Bulk material conveying belt abrasion monitoring system integrating digital twinning

Abstract

The invention provides a digital twinning fused bulk material conveying belt wear monitoring system, and relates to the technical field of data processing, and the system comprises a sensing data collection module which is used for collecting native data in the operation process of a conveying belt at a plurality of monitoring positions along the conveying belt; the data preprocessing module is used for carrying out formatting, noise reduction and calibration processing on the native data; the digital twinning construction module is used for dynamically generating a virtual model of the conveying belt and mapping the data to a preset corresponding area of the virtual model according to space and time dimensions; the abnormity identification module is used for performing partition detection on wear characteristics of each monitoring area of the belt and identifying and positioning a local area with an abnormal change trend; the early warning triggering module is used for generating early warning information containing the abnormal position and the abrasion degree and outputting the early warning information to the upper computer or the operation and maintenance terminal; the accuracy of the conveying belt abrasion monitoring system is improved.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a bulk material conveyor belt wear monitoring system integrated with digital twins. Background Art

[0002] Existing technologies primarily monitor the wear of bulk material conveyor belts using a combination of sensor arrays and regular manual inspections. Strain sensors, temperature sensors, and vibration sensors are typically placed at key locations on the belt. These sensors collect physical signals in real time to determine the wear status of the belt surface or interior. Simultaneously, the monitoring system statistically analyzes the sensor data to generate wear trend reports, which are supplemented by manual inspections for verification. Some systems also incorporate image acquisition and processing modules, using cameras to capture images of the belt surface and perform image recognition, thereby improving detection accuracy.

[0003] In practical applications, when belts are conveying large, hard bulk materials, existing monitoring systems often struggle to detect early signs of severe localized wear due to the limited number and placement of sensors. For example, in the case of raw ore conveying in mines, the frequent impact of material particles can easily lead to uneven wear at the edges or joints of the belt. However, due to blind spots in existing monitoring systems, abnormal wear is often not detected in a timely manner, increasing operational risks for the equipment. In this scenario, the system suffers from a technical flaw: a slow response to sudden localized wear, impacting subsequent maintenance and operational safety. Summary of the Invention

[0004] The purpose of the present invention is to provide a bulk material conveyor belt wear monitoring system integrating digital twins, aiming to solve the problems mentioned in the background technology.

[0005] In order to solve the above technical problems, the technical solutions of the present invention are as follows: A bulk material conveyor belt wear monitoring system integrated with digital twin, the system comprising: A sensor data acquisition module is used to collect raw data during the operation of the conveyor belt at multiple monitoring locations along the conveyor belt, wherein the raw data includes physical signal data and image data signals; The data preprocessing module is used to format, reduce noise and calibrate the raw data to obtain analytical data; The digital twin construction module is used to dynamically generate a virtual model of the conveyor belt based on the analysis data, map the analysis data to the corresponding areas of the preset virtual model according to the spatial and temporal dimensions, and obtain the multi-region state parameter set of the belt; The anomaly recognition module is used to perform partition detection on the wear characteristics of each monitoring area of ​​the belt based on the multi-area state parameter set of the belt, identify and locate local areas with abnormal change trends, and obtain anomaly recognition results; The early warning trigger module is used to generate early warning information including the abnormal location and wear degree based on the abnormality identification results, and output it to the host computer or operation and maintenance terminal.

[0006] Preferably, the digital twin building module includes: The virtual model construction submodule is used to generate a virtual model corresponding to the conveyor belt structure according to the monitoring position and conveyor belt structure information in the analysis data, and initialize the attributes of each spatial node; The data mapping submodule is used to map the analysis data to the corresponding spatial nodes and time indexes in the virtual model according to preset spatial partitions and time periods, and to update the original data sequence of each spatial node in different time periods. The spatial partitions are groupings of monitoring locations along the belt, the time periods are groupings of analysis data collection times, and the time indexes are numberings of time periods. The parameter extraction submodule is used to calculate the maximum value, minimum value, average value and rate of change of each spatial node through its original data sequence, and to correspond them to the spatial position and time index of the spatial node one by one to generate the state parameter set of the spatial node; The parameter sequence combination submodule is used to serialize the state parameter sets of all spatial nodes in each time period in the order of spatial partition and time index to generate a multi-dimensional parameter matrix, and perform multi-dimensional statistics on the various state parameter data therein to generate a multi-region state parameter set of the belt.

[0007] Preferably, the anomaly identification module includes: The parameter sequence analysis submodule is used to analyze the state parameter sequences of each spatial partition in different time periods based on the multi-region state parameter set of the belt, calculate the parameter change rate at adjacent time points, and compare it with the preset abnormal threshold to generate a candidate set of abnormal state parameters; The cluster identification submodule is used to cluster the candidate set of abnormal state parameters according to spatial proximity and change characteristics, identify spatial partition areas with similar abnormal characteristics, and generate clustered abnormal partition sets; The anomaly localization submodule is used to calibrate the anomaly location and time period based on the clustered anomaly partition set, combined with the spatial partition and time period information, to form an anomaly recognition result.

[0008] Preferably, the parameter extraction submodule includes: An extreme value calculation unit is used to determine the maximum and minimum values ​​of all sampled values ​​according to the original data sequence of each spatial node in each time period, and output the maximum and minimum values ​​as extreme value parameters corresponding to the spatial position and time index of the spatial node respectively; The mean calculation unit is used to accumulate all the sampled values ​​in the original data sequence of each spatial node in each time period and divide them by the number of samples to obtain an average value parameter. The average value is output in a one-to-one correspondence with the spatial position and time index of the spatial node; A change rate calculation unit is used to calculate the difference of all adjacent sampling values ​​in sequence according to the original data sequence of each spatial node in each time period to obtain a difference sequence, and divide the sum of the absolute values ​​of the difference sequence by the number of differences to obtain a change rate parameter. The change rate parameter is output in a one-to-one correspondence with the spatial position and time index of the spatial node; The parameter aggregation unit is used to uniformly aggregate extreme value parameters, average value parameters and change rate parameters according to the spatial position and time index of each spatial node to form a state parameter set for each spatial node and each time period.

[0009] Preferably, the parameter sequence combination submodule includes: The sequence arrangement unit is used to arrange the state parameter sets of all spatial nodes in each time period in sequence according to the spatial partition position order and the increasing order of time index to generate a multi-dimensional parameter matrix; The multidimensional statistical unit is used to perform statistics on various state parameter data in the multidimensional parameter matrix according to the following steps: For each spatial partition, according to the time index order, for the same state parameters, calculate the mean, range, and maximum continuous increasing interval length of each time period to generate the partition time series statistics; For the same state parameters of all spatial partitions under each time index, calculate the spatial maximum, minimum, mean and standard deviation at that time point and generate the corresponding spatial statistical results; The parameter integration unit is used to merge the time series statistical results of all spatial partitions and the spatial statistical results of each time period according to the two dimensions of spatial partition and time, and form a multi-region belt state parameter set indexed by spatial partition and time.

[0010] Preferably, the parameter sequence analysis submodule includes: A change rate calculation unit is used to calculate the difference of the state parameters at adjacent time indexes for each spatial partition state parameter sequence, and divide the sum of the absolute values ​​of all differences by the number of differences to obtain the change rate sequence of the spatial partition on the state parameter; The threshold comparison unit is used to compare each change rate value in the change rate sequence with the preset abnormality judgment threshold. If the change rate value is greater than the abnormality judgment threshold, the corresponding spatial partition, time index and state parameter are marked as abnormal candidates to generate an abnormal state parameter candidate set.

