Belt conveyor fault diagnosis method, system, terminal and storage medium

Abstract

The application relates to the technical field of data processing, and specifically provides a belt conveyor fault diagnosis method, a system, a terminal and a storage medium, which comprises the following steps: collecting vibration data, temperature data and sound data of a belt conveyor, and intercepting vibration data sequences, temperature data sequences and sound data sequences; performing normalization processing on the vibration data sequences and the temperature data sequences to obtain vibration feature vectors and temperature feature vectors; extracting a first sound feature vector from the sound data sequences by using an MFCC feature extraction technology, and extracting a second sound feature vector from the sound data sequences by using a deep learning model; predicting probabilities corresponding to fault types based on the vibration feature vectors, the temperature feature vectors, the first sound feature vector and the second sound feature vector respectively; and performing decision-level fusion on the predicted probabilities corresponding to various fault types by using a D-S evidence theory to obtain a diagnosis result. The fault type diagnosis is realized, and the timeliness of fault detection is further improved.

Description

Technical Field

[0001] This invention belongs to the field of data processing technology, and specifically relates to a fault diagnosis method, system, terminal and storage medium for belt conveyors. Background Technology

[0002] Early fault diagnosis of belt conveyors often relied on manual methods, depending on the workers' physical senses to monitor the mechanical equipment. For example, inspectors would diagnose the fault and provide solutions based on past experience or by discussing with other maintenance personnel, based on abnormal temperature, abnormal sound, and smoke during machine operation.

[0003] With the development of fault diagnosis technology, relying solely on manual inspection can no longer meet the requirements of fault diagnosis. Condition monitoring is gradually developing towards relying on sensors to measure the operating status information of mechanical equipment. For example, using sound sensors, smoke sensors, temperature and humidity sensors, infrared thermal imagers, etc., to obtain and record parameters such as the speed, acceleration, and temperature of the conveyor, compare them with the inherent parameters, and observe the trend of parameter changes to determine whether a fault has occurred or whether there are potential faults.

[0004] While this detection method automates fault diagnosis to some extent, it can only detect anomalies, not specific fault types. Furthermore, it can only detect severe fault symptoms and cannot identify anomalies in the early stages of a fault, exhibiting a delay in detection. Summary of the Invention

[0005] In view of the above-mentioned shortcomings of the prior art, the present invention provides a method, system, terminal and storage medium for diagnosing faults in belt conveyors to solve the above-mentioned technical problems.

[0006] In a first aspect, the present invention provides a method for diagnosing faults in a belt conveyor, comprising:

[0007] Vibration data, temperature data, and sound data of the belt conveyor are collected, and vibration data sequences, temperature data sequences, and sound data sequences are extracted using time windows of the same length.

[0008] The vibration data sequence and temperature data sequence are normalized to obtain vibration feature vectors and temperature feature vectors;

[0009] The first sound feature vector is extracted from the sound data sequence using MFCC feature extraction technology, and the second sound feature vector is extracted from the sound data sequence using a deep learning model.

[0010] The probability of the fault type is predicted based on the vibration feature vector, temperature feature vector, first sound feature vector, and second sound feature vector, respectively.

[0011] The probabilities of each predicted fault type are fused at the decision level using the DS evidence theory to obtain the diagnostic results.

[0012] In one optional implementation, vibration data, temperature data, and sound data of the belt conveyor are collected, and the vibration data sequence, temperature data sequence, and sound data sequence are extracted using time windows of the same length, including:

[0013] Multiple detection points are evenly set on the buffer bed of the belt conveyor, and each detection point is equipped with a vibration sensor, a temperature sensor and a sound sensor.

[0014] Generate numbers for the detection points and store the correspondence between the detection point numbers and the vibration sensors, temperature sensors, and sound sensors;

[0015] Based on the aforementioned correspondence, the corresponding detection point numbers are labeled for the vibration data, temperature data, and sound data.

[0016] In one optional implementation, the probability of a fault type is predicted based on the vibration feature vector, temperature feature vector, first sound feature vector, and second sound feature vector, respectively, including:

[0017] Temperature feature vectors are identified using support vector machines and sigmoid-fitting, and the identification results are used as the first evidence.

[0018] Vibration feature vectors and temperature feature vectors are identified using support vector machines and sigmoid-fitting, and the identification results are used as a second piece of evidence.

[0019] Support vector machine and sigmoid-fitting are used to identify temperature feature vector, first sound feature vector and second sound feature vector, and the identification results are used as third evidence.

