Belt conveyor intelligent monitoring method and system

Abstract

The application provides a belt conveyor intelligent monitoring method and system, and relates to the field of coal conveying belt conveyors. The method comprises the following steps: collecting images of the belt conveyor during operation in real time, wherein the images comprise material information and belt information; detecting the edge position of the belt in the images in real time, and judging whether the belt has a deviation tendency by comparing the movement range of the belt during normal operation, wherein the belt is corrected in real time when the belt deviates; continuously sampling the green light on the surface of the material in the image over time to determine the coal conveying flow, and judging whether the material blocking phenomenon occurs in the coal falling pipe by comparing the coal conveying flow with the standard coal conveying flow. The application realizes intelligent analysis and active early warning of safety hazards of the belt conveyor by analyzing the operation process of the belt conveyor in real time through image processing, and improves the production efficiency.

Description

Technical Field

[0001] This application relates to the field of coal conveyor belts, and in particular to an intelligent monitoring method and system for conveyor belts. Background Technology

[0002] As the core component of belt conveyors, coal conveyor belts are relatively expensive (accounting for more than 40% of the operating cost of belt conveyors). Due to the harsh environment in the coal conveying area of ​​power plants, coupled with the inherent strength issues of the belts themselves, the following faults are prone to occur during production: roller failure, belt misalignment, idler roller failure, and hopper blockage, which have a significant impact on production. The belt conveyor system is currently equipped with basic protection and monitoring devices, but these devices cannot meet the requirements of intelligent inspection, and a large number of dedicated belt conveyor inspection personnel are still needed to inspect the equipment.

[0003] Currently, the inspection methods used by patrol personnel mainly include visual, auditory, olfactory, and tactile inspections. Firstly, the on-site environment and working conditions are harsh, with large amounts of coal dust and ore dust present, significantly impacting the health of patrol personnel and increasing the risk of personal injury accidents during inspections and maintenance. Secondly, the work of patrol workers is monotonous and demanding, resulting in high staff turnover and recruitment difficulties. Thirdly, the long and extensive patrol routes lead to low inspection efficiency and require relatively high levels of personal experience, increasing the possibility of missed or incorrect inspections. Fourthly, the manual inspection and paper-based record-keeping methods make it difficult to achieve closed-loop management and dynamic tracking of hazard identification and mitigation. Summary of the Invention

[0004] To address the above problems, an intelligent monitoring method and system for belt conveyors is proposed. The technical solution of this application is as follows:

[0005] The first aspect of this application proposes an intelligent monitoring method for belt conveyors, including:

[0006] Real-time acquisition of images of the belt conveyor during operation, wherein the images include material information and belt information;

[0007] The edge position of the belt in the image is detected in real time. By comparing it with the range of motion of the belt during normal operation, it is determined whether the belt has a tendency to deviate. When the belt deviates, the belt is corrected in real time.

[0008] The green light on the surface of the material in the image is sampled continuously over time to determine the coal conveying flow rate. By comparing the coal conveying flow rate with the standard coal conveying flow rate, it is determined whether the coal chute is blocked.

[0009] Optionally, before detecting the edge position of the belt within the image in real time, the following steps are included:

[0010] Image samples of the belt conveyor during normal operation are collected, and image segmentation and feature extraction are performed on the image samples to obtain parameter information of the reference calibration plate in the image samples, wherein the parameter information includes color information and shape information;

[0011] The parameter information is used as feature samples, and the feature samples are trained and calibrated using a support vector machine to generate a belt misalignment diagnosis model.

[0012] Optionally, the real-time detection of the belt's edge position within the image, and the determination of whether the belt has a tendency to deviate by comparing it with the belt's normal operating range, includes:

[0013] The color difference characteristics of the belt and the reference calibration plate in the image are determined based on the belt misalignment diagnosis model.

[0014] Based on the color difference characteristics, the edge features and position of the belt are detected to determine the virtual deviation amount;

[0015] The real-time deviation of the belt is determined by comparing the virtual deviation with the virtual deviation feature table.

