Ore screen monitoring device and method based on target detection algorithm

Abstract

The invention discloses an ore screen monitoring device and method based on a target detection algorithm. The device comprises bases, and the bases are installed on the two sides of an ore screen respectively; a driving motor and a support are arranged at the top of the base, the driving motor is in transmission connection with a cover plate arranged above the ore screen through a transmission mechanism, the support extends to the position above the cover plate, and a light source used for providing brightness and a visual camera used for obtaining images of the ore screen are arranged on the support. The driving motor drives the cover plate to turn over through the transmission mechanism, so that the ore screen below the cover plate is exposed in the visual field range of the visual camera; after the light source and the visual camera are started, the visual camera collects an ore screen image; an image collected by the visual camera is sent to the image processing system, and the image processing system performs target recognition and feature extraction on the image through a target detection algorithm, analyzes the state of the ore screen in the image and generates a corresponding report; and if an abnormal condition exists, an alarm mechanism is triggered.

Description

Technical Field

[0001] This invention relates to the field of target detection, and in particular to a monitoring device and method for ore screens based on a target detection algorithm. Background Technology

[0002] Ore screen devices are a type of mechanical equipment widely used in the mining industry. When a vibrator is started, the screen generates a rapid reciprocating motion, causing ore particles to jump on the screen. Smaller particles fall through the screen openings to the next layer or collection area, while larger particles remain on the screen surface, thus achieving effective separation of particles of different sizes.

[0003] During vibration, the screen continuously comes into contact with ore particles, especially when processing wet or highly viscous ores, which can easily cause the ore particles to clog the screen openings. This clogging not only reduces screening efficiency but can also increase the operating burden on the equipment, thereby accelerating wear, increasing energy consumption, and potentially shortening the equipment's lifespan. Simultaneously, the continuous vibration of the screen and the impact of the ore also lead to wear on the screen itself. Screen wear further affects screening accuracy and efficiency, as a worn screen may be unable to effectively distinguish between ore particles of different sizes, directly impacting the quality and output of the entire ore processing flow.

[0004] To inspect and resolve these issues, staff need to manually open the equipment cover periodically or when malfunctions occur for inspection and maintenance. This method is not only time-consuming and labor-intensive, but also poses a potential safety hazard to workers, especially in harsh working environments. Furthermore, equipment downtime for maintenance means a decrease in production efficiency, negatively impacting the overall operational efficiency of ore processing enterprises.

[0005] To address the aforementioned issues, patent document No. 201310669565.4 discloses a method, device, and system for monitoring the mesh status of a vibrating screen. The method includes: monitoring and acquiring a static image of the vibrating screen mesh; performing grayscale processing on the static image to obtain a black and white image of the vibrating screen mesh; acquiring the grayscale value of each pixel in the black and white image; determining whether the set automatic cleaning conditions for the vibrating screen have been met based on the grayscale values ​​of each pixel; and initiating the automatic cleaning process of the vibrating screen when the automatic cleaning conditions are met.

[0006] The above technical solution obtains a static image of the vibrating screen mesh by monitoring, and obtains a corresponding black and white image. Based on the gray value of each pixel in the image, it determines whether the screen mesh clogging status has reached the level that needs to be cleaned, thereby realizing intelligent monitoring of the screen mesh clogging status.

[0007] However, because the vibrating screen is in a vibrating state during operation, it is difficult to obtain a static image of the screen, and monitoring can only be carried out during non-operational periods. In addition, it only uses gray and white pixels to determine whether cleaning is needed, which is easily affected by factors such as black ore.

[0008] Therefore, it is necessary to improve the existing technology to overcome the aforementioned defects. Summary of the Invention

[0009] The purpose of this invention is to provide an ore screen monitoring device and method based on a target detection algorithm to solve the problems existing in the prior art.

[0010] The above-mentioned technical objective of the present invention is achieved through the following technical solution:

[0011] A monitoring device for ore screens based on a target detection algorithm includes a base, a pair of bases, with the ore screen placed between the bases, and the bases respectively installed on both sides of the ore screen; a drive motor and a bracket are provided on the top of the base, the output shaft of the drive motor is connected to a cover plate above the ore screen through a transmission mechanism, the bracket extends above the cover plate, and a light source for providing brightness and a vision camera for acquiring images of the ore screen are provided on the bracket.

