Abnormal joint monitoring and predicting method for belt conveyor

Abstract

The embodiment of the invention provides a combined monitoring and predicting method for abnormity of a belt conveyor, and relates to the technical field of digital intelligent monitoring and analysis of abnormity of the belt conveyor. The method comprises the following steps: respectively determining to-be-analyzed constituent parts in the belt conveyor, to-be-analyzed constituent elements in each constituent part and operation abnormity types of all the constituent elements; constructing an operation exception type set based on all the operation exception types; acquiring operation data of each component element, wherein the operation data comprises image data and time sequence data; and performing single-point anomaly analysis on each component element based on the operation data and the operation anomaly type set, and performing joint anomaly analysis based on a single-point analysis anomaly result. According to the technical scheme, the problem of cause analysis of various types of abnormity of the belt conveyor is systematically solved, and joint monitoring and prediction of various types of abnormity are achieved.

Description

Technical Field

[0001] The present application relates to the technical field of digital intelligent monitoring and analysis of belt conveyor anomalies, and specifically, to a method for joint monitoring and prediction of belt conveyor anomalies. Background Art

[0002] Belt conveyor is a mechanical device that uses conveyor belts to achieve long-distance continuous material transportation. Thanks to its advantages such as flexible line layout, large conveying capacity and fast conveying speed, it is now widely used in various industries such as mining, docks, and chemicals. Due to its long conveying distance and large number of parts and components, it needs to be monitored and maintained to ensure its long-term continuous transportation requirements.

[0003] The traditional maintenance method requires maintenance personnel to inspect and maintain the conveyor belt to ensure the safe operation of the belt conveyor. On the one hand, this operation and maintenance method requires a lot of manpower costs; on the other hand, manual inspection can only be done after the failure occurs and regular preventive maintenance, and the monitoring accuracy is difficult to guarantee. Therefore, in practice, various sensors are generally arranged at specific locations to continuously monitor the status of the belt conveyor using physical and mechanical principles. However, this method is difficult to fully reflect the operating characteristics of the belt conveyor, and it is also difficult to analyze the potential failures that may occur in the belt conveyor.

[0004] In order to overcome the above difficulties, many advanced belt conveyor monitoring technologies combine machine learning with sensors to accurately analyze the operating status of belt conveyors. For example, Chinese patent document CN118334475B proposes a belt conveyor anomaly detection model training method and an anomaly real-time monitoring method based on computer vision. Through machine learning technology, the data obtained by sensors and cameras are further effectively utilized to improve the accuracy of monitoring. Chinese patent document CN117876363B uses image processing technology to analyze the running image of rollers, thereby improving the accuracy of real-time monitoring of rollers. The above technologies only focus on single-point status monitoring, and a small number of existing technologies have further realized fault prediction on the basis of status monitoring (see CN116424768B, CN115510901B).

[0005] However, these methods only consider the analysis of the operating status of the belt conveyor, without considering the causes of faults and abnormalities. Analyzing the causes of various abnormalities of the belt conveyor and actively monitoring the abnormalities are the key means to further improve the accuracy and timeliness of belt conveyor fault prediction. Summary of the invention

[0006] The embodiments of the present application provide a belt conveyor abnormality joint monitoring and prediction method to solve the problem of cause analysis of various abnormalities of the belt conveyor.

[0007] Other features and advantages of the present application will become apparent from the following detailed description, or may be learned in part by the practice of the present application.

[0008] According to a first aspect of an embodiment of the present application, a belt conveyor abnormality joint monitoring and prediction method is provided, comprising:

[0009] Determine the components to be analyzed in the belt conveyor, the elements to be analyzed in each component, and the abnormal operation type of each element;

[0010] Build a set of operation exception types based on all operation exception types;

[0011] Collecting operation data of each component element, wherein the operation data includes image data and time series data;

[0012] A single-point anomaly analysis is performed on each component element based on the operation data and the operation anomaly type set, and a joint anomaly analysis is performed based on the single-point analysis anomaly results.

[0013] In some embodiments of the present application, based on the aforementioned solution, the performing single-point abnormality analysis on each component element based on the operation data and the operation abnormality type set includes:

[0014] Traversing all the operation exception types in the operation exception type set;

[0015] Based on the operation data, it is determined whether a certain type of abnormality in the operation abnormality type has occurred in the component elements. If the certain type of abnormality has occurred, an alarm message is issued. If the certain type of abnormality has not occurred, the probability and time of occurrence of the certain type of abnormality are obtained by analysis and calculation based on the operation data.

[0016] In some embodiments of the present application, based on the above solution, the step of judging whether a component element has experienced a certain type of abnormality in the abnormal operation type based on the operation data includes:

[0017] When the operation data is image data, a visual analysis method is used to determine whether a component element has experienced a certain type of abnormality among the operation abnormality types;

[0018] When the operation data is time series data, a time series analysis method is used to determine whether a certain type of abnormality in the operation abnormality type has occurred in the component element.