[0016] Optionally, when the belt deviates from its designated path, real-time correction of the belt includes:

[0017] Based on the virtual belt misalignment, the belt is corrected in real time using PID control technology.

[0018] Optionally, the step of continuously sampling the green light on the surface of the material in the image to determine the coal conveying flow rate, and comparing the coal conveying flow rate with the standard coal conveying flow rate to determine whether a blockage has occurred in the coal chute, includes:

[0019] The green light on the surface of the material in the image is sampled continuously over time, the volume of the material during that time is calculated, and the coal conveying flow rate of the belt is determined based on the volume.

[0020] Based on the standard material weight passing on the belt and the pipe length per unit time, calculate the standard coal conveying flow rate within the same duration as the sampling time on the belt.

[0021] By comparing the coal conveying flow rate with the standard coal conveying flow rate, it is determined whether the coal chute is blocked.

[0022] Optionally, the step of continuously sampling the green light rays on the surface of the material within the image and calculating the volume of the material within that time period includes:

[0023] Extract the green light rays from the material surface in the image, and calculate the pixel height difference between each point on the green light rays and the surface of the belt;

[0024] Calculate the area of ​​the closed surface formed by the green light ray and the belt surface;

[0025] Repeat the above steps to continuously sample the green light, and calculate the volume of the material within that time period based on the pixel height difference and the area of ​​the closed surface at each sampling time.

[0026] Optionally, the method further includes:

[0027] The stacking pattern of the material within the image is identified to determine whether the material is aligned with the drop point.

[0028] Optionally, an alarm may be sent to the central platform when the conveyor belt deviates or when the coal chute becomes blocked.

[0029] The second aspect of this application proposes an intelligent monitoring system for belt conveyors, including a camera, a belt misalignment visual diagnosis system, an automatic correction system, and a coal chute blockage visual diagnosis and control system.

[0030] The camera is installed directly in front of or behind the belt. The belt misalignment visual diagnosis system, the automatic correction system, and the coal chute blockage visual diagnosis and control system are respectively installed at the head of the belt conveyor and the outlet of the guide chute.

[0031] The camera is used to capture images of the belt conveyor in real time during operation.

[0032] The belt misalignment visual diagnosis system is used to detect the edge position of the belt in the image in real time, and by comparing it with the range of movement of the belt during normal operation, it determines whether the belt has a tendency to deviate, and sends an alarm to the central platform when the belt deviates.

[0033] The automatic belt deviation correction system is used to correct the belt deviation in real time when the belt runs off-track.

[0034] The visual diagnosis and control system for material blockage in the coal chute is used to continuously sample the green light on the surface of the material in the image to determine the coal conveying flow rate. By comparing the coal conveying flow rate with the standard coal conveying flow rate, it determines whether a blockage has occurred in the coal chute and sends an alarm to the central platform when a blockage occurs.

[0035] The technical solutions provided by the embodiments of this application have at least the following beneficial effects:

[0036] By using image processing technology, the status of the belt and materials during the operation of the belt conveyor is monitored in real time, and alarms are issued when abnormalities occur. This enables intelligent analysis and proactive early warning of safety hazards in the belt conveyor, making hazard investigation more timely and efficient, reducing downtime and the number of downtimes caused by malfunctions, improving production efficiency, and ensuring the safety of personnel and equipment.

[0037] Additional aspects and advantages of this application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this application. Attached Figure Description

[0038] The above and / or additional aspects and advantages of this application will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, wherein:

[0039] Figure 1 This is a flowchart illustrating an intelligent monitoring method for belt conveyors according to an embodiment of this application;

[0040] Figure 2 This is a flowchart illustrating the training process of a belt misalignment diagnostic model according to an embodiment of this application;

[0041] Figure 3 This is a flowchart illustrating the determination of whether the belt is misaligned, according to an embodiment of this application;

[0042] Figure 4 This is a flowchart illustrating the process of determining whether a blockage has occurred in the coal chute, as shown in the embodiments of this application.