[0012] Furthermore, the transmission mechanism includes a first transmission wheel, a second transmission wheel, a synchronous belt, and a transmission shaft. The first transmission wheel is mounted on the output shaft of the drive motor and is connected to the second transmission wheel via the synchronous belt. The second transmission wheel is mounted at one end of the transmission shaft, and the other end of the transmission shaft is movably mounted via a bearing.

[0013] Furthermore, the drive motor is mounted on a base on one side of the ore screen, the bearing is mounted on a bearing base on the other side of the ore screen, one end of the drive shaft is connected to the drive motor, and the other end of the drive shaft is movably connected to the bearing base through the bearing.

[0014] Furthermore, the cover plate is fixedly connected to the side of the drive shaft, and the drive motor drives the cover plate to rotate through the drive shaft.

[0015] Furthermore, the support includes a first support part and a second support part, which are respectively disposed on the base on both sides of the ore screen. The top of the support is a crossbeam, and the two ends of the crossbeam are respectively connected to the first support part and the second support part. The light source and the vision camera are mounted on the crossbeam.

[0016] A method for monitoring ore screens based on target detection algorithms includes the following steps:

[0017] 1) Start the drive motor. The drive motor drives the cover plate to flip through the transmission mechanism, so that the ore screen under the cover plate is exposed to the field of view of the vision camera; the light source and vision camera are started, and the vision camera acquires images of the ore screen.

[0018] 2) Images captured by the vision camera are sent to the image processing system. The image processing system uses a target detection algorithm to identify targets and extract features from the images, analyzes the state of the ore screen in the images, and generates corresponding reports.

[0019] 3) If the image processing system detects an abnormality in the ore screen, it will trigger an alarm mechanism.

[0020] The specific process of target recognition and feature extraction in the image is as follows:

[0021] 2.1) Image preprocessing: Denoising, brightness adjustment, contrast adjustment, and image enhancement are performed on the image to optimize the input image and improve the stability and robustness of the algorithm;

[0022] 2.2) Feature Extraction: The target detection algorithm uses Haar feature extraction to extract representative features from the image to identify worn and clogged areas in the image;

[0023] 2.3) Target recognition stage: The image after feature extraction is fed into the target recognition model. The target recognition model learns from historical data to determine the wear and blockage of the ore screen.

[0024] In summary, the present invention has the following beneficial effects:

[0025] It enables real-time monitoring, timely detection and handling of problems with ore screens, reduces the need for manual intervention, and improves the stability and efficiency of the production line. Attached Figure Description

[0026] Figure 1 This is a three-dimensional schematic diagram of the ore screen monitoring device described in this invention.

[0027] Figure 2 This is a rear view of the ore screen monitoring device described in this invention. Detailed Implementation

[0028] To make the technical means, creative features, objectives and effects of this invention easier to understand, the invention will be further described below with reference to the figures and specific embodiments.

[0029] like Figure 1 and Figure 2As shown, the present invention proposes an ore screen monitoring device based on a target detection algorithm, comprising a base 1, wherein a pair of base 1s are provided, and the ore screen is placed between the base 1s, with the base 1s respectively installed on both sides of the ore screen; a drive motor 2 and a bracket 3 are provided on the top of the base 1s, the output shaft of the drive motor 2 is connected to a cover plate 4 disposed above the ore screen through a transmission mechanism, the bracket 3 extends above the cover plate 4, and a light source 5 for providing brightness and a visual camera 6 for acquiring images of the ore screen are provided on the bracket 3.

[0030] The transmission mechanism includes a first transmission wheel 21, a second transmission wheel 22, a synchronous belt 23, and a transmission shaft 24. The first transmission wheel 21 is mounted on the output shaft of the drive motor 2. The first transmission wheel 21 is connected to the second transmission wheel 22 via the synchronous belt 23. The second transmission wheel 22 is mounted at one end of the transmission shaft 24, and the other end of the transmission shaft 24 is movably mounted via a bearing.