[0019] In some embodiments of the present application, based on the above solution, the visual analysis method is used to determine whether a component element has a certain type of abnormality in the operation abnormality type, including:

[0020] Performing filtering processing on the image data;

[0021] Using the target detection algorithm model to obtain multiple target detection frames in the image data and the confidences corresponding to the multiple target detection frames;

[0022] A confidence threshold is set, and based on the confidences corresponding to the multiple target detection boxes and the confidence threshold, it is determined whether a certain type of abnormality in the operation abnormality type has occurred in the component element.

[0023] In some embodiments of the present application, based on the above solution, the time series analysis method is used to determine whether a component element has experienced a certain type of abnormality in the operation abnormality type, including:

[0024] Performing low-pass filtering on the time series data;

[0025] Use recurrent neural network to fit the filtered time series data;

[0026] Based on the filtered time series data and the fitted data series data, it is determined whether a certain type of abnormality in the operation abnormality type has occurred in the component element.

[0027] In some embodiments of the present application, based on the above solution, the probability of occurrence of the certain type of abnormality is obtained by analyzing and calculating based on the operating data, including:

[0028] When the operation data is image data, a visual analysis method is used to calculate the occurrence probability of the certain type of abnormality;

[0029] When the operating data is a time series, the time series analysis method is used to calculate the occurrence probability of the certain type of abnormality.

[0030] In some embodiments of the present application, based on the above solution, the method of using a visual analysis method to calculate the probability of occurrence of the certain type of abnormality includes:

[0031] Using the target detection algorithm model to obtain multiple target detection frames in the image data and the confidences corresponding to the multiple target detection frames;

[0032] The confidence level of each target detection frame is calibrated using Pratt scaling to obtain the abnormal probability of each target detection frame.

[0033] The probability of occurrence of a certain type of abnormality in the image data is obtained based on the abnormality probability corresponding to each target detection frame.

[0034] In some embodiments of the present application, based on the above scheme, the time series analysis method is used to calculate the occurrence probability of the certain type of abnormality, including:

[0035] By using the Gaussian distribution model, the error between the filtered time series data and the fitted data series data is converted into probability, and the occurrence probability of the aforementioned type of anomaly is obtained.

[0036] In some embodiments of the present application, based on the above solution, analyzing and calculating the operation data to obtain the occurrence time of the certain type of abnormality includes:

[0037] The occurrence probability of the certain type of abnormality is fitted using a recurrent neural network to obtain the occurrence time of the certain type of abnormality.

[0038] In some embodiments of the present application, based on the aforementioned solution, the joint abnormality analysis based on the abnormal results of single-point analysis includes:

[0039] Traversing all the operation exception types in the operation exception type set;

[0040] Determine whether the certain type of exception will trigger other exceptions in the operation exception type, and if so, update the occurrence probability and occurrence time of the other exceptions based on the occurrence probability and occurrence time of the certain type of exception;

[0041] If not, determine whether the other exceptions will trigger the certain type of exceptions. If so, update the probability and time of occurrence of the certain type of exceptions based on the probability and time of occurrence of the other exceptions.

[0042] According to a second aspect of an embodiment of the present application, a system applied to the method according to the first aspect is provided, including:

[0043] Data acquisition module, used to collect the operation data of each component element;

[0044] Anomaly analysis module, used to perform single-point anomaly analysis and joint anomaly analysis on each component element;

[0045] The result output module is used to output the abnormality analysis results.

[0046] According to a third aspect of an embodiment of the present application, a computer-readable storage medium is provided, wherein the storage medium stores computer instructions, and when the computer instructions are executed on a computer, the computer executes the method according to the first aspect.

[0047] According to a fourth aspect of the embodiments of the present application, there is provided an electronic device, including a memory and a processor;

[0048] The memory is used to store computer instructions;

[0049] The processor is used to call the computer instructions stored in the memory so that the electronic device executes the method as described in the first aspect.

[0050] The beneficial effects of this application are:

[0051] (1) The present application realizes the monitoring, analysis and calculation of the causes of abnormalities by classifying the causes of various abnormalities as abnormalities and combining sensor monitoring, single-point monitoring, single-point prediction, linkage prediction and other methods.

[0052] (2) This application considers the single-point monitoring and single-point prediction of each abnormality, ensuring timely response to the abnormality. It further considers the triggering of other abnormalities by each abnormality or potential abnormality, conducts linkage analysis and joint prediction of various abnormalities, and makes judgments before the abnormality occurs, thereby improving the accuracy of belt conveyor abnormality prediction.

[0053] (3) This application realizes continuous two-way analysis of various anomalies and real-time updating of calculation results by traversal and looping, thus ensuring the timeliness of belt conveyor anomaly prediction results.

