Coal belt running protection method and system based on data analysis

Abstract

The application discloses a coal conveying belt operation protection method and system based on data analysis, which comprises the following steps: acquiring and analyzing multi-dimensional operation monitoring data of the coal conveying belt to determine abnormal parameters; determining abnormal data features based on the data of the abnormal parameters, and determining the abnormal degree of the abnormal parameters based on the abnormal data features; fusing different abnormal parameters to obtain high-dimensional fused abnormal parameters, and determining the abnormal operation type of the coal conveying belt based on the high-dimensional fused abnormal parameters; determining the comprehensive abnormal degree of the high-dimensional fused abnormal parameters based on the abnormal degree of the abnormal parameters, and judging whether to perform operation protection on the coal conveying belt based on the comprehensive abnormal degree; determining the operation protection action of the coal conveying belt based on the comprehensive abnormal degree and the abnormal operation type, and protecting the operation of the coal conveying belt based on the operation protection action. The application determines the protection action of the coal conveying belt in advance through multi-dimensional data comprehensive quantitative analysis, realizes the leap from post-protection to intelligent pre-decision, and greatly improves the safety level of the operation of the coal conveying belt.

Description

Technical Field

[0001] This invention relates to the field of coal conveyor belt control technology, and in particular to a method and system for protecting the operation of coal conveyor belts based on data analysis. Background Technology

[0002] Coal conveyor belts, as core power equipment in bulk material conveying systems for thermal power generation, ports, mines, metallurgy, building materials, and chemicals, undertake the critical task of continuous and efficient material transport. Their operational status directly affects the continuity and safety of the entire production process. However, coal conveyor belts typically operate under harsh conditions of high load and continuous operation, with pervasive dust and intense noise, and their long distribution makes them highly susceptible to various malfunctions such as longitudinal belt tearing, belt misalignment, coal blockage, idler jamming, and fires. Accidents can lead not only to unplanned downtime and significant economic losses, but also potentially serious safety incidents such as personal injury or death.

[0003] Currently, traditional coal conveyor belt protection methods mainly rely on single-point, discrete sensors such as pull rope switches, belt misalignment switches, slippage detectors, and coal blockage switches. These protection devices are essentially switch-triggered, only activating when a fault occurs and develops to a certain extent. This is reactive protection, lacking the ability to detect and warn of early signs of faults. Furthermore, due to the complex on-site environment, the detection results of a single sensor are easily interfered with, leading to high false alarm or false alarm rates. Moreover, the information from different sensors is isolated, making comprehensive judgment impossible and hindering the provision of accurate fault type and severity assessments for operators. Summary of the Invention

[0004] To address the aforementioned technical problems, this invention provides a data analysis-based method and system for protecting the operation of coal conveyor belts, comprising: Acquire multidimensional operation monitoring data of the coal conveyor belt, analyze the multidimensional operation monitoring data, and identify abnormal parameters in the multidimensional operation monitoring data; Analyze the data of abnormal parameters, determine the characteristics of abnormal data, and determine the degree of abnormality of abnormal parameters based on the characteristics of abnormal data; Different abnormal parameters are fused to obtain high-dimensional fused abnormal parameters, and the abnormal operation type of the coal conveyor belt is determined based on the high-dimensional fused abnormal parameters; The comprehensive anomaly degree of the high-dimensional fused anomaly parameters is determined based on the anomaly degree of the anomaly parameters, and the operation protection of the coal conveyor belt is determined based on the comprehensive anomaly degree. The operation protection actions of the coal conveyor belt are determined based on the comprehensive degree of abnormality and the type of abnormal operation, and the operation of the coal conveyor belt is protected based on the operation protection actions.

[0005] Furthermore, the acquisition of multi-dimensional operation monitoring data of the coal conveyor belt, and the analysis of the multi-dimensional operation monitoring data to determine abnormal parameters in the multi-dimensional operation monitoring data, includes: Acquire multidimensional operation monitoring data of the coal conveyor belt and divide the multidimensional operation monitoring data into multiple parameter data groups according to parameter type; The current operating condition of the coal conveyor belt is determined based on multi-dimensional operation monitoring data, and the dynamic change baseline corresponding to each parameter data group is determined based on the operating condition. Data in each parameter data group that is not within the preset range of the dynamic change baseline is identified as abnormal data, and parameters in parameter data groups whose proportion of abnormal data exceeds the preset proportion value are identified as abnormal parameters in the multidimensional operation monitoring data.

