Fault prediction and health management system for belt conveyor

Abstract

The invention discloses a fault prediction and health management system for a belt conveyor, relates to the technical field of intelligent monitoring and management of mechanical equipment, and aims to solve the problems of fault recognition lagging and high misjudgment rate caused by insufficient consideration of real-time performance and high reliability required by industrial equipment. Motor current fluctuation, roller temperature change rate, belt tension distribution and vibration spectrum data are acquired in real time through a data acquisition unit; the fault feature extraction unit extracts abnormal features based on wavelet transform, and calculates an operation stability index through a principal component analysis method; the risk assessment unit combines the abnormal features, the abrasion loss and the stability index, and adopts fuzzy logic reasoning to judge the fault risk level; and the intelligent regulation and control unit dynamically regulates and controls the operation state or gives an alarm according to grading processing, so that accurate early warning and intelligent response of early faults of the equipment are realized.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent monitoring and management of mechanical equipment. More specifically, the present invention relates to a fault prediction and health management system for a belt conveyor. Background Art

[0002] As a core equipment in industrial production, belt conveyors are widely used in the mining, manufacturing, and logistics industries. The reliability and efficiency of their operation directly affect the continuity and economic benefits of the production line. However, traditional maintenance methods mainly rely on regular inspections and manual detections, which have limitations in real-time monitoring of equipment status and prediction of potential faults, easily leading to unexpected shutdowns, production interruptions, and high maintenance costs. With the development of industrial automation and intelligence, health management systems based on sensors and data analysis have gradually become a research hotspot, but there are still some deficiencies.

[0003] The existing technologies have the following deficiencies:

[0004] Currently, user health data is collected through wearable monitoring terminals and uploaded to a cloud server for storage and analysis, and finally health analysis results are provided to users. Although this system can achieve real-time monitoring and early warning of the user's health status, its early warning mechanism is relatively general, and its ability to provide accurate diagnosis and prediction for specific fault modes of belt conveyors is limited. Especially when facing the complex operation data of belt conveyors, it lacks efficient fault feature extraction and pattern recognition capabilities, and insufficient consideration of the real-time and high reliability required by industrial equipment, resulting in lagging fault identification, high misjudgment rate, and reduced continuous operation and production efficiency of belt conveyors. Therefore, a fault prediction and health management system for belt conveyors is proposed. Summary of the Invention

[0005] In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides a fault prediction and health management system for a belt conveyor, which performs hierarchical early warning of potential faults by collecting multi-dimensional dynamic parameters during the operation of the conveyor and combining with a real-time analysis model, and at the same time uses an intelligent regulation module to optimize and adjust the operation state of the equipment, so as to solve the problems that the traditional maintenance method in the background art is difficult to monitor in real time and accurately predict.

[0006] To achieve the above object, the present invention provides the following technical solutions:

[0007] A fault prediction and health management system for a belt conveyor, comprising a data acquisition unit, a fault feature extraction unit, a risk assessment unit, and an intelligent regulation unit;

[0008] The data acquisition unit monitors the key operating parameters of the belt conveyor in real time, obtains the current fluctuation value of the conveyor motor, the temperature change rate of the driving drum, and the belt tension distribution, transmits these parameters to the fault feature extraction unit, and collects the vibration spectrum data during the operation of the conveyor and transmits it to the risk assessment unit;

[0009] The fault feature extraction unit extracts the abnormal features of the equipment operating state through the wavelet transform algorithm, calculates the equipment operation stability index by using the principal component analysis method in combination with the belt tension distribution, and transmits the abnormal features and the stability index to the risk assessment unit;

[0010] The risk assessment unit is used to judge whether there is abnormal vibration in the conveyor, detect the wear degree of the conveyor bearing to obtain the wear amount, and comprehensively analyze the fault risk level through fuzzy logic reasoning based on the abnormal vibration phenomenon, the wear amount, and the equipment operation stability index, and transmit the fault risk level to the intelligent control unit;

[0011] The intelligent control unit is used to classify the fault risk level, and adjust the operating state of the belt conveyor or issue an alarm prompt according to the classification result.

