Data-driven Fault Early Warning Method and System for Material Conveyors

Abstract

The present application discloses a data-driven fault warning method and system for a material conveyor, relating to the field of data warning. The method includes: deploying a plurality of sensors for real-time collection to obtain a real-time operation data set of the material conveyor for multi-dimensional analysis, determining multi-dimensional operation data for time series decomposition, extracting a plurality of operation characteristics, obtaining a fault prediction model through learning and training according to historical operation record logs, synchronizing the real-time operation data set to the fault prediction model for prediction calculation, determining the operation health score of the material conveyor to conduct a fault determination on the material conveyor, determining the fault risk level, generating a warning signal and sending it to a remote terminal for intelligent warning feedback of the fault. It solves the technical problems that the fault monitoring of the material conveyor is not timely and the warning accuracy is low, resulting in difficulty in realizing intelligent maintenance. Through data-driven fault prediction and real-time warning, the real-time monitoring of the equipment status and intelligent feedback are realized, achieving the technical effect of improving the operation and maintenance efficiency.

Description

Technical Field

[0001] This application relates to the field of data warning, and particularly to a method and system for fault warning of a material conveyor driven by data. Background Art

[0002] With the continuous development of industrial automation and intelligence, as an important conveying device in the production line, the material conveyor is widely used in multiple fields such as mines, logistics, and manufacturing. Its stable operation is directly related to the efficiency and safety of the production line. However, the traditional fault monitoring methods of material conveyors mainly rely on regular manual inspections and equipment shutdown maintenance, which are not only inefficient but also unable to detect potential faults in a timely manner, easily leading to unexpected equipment shutdowns and even major production accidents. Especially in scenarios with complex operating environments and frequent load changes, traditional monitoring means are difficult to meet the requirements of efficient production and safe operation.

[0003] In the prior art, some material conveyors collect data by installing simple sensors on key components, such as monitoring parameters such as the tension, vibration, and motor temperature of the conveyor belt. However, these data are usually only used for the monitoring of single indicators and simple threshold alarms, lacking the ability to comprehensively analyze multi-dimensional data and being difficult to capture potential fault characteristics. In addition, the early warning of traditional methods is mainly based on rule algorithms, and the definition of anomalies depends on fixed empirical thresholds, lacking the ability of dynamic adjustment and being prone to false alarms or missed alarms when dealing with complex operating states. Summary of the Invention

[0004] This application provides a method and system for fault warning of a material conveyor driven by data, solves the technical problem that it is difficult to achieve intelligent maintenance due to untimely fault monitoring and low warning accuracy of the material conveyor, and realizes real-time monitoring and intelligent feedback of the equipment status through data-driven fault prediction and real-time warning, achieving the technical effect of improving the operation and maintenance efficiency.

[0005] This application provides a method for fault warning of a material conveyor driven by data. The method is applied to a fault warning system of a material conveyor driven by data and includes: traversing the material conveyor to deploy multiple sensors for real-time collection to obtain a real-time operation data set of the material conveyor;

[0006] Performing multi-dimensional analysis based on the real-time operation data set to determine multi-dimensional operation data, and performing time series decomposition according to the multi-dimensional operation data to extract multiple operation characteristics;

[0007] Retrieving the historical operation record log of the material conveyor, and performing learning and training according to the historical operation record log to obtain a fault prediction model;

[0008] Synchronize the real-time operation data set to the fault prediction model for prediction calculation to determine the operation health score of the material conveyor;

[0009] Perform fault determination on the material conveyor according to the operation health score, determine the fault risk level, generate a warning signal according to the fault risk level, and send the warning signal to the remote terminal for intelligent warning feedback of the fault.

[0010] In a possible implementation, perform multi-dimensional analysis based on the real-time operation data set to determine multi-dimensional operation data, and perform the following processing: perform data cleaning on the real-time operation data set to obtain a real-time operation standard data set; traverse the real-time operation standard data set to perform similarity calculation to determine multiple similarity coefficients; determine multiple clustering centers according to the multiple similarity coefficients, and divide the real-time operation standard data set into multiple data clusters according to the multiple clustering centers; add the multiple data clusters to the multi-dimensional operation data.

[0011] In a possible implementation, perform time series decomposition according to the multi-dimensional operation data to extract multiple operation characteristics, and perform the following processing: extract multiple data timestamps of the multiple clustering centers, arrange the multiple data timestamps in sequence, construct multiple time series, and there is a corresponding relationship between the multiple time series and the multi-dimensional operation data; sort the multi-dimensional operation data group in the time dimension according to the multiple time series to construct a time series model; use the time series model for decomposition to obtain multiple decomposition components, and integrate the multiple decomposition components to generate the multiple operation characteristics.

