Mobile detection device and method for rubber belt twisting pipe of pipe belt machine

Abstract

The invention relates to a mobile detection device for a twisted pipe of an adhesive tape of a pipe tape machine. The mobile detection device comprises an image recognition module, a position acquisition module, a data processing module and a twisted pipe alarm module, the data processing module calculates a pipe twisting angle value according to the adhesive tape lap joint orientation of the current pipe belt machine line, the track position where the camera is located, the twisting angle and the adhesive tape lap joint coincidence angle of the current pipe belt machine, the instant pipe twisting jitter of the adhesive tape is filtered out firstly, and then the pipe twisting angle and the pipe twisting duration are combined in an integral mode. Obtaining a pipe twisting alarm value for judging whether a pipe twisting alarm occurs or not; and the pipe twisting alarm module outputs a detection result according to a judgment result of the data processing module to realize an alarm function. According to the method, a comprehensive evaluation index for the severity of the twisted tube is formed by integrating two parameters of the twisted tube angle and the twisted tube occurrence time, and evaluation is more reliable.

Description

Technical Field

[0001] The invention relates to the technical field of belt conveyors, and in particular to a device and method for detecting the movement of a twisted pipe of a belt conveyor belt. Background Art

[0002] At present, pipe-belt conveyors have been widely used in industries such as electricity, metallurgy, and ports, and they have a tendency to develop towards large-volume and long-distance transportation. Most of the inspection work of pipe-belt conveyors relies on manual work, which involves regular inspections and on-site guarding. However, due to the complex on-site environment, small space, and long inspection routes, manual inspections are greatly hindered and interfered with. Some companies have conducted research on the use of robots for automated inspections. However, from the current situation, its function is limited to discovering some simple problems through a single indicator. For the failure of the pipe-belt conveyor to twist the belt, the inspection device has no actual detection method to make a comprehensive judgment on the degree of the twisted pipe failure. It can only set a simple apparent characteristic threshold to set the system to warn whether the pipe is twisted.

[0003] Patent document CN 202221815572.1 discloses a circular tube belt conveyor torsion detection device and a circular tube belt conveyor, including a pressure measuring component for being arranged on a PSK window plate, a first laser ranging component, a second laser ranging component, a control system and an alarm; Patent document CN202210789165.6 discloses a tube belt conveyor, a tube belt conveyor detection device and a detection method, wherein the tube belt conveyor detection device includes a plurality of mobile frames and a plurality of inspection robots arranged outside the tube belt conveyor body, each of the inspection robots can move along the corresponding mobile frame The inspection robot is provided with an image acquisition device and a transmission device. The main body of the pipe conveyor includes a conveyor belt. The image acquisition device can acquire images of the overlapping position of the conveyor belt. Patent document CN202310380089.8 discloses a method and device for detecting the twisted pipe of a tubular belt conveyor. The detection device includes: a camera for taking pictures of the overlapping position of the conveyor belt of the tubular belt conveyor; a picture information processing unit connected to the camera, and using the above-mentioned method for detecting the twisted pipe of the tubular belt conveyor to determine whether the belt conveyor has a twisted pipe failure. The above-mentioned patent represents the most commonly used technical solution at present, which is to use ultrasonic, laser, visual shooting, etc., and use a single sensor indicator to set the threshold value for allowing the tubular belt to twist. When the pipe belt is twisted to this position, an alarm occurs. This type of solution is prone to false alarms and it is difficult to adjust the sensitivity of the alarm.

