Coal conveying equipment whole life cycle health management system based on internet of things

Abstract

The application discloses a coal conveying equipment whole life cycle health management system based on Internet of Things, and relates to the technical field of coal conveying equipment management.The system is composed of a data sensing layer, an edge computing layer, a data transmission layer, a platform management layer and an application interaction layer.The application builds the coal conveying equipment whole life cycle health management system based on Internet of Things, uses a sensor array to stably and accurately sense equipment state information under harsh working conditions, and performs preprocessing on original signals, such as noise reduction and feature extraction, by the edge computing layer.Combined with the platform management layer, the equipment health condition can be comprehensively and accurately evaluated, early potential faults of the equipment can be found in time by monitoring key indexes such as vibration kurtosis and pulse factors, maintenance measures can be taken in advance, production interruption caused by sudden equipment failure can be avoided, and therefore, the reliability and stability of the coal conveying equipment operation can be improved, and the smooth progress of the industrial production process can be ensured.

Description

Technical Field

[0001] This invention relates to the field of coal conveying equipment management technology, specifically to a coal conveying equipment full lifecycle health management system based on the Internet of Things. Background Technology

[0002] In modern industrial production, coal conveying equipment is a key infrastructure in coal transportation and related production processes. With the development of industrial automation and intelligence, the requirements for the reliability, stability, and efficiency of coal conveying equipment are increasing. Coal conveying equipment operates in complex and harsh environments for extended periods, such as high dust, heavy loads, and continuous operation, which can easily lead to equipment failures, resulting in production interruptions and increased maintenance costs. Once equipment fails, it will not only affect the continuity of coal supply but may also pose a serious threat to the operational efficiency and safety of the entire production system. Therefore, achieving full life-cycle health management of coal conveying equipment, timely and accurate monitoring of equipment operating status, and early prevention of failures are of paramount importance to ensuring the stable operation of industrial production.

[0003] Currently, existing technologies for the health management of coal conveying equipment have many shortcomings. Equipment health assessments often rely on single indicators or simple models, failing to fully consider the multi-dimensional factors of equipment operation and thus unable to comprehensively and accurately assess the health status of the equipment. In the stages of fault prediction and maintenance plan formulation, existing technologies lack in-depth integration and analysis of historical and real-time data of the equipment, resulting in low accuracy of fault prediction and maintenance plans that often lack scientific rigor and foresight, easily leading to over-maintenance or untimely maintenance, causing resource waste or increased risk of equipment damage.

[0004] In summary, existing health management solutions for coal conveying equipment are insufficient to meet the current industrial production demands for high reliability and efficient operation and maintenance. There is an urgent need for an advanced, IoT-based full lifecycle health management system for coal conveying equipment that can effectively integrate multi-source data to achieve real-time, accurate monitoring and analysis of equipment operating status, thereby ensuring the reliable operation of coal conveying equipment. Summary of the Invention

[0005] The purpose of this invention is to overcome the shortcomings of existing technologies and provide an IoT-based full lifecycle health management system for coal conveying equipment. By constructing an IoT-based full lifecycle health management system for coal conveying equipment, it can accurately perceive equipment status information using a multimodal sensor array, perform noise reduction and feature extraction preprocessing on the raw signals using an edge computing layer, and combine the platform management layer to accurately assess the health status of the equipment, promptly detect potential early equipment failures, take maintenance measures in advance, avoid production interruptions caused by sudden equipment failures, and thus significantly improve the reliability and stability of coal conveying equipment operation.

[0006] To solve the above-mentioned technical problems, the present invention provides the following technical solution: a full life cycle health management system for coal conveying equipment based on the Internet of Things, the system comprising: a data perception layer, an edge computing layer, a data transmission layer, a platform management layer, and an application interaction layer;

[0007] The data perception layer includes a multimodal sensor array deployed on the coal conveyor belt, roller bearings, drive motors, and coal drop pipes. It is used to collect equipment operating parameters and image data in real time and output the collected data to the edge computing layer.