[0054] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] The drawings herein are incorporated into the specification and constitute a part of the specification, showing embodiments consistent with the present application, and together with the specification, are used to explain the principles of the present application. Obviously, the drawings described below are only some embodiments of the present application, and for ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. In the drawings:

[0056] Figure 1 A schematic flow chart of a belt conveyor abnormality joint monitoring and prediction method according to an embodiment of the present application is shown;

[0057] Figure 2 A structural block diagram of a belt conveyor abnormality joint monitoring and prediction system according to an embodiment of the present application is shown;

[0058] Figure 3 A schematic diagram of an application of an embodiment of the present application on a suspended cable wheel-rail belt conveyor is shown;

[0059] Figure 4 A block diagram of an electronic device according to an embodiment of the present application is shown;

[0060] Figure 5 A schematic diagram of the structure of a computer system suitable for implementing an electronic device of an embodiment of the present application is shown. DETAILED DESCRIPTION

[0061] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in a variety of forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this application will be more comprehensive and complete and fully convey the concept of the example embodiments to those skilled in the art.

[0062] In addition, described feature, structure or characteristic can be combined in one or more embodiments in any suitable manner. In the following description, many specific details are provided to provide a full understanding of the embodiments of the present application. However, those skilled in the art will appreciate that the technical scheme of the present application can be put into practice without one or more of the specific details, or other methods, components, devices, steps, etc. can be adopted. In other cases, known methods, devices, realizations or operations are not shown or described in detail to avoid blurring the various aspects of the application.

[0063] The block diagrams shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically independent entities. That is, these functional entities may be implemented in software form, or in one or more hardware modules or integrated circuits, or in different networks and / or processor devices and / or microcontroller devices.

[0064] The flowcharts shown in the accompanying drawings are only exemplary and do not necessarily include all the contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps can be decomposed, and some operations / steps can be combined or partially combined, so the actual execution order may change according to actual conditions.

[0065] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution in the embodiment of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiment of the present invention. Obviously, the described embodiment is only a part of the embodiment of the present invention, not all the embodiments. Based on the embodiment of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0066] Some embodiments of the present application will be described in detail below in conjunction with the accompanying drawings. In the absence of conflict, the following embodiments and features in the embodiments may be combined with each other.

[0067] See also Figure 1 , showing a flow chart of a belt conveyor abnormality joint monitoring and prediction method according to an embodiment of the present application.

[0068] like Figure 1 As shown, a method for joint monitoring and prediction of belt conveyor abnormalities is presented, which specifically includes steps S100 to S400.

[0069] refer to Figure 1 , step S100, respectively determining the components to be analyzed in the belt conveyor, the constituent elements to be analyzed in each component, and the operation abnormality type of each constituent element.

[0070] In some feasible embodiments, based on the above scheme, the components to be analyzed in the belt conveyor include at least one of a conveyor belt, a drive assembly, a load-bearing component, a material, a structural component, and an environment.

[0071] Exemplarily, in this embodiment, the belt conveyor is composed of a conveyor belt, a drive assembly, a load-bearing component, materials, structural parts and an environment.

[0072] It should be noted that the constituent elements refer to the elements that constitute the components. For example, the constituent elements of the conveyor belt are the trough conveyor belt; the constituent elements of the drive assembly are the motor, the reducer, and the transmission roller; the constituent elements of the load-bearing components are the driven roller and the roller; the constituent elements of the material are iron ore; the constituent elements of the structural parts are the tensioning car and the chute; the constituent elements of the environment are wind speed and direction, and dust concentration.

[0073] It should be noted that the operation abnormality type refers to various abnormal situations that occur during the operation of the component elements.

[0074] Exemplarily, the types of conveyor belt operation abnormalities include tearing, belt breakage, and slipping; the types of drive assembly operation abnormalities include motor abnormalities, reducer abnormalities, and transmission roller abnormalities; the types of load-bearing component operation abnormalities include roller abnormalities and driven roller abnormalities; the types of material operation abnormalities include large pieces of material and sharp materials; the types of structural parts operation abnormalities include tensioning car abnormalities and slide pipe seal abnormalities; the types of environmental operation abnormalities include wind direction and wind speed abnormalities and dust concentration abnormalities.

[0075] Continue to refer Figure 1 , step S200, constructing an operation exception type set based on all operation exception types.

[0076] It can be understood that the operation exception type set includes all operation exception types corresponding to all constituent elements corresponding to all components.

[0077] Continue to refer Figure 1 , step S300, collecting operation data of each component element, wherein the operation data includes image data and time series data.

[0078] In some feasible embodiments, based on the above solution, the collecting of the operation data of each component element includes:

[0079] Arrange sensing equipment to collect operating data of each component element, wherein the sensing equipment includes: at least one of a high-speed camera, a high-definition camera, a thermal imaging camera, a temperature and vibration sensor, a noise sensor, an optical fiber sensor, a rotation speed sensor, a wind speed and direction sensor, and a tension sensor.

[0080] It should be noted that the number of selected sensing devices is related to the components of the belt conveyor. For example, when the components of the belt conveyor do not have an environment, the sensing device does not need to be a wind speed and direction sensor.