[0012] In a preferred embodiment, the data acquisition unit uses an infrared thermometer to detect the initial temperature of the surface of the driving drum before the conveyor starts, and records the initial temperature as the reference temperature value;

[0013] During the operation of the conveyor, the data acquisition unit selects a fixed time period as the sampling period, receives the current fluctuation value collected by the current sensor installed on the conveyor motor. At the same time, within the sampling period, multiple detection sub-periods with the same time interval are divided, and the temperature sensor is used to monitor the surface temperature of the driving drum in real time.

[0014] In a preferred embodiment, the specific steps for the data acquisition unit to monitor the surface temperature of the driving drum are as follows:

[0015] Within the sampling period, multiple detection sub-periods with the same time interval are divided, and the surface temperature of the driving drum is recorded once at the time points at both ends of each detection sub-period;

[0016] The temperature change amount of the corresponding detection sub-period is obtained by subtracting the temperature value recorded at the latter time point of the detection sub-period from the temperature value recorded at the former time point of the detection sub-period;

[0017] The temperature change amounts of each detection sub-period within the sampling period are compared, and the maximum value is selected as the temperature change rate within the sampling period;

[0018] During the operation of the conveyor, the data acquisition unit uses a tension sensor to detect the tension at different positions of the conveyor belt, sorts the detected tension values according to the spatial distribution and plots a tension distribution curve, and uses the slope of the curve as a quantitative index of the belt tension distribution.

[0019] In a preferred embodiment, after receiving the current fluctuation value of the conveyor motor and the temperature change rate of the driving roller, the fault feature extraction unit first normalizes the two types of data using the Z-score normalization method;

[0020] Then, the normalized results of the two types of data are decomposed by wavelet basis functions to extract the abnormal features of the equipment operating state;

[0021] After receiving the quantitative index of the belt tension distribution, the fault feature extraction unit calculates the equipment operation stability index using the principal component analysis method. The specific steps are as follows:

[0022] Form a multi-dimensional data matrix with the quantitative index of the belt tension distribution and other operating parameters, calculate the covariance matrix of the data matrix and solve its eigenvalues and eigenvectors;

[0023] Select the eigenvectors corresponding to the top k largest eigenvalues to construct the principal component space, project the original data into the principal component space and calculate the Euclidean distance of the projection points, and use the Euclidean distance as the equipment operation stability index.

[0024] In a preferred embodiment, the risk assessment unit preprocesses the vibration spectrum data as follows:

[0025] Access the historical database to obtain the vibration spectrum reference value during the normal operation of the conveyor, and obtain the current vibration spectrum data during the operation of the conveyor;

[0026] Use the root mean square error between the current vibration spectrum data and the reference value as the vibration anomaly coefficient, and normalize the vibration spectrum data using the vibration anomaly coefficient;

[0027] After receiving the wear amount of the conveyor bearing, the risk assessment unit uses an ultrasonic flaw detector to detect the crack depth on the bearing surface, and performs a weighted sum of the crack depth and the wear amount to obtain a comprehensive wear index.

[0028] In a preferred embodiment, the risk assessment unit defines the abnormal vibration phenomenon, the comprehensive wear index, and the equipment operation stability index as input variables, and defines the fault risk level as the output variable;

[0029] Formulate a set of fuzzy rules to describe the relationship between different input variables and the output variable, perform fuzzy reasoning according to the fuzzy rules, calculate the output result in combination with the membership function, and mark the fault risk level.

[0030] In a preferred embodiment, after receiving the fault risk level, the intelligent control unit performs hierarchical processing, and the specific rules are as follows:

[0031] When the fault risk level is low, adjust the output power of the conveyor motor to reduce energy consumption;

[0032] When the fault risk level is medium, adjust the operating parameters of the conveyor drive system to improve equipment stability;

[0033] When the fault risk level is high, stop the conveyor operation and issue an alarm prompt;

[0034] The intelligent control unit controls the motor speed by adjusting the frequency of the conveyor inverter, and at the same time adjusts the position of the driving roller through the hydraulic device to change the belt tension distribution until the equipment operation state returns to normal;

[0035] The alarm prompt sends visual and auditory signals to the operator through the audible and visual alarm, and uploads the fault information to the remote monitoring platform through the wireless communication module.