[0004] Patent document CN201510824063.3 discloses a method and device for detecting torsion of a tubular conveyor, which obtains torsional displacement data of the tubular conveyor in real time, converts the torsional displacement data into torsion degree data, issues different command signals according to the torsion degree data, and issues a warning or alarm upon receiving the command signal; Patent document CN202310380333.0 discloses a method and device for identifying the torsion angle of a tubular belt conveyor, which collects image information of the overlapping position of the conveyor belt; constructs a data scale according to the outer diameter of the conveyor belt, and specifies the scale and range of the data scale; extracts characteristic pixel points of the overlapping position of the conveyor belt in the image; retains the characteristic pixel points located in the middle position as the judgment pixel points; takes the average value of the minimum number of rows and the maximum number of rows among all the judgment pixel points as the horizontal coordinate of the overlapping position of the conveyor belt; projects the horizontal coordinate of the overlapping position of the conveyor belt onto the data scale, and determines the torsion angle of the conveyor belt according to the intersection of the projection and the scale on the data scale. The above patent uses a sensor to obtain the torsion angle of the tape, and then issues an alarm for a torsion tube failure based on a set threshold. This type of solution can adjust the sensitivity, but it only deals with how to obtain torsion information, but does not deal with the relationship between the time and spatial degree of torsion of the tube. It lacks strict logic and is prone to problems such as the system being too sensitive or too slow, making it difficult to meet actual engineering needs.

[0005] It can be seen that the existing torsion tube detection method has the following problems:

[0006] First: Most detection solutions are based on fixed-point detection. For example, ultrasound, laser, camera, etc. are fixed at a certain position of the pipe conveyor. When in normal state and twisted state, the shape and size changes of the tape surface are reflected in the distance from the sensor, thereby realizing alarm or identifying the absolute position of the pixel point of the overlapping edge of the tape in the picture.

[0007] Second: The tape of the hose conveyor has left and right overlaps during the installation process. Therefore, when observing the tape of the hose conveyor from different directions, the test results should be treated differently to obtain a more accurate judgment.

[0008] Third: Since the belt of the belt conveyor may twist clockwise or counterclockwise, in order to achieve detection in these two directions, it is necessary to arrange detection devices on both sides of the truss, which is difficult to achieve for a platform that requires mobile monitoring. Summary of the invention

[0009] In view of the shortcomings of the prior art, the present invention provides a mobile detection device and method for detecting twisted pipes of a belt conveyor to solve the above technical problems:

[0010] The present invention provides the following technical solutions:

[0011] A mobile detection device for detecting twisted pipes of a pipe machine, comprising an image recognition module, a position acquisition module, a data processing module and a twisted pipe alarm module;

[0012] The image recognition module includes a camera and a walking mechanism, and the walking mechanism enables the camera to walk around the two sides of the pipe conveyor truss; the image recognition module obtains the tape lap direction of the current pipe conveyor line and the tape lap overlap angle of the current pipe conveyor through the picture taken by the camera, and identifies the position of the lap edge of the tubular tape relative to the four rollers, thereby converting the torsion angle;

[0013] The position acquisition module is provided with electronic tags on both sides of the belt conveyor truss. The electronic tags use radio frequency identification technology. The position acquisition module can obtain the track position of the current camera according to the electronic tags.

[0014] The data processing module calculates the tube twist angle value according to the tape overlap direction of the current tube conveyor line, the track position of the camera, the torsion angle and the tape overlap overlap angle of the current tube conveyor, first filters out the instantaneous tube twist jitter of the tape, then combines the tube twist angle and the tube twist duration by an integral method to obtain a tube twist alarm value for determining whether a tube twist alarm has occurred;

[0015] The torsion pipe alarm module outputs the detection result according to the judgment result of the data processing module to realize the alarm function.

[0016] A method for detecting movement of a twisted pipe of a belt conveyor belt is provided, wherein the following steps are performed using the aforementioned device for detecting movement of a twisted pipe of a belt conveyor belt:

[0017] Step S1: The image recognition module obtains the tape overlap direction a of the current pipe conveyor line. When the tape is installed in the form of left overlap and right overlap, a=-1, and when the tape is installed in the form of right overlap and left overlap, a=1; the position acquisition module obtains the track position b of the camera. The position acquisition module determines the track position of the camera based on the information read from the electronic tag. When the camera is on the left track of the pipe conveyor, b=1, and when the camera is on the right track of the pipe conveyor, b=-1; the image recognition module obtains the overlap angle y of the tape of the current pipe conveyor. The overlap angle is the angle between the overlap edge and the center line of the tubular belt;

