Conveyor belt deviation detection system

Abstract

A conveyor belt deviation detection system disclosed by the present invention comprises a mobile detection system and a fixed detection system, the mobile detection system uses a track inspection robot to inspect along a belt conveyor, and a robot camera is used to shoot a belt and a carrier roller; whether belt deviation exists or not and the severity degree of the deviation are judged through a detection algorithm, the fixed detection system is used for conducting supplementary detection on the movable detection system, and the severity degree of the belt deviation is judged through the semantic segmentation area of the carrier roller and the belt. The beneficial effects of the invention are that the mobile detection system and the fixed detection system are arranged, and the fixed detection system carries out supplementary detection on the mobile detection system, so that compared with a full-fixed point distribution mode, when the transportation distance is long and full coverage is realized, the cost can be reduced, and the detection efficiency is improved. And meanwhile, the mobile detection system and the fixed detection system not only can carry out binary judgment on whether deviation exists or not, but also can carry out graded alarm on the severity degree of deviation.

Description

Technical Field

[0001] The invention relates to the technical field of belt conveyors, in particular to a conveyor belt deviation detection system. Background Art

[0002] Belt conveyors are widely used in mining, coal, steel, electricity, chemical and other industries. As a key material conveying equipment, they undertake continuous and stable transportation tasks. However, due to the influence of various factors, belts may deviate during long-term operation. Deviation failure will not only lead to reduced transportation efficiency and increased maintenance costs, but may also cause equipment shutdown, material loss, and even safety accidents. Therefore, real-time and accurate monitoring of the belt deviation status is the key to ensuring production safety and improving equipment reliability.

[0003] Traditional belt deviation detection methods rely on manual inspections and monitoring systems based on fixed camera detection. Although manual inspections can detect obvious deviations, the inspection process is time-consuming and prone to missed inspections, which cannot meet the needs of efficient, all-weather, and uninterrupted monitoring. Fixed camera detection systems usually require fixed monitoring camera detection positions to manually set fault modes and alarm thresholds, that is, to determine whether the belt is deviating by detecting whether the number of rollers on both sides of the belt is consistent. This method cannot distinguish between mild, moderate, and severe deviations, and has many restrictions on the installation position, poor flexibility, and difficulty in adapting to complex changes in different working environments or operating conditions, and cannot cover the entire conveyor belt area. Summary of the invention

[0004] The purpose of the present invention is to overcome the shortcomings of the prior art and provide a conveyor belt deviation detection system.

[0005] The objective of the present invention is achieved through the following technical solutions: a conveyor belt deviation detection system, comprising a mobile detection system and a fixed detection system. The mobile detection system utilizes a track inspection robot to inspect along the belt conveyor, photographs the belt and rollers through the robot camera, and uses a detection algorithm to determine whether the belt is deviating and the severity of the deviation. The fixed detection system is used to supplement the mobile detection system and use the semantic segmentation area of ​​the rollers and belts to determine the severity of the belt deviation.

[0006] Preferably, the steps of the mobile detection system when working are as follows:

[0007] S1: Take the belt and roller images I(x,y) through the inspection robot camera;

[0008] S2: Identify the belt edge and roller edge in the image;

[0009] S3: Calculate the distance between the belt edge points and the roller edge points on the left and right sides.

[0010]

[0011]

[0012] S4: Compare the distance obtained in step S3 with the normal distance to obtain the offset.

[0013]

[0014] S5: Determine the degree of deviation by comparing the offset obtained in step S4 with the set offset.

[0015]

[0016] S6: The robot issues a belt deviation alarm.

[0017] Preferably, step S2 further includes the following steps:

[0018] S21: Use image segmentation algorithm to obtain the pixel area of ​​the belt and the pixel area of ​​the roller.

[0019] M(x, y) = S(I(x, y));

[0020] Where I(x, y) is the image before filtering, S represents the image segmentation algorithm, and M(x, y) is the mask of the segmented area;

[0021] S22: Extract the belt area and the roller area respectively according to the ID of the segmentation mask.

[0022] M(x,y)=M0(x,y)+M1(x,y)+M2(x,y);

[0023] Among them, M0(x, y) is the background area mask, M1(x, y) is the belt area mask, and M2(x, y) is the roller area mask;

[0024] S23: Use edge detection algorithm to extract mask edges of belt area and roller area.

[0025] B i (x, y) = D(M i (x, y)), i = 1, 2;

[0026] Among them, B i (x, y) is the obtained mask edge, and D is the edge detection algorithm;

[0027] S24: Use logical filtering conditions to select the left and right edges of the belt and the left and right edges of the roller.

[0028] B k(x, y)=U(F1(B1), F2(B2));

[0029] Among them, F is the boundary filtering condition,

[0030] S25: Find the belt edge target point and the roller end point from the edge point set.