[0036] In a preferred embodiment, when the intelligent control unit adjusts the conveyor operation state, it preferentially selects the adjustment strategy according to the change trend of the equipment operation stability index. When the equipment operation stability index continues to decline, it preferentially adjusts the position of the driving roller;

[0037] When the equipment operation stability index tends to be stable but the energy consumption is high, preferentially adjust the motor output power.

[0038] In a preferred embodiment, after the intelligent control unit issues an alarm prompt, it generates a fault report through the remote monitoring platform. The fault report includes the fault occurrence time, fault type, fault risk level, and recommended repair measures.

[0039] In a preferred embodiment, the data acquisition unit is composed of a current sensor, a temperature sensor, and a tension sensor, which are respectively used to collect the current fluctuation value of the conveyor motor, the temperature change rate on the surface of the driving roller, and the belt tension distribution;

[0040] The fault feature extraction unit internally integrates a wavelet transform algorithm module and a principal component analysis method module, and is used to extract abnormal features from the input data and calculate the operation stability index;

[0041] The risk assessment unit comprehensively analyzes the input variables through the fuzzy logic inference module and outputs the fault risk level.

[0042] The technical effects and advantages of a fault prediction and health management system for a belt conveyor according to the present invention:

[0043] The present invention constructs a multi-dimensional fault prediction and health management system for a belt conveyor by setting up a data acquisition unit, a fault feature extraction unit, a risk assessment unit, and an intelligent control unit. The data acquisition unit monitors the key operating parameters of the belt conveyor in real time, obtains the operating characteristics of the structure such as the motor current fluctuation value, the temperature change rate of the driving drum, and the belt tension distribution, and collects vibration spectrum data to provide basic data support for subsequent analysis; the fault feature extraction unit uses the wavelet transform algorithm to perform multi-scale decomposition on the operating data, extracts the time-frequency features reflecting potential abnormalities, and at the same time combines the principal component analysis method to reduce the dimension of the belt tension distribution, calculates the equipment operating stability index, and realizes the quantitative expression of the system operating state; the risk assessment unit, on the basis of fusing abnormal vibration features, bearing wear amount, and operating stability index, uses the fuzzy logic reasoning method to judge the fault risk level, improving the diagnostic accuracy and fault tolerance of potential faults; the intelligent control unit performs fault level classification processing based on the evaluation results, and dynamically adjusts the operating state of the belt conveyor or outputs an alarm prompt to ensure early warning and response in the fault germination stage of the system. Brief Description of the Drawings

[0044] Figure 1 It is a structural block diagram of a fault prediction and health management system for a belt conveyor according to the present invention.

[0045] Figure 2 It is a working flow chart of the data acquisition unit in a fault prediction and health management system for a belt conveyor according to the present invention.

[0046] Figure 3 It is a schematic diagram of fuzzy logic reasoning analysis of the risk assessment unit in a fault prediction and health management system for a belt conveyor according to the present invention. Detailed Embodiments

[0047] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0048] The present invention provides a fault prediction and health management system for a belt conveyor, the structure of which is as Figure 1 shown, including a data acquisition unit, a fault feature extraction unit, a risk assessment unit, and an intelligent control unit. Each unit is connected by signals to realize data transmission and processing.

[0049] The data acquisition unit consists of a current sensor, a temperature sensor, and a tension sensor, which are respectively used to collect the current fluctuation value of the conveyor motor, the temperature change rate of the surface of the driving roller, and the belt tension distribution.

[0050] These sensors are connected to the fault feature extraction unit through signal lines, and the collected data is transmitted to this unit for further analysis.

[0051] The fault feature extraction unit internally integrates a wavelet transform algorithm module and a principal component analysis module, which are used to extract abnormal features from the input data and calculate the operation stability index.