[0011] Preferably, the cluster identification submodule includes: The spatial clustering unit is used to take the abnormal state parameters with adjacent spatial positions as the same initial cluster according to the abnormal state parameter candidate set to generate an initial spatial cluster set; The feature similarity discrimination unit is used to classify the abnormal points with the same abnormal state parameter type and change direction according to the state parameter type and change characteristics in each initial spatial cluster according to the initial spatial cluster cluster set, and obtain feature consistency subclusters; The cluster merging unit is used to judge the spatial distance and parameter change amplitude between feature consistency subclusters. If the spatial distance is less than the preset spatial distance threshold and the change amplitude is less than the preset absolute difference threshold, the feature consistency subclusters that meet the conditions will be merged into cluster partitions to form a cluster anomaly partition set.

[0012] Preferably, the abnormality locating submodule includes: An abnormal interval determination unit is used to extract the spatial partition range and corresponding time range of each cluster partition according to the cluster abnormal partition set, and generate abnormal interval information; The abnormality type determination unit is used to extract the corresponding state parameters based on the abnormal interval information and analyze its change characteristics over time. If the abnormality persists throughout the entire time range, it is determined to be continuous wear. If a sudden change occurs at a certain moment, it is determined to be sudden wear. If the change shows regular fluctuations, it is determined to be a periodic abnormality and generates abnormality type information; The abnormality identification result generating unit is used to generate and output the abnormality identification result according to the spatial partition range, time range and abnormality type information of each abnormal interval.

[0013] Preferably, the feature similarity determination unit includes: The parameter type grouping unit is used to classify the abnormal state parameters in each cluster according to the parameter type according to the initial spatial clustering cluster set to form parameter type groups; The change trend analysis unit is used to determine whether the change directions of the abnormal state parameters in each parameter type group are consistent based on the changes in their parameter values ​​in adjacent time periods. If they are consistent, they are classified into the same trend group. If they are inconsistent, the abnormal state parameters with different change directions are divided into new trend groups and classified separately; The amplitude consistency screening unit is used to calculate the change amplitude of each parameter in each trend group for the abnormal state parameters, and compare it with the average change amplitude in the group. If the difference between the change amplitude of the parameter and the average value in the group is less than the preset amplitude difference threshold, the parameter is retained; otherwise, it is eliminated, and finally a feature consistency subcluster is generated.

[0014] Preferably, the cluster merging unit includes: The spatial distance determination unit is used to calculate the distance between the central spatial partitions of each sub-cluster based on the feature consistency sub-clusters. If the distance is less than the spatial distance threshold, the corresponding sub-cluster is classified as a mergeable object; A change amplitude determination unit is used to calculate the average parameter change amplitude of each sub-cluster in each group of mergeable objects, and then calculate the absolute difference of the average change amplitudes between the groups. If the absolute difference is less than the absolute difference threshold, it is determined that the sub-cluster corresponding to the group meets the merging condition; The merging generation unit is used to merge the feature consistency subclusters that meet both the spatial distance threshold and the absolute difference threshold into a cluster partition. The set of all cluster partitions constitutes the cluster anomaly partition set. The above solution of the present invention includes at least the following beneficial effects: The present invention greatly expands the monitoring coverage by simultaneously collecting physical signal data and image data signals at multiple monitoring locations along the conveyor belt. Compared with the existing technology with limited number of sensors and monitoring blind spots existing in manual inspections, it can more carefully capture the wear status of various areas of the belt, especially vulnerable locations such as edges and joints. The data preprocessing module formats, reduces noise and calibrates the raw data, effectively eliminating interference caused by the external environment or data collection anomalies, and improving the accuracy and reliability of wear identification. Through the digital twin construction module, the system can dynamically generate a virtual model based on the analyzed data, realize spatial and temporal multi-dimensional mapping of the actual belt operation status, and then obtain a set of belt multi-region state parameters, significantly improving the early perception of belt wear changes. The anomaly recognition module can not only automatically partition and detect each monitoring area along the entire line, but also accurately identify and locate abnormal change trends in local areas, so as to promptly detect local sudden wear caused by material impact, uneven particle distribution, etc. The early warning trigger module further outputs abnormal location and wear level information to a host computer or operation and maintenance terminal in real time, enabling operators to respond and perform maintenance immediately, effectively reducing the risk of equipment failure caused by monitoring blind spots and slow response. In typical application scenarios such as mining ore and heavy-loaded bulk materials, this invention can significantly improve the efficiency of identifying early localized wear and monitoring accuracy, providing strong technical support for the long-term safe operation of bulk material conveyor belts. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 This is an architectural diagram of a bulk material conveyor belt wear monitoring system integrated with digital twins, provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0016] Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. Rather, these embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0017] like Figure 1 As shown, an embodiment of the present invention provides a bulk material conveyor belt wear monitoring system integrated with digital twin, the system comprising: A sensor data acquisition module is used to collect raw data during the operation of the conveyor belt at multiple monitoring locations along the conveyor belt, wherein the raw data includes physical signal data and image data signals; The data preprocessing module is used to format, reduce noise and calibrate the raw data to obtain analytical data; The digital twin construction module is used to dynamically generate a virtual model of the conveyor belt based on the analysis data, map the analysis data to the corresponding areas of the preset virtual model according to the spatial and temporal dimensions, and obtain the multi-region state parameter set of the belt; The anomaly recognition module is used to perform partition detection on the wear characteristics of each monitoring area of ​​the belt based on the multi-area state parameter set of the belt, identify and locate local areas with abnormal change trends, and obtain anomaly recognition results; The early warning trigger module is used to generate early warning information including the abnormal location and wear degree based on the abnormality identification results, and output it to the host computer or operation and maintenance terminal.

[0018] In an embodiment of the present invention, the system can collect physical signal data and image data signals in real time at multiple monitoring locations along the conveyor belt through the sensor data acquisition module, covering the multi-dimensional state of the belt during operation. After formatting, noise reduction and calibration processing by the data preprocessing module, the noise and anomalies in the original data are effectively eliminated, and the accuracy and robustness of subsequent data analysis are improved. The digital twin construction module dynamically generates a virtual model of the conveyor belt based on the analysis data, realizes real-time mapping and simulation of the actual conveyor belt operation status, and can fully reflect the physical state of each monitoring area. By mapping the analysis data in the spatial and temporal dimensions, the system can generate a fine-grained belt multi-region state parameter set to ensure that the operation characteristics of each spatial partition and each moment can be recorded and tracked. The abnormality recognition module can realize accurate partition detection of the wear characteristics of each monitoring area of ​​the belt based on the above-mentioned state parameter set, and can timely identify and locate abnormal change trends in local areas, thereby discovering belt operation risks in advance. Finally, the early warning trigger module generates warning information based on the abnormality identification results, including the abnormal location and degree of wear. This information can be flexibly output to the host computer or operation and maintenance terminal, allowing operators to immediately identify the abnormal situation and take appropriate measures. For example, in actual application scenarios, if the status parameters of a monitoring location suddenly change within a short period of time, the system can quickly identify this area as a potential wear risk point and issue a timely alarm to ensure the safe and stable operation of the conveying equipment.

