Belt conveyor fault prediction method based on intelligent control

Abstract

The invention relates to the technical field of conveyor management, and particularly discloses a belt conveyor fault prediction method based on intelligent control, which comprises the following steps: setting a monitoring time period, acquiring an impact value, a deviation value and a category coefficient based on monitoring data in the monitoring time period, acquiring a deviation coefficient according to the impact value, the deviation value and the category coefficient, and predicting the fault of a belt conveyor according to the deviation coefficient. And in a plurality of continuous and adjacent monitoring time periods, comparing the offset coefficient with the contrast interval to obtain a judgment result of whether the offset coefficient falls into the contrast interval in different monitoring time periods, obtaining an influence coefficient based on a plurality of judgment results, and predicting the deviation fault according to the influence coefficient. The ultra-long belt conveyor can be effectively monitored and predicted on the basis of saving the cost, and possibility prediction can be carried out on an impending deviation fault.

Description

Technical Field

[0001] The invention relates to the technical field of conveyor management, and in particular to a belt conveyor fault prediction method based on intelligent control. Background Art

[0002] Belt conveyors have various functions and can be used as transfer equipment for products or raw materials in various situations. At present, the development direction of belt conveyors is intelligent control, that is, the use of intelligent control technologies such as status monitoring, intelligent video monitoring, and intelligent speed regulation and an integrated management and control platform to achieve centralized control and unattended operation of belt conveyors, thereby reducing the failure rate of belt conveyors and achieving the purpose of intelligent management and control.

[0003] When belt conveyors are used in situations where they need to be concentrated from multiple locations, such as transporting minerals or express deliveries, they are usually combined with multiple sub-conveyors and a main conveyor. In this case, the main conveyor is usually set very long, making comprehensive data monitoring difficult, and failure of the main conveyor will bring huge losses, which is unacceptable. Therefore, it is extremely important to extend the service life of the main conveyor in this situation and reduce its failure rate.

[0004] There are many types of main conveyor failures, which can usually be detected through status monitoring or intelligent video monitoring. Conveyor belt deviation is a special type of failure. Generally speaking, deviation will cause great damage to the belt conveyor, but the conveyor belt deviation can be corrected in time by a correction device. The correction device adjusts the running direction of the belt by increasing friction, which will cause increased wear on the edge of the belt. In other words, frequent use of the correction device will make the use status of the belt conveyor worse. In other words, how to reduce the use of the correction device is a problem that needs to be solved. In view of this, the present invention proposes a belt conveyor fault prediction method based on intelligent control, which predicts the deviation failure of the main conveyor, and adjusts the sub-conveyor based on intelligent control to reduce the occurrence of the main conveyor deviation problem. Summary of the invention

[0005] The purpose of the present invention is to provide a belt conveyor fault prediction method based on intelligent control to solve the following technical problems:

[0006] How to predict the deviation of the main conveyor and adjust the sub-conveyors based on intelligent control to reduce the occurrence of the main conveyor deviation problem.

[0007] The purpose of the present invention can be achieved through the following technical solutions:

[0008] The belt conveyor fault prediction method based on intelligent control includes the following steps:

[0009] At the intersection of the sub-conveyor and the main conveyor, video monitoring and quality monitoring are performed on the transported goods on the main conveyor and the sub-conveyor to obtain monitoring data;

[0010] Setting a monitoring period and obtaining a shock value, an offset value and a category coefficient based on monitoring data within the monitoring period, and then obtaining an offset coefficient based on the shock value, the offset value and the category coefficient;

[0011] In a plurality of continuous and adjacent monitoring periods, the deviation coefficient is compared with the control interval to obtain a judgment result of whether the deviation coefficient in different monitoring time periods falls into the control interval;

[0012] The influence coefficient is obtained based on multiple judgment results, and then the deviation fault is predicted according to the influence coefficient.