[0018] Step S2: Obtain the torsion angle x of the tape from the image recognition module in real time; if the torsion angle x value can be obtained, execute step S3; if the torsion angle x value cannot be obtained, execute step S5;

[0019] Step S3: The data processing module obtains the tape overlap direction a, the track position b, the torsion angle x and the tape overlap overlap angle y of the current belt conveyor line, and calculates the torsion angle value k; when a*b=1, the torsion angle value k=xy; when a*b=-1, the torsion angle value k=x+y.

[0020] Step S4: Compare the torsion tube angle value k with the reference value k 基准 Compare, when k is greater than k 基准 When k is equal to t, record the k value and duration t. If t is less than or equal to t 基准 No calculation is performed when t is greater than t 基准 When , it is calculated according to the following formula:

[0021]

[0022] M is the alarm value for the twisted tube; 基准 For comparison, if M is greater than M 基准 , the pipe twisting alarm module outputs the alarm information of the detection result "pipe twisting".

[0023] Step S5: If the x value cannot be obtained, it means that the mobile camera cannot observe the overlapping edge of the tubular tape, and a blind spot appears. If the x value cannot be obtained within 10 seconds from the moment when the overlapping edge disappears, the 10 k values ​​before the overlapping edge disappears are obtained, and the average value k of these 10 k values ​​is calculated. 平均 , if k 平均 = 0 to 90 degrees, the detection result output by the twisted pipe alarm module is "untwisted pipe, visual blind area", and no alarm is issued; if k 平均 If it is greater than 90, the output detection result is an alarm message of "twisted pipe, visual blind area".

[0024] Furthermore, the image recognition module obtains the torsion angle x of the tape including the following steps:

[0025] Step S21: The image of the belt conveyor truss is acquired through a camera, and the position of the roller in the picture is identified by using target recognition detection technology. Four rollers can be identified in the picture, and the center point coordinates of the four rollers are obtained (x1, y1), (x2, y2), (x3, y3), and (x4, y4);

[0026] Step S22: Identify the overlap line of the tubular tape, and obtain the coordinates of the upper left endpoint (x5, y5) and the lower right endpoint (x6, y6) of the overlap line in the picture;

[0027] Step S23: connect the two points (x1, y1) and (x2, y2) as a straight line line1, calculate the distance between the two points (x1, y1) and (x2, y2) in the vertical direction, divide the distance into equal parts and map it into angles of 0 to 45 degrees; connect the two points (x2, y2) and (x3, y3) as a straight line line2, calculate the distance between the two points (x2, y2) and (x3, y3) in the vertical direction, divide the distance into equal parts and map it into angles of 45 to 135 degrees; connect the two points (x3, y3) and (x4, y4) as a straight line line3, calculate the distance between the two points (x3, y3) and (x4, y4) in the vertical direction, divide the distance into equal parts and map it into angles of 135 to 180 degrees;

[0028] Step S24: connect the two points (x5, y5) and (x6, y6) to form a straight line line4; extend line4 and intersect it with any line line1 to 3 to obtain the coordinate value of the intersection point (x7, y7), and combine the mapping relationship between the vertical distance and the angle to obtain the output value of the belt torsion angle x of the belt conveyor.

[0029] Furthermore, the range of the twisting angle value k is 0 to 180 degrees, and the overlap angle y of the tape of the current pipe belt machine is in the range of 20 to 30 degrees; k 基准 The user-defined range is 20 to 90 degrees. 基准 Allows users to set the range from 5 to 60 seconds, M 基准 The user-defined range is 200 to 10000.

[0030] Furthermore, the upper limit of the t value is 60s, and the continuous tube twisting exceeding 60s is calculated according to the 60s recorded data.

