on the belt conveyor based on the device anomaly score and the fault label.

[0083] Some of the data in the above formula are calculated by removing the dimension and taking their numerical values. The formula is obtained by software simulation of a large amount of collected data to get a formula closest to the actual situation; the preset parameters and preset thresholds in the formula are set by those skilled in the art according to the actual situation or obtained through simulation of a large amount of data.

[0084] The working principle of the present invention:

[0085] The present invention obtains the equipment drawing information of a belt conveyor, as well as the noise characteristic data and environmental data during the operation of the belt conveyor; constructs a digital twin model of the belt conveyor based on the equipment drawing information, noise characteristic data and environmental data; divides the belt conveyor into several monitoring areas based on the digital twin model, and obtains the cargo capacity of each monitoring area; determines the regional investigation priority sequence based on the cargo capacity of several monitoring areas; analyzes the noise characteristic data of each monitoring area in turn based on the regional investigation priority sequence to obtain the target voiceprint characteristics of the corresponding monitoring area; inputs the target voiceprint characteristics of each monitoring area into a fault voiceprint characteristic database to obtain the corresponding fault labels; calculates the equipment anomaly score of the belt conveyor based on the noise characteristic data; and conducts fault early warning on the belt conveyor based on the equipment anomaly score and fault labels.

[0086] The above embodiments are only used to illustrate the technical method of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical method of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical method of the present invention.

Claims

1. An abnormal monitoring system for a belt conveyor based on voiceprint recognition, comprising: A data acquisition module, a data processing module, and an anomaly warning module; characterized in that the data acquisition module: is used to obtain the equipment drawing information of the belt conveyor, as well as the noise characteristic data and environmental data during the operation of the belt conveyor; the data processing module: is used to construct a digital twin model of the belt conveyor based on the equipment drawing information, noise characteristic data, and environmental data; divide the belt conveyor into several monitoring areas based on the digital twin model, and obtain the cargo volume of each monitoring area; and determine the regional investigation priority sequence based on the cargo volume of several monitoring areas; analyze the noise characteristic data of each monitoring area in turn based on the regional investigation priority sequence to obtain the corresponding target voiceprint characteristics; input the target voiceprint characteristics of each monitoring area into the fault voiceprint characteristic database to obtain a fault label; the anomaly warning module: is used to calculate the equipment anomaly score of the belt conveyor based on the noise characteristic data; perform fault warning on the belt conveyor based on the equipment anomaly score and the fault label.

2. The abnormal monitoring system of a belt conveyor based on voiceprint recognition according to claim 1, wherein The construction of the digital twin model of the belt conveyor based on the equipment drawing information, noise characteristic data, and environmental data includes: Extract the equipment drawing information, noise characteristic data, and environmental data of the belt conveyor; input the equipment drawing information into 3D model software to create a 3D geometric model of the building to be measured corresponding to the belt conveyor, synchronize the noise characteristic data and environmental data to the 3D geometric model, and mark the synchronized 3D geometric model as the digital twin model.

3. The abnormal monitoring system of a belt conveyor based on voiceprint recognition according to claim 1, wherein, The division of the belt conveyor into several monitoring areas based on the digital twin model includes: Extract the digital twin model corresponding to the belt conveyor, divide the belt in the belt conveyor into several monitoring areas according to a preset length, and sequentially mark the numbers of each monitoring area as i; where i = 1, 2,..., n, and n is the total number of monitoring areas.

4. The abnormal monitoring system of a belt conveyor based on voiceprint recognition according to claim 1, characterized in that, The determination of the regional investigation priority sequence based on the cargo volume of several monitoring areas includes: Extract the cargo volume of each monitoring area, perform linear fitting on the cargo volume of each monitoring area to obtain the cargo volume curves of several monitoring areas; calculate the first derivative function of the cargo volume curve to obtain the cargo volume change function; calculate the difference between the function maximum value and the function minimum value of the cargo volume change function, and mark the difference as the cargo volume variation value; sort the cargo volume variation values in descending order to obtain the regional investigation priority sequence.

5. The abnormal monitoring system of a belt conveyor based on voiceprint recognition according to claim 1, characterized in that, The analysis of the noise characteristic data of each monitoring area in turn based on the regional investigation priority sequence includes: Extract the regional investigation priority sequence; analyze the noise characteristic data of each monitoring area in turn according to the regional investigation priority sequence to obtain the target voiceprint characteristics of the corresponding monitoring area.

6. The abnormal monitoring system of a belt conveyor based on voiceprint recognition according to claim 1, characterized in that, The input of the target voiceprint characteristics of each monitoring area into the fault voiceprint characteristic database includes: Extract the target voiceprint characteristics of each monitoring area, input the target voiceprint characteristics into the fault voiceprint characteristic database for matching to obtain a matching result; determine whether the target voiceprint characteristics are successfully matched; if so, mark the matching result as a fault label; if not, mark the fault label as no fault.

7. The abnormal monitoring system of a belt conveyor based on voiceprint recognition according to claim 1, characterized in that, The fault voiceprint characteristic database is constructed by the following method: The belt conveyor is simulated and run through a digital twin model to obtain several groups of simulated fault characteristics and corresponding simulated sound data; the simulated sound data is analyzed based on a voiceprint recognition algorithm to obtain fault voiceprint characteristics; The mapping relationship between several groups of simulated fault characteristics and fault voiceprint characteristics is saved to the fault voiceprint characteristic database.

8. An abnormal monitoring system for a belt conveyor based on voiceprint recognition according to claim 1, characterized in that, The calculation of the equipment anomaly score of the belt conveyor based on the noise characteristic data includes: Extracting the noise characteristic data of each monitoring area; wherein, the noise characteristic data includes a decibel characteristic value and a frequency characteristic value; Calculate the equipment anomaly score SYP of the belt conveyor through the formula where FBi is the decibel eigenvalue of the monitoring area i, and PLi is the frequency eigenvalue of the monitoring area i; both a and b are proportionality coefficients greater than 0.

9. The abnormal monitoring system of a belt conveyor based on voiceprint recognition according to claim 1, characterized in that, The fault warning of the belt conveyor based on the equipment anomaly score and the fault label includes: Extracting the equipment anomaly score and the fault label; determining whether the equipment anomaly score is greater than a preset anomaly score threshold; if so, integrating the equipment anomaly score and the fault label into a fault warning message and sending the fault warning message to the intelligent terminal of the equipment maintenance personnel; if not, continuing to monitor the belt conveyor.

10. A method for abnormal monitoring of a belt conveyor based on voiceprint recognition, which operates based on the abnormal monitoring system of a belt conveyor based on voiceprint recognition described in any one of claims 1-9, characterized in that, Including: S1: Obtaining the equipment drawing information of the belt conveyor, as well as the noise characteristic data and environmental data during the operation of the belt conveyor; S2: Constructing a data twin model of the belt conveyor based on the equipment drawing information, noise characteristic data and environmental data; S3: Dividing the belt conveyor into several monitoring areas based on the data twin model and obtaining the cargo volume of each monitoring area; S4: Determining the regional investigation priority sequence based on the cargo volume of several monitoring areas; S5: Analyzing the noise characteristic data of each monitoring area in turn based on the regional investigation priority sequence to obtain the target voiceprint characteristics of the corresponding monitoring area; S6: Inputting the target voiceprint characteristics of each monitoring area into the fault voiceprint characteristic database to obtain the corresponding fault label; S7: Calculating the equipment anomaly score of the belt conveyor based on the noise characteristic data; S8: Conducting fault warning on the belt conveyor based on the equipment anomaly score and the fault label.

Images