[0081] Exemplarily, the sensing devices arranged in this example include a high-speed camera, a high-definition camera, a thermal imaging camera, a temperature and vibration sensor, a noise sensor, an optical fiber sensor, a rotation speed sensor, a wind speed and direction sensor, and a tension sensor.

[0082] Among them, the operating data obtained by high-speed cameras, high-definition cameras and thermal imaging cameras belong to image data, and the operating data obtained by noise sensors, optical fiber sensors, rotation speed sensors, wind speed and direction sensors and tension sensors belong to time series data.

[0083] Continue to refer Figure 1 , step S400, performing single-point anomaly analysis on each component element based on the operation data and the operation anomaly type set, and performing joint anomaly analysis based on the single-point analysis anomaly results.

[0084] In some feasible embodiments, based on the above solution, the performing single-point anomaly analysis on each component element based on the operation data and the operation anomaly type set includes:

[0085] Traversing all the operation exception types in the operation exception type set;

[0086] Based on the operation data, it is determined whether a certain type of abnormality in the operation abnormality type has occurred in the component elements. If the certain type of abnormality has occurred, an alarm message is issued. If the certain type of abnormality has not occurred, the probability and time of occurrence of the certain type of abnormality are obtained by analysis and calculation based on the operation data.

[0087] In some feasible embodiments, based on the above solution, judging whether a component element has a certain type of abnormality in the abnormal operation type based on the operation data includes:

[0088] When the operation data is image data, a visual analysis method is used to determine whether a component element has experienced a certain type of abnormality among the operation abnormality types;

[0089] When the operation data is time series data, a time series analysis method is used to determine whether a certain type of abnormality in the operation abnormality type has occurred in the component element.

[0090] In some feasible embodiments, based on the above solution, the visual analysis method is used to determine whether a component element has a certain type of abnormality in the operation abnormality type, including:

[0091] Performing filtering processing on the image data;

[0092] Using the target detection algorithm model to obtain multiple target detection frames in the image data and the confidences corresponding to the multiple target detection frames;

[0093] A confidence threshold is set, and based on the confidences corresponding to the multiple target detection boxes and the confidence threshold, it is determined whether a certain type of abnormality in the operation abnormality type has occurred in the component element.

[0094] Exemplarily, the specific process of using the visual analysis method to determine whether a component element has experienced a certain type of abnormality in the operation abnormality type is as follows:

[0095] Let image data I(x,y) be a two-dimensional grayscale function that converts pixels with coordinates x and y into grayscale values. Represents a neighborhood window containing all pixels around the pixel point (x, y). Apply the median filter formula to filter the image data I(x, y) to obtain the image I pre (x,y):

[0096]

[0097] Among them, Median(·) is the median function.

[0098] The filtered image data I pre (x,y) input YOLOv5x model, get {(R i ,p i |i=1,2,…,N}. Among them, R i ={x min ,x max ,y min ,y max} is the bounding box of the i-th target, p i is the confidence that the i-th target is classified as an anomaly.

[0099] Let the confidence threshold p * =0.8. If there exists at least one i=1,2,…,N such that p i ≥p * , it is determined that an abnormality occurs.

[0100] It should be noted that YOLOv5x is the fifth version of the YOLO series, where "x" represents the optimized balance between speed and accuracy. YOLO, the full name of "You Only Look Once", is a popular object detection algorithm. It converts the object detection task into a regression problem and completes the object detection of the entire image with a single convolutional layer feedforward. The YOLO algorithm has the characteristics of fast speed, simple model, and strong adaptability.

[0101] In some feasible embodiments, based on the above solution, the time series analysis method is used to determine whether a component element has experienced a certain type of abnormality in the operation abnormality type, including:

[0102] Performing low-pass filtering on the time series data;

[0103] Use recurrent neural network to fit the filtered time series data;

[0104] Based on the filtered time series data and the fitted data series data, it is determined whether a certain type of abnormality in the operation abnormality type has occurred in the component element.

[0105] Exemplarily, the specific process of using the time series analysis method to determine whether a component element has experienced a certain type of abnormality in the operation abnormality type is as follows:

[0106] For any time t in the time series data, the time series signal is represented by x t , low-pass filtering is applied to the signal. The filter order is set to 2 and the cutoff frequency is 10HZ. The filtered signal is represented by X t .

[0107] {X 1 ,X 2 ,…,X t}Use LSTM to fit. Among them, for any time i, (1≤i≤t), the input of LSTM is Input i ={X i-5 ,X i-4 ,…,X i}, the output is

[0108] For time t, if the difference between the actual data and the predicted data Then it is determined that an abnormality occurs. Where σ is the standard deviation of the error in the previous t moments.

[0109] In some feasible embodiments, based on the above solution, the probability of occurrence of the certain type of abnormality is obtained by analyzing and calculating based on the operating data, including:

[0110] When the operation data is image data, a visual analysis method is used to calculate the occurrence probability of the certain type of abnormality;

[0111] When the operating data is a time series, the time series analysis method is used to calculate the occurrence probability of the certain type of abnormality.