[0012] In a possible implementation, perform learning and training according to the historical operation record log to obtain a fault prediction model, and perform the following processing: traverse the historical operation record log to perform operation fault analysis to determine multiple fault operation characteristics; perform feature annotation on the historical operation record log based on the multiple fault operation characteristics to determine multiple fault annotation information; perform data segmentation on the historical operation record log according to the multiple fault annotation information to determine a training data set and a validation data set; perform supervised training iteration based on the training data set. When the training data set tends to converge, use the validation data set for cross-validation, and obtain the fault prediction model according to the validation result.

[0013] In a possible implementation, synchronize the real-time operation dataset to the fault prediction model for prediction calculation to determine the operation health score of the material conveyor, and perform the following processing: load the fault prediction model, synchronize the real-time operation dataset to the fault prediction model to perform operation prediction on the material conveyor, and generate an operation fault prediction result; map the historical operation record log to the operation fault prediction result for association to determine an operation fault association list; perform fault calculation according to the operation fault association list to generate multiple fault probabilities, and perform health assessment based on the multiple fault probabilities to generate the operation health score.

[0014] In a possible implementation, perform fault determination on the material conveyor according to the operation health score to determine the fault risk level, generate a warning signal according to the fault risk level, and send the warning signal to a remote terminal for intelligent warning feedback on the fault, and perform the following processing: set an expected operation threshold based on the historical operation record log, perform fault determination on the material conveyor according to the expected operation threshold and the operation health score, and generate a fault determination result; perform critical analysis according to the fault determination result to determine a fault risk data matrix, and correct the fault risk data matrix based on the multiple operation characteristics to generate a fault risk level; match the fault risk level to the operation health score to generate a status signal set, and the status signal set includes a normal status signal, a warning status signal, and a fault status signal; screen the normal status signal, the warning status signal, and the fault status signal according to the fault risk level to determine the warning signal and send it to the remote terminal for warning feedback.

[0015] In a possible implementation, perform fault determination on the material conveyor according to the expected operation threshold and the operation health score to generate a fault determination result, and perform the following processing: compare the operation health score with the expected operation threshold to determine whether the operation health score is greater than or equal to the expected operation threshold; if the operation health score is greater than or equal to the expected operation threshold, obtain normal operation data, perform continuous operation monitoring according to the normal operation data to generate an operation monitoring instruction, and add the operation monitoring instruction to the fault determination result; if the operation health score is less than the expected operation threshold, generate an abnormal operation dataset, perform fault impact analysis according to the abnormal operation dataset to generate an operation impact factor; perform weight assignment on the abnormal operation dataset according to the operation impact factor to determine multiple weight coefficients; associate the multiple weight coefficients with the abnormal operation dataset to generate the fault determination result.

[0016] The present application also provides a data-driven fault warning system for a material conveyor, including: a data acquisition module, configured to traverse multiple sensors arranged on the material conveyor for real-time acquisition to obtain a real-time operation data set of the material conveyor; a feature extraction module, configured to perform multi-dimensional analysis based on the real-time operation data set to determine multi-dimensional operation data, perform time series decomposition according to the multi-dimensional operation data, and extract multiple operation features; a learning and training module, configured to retrieve the historical operation record log of the material conveyor, perform learning and training according to the historical operation record log, and obtain a fault prediction model; a prediction calculation module, configured to synchronize the real-time operation data set to the fault prediction model for prediction calculation to determine the operation health score of the material conveyor; a fault determination module, configured to perform fault determination on the material conveyor according to the operation health score, determine the fault risk level, generate a warning signal according to the fault risk level, and send the warning signal to a remote terminal for intelligent warning feedback of the fault.

[0017] One or more technical solutions provided in the present application have at least the following technical effects or advantages:

[0018] The data-driven fault warning method and system for a material conveyor provided in the present application relate to the technical field of data warning, solve the technical problems of untimely fault monitoring and low warning accuracy of the material conveyor, which make it difficult to achieve intelligent maintenance, and realize real-time monitoring and intelligent feedback of the equipment status through data-driven fault prediction and real-time warning, achieving the technical effect of improving the operation and maintenance efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings of the embodiments of the present application will be briefly introduced below. Flowcharts are used in the present application to illustrate the operations performed by the system according to the embodiments of the present application. It should be understood that the operations before or below do not necessarily need to be executed precisely in order. On the contrary, according to the need, they can be executed in reverse order or simultaneously. At the same time, other operations can also be added to these processes, or one or several operations can be removed from these processes.

[0020] Figure 1 It is a schematic flowchart of the data-driven fault warning method for a material conveyor provided by an embodiment of the present application;

[0021] Figure 2 It is a schematic structural diagram of the data-driven fault warning system for a material conveyor provided by an embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0022] The above description is only an overview of the technical solution of the present application. In order to better understand the technical means of the present application, it can be implemented according to the content of the specification. And in order to make the above and other purposes, features and advantages of the present application more obvious and understandable, the specific embodiments of the present application are hereinafter specifically exemplified.