[0019] The digital twin in this invention not only includes virtual modeling of the conveyor belt structure but also continuously collects and maps actual monitoring data, dynamically synchronizing the analyzed data to the virtual model, enabling real-time linkage between the physical object and the virtual space. This virtual model, the core component of the digital twin, continuously updates its attributes as data changes, enabling accurate dynamic mapping of the conveyor belt's operating status throughout its lifecycle, thereby building a conveyor belt digital twin system.

[0020] The sensor data acquisition module is used to collect raw data during the operation of the conveyor belt at multiple monitoring locations along the conveyor belt, specifically including: Strain sensors, temperature sensors, vibration sensors, and industrial cameras, among other acquisition devices, are installed at various spatial locations on the conveyor belt (e.g., key areas like the belt's edges, center, and joints) to synchronously collect the belt's mechanical state, temperature changes, vibration conditions, and surface images in real time or periodically. Each sensor can be connected to the main controller via a data acquisition card or data bus. Physical signal data such as strain, temperature, and vibration amplitude are collected at a set sampling frequency and assigned a timestamp and spatial number to ensure that the collected data corresponds to the specific monitoring location and acquisition time. Image data signals are captured using a high-resolution camera to capture panoramic or detailed images of the belt surface. The image files are then labeled with the spatial location and acquisition time for subsequent analysis and traceability. For example, in a bulk material conveying scenario in a mine, the system can continuously collect and store physical quantities at key locations and images at corresponding moments, ensuring that the data comprehensively covers the entire belt's operating state.

[0021] The data preprocessing module is used to format, reduce noise, and calibrate the raw data to obtain analytical data. Specifically, it includes: After receiving the raw data output from the sensor data acquisition module, the physical signal data is first standardized, unifying sensor data from different sources into a specified format. The data is then sorted and archived by monitoring location and acquisition time. For the physical signal data, a sliding average or median filter is applied to remove fluctuations and noise caused by environmental interference or transient anomalies, ensuring data smoothness and reliability. For outliers or missing data, an anomaly detection algorithm automatically removes outliers and interpolates to fill in missing data segments. For image data signals, format conversion and size normalization are performed to a standard resolution. Image denoising algorithms (such as bilateral filtering) are then used to remove noise introduced during the capture process. All preprocessed data must be associated with the original acquisition time and spatial location to form a structured analysis dataset. For example, during continuous acquisition, if a strain sensor shows an abnormally high value, the system automatically identifies and removes this value by comparing data from adjacent time points. The value is then filled in with the mean of the adjacent valid data points, ultimately ensuring the validity of downstream analysis.

[0022] The early warning trigger module is used to generate early warning information including the abnormal location and wear degree based on the abnormality identification results, and output it to the host computer or operation and maintenance terminal. Specifically, it includes: After receiving the anomaly identification results from the anomaly recognition module, the system first extracts the spatial partition number, time range, and wear characteristic parameters for each anomaly area. Based on the anomaly location, type, and degree of wear, and in accordance with predefined warning classification criteria, the anomaly is categorized as general warning, severe warning, or other levels, and a corresponding warning message is generated. The warning message includes the anomaly's spatial location, start and end times, description of the anomaly type, wear parameters (such as maximum value and rate of change), and risk recommendations. The system automatically determines whether an immediate alert is necessary (e.g., if a set threshold is reached or the duration of the anomaly exceeds a certain limit) and pushes the warning message to a host computer, control center, or mobile terminal of maintenance personnel via a wired or wireless network, enabling real-time notification and response to the anomaly. For example, if the wear change rate in a certain section significantly exceeds the warning level for multiple consecutive time periods, the system automatically generates a detailed warning message containing the anomaly partition, time range, and wear parameters, prompting the relevant maintenance personnel to promptly inspect and maintain the area.

[0023] In a preferred embodiment of the present invention, the digital twin construction module includes: The virtual model construction submodule is used to generate a virtual model corresponding to the conveyor belt structure according to the monitoring position and conveyor belt structure information in the analysis data, and initialize the attributes of each spatial node; The data mapping submodule is used to map the analysis data to the corresponding spatial nodes and time indexes in the virtual model according to preset spatial partitions and time periods, and to update the original data sequence of each spatial node in different time periods. The spatial partitions are groupings of monitoring locations along the belt, the time periods are groupings of analysis data collection times, and the time indexes are numberings of time periods. The parameter extraction submodule is used to calculate the maximum value, minimum value, average value and rate of change of each spatial node through its original data sequence, and to correspond them to the spatial position and time index of the spatial node one by one to generate the state parameter set of the spatial node; The parameter sequence combination submodule is used to serialize the state parameter sets of all spatial nodes in each time period in the order of spatial partition and time index to generate a multi-dimensional parameter matrix, and perform multi-dimensional statistics on the various state parameter data therein to generate a multi-region state parameter set of the belt.

[0024] In an embodiment of the present invention, the digital twin construction module can construct a virtual model that corresponds one-to-one to the actual conveyor belt structure based on the monitoring location and conveyor belt structure information in the analysis data, and make the attributes of each spatial node consistent with the actual monitoring point through initialization operation. Through the data mapping submodule, the analysis data is mapped to the corresponding spatial node and time index in the virtual model according to the preset spatial partition and time period, so that each spatial node can obtain a complete original data sequence in different time periods, achieving full coverage and dynamic update of the space-time dimension. The parameter extraction submodule can perform multidimensional statistical analysis such as extreme value, mean and change rate on the original data sequence of each spatial node, so as to obtain a state parameter set that can accurately reflect the operating status of the conveyor belt. The parameter sequence combination submodule further arranges the state parameter sets of all spatial nodes in each time period in sequence, and generates a multidimensional parameter matrix, and extracts the operation and wear characteristic parameters of multiple regions of the belt through multidimensional statistics. In this way, the system can not only realize the traceability analysis of the history and current status of each monitoring point, but also support subsequent abnormality identification, prediction and decision-making. For example, during actual operation, the average value of a spatial partition gradually decreases over multiple consecutive time periods, while the rate of change increases. The system can promptly capture this abnormal trend through parameter matrix analysis, providing a solid data foundation for subsequent anomaly identification and risk warning.

[0025] The virtual model construction submodule is used to generate a virtual model corresponding to the conveyor belt structure based on the monitoring location and conveyor belt structure information in the analysis data, and initialize the attributes of each spatial node, including: First, based on data from on-site monitoring locations and incorporating basic design parameters such as the conveyor belt's structural dimensions, orientation, segmentation, and connection methods, a conveyor belt skeleton model is constructed in virtual space. For example, a 3D modeling tool or a proprietary digital modeling program can be used to generate model nodes and connections for each key component of the physical belt (such as belt segments, turning points, and connection joints) in virtual space. For each virtual model node, the system locates it according to the spatial coordinates of the actual monitoring location and assigns attribute parameters consistent with its physical location, including spatial coordinates, number, node type (e.g., edge, center, joint), and initialization time. For the entire belt structure, all nodes are connected sequentially according to the actual layout order, and inter-node attributes such as distances and angles are set according to design parameters. If the belt is divided into multiple spatial zones or has different structural features, the system can assign unique attribute sets to each zone. Once modeled, each node in the virtual model has a unique number and spatial coordinates, supporting subsequent dynamic data mapping and real-time attribute updates. For example, along a 500-meter-long belt, a monitoring position is set up every 5 meters. The virtual model includes 100 spatial nodes, and the attributes of each node completely correspond to the actual monitoring points on site.

