Sintering round roller material distribution unblocking control system based on video analysis and control method of sintering round roller material distribution unblocking control system

Abstract

The invention discloses a sintering round roller material distribution unblocking control system based on video analysis and a control method thereof, and belongs to the technical field of sintering process automation control, the system comprises a data acquisition module, a video analysis module and an unblocking control module which are in signal connection in sequence, and the data acquisition module acquires images through an industrial camera and communicates with a PLC through an OPC UA protocol; the video analysis module is used for accurately identifying the blockage and the position and outputting a signal through image preprocessing, cutting, feature extraction and judgment; and the unblocking control module receives the signal to automatically execute unblocking operation, and supports parameter setting and alarming. The control method comprises the following steps: executing blockage video analysis and blockage clearing control flow once per second, and triggering manual inspection alarm when blockage clearing is invalid. Automatic and digital operation of sintering round roller material distribution is achieved, the accuracy is improved, the working environment of workers is improved, and the safety risk is reduced.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of sintering process automatic control, and particularly relates to a sintering round roller material distribution and blockage clearing control system based on video analysis and a control method thereof. BACKGROUND

[0002] In the sintering process, material distribution is a crucial link, which is directly related to the quality and yield of sintered ore. Round roller distribution, as a common distribution method, has been widely used in the sintering process. However, the problem of round roller blockage caused by large pieces of material in the distribution is a common problem in the production process. Currently, post workers need to observe the material attached to the round roller to determine whether blockage occurs. Once blockage is confirmed, they need to manually open the auxiliary door to allow the large pieces of material to pass through and then restore the auxiliary door to the original opening. However, this work needs to be done at the sintering machine head, where the temperature is high, the noise is loud, and the dust is heavy, posing a serious threat to the health and safety of post workers. SUMMARY

[0003] To solve the above problems, the application provides a sintering round roller material distribution and blockage clearing control system based on video analysis, which includes a data acquisition module, a video analysis module, and a blockage clearing control module, and the modules are sequentially connected in signal. The data acquisition module is used to acquire image data of the round roller distribution area and communicate data with the PLC through the OPC UA protocol to realize real-time acquisition and control of round roller and auxiliary door related data. The video analysis module is used to process and analyze the acquired image data to determine whether there is blockage and the specific location of the blockage, and output a blockage signal. The blockage clearing control module is used to receive the blockage signal output by the video analysis module and perform corresponding blockage clearing control operations, and support user parameter setting and system alarm setting.

[0004] The data acquisition module includes an industrial camera, which is used to real-time shoot the round roller distribution area, acquire raw image data and transmit to the video analysis module.

[0005] The video analysis module includes the following modules: The image preprocessing module: performs RGB to HSV color space conversion, Gaussian filter denoising, and histogram equalization contrast enhancement processing on the original image. The image cutting module: cuts the preprocessed image horizontally in equal proportions according to the auxiliary door deployment position to obtain sub-images corresponding to the auxiliary door one by one. Feature extraction module: the feature extraction of the non-sintering material area of each sub-image is carried out, the actual area of the non-sintering material is obtained through the brightness V threshold segmentation of the HSV color space, the morphological edge processing and the area correction; Feature judgment module: the actual area of the non-sintering material is compared with the set area threshold value, and the blocking signal of the corresponding auxiliary door is output when the actual area of the non-sintering material is greater than the set area threshold value for three continuous periods; Visual display module: the blocking position is marked by a high-light red frame in the real-time image, and the auxiliary door number text is explained.

[0006] The parameter setting function of the clearing control module includes setting the maximum value of the auxiliary door opening degree, the maximum value of the opening degree retention time and the upper limit number of the clearing operation; the system alarm setting function is used to send an artificial inspection alarm signal when the clearing operation reaches the upper limit number and the blocking is not removed.

[0007] A control method of the sintering roller material clearing control system based on video analysis, including a roller blocking video analysis method and a roller clearing control method, both of which are executed once per second when the roller is normally running; The roller blocking video analysis method is used to judge the blocking state and the specific position, and output the blocking signal; The roller clearing control method is used to receive the blocking signal, execute the clearing operation and feedback the clearing result.