[0023] In order to make the purpose, technical solution and advantages of the present application clearer, the present application will be further described in detail below with reference to the accompanying drawings. The described embodiments should not be regarded as limitations on the present application. All other embodiments obtained by those of ordinary skill in the art without creative efforts fall within the scope of protection of the present application.

[0024] In the following description, "some embodiments" are involved, which describe a subset of all possible embodiments. However, it can be understood that "some embodiments" can be the same subset or different subsets of all possible embodiments, and can be combined with each other without conflict. The terms "first / second" involved are only used to distinguish similar objects and do not represent a specific order for the objects. The terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or server that includes a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or modules that are not clearly listed or are inherent to these processes, methods, products or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those of ordinary skill in the technical field to which the present application belongs. The terms used herein are only for the purpose of describing the embodiments of the present application.

[0025] The embodiment of the present application provides a data-driven fault warning method for a material conveyor. The method is applied to a data-driven fault warning system for a material conveyor, as Figure 1 shown, the method includes:

[0026] Step A100, traverse a plurality of sensors arranged on the material conveyor for real-time collection to obtain a real-time operation data set of the material conveyor;

[0027] First, according to the characteristics and operation requirements of the material conveyor, clarify the parameters to be monitored, such as temperature, pressure, vibration, flow rate, speed, etc. Then, according to the monitoring objectives, select appropriate sensor types. For example, a temperature sensor is used to monitor the temperature change of the equipment, a vibration sensor is used to monitor the vibration condition of the equipment, and a photoelectric sensor is used for object detection, distance measurement and speed monitoring, etc. At the same time, according to the structure and layout of the material conveyor, formulate a sensor layout plan. Determine the installation position, quantity and connection method of the sensors to ensure that the required data can be collected comprehensively and accurately. Install the sensors at the key parts of the material conveyor according to the layout plan.

[0028] Furthermore, connect the sensor to a data acquisition system (such as a PLC). The connection method can be wired or wireless, depending on the characteristics of the device and the on-site environment. The data acquisition system collects the raw data transmitted by the sensor. To ensure the real-time, accurate, and complete data acquisition, the collected raw data can be processed, including data filtering, data sampling, data encoding, etc. Then, the processed data is stored in the memory or external storage device of the data acquisition system for subsequent analysis and processing, realizing the real-time acquisition of multiple sensors installed on the material conveyor and obtaining the real-time operation dataset of the material conveyor. This helps improve the management and maintenance level of the equipment, reduce unexpected downtime, and increase production efficiency and equipment service life.

[0029] Execute step A200 to perform multi-dimensional analysis based on the real-time operation dataset, determine multi-dimensional operation data, and perform time series decomposition according to the multi-dimensional operation data to extract multiple operation characteristics. In a possible implementation, step A200 further includes step A210 to perform data cleaning on the real-time operation dataset to obtain a real-time operation standard dataset; execute step A220 to traverse the real-time operation standard dataset to calculate similarity coefficients to determine multiple similarity coefficients; execute step A230 to determine multiple cluster centers according to the multiple similarity coefficients and divide the real-time operation standard dataset into multiple data clusters according to the multiple cluster centers; execute step A240 to add the multiple data clusters to the multi-dimensional operation data.

[0030] By checking the outliers in the obtained real-time operation dataset above, the outliers may be caused by sensor failures, data transmission errors, or abnormal equipment operations. At the same time, statistical methods or machine learning algorithms (such as Isolation Forest) can be used to identify and process these outliers, and standardize the data with different dimensions and ranges to ensure their comparability in similarity calculation and clustering analysis, thereby obtaining a real-time operation standard dataset. Further, according to the characteristics of the data and business requirements, similarity measurement methods such as Euclidean distance, Manhattan distance, cosine similarity, Pearson correlation coefficient, etc. can be used to traverse the real-time operation standard dataset, calculate the similarity coefficients between each pair of data points, and then use clustering algorithms such as K-means, DBSCAN, hierarchical clustering, etc. to perform clustering analysis on the real-time operation standard dataset according to the multiple similarity coefficients to determine multiple cluster centers. The multiple cluster centers contain the central points of different categories in the real-time operation dataset. Further, according to the cluster centers and similarity coefficients, the real-time operation standard dataset is divided into multiple data clusters, which means that the data points in each data cluster have high similarity in terms of similarity, while the data points between different data clusters have low similarity.

[0031] Finally, add the label of the data cluster to which each data point belongs. The label can be used for subsequent data analysis and visualization, providing strong support for the data analysis of the subsequent material conveyor.

[0032] In a possible implementation, step A200 further includes step A250 of extracting multiple data timestamps of the multiple cluster centers, arranging the multiple data timestamps in sequence, constructing multiple time series, where the multiple time series have a corresponding relationship with the multi-dimensional operation data; executing step A260 of sorting the multi-dimensional operation data groups in the time dimension according to the multiple time series to construct a time series model; executing step A270 of decomposing using the time series model to obtain multiple decomposed components, and integrating the multiple decomposed components to generate the multiple operation features.