[0031] The drive motor 2 is mounted on the base 1 on one side of the ore screen, and the bearing is mounted on the bearing base on the other side of the ore screen. One end of the drive shaft 24 is connected to the drive motor 2, and the other end of the drive shaft 24 is movably connected to the bearing base through the bearing.

[0032] The cover plate 4 is fixedly connected to the side of the transmission shaft 24, and the drive motor 2 drives the cover plate 4 to rotate by driving the transmission shaft 24.

[0033] The support 3 includes a first support part and a second support part, which are respectively set on the base 1 on both sides of the ore screen. The top of the support 3 is a crossbeam, and the two ends of the crossbeam are respectively connected to the first support part and the second support part. The light source 5 and the vision camera 6 are installed on the crossbeam.

[0034] A method for monitoring ore screens based on target detection algorithms includes the following steps:

[0035] 1) Start the drive motor. The drive motor drives the cover plate 4 to flip through the transmission mechanism, so that the ore screen under the cover plate 4 is exposed to the field of view of the vision camera 6; the light source 5 and the vision camera 6 are started, and the vision camera 6 acquires images of the ore screen.

[0036] 2) The images captured by the vision camera 6 are sent to the image processing system. The image processing system performs target recognition and feature extraction on the images through target detection algorithms, analyzes the state of the ore screen in the images, and generates corresponding reports.

[0037] 3) If the image processing system detects an abnormality in the ore screen, it will trigger an alarm mechanism.

[0038] The specific process of target recognition and feature extraction in the image is as follows:

[0039] 2.1) Image preprocessing: Denoising, brightness adjustment, contrast adjustment, and image enhancement are performed on the image to optimize the input image and improve the stability and robustness of the algorithm;

[0040] 2.2) Feature Extraction: The target detection algorithm uses Haar feature extraction to extract representative features from the image to identify worn and clogged areas in the image;

[0041] Haar feature extraction is a widely used feature extraction algorithm in computer vision, especially excelling in areas such as face detection and object tracking. Haar features describe image features by calculating the difference in pixel values ​​between neighboring regions, and these features are highly sensitive to structures such as edges, lines, and regions in the image.

[0042] 2.3) Target recognition stage: The image after feature extraction is fed into the target recognition model. The target recognition model learns from historical data to determine the wear and blockage of the ore screen.

[0043] Example

[0044] Traditional machine learning-based target detection algorithms can effectively monitor screen wear and clogging in this industrial application. This process can be divided into stages such as cover opening, camera capturing, image processing, and alarm activation.

[0045] (1) Open the cover plate

[0046] A cover plate is a mechanical device used to open the equipment's casing or cover, allowing the camera to directly capture images of the screen. The cover plate is motor-driven, and the opening operation is achieved through an automatic control system. This step ensures that the screen is fully exposed within the camera's field of view, providing the necessary conditions for subsequent image acquisition.

[0047] (2) Taking photos with a camera

[0048] Once the screen is exposed, the camera will be triggered to acquire images. Camera selection should take into account factors such as ambient lighting conditions, field-of-view requirements, and image resolution. The captured images will contain detailed information about the screen, including potential wear, clogging, etc.

[0049] (3) Image processing stage

[0050] The captured images will be sent to an image processing system, which uses traditional machine learning algorithms for feature extraction and target recognition. At this stage, the system will analyze the state of the screen in the image, detect wear, blockages, and other issues, and generate corresponding reports.

[0051] (4) Alarm stage

[0052] Once the image processing system detects an abnormality in the screen, such as wear exceeding a threshold or blockage, the system will trigger an alarm mechanism. The alarm can be triggered via sound, light, a visual interface, or remote notification to promptly notify relevant personnel to take necessary maintenance and repair measures.

[0053] The advantage of this automated inspection process lies in its ability to monitor in real time, promptly detect and address screen problems, reduce the need for manual intervention, and improve the stability and efficiency of the production line. The successful implementation of the entire process relies on the coordinated operation of the equipment to ensure the smooth progress of each step, thus providing a reliable screen condition monitoring solution for industrial production.

