Method, device and system for monitoring personnel in dangerous area in converter smelting process

Abstract

The invention provides a dangerous area personnel monitoring method, device and system in the converter smelting process, and relates to the technical field of steel smelting. Comprising the steps that a to-be-processed picture is obtained, and the to-be-processed picture is a real-time monitoring picture for a converter platform; frame labeling processing is conducted on the to-be-processed picture through a trained first processing model, first intermediate information is obtained, the first intermediate information is three-dimensional data information, and the content of the first intermediate information is the to-be-processed picture containing a labeling frame; adding personnel coordinates in the first intermediate information through a trained second processing model to obtain second intermediate information; on the basis of the second intermediate information, whether the personnel coordinates are located in the range of the labeling box or not is judged through a trained first processing model; if the personnel coordinates are located in the marking frame, determining that personnel exist in the dangerous area in the converter platform; and if the personnel coordinates are not located in the labeling box, determining that no personnel exist in the dangerous area.

Description

Technical Field

[0001] The present application relates to the technical field of steel smelting, and in particular to a method, device and system for monitoring personnel in dangerous areas during converter smelting. Background Art

[0002] The converter is an important equipment used in steel smelting. The oxygen lance top blowing technology is used to improve the quality of molten steel. In order to ensure the safe operation of the converter platform, it is necessary to monitor the personnel passing through the converter platform during the converter smelting process to achieve the purpose of control.

[0003] In the related technology, the steel workers working on the platform mainly use their eyes to observe manually to determine whether anyone has entered the smelting area. However, due to the high temperature, high dust and strong noise interference in the working environment of the converter platform, the traditional manual inspection method cannot accurately control the smelting status information in the dangerous area, which seriously affects the safe operation of the converter platform. Summary of the invention

[0004] The present application provides a method, device and system for monitoring personnel in dangerous areas during a converter smelting process, which are used to solve the problem in the related art that the accuracy of manual monitoring of the converter platform is low, which affects the safe operation of the converter platform.

[0005] In a first aspect, the present application provides a method for monitoring personnel in a dangerous area during a converter smelting process, comprising:

[0006] Obtaining a picture to be processed, wherein the picture to be processed is a real-time monitoring picture for a converter platform;

[0007] Performing frame annotation processing on the to-be-processed picture by using the trained first processing model to obtain first intermediate information, where the first intermediate information is three-dimensional data information, and the content of the first intermediate information is the to-be-processed picture including the annotation frame;

[0008] Adding the coordinates of the person to the first intermediate information through the trained second processing model to obtain second intermediate information;

[0009] Based on the second intermediate information, judging whether the coordinates of the person are within the range of the annotation box by using the trained first processing model;

[0010] If the personnel coordinates are within the marked frame, it is determined that there is a person in the dangerous area of ​​the converter platform;

[0011] If the coordinates of the person are not located in the marking box, it is determined that there is no person in the dangerous area.

[0012] In a second aspect, the present application also provides a personnel monitoring device in a dangerous area during a converter smelting process, comprising:

[0013] An acquisition module is used to acquire a to-be-processed screen, wherein the to-be-processed screen is a real-time monitoring screen of a dangerous area in a converter smelting process;

[0014] A first processing module is used to perform frame annotation processing on the to-be-processed picture by using a trained first processing model to obtain first intermediate information, where the first intermediate information is three-dimensional data information, and the content of the first intermediate information is the to-be-processed picture including the annotation frame;

[0015] A second processing module, configured to add the coordinates of the person to the first intermediate information by using a trained second processing model to obtain second intermediate information;

[0016] The first processing module is further used to determine whether the coordinates of the person are within the range of the annotation box based on the second intermediate information through the trained first processing model;

[0017] The determination module is used to determine that there is a person in the dangerous area of ​​the converter platform if the person coordinates are located in the marked box; if the person coordinates are not located in the marked box, determine that there is no person in the dangerous area.

[0018] In the third aspect, the present application also provides a personnel monitoring system in a dangerous area during a converter smelting process, comprising the device as described in the second aspect, a camera device, an alarm device, a laser projection device and an anti-splash retaining wall, wherein the camera device and the laser projection device are installed at the edge of the converter platform, facing the position of the converter, and the alarm device and the anti-splash retaining wall are installed at the entrance of the converter platform.

[0019] In a fourth aspect, the present application further provides an electronic device, including:

[0020] processor;

[0021] a memory for storing processor-executable instructions;

[0022] The processor is configured to execute instructions to implement the method provided in the first aspect of the present application.

[0023] In a fifth aspect, the present application also provides a storage medium, which, when the instructions in the storage medium are executed by a processor of an electronic device, enables the electronic device to execute the method provided in the first aspect of the present application.