[0033] First, from the multiple cluster centers obtained from the cluster analysis, extract the data timestamp corresponding to each cluster center. The extracted timestamp is used to represent the time position of the cluster center in the dataset. At the same time, arrange the multiple extracted data timestamps in sequence to construct a framework for the time series. Among them, the arrangement order can be based on the chronological order of the timestamps or specific requirements. According to the arranged data timestamps, construct multiple time series, and each time series corresponds to the time evolution of a cluster center or a group of related data. At the same time, it is necessary to ensure that there is a one-to-one correspondence between the constructed time series and the multi-dimensional operation data.

[0034] Furthermore, organize the multi-dimensional operation data according to their corresponding feature dimensions to form a multi-dimensional operation data group. Each data group in the multi-dimensional operation data group contains multiple operation feature values at the same time point. Meanwhile, according to the constructed time series, sort the multi-dimensional operation data group in the time dimension to ensure that the data groups are arranged in the order of the time series to reflect the time evolution law of the data. Use the sorted multi-dimensional operation data group to construct a time series model. The time series model can capture features such as the trend, periodicity, and seasonality of the data changing over time. Decompose the constructed time series model to obtain multiple decomposition components. The multiple decomposition components can include trend decomposition, periodic decomposition, and random term decomposition. The trend decomposition is to extract the long-term change trend of the data (such as the temperature gradually increasing or the vibration amplitude increasing in the long term) using the moving average method or the Hodrick-Prescott filter. The periodic decomposition is to extract periodic features (such as the change of the vibration frequency of the equipment operation and the daily change law of the temperature) through Fourier transform or wavelet decomposition. The random term decomposition is to separate the random fluctuations outside the trend and periodic parts to extract unpredictable perturbation characteristics, ensure that the influence of noise on the extraction of main features is minimized, and perform feature extraction on the decomposed time series. Exemplarily, the change rate and inflection point features can be extracted from the trend component, the main frequency, amplitude, and phase can be extracted from the periodic component, and indicators such as variance and peak value can be extracted from the random component to evaluate the data volatility. Finally, integrate the multiple decomposition components in the time dimension to generate the multiple operation features, providing important data support for subsequent fault warning, health assessment, and maintenance decision-making.

[0035] Execute step A300 to retrieve the historical operation record log of the material conveyor, and perform learning and training based on the historical operation record log to obtain a fault prediction model. In a possible implementation manner, step A300 further includes step A310, traverse the historical operation record log for operation fault analysis to determine multiple fault operation features; execute step A320, perform feature annotation on the historical operation record log based on the multiple fault operation features to determine multiple fault annotation information; execute step A330, segment the historical operation record log according to the multiple fault annotation information to determine a training data set and a validation data set; execute step A340, perform supervised training iteration based on the training data set. When the training data set tends to converge, use the validation data set for cross-validation, and obtain the fault prediction model according to the validation result.

[0036] First, analyze the operation data in the historical operation record log, extract the features related to faults. The features related to faults may include the operation parameters of the equipment (such as temperature, pressure, vibration, etc.), time series data (such as change trend, periodicity, etc.), and environmental factors (such as temperature, humidity, etc.). And according to the known equipment fault records and log information, identify the time points of fault occurrence and the corresponding operation features, so as to determine multiple fault operation features. The multiple fault operation features are parameters or patterns that change significantly when a fault occurs. Based on the extracted fault operation features, feature annotation of the historical operation record log means adding annotation information such as fault type and fault level to each time point or data point, forming multiple fault annotation information. Organize the annotated historical operation record log into multiple fault annotation information. The multiple fault annotation information may include the original operation data and the corresponding fault annotation information.

[0037] Furthermore, according to the size and characteristics of the annotation dataset, divide it into a training dataset and a validation dataset. The training dataset is used to train the fault prediction model, and the validation dataset is used to evaluate the performance of the model and conduct cross-validation. If there is an imbalance in the number of samples of different fault types in the annotation dataset, data balancing processing needs to be carried out through methods such as oversampling, undersampling, or synthetic minority over-sampling technique. Use the training dataset to perform supervised training iterations on the model. At the same time, during the training process, continuously adjust the parameters and structure of the model to improve the performance of the model. By observing the changes in indicators such as the loss function value and accuracy during the training process, judge whether the model tends to converge. When the performance of the model on the training dataset no longer improves significantly, it can be considered that the model has converged. When the training dataset tends to converge, use the validation dataset for cross-validation. Evaluate the generalization ability of the model through cross-validation to avoid overfitting or underfitting. According to the results of cross-validation, further optimize and adjust the model. That is, it is possible to adjust the parameters of the model, add regularization terms, use ensemble learning methods, etc. to improve the performance of the model. When the performance of the model on the validation dataset reaches a satisfactory level, use it as the final fault prediction model, providing strong support for the fault prediction and preventive maintenance of the material conveyor.