[0031] The present invention has the following beneficial technical effects:

[0032] In view of the structural characteristics of the pipe and belt conveyor, a solution for detecting the torsion pipe angle suitable for use on a mobile platform is disclosed, which overcomes the defect that the traditional solution is only suitable for fixed-point monitoring. The present invention adopts a relative judgment method based on the position of the roller, which is suitable for the detection of a mobile camera platform. In combination with the characteristics of the pipe and belt conveyor with different left and right overlapping directions and blind spot viewing angles in different directions, corresponding detection devices and methods are formulated, and the method of obtaining the torsion pipe angle is more reliable.

[0033] The present invention develops an algorithm logic for the pipe twisting alarm, which distinguishes the detection of the pipe twisting phenomenon from the alarm of the pipe twisting fault. The occurrence of the pipe twisting phenomenon does not mean that an alarm of the pipe twisting needs to be issued immediately; and it no longer relies on a single threshold value, but introduces the thinking mode of patrol workers, adds the time and space degree judgment of the pipe twisting fault, and adopts the method of integrating the two parameters of the pipe twisting angle and the time when the pipe twisting occurs, thereby forming a comprehensive evaluation index for the severity of the pipe twisting, and the evaluation is more reliable. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] Figure 1 It is a structural schematic diagram of a mobile detection device for a belt twisting pipe of a belt conveyor according to the present invention;

[0035] Figure 2 A flow chart for performing a twisted tube detection for the present invention;

[0036] Figure 3 It is a schematic diagram of moving the camera to different positions on the truss when the tubular tape of the present invention overlaps the left direction from right to left;

[0037] Figure 4 It is a schematic diagram of moving the camera to different positions on the truss when the tubular tape of the present invention overlaps left and right;

[0038] Figure 5 It is a schematic diagram of the overlap angle y of the adhesive tape of the present invention;

[0039] Figure 6 This is a schematic diagram of the present invention when a*b=1 and the overlapping edge of the tape is in the blind area of ​​the camera;

[0040] Figure 7 This is a schematic diagram of the present invention when a*b=-1 and the overlapping edge of the tape is in the blind area of ​​the camera;

[0041] Figure 8 It is a schematic diagram of steps 21 to 23 in the angle acquisition module of the present invention;

[0042] Fig. 9 It is a schematic diagram of step S24 in the angle acquisition module of the present invention.

[0043] The reference numerals in the figure are:

[0044] Mobile camera system 100 , camera 110 , walking structure 120 , and electronic tag 200 . DETAILED DESCRIPTION

[0045] 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.

[0046] Example

[0047] like Figure 1 As shown, a mobile detection device for detecting twisted pipes of a pipe machine belt conveyor is composed of an image recognition module, a position acquisition module, a data processing module, and a twisted pipe alarm module.

[0048] The image recognition module includes a mobile camera 100 and an electronic tag 200; the mobile camera 100 has a camera 110 and a walking structure 120, and can walk around the two sides of the pipe belt truss; the center height of the camera 110 is the same as the center height of the tubular tape, and the camera angle of view can capture the four rollers on one side of the truss. The mobile camera 100 can be mounted on a rail, wheeled, or tracked to achieve the goal of walking along the pipe belt machine truss. The image recognition module obtains the tape lap direction of the current pipe belt machine line and the tape lap overlap angle of the current pipe belt machine through the images captured by the camera, and identifies the position of the lap edge of the tubular tape relative to the four rollers, thereby converting the torsion angle.

[0049] An electronic tag 200 is installed on one side of the belt conveyor truss. When the mobile camera 100 moves around the truss, the position acquisition module can know whether the current mobile camera platform is on the left or right side of the truss based on the electronic tag; the electronic tag 200 records the position information. The electronic tag adopts radio frequency identification technology and is installed in the area where the mobile camera moves. There is a data bit b in the electronic tag. The b in the electronic tag on the left side of the truss is equal to -1, and the b in the electronic tag on the right side of the truss is equal to 1.