[0020] In an optional implementation, decision-level fusion is performed on the probabilities corresponding to each predicted fault type using DS evidence theory to obtain diagnostic results, including:

[0021] The various fault types of the belt conveyor are set as hypothetical subsets, including head motor or reducer failure, drum overheating, and idler damage.

[0022] Use the probability corresponding to the predicted fault type as evidence.

[0023] Using the DS evidence theory synthesis rules, calculate the fusion reliability of each proposition under the combination of multiple evidence bodies;

[0024] The composite confidence scores of the fused evidence are aggregated onto a single confidence score, and the fault diagnosis results are obtained through decision rules.

[0025] In an optional implementation, the method further includes:

[0026] The actual operating speed of the belt is collected using a laser sensor;

[0027] The actual running speed of the belt is compared with the set theoretical speed. If the difference between the two exceeds the set error threshold, a slippage alarm is generated.

[0028] In a second aspect, the present invention provides a fault diagnosis system for a belt conveyor, comprising:

[0029] The data acquisition module is used to collect vibration data, temperature data, and sound data of the belt conveyor, and to extract vibration data sequences, temperature data sequences, and sound data sequences using time windows of the same length.

[0030] The first extraction module is used to normalize the vibration data sequence and the temperature data sequence to obtain vibration feature vector and temperature feature vector.

[0031] The second extraction module is used to extract a first sound feature vector from the sound data sequence using MFCC feature extraction technology and to extract a second sound feature vector from the sound data sequence using a deep learning model.

[0032] The model processing module is used to predict the probability of the fault type based on the vibration feature vector, temperature feature vector, first sound feature vector, and second sound feature vector, respectively.

[0033] The decision fusion module is used to perform decision-level fusion of the probabilities corresponding to each predicted fault type using DS evidence theory to obtain diagnostic results.

[0034] In an optional implementation, the data acquisition module includes:

[0035] The detection deployment unit is used to uniformly set multiple detection points on the buffer bed of the belt conveyor, and each detection point is equipped with a vibration sensor, a temperature sensor and a sound sensor.

[0036] The relationship establishment unit is used to generate numbers for the detection points and store the correspondence between the detection point numbers and the vibration sensor, temperature sensor and sound sensor;

[0037] The data labeling unit is used to label the corresponding detection point numbers for the corresponding vibration data, temperature data, and sound data based on the correspondence.

[0038] In an optional implementation, the model processing module includes:

[0039] The first processing unit is used to identify the temperature feature vector using support vector machine and sigmoid-fitting, and to use the identification result as the first evidence.

[0040] The second processing unit is used to identify vibration feature vectors and temperature feature vectors using support vector machines and sigmoid-fitting, and uses the identification results as the second evidence body.

[0041] The third processing unit is used to identify the temperature feature vector, the first sound feature vector, and the second sound feature vector using support vector machine and sigmoid-fitting, and uses the identification result as the third piece of evidence.

[0042] Thirdly, a terminal is provided, including:

[0043] Processor, memory, among which,

[0044] This memory is used to store computer programs.

[0045] The processor is used to retrieve and run the computer program from memory, causing the terminal to perform the terminal method described above.

[0046] Fourthly, a computer storage medium is provided, wherein instructions are stored therein, which, when executed on a computer, cause the computer to perform the methods described in the above aspects.

[0047] The beneficial effects of the present invention are that the belt conveyor fault diagnosis method, system, terminal and storage medium provided by the present invention realize fault type diagnosis based on multiple influencing factors for multi-source heterogeneous information of belt conveyors, and further improve the timeliness of fault detection.

[0048] Furthermore, the design principle of this invention is reliable, the structure is simple, and it has a very wide range of application prospects. Attached Figure Description

[0049] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0050] Figure 1 This is a schematic flowchart of a method according to an embodiment of the present invention.

[0051] Figure 2 This is another illustrative flowchart of a method according to an embodiment of the present invention.

[0052] Figure 3 This is a schematic block diagram of a system according to an embodiment of the present invention.

[0053] Figure 4 This is a schematic diagram of the structure of a terminal provided in an embodiment of the present invention. Detailed Implementation

[0054] To enable those skilled in the art to better understand the technical solutions of this invention, the technical solutions of the embodiments of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this invention, and not all embodiments. Based on the embodiments of this invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of this invention.

[0055] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. The terminology used herein in the description of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention.