[0006] Furthermore, the analysis of the abnormal parameter data, the determination of abnormal data characteristics, and the determination of the degree of abnormality of the abnormal parameters based on the abnormal data characteristics include: Identify the parameter data group corresponding to the abnormal parameters and the corresponding dynamic change baseline, and determine the proportion of abnormal data in the parameter data group; Construct a data change curve for the time progress based on the parameter data set, and calculate the deviation of the data change curve from the dynamic change baseline; The proportion and deviation of abnormal data are determined as abnormal data features of abnormal parameters, and the abnormality degree of each abnormal data feature is evaluated and valued to obtain the abnormality degree evaluation value of each abnormal data feature. The degree of abnormality of each abnormal data feature is calculated by summing the abnormality assessment values.

[0007] Furthermore, the process of fusing different abnormal parameters to obtain high-dimensional fused abnormal parameters, and determining the abnormal operation type of the coal conveyor belt based on the high-dimensional fused abnormal parameters, includes: Features of different anomaly parameters are extracted and the features of each anomaly parameter are fused to obtain high-dimensional fused anomaly parameters; The high-dimensional fusion anomaly parameters are input into the preset anomaly classification and identification model, and the preset anomaly classification and identification model outputs the abnormal operation type of the coal conveyor belt.

[0008] Furthermore, determining the comprehensive anomaly degree of the high-dimensional fused anomaly parameters based on the anomaly degree of the anomaly parameters includes: The degree of abnormality of the abnormal parameters is normalized to obtain the normalized value of the degree of abnormality of the abnormal parameters, and the weight of the abnormal parameters is determined based on the normalized value of the degree of abnormality. The degree of anomalousness of the anomalous parameters is calculated by weighting and summing the corresponding weights to obtain the comprehensive degree of anomalousness of the high-dimensional fused anomalous parameters.

[0009] Furthermore, determining the weights of the anomaly parameters based on the anomaly degree normalization value includes: A preset weight-abnormality normalization value interval correspondence is set in advance. For each abnormality normalization value interval, a corresponding preset weight is associated with it. Determine the normalized value of the abnormality degree of the abnormal parameter, and based on the mapping relationship between the normalized value interval of the abnormality degree to which the normalized value of the abnormality degree belongs and the corresponding relationship between the preset weight and the normalized value interval of the abnormality degree, select the preset weight corresponding to the normalized value interval of the abnormality degree as the weight of the abnormal parameter.

[0010] Furthermore, the determination of whether to implement operational protection for the coal conveyor belt based on the comprehensive degree of anomaly includes: Determine a pre-set anomaly threshold, and determine whether the coal conveyor belt needs to be protected based on the relationship between the comprehensive anomaly level of the high-dimensional fused anomaly parameters and the anomaly threshold. If the overall anomaly degree of the high-dimensional fusion anomaly parameters is less than the anomaly degree threshold, it is determined that no operational protection is required for the coal conveyor belt. If the overall anomaly degree of the high-dimensional fusion anomaly parameters is greater than or equal to the anomaly degree threshold, it is determined that the coal conveyor belt needs to be protected during operation.

[0011] Furthermore, the process of determining the operational protection actions of the coal conveyor belt based on the comprehensive degree of abnormality and the type of abnormal operation, and protecting the operation of the coal conveyor belt based on these operational protection actions, includes: The comprehensive abnormality level and abnormal operation type are input into the operation protection action model, and the operation protection action model outputs the operation protection action of the coal conveyor belt. The operation protection actions of the coal conveyor belt are converted into operation control commands, and the operation of the coal conveyor belt is adjusted and controlled according to the operation control commands in order to protect the operation of the coal conveyor belt.

[0012] Furthermore, the method for constructing the operational protection action model includes: Acquire historical multidimensional operation monitoring data of coal conveyor belts, and determine the historical comprehensive anomaly degree and historical anomaly operation type based on the historical multidimensional operation monitoring data and historical high-dimensional fusion anomaly parameters; Determine the historical operation protection actions corresponding to the historical comprehensive anomaly degree and historical anomaly operation type, and construct a dataset based on the historical comprehensive anomaly degree, historical anomaly operation type and historical operation protection actions; The dataset is divided into training and testing sets according to a preset ratio, and the training and testing sets are input into a preset neural network model for training to build an initial operation protection action model; The test set is input into the initial operation protection action model for testing until the initial operation protection action model meets the preset convergence condition, thus obtaining the operation protection action model.

[0013] This invention also provides a data analysis-based coal conveyor belt operation protection system, comprising: The acquisition module is used to acquire multi-dimensional operation monitoring data of the coal conveyor belt, analyze the multi-dimensional operation monitoring data, and determine abnormal parameters in the multi-dimensional operation monitoring data; The analysis module is used to analyze the data of abnormal parameters, determine the characteristics of abnormal data, and determine the degree of abnormality of abnormal parameters based on the characteristics of abnormal data. The determination module is used to fuse different abnormal parameters to obtain high-dimensional fused abnormal parameters, and to determine the abnormal operation type of the coal conveyor belt based on the high-dimensional fused abnormal parameters; The judgment module is used to determine the comprehensive anomaly degree of the high-dimensional fused anomaly parameters based on the anomaly degree of the anomaly parameters, and to determine whether to implement operation protection for the coal conveyor belt based on the comprehensive anomaly degree. The protection module is used to determine the operation protection actions of the coal conveyor belt based on the comprehensive degree of abnormality and the type of abnormal operation, and to protect the operation of the coal conveyor belt based on the operation protection actions.