[0038] Execute step A400 to synchronize the real-time operation dataset to the fault prediction model for prediction calculation, and determine the operation health score of the material conveyor; In a possible implementation, step A400 further includes step A410, loading the fault prediction model, synchronizing the real-time operation dataset to the fault prediction model to perform operation prediction on the material conveyor, and generating an operation fault prediction result; Execute step A420, map the historical operation record log to the operation fault prediction result for association, and determine an operation fault association list; Execute step A430, perform fault calculation according to the operation fault association list, generate multiple fault probabilities, and perform health assessment based on the multiple fault probabilities to generate the operation health score.

[0039] Load the trained fault prediction model from the storage location, then synchronize the real-time operation dataset to the fault prediction model, while ensuring the real-time, accuracy, and integrity of the data. Use the fault prediction model to process the real-time operation dataset, which may include the time series trend, periodic characteristics, and random fluctuation characteristics of the real-time operation dataset, and generate an operation fault prediction result. The operation fault prediction result may include fault type, fault probability, fault occurrence time, etc. At the same time, map the historical operation record log to the operation fault prediction result for association, which means matching through keyword fields such as timestamp and device ID to ensure the corresponding relationship of the data. Further, according to the mapping result, generate an operation fault association list, and the operation fault association list may include the corresponding relationship between the fault information in the historical record and the real-time prediction result.

[0040] Further, according to the operation fault association list, statistically analyze the faults in the real-time prediction result, calculate the probability of each fault type, and generate multiple fault probabilities for the health assessment of the equipment, which means health score = 100 - (fault probability × weight 1 + minor anomaly probability × weight 2), and calculate the operation health score of the material conveyor (for example, the score range is from 0 to 100 points, and the higher the score, the better the health state of the equipment). The score can also be divided into different levels, such as excellent, good, average, poor, etc., which provides strong support for the preventive maintenance, optimized operation, and extended service life of the material conveyor.

[0041] Finally, execute step A500, perform fault determination on the material conveyor according to the operation health score, determine the fault risk level, generate a warning signal according to the fault risk level, and send the warning signal to the remote terminal for intelligent warning feedback of the fault.

[0042] In a possible implementation, step A500 further includes step A510 of setting an expected operation threshold based on the historical operation record log, making a fault determination for the material conveyor according to the expected operation threshold and the operation health score, and generating a fault determination result; in a possible implementation, step A510 further includes step A511 of comparing the operation health score with the expected operation threshold to determine whether the operation health score is greater than or equal to the expected operation threshold; performing step A512, if the operation health score is greater than or equal to the expected operation threshold, obtaining normal operation data, performing continuous operation monitoring according to the normal operation data, generating an operation monitoring instruction, and adding the operation monitoring instruction to the fault determination result; performing step A513, if the operation health score is less than the expected operation threshold, generating an abnormal operation data set, performing a fault impact analysis according to the abnormal operation data set, and generating an operation impact factor; performing step A514 of allocating weights to the abnormal operation data set according to the operation impact factor to determine a plurality of weight coefficients; performing step A515 of associating the plurality of weight coefficients with the abnormal operation data set to generate the fault determination result.

[0043] Perform historical operation analysis on the material conveyor based on the historical operation record log, extract and integrate the data under normal operation conditions, and set the expected operation threshold of the boring conveyor according to the preset normal operation data for each dimension. Further, compare the operation health score with the expected operation threshold to determine whether the operation health score is greater than or equal to the expected operation threshold. If the operation health score is greater than or equal to the expected operation threshold, it is considered that the material conveyor is in a normal operation state, and normal operation data can be obtained, which may include key operation parameters, time series data, etc. At the same time, continuously monitor the normal operation data to monitor whether the operation state of the material conveyor is stable and whether there are abnormal changes, and generate an operation monitoring instruction according to the continuous monitoring result. The monitoring instruction may include continuing to monitor, adjusting operation parameters, performing preventive maintenance, etc., and then adding the operation monitoring instruction to the fault determination result to indicate that the material conveyor is currently in a normal operation state and corresponding monitoring instructions are given.

[0044] Furthermore, if the running health score is less than the expected running threshold, it is considered that the material conveyor is in an abnormal running state. Then, an abnormal running data set is generated, including abnormal running parameters, abnormal occurrence time, etc. And a fault impact analysis is performed on the abnormal running data set to evaluate the impact of the abnormal running on the performance, safety, reliability, etc. of the material conveyor. According to the results of the fault impact analysis, a running impact factor is generated. The running impact factor may include fault type, fault probability, fault severity, etc. Then, based on the running impact factor, weight distribution is performed on the abnormal running data set to determine multiple weight coefficients to reflect the importance of different abnormal running data for fault determination, and the multiple weight coefficients are associated with the abnormal running data set, which means matching the degree of influence of the abnormal running data set on the material conveyor with the multiple weight coefficients. The greater the degree of influence, the higher the weight coefficient. Then, according to the association result and the weight coefficient, a fault determination result is generated. The fault determination result may include fault type, fault level, recommended maintenance measures, etc., ensuring the safe, stable and efficient operation of the material conveyor.