[0014] As a further technical solution of the present invention: the step of obtaining the impact value comprises:

[0015] Through quality monitoring, the mass of transported materials entering the main conveyor from the sub-conveyor during the monitoring period is obtained;

[0016] Obtain image data of the sub-conveyor during the monitoring period through video monitoring, and determine the height difference between the sub-conveyor and the main conveyor, as well as the type of transported objects and the corresponding category coefficient;

[0017] The first correction coefficient is set based on the category coefficient, and the impact value is the product of the denormalized first correction value and the weight of the transported objects entering the main conveyor from the sub-conveyor during the monitoring period, the square of the height difference, and the first correction coefficient.

[0018] As a further technical solution of the present invention: the process of obtaining the offset value includes:

[0019] During the monitoring period, the video frames of the main conveyor belt before and after an impact action are monitored by video;

[0020] Acquire the contour image of the goods falling on the conveyor belt of the main conveyor by contour recognition in the video frame;

[0021] Obtain the centroid of the contour of the main conveyor belt before and after an impact action is completed, and obtain the first distance and the second distance from the two centroids to the center line of the main conveyor belt;

[0022] The offset value is calculated based on the first distance and the second distance.

[0023] As a further technical solution of the present invention: the process of calculating and obtaining the offset value includes:

[0024] By formula:

[0025]

[0026] Among them, De j is the offset value of the jth monitoring period, n is the number of impact actions that occurred during the monitoring period, is the first distance between the centroid of the main conveyor belt contour and the centerline of the main conveyor belt after the ith impact action is completed, is the second distance from the centroid of the main conveyor belt contour to the centerline of the main conveyor belt after the ith impact action is completed, σ 1 is the first de-unitization coefficient, δ is a preset modified distance conversion function, and i is a positive integer greater than 0 and less than n.

[0027] As a further technical solution of the present invention: the process of obtaining the offset coefficient includes:

[0028] By formula:

[0029]

[0030] Where Ex is the offset coefficient of the jth monitoring period, α 1 is the preset first weight coefficient, α 2 is the preset second weight coefficient, ty is the category coefficient, m is the mass of transported goods entering the main conveyor from the sub-conveyor during the monitoring period, h is the height difference, σ 2 is the second de-unitization coefficient, De 0 It is the standard value preset by the offset value.

[0031] As a further technical solution of the present invention: the process of obtaining the judgment result includes:

[0032] The offset coefficient is compared with a pair of preset critical intervals (-k 1 , -k 2 ) and (k 3 , k 4 ) for comparison;

[0033] If the offset coefficient falls within any critical interval, the output judgment result is that there is a landing point offset within the monitoring period.

[0034] Through the above technical solution: a method step for obtaining a judgment result is provided. The judgment of the landing point offset of the present invention is based on the offset coefficient. The offset coefficient takes the offset, impact amount and transport object type as reference variables. The larger the offset or impact amount, the greater the impact of the transport object on the conveyor belt during the impact process, and it can assist in judging the impact direction of the conveyor belt during the impact process.

[0035] As a further technical solution of the present invention: the process of obtaining the influence coefficient based on the judgment result includes:

[0036] By formula:

[0037]

[0038] Among them, Inf is the influence coefficient, m 1 is the number of monitoring periods judged to have landing point offset, m 2 is the number of monitoring periods that are judged to have no landing point offset, j is greater than 0 and less than m 1 +m 2 A positive integer.

[0039] As a further technical solution of the present invention: the process of predicting the deviation fault according to the influence coefficient includes:

[0040] Based on the changes in the impact coefficient in the historical data, a linear trend model is selected to predict the next impact coefficient and obtain the predicted value;

[0041] Compare the predicted value with the safety interval. If the predicted value falls within the safety interval, it is predicted that there is no possibility of conveyor belt deviation failure.

[0042] If the predicted value is not within the safe range, it is predicted that a conveyor belt deviation failure may occur.

[0043] Through the above technical solution: a process for predicting conveyor belt deviation failure is provided. In the deviation prediction process, it is necessary to make a prediction based on the influence coefficient obtained in time series, so as to achieve the purpose of early prediction, thereby facilitating the implementation of subsequent maintenance or adjustment plans.