[0043] Figure 5 This is an image captured by a camera during the operation of a conveyor belt, as shown in an embodiment of this application. Detailed Implementation

[0044] The embodiments of this application are described in detail below. Examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain this application, and should not be construed as limiting this application.

[0045] Figure 1 This is a flowchart illustrating an intelligent monitoring method for a belt conveyor according to an embodiment of this application, including:

[0046] Step 101: Real-time acquisition of images of the belt conveyor during operation, including material information and belt information.

[0047] In this embodiment, a high-definition camera installed directly in front of or behind the belt captures images of the belt conveyor in real time during operation. Figure 5It is an image of a belt conveyor in operation, captured by a high-definition camera.

[0048] Step 102: Detect the edge position of the belt in the image in real time. By comparing it with the range of motion of the belt during normal operation, determine whether the belt has a tendency to deviate. When the belt deviates, correct the belt deviation in real time.

[0049] Prolonged operation of belt conveyors can lead to belt misalignment, where the conveyor belt's centerline does not align with the frame's centerline. When belt misalignment reaches a certain level, it triggers the emergency stop device used to prevent deviation, causing the operating system to shut down and impacting production. If the belt misalignment is severe, causing the force on one side of the belt to exceed its longitudinal breaking strength, it can lead to safety hazards such as lateral belt tearing. Traditional two-stage detection switches can only detect misalignment alarms and stop operations in cases of severe misalignment; the switching sensors cannot establish belt misalignment data or perform corrective control.

[0050] In this embodiment, a belt misalignment visual diagnosis system and an automatic correction system installed at the head of the conveyor belt and the outlet of the guide chute determine and correct the belt misalignment tendency. White calibration plates of the same size and shape are installed on both sides of the belt near the lower surface of the belt as reference calibration plates. Image recognition technology is used to diagnose belt misalignment, realizing non-destructive monitoring, alarm and emergency shutdown of belt misalignment.

[0051] In this embodiment of the application, the belt running status is diagnosed using a trained belt misalignment diagnosis model. The training process of the belt misalignment diagnosis model includes:

[0052] Step 201: Collect image samples of the belt conveyor during normal operation, perform image segmentation and feature extraction on the image samples, and obtain the parameter information of the reference calibration plate in the image samples. The parameter information includes color information and shape information.

[0053] Step 202: The parameter information is used as feature samples. The feature samples are trained and calibrated using a support vector machine to generate a belt misalignment diagnosis model.

[0054] The image samples are captured by a camera, and the belt misalignment diagnosis model is built into the belt misalignment visual diagnosis system. In this embodiment, the process by which the belt misalignment visual diagnosis system determines whether the belt has a tendency to misalign includes:

[0055] Step 301: Determine the color difference characteristics between the belt and the reference calibration plate in the image based on the belt misalignment diagnosis model;

[0056] Step 302: Detect the edge features and position of the belt based on the color difference characteristics to determine the virtual deviation amount;

[0057] Step 303: Based on the virtual belt misalignment feature table, compare the virtual belt misalignment to determine the real-time belt misalignment.

[0058] Among them, the belt misalignment detection is accurate to the 5mm level, the system has high reliability, the belt itself does not need to be specially designed, the calibration plate can be replaced at any time, it has strong versatility, maximizes the protection of belt life, and has high detection accuracy.

[0059] In this embodiment, the automatic belt alignment system achieves active belt alignment and correction through a powerful electric belt alignment device configured at the belt, ensuring belt conveying efficiency and preventing material spillage.

[0060] The automatic belt alignment system utilizes advanced PID control technology. It detects and provides real-time feedback of the simulated belt deviation displacement through a visual belt alignment system. The system then controls the electric belt alignment device through PID data processing to correct the belt misalignment. The entire system achieves closed-loop control and ultimately realizes steady-state control of the belt operation.