[0008] The edge computing layer has a built-in denoising module and a feature extraction module, which processes the kurtosis factor, impulse index and voiceprint features of vibration signals in real time, and is configured with a threshold triggering mechanism to trigger high-definition video capture commands under abnormal conditions.

[0009] The data transmission layer adopts a dual-channel approach of industrial fiber optic ring network and 5G private network, supporting parallel transmission of multiple protocols for vibration, video stream and thermal imaging data, and transmitting them to the platform management layer.

[0010] The platform management layer uses IoT processing technology to combine data from the data transmission layer with historical equipment operation data, maintenance records, and design parameters to establish an equipment health assessment model, generate equipment health status levels, and establish a full lifecycle archive for the equipment.

[0011] The application interaction layer provides a visual user interface that supports access from both desktop and mobile devices.

[0012] Furthermore, the sensor types of the multimodal sensor array include a triaxial vibration sensor, an infrared thermal imager, an acoustic emission probe, and a coal flow video monitoring device, wherein the vibration sensor has a built-in temperature self-compensation module to eliminate measurement deviations caused by coal dust adhesion.

[0013] The multimodal sensor array is connected to the edge computing layer, and the vibration sensor establishes an event trigger association with the video monitoring device. When the vibration amplitude exceeds the threshold, the video recording function is automatically started.

[0014] Furthermore, the edge computing layer specifically includes:

[0015] Noise reduction module: Reduces noise in the data collected by the sensor array based on the equipment rotation speed signal, and dynamically adjusts the vibration signal frequency;

[0016] Feature extraction module: Receives the denoised vibration signal and acoustic emission signal, establishes a time-frequency domain feature vector, including kurtosis and impulse factor;

[0017] The feature extraction module establishes a two-way interaction channel with the platform management layer. On the one hand, the two-way interaction channel enables the periodic receipt of health assessment model parameter update packages issued by the platform; on the other hand, it automatically labels the current operating condition when uploading feature vectors in real time. The operating condition labels include no load, half load, and full load.

[0018] Event triggering module: Used to monitor the output data of the feature extraction module in real time, establish a timestamp alignment mechanism, synchronize the feature vectors of kurtosis and impulse factor according to the acquisition time t, and then execute the feedback control loop for joint judgment;

[0019] Data compression module: performs lossy compression on high-frequency components. The lossy compression performs frequency analysis on the vibration data, separates the high-frequency part, and encodes and compresses the high-frequency data.

[0020] Furthermore, the event triggering module and the data compression module form a feedback control loop, and the execution logic includes:

[0021] When the vibration kurtosis value output by the feature extraction module And pulse factor At that time, parallel operations are triggered: a high-definition video capture command is sent to the data perception layer, and lossy compression of the data compression module is started;

[0022] When the acoustic emission energy entropy mutation rate At the same time: automatically increase the acoustic emission signal sampling rate and synchronously enhance the network bandwidth priority of the data transmission layer;

[0023] in, For the first Each vibration signal sample value, The mean value of the vibration signal samples. The number of sampling points. For the time of collection, For collection time The energy entropy value at that time and , For the first The proportion of energy of the frequency component to the total energy in each sample.

[0024] Furthermore, the data transmission layer specifically includes:

[0025] Dual-channel redundant transmission module: It adopts a dual-channel redundant architecture of industrial ring network and 5G. The link status between the two channels is monitored in real time. When the transmission signal of the industrial ring network transmission link is abnormal, the system automatically switches to the 5G channel for data transmission. When the transmission signal of the 5G channel is abnormal, the data is automatically transferred to the industrial ring network for transmission.

[0026] Transmission Priority Module: Establishes a bandwidth allocation weight function and configures data priority transmission. ,in, For the first Class data weights, For the first Priority coefficient for class data, i.e., vibration data Video stream data Thermal imaging data , For data backlog, For adjustment coefficients, The maximum data backlog value set for the system;

[0027] Dynamic bandwidth allocation module: Dynamically adjusts the bandwidth of transmission resources according to the allocation weight of the transmission priority module, i.e. ,in For the first Bandwidth allocated to class data For the first Priority weights for class data The total number of data types, This represents the total available bandwidth.