[0112] In some feasible embodiments, based on the above solution, the method of using a visual analysis method to calculate the probability of occurrence of the certain type of abnormality includes:

[0113] Using the target detection algorithm model to obtain multiple target detection frames in the image data and the confidences corresponding to the multiple target detection frames;

[0114] The confidence level of each target detection frame is calibrated using Pratt scaling to obtain the abnormal probability of each target detection frame.

[0115] The probability of occurrence of a certain type of abnormality in the image data is obtained based on the abnormality probability corresponding to each target detection frame.

[0116] Exemplarily, based on the above example, the specific process of using the visual analysis method to calculate the probability of occurrence of the aforementioned type of abnormality is as follows:

[0117] For the filtered image I pre (x, y), get N detection boxes R through YOLOv5x output i , and its corresponding confidence level p i , i=1,2,…,N.

[0118] For each detection box R i , Platt Sacling is used to calibrate the confidence level and obtain the abnormal probability P i :

[0119] P i (abnormal) = 1 / (1+exp(-a·P i -b)),

[0120] Among them, a and b are determined by using the maximum likelihood estimation method on the validation set.

[0121] For each image I pre (x, y), the probability of the overall abnormality is calculated by the following formula:

[0122]

[0123] In some feasible embodiments, based on the above scheme, the time series analysis method is used to calculate the occurrence probability of the certain type of abnormality, including:

[0124] By using the Gaussian distribution model, the error between the filtered time series data and the fitted data series data is converted into probability, and the occurrence probability of the aforementioned type of anomaly is obtained.

[0125] Exemplarily, based on the above example, the specific process of using the time series analysis method to calculate the probability of occurrence of the above-mentioned type of abnormality is as follows:

[0126] For any time t in the time series data, the error between the predicted value and the true value is Convert it into probability through Gaussian distribution model:

[0127]

[0128] In some feasible embodiments, based on the above solution, analyzing and calculating the operation data to obtain the occurrence time of the certain type of abnormality includes:

[0129] The occurrence probability of the certain type of abnormality is fitted using a recurrent neural network to obtain the occurrence time of the certain type of abnormality.

[0130] Exemplarily, based on the above example, the specific process of analyzing and calculating the occurrence time of the certain type of abnormality based on the operation data is as follows:

[0131] Let the current time be t. The occurrence probability calculated by visual analysis and time series analysis is uniformly expressed as Will Fitted with LSTM. For any time i, (1≤i≤t), the input of LSTM is The output is

[0132] For time t, LSTM prediction using fitting For each subsequent time t+j, (j≥1), the Input t+j-1 Delete the first element in and Put it into the collection as the last element to construct the Input t+j . Further Input t+j Input LSTM, prediction

[0133] Set the threshold ε = 0.5, when When t+j is output, the time prediction of the fault occurrence is t+j.

[0134] In some feasible embodiments, based on the above solution, the joint abnormality analysis based on the abnormal results of single-point analysis includes:

[0135] Traversing all the operation exception types in the operation exception type set;

[0136] Determine whether the certain type of exception will trigger other exceptions in the operation exception type, and if so, update the occurrence probability and occurrence time of the other exceptions based on the occurrence probability and occurrence time of the certain type of exception;

[0137] If not, determine whether the other exceptions will trigger the certain type of exceptions. If so, update the probability and time of occurrence of the certain type of exceptions based on the probability and time of occurrence of the other exceptions.

[0138] For example, a specific update process of the probability of occurrence of another anomaly or a certain type of anomaly is given:

[0139] For any time t, the probability of a certain type of anomaly A occurring is expressed as The probability of another type of anomaly B occurring is expressed as Then, if exception B can cause exception A, the probability of exception A occurring is updated as follows:

[0140]

[0141] in, It represents the probability that abnormality A will be triggered after abnormality B occurs. This probability value is estimated by the results of 100 independent repeated experiments in the experimental stage.

[0142] It is understandable that after the probability of occurrence of other anomalies or a certain type of anomalies is updated, the specific process of analyzing and calculating the occurrence time of the certain type of anomalies based on the operating data described above is used to update the occurrence time of other anomalies or a certain type of anomalies.

[0143] Exemplarily, a specific process of step S400 is provided below.