[0056] The belt conveyor fault diagnosis method provided in this embodiment of the invention is executed by a computer device, and correspondingly, the belt conveyor fault diagnosis system runs in the computer device.

[0057] Figure 1 This is a schematic flowchart illustrating a method according to an embodiment of the present invention. Wherein, Figure 1 The implementing entity can be a belt conveyor fault diagnosis system. Depending on different requirements, the order of the steps in this flowchart can be changed, and some steps can be omitted.

[0058] like Figure 1 As shown, the method includes:

[0059] Step 110: Collect vibration data, temperature data, and sound data of the belt conveyor, and extract the vibration data sequence, temperature data sequence, and sound data sequence using time windows of the same length;

[0060] Step 120: Normalize the vibration data sequence and temperature data sequence to obtain vibration feature vector and temperature feature vector;

[0061] Step 130: Extract the first sound feature vector from the sound data sequence using MFCC feature extraction technology, and extract the second sound feature vector from the sound data sequence using a deep learning model;

[0062] Step 140: Predict the probability of the fault type based on the vibration feature vector, temperature feature vector, first sound feature vector, and second sound feature vector, respectively.

[0063] Step 150: Decision-level fusion of the probabilities corresponding to each predicted fault type is performed using DS evidence theory to obtain the diagnostic results.

[0064] To facilitate understanding of the present invention, the following description further illustrates the belt conveyor fault diagnosis method provided by the present invention, based on the principle of the belt conveyor fault diagnosis method of the present invention and in conjunction with the fault diagnosis process of the belt conveyor in the embodiments.

[0065] For details, please refer to Figure 2 Methods for diagnosing belt conveyor faults include:

[0066] S1. Collect vibration data, temperature data, and sound data of the belt conveyor, and extract the vibration data sequence, temperature data sequence, and sound data sequence using a time window of the same length.

[0067] Multiple detection points are evenly set on the buffer bed of the belt conveyor, and each detection point is equipped with a vibration sensor, a temperature sensor, and a sound sensor. A number is generated for each detection point, and the correspondence between the detection point number and the vibration sensor, temperature sensor, and sound sensor is stored. Based on the correspondence, the corresponding vibration data, temperature data, and sound data are labeled with the corresponding detection point number.

[0068] In subsequent data processing, data from different detection points are processed in batches, and the fault location can be achieved based on the corresponding detection points after obtaining the processing results.

[0069] To denoise audio data, a wavelet denoising algorithm based on Bayesian threshold inference is proposed. This algorithm combines Bayesian theory with wavelet transform to calculate the optimal threshold point for the wavelet transform, accurately separating the wavelet transform coefficients of the signal and noise, thus improving the signal-to-noise ratio. To address the problems of mode aliasing and endpoint effects, an EEMD algorithm is proposed to decompose the signal and extract modal components, ensuring high accuracy in both the time and frequency domains for abrupt signal changes.

[0070] Noise reduction processing includes the following steps:

[0071] (1) Select the wavelet basis db6 with attenuation;

[0072] (2) Perform 3-level wavelet decomposition using the wavelet basis db6;

[0073] (3) Select a fixed threshold λ, and set the wavelet coefficients after wavelet decomposition as w, and use the formula

[0074] The threshold function is improved, and then the wavelet coefficients processed by the threshold function are used to reconstruct the noise-reduced sound signal of the belt conveyor, where j and k are integers and a > 0.

[0075] S2. Normalize the vibration data sequence and temperature data sequence to obtain the vibration feature vector and temperature feature vector.

[0076] S3. Use MFCC feature extraction technology to extract the first sound feature vector from the sound data sequence, and use a deep learning model to extract the second sound feature vector from the sound data sequence.

[0077] The MFCC feature extraction method includes: pre-emphasis, framing, and windowing of the audio data sequence (continuous audio); after pre-processing, Fourier transform, filtering, logarithmic operation, discrete cosine transform, and dynamic feature extraction are performed in sequence to obtain a 39-dimensional MFCC feature vector, which is the first audio feature vector.

[0078] A second sound feature vector is extracted from a sound data sequence using a convolutional neural network (CNN).

[0079] S4. Predict the probability of the fault type based on the vibration feature vector, temperature feature vector, first sound feature vector, and second sound feature vector, respectively.