[0008] The roller blocking video analysis method includes the following steps: S1. Image acquisition: reading the image data of the roller material area shot by the industrial camera; S2. Image preprocessing: sequentially performing RGB to HSV color space conversion, Gaussian filter denoising and histogram equalization contrast enhancement; S3. Image cutting: cutting the preprocessed image horizontally in equal proportions according to the number of auxiliary doors to obtain sub-images Pic[x] corresponding to each auxiliary door, x=1~n, n is the number of auxiliary doors; S4. Feature extraction: the feature extraction of the non-sintering material area of each sub-image Pic[x] is carried out, which specifically includes: S41. Threshold segmentation: setting the brightness threshold Vsp, determining the pixel area of the non-sintering material area in the sub-image as the pixel area of the non-sintering material area whose V value is greater than Vsp; S42. Edge processing: removing noise through morphological operation and enhancing the connectivity of the non-sintering material area; S43. Area correction: converting the pixel area into the actual area (unit: square centimeter) according to the corresponding relationship between the image resolution and the actual physical size; S5. Feature judgment: Set the area threshold HspLsp (Hsp, Lsp are length parameters set), if the actual area of the sub-image Pic[x] without sintered material is greater than HspLsp for three consecutive periods, it is determined that the x auxiliary door exists blockage, and a blockage signal DLx=True is output.

[0009] The following variables are defined in the circular roller unblocking control method: blockage signal DLx, auxiliary door opening feedback value PVx, auxiliary door opening set value Spx, unblocking counter Countx, opening intermediate variable TVx, and unblocking opening upper limit SPmax (preset value).

[0010] The circular roller unblocking control method comprises the following steps: T1. Detect whether the blockage signal DLx of the x auxiliary door is true; T2. If DLx=True, enter the unblocking process: set Spx as SPmax, and assign TVx as the current PVx; T3. Maintain the auxiliary door opening as SPmax for 5 seconds, and confirm that PVx approaches SPmax and remains in this state; T4. After 5 seconds, set Spx as TVx, and wait for PVx to stabilize and approach TVx; T5. Detect the DLx state again: If DLx=False, clear Countx, and end the unblocking process this time; If DLx=True and Countx<=3, Countx is incremented by 1, and return to step T2; If DLx=True and Countx>3, an alarm signal "Repeated unblocking is invalid, please manually check the x auxiliary door" is sent, Countx is cleared, and the unblocking process this time is ended.

[0011] In step S3, the number of auxiliary doors n>=1, and the number of sub-images is consistent with the number of auxiliary doors.

[0012] In step S41, the value range of the brightness threshold Vsp is 0-255, which can be adjusted and set in the video analysis module.

[0013] The beneficial effects of the present application are: the present application proposes a sintering circular roller material unblocking control system and control method based on video analysis. The system uses advanced video analysis technology to automatically and accurately analyze the blockage state and specific position of the circular roller. Once the blockage is detected, the system will automatically control the auxiliary door to release the large block of material according to the obtained blockage information. The present application not only realizes the automation and digitization of the sintering circular roller material operation, but also significantly improves the accuracy of the production operation. At the same time, it greatly improves the working environment of the workers and reduces their working risk in the high temperature, noise and dust environment. BRIEF DESCRIPTION OF DRAWINGS

[0014] Figure 1 The flow chart of the round roller blocking video analysis method of the present application.

[0015] Figure 2 The flow chart of the round roller unblocking control method of the present application.

[0016] Figure 3 The functional structure diagram of the sintering round roller material distribution unblocking control system of the present application. DETAILED DESCRIPTION

[0017] The present application proposes a sintering round roller material distribution unblocking control system and control method based on video analysis.

[0018] The specific control method of the present application: a sintering round roller material distribution unblocking control method based on video analysis, mainly including a round roller blocking video analysis method and a round roller unblocking control method.