[0031] P(x, y) = L(B k );

[0032] Among them, L is the traversal and screening logic of edge points, and P is the target point.

[0033] Preferably, the steps of the fixed detection system when working are as follows:

[0034] A1: The camera of the edge computing device captures the belt and roller image I(x, y);

[0035] A2: Perform instance segmentation on the image to obtain the pixel areas of the roller and belt.

[0036] M(x, y) = S(I(x, y));

[0037] Where I(x, y) is the image before filtering, S represents the image segmentation algorithm, and M(x, y) is the mask of the roller area;

[0038] A3: Calculate the ratio of the pixel area on the left and right sides of the roller in the image.

[0039]

[0040] A4: Compare the area ratio obtained in step A3 with the preset normal value to obtain the difference value.

[0041] diff=|ratio-ratio normal |;

[0042] A5: Determine the degree of deviation by comparing the difference value obtained in step A4 with the set difference value.

[0043]

[0044] A6: The edge computing device issues a belt deviation alarm.

[0045] The present invention has the following advantages: by setting up a mobile detection system and a fixed detection system, and enabling the fixed detection system to perform supplementary detection on the mobile detection system, compared with the all-fixed point distribution method, when full coverage is achieved over a long transportation distance, the cost can be reduced. At the same time, the mobile detection system and the fixed detection system can not only perform a binary judgment on whether the vehicle has deviated, but can also provide graded alarms for the severity of the deviation. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 is a schematic diagram of a mobile detection system;

[0047] Figure 2 Schematic diagram of the fixed detection system. DETAILED DESCRIPTION

[0048] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Generally, the components of the embodiments of the present invention described and shown in the drawings here can be arranged and designed in various different configurations.

[0049] Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the invention claimed for protection, but merely represents selected embodiments of the present invention. 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.

[0050] It should be noted that, in the absence of conflict, the embodiments of the present invention and the features of the embodiments may be combined with each other.

[0051] It should be noted that similar reference numerals and letters denote similar items in the following drawings, and therefore, once an item is defined in one drawing, further definition and explanation thereof is not required in subsequent drawings.

[0052] In the description of the present invention, it should be noted that the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inside", "outside", etc. indicate positions or positional relationships based on the positions or positional relationships shown in the accompanying drawings, or the positions or positional relationships in which the product of the invention is usually placed when in use, or the positions or positional relationships commonly understood by those skilled in the art, which are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, the terms "first", "second", etc. are only used to distinguish the description, and cannot be understood as indicating or implying relative importance.

[0053] In the description of the present invention, it is also necessary to explain that, unless otherwise clearly specified and limited, the terms "set", "install", "connect", and "connect" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two elements. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0054] In this embodiment, a conveyor belt deviation detection system includes a mobile detection system and a fixed detection system. The mobile detection system uses a track inspection robot to inspect along the belt conveyor, takes pictures of the belt and rollers through the robot camera, and uses a detection algorithm to determine whether the belt is deviating and the severity of the deviation. The fixed detection system is used to supplement the mobile detection system and use the semantic segmentation area of ​​the rollers and belts to determine the severity of the belt deviation. By setting up a mobile detection system and a fixed detection system, and allowing the fixed detection system to supplement the mobile detection system, compared with the full fixed point arrangement method, when the transportation distance is long and full coverage is achieved, the cost can be reduced. At the same time, the mobile detection system and the fixed detection system can not only perform a binary judgment on whether the belt is deviating, but also provide a graded alarm for the severity of the deviation.

[0055] Further, such as Figure 1 As shown, the steps of the mobile detection system are as follows:

[0056] S 1: Use the inspection robot camera to capture the belt and roller images I (x, y);

[0057] S2: Identify the belt edge and roller edge in the image; specifically, the belt edge is Figure 1 The inner dotted line in the figure shows the edge of the roller. Figure 1 The outer dotted line in , further comprising the following steps:

[0058] S21: Use image segmentation algorithm to obtain the pixel area of ​​the belt and the pixel area of ​​the roller.

[0059] M(x, y) = S(I(x, y));

[0060] Where I(x, y) is the image before filtering, S represents the image segmentation algorithm, and M(x, y) is the mask of the segmented area;

[0061] S22: Extract the belt area and the roller area respectively according to the ID of the segmentation mask.

[0062] M(x,y)=M0(x,y)+M1(x,y)+M2(x,y);

[0063] Among them, M0(x, y) is the background area mask, M1(x, y) is the belt area mask, and M2(x, y) is the roller area mask;

[0064] S23: Use edge detection algorithm to extract mask edges of belt area and roller area.

[0065] B i (x, y) = D(M i (x, y)), i = 1, 2;

[0066] Among them, B i (x, y) is the obtained mask edge, and D is the edge detection algorithm;

[0067] S24: Use logical filtering conditions to select the left and right edges of the belt and the left and right edges of the roller.