[0028] Furthermore, the platform management layer includes:

[0029] Health assessment module: Constructing a judgment matrix ,in Representation factor and The relative importance of establishing a four-dimensional health factor set ,in, For real-time monitoring indicators, including vibration amplitude Pulse factor , Historical maintenance data, including mean time between failures (MTBF) and number of repairs. For design parameters, For environmental parameters, a judgment matrix is ​​constructed by comparing the importance of each health factor pairwise to quantify the relative weight relationships between factors and calculate the weight vector. , Indicates the first The weight of each health factor in the comprehensive assessment and meeting the following requirements. , The health index is obtained by transposing the weight vector. and , For the first The weights of each health factor For the first The current actual value of each health factor and These are the historical minimum and maximum values ​​for health factors;

[0030] Fault prediction module: Uses IoT time series analysis to predict fault time. ,in, The model order is... The trend term represents the long-term trend of the time series data. These are autoregressive coefficients, reflecting past performance. Health Index of the Period The extent of the impact on current failure time prediction The equipment health index for the past period v. for The white noise term at time, The moving average coefficient is used to predict the time when equipment failures will occur using this time series.

[0031] Furthermore, the platform management layer also includes a device lifecycle archive module for recording device data. The system records equipment model, purchase date, design life, record timestamp, load rate, and health index, and generates a full lifecycle profile of the equipment. When a maintenance work order is uploaded by the application interaction layer, it automatically links to the historical fault case library. By comparing the fault situation involved in the current maintenance work order with historical fault cases, it finds the handling experience and solutions for the same fault, and at the same time supplements and updates the historical case library.

[0032] Furthermore, the application interaction layer is used to view the equipment's operating status, health assessment results, fault prediction information, and maintenance plan content in real time, and to perform equipment information queries, maintenance task assignments, and alarm setting operations.

[0033] Compared with existing technologies, this IoT-based full lifecycle health management system for coal conveying equipment has the following beneficial effects:

[0034] I. This invention constructs a full lifecycle health management system for coal conveying equipment based on the Internet of Things. By utilizing a sensor array, it can stably and accurately perceive equipment status information under harsh working conditions. The edge computing layer performs noise reduction and feature extraction preprocessing on the raw signals. Combined with the platform management layer, it can comprehensively and accurately assess the health status of the equipment. By monitoring key indicators such as vibration kurtosis and impulse factor in real time, it can promptly detect early potential equipment failures and take maintenance measures in advance to avoid production interruptions caused by sudden equipment failures. This significantly improves the reliability and stability of coal conveying equipment operation and ensures the smooth operation of industrial production processes.

[0035] Second, based on the health assessment results and fault prediction information of the equipment, this invention formulates a precise maintenance plan, realizes the transformation from periodic maintenance to condition-based maintenance, and comprehensively manages the entire life cycle of coal conveying equipment, records information of the equipment at each stage, and provides comprehensive and accurate data support for equipment management decisions, which helps to optimize equipment procurement and upgrading decisions.

[0036] Other advantages, objectives and features of the invention will be set forth in part in the description which follows, and in part will be apparent to those skilled in the art from the following examination or study, or may be learned from the practice of the invention. Attached Figure Description

[0037] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the accompanying drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are merely some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without any creative effort.

[0038] Figure 1 This is an operation flowchart for an IoT-based full lifecycle health management system for coal conveying equipment.

[0039] Figure 2 This is a schematic diagram of the components of an IoT-based full lifecycle health management system for coal conveying equipment. Detailed Implementation

[0040] To further illustrate the technical means and effects of the present invention in achieving its intended purpose, the following detailed description of the specific implementation methods, structures, features, and effects of the present invention, in conjunction with the accompanying drawings and preferred embodiments, is provided below.

[0041] Example 1

[0042] This embodiment details the implementation process of an IoT-based full lifecycle health management system for coal conveying equipment, such as... Figure 2 As shown, the data perception layer collects equipment operation data in real time. With the collaborative work of the edge computing layer, data transmission layer, platform management layer and application interaction layer, the system can monitor the status of coal conveying equipment, conduct health assessments, predict faults and manage the entire life cycle. The functions of each layer work together to effectively improve the reliability and stability of the coal conveying equipment and provide strong support for industrial production.