[0044] As a further technical solution of the present invention: the end of the sub-conveyor is set to a structure that can rotate between [a°, b°], and the rotation angle is set;

[0045] If the positive or negative value of the influence coefficient obtained after the rotation is different from the influence coefficient obtained before the rotation, the rotation is stopped until the sum of the influence coefficient before the rotation and the influence coefficient after multiple rotations completes the change of positive or negative value and then returns to the initial state;

[0046] If the positive or negative value of the influence coefficient obtained after the rotation is the same as the influence coefficient obtained before the rotation, the rotation will continue at the same rotation angle and in the same direction.

[0047] Through the above technical solution: a method for controlling the intelligent conveyor belt to make adjustments is provided, and the end of the sub-conveyor of the present invention is set as a rotatable structure. The landing point of the transported objects on the sub-conveyor on the main conveyor can be changed by rotation, so as to adjust the influence coefficient. The deviation of the conveyor belt is due to excessive unidirectional impact. By adjusting the end of the sub-conveyor, the influences before and after the adjustment can be offset or the cumulative speed of the influences before and after the adjustment can be reduced. Both can achieve the purpose of reducing the number of times the deviation correction device is started, thereby increasing the service life of the main conveyor.

[0048] Beneficial effects of the present invention:

[0049] (1) The monitoring and prediction method based on the deviation coefficient provided by the present invention has low difficulty in obtaining monitoring data, can effectively monitor and predict the extra-long belt conveyor on the basis of cost saving, and can predict the possibility of impending deviation failure.

[0050] (2) The offset coefficient determined by the present invention takes the offset amount, impact amount and type of transported object as reference variables. The larger the offset amount or impact amount, the greater the impact of the transported object on the conveyor belt during the impact process, and can assist in determining the impact direction on the conveyor belt during the impact process.

[0051] (3) The present invention can change the landing point of the transported objects on the sub-conveyor on the main conveyor by rotating, thereby adjusting the influence coefficient. The deviation of the conveyor belt is caused by excessive unidirectional impact. By adjusting the end of the sub-conveyor, the influences before and after the adjustment can be offset or the cumulative speed of the influences before and after the adjustment can be reduced. Both can achieve the purpose of reducing the number of times the deviation correction device is started, thereby increasing the service life of the main conveyor. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] The present invention will be further described below in conjunction with the accompanying drawings.

[0053] Figure 1 It is a flow chart of the overall steps of the present invention;

[0054] Figure 2 is a flow chart of the steps of obtaining the impact value of the present invention;

[0055] Figure 3 It is a flow chart of the steps of obtaining the offset value of the present invention. DETAILED DESCRIPTION

[0056] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments 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.

[0057] See also Figure 1 As shown, in one embodiment, a belt conveyor fault prediction method based on intelligent control is provided, comprising:

[0058] S100, at the intersection of the sub-conveyor and the main conveyor, video monitoring and quality monitoring are performed on the transported objects on the main conveyor and the sub-conveyor to obtain monitoring data;

[0059] S200, setting a monitoring period and obtaining an impact value, an offset value and a category coefficient based on the monitoring data within the monitoring period, and then obtaining an offset coefficient according to the impact value, the offset value and the category coefficient, wherein the category coefficient obtains and distinguishes the transported object image through the image data of the video monitoring, and different values ​​are set correspondingly for different types of goods, and the value is taken as the category coefficient;

[0060] S300, comparing the deviation coefficient with the control interval in a plurality of continuous and adjacent monitoring time periods, and obtaining a judgment result of whether the deviation coefficient in different monitoring time periods falls into the control interval;

[0061] S400, obtaining an influence coefficient based on multiple judgment results, and then predicting the deviation fault according to the influence coefficient.

[0062] In this embodiment, a method for predicting deviation failure is provided. Specifically, the monitoring and prediction method based on the offset coefficient provided by the present invention has low difficulty in obtaining monitoring data, can effectively monitor and predict extra-long belt conveyors on a cost-saving basis, and can predict the possibility of impending deviation failure.

