Visual identification device and method for deviation of trolley

Abstract

The invention discloses a trolley deviation visual identification device. Comprising a support arranged on one side of a track, and a protective cover is arranged on the support. A camera device is arranged in the protective cover; the camera device is positioned right above the wheels; and the visual identification system is used for identifying the images, collected by the camera device, of the wheels. Through the visual recognition device arranged on one side of the track, the pose of the trolley can be accurately recognized and judged; and the service lives of the wheels and the bearings of the trolley can be judged.

Description

Technical Field

[0001] The present invention relates to a visual recognition device and method for trolley deviation. Background Art

[0002] For many years, the wheels of the sintering machine trolley have always been lubricated manually when the sintering machine is in a stopped state. During the limited downtime for maintenance, the wheels of the sintering machine trolley often cannot be effectively lubricated. Moreover, within the downtime interval of the sintering machine, the lubricating grease in the wheels of the sintering machine trolley has been completely consumed. The insufficient lubricating grease in the sintering machine wheels will shorten the service life of the bearings, and thus affect the function of the trolley wheels. When the trolley wheels get stuck, it is necessary to stop the machine and replace them in time, otherwise it may affect the overall operation of the sintering machine.

[0003] Replacing the trolley during downtime will, first, affect the operation rate of the sintering machine and the output of sintered ore, resulting in economic losses. Second, the replacement of the sintering machine trolley will affect the material balance during the sintering process. The process of the material returning from imbalance to balance not only affects the quality of the sintered ore, but also causes unnecessary energy losses. The use of an automatic lubricating device for the sintering machine can solve the above problems. And the automatic lubricating device has precise requirements for the position and posture of the trolley to control its own posture, while the traditional method of visual recognition plus sensors cannot effectively sense the posture of the wheels Summary of the Invention

[0004] In view of the above problems, the present invention relates to a visual recognition device and method for trolley deviation.

[0005] To achieve the above object, a visual recognition device for trolley deviation of the present invention includes a bracket arranged on one side of the track,

[0006] A protective cover is arranged on the bracket;

[0007] A camera device is arranged inside the protective cover; the camera device is located directly above the wheel;

[0008] It further includes a visual recognition system for recognizing the image of the wheel collected by the camera device.

[0009] Further, an inlet check valve and an outlet check valve are arranged inside the protective cover; compressed air is connected to the check valves through pipelines.

[0010] Further, an auxiliary light source is arranged inside the protective cover.

[0011] To achieve the above object, a visual recognition method for trolley deviation of the present invention is implemented based on the above device, and the method includes the following steps:

[0012] Obtain the historical images of the wheels and perform preprocessing;

[0013] Use the preprocessed images to make labels and then use them to train the neural network;

[0014] Use the neural network to identify and judge the images of the wheels collected in real time by the imaging device, and then output the wheel attitude data.

[0015] Furthermore, the wheel attitude data includes the deflection angle α of the wheel, the wheel alignment value z, and the deviation value x of the wheel radius on the track center line.

[0016] Furthermore, the preprocessing is performed using the histogram equalization method.

[0017] Furthermore, it also includes the step of judging the threshold of the wheel boundary continuity. After the boundary continuity meets the requirements, it is output as qualified data.

[0018] Through the visual recognition device provided on one side of the track, the present invention can accurately identify and judge the pose of the trolley; it is beneficial to judge the service life of the wheels and bearings of the trolley. Brief Description of the Drawings

[0019] Figure 1 It is the hardware structure diagram of the visual recognition device.

[0020] Figure 2 It is the schematic diagram of the algorithm flow of the visual recognition device.

[0021] Figure 3(a) shows the original state of the wheel; Figure 3(b) shows the schematic diagram of the output result of the visual recognition device. Detailed Embodiment

[0022] The embodiments of the present invention will be described in detail below with reference to the drawings.

[0023] In the description of the present invention, it should be understood that the orientation or positional relationship indicated by the terms "center", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", etc. is based on the orientation or positional relationship shown in the drawings, and is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be construed as a limitation to the present invention.

[0024] The terms "first" and "second" are for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, features defined with "first" and "second" may explicitly or implicitly include one or more of such features. In the description of the present invention, unless otherwise specified, the meaning of "a plurality" is two or more.