[0080] The temperature feature vector is identified using support vector machine and sigmoid-fitting, and the identification result is used as the first piece of evidence. The vibration feature vector and temperature feature vector are identified using support vector machine and sigmoid-fitting, and the identification result is used as the second piece of evidence. The temperature feature vector, the first sound feature vector and the second sound feature vector are identified using support vector machine and sigmoid-fitting, and the identification result is used as the third piece of evidence.

[0081] Among them, the weights of the recognition models (support vector machine and sigmoid-fitting) corresponding to the three types of evidence are different, and the training sets used during training are also different.

[0082] S5. Decision-level fusion of the probabilities corresponding to each predicted fault type is performed using DS evidence theory to obtain the diagnostic results.

[0083] Multiple fault types of the belt conveyor are set as hypothesis subsets, including head motor or reducer failure, drum overheating, and idler damage. The probabilities corresponding to the predicted fault types are used as evidence bodies. The DS evidence theory synthesis rules are used to calculate the fusion confidence of each proposition under the joint evidence bodies. The composite confidence of the fused evidence bodies is assigned and aggregated to a single confidence, and the fault diagnosis result is obtained through decision rules.

[0084] When synthesizing evidence using the DS evidence theory, the degree of conflict in the evidence set is analyzed. The degree of conflict between the evidence is obtained by calculating the distance between the evidence pieces. The evidence pieces with the highest degree of conflict are then merged last, thereby avoiding the problem of inappropriate allocation of conflict during the fusion process.

[0085] Based on the DS evidence theory, decision-level fusion is performed. Given an identified global framework U, then for each hypothesis A: Where K is the normalization constant, and Let these be Hypothesis 1 and Hypothesis 2, which are the corresponding two posterior probabilities. The formula is transformed into: Substituting the posterior probability and Later obtained .

[0086] In some embodiments, the belt conveyor fault diagnosis system may include multiple functional modules composed of computer program segments. The computer programs for each program segment in the belt conveyor fault diagnosis system may be stored in the memory of a computer device and executed by at least one processor to perform (see details). Figure 1 (Description) Functions for fault diagnosis of belt conveyors.

[0087] In this embodiment, the belt conveyor fault diagnosis system can be divided into multiple functional modules according to its functions, such as... Figure 3 As shown. The functional modules of system 300 may include: a data acquisition module 310, a first extraction module 320, a second extraction module 330, a model processing module 340, and a decision fusion module 350. The module referred to in this invention is a series of computer program segments that can be executed by at least one processor and perform a fixed function, and are stored in memory. In this embodiment, the functions of each module will be described in detail in subsequent embodiments.

[0088] The data acquisition module is used to collect vibration data, temperature data, and sound data of the belt conveyor, and to extract vibration data sequences, temperature data sequences, and sound data sequences using time windows of the same length.

[0089] The first extraction module is used to normalize the vibration data sequence and the temperature data sequence to obtain vibration feature vector and temperature feature vector.

[0090] The second extraction module is used to extract a first sound feature vector from the sound data sequence using MFCC feature extraction technology and to extract a second sound feature vector from the sound data sequence using a deep learning model.

[0091] The model processing module is used to predict the probability of the fault type based on the vibration feature vector, temperature feature vector, first sound feature vector, and second sound feature vector, respectively.

[0092] The decision fusion module is used to perform decision-level fusion of the probabilities corresponding to each predicted fault type using DS evidence theory to obtain diagnostic results.

[0093] Optionally, as an embodiment of the present invention, the data acquisition module includes:

[0094] The detection deployment unit is used to uniformly set multiple detection points on the buffer bed of the belt conveyor, and each detection point is equipped with a vibration sensor, a temperature sensor and a sound sensor.

[0095] The relationship establishment unit is used to generate numbers for the detection points and store the correspondence between the detection point numbers and the vibration sensor, temperature sensor and sound sensor;

[0096] The data labeling unit is used to label the corresponding detection point numbers for the corresponding vibration data, temperature data, and sound data based on the correspondence.

[0097] Optionally, as an embodiment of the present invention, the model processing module includes:

[0098] The first processing unit is used to identify the temperature feature vector using support vector machine and sigmoid-fitting, and to use the identification result as the first evidence.

[0099] The second processing unit is used to identify vibration feature vectors and temperature feature vectors using support vector machines and sigmoid-fitting, and uses the identification results as the second evidence body.

[0100] The third processing unit is used to identify the temperature feature vector, the first sound feature vector, and the second sound feature vector using support vector machine and sigmoid-fitting, and uses the identification result as the third piece of evidence.