[0061] In this embodiment, when the belt deviates from its designated path, an alarm is sent to the central platform. The platform generates corresponding alarm information to remind the production department's on-duty supervisor. The supervisor manually reviews the alarm for both positive and false alarms. If a positive alarm is confirmed, operations are immediately stopped, and belt conveyor maintenance personnel are contacted for on-site rectification. After the maintenance personnel complete the on-site rectification, the production department's on-duty supervisor further confirms the rectification. Once confirmed, the production department's on-duty supervisor completes the closed-loop event archiving of hazard discovery, handling, and rectification confirmation, and the belt conveyor can be restarted.

[0062] Step 103: Continuously sample the green light on the surface of the material in the image to determine the coal conveying flow rate. By comparing the coal conveying flow rate with the standard coal conveying flow rate, determine whether the coal chute is blocked.

[0063] Blockage of the conveyor belt hopper is a common problem in the conveying process. When the receiving hopper's discharge chute is blocked, it often causes the equipment to trip due to interlocking, affecting normal production.

[0064] Traditional coal conveying systems cannot effectively and automatically detect and control changes in material points, belt misalignment, instantaneous overload, and spillage caused by instantaneous overload. Existing blockage sensors have low reliability and cannot provide blockage warnings.

[0065] In this embodiment, a visual diagnosis and control system for material blockage in the coal chute, installed at the head of the conveyor belt and the outlet of the feed chute, determines whether material blockage has occurred in the coal chute and sends an alarm to the central platform when material blockage occurs.

[0066] In this embodiment of the application, step 103 further includes:

[0067] Step 401: Continuously sample the green light rays on the surface of the material in the image, calculate the volume of the material within that time period, and determine the coal conveying flow rate of the conveyor belt within that time period based on the volume.

[0068] In this embodiment, firstly, green light rays from the material surface in the image are extracted, and the pixel height difference between each point on the green light ray and the belt surface is calculated. Secondly, the area of ​​the closed surface formed by the green light ray and the belt surface is calculated. The above steps are repeated to continuously sample the green light ray over time. Based on the pixel height difference and the area of ​​the closed surface at each sampling time, the volume of the material during that time is calculated.

[0069] Step 402: Based on the standard material weight passing on the belt and the pipe length per unit time, calculate the standard coal conveying flow rate within the same time frame as the sampling time.

[0070] In this embodiment of the application, the weight of the material passing through the belt per unit time is set, and the estimated standard coal conveying flow rate is calculated based on the sampling time.

[0071] Step 403: Compare the coal conveying flow rate with the standard coal conveying flow rate to determine whether there is a blockage in the coal chute.

[0072] In addition, the visual diagnosis and control system for material blockage in the coal chute is also used to identify the pile shape of materials on the belt conveyor at the transfer point and determine whether the materials are aligned. Misalignment of the material point will induce belt deviation, causing material spillage and reducing conveying efficiency. The alignment of the material point can guide operation and maintenance. In special transfer links, the signal of material deviation can be used to control the adjusting baffle or adjust the posture of the belt before receiving material, thereby achieving material alignment.

[0073] Similarly, when a blockage occurs in the coal chute, an alarm is sent to the central platform. The platform then generates a corresponding alarm message to remind the production department's on-duty supervisor. The supervisor manually verifies the alarm's validity and whether it is a false alarm. If it is confirmed to be a valid alarm, operations are immediately stopped, and the conveyor belt maintenance personnel are contacted for on-site rectification. After the maintenance personnel complete the on-site rectification, the production department's on-duty supervisor further confirms the rectification. Once confirmed, the production department's on-duty supervisor completes the closed-loop event archiving of the hazard discovery, handling, and rectification confirmation, and the conveyor belt can be restarted.