[0063] S210, the step of obtaining the impact value comprises:

[0064] S211, obtaining the mass of the transported objects entering the main conveyor from the sub-conveyor during the monitoring period through quality monitoring. Different monitoring methods can be used for monitoring the mass of different transported objects. For example, express delivery can be weighed in advance and then the weight of the transported objects can be obtained through label recognition. Preferably, the conveyor belt of the sub-conveyor is divided into several parts, and a weighing sensor is installed for each part, so that the measured weight values ​​of each section are summed up to obtain the required measured mass;

[0065] S212, obtaining image data of the sub-conveyor during the monitoring period through video monitoring, and determining the height difference between the sub-conveyor and the main conveyor, as well as the type of transported objects and the corresponding category coefficient;

[0066] S213. A first correction coefficient is set based on the category coefficient. The impact value is the product of the first correction value after denormalization and the weight of the transported objects entering the main conveyor from the sub-conveyor during the monitoring period, the square of the height difference, and the first correction coefficient.

[0067] S220, the process of obtaining the offset value includes:

[0068] S221. During the monitoring period, video frames of the main conveyor belt before and after an impact action are monitored by video. An impact action refers to a process in which the corresponding position senses of the main conveyor and the sub-conveyor change in quality and stabilize again;

[0069] S222, obtaining a contour image of the goods falling on the conveyor belt of the main conveyor by contour recognition in the video frame;

[0070] S223, obtaining the centroid of the contour of the main conveyor belt before and after the impact action is completed, and obtaining the first distance and the second distance from the two centroids to the center line of the main conveyor belt, wherein the center line of the conveyor belt is parallel to the moving direction of the conveyor belt, and the first distance and the second distance have positive and negative values, and the positive and negative values ​​are distinguished in that if the centroid position is located on the right side of the conveyor belt moving direction vector, a positive value is assigned, and if it is located on the left side, a negative value is assigned;

[0071] S224. Calculate and obtain an offset value based on the first distance and the second distance.

[0072] The process of calculating and obtaining the offset value includes:

[0073] By formula:

[0074]

[0075] Among them, De j is the offset value of the jth monitoring period, n is the number of impact actions that occurred during the monitoring period, is the first distance between the centroid of the main conveyor belt contour and the centerline of the main conveyor belt after the ith impact action is completed, is the second distance from the centroid of the main conveyor belt contour to the centerline of the main conveyor belt after the ith impact action is completed, σ 1 is the first de-unitization coefficient, δ is a preset modified distance conversion function, which is a preset reference table function used to correct the landing point of transport objects that may be stacked. When there is no stacking problem, and δ are both 0, and i is a positive integer greater than 0 and less than n.

[0076] The process of obtaining the offset coefficient includes:

[0077] By formula:

[0078]

[0079] Where Ex is the offset coefficient of the jth monitoring period, α 1 is the preset first weight coefficient, α 2 is the preset second weight coefficient, ty is the category coefficient, m is the mass of transported goods entering the main conveyor from the sub-conveyor during the monitoring period, h is the height difference, σ 2 is the second de-unitization coefficient, De 0 It is the standard value preset by the offset value.

[0080] The process of obtaining the judgment result includes:

[0081] S310, compare the offset coefficient with a pair of preset critical intervals (-k 1 , -k 2 ) and (k 3 , k 4 ) for comparison;

[0082] S320: If the offset coefficient falls within any critical interval, the output judgment result is that there is a landing point offset within the monitoring period.

[0083] In this embodiment, a method and steps for obtaining the judgment result are provided. The judgment of the landing point offset of the present invention is based on the offset coefficient. The offset coefficient takes the offset amount, impact amount and transport object type as reference variables. The larger the offset amount or impact amount, the greater the impact of the transport object on the conveyor belt during the impact process, and it can assist in judging the impact direction of the conveyor belt during the impact process.

[0084] The process of obtaining the influence coefficient based on the judgment result includes:

[0085] By formula:

[0086]

[0087] Among them, Inf is the influence coefficient, m 1 is the number of monitoring periods judged to have landing point offset, m 2 is the number of monitoring periods that are judged to have no landing point offset, j is greater than 0 and less than m 1 +m 2 A positive integer.