[0144] Step S401: traverse each component and execute step S402 for each component. In this example, the conveyor belt, drive assembly, load-bearing components, materials, structural parts, and environment are traversed in sequence;

[0145] Step S402: traverse each component element under the current component, and execute step S403 for each component element. In the example, the conveyor belt only has a trough conveyor belt, which does not need to be traversed; the drive assembly is traversed in the order of motor, reducer, and transmission roller; the bearing component is traversed in the order of driven roller and roller; the material is only iron ore, which does not need to be traversed; the structural parts are traversed in the order of tensioner and chute; the environment is traversed in the order of wind speed and direction, and dust concentration;

[0146] Step S403: traverse the abnormality types to be analyzed for the current element, and execute step S404 for each type of abnormality. In this example, traverse in the order of tearing, belt breakage, slippage, motor abnormality, reducer abnormality, drive roller abnormality, driven roller abnormality, roller abnormality, bulk material, sharp material, tensioner abnormality, slide pipe abnormality, wind direction and wind speed abnormality, and dust concentration abnormality;

[0147] Step S404: Analyze the operation data and determine whether a certain type of abnormality has occurred. If a certain type of abnormality has occurred, an alarm is triggered, and then step S405 is executed; if a certain type of abnormality has not occurred, the operation data is analyzed, the probability and time of the occurrence of a certain type of abnormality are calculated, updated and output, and then step S405 is executed;

[0148] Step S405: traverse each component, and execute step S406 for each component. In this example, the traversal order refers to the above step S401;

[0149] Step S406: traverse the elements under the current component and execute step S407 for each element. In this example, the traversal order refers to the above step S402;

[0150] Step S407: traverse the abnormality types to be analyzed for the current element, and execute step S408 for each type of abnormality. In this example, the traversal order refers to the above step S403;

[0151] Step S408: determining whether other abnormalities in the operation abnormality types except the abnormality of the certain type are caused by the abnormality of the certain type in step S404; if so, calculating, updating and outputting the occurrence probability and time of the other abnormalities based on the analysis and calculation results of step S404; if not, directly executing step S409;

[0152] Step S409: Determine whether the other exceptions will trigger a certain type of exception in step S404. If yes, calculate, update and output the occurrence probability and time of the certain type of exception in step S404 based on the analysis and calculation results of step S404 and step S408; if no, skip the current exception;

[0153] Step S410: After the traversal is completed, step S401 is repeatedly executed until the belt conveyor is shut down for maintenance. In this example, the belt conveyor is fixedly shut down at 8 pm every day and is shut down for maintenance when encountering a major abnormality.

[0154] Based on the same inventive concept, the present application also provides a system for use in the method described in any of the above embodiments. Figure 2 , the system comprises:

[0155] Data acquisition module, used to collect the operation data of each component element;

[0156] Anomaly analysis module, used to perform single-point anomaly analysis and joint anomaly analysis on each component element;

[0157] The result output module is used to output the abnormality analysis results.

[0158] like Figure 2 As shown, the data acquisition module includes: a high-speed camera, a thermal imaging camera, a temperature and vibration sensor, an optical fiber sensor, a rotation speed sensor, a wind speed and direction sensor, and a tension sensor.

[0159] The abnormality analysis module includes: a conveyor belt abnormality analysis module, a drive assembly abnormality analysis module, a load-bearing component abnormality analysis module, a material abnormality analysis module, an environmental abnormality analysis module, and a structural component abnormality analysis module.

[0160] The result output module includes: an abnormality detection result output module and an abnormality prediction result output module.

[0161] Among them, the conveyor belt abnormality analysis module, the drive assembly abnormality analysis module, the load-bearing component abnormality analysis module, the material abnormality analysis module, the environmental abnormality analysis module, and the structural component abnormality analysis module respectively include: an abnormal single point real-time detection module, an abnormal single point prediction module, and an abnormal joint prediction module; used for abnormal single point real-time monitoring, single point prediction, linkage analysis, and joint prediction of each component. For example, the abnormal situation of the conveyor belt can be obtained by using a camera to obtain the running image of the conveyor belt, and the conveyor belt single point real-time monitoring and conveyor belt single point prediction modules can be used to determine the damage and abnormal situation of the conveyor belt. At the same time, by obtaining the abnormality of sharp materials and using the conveyor belt joint prediction module to analyze the scratches of sharp materials on the conveyor belt, the accuracy of conveyor belt tearing abnormalities can be further improved.

[0162] It should be noted that there is a data connection between all abnormal single-point real-time detection modules, abnormal single-point prediction modules, and abnormal joint prediction modules to ensure the two-way transmission of data and calculation results. For example, the failure of the tensioning car may cause slipping, and slipping may also reflect the failure of the tensioning car. Therefore, the abnormal single-point real-time detection module, abnormal single-point prediction module, and abnormal joint prediction module for tensioning car abnormalities and slipping abnormalities should have the function of two-way transmission.

[0163] The following is an example of the application of the technical solution of the present application on a suspended cable wheel-rail belt conveyor.

[0164] like Figure 3As shown in the figure, in this example, the data acquisition equipment consists of a camera, a temperature and vibration sensor, a speed sensor, and a fiber optic sensor. The AI ​​big model consisting of a visual big model and a prediction big model is used for real-time monitoring and single-point prediction of various abnormalities.

[0165] In this example, the components of the conveyor are composed of a conveyor belt, a drive assembly, load-bearing components, structural parts, materials, and the environment. The conveyor belt is a trough-type conveyor belt; the drive assembly is composed of a motor, a reducer, and a transmission roller; the load-bearing components are composed of: a trolley, an idler, and a driven roller; the structural parts are composed of a wire rope and a track; the material is coal mine; and the environment is composed of wind direction, wind speed, and dust concentration.