[0052] Subsequently, the fault feature extraction unit sends the processed result to the risk assessment unit, and the risk assessment unit comprehensively analyzes the input variables through the fuzzy logic inference module and outputs the fault risk level.

[0053] Finally, the intelligent regulation unit performs corresponding adjustment or warning operations according to the received fault risk level.

[0054] In practical applications, the specific working process of the data acquisition unit is as Figure 2 shown.

[0055] First, before the conveyor starts, an infrared thermometer is used to detect the initial temperature of the surface of the driving roller and record it as the reference temperature value.

[0056] During the operation of the conveyor, the current sensor is installed on the conveyor motor to monitor the current fluctuation value of the motor in real time.

[0057] At the same time, the temperature sensor is arranged on the surface of the driving roller to monitor the temperature of the driving roller according to a fixed sampling period.

[0058] Within each sampling period, the temperature sensor divides the sampling period into multiple detection sub-periods with the same time interval, and records the temperature values of the surface of the driving roller at the two end time points of each detection sub-period respectively.

[0059] Subtract the temperature value recorded at the previous time point from the temperature value recorded at the latter time point to obtain the temperature change amount of the corresponding detection sub-period.

[0060] By comparing the temperature change amounts of all detection sub-periods within the sampling period, the maximum value is selected as the temperature change rate within this sampling period.

[0061] In addition, the tension sensors are arranged at different positions of the conveyor belt to detect the belt tension distribution.

[0062] The tension sensor sorts the detected tension values according to the spatial distribution, plots the tension distribution curve, and uses the slope of the curve as a quantitative index of the belt tension distribution.

[0063] The above-mentioned current fluctuation value, temperature change rate, and quantitative index of the belt tension distribution are transmitted to the fault feature extraction unit through the signal line.

[0064] After receiving the data transmitted by the data acquisition unit, the fault feature extraction unit first performs Z-score standardization on the current fluctuation value of the conveyor motor and the temperature change rate of the driving drum to eliminate the influence of the data dimension.

[0065] The standardized data is input into the wavelet transform algorithm module, and the data is decomposed through the wavelet basis function to extract the abnormal features of the equipment operation state.

[0066] Specifically, the wavelet transform algorithm module calculates the abnormal feature value F by using the scale factor a and the translation factor b for the normalized current fluctuation value and temperature change rate.

[0067] At the same time, the principal component analysis method module receives the multi-dimensional data matrix composed of the quantitative index of the belt tension distribution and other operation parameters (such as motor speed, load weight, etc.), calculates the covariance matrix of the matrix, and solves its eigenvalues and eigenvectors.

[0068] Select the eigenvectors corresponding to the first k largest eigenvalues to construct the principal component space, project the original data into the principal component space, calculate the Euclidean distance of the projection points, and use it as the equipment operation stability index.

[0069] The above-mentioned abnormal feature value and equipment operation stability index are transmitted to the risk assessment unit through the signal line.

[0070] The risk assessment unit preprocesses the received vibration spectrum data, and the process is as follows: access the historical database to obtain the vibration spectrum reference value during the normal operation of the conveyor, and obtain the current vibration spectrum data during the operation of the conveyor.

[0071] Take the root mean square error between the current vibration spectrum data and the reference value as the vibration abnormality coefficient, and use this coefficient to normalize the vibration spectrum data.

[0072] In addition, the risk assessment unit also receives the wear amount data of the conveyor bearings. The ultrasonic flaw detector detects the crack depth on the bearing surface, and performs weighted summation of the crack depth and the wear amount to obtain the comprehensive wear index.

[0073] Subsequently, the risk assessment unit defines the abnormal vibration phenomenon, the comprehensive wear index, and the equipment operation stability index as input variables, and defines the fault risk level as the output variable.

[0074] A set of fuzzy rules is formulated by the fuzzy logic inference module to describe the relationship between different input variables and the output variable.

[0075] For example, when the abnormal vibration phenomenon is significant, the comprehensive wear index is high, and the equipment operation stability index is low, the fault risk level is marked as high.