[0019] The round roller blocking video analysis method executes an algorithm once per second when the round roller is normally distributing materials, and the flow is as shown in the figure, including image acquisition, image preprocessing, image cutting, feature extraction, and feature judgment. Figure 1

[0020] The image acquisition: reads the image data of the industrial camera as the original input for analysis.

[0021] The image preprocessing: including color space conversion, noise removal processing, and contrast enhancement.

[0022] The color space conversion adopts the RGB to HSV method to convert the image from the RGB color space to the HSV color space, to more robustly handle color changes and facilitate subsequent color threshold segmentation.

[0023] The noise removal processing uses Gaussian Blur to remove noise in the image, reducing the interference of external environmental light changes on the detection result.

[0024] The contrast enhancement uses Histogram Equalization to enhance the contrast of the image, improving the distinction between the material area and the background in the image and strengthening the distinction effect in the low-light environment near the round roller.

[0025] The image cutting refers to cutting the image horizontally according to the auxiliary gate deployment position, and performing feature extraction and feature judgment on the cut images. In this embodiment, the number of auxiliary gates is 7, so the cut image is defined as Pic[x], x=1~7.

[0026] ​The feature extraction refers to feature extraction on the sintering material free area in the cut image Pic[x], and when the large material block is blocked, the circular roller body is exposed at the downstream of the blocked material. The HSV color space is composed of three channels of hue (H), saturation (S) and brightness (V). According to the color features of the sintering material and the color features of the circular roller, the present application needs to distinguish black, white and gray in the HSV color space, and mainly relies on the value of brightness V to obtain the area of the sintering material free area. The specific method is as follows: Threshold segmentation method: when the V value is greater than Vsp, it is considered that the pixel area is free of sintering material distribution, and the pixel area of the sintering material free area can be obtained by calculating the number of pixels with a value greater than Vsp in the binary image. Wherein Vsp can be set in the video analysis module, representing the identification threshold setting value.

[0027] Edge processing: morphological operation is used to remove noise and enhance the connectivity of the sintering material free area, to smooth the image and more accurately identify the white area.

[0028] Corrected area: according to the relationship between the resolution or size of the image and the actual physical size, the calculated pixel area is converted into actual area unit, unit: square centimeter.

[0029] The feature judgment refers to comparing the sintering material free area obtained by Pic[x] with Hsp*Lsp, and when the sintering material free area is greater than Hsp*Lsp for three consecutive periods, it is considered that the x auxiliary door is in a true blocked state.

[0030] The circular roller unblocking control method executes the algorithm once per second when the circular roller is normally running, and the flow is as shown in Figure 2 .

[0031] The following variables are defined: The blocked signal of the x auxiliary door is DLx, the auxiliary door opening feedback value is PVx, the auxiliary door opening set value is Spx, the unblocking counter is Countx, the opening intermediate variable is TVx, and the unblocking opening upper limit is SPmax (preset in the man-machine interface according to the debugging experience).

[0032] The specific control flow is as follows: 1. Determine whether the x auxiliary door is in a blocked state, that is, check whether DLx is true.

[0033] 2. If the x auxiliary door is in a blocked state, enter the unblocking flow: A. Set Spx as SPmax to maximize the auxiliary door opening; B. Set TVx as the current PVx, that is, save the current actual opening of the auxiliary door.

[0034] 3, After the auxiliary door opens to the maximum set value, keep this state for 5 seconds to ensure that the bulk material is released. That is, confirm that PVx is close to SPmax and maintain for 5 seconds.

[0035] 4, 5 seconds later, restore the auxiliary door opening to the state before clearing the blockage: A. Set Spx to TVx, which is the intermediate value of the previous opening; B. Wait for PVx to stabilize and approach the new Spx value.

[0036] 5, Continue to monitor the state of the x auxiliary door: If the blockage state still exists (DLx is true) and the clearing operation has not exceeded three times (Countx is not greater than 3), then Countx is incremented by 1, and the control flow of steps 2 to 4 is repeated.