[0014] Compared with existing technologies, the beneficial effects of the data analysis-based coal conveyor belt operation protection method and system of this invention are as follows: This invention acquires multi-dimensional operation monitoring data of coal conveyor belts and performs multi-level intelligent analysis on the data. First, it accurately identifies abnormal parameters, then deeply mines the characteristics of abnormal data and quantifies their degree of abnormality, and fuses abnormal parameters of different modes to construct high-dimensional fusion parameters, thereby accurately determining the type of abnormal operation. This invention calculates the overall anomaly degree of high-dimensional fusion parameters by comprehensively considering the anomaly degree of each anomaly parameter, and intelligently decides whether to trigger operational protection based on this. Furthermore, it automatically matches and executes the optimal protection action by combining the anomaly type and the overall degree of anomaly. This invention represents a leap from passive alarm by a single sensor to proactive early warning and tiered protection based on multi-source data. It significantly improves the accuracy and timeliness of anomaly identification, effectively reduces false alarms and missed alarms, enables early intervention in the early stages of a fault, and adopts differentiated protection strategies based on the severity of the anomaly to avoid unplanned downtime, ensuring the safe and stable operation of the coal conveyor belt. At the same time, it provides data support for predictive maintenance of equipment, comprehensively improving the intelligence level and operational efficiency of the coal conveying system. Attached Figure Description

[0015] Figure 1 This is a schematic diagram of the process structure of the coal conveyor belt operation protection method based on data analysis in an embodiment of the present invention; Figure 2 This is a schematic diagram of the composition of the coal conveyor belt operation protection system based on data analysis in an embodiment of the present invention. Detailed Implementation

[0016] The specific embodiments of this application will be described in further detail below with reference to the accompanying drawings and examples. The following examples are for illustrative purposes only and are not intended to limit the scope of the invention.

[0017] like Figure 1 As shown in the embodiments of this application, a data analysis-based method for protecting the operation of a coal conveyor belt is provided, comprising: S100: acquiring multi-dimensional operation monitoring data of the coal conveyor belt, analyzing the multi-dimensional operation monitoring data, and determining abnormal parameters in the multi-dimensional operation monitoring data; S200: analyzing the data of abnormal parameters, determining the abnormal data characteristics, and determining the degree of abnormality of the abnormal parameters based on the abnormal data characteristics; S300: fusing different abnormal parameters to obtain high-dimensional fused abnormal parameters, and determining the abnormal operation type of the coal conveyor belt based on the high-dimensional fused abnormal parameters; S400: determining the comprehensive degree of abnormality of the high-dimensional fused abnormal parameters based on the degree of abnormality of the abnormal parameters, and determining whether to perform operation protection on the coal conveyor belt based on the comprehensive degree of abnormality; S500: determining the operation protection action of the coal conveyor belt based on the comprehensive degree of abnormality and the abnormal operation type, and protecting the operation of the coal conveyor belt based on the operation protection action.

[0018] Furthermore, this invention acquires multi-dimensional operational monitoring data of the coal conveyor belt and performs multi-level intelligent analysis on the data. First, it accurately identifies abnormal parameters, then deeply mines the characteristics of abnormal data and quantifies their degree of abnormality. Abnormal parameters from different modalities are fused to construct high-dimensional fusion parameters, thereby accurately determining the type of abnormal operation. This invention calculates the comprehensive abnormality degree of the high-dimensional fusion parameters based on the abnormality degree of each abnormal parameter, and intelligently decides whether to trigger operational protection. Combining the abnormality type and comprehensive degree, it automatically matches and executes the optimal protection action. This invention achieves a leap from passive alarm by a single sensor to proactive early warning and hierarchical protection based on multi-source data, significantly improving the accuracy and timeliness of abnormality identification, effectively reducing false alarms and missed alarms, enabling early intervention at the fault initiation stage, and adopting differentiated protection strategies according to the severity of the abnormality to avoid unplanned downtime, ensuring the safe and stable operation of the coal conveyor belt. Simultaneously, it provides data support for predictive maintenance of equipment, comprehensively improving the intelligence level and operational efficiency of the coal conveying system.