[0024] In a sixth aspect, the present application also provides a computer program product, including a computer program, which, when executed by a processor, performs the method provided in the first aspect of the present application.

[0025] The present application provides a method for monitoring personnel in dangerous areas during converter smelting, specifically, obtaining a to-be-processed screen, the to-be-processed screen is a real-time monitoring screen for a converter platform; performing frame annotation processing on the to-be-processed screen through a trained first processing model to obtain first intermediate information, the first intermediate information is three-dimensional data information, and the content of the first intermediate information is a to-be-processed screen containing an annotation frame; adding personnel coordinates to the first intermediate information through a trained second processing model to obtain second intermediate information; based on the second intermediate information, judging whether the personnel coordinates are within the range of the annotation frame through the trained first processing model; if the personnel coordinates are within the annotation frame, it is determined that there are personnel in the dangerous area of ​​the converter platform; if the personnel coordinates are not within the annotation frame, it is determined that there are no personnel in the dangerous area. In this way, the trained first processing model and the trained second processing model jointly analyze and process the to-be-processed screen, and monitor the converter platform by judging whether the personnel coordinates are within the range of the annotation frame, so that the personnel control in the converter platform is more accurate, and the safe operation of the converter platform is guaranteed, which solves the problem of low accuracy in manually monitoring the converter platform in the related art, which affects the safe operation of the converter platform to a certain extent. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, a brief introduction will be given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0027] Figure 1 A flow chart of a method for monitoring personnel in a dangerous area during a converter smelting process provided in an embodiment of the present application;

[0028] Figure 2 A structural block diagram of a personnel monitoring device in a dangerous area during a converter smelting process provided in an embodiment of the present application;

[0029] Figure 3 A conceptual diagram of a personnel monitoring system in a dangerous area during a converter smelting process provided in an embodiment of the present application;

[0030] Figure 4 A structural block diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0031] Hereinafter, embodiments of the present disclosure will be described with reference to the accompanying drawings, but it should be understood that these descriptions are only exemplary and are not intended to limit the scope of the present disclosure.

[0032] As described in the background technology, the converter is an important equipment used for steel smelting, and the quality of molten steel is improved by oxygen lance top blowing technology. In order to ensure the safe operation of the converter platform, during the converter smelting process, it is necessary to monitor the personnel passing through the converter platform to achieve the purpose of control. In the related technology, it is mainly the steel workers working on the platform who use their eyes to observe manually to determine whether anyone has entered the smelting area. However, due to the high temperature, high dust and strong noise interference of the working environment of the converter platform, the traditional manual inspection method cannot accurately control the smelting status information in the dangerous area, which seriously affects the safe operation of the converter platform.

[0033] In this regard, the present application provides a method for monitoring personnel in dangerous areas during a converter smelting process. Specifically, a to-be-processed picture is obtained, and the to-be-processed picture is a real-time monitoring picture for a converter platform; a frame annotation process is performed on the to-be-processed picture through a trained first processing model to obtain first intermediate information, and the first intermediate information is three-dimensional data information, and the content of the first intermediate information is the to-be-processed picture including a annotation frame; personnel coordinates are added to the first intermediate information through a trained second processing model to obtain second intermediate information; based on the second intermediate information, whether the personnel coordinates are within the range of the annotation frame is determined through the trained first processing model; if the personnel coordinates are within the annotation frame, it is determined that there are personnel in the dangerous area of ​​the converter platform; if the personnel coordinates are not within the annotation frame, it is determined that there are no personnel in the dangerous area. In this way, the trained first processing model and the trained second processing model jointly analyze and process the image to be processed, and monitor the converter platform by judging whether the coordinates of the personnel are within the range of the marked box, so that the personnel control in the converter platform is more accurate, thereby ensuring the safe operation of the converter platform. To a certain extent, it solves the problem in related technologies that the accuracy of manual monitoring of the converter platform is low, which affects the safe operation of the converter platform.

[0034] In addition, in the related art, in the process of manually monitoring the converter platform, not only is the accuracy low, but there is also a certain delay, and it is impossible to monitor in real time and stably. The method for monitoring personnel in dangerous areas during converter smelting provided in the embodiment of the present application processes the real-time monitoring screen through the trained first processing model and the trained second processing model to determine whether there are personnel in the dangerous area of ​​the converter platform, which can not only realize real-time monitoring of the converter platform, but also has a certain stability.

[0035] It should be understood that the method for monitoring personnel in dangerous areas during converter smelting provided in the embodiment of the present application can be executed by a target device. The target device can be one electronic device or multiple electronic devices that cooperate with each other to execute. The electronic device can be a server, such as an independent physical server, a server cluster composed of multiple servers, and a cloud server capable of cloud computing.