[0026] The data mapping submodule is used to map the analysis data to the corresponding spatial nodes and time indexes in the virtual model according to the preset spatial partitions and time periods, and to update the original data sequence of each spatial node in different time periods. Specifically, it includes: The system first groups all actual monitoring locations according to the preset spatial partitioning rules. For example, several consecutive monitoring points along the belt direction are divided into the same spatial partition; the nodes within each partition are numbered in order of their physical location. For analytical data, the system divides all data into multiple time periods in chronological order according to the set grouping interval of the acquisition time (such as every 1 minute, every 10 minutes, or customized according to process requirements), and assigns a unique time index number to each time period. Subsequently, the system traverses each spatial partition and each time period, and assigns or links the original physical signal data and image data signals collected by each monitoring node in the spatial partition during the corresponding time period to the corresponding spatial nodes and time indexes in the virtual model to form the original data sequence. For nodes and time periods with missing data or collection anomalies, interpolation or historical averaging can be used to supplement the data to ensure that each node and each time period has a complete original data sequence record. For example, if the belt is running for one day and a time period is divided every 10 minutes, each spatial node will correspond to 144 time indexes. The system will automatically fill in various types of analysis data collected during these 144 time periods into the virtual model nodes in sequence, laying the foundation for subsequent parameter extraction and anomaly analysis.

[0027] In a preferred embodiment of the present invention, the anomaly identification module includes: The parameter sequence analysis submodule is used to analyze the state parameter sequences of each spatial partition in different time periods based on the multi-region state parameter set of the belt, calculate the parameter change rate at adjacent time points, and compare it with the preset abnormal threshold to generate a candidate set of abnormal state parameters; The cluster identification submodule is used to cluster the candidate set of abnormal state parameters according to spatial proximity and change characteristics, identify spatial partition areas with similar abnormal characteristics, and generate clustered abnormal partition sets; The anomaly localization submodule is used to calibrate the anomaly location and time period based on the clustered anomaly partition set, combined with the spatial partition and time period information, to form an anomaly recognition result.

[0028] In an embodiment of the present invention, the abnormality identification module uses the parameter sequence analysis submodule to gradually analyze the state parameter sequences of each spatial partition and different time periods in the multi-region state parameter set of the belt, and calculates the parameter change rate of adjacent time points in sequence, effectively identifying parameter fluctuation anomalies and trend changes. Furthermore, the clustering identification submodule can cluster in the spatial and feature dimensions based on the abnormal state parameter candidate set, and classify spatial partition areas with similar abnormal characteristics into the same group, which significantly improves the accuracy and pertinence of abnormality identification. After obtaining the clustered abnormality partition set, the abnormality positioning submodule can combine the spatial partition and time period information to accurately calibrate the location and time period of the abnormality, ensuring that the abnormal information is located in a specific monitoring area and time period. For example, in actual application scenarios, if a certain area continues to have an abnormal parameter change rate for a period of time, the module can automatically identify it as an abnormal partition and clarify the specific location, and finally form an abnormality identification result, providing a scientific basis for subsequent warning and maintenance, and effectively reducing the risk of failure caused by wear and maintenance blind spots.

[0029] In a preferred embodiment of the present invention, the parameter extraction submodule includes: An extreme value calculation unit is used to determine the maximum and minimum values ​​of all sampled values ​​according to the original data sequence of each spatial node in each time period, and output the maximum and minimum values ​​as extreme value parameters corresponding to the spatial position and time index of the spatial node respectively; The mean calculation unit is used to accumulate all the sampled values ​​in the original data sequence of each spatial node in each time period and divide them by the number of samples to obtain an average value parameter. The average value is output in a one-to-one correspondence with the spatial position and time index of the spatial node; A change rate calculation unit is used to calculate the difference of all adjacent sampling values ​​in sequence according to the original data sequence of each spatial node in each time period to obtain a difference sequence, and divide the sum of the absolute values ​​of the difference sequence by the number of differences to obtain a change rate parameter. The change rate parameter is output in a one-to-one correspondence with the spatial position and time index of the spatial node; The parameter aggregation unit is used to uniformly aggregate extreme value parameters, average value parameters and change rate parameters according to the spatial position and time index of each spatial node to form a state parameter set for each spatial node and each time period.

[0030] In an embodiment of the present invention, the parameter extraction submodule can perform multi-dimensional feature extraction on the original data sequence of each spatial node in each time period through the extreme value calculation unit, the mean calculation unit and the change rate calculation unit. The system can not only obtain the maximum and minimum values ​​to reflect the operating limits, but also obtain the average value to reflect the overall operating level, and identify the dynamic trend of data changes through the change rate index. The parameter collection unit uniformly collects the above parameter results according to the spatial position and time index of the spatial node, effectively ensuring that all feature data of each spatial node and each time period can be fully retained and subsequently traced. This technical solution can digitize and standardize the operating status of each monitoring point in any time period, greatly improving the efficiency and accuracy of subsequent statistics, comparison and analysis. For example, when the maximum value of a node along a certain section of the conveyor belt continues to decrease and the change rate suddenly increases, the system can directly locate the node and the specific time period, so that the operation and maintenance personnel can pay attention to it in advance and take maintenance measures to reduce the risk of equipment failure.

[0031] In a preferred embodiment of the present invention, the parameter sequence combination submodule includes: The sequence arrangement unit is used to arrange the state parameter sets of all spatial nodes in each time period in sequence according to the spatial partition position order and the increasing order of time index to generate a multi-dimensional parameter matrix; The multidimensional statistical unit is used to perform statistics on various state parameter data in the multidimensional parameter matrix according to the following steps: For each spatial partition, according to the time index order, for the same state parameters, calculate the mean, range, and maximum continuous increasing interval length of each time period to generate the partition time series statistics; For the same state parameters of all spatial partitions under each time index, calculate the spatial maximum, minimum, mean and standard deviation at that time point and generate the corresponding spatial statistical results; The parameter integration unit is used to merge the time series statistical results of all spatial partitions and the spatial statistical results of each time period according to the two dimensions of spatial partition and time, and form a multi-region belt state parameter set indexed by spatial partition and time.

[0032] In this embodiment of the present invention, the parameter sequence combination submodule first uses the sequence arrangement unit to sequentially arrange the state parameter sets of all spatial nodes in each time period in the order of spatial partition positions and ascending time indexes, generating a multidimensional parameter matrix. This matrix systematically represents the spatial and temporal operational status of the entire conveyor belt. The multidimensional statistics unit then applies various statistical analyses to this parameter matrix, including mean, range, and maximum continuous increment interval length, to further explore the dynamic characteristics of each spatial partition during operation. Furthermore, the multidimensional statistics unit calculates the maximum, minimum, mean, and standard deviation of the spatial distribution of the state parameters of all spatial partitions at each time point, enabling horizontal comparison and global fluctuation assessment. The parameter integration unit then merges these statistical results based on spatial partitions and time, ultimately forming a multi-region belt state parameter set indexed by spatial partitions and time. This provides structured, quantifiable, and multidimensional foundational data for subsequent anomaly identification and trend assessment. For example, this parameter set can allow maintenance personnel to identify areas with unusually widening extremes or significantly increased standard deviations over a period of time, thereby proactively identifying potential abnormal evolution trends in that area.