[0074] This application utilizes image processing technology to monitor the status of the belt and materials during the operation of the conveyor belt in real time, and issues an alarm when an abnormality occurs. This enables intelligent analysis and proactive early warning of potential safety hazards in the conveyor belt, making hazard investigation more timely and efficient, reducing downtime and the number of downtimes caused by malfunctions, improving production efficiency, and ensuring the safety of personnel and equipment.

[0075] Regarding the apparatus in the above embodiments, the specific manner in which each module performs its operation has been described in detail in the embodiments related to the method, and will not be elaborated upon here.

[0076] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution disclosed in this disclosure can be achieved, and this is not limited herein.

[0077] The specific embodiments described above do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure should be included within the scope of protection of this disclosure.

Claims

1. A method for intelligent monitoring of a belt conveyor, characterized by, The method comprises the following steps: real-time image acquisition of the belt conveyor in operation, wherein the image comprises material information and belt information; determination of color difference characteristics of the belt and the reference calibration plate in the image; detection of edge characteristics and position of the belt according to the color difference characteristics, and determination of virtual deviation amount; comparison of the virtual deviation amount with a virtual deviation amount characteristic table to determine whether the belt has a deviation tendency and to determine real-time deviation amount of the belt, wherein white calibration plates of the same size and shape are installed on both sides of the belt near the lower surface of the belt as reference calibration plates to diagnose belt deviation, and the belt is corrected in real time according to PID control technology based on the virtual deviation amount when the belt deviates; extraction of green light on the surface of the material in the image, and calculation of pixel height difference between each point on the green light and the surface of the belt; calculation of the area of the closed surface formed by the green light and the surface of the belt; continuous time sampling of the green light, and calculation of the volume of the material in each sampling time according to the pixel height difference and the area of the closed surface in each sampling time, and determination of the coal conveying flow of the belt in each sampling time according to the volume; calculation of the standard coal conveying flow of the belt in the same time period as the sampling time based on the weight of the standard material passing through the belt in unit time and the length of the pipeline; comparison of the coal conveying flow and the standard coal conveying flow to determine whether the coal chute is blocked. The method further comprises the following steps: identification of the stacking type of the material in the image to determine whether the material is centered on the material dropping point.

2. The method of claim 1, wherein, Before real-time detection of the edge position of the belt in the image, the method comprises the following steps: image sample acquisition of the belt conveyor in normal operation, image segmentation and feature extraction of the image sample to obtain parameter information of the reference calibration plate in the image sample, wherein the parameter information comprises color information and shape information; training and calibration of the feature sample by support vector machine using the parameter information as the feature sample to generate a belt deviation diagnosis model.

3. The method of claim 2, wherein, determination of color difference characteristics of the belt and the reference calibration plate in the image according to the belt deviation diagnosis model.

4. The method of claim 1, wherein, warning to the central platform when the belt deviates or the coal chute is blocked.

5. A belt conveyor intelligent monitoring system, characterized in that, The belt conveyor intelligent monitoring system is used to realize the belt conveyor intelligent monitoring method according to claim 1, and the system comprises a camera, a belt deviation visual diagnosis system, an automatic deviation correction system, and a coal chute blockage visual diagnosis and control system, wherein the camera is installed in front of or behind the belt, and the belt deviation visual diagnosis system, the automatic deviation correction system, and the coal chute blockage visual diagnosis and control system are installed at the head of the belt conveyor and the outlet of the material guide groove, respectively; the camera is used to acquire images of the belt conveyor in operation in real time; the belt deviation visual diagnosis system is used to detect the edge position of the belt in the image in real time, to determine whether the belt has a deviation tendency by comparing the movement range of the belt in normal operation, and to warn the central platform when the belt deviates; The automatic deviation correction system is used for correcting the deviation of the belt in real time when the belt deviates; The coal falling pipe blockage visual diagnosis and control system is used for continuously sampling the green light on the surface of the material in the image to determine the coal conveying flow rate, comparing the coal conveying flow rate with the standard coal conveying flow rate to determine whether the coal falling pipe is blocked, and alarming the center platform when the coal falling pipe is blocked.

Images