[0037] 6, If the blockage state disappears (DLx is false) during the monitoring process in step 5, then: A. Clear Countx; B. End this control flow.

[0038] 7, If the clearing counter exceeds 3 times (Countx is greater than 3) and the blockage state continues to exist (DLx is true) during the monitoring process in step 5, then: A. Issue a system alarm with the content "Repeated clearing is ineffective, please manually check the x auxiliary door"; B. Clear Countx; C. End this control flow.

[0039] In addition, at any time, if the blockage state of the x auxiliary door disappears (DLx is false), the possible alarm is removed and the control flow is ended.

[0040] The present application also proposes a sintering round roller material clearing control system based on video analysis, which has the structure as shown in Figure 3 The system mainly includes three core modules: data acquisition module, video analysis module and clearing control module.

[0041] The data acquisition module is responsible for two tasks: one is to collect image data through an industrial camera; the other is to use the OPC UA protocol to communicate with the PLC (Programmable Logic Controller) to realize real-time acquisition and control of round roller and valve related data.

[0042] The video analysis module has a real-time image display function. It can accurately determine whether there is a blockage and determine the specific location of the blockage by cutting and identifying the collected images. In order to visually display the blockage location, the module will mark the location by a high-light red frame in the real-time picture and attach a text description indicating the corresponding auxiliary gate number of the blockage location. At the same time, the module provides a setting value (Vsp, 0~255) of the brightness V and a setting value (Hsp, Lsp in centimeters) of the length and width of the identified area.

[0043] The blockage clearing control module executes the blockage clearing control operation based on the information provided by the video analysis module and allows the user to set parameters and system alarm settings. The parameter setting part covers key parameters such as the maximum value of the auxiliary gate opening, the time length of maintaining the maximum value, and the upper limit number of blockage clearing operations.

[0044] It is worth noting that the present application has high flexibility and adaptability, and can make various reasonable adjustments and optimizations according to different field conditions. Therefore, any form of modification, equivalent replacement or improvement based on the technical features of the present application should be considered within the protection scope of the present application.

[0045] The above is only the preferred specific implementation of the present application, but the protection scope of the present application is not limited to this. Any person skilled in the art can make equivalent replacement or change within the technical range disclosed in the present application according to the technical solution and concept of the present application, which should be covered within the protection scope of the present application.

Claims

1. A sintering roller material distribution blockage control system based on video analysis, characterized by, It comprises a data acquisition module, a video analysis module and a blockage control module, and the modules are sequentially connected in signal; The data acquisition module is used for acquiring image data of the circular roller material distribution area, and performing data communication with the PLC through the OPC UA protocol, so as to realize real-time acquisition and control of the circular roller and related data of the auxiliary door; The video analysis module is used for processing and analyzing the acquired image data, judging whether there is blockage and the specific position of the blockage, and outputting a blockage signal; The blockage control module is used for receiving the blockage signal output by the video analysis module, executing corresponding blockage control operation, and supporting user parameter setting and system alarm setting.

2. The video analysis-based sintering roller material distribution blockage control system according to claim 1, characterized in that, The data acquisition module comprises an industrial camera, which is used for real-time shooting of the circular roller material distribution area, acquisition of original image data and transmission to the video analysis module.

3. The video analysis-based sintering roller material distribution clogging control system according to claim 1, characterized by, The video analysis module comprises the following modules: An image preprocessing module: RGB to HSV color space conversion, Gaussian filter denoising and histogram equalization contrast enhancement processing are sequentially performed on the original image; An image cutting module: the preprocessed image is cut horizontally in equal proportions according to the auxiliary door deployment position, and a sub-image corresponding to each auxiliary door is obtained; A feature extraction module: the feature of the non-sintered material area of each sub-image is extracted, the actual area of the non-sintered material is obtained through HSV color space brightness V threshold segmentation, morphological edge processing and area correction; A feature judgment module: the actual area of the non-sintered material is compared with the set area threshold value, and when the actual area is greater than the set area threshold value for three consecutive periods, a blockage signal of the corresponding auxiliary door is output; A visual display module: the blockage position is marked by a high-light red frame in the real-time image, and the auxiliary door number is explained by text.