[0033] The sequence arrangement unit is used to arrange the state parameter sets of all spatial nodes in each time period in sequence according to the spatial partition position order and the ascending order of time index to generate a multi-dimensional parameter matrix, which specifically includes: First, the system determines the physical location order of all spatial nodes based on the virtual model and spatial partitioning settings. For example, they can be numbered according to the actual layout sequence from the start to the end of the belt. Subsequently, the extracted state parameters (such as maximum, minimum, average, and rate of change) for each node during different time periods are summarized. For each time period, the system arranges the state parameters of all nodes within the same time period in the order of their spatial node positions, forming a row of data. Multiple rows of data correspond to multiple consecutive time periods. These rows are then concatenated in ascending order of time index, ultimately generating a parameter matrix in both spatial and temporal dimensions. Each column of this matrix corresponds to a spatial node, and each row to a time period. Each matrix element represents a specific state parameter for a specific spatial node during a specific time period. This structured mapping of the entire conveyor belt's operating status over a period of time is then mapped into a multidimensional data table, facilitating subsequent batch processing and analysis. For example, if a belt has 20 spatial nodes and the analysis period is 100 time periods, the system can generate a 20-column x 100-row parameter matrix, providing an efficient data organization for big data analysis and trend identification.

[0034] Among them, the multidimensional statistical unit is used to perform statistics on various state parameter data in the multidimensional parameter matrix according to the following steps: for each spatial partition, in the order of time index, for similar state parameters, calculate the mean, range, and maximum continuous increasing interval length of each time period to generate partition time series statistical results; for similar state parameters of all spatial partitions under each time index, calculate the spatial maximum, minimum, mean, and standard deviation at that time point to generate corresponding spatial statistical results, specifically including: For partitioned time series statistics, the system traverses similar state parameters (e.g., the average value series for all nodes) for each spatial partition across all time periods. For each parameter type, the system first calculates its value across all time periods within the partition to obtain the average value for all time periods. The system then compares the maximum and minimum values ​​of the parameter across all time periods and subtracts them to obtain the range. For the maximum continuous increment interval length, the system traverses the state parameter time series for each partition from the beginning, records the length of each continuous increment interval, and selects the longest interval length as the maximum increment interval for that parameter in that partition. For spatial statistics, within each time period, the system compares the maximum and minimum values ​​of similar state parameters across all spatial partitions, calculates the average value for that parameter across all partitions, and then calculates the square root of the difference between each partition's parameter and the average value. This statistical method reveals the central tendency, extreme fluctuations, and overall dispersion of state parameters across different spaces and time periods. For example, in a certain statistics, if the average value of a certain partition increases continuously over multiple time periods and the range is large, the system can determine that the wear of the partition is tending to intensify; if the parameter standard deviation of multiple spatial partitions at the same time is large, it means that the overall operating status is discrete and requires operation and maintenance attention.

[0035] The parameter integration unit is used to merge the time series statistics of all spatial partitions and the spatial statistics of each time period according to the spatial partition and time dimensions to form a multi-region belt status parameter set indexed by spatial partition and time, including: The system reorganizes the time series statistics output by the multidimensional statistics unit for each partition (such as the mean, range, and maximum increment interval length for each partition across all time periods) and the spatial statistics for each time period (such as the maximum, minimum, mean, and standard deviation for each partition at that moment) by partition number and time index. For each spatial partition, the system organizes all relevant time series statistical parameters using the time index as the horizontal axis to form the multidimensional time series characteristics of that partition. For each time period, the system organizes all spatial statistical parameters using the spatial partition as the horizontal axis to form the spatial distribution characteristics at that moment. Ultimately, all these structured parameter sets are combined into a multi-zone belt status parameter set using the "spatial partition - time period" two-dimensional index. This dataset not only provides the data foundation for subsequent anomaly detection and trend analysis, but can also be easily exported for further analysis by external systems or experts. For example, operations and maintenance engineers can use this parameter set to quickly trace the historical status of any partition at any moment or compare the operating differences of multiple partitions within the same time period, improving the scientific and accurate wear monitoring.

[0036] In a preferred embodiment of the present invention, the parameter sequence analysis submodule includes: A change rate calculation unit is used to calculate the difference of the state parameters at adjacent time indexes for each spatial partition state parameter sequence, and divide the sum of the absolute values ​​of all differences by the number of differences to obtain the change rate sequence of the spatial partition on the state parameter; The threshold comparison unit is used to compare each change rate value in the change rate sequence with the preset abnormality judgment threshold. If the change rate value is greater than the abnormality judgment threshold, the corresponding spatial partition, time index and state parameter are marked as abnormal candidates to generate an abnormal state parameter candidate set.

[0037] In an embodiment of the present invention, the parameter sequence analysis submodule uses a rate of change calculation unit to perform a point-by-point analysis on the state parameter sequence of each spatial partition, calculate the parameter difference between adjacent time points, and obtain a rate of change sequence, thereby realizing continuous monitoring and sensitive capture of parameter changes in the time dimension. The threshold comparison unit strictly compares each rate of change with a preset abnormality judgment threshold. Once the rate of change is found to be greater than the threshold, it can be automatically marked as an abnormal candidate, effectively reducing the subjectivity and risk of omissions in manual judgment. This automated analysis and screening method can quickly and accurately screen out abnormal trends or mutations hidden in massive monitoring data, greatly improving the intelligence and real-time performance of wear monitoring of large-scale conveying systems. For example, during the operation of a conveyor belt, if the rate of change of a certain spatial partition exceeds the set threshold for multiple consecutive times, the system can immediately mark the parameters of the partition in the relevant time period as abnormal candidates, and the operation and maintenance personnel can intervene in time to investigate and effectively avoid major production stoppages caused by worsening wear.

[0038] The preset abnormality determination threshold refers to the reference standard for determining whether the rate of change of the state parameter constitutes an abnormality, specifically including: Before the system is deployed, one or more thresholds for abnormality detection can be established based on historical operational data, expert experience, or field conditions. Typically, engineers analyze a large amount of data from both normal operation and known abnormal cases, compiling statistics on the maximum fluctuation, mean, and standard deviation of the rate of change of each parameter under normal conditions. Based on these statistical results, a reasonable threshold is set. For example, the mean of the normal rate of change plus twice the standard deviation can be used as a criterion. Alternatively, the threshold can be set by the equipment manufacturer or maintenance experts based on safety requirements. When the rate of change calculated by the system in real time exceeds this threshold, a potential abnormality is identified. These thresholds can be set for different parameter types (such as maximum value, mean value, and rate of change) and can be regularly optimized and adjusted based on different operating environments. For example, during high-load operation, the rate of change threshold for a wear parameter can be relaxed to prevent false alarms; while during low-load conditions or critical equipment inspections, the threshold can be tightened to increase abnormality detection sensitivity. The system supports regular, manual or automatic threshold calibration to ensure that abnormality detection is both accurate and tailored to actual field needs.

[0039] In a preferred embodiment of the present invention, the cluster identification submodule includes: The spatial clustering unit is used to take the abnormal state parameters with adjacent spatial positions as the same initial cluster according to the abnormal state parameter candidate set to generate an initial spatial cluster set; The feature similarity discrimination unit is used to classify the abnormal points with the same abnormal state parameter type and change direction according to the state parameter type and change characteristics in each initial spatial cluster according to the initial spatial cluster cluster set, and obtain feature consistency subclusters; The cluster merging unit is used to judge the spatial distance and parameter change amplitude between feature consistency subclusters. If the spatial distance is less than the preset spatial distance threshold and the change amplitude is less than the preset absolute difference threshold, the feature consistency subclusters that meet the conditions will be merged into cluster partitions to form a cluster anomaly partition set.