[0166] The abnormalities that need to be monitored for the suspended wheel-rail belt conveyor include tearing, belt breakage, slipping, drive, motor abnormality, reducer abnormality, transmission roller, trolley abnormality, roller abnormality, driven roller abnormality, wire rope abnormality, track abnormality, large pieces of material, sharp foreign objects, abnormal wind direction and speed, and abnormal dust concentration.

[0167] In this example, the AI ​​big model is used to perform single-point real-time monitoring and single-point prediction of various anomalies, and further use Figure 3 The cable-suspended wheel-rail belt conveyor abnormality mechanism model shown in the figure establishes a two-way connection between various abnormalities, and finally uses the discrete event-driven belt conveyor abnormality joint monitoring and prediction method provided by the technical solution of the present application to continuously monitor the conveyor.

[0168] like Figure 4 As shown, an embodiment of the present application also provides an electronic device 400, including a memory 410, a processor 420, and a computer program 411 stored in the memory 410 and executable on the processor. When the processor 420 executes the computer program 411, the steps of the above-mentioned method for joint monitoring and prediction of belt conveyor abnormalities are implemented.

[0169] Since the electronic device introduced in this embodiment is a device used to implement a belt conveyor abnormality joint monitoring and prediction system in the embodiment of the present application, based on the method introduced in the embodiment of the present application, the technical personnel in this field can understand the specific implementation mode of the electronic device of this embodiment and its various variations. Therefore, how the electronic device implements the method in the embodiment of the present application is not introduced in detail here. As long as the equipment used by the technical personnel in this field to implement the method in the embodiment of the present application is within the scope of protection of this application.

[0170] During the specific implementation process, when the computer program 411 is executed by a processor, any implementation method in the embodiments corresponding to the first aspect can be implemented.

[0171] Figure 5A schematic diagram of the structure of a computer system suitable for implementing an electronic device of an embodiment of the present application is shown.

[0172] It should be noted that Figure 5 The computer system 500 of the electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0173] like Figure 5 As shown, the computer system 500 includes a central processing unit (CPU) 501, which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM) 502 or the program loaded from the storage part 508 to the random access memory (RAM) 503, such as executing the method described in the above embodiment. In the RAM 503, various programs and data required for system operation are also stored. The CPU 501, the ROM 502 and the RAM 503 are connected to each other through the bus 504. The input / output (I / O) interface 505 is also connected to the bus 504.

[0174] The following components are connected to the I / O interface 505: an input section 506 including a keyboard, a mouse, etc.; an output section 507 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker; a storage section 508 including a hard disk, etc.; and a communication section 509 including a network interface card such as a LAN (Local Area Network) card, a modem, etc. The communication section 509 performs communication processing via a network such as the Internet. A drive 510 is also connected to the I / O interface 505 as needed. A removable medium 511, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 510 as needed so that a computer program read therefrom is installed into the storage section 508 as needed.

[0175] In particular, according to an embodiment of the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present application includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication section 509, and / or installed from a removable medium 511. When the computer program is executed by a central processing unit (CPU) 501, various functions defined in the system of the present application are executed.

[0176] It should be noted that the computer-readable medium shown in the embodiment of the present application may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, - but not limited to - an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a flash memory, an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, a computer-readable storage medium may be any tangible medium containing or storing a program, which may be used by an instruction execution system, device or device or used in combination with it. In the present application, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, wherein a computer-readable program code is carried. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, which may send, propagate, or transmit programs for use by or in conjunction with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wired, etc., or any suitable combination of the above.

[0177] The flowchart and block diagram in the accompanying drawings illustrate the possible architecture, functions and operations of the system, method and computer program product according to various embodiments of the present application. Wherein, each box in the flowchart or block diagram can represent a module, a program segment, or a part of the code, and the above-mentioned module, program segment, or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flowchart, and the combination of boxes in the block diagram or flowchart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0178] The units involved in the embodiments described in this application may be implemented by software or hardware, and the units described may also be set in a processor. The names of these units do not, in some cases, constitute limitations on the units themselves.

[0179] As another aspect, the present application also provides a computer program product or a computer program, which includes computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes a belt conveyor abnormality joint monitoring and prediction method described in the above embodiment.

[0180] As another aspect, the present application also provides a computer-readable medium, which may be included in the electronic device described in the above embodiment; or may exist independently without being assembled into the electronic device. The above computer-readable medium carries one or more programs, and when the above one or more programs are executed by an electronic device, the electronic device implements a belt conveyor abnormality joint monitoring and prediction method described in the above embodiment.

[0181] It should be noted that, although several modules or units of the equipment for action execution are mentioned in the above detailed description, this division is not mandatory. In fact, according to the embodiments of the present application, the features and functions of two or more modules or units described above can be embodied in one module or unit. On the contrary, the features and functions of one module or unit described above can be further divided into being embodied by multiple modules or units.