[0076] The fuzzy logic inference module calculates the output result according to the membership function, marks the fault risk level as low, medium or high, and transmits the result to the intelligent control unit through the signal line.

[0077] After receiving the fault risk level, the intelligent control unit performs corresponding adjustment or alarm operations according to the classification result.

[0078] Specifically, when the fault risk level is low, the intelligent control unit reduces the motor output power by adjusting the frequency of the conveyor inverter, thereby reducing energy consumption. When the fault risk level is medium, the intelligent control unit adjusts the operating parameters of the conveyor drive system;

[0079] For example, the position of the driving drum is changed through a hydraulic device to optimize the belt tension distribution and improve the equipment stability.

[0080] When the fault risk level is high, the intelligent control unit stops the conveyor operation and issues an alarm prompt through an audible and visual alarm.

[0081] The audible and visual alarm sends visual and auditory signals to the operator, and at the same time the intelligent control unit uploads the fault information to the remote monitoring platform through the wireless communication module.

[0082] In addition, when adjusting the conveyor operation state, the intelligent control unit preferentially selects adjustment strategies according to the change trend of the equipment operation stability index.

[0083] For example, when the equipment operation stability index continues to decline, the position of the driving drum is preferentially adjusted; when the equipment operation stability index tends to be stable but the energy consumption is high, the motor output power is preferentially adjusted.

[0084] After issuing the alarm prompt, the intelligent control unit generates a fault report through the remote monitoring platform. The report content includes the fault occurrence time, fault type, fault risk level, and recommended maintenance measures for the reference of maintenance personnel.

[0085] The cooperation relationship between the above-mentioned units is close and clear. The data acquisition unit is responsible for collecting multi-dimensional dynamic parameters from the key parts of the conveyor, and its acquisition accuracy directly affects the accuracy of subsequent analysis.

[0086] The fault feature extraction unit processes the collected data through the wavelet transform algorithm module and the principal component analysis method module to extract the core features that can reflect the operating state of the equipment.

[0087] The risk assessment unit uses the fuzzy logic inference module to comprehensively analyze the input variables and obtain the fault risk level.

[0088] The intelligent regulation unit performs corresponding adjustment or warning operations according to the fault risk level to ensure the safe and stable operation of the conveyor.

[0089] The entire system realizes the efficient transmission of data through signal lines. Each unit has a clear division of labor and works collaboratively to jointly achieve the comprehensive monitoring and intelligent management of the belt conveyor.

[0090] To enable the relevant personnel in the technical field to fully understand and implement the present invention better, the following further supplements the specific implementation principle of the present invention in combination with a specific application scenario.

[0091] In a belt conveyor production line of a mining company, the system is deployed to monitor and manage the operating state of the conveyor.

[0092] The main task of the conveyor is to transport ore from the mining point to the processing workshop, and its operating environment is complex and the load fluctuates frequently.

[0093] The following are the specific operation steps and implementation principles of the system in actual application:

[0094] First, in the data acquisition stage, the operator makes initial settings according to Figure 2 the shown work process.

[0095] Before the conveyor starts, use an infrared thermometer to detect the initial temperature of the surface of the driving roller and record it as the reference temperature value.

[0096] Subsequently, current sensors are installed on the conveyor motor to monitor the current fluctuation value of the motor in real time; temperature sensors are arranged on the surface of the driving roller to monitor the temperature change rate of the driving roller at a fixed sampling period; and tension sensors are distributed at different positions of the belt to detect the belt tension distribution.

[0097] In each sampling period, the temperature sensor divides the sampling period into multiple detection sub-periods and records the temperature values on the surface of the driving roller at the two end time points of each detection sub-period.

[0098] By calculating the temperature difference between the latter time point and the former time point, the temperature change amount of the corresponding detection sub-period is obtained, and the maximum value within the sampling period is selected as the temperature change rate.

[0099] Meanwhile, the tension sensor sorts the detected tension values according to the spatial distribution, plots the tension distribution curve, and uses the curve slope as a quantization index.