[0040] In this embodiment of the present invention, the cluster identification submodule, through a spatial clustering unit, automatically groups spatially adjacent abnormal parameters into initial spatial clusters based on a candidate set of abnormal parameters, enabling automated detection of spatially correlated anomalies in large-scale monitoring data. The feature similarity discrimination unit further subdivides the abnormal parameters within the clusters, categorizing them by parameter type and variation characteristics. This ensures that only anomalies with consistent characteristics are aggregated, effectively improving the homogeneity and interpretability of the anomaly partitions. The cluster merging unit determines the spatial distance and parameter variation amplitude of feature-consistent subclusters, merging subclusters with spatial distances less than a preset threshold and similar parameter variation amplitudes into larger cluster partitions, ultimately forming a clustered abnormal partition set. This series of processes enables the system to not only quickly identify single-point anomalies but also accurately locate and summarize multiple spatially adjacent abnormal regions with similar characteristics, facilitating a comprehensive understanding of the overall operating status of bulk material conveyor belts. For example, when parameters at multiple monitoring points in a certain belt section exhibit similar anomalies and are spatially close to each other, the system can automatically cluster them into a large-scale wear anomaly partition, providing a scientific basis for equipment maintenance and risk stratification.

[0041] The spatial clustering unit is used to take the abnormal state parameters with adjacent spatial positions as the same initial cluster according to the abnormal state parameter candidate set to generate an initial spatial cluster set, specifically including: The system first arranges all spatial nodes or partitions marked as abnormal in order of their spatial positions. For spatial nodes with abnormalities detected at adjacent positions at the same time, the system automatically classifies them into the same initial cluster. For example, if the abnormal state parameters of the belt's No. 8, 9, and 10 spatial nodes are all abnormal, and the three are physically connected, then these three nodes are merged into an initial spatial cluster. For abnormal nodes with intervals in their physical positions, the system determines whether their spacing exceeds the spatial distance threshold (see below). If so, they are divided into different initial clusters. This method refers to the existing segmented clustering technology in the field of geographic information clustering and industrial monitoring, and realizes automatic grouping of spatial anomalies by traversing the abnormal point groups in spatial order. The initial spatial cluster can provide a basis for subsequent feature similarity judgment and further merging processing, significantly improving the flexibility and adaptability of spatial anomaly identification.

[0042] The preset spatial distance threshold refers to the spatial distance threshold used to determine whether two feature-consistent subclusters or abnormal spatial nodes can be classified into the same cluster partition, specifically including: Before deployment, the system sets a spatial distance upper limit based on the actual length of the conveyor belt, the density of monitoring nodes, and on-site engineering requirements. This threshold can typically be an integer multiple of the distance between adjacent monitoring nodes, or the maximum physical distance typically observed for the same type of anomaly in historical data statistics. For example, if the center-to-center distance between two anomaly nodes is less than the set 10 meters, they are considered physically related and can be clustered into the same partition. If the distance is greater than the threshold, they are considered to belong to different spatial anomalies and are handled separately. The spatial distance can be calculated based on the physical distance between nodes, the actual layout of the conveyor path, or latitude and longitude / three-dimensional coordinates. This threshold should be customizable by on-site engineers and dynamically adjustable based on equipment operation, monitoring density, and spatial distribution. Properly setting the spatial distance threshold prevents the mis-clustering of spatially unrelated anomalies while ensuring the accurate identification of spatially continuous anomalies.

[0043] The preset absolute difference threshold refers to the threshold used to determine whether the parameter change amplitude of each feature consistency sub-cluster can be considered consistent during the clustering process. Specifically, it includes: After the initial spatial clustering, the system calculates the average parameter change amplitude for each group of spatially adjacent feature consistency subclusters. For example, the average value of all abnormal state parameters in each subcluster is taken, and then the mean difference between different subclusters is compared. The preset absolute difference threshold is the standard for determining whether the amplitudes of these parameter changes are close enough. If the difference in the average change amplitudes of two subclusters is lower than the threshold, they are considered to have a high degree of consistency in parameter changes and can be further merged into a larger cluster partition. If the threshold is exceeded, it means that the abnormal characteristics may have different sources, and it is more reasonable to cluster them separately. The setting of this threshold can be determined in combination with historical wear data analysis, equipment safety specifications and operation and maintenance experience, and dynamically adjusted according to the actual monitoring object. By reasonably setting the absolute difference threshold, it can be ensured that only abnormal points with similar change amplitudes are clustered together, thereby improving the homogeneity and reliability of the clustering results.

[0044] In a preferred embodiment of the present invention, the abnormality locating submodule includes: An abnormal interval determination unit is used to extract the spatial partition range and corresponding time range of each cluster partition according to the cluster abnormal partition set, and generate abnormal interval information; The abnormality type determination unit is used to extract the corresponding state parameters based on the abnormal interval information and analyze its change characteristics over time. If the abnormality persists throughout the entire time range, it is determined to be continuous wear. If a sudden change occurs at a certain moment, it is determined to be sudden wear. If the change shows regular fluctuations, it is determined to be a periodic abnormality and generates abnormality type information; The abnormality identification result generating unit is used to generate and output the abnormality identification result according to the spatial partition range, time range and abnormality type information of each abnormal interval.

[0045] In an embodiment of the present invention, the abnormality positioning submodule first automatically extracts the spatial partition range and corresponding time range of each cluster partition according to the cluster abnormality partition set through the abnormal interval determination unit, and accurately locks the specific interval where the abnormality occurs. The abnormality type determination unit analyzes the change pattern of the state parameters in each abnormal interval over time, and can intelligently distinguish different types such as continuous wear, sudden wear or periodic abnormalities, and realize automatic judgment of the nature of the abnormality. The abnormality identification result generation unit automatically generates a complete abnormality identification result based on the identified spatial partition range, time range and abnormality type information, and outputs it to the subsequent early warning link. This process can ensure that the system can fully automate and refine the classification and positioning of abnormalities with complex spatial and temporal changes, significantly improving operation and maintenance efficiency and emergency response speed. For example, in actual applications, the system can not only determine that a certain spatial partition is continuously worn within a specific time period, but also indicate its specific type, continuous interval and evolution trend, providing decision support for on-site personnel decision-making and remote monitoring.

[0046] The abnormal interval determination unit is used to extract the spatial partition range and corresponding time range of each cluster partition based on the cluster abnormal partition set, and generate abnormal interval information, specifically including: After obtaining a clustered anomaly partition set, the system first searches for all spatial partition numbers and associated time period numbers within each clustered anomaly partition. For spatial partition ranges, the system searches for the spatial nodes with the smallest and largest partition numbers in order of spatial partition numbers to determine the start and end locations of the anomaly area on the belt. For time ranges, the system searches for all time period numbers within the clustered partition, identifying the earliest and latest time points and the interval in which the anomaly occurred. By traversing all clustered partitions, the system automatically organizes and archives the spatial start and end partitions and time start and end segments of each anomaly area, generating structured anomaly interval information. This anomaly interval information includes not only the anomaly partition number range and start and end times, but also further records the anomaly type and parameter characteristics within the interval, facilitating subsequent type determination and anomaly notification. For example, in a conveyor operation, if a clustered anomaly partition set includes spatial partitions 5 to 8 and time periods 10 to 14, the system combines these segments and time periods into a single anomaly interval and associates the anomaly parameters to ensure accurate location and efficient processing.