[0025] In the description of the present invention, it should be noted that, unless otherwise clearly specified and limited, the terms "mounted", "connected" and "coupled" should be understood in a broad sense. For example, it may be a fixed connection, a detachable connection, or an integral connection; it may be directly connected, or indirectly connected through an intermediate medium, and it may be the communication inside two components. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific situations.

[0026] As shown in the figure, a visual recognition device for trolley deviation includes (1) a bracket, (2) a protective cover, (3-1) an inlet check valve, (3-2) an outlet check valve, and (4) a camera.

[0027] (1) The bracket is used to support (2) the protective cover, and the protective cover is supplied with compressed air. (3-1) The inlet check valve and (3-2) the outlet check valve are installed on (2) the protective cover. The protective cover is used to protect the imaging device - the camera, and at least the bottom side thereof is made of a glass plate; (3-1) the inlet check valve ensures that the compressed air does not flow back, and (3-2) the outlet check valve ensures that dust does not flow back into the protective cover, so that it can not only protect the camera but also play a role in heat dissipation. (4) The camera is located directly above the wheel and converts the physical characteristics of the wheel pose into digital signals. (5) The auxiliary light source is arranged in (2) the protective cover. When the camera works, the auxiliary light source is turned on to ensure the stability of the photo quality. The hardware is arranged as shown in Figure (1).

[0028] The software part and the algorithm part convert the digital signals into characteristic signals for output: The preprocessing of the photo image can adopt the histogram equalization method to filter various signal noises. After the preprocessing, the photo is labeled and used to train the neural network. The trained neural network can output the pose size of the wheel. The software flow chart is shown in Figure (2).

[0029] In actual application cases, histogram equalization is used for image preprocessing, while the U-Net neural network is adopted. The output wheel attitude data is shown in Figure (3): Taking the track center line as the reference line, the complete coincidence of the wheel center line and the track center line is used for calibration, as shown in Figure (3a). During actual use, comparing the position of the wheel with the calibrated position, the neural network outputs the wheel deflection angle α, the wheel deviation value z, and the wheel radius deviation value x on the track center line, as shown in Figure (3b). The data output by the U-Net network needs to be judged by the threshold of boundary continuity. After the boundary continuity meets the requirements, it is output as qualified data.

[0030] The present invention has been described in detail above with reference to the accompanying drawings. However, the present invention is not limited to the above embodiments. Within the scope of knowledge possessed by those of ordinary skill in the art, various changes can be made without departing from the gist of the present invention. Many other changes and modifications made without departing from the concept and scope of the present invention should be regarded as within the protection scope of the present invention.

[0031] In the description of this specification, specific features, structures, materials, or characteristics can be combined in a suitable manner in any one or more embodiments or examples.

[0032] As mentioned above, only the specific embodiments of the present invention are described, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention can easily think of changes or substitutions, which should all be covered by the protection scope of the present invention. Therefore, the protection scope of the present invention should be subject to the protection scope of the claims.

Claims

1. A visual recognition device for trolley deviation, characterized in that, It includes a bracket arranged on one side of the track, and a protective cover is arranged on the bracket; a camera device is arranged in the protective cover; the camera device is located directly above the wheel; it further includes a visual recognition system for recognizing the image of the wheel collected by the camera device.

2. The visual recognition device for trolley deviation as described in claim 1, characterized in that, An inlet check valve and an outlet check valve are arranged in the protective cover; compressed air is communicated through a pipeline on the check valve.

3. The visual recognition device for trolley deviation as described in claim 1, characterized in that An auxiliary light source is arranged in the protective cover.

4. A visual recognition method for trolley deviation, the method is implemented based on the device described in claim 1, and is characterized in that, The method includes the following steps: Obtain the historical image of the wheel and perform preprocessing; Use the preprocessed image to make labels and then use them to train the neural network; After using the neural network to recognize and judge the image of the wheel collected in real time by the camera device, output the wheel attitude data.

5. The visual recognition method for trolley deviation as described in claim 4, wherein The wheel attitude data includes the deflection angle α of the wheel, the wheel deviation value z, and the wheel radius deviation value x on the track center line.

6. The visual recognition method for trolley deviation as claimed in claim 4, wherein, The preprocessing is performed by using the histogram equalization method.

7. The trolley deviation visual recognition method according to claim 4, characterized in that, It further includes the step of judging the threshold of the wheel boundary continuity, and output the qualified data after the boundary continuity meets the requirements.

Images