[0019] In the embodiments of this application, a data analysis-based method for protecting the operation of a coal conveyor belt is provided. The method involves acquiring multi-dimensional operation monitoring data of the coal conveyor belt and analyzing the data to determine abnormal parameters. This includes: acquiring multi-dimensional operation monitoring data of the coal conveyor belt and dividing the data into multiple parameter data groups according to parameter type; determining the current operating condition of the coal conveyor belt based on the multi-dimensional operation monitoring data and determining the dynamic change baseline corresponding to each parameter data group based on the operating condition; identifying data in each parameter data group that is not within a preset range of the dynamic change baseline as abnormal data, and identifying parameters corresponding to parameter data groups whose abnormal data proportion exceeds a preset proportion as abnormal parameters in the multi-dimensional operation monitoring data.

[0020] Specifically, the system comprehensively acquires multi-dimensional operational monitoring data of the coal conveyor belt and scientifically divides it into multiple parameter data groups according to parameter types, such as vibration, temperature, and current. Based on this, the system intelligently identifies the current specific operating condition of the coal conveyor belt through comprehensive analysis of the multi-dimensional data, such as no-load, light-load, full-load, or variable-speed operation. For each operating condition, the system dynamically generates a baseline for the change of each parameter data group, replacing the traditional fixed threshold. By comparing the real-time data in each parameter group with the dynamic baseline under the corresponding operating condition, the system accurately identifies abnormal data points that exceed the preset range of the baseline and calculates the proportion of abnormal data in each parameter group. When the proportion of abnormal data in a certain parameter group exceeds the preset threshold, the parameter corresponding to that group is determined to be an abnormal parameter in the multi-dimensional operational monitoring data. This step enables adaptive perception of the operating status of the coal conveyor belt. By establishing a dynamic baseline, it effectively avoids misjudgments caused by changes in operating conditions, significantly improving the accuracy of abnormal parameter identification and environmental adaptability. At the same time, through the abnormal data ratio screening mechanism, it eliminates occasional noise interference and ensures that only parameters that continuously deviate from the normal state are marked as abnormal, providing a reliable and accurate data foundation for subsequent fault diagnosis and protection decisions.

[0021] In the embodiments of this application, a data analysis-based method for protecting the operation of a coal conveyor belt is provided. The method involves analyzing abnormal parameter data, determining abnormal data characteristics, and determining the degree of abnormality of the abnormal parameters based on these characteristics. This includes: determining the parameter data group corresponding to the abnormal parameter and the corresponding dynamic change baseline, and determining the proportion of abnormal data in the parameter data group; constructing a time-progress data change curve based on the parameter data group, and calculating the deviation between the data change curve and the dynamic change baseline; determining the proportion and deviation of abnormal data as abnormal data characteristics of the abnormal parameter, and evaluating each abnormal data characteristic to obtain an abnormality degree evaluation value for each abnormal data characteristic; and summing the abnormality degree evaluation values ​​of each abnormal data characteristic to obtain the degree of abnormality of the abnormal parameter.

[0022] Specifically, the proportion of abnormal data in the parameter set is statistically analyzed to reflect the persistence and intensity of anomalies. Based on the data curve of this parameter set over time, the overall deviation from the dynamic baseline is calculated to measure the cumulative effect of the anomaly magnitude. The proportion of abnormal data and the deviation are used together as the abnormal data characteristics of the anomaly parameter. These two characteristics are quantitatively evaluated separately to obtain their respective anomaly severity assessment values. Finally, they are summed to calculate the final anomaly severity of the parameter. This step, by fusing the proportional characteristics and curve deviation characteristics of abnormal data, comprehensively characterizes the severity of parameter anomalies from both the frequency and magnitude of anomalies, overcoming the limitations of single-indicator evaluation. It provides accurate and quantitative data support for subsequent multi-parameter fusion and protection decisions, significantly improving the objectivity and reliability of anomaly severity assessment. In the embodiments of this application, a data analysis-based method for protecting the operation of a coal conveyor belt is provided. The method involves fusing different abnormal parameters to obtain high-dimensional fused abnormal parameters, and determining the abnormal operation type of the coal conveyor belt based on the high-dimensional fused abnormal parameters. This includes: extracting features of different abnormal parameters and fusing the features of each abnormal parameter to obtain high-dimensional fused abnormal parameters; inputting the high-dimensional fused abnormal parameters into a preset abnormal classification and recognition model, and having the preset abnormal classification and recognition model output the abnormal operation type of the coal conveyor belt.