[0045] Execute step A520, perform a critical analysis according to the fault determination result to determine a fault risk data matrix, and correct the fault risk data matrix based on the multiple running characteristics to generate a fault risk level; execute step A530, match the fault risk level to the running health score to generate a state signal set, and the state signal set includes a normal state signal, a warning state signal, and a fault state signal; execute step A540, perform signal screening on the normal state signal, the warning state signal, and the fault state signal according to the fault risk level to determine the warning signal and send it to the remote terminal for warning feedback.

[0046] First, perform a critical analysis on the fault determination results. Determine the possibility and urgency of the fault occurrence based on factors such as fault type, fault probability, and fault impact, and generate the critical analysis results. Analyze the risk levels of different fault types under different conditions according to the critical analysis results, construct a fault risk data matrix, and correct the fault risk data matrix based on multiple operating characteristics, which means that the operating trend analysis can be carried out according to multiple operating characteristics, and the fault risk data matrix can be synchronously updated according to the trend change to generate a more accurate fault risk level. Further, match the fault risk level with the operating health score, and ensure that the state signal set can accurately reflect the current state of the material conveyor. Construct corresponding state signals according to the state information to determine the state signal set. The state signal set includes a normal state signal, a warning state signal, and a fault state signal. The normal state signal can be the fault risk level corresponding to an operating health score greater than or equal to 80 points. The warning state signal can be the fault risk level corresponding to less than 80 points and greater than or equal to 50 points. The fault state signal can be the fault risk level corresponding to less than 50 points, and each signal should have a clear definition and trigger condition. Finally, screen the state signal set according to the fault risk level, which means giving priority to processing the warning state signal and the fault state signal, and sending the selected warning signals to the remote terminal to ensure that the signals can be transmitted to the relevant personnel in a timely and accurate manner. After receiving the warning signal, the remote terminal performs warning feedback processing, including notifying relevant personnel, starting an emergency plan, adjusting equipment operating parameters, etc., which provides strong support for the preventive maintenance, timely response, and reduction of fault losses of the material conveyor.

[0047] The embodiment of the present application solves the technical problem that it is difficult to achieve intelligent maintenance due to untimely fault monitoring and low warning accuracy of the material conveyor, and realizes real-time monitoring and intelligent feedback of the equipment state through data-driven fault prediction and real-time warning, achieving the technical effect of improving the operation and maintenance efficiency.

[0048] In the above text, reference is made to Figure 1 Describe in detail the data-driven fault warning method for the material conveyor according to the embodiment of the present application. Next, reference will be made to Figure 2 Describe the data-driven fault warning system for the material conveyor according to the embodiment of the present application.

[0049] The data-driven fault warning system for the material conveyor according to the embodiment of the present application is used to solve the technical problem that it is difficult to achieve intelligent maintenance due to untimely fault monitoring and low warning accuracy of the material conveyor, and realizes real-time monitoring and intelligent feedback of the equipment state through data-driven fault prediction and real-time warning, achieving the technical effect of improving the operation and maintenance efficiency. The data-driven fault warning system for the material conveyor includes: a data acquisition module 10, a feature extraction module 20, a learning and training module 30, a prediction calculation module 40, and a fault determination module 50.

[0050] The data acquisition module 10 is used to traverse the material conveyor to deploy multiple sensors for real-time acquisition, and obtain a real-time operation data set of the material conveyor;

[0051] The feature extraction module 20 is used to perform multi-dimensional analysis based on the real-time operation data set, determine multi-dimensional operation data, perform time series decomposition according to the multi-dimensional operation data, and extract multiple operation features;

[0052] The learning and training module 30 is used to retrieve the historical operation record log of the material conveyor, perform learning and training according to the historical operation record log, and obtain a fault prediction model;

[0053] The prediction calculation module 40 is used to synchronize the real-time operation data set to the fault prediction model for prediction calculation, and determine the operation health score of the material conveyor;

[0054] The fault determination module 50 is used to perform fault determination on the material conveyor according to the operation health score, determine the fault risk level, generate a warning signal according to the fault risk level, and send the warning signal to the remote terminal for intelligent warning feedback of the fault.

[0055] Next, the specific configuration of the feature extraction module 20 will be described in detail. As described above, based on the real-time operation data set for multi-dimensional analysis to determine multi-dimensional operation data, the feature extraction module 20 may further include: performing data cleaning on the real-time operation data set to obtain a real-time operation standard data set; traversing the real-time operation standard data set to perform similarity calculation to determine multiple similarity coefficients; determining multiple cluster centers according to the multiple similarity coefficients, and dividing the real-time operation standard data set into multiple data clusters according to the multiple cluster centers; adding the multiple data clusters to the multi-dimensional operation data.