[0043] The data sensing layer deploys a multimodal sensor array, encompassing a triaxial vibration sensor, an infrared thermal imager, an acoustic emission probe, and a coal flow video monitoring device. These are installed in key components such as the coal conveyor belt, roller bearings, drive motors, and coal chutes. The triaxial vibration sensor monitors the equipment's vibration, and its built-in temperature self-compensation module eliminates measurement deviations caused by coal dust adhesion. Since coal dust adhesion can alter the sensor's temperature characteristics and affect the accuracy of vibration measurements, the temperature self-compensation module adjusts the measurement results by monitoring its own temperature in real time. The infrared thermal imager acquires images of the equipment's surface temperature distribution and analyzes temperature differences to determine if there are abnormal heat points. In coal conveying equipment, components such as motors and bearings generate heat during operation; if a malfunction occurs, such as bearing wear or motor overload, the temperature will rise abnormally. Infrared thermal imagers can capture these changes in a timely manner; acoustic emission probes are used to detect acoustic emission signals generated when materials inside the equipment deform or cracks expand. During the operation of coal conveying equipment, wear, fatigue, and other damage to components can trigger acoustic emission phenomena. The acoustic emission probes convert these weak signals into electrical signals for output; the coal flow video monitoring device monitors the coal flow in real time, collecting image data such as the flow rate, shape, and presence of blockages. By analyzing this image data, the working status of the coal conveying system can be understood, and abnormal coal flow conditions can be detected in a timely manner. All data collected by the sensors are transmitted to the edge computing layer via the industrial bus. At the same time, the vibration sensor establishes an event trigger association with the video monitoring device. When the vibration amplitude exceeds a preset threshold, the video recording function will be automatically activated to record and analyze the abnormal state of the equipment more comprehensively.

[0044] The edge computing layer incorporates a denoising module, a feature extraction module, an event triggering module, and a data compression module. It processes the kurtosis factor, impulse index, and MFCC features of vibration signals in real time and is configured with a threshold triggering mechanism to trigger high-definition video capture commands under abnormal conditions. Specifically, the denoising module performs noise reduction processing on the data collected by the sensor array based on the device's rotational speed signal. The frequency characteristics of the vibration signal vary at different rotational speeds. The denoising module dynamically adjusts the frequency of the vibration signal by acquiring the device's rotational speed information to adapt to the signal characteristics under different operating conditions. It automatically adjusts the filter parameters based on the statistical characteristics of the signal to remove noise interference and retain useful signals. The feature extraction module receives the denoised vibration signal and acoustic emission signal, establishes a time-frequency domain feature vector, and calculates features such as kurtosis and impulse factor for the vibration signal. The kurtosis calculation formula is... ,in For the first Each vibration signal sample value, Let N be the mean of the vibration signal sample values, and N be the number of sampling points. The kurtosis value reflects the peak characteristics of the vibration signal. When equipment malfunctions, the kurtosis value of the vibration signal usually changes. The pulse factor is calculated using the following formula: It is used to measure the impact of vibration signals. For acoustic emission signals, it reflects the frequency structure and energy distribution of the acoustic emission signal. The feature extraction module establishes a two-way interactive channel with the platform management layer. On the one hand, it regularly receives health assessment model parameter update packages from the platform to ensure the accuracy and adaptability of feature extraction. On the other hand, it automatically labels the current operating condition, such as no load, half load, and full load, when uploading feature vectors in real time, so that the platform management layer can perform more accurate analysis of equipment status. The event triggering module is used to monitor the output data of the feature extraction module in real time and establish a timestamp alignment mechanism to align feature vectors such as kurtosis and impulse factor according to the acquisition time. After synchronization, the feedback control loop makes a joint judgment, and when the vibration kurtosis value output by the feature extraction module... At this time, parallel operations are triggered: a high-definition video capture command is sent to the data perception layer to acquire image information under abnormal device conditions; lossy compression of the data compression module is initiated to perform lossy compression on high-frequency components to reduce data transmission volume; when the acoustic emission energy entropy change rate... It automatically increases the acoustic emission signal sampling rate to obtain more detailed acoustic emission signal information; it also synchronously enhances the network bandwidth priority of the data transmission layer to ensure that important data can be transmitted preferentially. For collection time The energy entropy value at time is calculated using the formula: , For the first The proportion of energy of frequency components in the total energy of each sample; the data compression module performs lossy compression on high-frequency components. After frequency analysis of vibration data, the high-frequency part is separated and encoded and compressed. While ensuring that key data information is not lost, the amount of data is effectively reduced, and the pressure of data transmission and storage is reduced.