[0023] Specifically, after obtaining the quantitative features of each abnormal parameter, the deep features that characterize the fault attributes of each abnormal parameter are further extracted. Then, feature-level fusion technology is used to concatenate or combine feature vectors of different modalities and dimensions to construct a high-dimensional fused abnormal parameter containing multi-source information. This high-dimensional fused parameter is input into a preset abnormal classification and recognition model, which automatically performs inference calculations and ultimately outputs the specific abnormal operation type of the coal conveyor belt, such as longitudinal tear, belt misalignment, idler failure, coal blockage, or fire. This step, through the combination of multimodal feature fusion and intelligent classification models, achieves accurate mapping from scattered abnormal signals to specific fault types, effectively solving the problem that a single parameter cannot comprehensively characterize complex fault modes. This significantly improves the accuracy and granularity of abnormal diagnosis, providing a clear decision-making basis for subsequent differentiated protection actions for different types of abnormalities.

[0024] In the embodiments of this application, a method for protecting the operation of a coal conveyor belt based on data analysis is provided. The method for determining the comprehensive anomaly degree of high-dimensional fused anomaly parameters based on the anomaly degree of the anomaly parameters includes: normalizing the anomaly degree of the anomaly parameters to obtain normalized values ​​of the anomaly degree of the anomaly parameters, and determining the weights of the anomaly parameters based on the normalized values ​​of the anomaly degree; and calculating the comprehensive anomaly degree of high-dimensional fused anomaly parameters by weighted summation of the anomaly degree of the anomaly parameters and their corresponding weights.

[0025] Specifically, the abnormality severity values ​​of each abnormal parameter are normalized and mapped to a unified dimensional range to obtain normalized abnormality severity values ​​for each parameter, thereby eliminating the incomparability caused by differences in physical meaning and dimensions between different parameters. Based on these normalized values, the weights of each abnormal parameter are dynamically determined, assigning greater weights to parameters with higher abnormality severity to highlight the impact of severe faults on overall safety. The original abnormality severity values ​​of each abnormal parameter are then weighted and summed with their corresponding weights to obtain the comprehensive abnormality severity of the high-dimensional fused abnormal parameters. This step achieves unified quantification of the severity of multi-source heterogeneous anomalies through normalization, and the dynamic weighting based on anomaly severity ensures that the assessment results can truly reflect the contribution of each fault factor. Finally, a comprehensive index reflecting the overall operational health status is obtained through weighted fusion, providing a scientific and accurate quantitative decision-making basis for whether to trigger protection and which protection level to select, effectively avoiding misjudgments or omissions caused by a single parameter anomaly.

[0026] In the embodiments of this application, a method for protecting the operation of a coal conveyor belt based on data analysis is provided. The method for determining the weight of anomaly parameters based on the normalized value of anomaly degree includes: pre-setting a preset weight-normalized value interval correspondence relationship, wherein each normalized value interval is associated with a corresponding preset weight; determining the normalized value of the anomaly degree of the anomaly parameter, and selecting the preset weight corresponding to the normalized value interval as the weight of the anomaly parameter based on the mapping relationship between the normalized value interval to which the normalized value belongs and the preset weight-normalized value interval correspondence relationship.

[0027] Specifically, a pre-established correspondence between weights and normalized anomaly ranges is created, assigning a preset weight value to each consecutive normalized range. When determining the weight of an anomaly parameter, its normalized anomaly value is first calculated. Then, based on the specific range this value falls into, the preset weight associated with that range is directly selected from the pre-established correspondence as the parameter's final weight. This step discretizes the consecutive anomaly values ​​into finite weight ranges, making the weight allocation logic clearer and more stable, avoiding drastic weight changes due to minor fluctuations in anomaly levels, and enhancing the robustness of weight allocation.

[0028] In the embodiments of this application, a data analysis-based method for protecting the operation of a coal conveyor belt is provided. The step of determining whether to protect the operation of the coal conveyor belt based on the comprehensive anomaly level includes: determining a pre-set anomaly level threshold, and determining whether to protect the operation of the coal conveyor belt based on the relationship between the comprehensive anomaly level of the high-dimensional fused anomaly parameters and the anomaly level threshold; if the comprehensive anomaly level of the high-dimensional fused anomaly parameters is less than the anomaly level threshold, it is determined that no protection is needed for the operation of the coal conveyor belt; if the comprehensive anomaly level of the high-dimensional fused anomaly parameters is greater than or equal to the anomaly level threshold, it is determined that protection is needed for the operation of the coal conveyor belt.

[0029] Specifically, by setting a clear anomaly threshold as the trigger criterion for protection actions, the overall anomaly level of the high-dimensional fused anomaly parameters is compared with this threshold: if the overall anomaly level is less than the threshold, it indicates that the current anomaly is within an acceptable range, and the system determines that there is no need to activate operational protection, only monitoring or recording; if the overall anomaly level reaches or exceeds the threshold, it indicates that the anomaly has exceeded the safety limit, and the system immediately determines that operational protection needs to be activated. This step, by introducing a quantitative threshold criterion, transforms the comprehensive health indicators obtained from multi-dimensional fusion analysis into a clear binary decision logic, achieving objectivity and precision in protection triggering. It avoids human judgment hesitation caused by a lack of clear standards and prevents frequent malfunctions caused by slight fluctuations, providing a reliable automated protection barrier for the safe operation of coal conveyor belts. At the same time, this threshold can be flexibly adjusted according to the importance of the equipment, safety level, and historical experience to adapt to the actual needs of different sites.