[0050] The data processing module calculates the tube twist angle value according to the tape overlap direction of the current tube conveyor line, the track position of the camera, the torsion angle and the tape overlap overlap angle of the current tube conveyor, first filters out the instantaneous tube twist jitter of the tape, and then combines the tube twist angle and the tube twist duration by an integral method to obtain a tube twist alarm value for determining whether a tube twist alarm has occurred.

[0051] The torsion pipe alarm module outputs the detection result according to the judgment result of the data processing module to realize the alarm function.

[0052] like Figure 2 As shown in the figure, the operation process of the pipe belt machine twist detection is:

[0053] Since the tape has an overlapping width and the tubular tape has different overlapping directions, different data processing is required in different situations according to the tape overlapping direction a of the current tubular tape machine line, the track position b of the mobile camera, and the tape overlapping overlap angle y of the tubular tape machine.

[0054] Provide three global variables a, b, and y. According to the construction of the pipe belt machine, set the tape overlap direction of the current pipe belt machine line, represented by the letter a: from the tail of the pipe belt machine to the head, the tape installation form is left overlap right a=-1, right overlap left a=1;

[0055] like Figure 5As shown, set the overlap angle of the current belt conveyor, represented by the letter y, which is usually in the range of 20 to 30 degrees. The overlap angle must be added or subtracted to obtain the theoretical center position of the belt.

[0056] like Figure 3-4 As shown, the module can also read the information of the electronic tag to determine the track position of the mobile camera. When it is on the left track of the belt conveyor, b=1, and when it is on the right track of the belt conveyor, b=-1.

[0057] The torsion angle x of the tape is obtained from the image recognition module in real time; if the x value can be obtained, when a*b=1, the torsion tube angle value k(0~180°)=xy; when a*b=-1, the torsion tube angle value k(0~180°)=x+y.

[0058] The data processing module obtains the torsion tube angle value k and compares it with the reference value k 基准 Compare, when k is greater than k 基准 When the k value and duration t are recorded; if the t value is less than or equal to t 基准 No calculation is performed when t is greater than t 基准 , calculate according to the following formula (the upper limit of t value is 60s, and the continuous twisting pipe exceeding 60s is calculated according to the 60s recorded data):

[0059]

[0060] M is the alarm value for the twisted tube; 基准 For comparison, if it is greater than M 基准 Then the warning information of the detection result "pipe twisting" is output.

[0061] Depending on the owner's sensitivity to the alarm and the stability of different items of tape, k 基准 ,t 基准 、M 基准 Make settings. 基准 The user-defined range is 20 to 90 degrees. 基准 Allows users to set the range from 5 to 60 seconds, M 基准 The user-defined range is 200 to 10000.

[0062] If the x value cannot be obtained, it means that the mobile camera cannot observe the overlapping edge of the tubular tape (blind spot of view). Then, if x cannot be obtained within 10 seconds from the moment when the overlapping edge disappears, obtain the 10 nearest k values ​​before disappearance and calculate the average value k of these 10 k values. 平均 , if k 平均 = 0 to 90 degrees, the detection result is "blind area" and no alarm is given; if k 平均If it is greater than 90, the detection result is the alarm information of "twisted pipe, visual blind area", which can be referred to Figure 6-7 shown.

[0063] In this embodiment, the image recognition module obtains the torsion angle x of the tape in the following working process: the image of the pipe conveyor truss is obtained through the camera, and the position of the roller in the picture is identified by using the target recognition detection technology. Four groups of rollers can be identified in the picture, and the coordinates of the roller points in the picture are obtained (x1, y1), (x2, y2), (x3, y3), and (x4, y4). The overlap line of the tubular tape is identified, and the coordinates of the upper left end point (x5, y5) and the lower right end point (x6, y6) of the overlap line in the picture are obtained. Figure 8 shown.