[0045] The data transmission layer adopts a dual-channel redundant architecture of industrial fiber optic ring network and 5G private network to ensure data transmission reliability. This data transmission layer includes a dual-channel redundant transmission module, a transmission priority module, and a dynamic bandwidth allocation module. The link status between the two channels is monitored in real time. When the transmission signal of the industrial ring network link is abnormal, the system automatically switches to the 5G channel for data transmission; when the transmission signal of the 5G channel is abnormal, the data is automatically switched back to the industrial ring network for transmission. This redundancy mechanism ensures the continuity of data transmission and avoids data loss due to link failure. The transmission priority module establishes a bandwidth allocation weight function. ,in, For the first Class data weights, For the first Priority coefficient for class data, i.e., vibration data Video stream data Thermal imaging data , For data backlog, For adjustment coefficients, The maximum data backlog value is set for the system. This function calculates the weight of each data type based on its priority and backlog status. The dynamic bandwidth allocation module dynamically adjusts the bandwidth of transmission resources according to the allocation weights from the transmission priority module. ,in For the first Bandwidth allocated to class data For the first Priority weights for class data The total number of data types, To ensure sufficient bandwidth for important data, dynamic bandwidth allocation is used to guarantee that critical data receives adequate bandwidth resources, thereby improving the efficiency and quality of data transmission.

[0046] The platform management layer utilizes IoT processing technology, combined with data from the data transmission layer, historical equipment operating data, maintenance records, and design parameters, to establish an equipment health assessment model. This model generates equipment health status levels and creates a full lifecycle archive for the equipment, including a health assessment module, a fault prediction module, and a full lifecycle archive module. This module is responsible for in-depth data analysis and processing. Specifically, the health assessment module constructs a judgment matrix. ,in Representation factor and The relative importance of establishing a four-dimensional health factor set , For real-time monitoring indicators, including vibration amplitude Pulse factor , Historical maintenance data, including mean time between failures (MTBF) and number of repairs. For design parameters, For environmental parameters, a judgment matrix is ​​constructed by comparing the importance of each health factor pairwise to quantify the relative weight relationships between factors and calculate the weight vector. , Indicates the first The weight of each health factor in the comprehensive assessment and meeting the following requirements. , It is the transpose of the weight vector. By calculating the eigenvalues ​​of the judgment matrix, the weights of each health factor are obtained, and thus the health index is derived. and , For the first The current actual value of each health factor and The health index represents the historical minimum and maximum values ​​of health factors. It can comprehensively reflect the health status of equipment, providing important information for equipment maintenance and management; the fault prediction module uses IoT time series analysis to predict fault time. ,in, The model order is... The trend term represents the long-term trend of the time series data. These are autoregressive coefficients, reflecting past performance. Health Index of the Period The extent of the impact on current failure time prediction For the past Equipment health index during the period, for The white noise term at time, This is the moving average coefficient. Using this time series model, combined with historical equipment health index data, the timing of equipment failures can be predicted, providing early support for maintenance decisions. The equipment lifecycle archive module is used to record equipment... Information such as model, purchase date, design life, record timestamp, load rate, and health index is collected and a full lifecycle file of the equipment is generated. When a maintenance work order is uploaded by the application interaction layer, it is automatically linked to the historical fault case library. By comparing the fault situation involved in the current maintenance work order with historical fault cases, the system can find the handling experience and solutions for the same fault. At the same time, the historical case library is supplemented and updated. In this way, the experience of equipment maintenance can be continuously accumulated, and the efficiency and accuracy of fault handling can be improved.