[0054] In this document, the terms "upper," "lower," "front," "back," "left," "right," "top," "bottom," "inner," "outer," "vertical," and "horizontal," etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are only used for the clarity of expressing the technical solution and for the convenience of description, and therefore should not be construed as limiting the present invention.

[0055] In this document, the terms “comprising,” “including,” or any other variations thereof are intended to cover non-exclusive inclusion, which includes not only the elements listed but also other elements not expressly listed.

[0056] The foregoing has shown and described the basic principles, main features, and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The embodiments and descriptions in the specification are merely illustrative of the principles of the invention. Various changes and modifications can be made to the invention without departing from its spirit and scope, and all such changes and modifications fall within the scope of the present invention as claimed. The scope of protection of this invention is defined by the appended claims and their equivalents.

Claims

1. A monitoring device for ore screens based on a target detection algorithm, characterized in that, The device includes a base (1), which is provided in pairs. The ore screen is placed between the bases (1) and the bases (1) are respectively installed on both sides of the ore screen. A drive motor (2) and a bracket (3) are provided on the top of the base (1). The output shaft of the drive motor (2) is connected to the cover plate (4) above the ore screen through a transmission mechanism. The bracket (3) extends above the cover plate (4). A light source (5) for providing brightness and a vision camera (6) for acquiring images of the ore screen are provided on the bracket (3).

2. The ore screen monitoring device based on target detection algorithm according to claim 1, characterized in that, The transmission mechanism includes a first transmission wheel (21), a second transmission wheel (22), a synchronous belt (23), and a transmission shaft (24). The first transmission wheel (21) is mounted on the output shaft of the drive motor (2). The first transmission wheel (21) is connected to the second transmission wheel (22) via the synchronous belt (23). The second transmission wheel (22) is mounted on one end of the transmission shaft (24), and the other end of the transmission shaft (24) is movably mounted via a bearing.

3. The ore screen monitoring device based on target detection algorithm according to claim 2, characterized in that, The drive motor (2) is mounted on the base (1) on one side of the ore screen, and the bearing is mounted on the bearing base on the other side of the ore screen. One end of the drive shaft (24) is connected to the drive motor (2) for transmission, and the other end of the drive shaft (24) is movably connected to the bearing base through the bearing.

4. The ore screen monitoring device based on target detection algorithm according to claim 2, characterized in that, The cover plate (4) is fixedly connected to the side of the transmission shaft (24), and the drive motor (2) drives the cover plate (4) to rotate through the drive shaft (24).

5. The ore screen monitoring device based on target detection algorithm according to claim 1, characterized in that, The bracket (3) includes a first support part and a second support part, which are respectively set on the base (1) on both sides of the ore screen. The top of the bracket (3) is a crossbeam, and the two ends of the crossbeam are respectively connected to the first support part and the second support part. The light source (5) and the vision camera (6) are installed on the crossbeam.

6. A method for monitoring ore screens based on a target detection algorithm, characterized in that, Includes the following steps: 1) Start the drive motor. The drive motor drives the cover plate (4) to flip through the transmission mechanism, so that the ore screen under the cover plate (4) is exposed to the field of view of the vision camera (6); the light source (5) and the vision camera (6) are started, and the vision camera (6) acquires images of the ore screen. 2) The images acquired by the vision camera (6) are sent to the image processing system. The image processing system performs target recognition and feature extraction on the images through the target detection algorithm, analyzes the state of the ore screen in the images, and generates corresponding reports. 3) If the image processing system detects an abnormality in the ore screen, it will trigger an alarm mechanism.

7. The ore screen monitoring method based on target detection algorithm according to claim 6, characterized in that, The specific process of target recognition and feature extraction in the image is as follows: 2.1) Image preprocessing: Denoising, brightness adjustment, contrast adjustment, and image enhancement are performed on the image to optimize the input image and improve the stability and robustness of the algorithm; 2.2) Feature Extraction: The target detection algorithm uses Haar feature extraction to extract representative features from the image to identify worn and clogged areas in the image; 2.3) Target recognition stage: The image after feature extraction is fed into the target recognition model. The target recognition model learns from historical data to determine the wear and blockage of the ore screen.

Images