4. The video analysis-based sintering roller material distribution clogging control system according to claim 1, characterized by, The parameter setting function of the blockage control module includes setting the maximum opening degree of the auxiliary door, the maximum opening degree retention time and the upper limit number of blockage operation; the system alarm setting function is used to send a manual inspection alarm signal when the blockage operation reaches the upper limit number but the blockage is not removed.

5. A control method of a clogging control system of a sintering roller based on video analysis according to any one of claims 1 to 4, characterized in that, It comprises a circular roller blockage video analysis method and a circular roller blockage control method, both of which are executed once per second when the circular roller is normally running; The circular roller blockage video analysis method is used for judging the blockage state and the specific position, and outputting a blockage signal; The circular roller blockage control method is used for receiving the blockage signal, executing the blockage operation and feeding back the blockage result.

6. The control method of the sinter roller burn-off control system based on video analysis according to claim 5, characterized in that, The circular roller blockage video analysis method comprises the following steps: S1. Image acquisition: reading the image data of the circular roller material distribution area shot by the industrial camera; S2. Image preprocessing: sequentially performing RGB to HSV color space conversion, Gaussian filter denoising and histogram equalization contrast enhancement; S3. Image cutting: cutting the preprocessed image horizontally in equal proportions according to the number of auxiliary doors, and obtaining a sub-image Pic[x] corresponding to each auxiliary door, x=1~n, n being the number of auxiliary doors; S4. Feature extraction: extracting the feature of the non-sintered material area of each sub-image Pic[x], specifically including: S41. Threshold segmentation: setting a brightness threshold Vsp, judging the pixel area with a V value greater than Vsp in the sub-image as a non-sintered material area, and calculating the pixel area of the area; S42. Edge processing: remove noise by morphological operation, enhance the connectivity of non-sintered material area; S43. Area correction: convert pixel area to actual area (unit: square centimeter) according to the corresponding relationship between image resolution and actual physical size; S5. Feature judgment: set area threshold HspLsp (Hsp, Lsp are length parameters set), if the actual area of non-sintered material of sub-image Pic[x] is greater than HspLsp for three consecutive periods, it is judged that x number of auxiliary door exists blockage, output blockage signal DLx=True.

7. The control method of the sinter roller burn-off control system based on video analysis according to claim 5, characterized by, The following variables are defined in the round roller unblocking control method: blockage signal DLx, auxiliary door opening feedback value PVx, auxiliary door opening set value Spx, unblocking counter Countx, opening intermediate variable TVx, and unblocking opening upper limit SPmax (preset value).

8. The control method of the sinter roller burn-off control system based on video analysis according to claim 7, characterized by, The round roller unblocking control method comprises the following steps: T1. Detect whether the blockage signal DLx of the x number of auxiliary door is true; T2. If DLx=True, enter the unblocking process: set Spx to SPmax, and assign TVx to the current PVx; T3. Maintain the auxiliary door opening at SPmax for 5 seconds, and confirm that PVx approaches SPmax and remains in this state; T4. After 5 seconds, set Spx to TVx, and wait for PVx to stabilize and approach TVx; T5. Detect the DLx state again: If DLx=False, clear Countx, and end the unblocking process this time; If DLx=True and Countx≤3, Countx is incremented by 1, and return to step T2; If DLx=True and Countx>3, an alarm signal "Repeated unblocking is invalid, please manually check the x number of auxiliary door" is issued, Countx is cleared, and the unblocking process this time is ended. 9.The control method of the sintering roller clogging control system based on video analysis according to claim 6, wherein, The number of auxiliary doors n in step S3 is greater than or equal to 1, and the number of sub-images is consistent with the number of auxiliary doors.

10. The control method of the sinter roller burn-off control system based on video analysis according to claim 6, wherein, The value of the brightness threshold Vsp in step S41 ranges from 0 to 255, which can be adjusted and set in the video analysis module.

Images