[0036] The following is a detailed description of the technical solution of the present application and how the technical solution of the present application solves the above-mentioned technical problems with specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below in conjunction with the accompanying drawings.

[0037] Figure 1 A flowchart of a method for monitoring personnel in a dangerous area during a converter smelting process provided in an embodiment of the present application. Figure 1 As shown, the method for monitoring personnel in dangerous areas during converter smelting provided in the embodiment of the present application includes the following steps:

[0038] Step 110, obtaining a picture to be processed, wherein the picture to be processed is a real-time monitoring picture of the converter platform.

[0039] In the embodiment of the present application, during the converter smelting process, a certain range of area in front of the converter is usually regarded as the converter platform, for example, a rectangular area of ​​a certain length and width in front of the converter is the converter platform, or a circular area centered on the converter is the converter platform, and the embodiment of the present application does not impose specific restrictions on this. Accordingly, the image content of the to-be-processed image is the converter, the image range can be the entire monitoring range, or a key range can be preset in advance, and the image content of the to-be-processed image can be the key range in the monitoring image.

[0040] In the embodiment of the present application, the target device can be a processor with a built-in camera, which obtains the image to be processed by shooting, and can also obtain the image to be processed by receiving transmissions from a third-party monitoring device. For example, a high-temperature resistant camera is installed above the converter, and the target device obtains the image to be processed by receiving the image captured by the camera. The embodiment of the present application does not impose any specific restrictions on this.

[0041] After receiving the screen to be processed, the target device can execute the following steps to process the screen to be processed and complete real-time personnel monitoring in dangerous areas during the converter smelting process.

[0042] Step 120 , performing frame annotation processing on the to-be-processed picture through the trained first processing model to obtain first intermediate information, wherein the first intermediate information is three-dimensional data information, and the content of the first intermediate information is the to-be-processed picture including the annotation frame.

[0043] In an embodiment of the present application, the trained first processing model can be a traditional computer vision (CV) model. Before the frame is marked for the image to be processed by the trained first processing model, the image to be processed can also be pre-processed, including basic processing such as brightness adjustment, contrast enhancement, and denoising, so as to improve the image quality of the image to be processed.

[0044] After the trained first processing model performs image preprocessing on the image to be processed, the key areas in the image to be processed can be marked, for example, a rectangle is marked with the converter as the midpoint of the long side of the rectangle, and the rectangle is the marking frame. In addition, in order to facilitate subsequent processing, the image to be processed with the marking frame is also converted in the trained first processing model, the image data is converted into three-dimensional data, and finally the first intermediate information is output.

[0045] After obtaining the first intermediate information, the target device may execute step 130 to process the first intermediate information.

[0046] Step 130: Add the coordinates of the person to the first intermediate information through the trained second processing model to obtain the second intermediate information.

[0047] In an embodiment of the present application, the trained second processing model may be a Convolutional Neural Networks (CNN) model. After the trained first processing model has completed processing, the first intermediate information may be input into the trained second processing model, and the trained second processing model may perform recognition processing on the first intermediate information to identify whether the first intermediate information contains three-dimensional data information of a person. If the first intermediate information contains image data information of a person, the person information may be further recognized to determine the coordinate information corresponding to the person, and the first intermediate information containing the coordinate information of the person may be output as the second intermediate information. If the trained second processing model fails to recognize the three-dimensional data information of a person after performing recognition processing on the first intermediate information, the first intermediate information may be used as the second intermediate information.

[0048] In the embodiment of the present application, after the trained second processing model outputs the second intermediate information, step 140 may be executed to perform further processing through the trained first processing model.

[0049] Step 140: Based on the second intermediate information, determine whether the coordinates of the person are within the range of the annotation box through the trained first processing model.

[0050] In an embodiment of the present application, the second intermediate information includes a marking box and personnel coordinates, which can be judged by the trained first processing model to determine whether there are personnel coordinates within the range of the marking box, that is, to determine whether there are personnel in the dangerous area of ​​the converter platform.

[0051] Step 150: If the personnel coordinates are located within the marked frame, it is determined that there is a person in the dangerous area of ​​the converter platform.

[0052] In the embodiment of the present application, if the coordinates of the personnel are within the range of the marked box, it means that there are personnel in the dangerous area of ​​the converter platform, and a prompt can be given, such as sounding an alarm.

[0053] Step 160: If the coordinates of the person are not located in the marked box, it is determined that there is no person in the dangerous area.