[0101] Figure 4 This is a schematic diagram of the structure of a terminal 400 provided in an embodiment of the present invention. The terminal 400 can be used to execute the belt conveyor fault diagnosis method provided in the embodiment of the present invention.

[0102] The terminal 400 may include a processor 410, a memory 420, and a communication unit 430. These components communicate via one or more buses. Those skilled in the art will understand that the server structure shown in the figure does not constitute a limitation of the present invention. It may be a bus topology or a star topology, and may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0103] The memory 420 can be used to store the execution instructions of the processor 410. The memory 420 can be implemented by any type of volatile or non-volatile storage terminal or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. When the execution instructions in the memory 420 are executed by the processor 410, the terminal 400 is able to perform some or all of the steps in the above method embodiments.

[0104] The processor 410 serves as the control center of the storage terminal, connecting various parts of the electronic terminal via various interfaces and lines. It executes software programs and / or modules stored in the memory 420, and calls data stored in the memory to perform various functions of the electronic terminal and / or process data. The processor can be composed of integrated circuits (ICs), such as a single packaged IC or multiple packaged ICs with the same or different functions connected together. For example, the processor 410 may consist only of a central processing unit (CPU). In this embodiment of the invention, the CPU may have a single processing core or include multiple processing cores.

[0105] The communication unit 430 is used to establish a communication channel, enabling the storage terminal to communicate with other terminals. It can receive user data sent by other terminals or send user data to other terminals.

[0106] The present invention also provides a computer storage medium, wherein the computer storage medium may store a program, which, when executed, may include some or all of the steps provided in the embodiments of the present invention. The storage medium may be a magnetic disk, an optical disk, read-only memory (ROM), or random access memory (RAM), etc.

[0107] Therefore, this invention addresses the multi-source heterogeneous information of belt conveyors by establishing a belt conveyor data platform. This platform provides a large volume of data analysis information that is intuitive, accurate, and highly integrated. It incorporates important data such as online monitoring, intelligent early warning, predictive maintenance guidance, and information spectrum, enabling real-time online intelligent monitoring and fault classification early warning of belt conveyors. This optimizes maintenance time, extends equipment lifespan, improves work efficiency and quality, and enhances overall benefits. It also strengthens the information management level of belt conveyors. The technical effects achievable in this embodiment can be found in the description above and will not be repeated here.

[0108] Those skilled in the art will clearly understand that the techniques in the embodiments of the present invention can be implemented using software plus necessary general-purpose hardware platforms. Based on this understanding, the technical solutions in the embodiments of the present invention, or the parts that contribute to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium such as a USB flash drive, mobile hard drive, read-only memory (ROM), random access memory (RAM), magnetic disk, or optical disk, or other media capable of storing program code. It includes several instructions to cause a computer terminal (which may be a personal computer, server, or a second terminal, network terminal, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention.

[0109] The same or similar parts between the various embodiments in this specification can be referred to mutually. In particular, the terminal embodiments are basically similar to the method embodiments, so the description is relatively simple, and the relevant parts can be referred to the description in the method embodiments.

[0110] In the embodiments provided by this invention, it should be understood that the disclosed systems and methods can be implemented in other ways. For example, the system embodiments described above are merely illustrative. For instance, the division of modules is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple modules or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between systems or modules may be electrical, mechanical, or other forms.

[0111] The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical modules; that is, they may be located in one place or distributed across multiple network modules. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0112] In addition, the functional modules in the various embodiments of the present invention can be integrated into one processing module, or each module can exist physically separately, or two or more modules can be integrated into one module.

[0113] Although the present invention has been described in detail with reference to the accompanying drawings and preferred embodiments, the present invention is not limited thereto. Various equivalent modifications or substitutions can be made to the embodiments of the present invention by those skilled in the art without departing from the spirit and essence of the invention, and such modifications or substitutions should all be within the scope of the present invention. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should also be covered within the protection scope of the present invention.