[0030] In the embodiments of this application, a data analysis-based method for protecting the operation of a coal conveyor belt is provided. The method involves determining the operation protection action of the coal conveyor belt based on the comprehensive degree of abnormality and the type of abnormal operation, and protecting the operation of the coal conveyor belt based on the operation protection action. The method includes: inputting the comprehensive degree of abnormality and the type of abnormal operation into an operation protection action model, outputting the operation protection action of the operation protection action model to obtain the operation protection action of the coal conveyor belt; converting the operation protection action of the coal conveyor belt into an operation control command, and adjusting and controlling the operation of the coal conveyor belt according to the operation control command to protect the operation of the coal conveyor belt.

[0031] Specifically, the comprehensive anomaly severity and anomaly type obtained from the preceding analysis are input into a pre-built operational protection action model. The model, based on its built-in decision logic, performs intelligent matching and reasoning, automatically outputting the most suitable operational protection action for the current anomaly scenario. This protection action command is then converted into operational control commands recognizable by the control system. Through actuators, the drive unit, braking unit, and auxiliary equipment of the coal conveyor belt are precisely adjusted and controlled, thus achieving a complete closed loop from intelligent decision-making to physical execution. This step, through model-driven automated decision-making, achieves precise matching of protection actions with anomaly type and severity, avoiding the delays and uncertainties of manual judgment. It ensures that the most appropriate protective measures can be taken quickly and accurately at critical moments, minimizing failure losses and protecting personal and equipment safety. Simultaneously, it provides reliable technical support for the unmanned and intelligent operation of the coal conveying system.

[0032] In the embodiments of this application, a data analysis-based method for protecting the operation of a coal conveyor belt is provided. The method for constructing the operation protection action model includes: acquiring historical multi-dimensional operation monitoring data of the coal conveyor belt, and determining the historical comprehensive anomaly degree and historical abnormal operation type based on the historical multi-dimensional operation monitoring data; determining the historical operation protection actions corresponding to the historical comprehensive anomaly degree and historical abnormal operation type, and constructing a dataset based on the historical comprehensive anomaly degree, historical abnormal operation type, and historical operation protection actions; dividing the dataset into a training set and a test set according to a preset ratio, and inputting the training set and the test set into a preset neural network model for training to construct an initial operation protection action model; inputting the test set into the initial operation protection action model for testing until the initial operation protection action model meets a preset convergence condition to obtain the operation protection action model.

[0033] Specifically, the process involves acquiring historical multi-dimensional operational monitoring data of the coal conveyor belt, extracting the historical comprehensive anomaly degree and historical anomaly operation type corresponding to the historical high-dimensional fusion anomaly parameters through a preliminary analysis process, and recording the actual historical operational protection actions taken at that time. This data is used as samples to construct a dataset containing inputs and outputs. The dataset is divided into training and testing sets according to a preset ratio and input into a preset neural network model for supervised training, enabling the model to autonomously learn the complex mapping relationship from abnormal states to protection actions. Through repeated iterative training and verification of the model's accuracy and generalization ability using the test set, the model is trained until it meets the preset convergence conditions, ultimately yielding an optimized operational protection action model. This step, through a data-driven approach, combines historical operation and maintenance experience with deep learning capabilities to automatically discover the optimal protection decision logic, avoiding the subjectivity and incompleteness of manual rule bases, and significantly improving the accuracy and adaptability of protection action selection. As historical data accumulates, the model can undergo continuous iterative optimization, enabling the protection strategy to dynamically adapt to new situations such as equipment aging and changes in operating conditions, providing a core decision engine with self-evolving capabilities for the intelligent protection of coal conveyor belts.

[0034] like Figure 2 As shown in the embodiments of this application, a data analysis-based coal conveyor belt operation protection system is provided, comprising: an acquisition module for acquiring multi-dimensional operation monitoring data of the coal conveyor belt, analyzing the multi-dimensional operation monitoring data, and determining abnormal parameters in the multi-dimensional operation monitoring data; an analysis module for analyzing the abnormal parameter data, determining abnormal data characteristics, and determining the degree of abnormality of the abnormal parameters based on the abnormal data characteristics; a determination module for fusing different abnormal parameters to obtain high-dimensional fused abnormal parameters, and determining the abnormal operation type of the coal conveyor belt based on the high-dimensional fused abnormal parameters; a judgment module for determining the comprehensive degree of abnormality of the high-dimensional fused abnormal parameters based on the degree of abnormality of the abnormal parameters, and determining whether to perform operation protection on the coal conveyor belt based on the comprehensive degree of abnormality; and a protection module for determining the operation protection action of the coal conveyor belt based on the comprehensive degree of abnormality and the abnormal operation type, and protecting the operation of the coal conveyor belt based on the operation protection action.