[0068] B k (x, y)=U(F1(B1), F2(B2));

[0069] Among them, F is the boundary filtering condition,

[0070] S25: Find the belt edge target point and the roller end point from the edge point set.

[0071] P(x, y) = L(B k );

[0072] Among them, L is the traversal and screening logic of edge points, and P is the target point.

[0073] S3: Calculate the distance between the belt edge points and the roller edge points on the left and right sides.

[0074]

[0075]

[0076] S4: Compare the distance obtained in step S3 with the normal distance to obtain the offset.

[0077]

[0078] S5: Determine the degree of deviation by comparing the offset obtained in step S4 with the set offset.

[0079]

[0080] S6: The robot issues a belt deviation alarm.

[0081] In this embodiment, if Figure 2 As shown, the steps of the fixed detection system are as follows:

[0082] A1: The camera of the edge computing device captures the belt and roller image I(x, y);

[0083] A2: Perform instance segmentation on the image to obtain the pixel areas of the roller and belt.

[0084] M(x, y) = S(I(x, y));

[0085] Where I(x, y) is the image before filtering, S represents the image segmentation algorithm, and M(x, y) is the mask of the roller area;

[0086] A3: Calculate the ratio of the pixel area on the left and right sides of the roller in the image.

[0087]

[0088] A4: Compare the area ratio obtained in step A3 with the preset normal value to obtain the difference value.

[0089] diff=|ratio-ratio normal |;

[0090] A5: Determine the degree of deviation by comparing the difference value obtained in step A4 with the set difference value.

[0091]

[0092] A6: The edge computing device issues a belt deviation alarm.

[0093] Although the present invention has been described in detail with reference to the aforementioned embodiments, it is still possible for those skilled in the art to modify the technical solutions described in the aforementioned embodiments, or to make equivalent substitutions for some of the technical features therein. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A conveyor belt deviation detection system, characterized in that: The invention comprises a mobile detection system and a fixed detection system. The mobile detection system uses a track inspection robot to inspect along the belt conveyor, takes pictures of the belt and rollers through the robot camera, and uses a detection algorithm to determine whether the belt is deviating and the severity of the deviation. The fixed detection system is used to perform supplementary detection on the mobile detection system, and uses the semantic segmentation area of ​​the rollers and belts to determine the severity of the belt deviation.

2. The conveyor belt deviation detection system according to claim 1 is characterized in that: The steps of the mobile detection system when working are as follows: S1: Take the belt and roller images I(x,y) through the inspection robot camera; S2: Identify the belt edge and roller edge in the image; S3: Calculate the distance between the belt edge points and the roller edge points on the left and right sides. S4: Compare the distance obtained in step S3 with the normal distance to obtain the offset. S5: Determine the degree of deviation by comparing the offset obtained in step S4 with the set offset. S6: The robot issues a belt deviation alarm.

3. The conveyor belt deviation detection system according to claim 2 is characterized in that: The step S2 further includes the following steps: S21: Use image segmentation algorithm to obtain the pixel area of ​​the belt and the pixel area of ​​the roller. M(x,y)=S(I(x,y)); Among them, I(x,y) is the image before filtering, S represents the image segmentation algorithm, and M(x,y) is the mask of the segmented area; S22: Extract the belt area and the roller area respectively according to the ID of the segmentation mask. M(x,y)=M0(x,y)+M1(x,y)+M2(x,y); Among them, M0(x,y) is the background area mask, M1(x,y) is the belt area mask, and M2(x,y) is the roller area mask; S23: Use edge detection algorithm to extract mask edges of belt area and roller area. B i (x,y)=D(M i (x,y)),i=1,2; Among them, B i (x, y) is the obtained mask edge, and D is the edge detection algorithm; S24: Use logical filtering conditions to select the left and right edges of the belt and the left and right edges of the roller. B k (x,y)=∪(F1(B1),F2(B2)); Among them, F is the boundary filtering condition, S25: Find the belt edge target point and the roller end point from the edge point set. P(x,y)=L(B k ); Among them, L is the traversal and screening logic of edge points, and P is the target point.

4. The conveyor belt deviation detection system according to claim 3 is characterized in that: The steps of the fixed detection system when working are as follows: A1: The camera of the edge computing device captures the belt and roller image I(x,y); A2: Perform instance segmentation on the image to obtain the pixel areas of the roller and belt. M(x,y)=S(I(x,y)); Where I(x,y) is the image before filtering, S represents the image segmentation algorithm, and M(x,y) is the mask of the roller area; A3: Calculate the ratio of the pixel area on the left and right sides of the roller in the image. A4: Compare the area ratio obtained in step A3 with the preset normal value to obtain the difference value. diff=|ratio-ratio normal |; A5: Determine the degree of deviation by comparing the difference value obtained in step A4 with the set difference value. A6: The edge computing device issues a belt deviation alarm.

Images