[0056] Next, the specific configuration of the feature extraction module 20 will be described in detail. As described above, performing time series decomposition according to the multi-dimensional operation data to extract multiple operation features, the feature extraction module 20 may further include: extracting multiple data timestamps of the multiple cluster centers, arranging the multiple data timestamps in sequence to construct multiple time series, and there is a corresponding relationship between the multiple time series and the multi-dimensional operation data; sorting the multi-dimensional operation data group in the time dimension according to the multiple time series to construct a time series model; using the time series model for decomposition to obtain multiple decomposition components, and integrating the multiple decomposition components to generate the multiple operation features.

[0057] Next, the specific configuration of the learning and training module 30 will be described in detail. As described above, learning and training are performed according to the historical operation record log to obtain a fault prediction model. The learning and training module 30 may further include: traversing the historical operation record log for operation fault analysis to determine multiple fault operation characteristics; performing feature annotation on the historical operation record log based on the multiple fault operation characteristics to determine multiple fault annotation information; segmenting the historical operation record log according to the multiple fault annotation information to determine a training data set and a validation data set; performing supervised training iteration based on the training data set. When the training data set tends to converge, cross-validation is performed using the validation data set, and the fault prediction model is obtained according to the validation result.

[0058] Next, the specific configuration of the prediction calculation module 40 will be described in detail. As described above, the real-time operation data set is synchronized to the fault prediction model for prediction calculation to determine the operation health score of the material conveyor. The prediction calculation module 40 may further include: loading the fault prediction model, synchronizing the real-time operation data set to the fault prediction model to perform operation prediction on the material conveyor, and generating an operation fault prediction result; mapping the historical operation record log to the operation fault prediction result for association to determine an operation fault association list; performing fault calculation according to the operation fault association list to generate multiple fault probabilities, and generating the operation health score based on the multiple fault probabilities.

[0059] Next, the specific configuration of the fault determination module 50 will be described in detail. As described above, fault determination is performed on the material conveyor according to the operation health score to determine the fault risk level, an early warning signal is generated according to the fault risk level, and the early warning signal is sent to the remote terminal for intelligent early warning feedback of the fault. The fault determination module 50 may further include: setting an expected operation threshold based on the historical operation record log, performing fault determination on the material conveyor according to the expected operation threshold and the operation health score, and generating a fault determination result; performing critical analysis according to the fault determination result to determine a fault risk data matrix, and correcting the fault risk data matrix based on the multiple operation characteristics to generate a fault risk level; matching the fault risk level to the operation health score to generate a status signal set, where the status signal set includes a normal status signal, a warning status signal, and a fault status signal; screening the normal status signal, the warning status signal, and the fault status signal according to the fault risk level to determine the early warning signal and sending it to the remote terminal for early warning feedback.

[0060] Next, the specific configuration of the fault determination module 50 will be described in detail. As described above, based on the expected operation threshold and the operation health score, a fault determination is made for the material conveyor to generate a fault determination result. The fault determination module 50 may further include: comparing the operation health score with the expected operation threshold to determine whether the operation health score is greater than or equal to the expected operation threshold; if the operation health score is greater than or equal to the expected operation threshold, obtaining normal operation data, performing continuous operation monitoring based on the normal operation data to generate an operation monitoring instruction, and adding the operation monitoring instruction to the fault determination result; if the operation health score is less than the expected operation threshold, generating an abnormal operation data set, performing a fault impact analysis based on the abnormal operation data set to generate an operation impact factor; assigning weights to the abnormal operation data set according to the operation impact factor to determine a plurality of weight coefficients; associating the plurality of weight coefficients with the abnormal operation data set to generate the fault determination result.

[0061] The data-driven fault warning system for a material conveyor provided by the embodiments of the present application can execute the data-driven fault warning method for a material conveyor provided by any embodiment of the present application, and has corresponding functional modules and beneficial effects for executing the method.

[0062] Although various references are made to certain modules in the system according to the embodiments of the present application, any number of different modules can be used and run on the user terminal and / or the server. The various units and modules included are only divided according to functional logic, but are not limited to the above division as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for easy distinction from each other and do not limit the protection scope of the present application.

[0063] The above specific implementation manners do not constitute a limitation to the protection scope of the present application. Those skilled in the art should understand that various modifications, combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principle of the present application shall be included within the protection scope of the present application.