[0182] Through the description of the above implementation methods, it is easy for those skilled in the art to understand that the example implementation methods described here can be implemented by software or by combining software with necessary hardware. Therefore, the technical solution according to the implementation methods of the present application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, and includes several instructions to enable a computing device (which can be a personal computer, a server, a touch terminal, or a network device, etc.) to execute the method according to the implementation methods of the present application.

[0183] Those skilled in the art will readily appreciate other embodiments of the present application after considering the specification and practicing the embodiments disclosed herein. The present application is intended to cover any variations, uses or adaptations of the present application, which follow the general principles of the present application and include common knowledge or customary techniques in the art that are not disclosed in the present application. It should be understood that the present application is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from the scope thereof. The scope of the present application is limited only by the appended claims.

Claims

1. A belt conveyor abnormality joint monitoring and prediction method, characterized in that: include: Determine the components to be analyzed in the belt conveyor, the elements to be analyzed in each component, and the abnormal operation type of each element; Build a set of operation exception types based on all operation exception types; Collecting operation data of each component element, wherein the operation data includes image data and time series data; A single-point anomaly analysis is performed on each component element based on the operation data and the operation anomaly type set, and a joint anomaly analysis is performed based on the single-point analysis anomaly results.

2. The method according to claim 1, characterized in that The performing single-point anomaly analysis on each component element based on the operation data and the operation anomaly type set includes: Traversing all the operation exception types in the operation exception type set; Based on the operation data, it is determined whether a certain type of abnormality in the operation abnormality type has occurred in the component elements. If the certain type of abnormality has occurred, an alarm message is issued. If the certain type of abnormality has not occurred, the probability and time of occurrence of the certain type of abnormality are obtained by analysis and calculation based on the operation data.

3. The method according to claim 2, characterized in that The determining, based on the operation data, whether a component element has experienced a certain type of abnormality in the operation abnormality type includes: When the operation data is image data, a visual analysis method is used to determine whether a component element has experienced a certain type of abnormality among the operation abnormality types; When the operation data is time series data, a time series analysis method is used to determine whether a certain type of abnormality in the operation abnormality type has occurred in the component element.

4. The method according to claim 3, characterized in that The visual analysis method is used to determine whether a component element has experienced a certain type of abnormality in the operation abnormality type, including: Performing filtering processing on the image data; Using the target detection algorithm model to obtain multiple target detection frames in the image data and the confidences corresponding to the multiple target detection frames; A confidence threshold is set, and based on the confidences corresponding to the multiple target detection boxes and the confidence threshold, it is determined whether a certain type of abnormality in the operation abnormality type has occurred in the component element.

5. The method according to claim 4, characterized in that The time series analysis method is used to determine whether a component element has experienced a certain type of abnormality in the operation abnormality type, including: Performing low-pass filtering on the time series data; Use recurrent neural network to fit the filtered time series data; Based on the filtered time series data and the fitted data series data, it is determined whether a certain type of abnormality in the operation abnormality type has occurred in the component element.

6. The method according to claim 5, characterized in that The probability of occurrence of the certain type of abnormality is obtained by analyzing and calculating based on the operation data, including: When the operation data is image data, a visual analysis method is used to calculate the occurrence probability of the certain type of abnormality; When the operating data is a time series, the time series analysis method is used to calculate the occurrence probability of the certain type of abnormality.

7. The method according to claim 6, characterized in that The method of using the visual analysis method to calculate the probability of occurrence of the certain type of abnormality includes: Using the target detection algorithm model to obtain multiple target detection frames in the image data and the confidences corresponding to the multiple target detection frames; The confidence level of each target detection frame is calibrated using Pratt scaling to obtain the abnormal probability of each target detection frame. The probability of occurrence of a certain type of abnormality in the image data is obtained based on the abnormality probability corresponding to each target detection frame.

8. The method according to claim 7, characterized in that The time series analysis method is used to calculate the occurrence probability of the certain type of abnormality, including: By using the Gaussian distribution model, the error between the filtered time series data and the fitted data series data is converted into probability, and the occurrence probability of the aforementioned type of anomaly is obtained.

9. The method according to claim 8, characterized in that The time of occurrence of the certain type of abnormality is obtained by analyzing and calculating based on the operation data, including: The occurrence probability of the certain type of abnormality is fitted using a recurrent neural network to obtain the occurrence time of the certain type of abnormality.

10. The method according to any one of claims 2 to 9, characterized in that: The combined abnormality analysis based on the abnormal results of single-point analysis includes: Traversing all the operation exception types in the operation exception type set; Determine whether the certain type of exception will trigger other exceptions in the operation exception type, and if so, update the occurrence probability and occurrence time of the other exceptions based on the occurrence probability and occurrence time of the certain type of exception; If not, determine whether the other exceptions will trigger the certain type of exceptions. If so, update the probability and time of occurrence of the certain type of exceptions based on the probability and time of occurrence of the other exceptions.

Images