[0088] The process of predicting the deviation fault according to the influence coefficient includes:

[0089] S410, based on the change of the influence coefficient in the historical data, a linear trend model is selected to predict the next influence coefficient and obtain a predicted value. The influence coefficient tends to change linearly over a long period of time, so a linear trend model such as the Hole linear trend model is used to predict the data. The linear trend model belongs to the prior art, so it will not be described in detail.

[0090] S420, compare the predicted value with the safety interval [Inf 1 ,Inf 2 ] for comparison. If the predicted value falls into the safe range, it is predicted that there is no possibility of conveyor belt deviation failure.

[0091] S430: If the predicted value is not within the safety interval, it is predicted that a conveyor belt deviation failure may occur.

[0092] In this embodiment, a process for predicting conveyor belt deviation failure is provided. In the deviation prediction process, it is necessary to make a prediction based on the influence coefficient obtained in time series, so as to achieve the purpose of early prediction, thereby facilitating the implementation of subsequent maintenance or adjustment plans.

[0093] The end of the sub-conveyor is set to a structure that can rotate between [a°, b°], and the rotation angle is set to control the end of the sub-conveyor to rotate to change the landing point of the transported objects on the sub-conveyor on the main conveyor;

[0094] If the positive or negative value of the influence coefficient obtained after the rotation is different from the influence coefficient obtained before the rotation, the rotation is stopped until the sum of the influence coefficient before the rotation and the influence coefficient after multiple rotations completes the change of positive or negative value and then returns to the initial state;

[0095] If the positive or negative value of the influence coefficient obtained after the rotation is the same as the influence coefficient obtained before the rotation, the rotation will continue at the same rotation angle and in the same direction.

[0096] It should be noted that the combination of the influence coefficient and rotation adjustment can also be used to offset environmental effects. As an example, the influence of different wind forces and wind directions on the conveyor belt is described in a digital way through big data, for example, through a vector description, and then a comparison relationship between the digital description and the influence coefficient is established. After the comparison relationship is established, different influence coefficients are output under different wind conditions and the influence coefficient is added to the influence coefficient obtained in step S400 as a new influence coefficient to act on the adjustment process of the end of the sub-conveyor.

[0097] In this embodiment, a method for controlling the intelligent conveyor belt to make adjustments is provided. The end of the sub-conveyor of the present invention is set as a rotatable structure. The landing point of the transported objects on the sub-conveyor on the main conveyor can be changed by rotation, so as to adjust the influence coefficient. The deviation of the conveyor belt is due to excessive unidirectional impact. By adjusting the end of the sub-conveyor, the influences before and after the adjustment can be offset or the cumulative speed of the influences before and after the adjustment can be reduced. Both can achieve the purpose of reducing the number of times the deviation correction device is started, thereby increasing the service life of the main conveyor.

[0098] The above is a detailed description of an embodiment of the present invention, but the content is only a preferred embodiment of the present invention and cannot be considered to limit the scope of implementation of the present invention. All equivalent changes and improvements made within the scope of the present invention should still fall within the scope of the patent coverage of the present invention.

Claims

1. A belt conveyor fault prediction method based on intelligent control, characterized in that: The steps include: At the intersection of the sub-conveyor and the main conveyor, video monitoring and quality monitoring are performed on the transported goods on the main conveyor and the sub-conveyor to obtain monitoring data; Setting a monitoring period and obtaining a shock value, an offset value and a category coefficient based on monitoring data within the monitoring period, and then obtaining an offset coefficient based on the shock value, the offset value and the category coefficient; In a plurality of continuous and adjacent monitoring periods, the deviation coefficient is compared with the control interval to obtain a judgment result of whether the deviation coefficient in different monitoring time periods falls into the control interval; The influence coefficient is obtained based on multiple judgment results, and then the deviation fault is predicted according to the influence coefficient.