[0064] Connect the two points (x1, y1) and (x2, y2) as line 1, calculate the vertical distance between the two points (x1, y1) and (x2, y2), divide the distance into equal parts and map it into angles of 0 to 45 degrees; connect the two points (x2, y2) and (x3, y3) as line 2, calculate the vertical distance between the two points (x2, y2) and (x3, y3), divide the distance into equal parts and map it into angles of 45 to 135 degrees; connect the two points (x3, y3) and (x4, y4) as line 3, calculate the vertical distance between the two points (x3, y3) and (x4, y4), divide the distance into equal parts and map it into angles of 135 to 180 degrees; connect the two points (x5, y5) and (x6, y6) as line 4.

[0065] Extend line4 and intersect it with any line from line1 to line3 to obtain the coordinate value of the intersection (x7, y7). Combined with the mapping relationship between vertical distance and angle, the output value x of the belt torsion angle of the belt conveyor is obtained, such as Fig. 9 shown.

[0066] This embodiment adopts multiple thresholds (k 基准 , t 基准 , M 基准 ) Screening and controlling the detection of the tube twisting phenomenon makes it less likely to have false alarms. In addition, this embodiment uses the method of integrating the two parameters of the tube twisting angle and the time when the tube twisting occurs to form a comprehensive evaluation index for the severity of the tube twisting, which makes the evaluation more reliable.

[0067] The above-mentioned embodiments only express the specific implementation of the present invention, and the description thereof is relatively specific and detailed, but it cannot be understood as limiting the scope of the present invention. It should be pointed out that, for ordinary technicians in this field, several variations and improvements can be made without departing from the concept of the present invention, which all belong to the protection scope of the present invention.

Claims

1. A mobile detection device for detecting twisted pipe of a pipe machine, characterized in that: It includes an image recognition module, a position acquisition module, a data processing module and a twisted pipe alarm module; The image recognition module includes a camera and a walking mechanism, and the walking mechanism enables the camera to walk around the two sides of the pipe conveyor truss; the image recognition module obtains the tape lap direction of the current pipe conveyor line and the tape lap overlap angle of the current pipe conveyor through the picture taken by the camera, and identifies the position of the lap edge of the tubular tape relative to the four rollers, thereby converting the torsion angle; The position acquisition module is provided with electronic tags on both sides of the belt conveyor truss, and the position acquisition module can obtain the track position of the current camera according to the electronic tags; The data processing module calculates the tube twist angle value according to the tape overlap direction of the current tube conveyor line, the track position of the camera, the torsion angle and the tape overlap overlap angle of the current tube conveyor, first filters out the instantaneous tube twist jitter of the tape, then combines the tube twist angle and the tube twist duration by an integral method to obtain a tube twist alarm value for determining whether a tube twist alarm has occurred; The torsion pipe alarm module outputs the detection result according to the judgment result of the data processing module to realize the alarm function.

2. According to the device for detecting the movement of a twisted pipe of a belt conveyor according to claim 1, the electronic tag adopts radio frequency identification technology.

3. A method for detecting the movement of a pipe machine belt twisting pipe, characterized in that: The following steps are performed using the mobile detection device for detecting twisted pipe of a belt conveyor belt according to claim 1 or 2: Step S1: The image recognition module obtains the tape overlap direction a of the current pipe conveyor line. When the tape is installed in the form of left overlap and right overlap, a=-1, and when the tape is installed in the form of right overlap and left overlap, a=1; the position acquisition module obtains the track position b of the camera. The position acquisition module determines the track position of the camera based on the information read from the electronic tag. When the camera is on the left track of the pipe conveyor, b=1, and when the camera is on the right track of the pipe conveyor, b=-1; the image recognition module obtains the overlap angle y of the tape of the current pipe conveyor. The overlap angle is the angle between the overlap edge and the center line of the tubular belt; Step S2: Obtain the torsion angle x of the tape from the image recognition module in real time; if the torsion angle x value can be obtained, execute step S3; if the torsion angle x value cannot be obtained, execute step S5; Step S3: The data processing module obtains the tape overlap direction a, the track position b, the torsion angle x and the tape overlap overlap angle y of the current pipe conveyor line, and calculates the torsion angle value k; Step S4: Compare the torsion tube angle value k with the reference value k 基准 Compare, when k is greater than k 基准 When k is equal to t, record the k value and duration t. If t is less than or equal to t 基准 No calculation is performed when t is greater than t 基准 When , it is calculated according to the following formula: M is the alarm value for the twisted tube; 基准 For comparison, if M is greater than M 基准 , the pipe twisting alarm module outputs the alarm information of the detection result "pipe twisting".