Claims

1. A fault diagnosis method for a belt conveyor, characterized in that, include: Vibration data, temperature data, and sound data of the belt conveyor are collected, and vibration data sequences, temperature data sequences, and sound data sequences are extracted using time windows of the same length. The vibration data sequence and temperature data sequence are normalized to obtain vibration feature vectors and temperature feature vectors; The first sound feature vector is extracted from the sound data sequence using MFCC feature extraction technology, and the second sound feature vector is extracted from the sound data sequence using a deep learning model. The probability of the fault type is predicted based on the vibration feature vector, temperature feature vector, first sound feature vector, and second sound feature vector, respectively. The probabilities of each predicted fault type are fused at the decision level using the DS evidence theory to obtain the diagnostic results. Vibration data, temperature data, and sound data of the belt conveyor are collected, and vibration data sequences, temperature data sequences, and sound data sequences are extracted using time windows of the same length, including: Multiple detection points are evenly set on the buffer bed of the belt conveyor, and each detection point is equipped with a vibration sensor, a temperature sensor and a sound sensor. Generate numbers for the detection points and store the correspondence between the detection point numbers and the vibration sensors, temperature sensors, and sound sensors; Based on the correspondence, the corresponding detection point numbers are labeled for the vibration data, temperature data, and sound data. The probability of the fault type is predicted based on the vibration feature vector, temperature feature vector, first sound feature vector, and second sound feature vector, respectively, including: Temperature feature vectors are identified using support vector machines and sigmoid-fitting, and the identification results are used as the first evidence. Vibration feature vectors and temperature feature vectors are identified using support vector machines and sigmoid-fitting, and the identification results are used as a second piece of evidence. Support vector machine and sigmoid-fitting are used to identify temperature feature vector, first sound feature vector and second sound feature vector, and the identification results are used as third evidence.

2. The method according to claim 1, characterized in that, The probabilities of each predicted fault type are fused at the decision level using the DS evidence theory to obtain diagnostic results, including: The various fault types of the belt conveyor are set as hypothetical subsets, including head motor or reducer failure, drum overheating, and idler damage. Use the probability corresponding to the predicted fault type as evidence. Using the DS evidence theory synthesis rules, calculate the fusion reliability of each proposition under the combination of multiple evidence bodies; The composite confidence scores of the fused evidence are aggregated onto a single confidence score, and the fault diagnosis results are obtained through decision rules.

3. The method according to claim 1, characterized in that, The method further includes: The actual operating speed of the belt is collected using a laser sensor; The actual running speed of the belt is compared with the set theoretical speed. If the difference between the two exceeds the set error threshold, a slippage alarm is generated.

4. A fault diagnosis system for a belt conveyor, characterized in that, include: The data acquisition module is used to collect vibration data, temperature data, and sound data of the belt conveyor, and to extract vibration data sequences, temperature data sequences, and sound data sequences using time windows of the same length. The first extraction module is used to normalize the vibration data sequence and the temperature data sequence to obtain vibration feature vector and temperature feature vector. The second extraction module is used to extract a first sound feature vector from the sound data sequence using MFCC feature extraction technology and to extract a second sound feature vector from the sound data sequence using a deep learning model. The model processing module is used to predict the probability of the fault type based on the vibration feature vector, temperature feature vector, first sound feature vector, and second sound feature vector, respectively. The decision fusion module is used to perform decision-level fusion of the probabilities corresponding to each predicted fault type using DS evidence theory to obtain diagnostic results. The data acquisition module includes: The detection deployment unit is used to uniformly set multiple detection points on the buffer bed of the belt conveyor, and each detection point is equipped with a vibration sensor, a temperature sensor and a sound sensor. The relationship establishment unit is used to generate numbers for the detection points and store the correspondence between the detection point numbers and the vibration sensor, temperature sensor and sound sensor; The data tagging unit is used to tag the corresponding detection point number for the corresponding vibration data, temperature data and sound data based on the correspondence relationship; The model processing module includes: The first processing unit is used to identify the temperature feature vector using support vector machine and sigmoid-fitting, and to use the identification result as the first evidence. The second processing unit is used to identify vibration feature vectors and temperature feature vectors using support vector machines and sigmoid-fitting, and uses the identification results as the second evidence body. The third processing unit is used to identify the temperature feature vector, the first sound feature vector, and the second sound feature vector using support vector machine and sigmoid-fitting, and uses the identification result as the third piece of evidence.

5. A terminal, characterized in that, include: Memory, used to store fault diagnosis programs for belt conveyors; A processor is configured to implement the steps of the belt conveyor fault diagnosis method as described in any one of claims 1-3 when executing the belt conveyor fault diagnosis program.

6. A computer-readable storage medium storing a computer program, characterized in that, The readable storage medium stores a belt conveyor fault diagnosis program, which, when executed by a processor, implements the steps of the belt conveyor fault diagnosis method as described in any one of claims 1-3.

Images