2. The belt conveyor fault prediction method based on intelligent control according to claim 1 is characterized in that: The steps to obtain the shock value include: Through quality monitoring, the mass of transported materials entering the main conveyor from the sub-conveyor during the monitoring period is obtained; Obtain image data of the sub-conveyor during the monitoring period through video monitoring, and determine the height difference between the sub-conveyor and the main conveyor, as well as the type of transported objects and the corresponding category coefficient; The first correction coefficient is set based on the category coefficient, and the impact value is the product of the denormalized first correction value and the weight of the transported objects entering the main conveyor from the sub-conveyor during the monitoring period, the square of the height difference, and the first correction coefficient.

3. The belt conveyor fault prediction method based on intelligent control according to claim 2 is characterized in that: The process of obtaining the offset value includes: During the monitoring period, the video frames of the main conveyor belt before and after an impact action are monitored by video; Acquire the contour image of the goods falling on the conveyor belt of the main conveyor by contour recognition in the video frame; Obtain the centroid of the contour of the main conveyor belt before and after an impact action is completed, and obtain the first distance and the second distance from the two centroids to the center line of the main conveyor belt; The offset value is calculated based on the first distance and the second distance.

4. The belt conveyor fault prediction method based on intelligent control according to claim 3 is characterized in that: The process of calculating the offset value includes: By formula: Among them, De j is the offset value of the jth monitoring period, n is the number of impact actions that occurred during the monitoring period, is the first distance between the centroid of the main conveyor belt contour and the centerline of the main conveyor belt after the ith impact action is completed, is the second distance from the centroid of the contour of the main conveyor belt to the centerline of the main conveyor belt after the i-th impact action is completed, σ1 is the first de-unitization coefficient, δ is the preset modified distance conversion function, and i is a positive integer greater than 0 and less than n.

5. The belt conveyor fault prediction method based on intelligent control according to claim 4 is characterized in that: The process of obtaining the offset coefficient includes: By formula: Among them, Ex is the offset coefficient of the jth monitoring period, α1 is the preset first weight coefficient, α2 is the preset second weight coefficient, ty is the category coefficient, m is the mass of the transported material entering the main conveyor from the sub-conveyor during the monitoring period, h is the height difference, σ2 is the second de-unitization coefficient, and De0 is the preset standard value of the offset value.

6. The belt conveyor fault prediction method based on intelligent control according to claim 1 is characterized in that: The process of obtaining the judgment result includes: The offset coefficient is compared with a pair of preset critical intervals (-k1, -k2) and (k3, k4); If the offset coefficient falls within any critical interval, the output judgment result is that there is a landing point offset within the monitoring period.

7. The belt conveyor fault prediction method based on intelligent control according to claim 6 is characterized in that: The process of obtaining the influence coefficient based on the judgment results includes: By formula: Wherein, Inf is the influence coefficient, m1 is the number of monitoring periods judged to have landing point offset, m2 is the number of monitoring periods judged to have no landing point offset, and j is a positive integer greater than 0 and less than m1+m2.

8. The belt conveyor fault prediction method based on intelligent control according to claim 1 is characterized in that: The process of predicting the deviation fault according to the influence coefficient includes: Based on the changes in the impact coefficient in the historical data, a linear trend model is selected to predict the next impact coefficient and obtain the predicted value; Compare the predicted value with the safety interval. If the predicted value falls within the safety interval, it is predicted that there is no possibility of conveyor belt deviation failure. If the predicted value is not within the safe range, it is predicted that a conveyor belt deviation failure may occur.

9. The belt conveyor fault prediction method based on intelligent control according to claim 1 is characterized in that: include: The end of the sub-conveyor is set to a structure that can rotate between [a°, b°], and the rotation angle is set; If the positive or negative value of the influence coefficient obtained after the rotation is different from the influence coefficient obtained before the rotation, the rotation is stopped until the sum of the influence coefficient before the rotation and the influence coefficient after multiple rotations completes the change of positive or negative value and then returns to the initial state; If the positive or negative value of the influence coefficient obtained after the rotation is the same as the influence coefficient obtained before the rotation, the rotation will continue at the same rotation angle and in the same direction.

Images