[0047] The application interaction layer provides users with a convenient operating interface, supporting access from both computers and mobile devices. Users can view real-time equipment operating status, health assessment results, fault prediction information, and maintenance plans through this interface. The equipment operating status interface displays real-time vibration data, temperature data, coal flow conditions, and other information. The health assessment results interface presents the equipment's health index and health status level in intuitive charts. The fault prediction information interface displays the predicted fault time and fault type. The maintenance plan interface displays maintenance tasks and schedules based on the equipment's health status. Users can also query equipment information, inputting equipment ID and other information to obtain detailed parameters and historical operating data. They can also issue maintenance tasks, sending maintenance instructions to relevant maintenance personnel; and set alarm parameters, such as vibration amplitude thresholds and temperature thresholds. When equipment operating parameters exceed the thresholds, the system automatically sends alarm information to notify relevant personnel for timely handling.

[0048] In summary, this embodiment demonstrates that the IoT-based coal conveying equipment lifecycle health management system operates with close collaboration across all layers. The data perception layer accurately collects equipment operation data, the edge computing layer preprocesses and performs preliminary analysis on the data, the data transmission layer ensures reliable data transmission, the platform management layer performs equipment health assessment, fault prediction, and lifecycle management, and the application interaction layer provides users with a convenient operation and management interface. The entire system effectively integrates multi-source data, enabling real-time and accurate monitoring and analysis of the coal conveying equipment's operating status. It can promptly detect potential equipment faults, formulate maintenance plans in advance, and significantly improve the reliability and stability of coal conveying equipment operation.

[0049] Example 2

[0050] like Figure 1 As shown, this embodiment provides an IoT-based full lifecycle health management system for coal conveying equipment, outlining the operation process of the coal conveying equipment. The specific steps of this operation process are as follows:

[0051] (1) Data acquisition stage

[0052] Sensor deployment: Install multimodal sensors such as triaxial vibration sensors, infrared thermal imagers, acoustic emission probes, and coal flow video monitoring devices in key parts of coal conveying equipment, such as belt conveyors, drum bearings, drive motors, and coal chutes.

[0053] Real-time data acquisition: Each sensor collects real-time operating data of the coal conveying equipment, including information such as vibration, temperature distribution, acoustic emission signals, and coal flow.

[0054] Preliminary data association: Establish event trigger association between vibration sensors and video monitoring devices. When the vibration amplitude exceeds a preset threshold, the video recording function will be automatically activated.

[0055] (2) Edge computing stage

[0056] Data transmission to the edge layer: Data collected by sensors is transmitted to the edge computing layer via an industrial bus;

[0057] Data noise reduction processing: The noise reduction module of the edge computing layer performs noise reduction on the collected data based on the device rotation speed signal, removes noise interference, and retains useful signals;

[0058] Feature extraction: Features are extracted from the denoised vibration signal and acoustic emission signal, vibration features such as kurtosis and impulse factor are calculated, and a time-frequency domain feature vector is established;

[0059] Operating condition labeling: When uploading feature vectors, the operating condition labels of the current device are automatically labeled, such as no load, half load, and full load;

[0060] Event trigger judgment: Real-time monitoring of the output data of the feature extraction module. When the vibration kurtosis value, impulse factor and other indicators exceed the preset threshold, or the acoustic emission energy entropy mutation rate exceeds the specified value, parallel operation is performed.

[0061] (3) Data transmission stage

[0062] Dual-channel link monitoring: Real-time monitoring of the link status between the industrial fiber optic ring network and the 5G private network at the data transmission layer;

[0063] Link switching: When the channel transmission signal is abnormal, it automatically switches to another channel for data transmission;

[0064] Data priority determination: Based on the data type (such as vibration data, video stream data, thermal imaging data) and backlog situation, the transmission priority of each type of data is determined;

[0065] Dynamic bandwidth allocation: Dynamically adjusts the bandwidth of transmission resources according to data priority to ensure that important data is transmitted first;