[0100] These data are transmitted to the fault feature extraction unit through the signal line.

[0101] Secondly, in the fault feature extraction stage, the fault feature extraction unit processes the received data.

[0102] As Figure 1 shown, the current fluctuation value and the temperature change rate are first processed by Z-score standardization to eliminate the dimensional differences between different parameters.

[0103] The standardized data is input into the wavelet transform algorithm module, and the data is decomposed through wavelet basis functions to extract the abnormal eigenvalue F of the equipment operation state.

[0104] Meanwhile, the principal component analysis module receives the multi-dimensional data matrix composed of the quantization index of the belt tension distribution and other operating parameters (such as motor speed, load weight, etc.), calculates the covariance matrix and solves its eigenvalues and eigenvectors.

[0105] Select the eigenvectors corresponding to the top k largest eigenvalues to construct the principal component space, project the original data into the principal component space, and obtain the equipment operation stability index by calculating the Euclidean distance of the projection points.

[0106] The above abnormal eigenvalue and operation stability index are transmitted to the risk assessment unit through the signal line.

[0107] Then, in the risk assessment stage, the risk assessment unit preprocesses the received vibration spectrum data.

[0108] As Figure 3 shown, the risk assessment unit accesses the historical database to obtain the vibration spectrum reference value during the normal operation of the conveyor, and obtains the current vibration spectrum data during the operation of the conveyor.

[0109] By calculating the root mean square error between the current vibration spectrum data and the reference value, it is used as the vibration anomaly coefficient, and the vibration spectrum data is normalized using this coefficient.

[0110] In addition, the ultrasonic flaw detector detects the crack depth of the conveyor bearing, and sums the crack depth and the wear amount with weights to obtain a comprehensive wear index.

[0111] Subsequently, the risk assessment unit defines the abnormal vibration phenomenon, the comprehensive wear index, and the equipment operation stability index as input variables, and formulates a set of fuzzy rules through the fuzzy logic inference module to describe the relationship between different input variables and the output variable.

[0112] For example, when the abnormal vibration phenomenon is significant, the comprehensive wear index is high, and the equipment operation stability index is low, the fault risk level is marked as high.

[0113] The fuzzy logic inference module calculates the output result according to the membership function, marks the fault risk level as low, medium, or high, and transmits the result to the intelligent regulation unit through the signal line.

[0114] Finally, in the intelligent regulation stage, the intelligent regulation unit performs corresponding adjustment or warning operations according to the received fault risk level.

[0115] When the fault risk level is low, the intelligent regulation unit reduces the motor output power by adjusting the frequency of the conveyor inverter, thereby reducing energy consumption.

[0116] When the fault risk level is medium, the intelligent regulation unit adjusts the operating parameters of the conveyor drive system. For example, it changes the position of the drive roller through a hydraulic device to optimize the belt tension distribution and improve equipment stability.

[0117] When the fault risk level is high, the intelligent regulation unit stops the conveyor operation and issues a warning prompt through an audible and visual alarm.

[0118] The audible and visual alarm sends visual and auditory signals to the operator. At the same time, the intelligent regulation unit uploads the fault information to the remote monitoring platform through the wireless communication module.

[0119] In addition, the intelligent regulation unit selects adjustment strategies according to the change trend of the equipment operation stability index.

[0120] For example, when the equipment operation stability index continues to decline, the position of the drive roller is preferentially adjusted; when the equipment operation stability index tends to be stable but the energy consumption is high, the motor output power is preferentially adjusted.

[0121] After issuing the warning prompt, the intelligent regulation unit generates a fault report through the remote monitoring platform. The report content includes the fault occurrence time, fault type, fault risk level, and recommended repair measures for the reference of maintenance personnel.

[0122] Through the above steps, the entire system realizes the comprehensive monitoring and intelligent management of the key operating parameters of the belt conveyor.

[0123] The data acquisition unit is responsible for collecting multi-dimensional dynamic parameters from the key parts of the conveyor, and its acquisition accuracy directly affects the accuracy of subsequent analysis. The fault feature extraction unit processes the collected data through the wavelet transform algorithm module and the principal component analysis module, and extracts the core features that can reflect the equipment operation state.