[0035] In summary, this invention provides a data analysis-based method and system for protecting the operation of a coal conveyor belt. The method includes: acquiring and analyzing multi-dimensional operational monitoring data of the coal conveyor belt to determine abnormal parameters; determining abnormal data characteristics based on the abnormal parameters and determining the degree of abnormality of the abnormal parameters; fusing different abnormal parameters to obtain high-dimensional fused abnormal parameters and determining the abnormal operation type of the coal conveyor belt based on these parameters; determining the comprehensive degree of abnormality of the high-dimensional fused abnormal parameters based on the degree of abnormality of the abnormal parameters and determining whether to implement operational protection for the coal conveyor belt; determining the operational protection action of the coal conveyor belt based on the comprehensive degree of abnormality and the abnormal operation type, and protecting the operation of the coal conveyor belt accordingly. This invention uses comprehensive quantitative analysis of multi-dimensional data to determine the early protection action of the coal conveyor belt, achieving a leap from post-event protection to pre-event intelligent decision-making, and significantly improving the safety level of coal conveyor belt operation.

[0036] Finally, it should be noted that those skilled in the art can obviously make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims and their equivalents, this invention also intends to include these modifications and variations.

Claims

1. A data analysis-based method for protecting the operation of a coal conveyor belt, characterized in that, include: Acquire multidimensional operation monitoring data of the coal conveyor belt, analyze the multidimensional operation monitoring data, and identify abnormal parameters in the multidimensional operation monitoring data; Analyze the data of abnormal parameters, determine the characteristics of abnormal data, and determine the degree of abnormality of abnormal parameters based on the characteristics of abnormal data; Different abnormal parameters are fused to obtain high-dimensional fused abnormal parameters, and the abnormal operation type of the coal conveyor belt is determined based on the high-dimensional fused abnormal parameters; The comprehensive anomaly degree of the high-dimensional fused anomaly parameters is determined based on the anomaly degree of the anomaly parameters, and the operation protection of the coal conveyor belt is determined based on the comprehensive anomaly degree. The operation protection actions of the coal conveyor belt are determined based on the comprehensive degree of abnormality and the type of abnormal operation, and the operation of the coal conveyor belt is protected based on the operation protection actions.

2. The method for protecting the operation of a coal conveyor belt based on data analysis according to claim 1, characterized in that, The acquisition of multi-dimensional operation monitoring data of the coal conveyor belt, and the analysis of the multi-dimensional operation monitoring data to determine abnormal parameters in the multi-dimensional operation monitoring data, includes: Acquire multidimensional operation monitoring data of the coal conveyor belt and divide the multidimensional operation monitoring data into multiple parameter data groups according to parameter type; The current operating condition of the coal conveyor belt is determined based on multi-dimensional operation monitoring data, and the dynamic change baseline corresponding to each parameter data group is determined based on the operating condition. Data in each parameter data group that is not within the preset range of the dynamic change baseline is identified as abnormal data, and parameters in parameter data groups whose proportion of abnormal data exceeds the preset proportion value are identified as abnormal parameters in the multidimensional operation monitoring data.

3. The method for protecting the operation of a coal conveyor belt based on data analysis according to claim 2, characterized in that, The process of analyzing the abnormal parameter data, determining the characteristics of the abnormal data, and determining the degree of abnormality of the abnormal parameters based on the characteristics of the abnormal data includes: Identify the parameter data group corresponding to the abnormal parameters and the corresponding dynamic change baseline, and determine the proportion of abnormal data in the parameter data group; Construct a data change curve for the time progress based on the parameter data set, and calculate the deviation of the data change curve from the dynamic change baseline; The proportion and deviation of abnormal data are determined as abnormal data features of abnormal parameters, and the abnormality degree of each abnormal data feature is evaluated and valued to obtain the abnormality degree evaluation value of each abnormal data feature. The degree of abnormality of each abnormal data feature is calculated by summing the abnormality assessment values.

4. The method for protecting the operation of a coal conveyor belt based on data analysis according to claim 1, characterized in that, The process of fusing different abnormal parameters to obtain high-dimensional fused abnormal parameters, and determining the abnormal operation type of the coal conveyor belt based on the high-dimensional fused abnormal parameters, includes: Features of different anomaly parameters are extracted and the features of each anomaly parameter are fused to obtain high-dimensional fused anomaly parameters; The high-dimensional fusion anomaly parameters are input into the preset anomaly classification and identification model, and the preset anomaly classification and identification model outputs the abnormal operation type of the coal conveyor belt.