[0066] (4) Platform Management Phase

[0067] Data reception and storage: The platform management layer receives data from the data transmission layer, stores it, establishes a full lifecycle profile of the device, and records various information about the device;

[0068] Health assessment: Construct a judgment matrix, determine the relative importance of each health factor, calculate the weight vector, and then obtain the health index of the equipment to assess the health status of the equipment;

[0069] Fault prediction: Using time series forecasting methods and combining historical health index data of the equipment, the timing and type of equipment failure are predicted;

[0070] Maintenance plan development: Based on the equipment health assessment results and fault prediction information, and in conjunction with maintenance resources, a scientific and reasonable maintenance plan is developed, and a full life cycle record is generated;

[0071] Case library association and update: When a maintenance work order is received from the application interaction layer, it automatically associates with the historical fault case library, searches for similar fault handling experience, and updates the case library;

[0072] (5) Application interaction stage

[0073] Interface display: Through computer and mobile interfaces, users are shown the device's operating status, health assessment results, fault prediction information, and maintenance plans.

[0074] Information Inquiry: Users can enter information such as device ID to query detailed parameters and historical operating data of the device;

[0075] Task assignment: Users can assign maintenance tasks to relevant maintenance personnel through a visual interface;

[0076] Parameter settings: Users can set alarm parameters, and the system will automatically alarm when the device operating parameters exceed the threshold.

[0077] The above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention in any way. Although the present invention has been disclosed above with reference to preferred embodiments, it is not intended to limit the present invention. Any person skilled in the art can make some modifications or alterations to the above-disclosed technical content to create equivalent embodiments without departing from the scope of the present invention. Any simple modifications, equivalent changes and alterations made to the above embodiments based on the technical essence of the present invention without departing from the scope of the present invention shall still fall within the scope of the present invention.

Claims

1. A coal conveying equipment full lifecycle health management system based on the Internet of Things, characterized in that, The system consists of: a data perception layer, an edge computing layer, a data transmission layer, a platform management layer, and an application interaction layer. The data perception layer includes a multimodal sensor array deployed on the coal conveyor belt, roller bearings, drive motors, and coal drop pipes. It is used to collect equipment operating parameters and image data in real time and output the collected data to the edge computing layer. The edge computing layer has a built-in denoising module and a feature extraction module, which processes the kurtosis factor, impulse index and voiceprint features of vibration signals in real time, and is configured with a threshold triggering mechanism to trigger high-definition video capture commands under abnormal conditions. The edge computing layer specifically includes: Noise reduction module: Reduces noise in the data collected by the sensor array based on the equipment rotation speed signal, and dynamically adjusts the vibration signal frequency; Feature extraction module: Receives the denoised vibration signal and acoustic emission signal, establishes a time-frequency domain feature vector, including kurtosis and impulse factor; The feature extraction module establishes a two-way interaction channel with the platform management layer. On the one hand, the two-way interaction channel enables the periodic receipt of health assessment model parameter update packages issued by the platform; on the other hand, it automatically labels the current operating condition when uploading feature vectors in real time. The operating condition labels include no load, half load, and full load. Event triggering module: Used to monitor the output data of the feature extraction module in real time, establish a timestamp alignment mechanism, synchronize the feature vectors of kurtosis and impulse factor according to the acquisition time t, and then execute the feedback control loop for joint judgment; Data compression module: performs lossy compression on high-frequency components. The lossy compression performs frequency analysis on the vibration data, separates the high-frequency components, and encodes and compresses the high-frequency data. The event triggering module and the data compression module form a feedback control loop, and the execution logic includes: When the vibration kurtosis value output by the feature extraction module And pulse factor At that time, parallel operations are triggered: a high-definition video capture command is sent to the data perception layer, and lossy compression of the data compression module is started; When the acoustic emission energy entropy mutation rate At the same time: automatically increase the acoustic emission signal sampling rate and synchronously enhance the network bandwidth priority of the data transmission layer; in, For the first Each vibration signal sample value, The mean value of the vibration signal samples. The number of sampling points. For the time of collection, For collection time The energy entropy value at that time and , For the first The proportion of the energy of the frequency component in each sample to the total energy; The data transmission layer adopts a dual-channel approach of industrial fiber optic ring network and 5G private network, supporting parallel transmission of multiple protocols for vibration, video stream and thermal imaging data, and transmitting them to the platform management layer. The platform management layer uses IoT processing technology to combine data from the data transmission layer with historical equipment operation data, maintenance records, and design parameters to establish an equipment health assessment model, generate equipment health status levels, and establish a full lifecycle archive for the equipment. The application interaction layer provides a visual user interface that supports access from both desktop and mobile devices.