[0124] The risk assessment unit uses the fuzzy logic inference module to comprehensively analyze the input variables and obtain the fault risk level.

[0125] The intelligent regulation unit performs corresponding adjustment or warning operations according to the fault risk level to ensure the conveyor operates under safe and stable conditions.

[0126] The entire system realizes the efficient transmission of data through signal lines. Each unit has a clear division of labor and works together to jointly achieve the comprehensive monitoring and intelligent management of the belt conveyor.

[0127] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product.

[0128] Those of ordinary skill in the art can realize that the modules and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed in hardware or software depends on the specific application of the technical solution and the invention constraints. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of this application.

[0129] In addition, the functional modules in each embodiment of this application can be integrated into one processing module, or each module can exist physically alone, or two or more modules can be integrated into one module.

[0130] The above is only the specific implementation manner of this application, but the protection scope of this application is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed in this application, and all should be covered by the protection scope of this application. Therefore, the protection scope of this application should be subject to the protection scope of the claims.

[0131] Finally: The above is only the preferred embodiment of the present invention and is not used to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A fault prediction and health management system for a belt conveyor, characterized in that, It includes a data acquisition unit, a fault feature extraction unit, a risk assessment unit, and an intelligent regulation unit; The data acquisition unit monitors the key operating parameters of the belt conveyor in real time, obtains the current fluctuation value of the conveyor motor, the temperature change rate of the driving drum, and the belt tension distribution, transmits these parameters to the fault feature extraction unit, and collects the vibration spectrum data during the operation of the conveyor and transmits it to the risk assessment unit; The fault feature extraction unit extracts the abnormal features of the equipment operating state through the wavelet transform algorithm, calculates the equipment operation stability index by using the principal component analysis method in combination with the belt tension distribution, and transmits the abnormal features and the stability index to the risk assessment unit; The risk assessment unit is used to judge whether there is an abnormal vibration phenomenon in the conveyor, detect the wear degree of the conveyor bearing to obtain the wear amount, and analyze the fault risk level through fuzzy logic reasoning by integrating the abnormal vibration phenomenon, the wear amount, and the equipment operation stability index, and transmit the fault risk level to the intelligent regulation unit; The intelligent regulation unit is used to classify the fault risk level and adjust the operating state of the belt conveyor or issue an alarm prompt according to the classification result.

2. The fault prediction and health management system for a belt conveyor according to claim 1, characterized in that: Before the conveyor starts, the data acquisition unit uses an infrared thermometer to detect the initial temperature of the surface of the driving drum and records the initial temperature as the reference temperature value; During the operation of the conveyor, the data acquisition unit selects a fixed time period as the sampling period, receives the current fluctuation value collected by the current sensor installed on the conveyor motor. At the same time, within the sampling period, multiple detection sub-periods with the same time interval are divided, and the temperature sensor is used to monitor the surface temperature of the driving drum in real time.

3. The fault prediction and health management system for a belt conveyor according to claim 2, characterized in that: The specific steps for the data acquisition unit to monitor the surface temperature of the driving drum are as follows: Within the sampling period, multiple detection sub-periods with the same time interval are divided, and the surface temperature of the driving drum is recorded once at the time points at both ends of each detection sub-period; The temperature change amount of the corresponding detection sub-period is obtained by subtracting the temperature value recorded at the previous time point of the detection sub-period from the temperature value recorded at the latter time point of the detection sub-period; The temperature change amounts of each detection sub-period within the sampling period are compared, and the maximum value is selected as the temperature change rate within the sampling period; During the operation of the conveyor, the data acquisition unit uses a tension sensor to detect the tension at different positions of the conveyor belt, sorts the detected tension values according to the spatial distribution and draws a tension distribution curve, and takes the slope of the curve as the quantization index of the belt tension distribution.