Claims

1. A data-driven fault warning method for a material conveyor, characterized in that, The method includes: Traverse the material conveyor to deploy multiple sensors for real-time collection to obtain a real-time operation data set of the material conveyor; Conduct multi-dimensional analysis based on the real-time operation data set to determine multi-dimensional operation data, perform time series decomposition according to the multi-dimensional operation data, and extract multiple operation characteristics; Retrieve the historical operation record log of the material conveyor, and perform learning and training according to the historical operation record log to obtain a fault prediction model; Synchronize the real-time operation data set to the fault prediction model for prediction calculation to determine the operation health score of the material conveyor; Conduct fault determination on the material conveyor according to the operation health score, determine the fault risk level, generate an early warning signal according to the fault risk level, and send the early warning signal to a remote terminal for intelligent early warning feedback of the fault; Conduct multi-dimensional analysis based on the real-time operation data set to determine multi-dimensional operation data. The method includes: Conduct data cleaning on the real-time operation data set to obtain a real-time operation standard data set; Traverse the real-time operation standard data set to conduct similarity calculation to determine multiple similarity coefficients; Determine multiple clustering centers according to the multiple similarity coefficients, and divide the real-time operation standard data set into multiple data clusters according to the multiple clustering centers; Add the multiple data clusters to the multi-dimensional operation data; Perform time series decomposition according to the multi-dimensional operation data to extract multiple operation characteristics. The method includes: Extract multiple data timestamps of the multiple clustering centers, arrange the multiple data timestamps in sequence, and construct multiple time series. The multiple time series have a corresponding relationship with the multi-dimensional operation data; Sort the multi-dimensional operation data group in the time dimension according to the multiple time series to construct a time series model; Use the time series model for decomposition to obtain multiple decomposition components, and integrate the multiple decomposition components to generate the multiple operation characteristics; Perform learning and training according to the historical operation record log to obtain a fault prediction model. The method includes: Traverse the historical operation record log to conduct operation fault analysis to determine multiple fault operation characteristics; Perform feature annotation on the historical operation record log based on the multiple fault operation characteristics to determine multiple fault annotation information; Perform data segmentation on the historical operation record log according to the multiple fault annotation information to determine a training data set and a validation data set; Conduct supervised training iteration based on the training data set. When the training data set tends to converge, use the validation data set for cross-validation, and obtain the fault prediction model according to the validation result; Synchronize the real-time operation data set to the fault prediction model for prediction calculation to determine the operation health score of the material conveyor. The method includes: Load the fault prediction model, synchronize the real-time operation data set to the fault prediction model to conduct operation prediction on the material conveyor, and generate an operation fault prediction result; Map the historical operation record log to the operation fault prediction result for association to determine an operation fault association list; Perform fault calculations according to the described operation fault association list, generate multiple fault probabilities, and perform health assessment based on the multiple fault probabilities to generate the operation health score; Perform fault determination on the material conveyor according to the operation health score, determine the fault risk level, generate a warning signal according to the fault risk level, and send the warning signal to a remote terminal for intelligent warning feedback of the fault. The method includes: Set an expected operation threshold based on the historical operation record log, perform fault determination on the material conveyor according to the expected operation threshold and the operation health score, and generate a fault determination result; Perform critical analysis according to the fault determination result, determine the fault risk data matrix, and correct the fault risk data matrix based on the multiple operation characteristics to generate the fault risk level; Match the fault risk level to the operation health score to generate a status signal set, and the status signal set includes a normal status signal, a warning status signal, and a fault status signal; Screen the normal status signal, the warning status signal, and the fault status signal according to the fault risk level, determine the warning signal, and send it to the remote terminal for warning feedback.

2. The data-driven fault warning method for a material conveyor according to claim 1, wherein Perform fault determination on the material conveyor according to the expected operation threshold and the operation health score, and generate a fault determination result. The method includes: Compare the operation health score with the expected operation threshold to determine whether the operation health score is greater than or equal to the expected operation threshold; If the operation health score is greater than or equal to the expected operation threshold, obtain normal operation data, perform continuous operation monitoring according to the normal operation data, generate an operation monitoring instruction, and add the operation monitoring instruction to the fault determination result; If the operation health score is less than the expected operation threshold, generate an abnormal operation data set, perform fault impact analysis according to the abnormal operation data set, and generate an operation impact factor; Perform weight allocation on the abnormal operation data set according to the operation impact factor to determine multiple weight coefficients; Associate the multiple weight coefficients with the abnormal operation data set to generate the fault determination result.

3. Data-driven fault warning system for material conveyors, characterized in that, The system is used to implement the data-driven material conveyor fault warning method described in any one of claims 1-2, and includes: A data acquisition module for traversing a plurality of sensors arranged on the material conveyor for real-time acquisition to obtain a real-time operation data set of the material conveyor; A feature extraction module for performing multi-dimensional analysis based on the real-time operation data set, determining multi-dimensional operation data, and performing time series decomposition according to the multi-dimensional operation data to extract multiple operation characteristics; A learning and training module for retrieving the historical operation record log of the material conveyor, performing learning and training according to the historical operation record log, and obtaining a fault prediction model; A prediction calculation module for synchronizing the real-time operation data set to the fault prediction model for prediction calculation to determine the operation health score of the material conveyor; A fault determination module is used to determine faults of the material conveyor according to the running health score, determine the fault risk level, generate a warning signal according to the fault risk level, and send the warning signal to a remote terminal for intelligent warning feedback of the fault.

Images