2. The IoT-based full lifecycle health management system for coal conveying equipment according to claim 1, characterized in that, The multimodal sensor array includes a triaxial vibration sensor, an infrared thermal imager, an acoustic emission probe, and a coal flow video monitoring device. The vibration sensor has a built-in temperature self-compensation module to eliminate measurement deviations caused by coal dust adhesion. The multimodal sensor array is connected to the edge computing layer, and the vibration sensor establishes an event trigger association with the video monitoring device. When the vibration amplitude exceeds the threshold, the video recording function is automatically started.

3. The IoT-based full lifecycle health management system for coal conveying equipment according to claim 1, characterized in that, The data transmission layer specifically includes: Dual-channel redundant transmission module: It adopts a dual-channel redundant architecture of industrial ring network and 5G. The link status between the two channels is monitored in real time. When the transmission signal of the industrial ring network transmission link is abnormal, the system automatically switches to the 5G channel for data transmission. When the transmission signal of the 5G channel is abnormal, the data is automatically transferred to the industrial ring network for transmission. Transmission Priority Module: Establishes a bandwidth allocation weight function and configures data priority transmission. ,in, For the first Class data weights, For the first Priority coefficient for class data, i.e., vibration data Video stream data Thermal imaging data , For data backlog, For adjustment coefficients, The maximum data backlog value set for the system; Dynamic bandwidth allocation module: Dynamically adjusts the bandwidth of transmission resources according to the allocation weight of the transmission priority module, i.e. ,in For the first Bandwidth allocated to class data For the first Priority weights for class data The total number of data types, This represents the total available bandwidth.

4. The IoT-based full lifecycle health management system for coal conveying equipment according to claim 1, characterized in that, The platform management layer includes: Health assessment module: Constructing a judgment matrix ,in Representation factor and The relative importance of establishing a four-dimensional health factor set ,in, For real-time monitoring indicators, including vibration amplitude Pulse factor , Historical maintenance data, including mean time between failures (MTBF) and number of repairs. For design parameters, For environmental parameters, a judgment matrix is ​​constructed by comparing the importance of each health factor pairwise to quantify the relative weight relationships between factors and calculate the weight vector. , Indicates the first The weight of each health factor in the comprehensive assessment and meeting the following requirements. , The health index is obtained by transposing the weight vector. and , For the first The current actual value of each health factor and These are the historical minimum and maximum values ​​for health factors; Fault prediction module: Uses IoT time series analysis to predict fault time. ,in, The model order is... The trend term represents the long-term trend of the time series data. These are autoregressive coefficients, reflecting past performance. Health Index of the Period The extent of the impact on current failure time prediction The equipment health index for the past period v. for The white noise term at time, The moving average coefficient is used to predict the time when equipment failures will occur using this time series.

5. The IoT-based full lifecycle health management system for coal conveying equipment according to claim 1, characterized in that, The platform management layer also includes a device lifecycle archive module for recording device data. The system records equipment model, purchase date, design life, record timestamp, load rate, and health index, and generates a full lifecycle profile of the equipment. When a maintenance work order is uploaded by the application interaction layer, it automatically links to the historical fault case library. By comparing the fault situation involved in the current maintenance work order with historical fault cases, it finds the handling experience and solutions for the same fault, and at the same time supplements and updates the historical case library.

6. The IoT-based full lifecycle health management system for coal conveying equipment according to claim 1, characterized in that, The application interaction layer is used to view the equipment operating status, health assessment results, fault prediction information, and maintenance plan content in real time, and to perform equipment information queries, maintenance task assignments, and alarm setting operations.

Images