4. A method for detecting movement of a belt conveyor belt twisting pipe according to claim 3, characterized in that: The calculated torsion tube angle value k is: when a*b=1, the torsion tube angle value k=xy; when a*b=-1, the torsion tube angle value k=x+y.

5. A method for detecting movement of a belt twisting pipe of a belt conveyor according to claim 3, characterized in that: Step S5: If the x value cannot be obtained, it means that the mobile camera cannot observe the overlapping edge of the tubular tape, and a blind spot appears. If the x value cannot be obtained within 10 seconds from the moment when the overlapping edge disappears, the 10 k values ​​before the overlapping edge disappears are obtained, and the average value k of these 10 k values ​​is calculated. 平均 , if k 平均 = 0 to 90 degrees, the detection result output by the twisted pipe alarm module is "untwisted pipe, visual blind area", and no alarm is issued; if k 平均 If it is greater than 90, the output detection result is an alarm message of "twisted pipe, visual blind area".

6. A method for detecting movement of a belt twisting pipe of a belt conveyor according to claim 3, characterized in that: The image recognition module obtains the torsion angle x of the tape by the following steps: Step S21: The image of the belt conveyor truss is acquired through a camera, and the position of the roller in the picture is identified by using target recognition detection technology. Four rollers can be identified in the picture, and the center point coordinates of the four rollers are obtained (x1, y1), (x2, y2), (x3, y3), and (x4, y4); Step S22: Identify the overlap line of the tubular tape, and obtain the coordinates of the upper left endpoint (x5, y5) and the lower right endpoint (x6, y6) of the overlap line in the picture; Step S23: connect the two points (x1, y1) and (x2, y2) as a straight line line1, calculate the distance between the two points (x1, y1) and (x2, y2) in the vertical direction, divide the distance into equal parts and map it into angles of 0 to 45 degrees; connect the two points (x2, y2) and (x3, y3) as a straight line line2, calculate the distance between the two points (x2, y2) and (x3, y3) in the vertical direction, divide the distance into equal parts and map it into angles of 45 to 135 degrees; connect the two points (x3, y3) and (x4, y4) as a straight line line3, calculate the distance between the two points (x3, y3) and (x4, y4) in the vertical direction, divide the distance into equal parts and map it into angles of 135 to 180 degrees; Step S24: connect the two points (x5, y5) and (x6, y6) to form a straight line line4; extend line4 and intersect it with any line line1 to 3 to obtain the coordinate value of the intersection point (x7, y7), and combine the mapping relationship between the vertical distance and the angle to obtain the output value of the belt torsion angle x of the belt conveyor.

7. A method for detecting movement of a belt twisting pipe of a belt conveyor according to claim 3, characterized in that: The torsion tube angle value k ranges from 0 to 180 degrees.

8. A method for detecting movement of a belt twisting pipe of a belt conveyor according to claim 3, characterized in that: The overlap angle y of the tape of the current belt conveyor is within the range of 20 to 30 degrees.

9. A method for detecting movement of a belt twisting pipe of a belt conveyor according to claim 3, characterized in that: The upper limit of t value is 60s. The continuous tube twisting exceeding 60s is calculated based on the 60s recorded data.

10. A method for detecting movement of a belt twisting pipe of a belt conveyor according to claim 3, characterized in that: k 基准 The user-defined range is 20 to 90 degrees. 基准 Allows users to set the range from 5 to 60 seconds, M 基准 The user-defined range is 200 to 10000.

Images