4. The fault prediction and health management system for a belt conveyor according to claim 1, characterized in that: After receiving the current fluctuation value of the conveyor motor and the temperature change rate of the driving drum, the fault feature extraction unit first normalizes the two kinds of data by using the Z-score normalization method; Then, decompose the results of normalizing the two types of data using wavelet basis functions to extract abnormal features of the equipment operation status; After receiving the quantization index of the belt tension distribution, the fault feature extraction unit calculates the equipment operation stability index using the principal component analysis method. The specific steps are as follows: Form a multi-dimensional data matrix by combining the quantization index of the belt tension distribution with other operation parameters, calculate the covariance matrix of the data matrix, and solve its eigenvalues and eigenvectors; Select the eigenvectors corresponding to the top k largest eigenvalues to construct the principal component space, project the original data into the principal component space, and calculate the Euclidean distance of the projection points. Take the Euclidean distance as the equipment operation stability index.

5. A fault prediction and health management system for a belt conveyor according to claim 4, characterized in that: After receiving the vibration spectrum data, the risk assessment unit performs preprocessing as follows: Access the historical database to obtain the vibration spectrum reference value during the normal operation of the conveyor, and obtain the current vibration spectrum data during the operation of the conveyor; Take the root mean square error between the current vibration spectrum data and the reference value as the vibration anomaly coefficient, and use the vibration anomaly coefficient to normalize the vibration spectrum data; After receiving the wear amount of the conveyor bearing, the risk assessment unit uses an ultrasonic flaw detector to detect the crack depth on the bearing surface, and perform a weighted sum of the crack depth and the wear amount to obtain a comprehensive wear index.

6. A fault prediction and health management system for a belt conveyor according to claim 5, characterized in that: The risk assessment unit defines the abnormal vibration phenomenon, the comprehensive wear index, and the equipment operation stability index as input variables, and defines the fault risk level as the output variable; Formulate a set of fuzzy rules to describe the relationship between different input variables and the output variable, perform fuzzy reasoning according to the fuzzy rules, calculate the output result in combination with the membership function, and mark the fault risk level.

7. A fault prediction and health management system for a belt conveyor according to claim 6, characterized in that: After receiving the fault risk level, the intelligent control unit performs grading processing. The specific rules are as follows: When the fault risk level is low, adjust the output power of the conveyor motor to reduce energy consumption; When the fault risk level is medium, adjust the operation parameters of the conveyor drive system to improve equipment stability; When the fault risk level is high, stop the conveyor operation and issue an alarm prompt; The intelligent control unit controls the motor speed by adjusting the frequency of the conveyor inverter, and at the same time adjusts the position of the driving drum through the hydraulic device to change the belt tension distribution until the equipment operation status returns to normal; The alarm prompt sends visual and auditory signals to the operator through an audible and visual alarm, and uploads the fault information to the remote monitoring platform through a wireless communication module.

8. A fault prediction and health management system for a belt conveyor according to claim 7, characterized in that: When adjusting the operation status of the conveyor, the intelligent control unit preferentially selects an adjustment strategy according to the change trend of the equipment operation stability index. When the equipment operation stability index continues to decline, preferentially adjust the position of the driving drum; When the equipment operation stability index tends to be stable but the energy consumption is high, the motor output power is preferentially adjusted.

9. A fault prediction and health management system for a belt conveyor according to claim 7, characterized in that: After issuing an alarm prompt, the intelligent control unit generates a fault report through the remote monitoring platform. The fault report includes the fault occurrence time, fault type, fault risk level, and recommended repair measures.

10. A fault prediction and health management system for a belt conveyor according to claim 1, characterized in that: The data acquisition unit is composed of a current sensor, a temperature sensor, and a tension sensor, which are respectively used to collect the current fluctuation value of the conveyor motor, the temperature change rate on the surface of the driving drum, and the belt tension distribution. The fault feature extraction unit internally integrates a wavelet transform algorithm module and a principal component analysis method module, and is used for abnormal feature extraction and operation stability index calculation of the input data. The risk assessment unit comprehensively analyzes the input variables through the fuzzy logic reasoning module and outputs the fault risk level.

Images