[0047] In a preferred embodiment of the present invention, the feature similarity determination unit includes: The parameter type grouping unit is used to classify the abnormal state parameters in each cluster according to the parameter type according to the initial spatial clustering cluster set to form parameter type groups; The change trend analysis unit is used to determine whether the change directions of the abnormal state parameters in each parameter type group are consistent based on the changes in their parameter values ​​in adjacent time periods. If they are consistent, they are classified into the same trend group. If they are inconsistent, the abnormal state parameters with different change directions are divided into new trend groups and classified separately; The amplitude consistency screening unit is used to calculate the change amplitude of each parameter in each trend group for the abnormal state parameters, and compare it with the average change amplitude in the group. If the difference between the change amplitude of the parameter and the average value in the group is less than the preset amplitude difference threshold, the parameter is retained; otherwise, it is eliminated, and finally a feature consistency subcluster is generated.

[0048] In this embodiment of the present invention, the feature similarity determination unit, through a parameter type grouping unit, a change trend analysis unit, and an amplitude consistency screening unit, enables a multi-level, multi-angle, and detailed screening of abnormal state parameters within the initial spatial clustering set. The parameter type grouping unit first categorizes different types of abnormal state parameters, ensuring that subsequent analysis is performed only on parameters of the same type, thus avoiding feature confusion. The change trend analysis unit identifies and classifies abnormal parameters with consistent or different change directions. Through dynamic trend discrimination, parameters with the same change trend are grouped into the same trend group. The amplitude consistency screening unit compares the change amplitude of parameters within a trend group with the group average, retaining only abnormal parameters with consistent amplitudes, ultimately forming high-purity feature consistency subclusters. This technical solution effectively filters out "false anomalies" in spatial distribution and feature expression, significantly improving the homogeneity of cluster partitioning and the accuracy of discrimination. For example, in actual monitoring, if a cluster contains a few interfering points with abnormal fluctuations, the system can automatically remove these interfering points through the above screening process and output only the most representative abnormal feature groups, significantly reducing false positives and false negatives.

[0049] The preset amplitude difference threshold refers to the limiting standard used to determine the difference between the amplitude of each abnormal state parameter change and the average value within the group in the process of feature similarity determination, specifically including: When screening each trend group for amplitude consistency, the system first calculates the amplitude of change of all abnormal state parameters in the group, and then calculates the average amplitude of change of the group. Next, the actual amplitude of change of each abnormal state parameter is compared with the average amplitude of change of the group, and the difference between the two is calculated. If this difference is less than the preset amplitude difference threshold, the parameter is considered to be highly consistent with the change trend within the group and can be retained in the group; otherwise, it is considered that the change characteristics do not match and it is removed from the trend group. The setting of the amplitude difference threshold usually relies on historical monitoring data analysis and expert experience. For example, within the normal wear fluctuation range, the amplitude difference threshold is set to a certain proportion of the historical average change amplitude, which can avoid misjudgment due to individual abnormal fluctuations. By reasonably setting and dynamically adjusting the amplitude difference threshold, the system can effectively screen out abnormal state parameters that perform consistently in the same trend group, and improve the homogeneity and reliability of the clustering results.

[0050] In a preferred embodiment of the present invention, the cluster merging unit includes: The spatial distance determination unit is used to calculate the distance between the central spatial partitions of each sub-cluster based on the feature consistency sub-clusters. If the distance is less than the spatial distance threshold, the corresponding sub-cluster is classified as a mergeable object; A change amplitude determination unit is used to calculate the average parameter change amplitude of each sub-cluster in each group of mergeable objects, and then calculate the absolute difference of the average change amplitudes between the groups. If the absolute difference is less than the absolute difference threshold, it is determined that the sub-cluster corresponding to the group meets the merging condition; The merging generation unit is used to merge the feature consistency subclusters that meet both the spatial distance threshold and the absolute difference threshold into a cluster partition. The set of all cluster partitions constitutes the cluster anomaly partition set. In an embodiment of the present invention, the cluster merging unit realizes the intelligent aggregation of feature consistency subclusters through the spatial distance determination unit, the variation amplitude determination unit and the merging generation unit. The spatial distance determination unit can calculate the distance of the central spatial partition position of all feature consistency subclusters, and automatically identify the subclusters whose spatial distance is less than the set threshold as mergeable objects, thereby ensuring that the aggregation only occurs between abnormal groups that are physically close enough. The variation amplitude determination unit further analyzes the average parameter variation amplitude of these mergeable objects and calculates the absolute difference between the groups. Only when the difference is lower than the preset absolute difference threshold, it is determined that the parameter features are highly consistent, ensuring the consistency and reliability of the cluster partition in the expression of abnormal features. Based on this, the merging generation unit merges the feature consistency subclusters that meet the conditions of spatial distance and parameter amplitude into a cluster partition. All cluster partition sets eventually form a cluster abnormal partition set and serve as the basic data for subsequent abnormality positioning.

[0051] Through the above process, the system not only achieves the coordinated aggregation of spatial and feature dimensions of abnormal data, but also prevents anomalies with dispersed physical locations or large parameter feature differences from being misclassified, effectively improving the accuracy and engineering usability of clustered anomaly partitioning. In practical applications, if multiple monitoring nodes in a certain area of ​​the belt are spatially adjacent and have very similar parameter variation amplitudes, the system can automatically merge the anomalies of these nodes into the same cluster partition and include them in the clustered anomaly partition set. This greatly facilitates subsequent analysis, tracing, and early warning response of the anomaly partition, thereby contributing to precise maintenance and risk management.

[0052] The above is a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present invention. These improvements and modifications should also be regarded as within the scope of protection of the present invention.

Claims

1. A bulk material conveyor belt wear monitoring system integrating digital twin, characterized by: The system comprises: A sensor data acquisition module is used to collect raw data during the operation of the conveyor belt at multiple monitoring locations along the conveyor belt, wherein the raw data includes physical signal data and image data signals; The data preprocessing module is used to format, reduce noise and calibrate the raw data to obtain analytical data; The digital twin construction module is used to dynamically generate a virtual model of the conveyor belt based on the analysis data, map the analysis data to the corresponding areas of the preset virtual model according to the spatial and temporal dimensions, and obtain the multi-region state parameter set of the belt; The anomaly recognition module is used to perform partition detection on the wear characteristics of each monitoring area of ​​the belt based on the multi-area state parameter set of the belt, identify and locate local areas with abnormal change trends, and obtain anomaly recognition results; The early warning trigger module is used to generate early warning information including the abnormal location and wear degree based on the abnormality identification results, and output it to the host computer or operation and maintenance terminal.

2. The bulk material conveyor belt wear monitoring system integrating digital twin according to claim 1 is characterized in that: The digital twin building blocks include: The virtual model construction submodule is used to generate a virtual model corresponding to the conveyor belt structure according to the monitoring position and conveyor belt structure information in the analysis data, and initialize the attributes of each spatial node; The data mapping submodule is used to map the analysis data to the corresponding spatial nodes and time indexes in the virtual model according to preset spatial partitions and time periods, and to update the original data sequence of each spatial node in different time periods. The spatial partitions are groupings of monitoring locations along the belt, the time periods are groupings of analysis data collection times, and the time indexes are numberings of time periods. The parameter extraction submodule is used to calculate the maximum value, minimum value, average value and rate of change of each spatial node through its original data sequence, and to correspond them to the spatial position and time index of the spatial node one by one to generate the state parameter set of the spatial node; The parameter sequence combination submodule is used to serialize the state parameter sets of all spatial nodes in each time period in the order of spatial partition and time index to generate a multi-dimensional parameter matrix, and perform multi-dimensional statistics on the various state parameter data therein to generate a multi-region state parameter set of the belt.