5. The method for protecting the operation of a coal conveyor belt based on data analysis according to claim 1, characterized in that, The determination of the comprehensive anomaly degree of high-dimensional fused anomaly parameters based on the anomaly degree of the anomaly parameters includes: The degree of abnormality of the abnormal parameters is normalized to obtain the normalized value of the degree of abnormality of the abnormal parameters, and the weight of the abnormal parameters is determined based on the normalized value of the degree of abnormality. The degree of anomalousness of the anomalous parameters is calculated by weighting and summing the corresponding weights to obtain the comprehensive degree of anomalousness of the high-dimensional fused anomalous parameters.

6. The method for protecting the operation of a coal conveyor belt based on data analysis according to claim 5, characterized in that, The determination of the weights of the anomaly parameters based on the anomaly degree normalization value includes: A preset weight-abnormality normalization value interval correspondence is set in advance. For each abnormality normalization value interval, a corresponding preset weight is associated with it. Determine the normalized value of the abnormality degree of the abnormal parameter, and based on the mapping relationship between the normalized value interval of the abnormality degree to which the normalized value of the abnormality degree belongs and the corresponding relationship between the preset weight and the normalized value interval of the abnormality degree, select the preset weight corresponding to the normalized value interval of the abnormality degree as the weight of the abnormal parameter.

7. The method for protecting the operation of a coal conveyor belt based on data analysis according to claim 1, characterized in that, The method of determining whether to implement operational protection for the coal conveyor belt based on the comprehensive degree of anomaly includes: Determine a pre-set anomaly threshold, and determine whether the coal conveyor belt needs to be protected based on the relationship between the comprehensive anomaly level of the high-dimensional fused anomaly parameters and the anomaly threshold. If the overall anomaly degree of the high-dimensional fusion anomaly parameters is less than the anomaly degree threshold, it is determined that no operational protection is required for the coal conveyor belt. If the overall anomaly degree of the high-dimensional fusion anomaly parameters is greater than or equal to the anomaly degree threshold, it is determined that the coal conveyor belt needs to be protected during operation.

8. The method for protecting the operation of a coal conveyor belt based on data analysis according to claim 1, characterized in that, The process of determining the operational protection actions for the coal conveyor belt based on the comprehensive degree of abnormality and the type of abnormal operation, and protecting the operation of the coal conveyor belt based on these operational protection actions, includes: The comprehensive abnormality level and abnormal operation type are input into the operation protection action model, and the operation protection action model outputs the operation protection action of the coal conveyor belt. The operation protection actions of the coal conveyor belt are converted into operation control commands, and the operation of the coal conveyor belt is adjusted and controlled according to the operation control commands in order to protect the operation of the coal conveyor belt.

9. A method for protecting the operation of a coal conveyor belt based on data analysis according to claim 8, characterized in that, The method for constructing the operational protection action model includes: Acquire historical multidimensional operation monitoring data of coal conveyor belts, and determine the historical comprehensive anomaly degree and historical anomaly operation type based on the historical multidimensional operation monitoring data and historical high-dimensional fusion anomaly parameters; Determine the historical operation protection actions corresponding to the historical comprehensive anomaly degree and historical anomaly operation type, and construct a dataset based on the historical comprehensive anomaly degree, historical anomaly operation type and historical operation protection actions; The dataset is divided into training and testing sets according to a preset ratio, and the training and testing sets are input into a preset neural network model for training to build an initial operation protection action model; The test set is input into the initial operation protection action model for testing until the initial operation protection action model meets the preset convergence condition, thus obtaining the operation protection action model.

10. A coal conveyor belt operation protection system based on data analysis, characterized in that, include: The acquisition module is used to acquire multi-dimensional operation monitoring data of the coal conveyor belt, analyze the multi-dimensional operation monitoring data, and determine abnormal parameters in the multi-dimensional operation monitoring data; The analysis module is used to analyze the data of abnormal parameters, determine the characteristics of abnormal data, and determine the degree of abnormality of abnormal parameters based on the characteristics of abnormal data. The determination module is used to fuse different abnormal parameters to obtain high-dimensional fused abnormal parameters, and to determine the abnormal operation type of the coal conveyor belt based on the high-dimensional fused abnormal parameters; The judgment module is used to determine the comprehensive anomaly degree of the high-dimensional fused anomaly parameters based on the anomaly degree of the anomaly parameters, and to determine whether to implement operation protection for the coal conveyor belt based on the comprehensive anomaly degree. The protection module is used to determine the operation protection actions of the coal conveyor belt based on the comprehensive degree of abnormality and the type of abnormal operation, and to protect the operation of the coal conveyor belt based on the operation protection actions.

Images