3. The bulk material conveyor belt wear monitoring system integrating digital twin according to claim 1 is characterized in that: The abnormality identification module includes: The parameter sequence analysis submodule is used to analyze the state parameter sequences of each spatial partition in different time periods based on the multi-region state parameter set of the belt, calculate the parameter change rate at adjacent time points, and compare it with the preset abnormal threshold to generate a candidate set of abnormal state parameters; The cluster identification submodule is used to cluster the candidate set of abnormal state parameters according to spatial proximity and change characteristics, identify spatial partition areas with similar abnormal characteristics, and generate clustered abnormal partition sets; The anomaly localization submodule is used to calibrate the anomaly location and time period based on the clustered anomaly partition set, combined with the spatial partition and time period information, to form an anomaly recognition result.

4. The bulk material conveyor belt wear monitoring system integrating digital twin according to claim 2 is characterized in that: The parameter extraction submodule includes: An extreme value calculation unit is used to determine the maximum and minimum values ​​of all sampled values ​​according to the original data sequence of each spatial node in each time period, and output the maximum and minimum values ​​as extreme value parameters corresponding to the spatial position and time index of the spatial node respectively; The mean calculation unit is used to accumulate all the sampled values ​​in the original data sequence of each spatial node in each time period and divide them by the number of samples to obtain an average value parameter. The average value is output in a one-to-one correspondence with the spatial position and time index of the spatial node; A change rate calculation unit is used to calculate the difference of all adjacent sampling values ​​in sequence according to the original data sequence of each spatial node in each time period to obtain a difference sequence, and divide the sum of the absolute values ​​of the difference sequence by the number of differences to obtain a change rate parameter. The change rate parameter is output in a one-to-one correspondence with the spatial position and time index of the spatial node; The parameter aggregation unit is used to uniformly aggregate extreme value parameters, average value parameters and change rate parameters according to the spatial position and time index of each spatial node to form a state parameter set for each spatial node and each time period.

5. The bulk material conveyor belt wear monitoring system integrating digital twin according to claim 2 is characterized in that: The parameter sequence combination submodule includes: The sequence arrangement unit is used to arrange the state parameter sets of all spatial nodes in each time period in the order of spatial partition positions and the ascending order of time indexes to generate a multi-dimensional parameter matrix; The multidimensional statistical unit is used to perform statistics on various state parameter data in the multidimensional parameter matrix according to the following steps: For each spatial partition, according to the time index order, for the same state parameters, calculate the mean, range, and maximum continuous increasing interval length of each time period to generate the partition time series statistics; For the same state parameters of all spatial partitions under each time index, calculate the spatial maximum, minimum, mean and standard deviation at that time point and generate the corresponding spatial statistical results; The parameter integration unit is used to merge the time series statistical results of all spatial partitions and the spatial statistical results of each time period according to the two dimensions of spatial partition and time, and form a multi-region belt state parameter set indexed by spatial partition and time.

6. The bulk material conveyor belt wear monitoring system integrating digital twin according to claim 3 is characterized in that: The parameter sequence analysis submodule includes: A change rate calculation unit is used to calculate the difference of the state parameters at adjacent time indexes for each spatial partition state parameter sequence, and divide the sum of the absolute values ​​of all differences by the number of differences to obtain the change rate sequence of the spatial partition on the state parameter; The threshold comparison unit is used to compare each change rate value in the change rate sequence with the preset abnormality judgment threshold. If the change rate value is greater than the abnormality judgment threshold, the corresponding spatial partition, time index and state parameter are marked as abnormal candidates to generate an abnormal state parameter candidate set.

7. The bulk material conveyor belt wear monitoring system integrating digital twin according to claim 3 is characterized in that: The cluster identification submodule includes: The spatial clustering unit is used to take the abnormal state parameters with adjacent spatial positions as the same initial cluster according to the abnormal state parameter candidate set to generate an initial spatial cluster set; The feature similarity discrimination unit is used to classify the abnormal points with the same abnormal state parameter type and change direction according to the state parameter type and change characteristics in each initial spatial cluster according to the initial spatial cluster cluster set, and obtain feature consistency subclusters; The cluster merging unit is used to judge the spatial distance and parameter change amplitude between feature consistency subclusters. If the spatial distance is less than the preset spatial distance threshold and the change amplitude is less than the preset absolute difference threshold, the feature consistency subclusters that meet the conditions will be merged into cluster partitions to form a cluster anomaly partition set.

8. The bulk material conveyor belt wear monitoring system integrating digital twin according to claim 3 is characterized in that: The abnormality locating submodule includes: An abnormal interval determination unit is used to extract the spatial partition range and corresponding time range of each cluster partition according to the cluster abnormal partition set, and generate abnormal interval information; The abnormality type determination unit is used to extract the corresponding state parameters based on the abnormal interval information and analyze its change characteristics over time. If the abnormality persists throughout the entire time range, it is determined to be continuous wear. If a sudden change occurs at a certain moment, it is determined to be sudden wear. If the change shows regular fluctuations, it is determined to be a periodic abnormality and generates abnormality type information; The abnormality identification result generating unit is used to generate and output the abnormality identification result according to the spatial partition range, time range and abnormality type information of each abnormal interval.

9. The bulk material conveyor belt wear monitoring system integrating digital twin according to claim 7 is characterized in that: The feature similarity determination unit includes: The parameter type grouping unit is used to classify the abnormal state parameters in each cluster according to the parameter type according to the initial spatial clustering cluster set to form parameter type groups; The change trend analysis unit is used to determine whether the change directions of the abnormal state parameters in each parameter type group are consistent based on the changes in their parameter values ​​in adjacent time periods. If they are consistent, they are classified into the same trend group. If they are inconsistent, the abnormal state parameters with different change directions are divided into new trend groups and classified separately; The amplitude consistency screening unit is used to calculate the change amplitude of each parameter in each trend group for the abnormal state parameters, and compare it with the average change amplitude in the group. If the difference between the change amplitude of the parameter and the average value in the group is less than the preset amplitude difference threshold, the parameter is retained; otherwise, it is eliminated, and finally a feature consistency subcluster is generated.

10. The bulk material conveyor belt wear monitoring system integrating digital twin according to claim 7, characterized in that: The cluster merging unit includes: The spatial distance determination unit is used to calculate the distance between the central spatial partitions of each sub-cluster based on the feature consistency sub-clusters. If the distance is less than the spatial distance threshold, the corresponding sub-cluster is classified as a mergeable object; A change amplitude determination unit is used to calculate the average parameter change amplitude of each sub-cluster in each group of mergeable objects, and then calculate the absolute difference of the average change amplitudes between the groups. If the absolute difference is less than the absolute difference threshold, it is determined that the sub-cluster corresponding to the group meets the merging condition; The merging generation unit is used to merge the feature consistency subclusters that meet both the spatial distance threshold and the absolute difference threshold into a cluster partition, and the set of all cluster partitions constitutes a cluster anomaly partition set.

Images