[0054] In the embodiment of the present application, if the coordinates of the personnel are not within the range of the marking box, it is determined that there is no personnel in the danger zone, and no processing is required, and the converter platform continues to be monitored.

[0055] In this way, the trained first processing model and the trained second processing model jointly analyze and process the image to be processed, and monitor the converter platform by judging whether the coordinates of the personnel are within the range of the marked box, so that the personnel control in the converter platform is more accurate, thereby ensuring the safe operation of the converter platform. To a certain extent, it solves the problem in related technologies that the accuracy of manual monitoring of the converter platform is low, which affects the safe operation of the converter platform.

[0056] In step 120 provided in the embodiment of the present application, a specific implementation method may be: performing image preprocessing on the picture to be processed through a trained first processing model to obtain a first intermediate picture; performing frame labeling processing on the first intermediate picture through a first algorithm in the trained first processing model to obtain a second intermediate picture; and converting the second intermediate picture into first intermediate information through the trained first processing model.

[0057] In an embodiment of the present application, the image to be processed can be input into a trained traditional CV model, and the image preprocessing can be performed by the trained traditional CV model, such as adjusting the brightness of the image to be processed, enhancing contrast, denoising and other basic image preprocessing to improve image quality and provide clearer image data (i.e., the first intermediate image) for subsequent image recognition. After obtaining the first intermediate image, the preprocessed image can be preliminarily analyzed by a first algorithm, including dangerous area edge detection, morphological operations (such as expansion, corrosion), etc., to highlight key features in the image, such as people, and use brightness detection to identify dangerous areas in the image, which are usually related to people, to obtain a second intermediate image containing a marked box, and the first algorithm can be any algorithm that can frame a region of interest (ROI), such as a custom ROI box algorithm, or a RoI pooling algorithm, etc. The second intermediate image in the form of a picture is then converted into the first intermediate information in the form of three-dimensional data.

[0058] In addition, the method provided in the embodiment of the present application can also be applied to vehicle monitoring in dangerous areas during converter smelting. For example, in step 120 provided in the embodiment of the present application, the vehicle information on the processing screen can be analyzed by the trained first processing model.

[0059] In the embodiment of the present application, during the process of frame marking using the first algorithm, the dangerous areas on the converter platform can be manually point marked in advance so that the first algorithm can perform frame marking more accurately.

[0060] In step 130 provided in the embodiment of the present application, a specific implementation method may be: performing convolution processing on the first intermediate information through a trained second processing model to identify the coordinate information of the person in the first intermediate information; and using the first intermediate information including the coordinate information as the second intermediate information.

[0061] In an embodiment of the present application, convolution processing can be performed through a deep learning model of a trained convolutional neural network (CNN) to identify specific smelting personnel and vehicles in the first intermediate information, such as people and vehicles entering.

[0062] In step 140 provided in the embodiment of the present application, a specific implementation method may be: based on the second intermediate information, a judgment is made through the second algorithm in the trained first processing model to determine whether the coordinates of the person are within the range of the marking box; the second intermediate information is converted into a result image, and the result image is output.

[0063] In an embodiment of the present application, the second algorithm may also be a customized algorithm for determining whether the coordinates of the person are within the range of the annotation box. After the determination, the second intermediate information of the three-dimensional data mode may be converted into a result image of the image mode through the trained traditional CV model and output. In an embodiment of the present application, after the trained traditional CV model outputs the result image, the target device may provide a control system page feedback to the operator for viewing.

[0064] In step 150 provided in the embodiment of the present application, a specific implementation method may be: obtaining the screen status of the converter smelting in the screen to be processed; if the screen status indicates that the converter smelting process is in one of the situations of smelting, iron addition and scrap steel addition, and the personnel coordinates are within the range of the marking box, it is determined that there are personnel in the dangerous area in the converter platform.

[0065] In an embodiment of the present application, the target device can obtain the screen status of the converter smelting in the to-be-processed screen by receiving the transmission of a third-party device, for example, by adding another signal device near the converter to monitor the process status of the converter, and using the real-time process status of the converter as the screen status of the to-be-processed screen. In addition, the target device can also analyze the screen content of the to-be-processed screen through the trained first processing model and / or the trained second processing model to obtain the process status of the converter. When the converter smelting process is in any of the situations of smelting, iron addition, and scrap steel addition, and the personnel coordinates are within the range of the marked box, it is determined that there are personnel in the dangerous area in the converter platform.

[0066] In the embodiment of the present application, after determining that there are people in the dangerous area of ​​the converter platform, a warning prompt can be given. For example, a safety sound and light alarm is installed at the entrance of the converter platform, and the alarm is connected to the target device with a signal line. When the converter smelting process is in any of the situations of smelting, adding iron, and adding scrap steel, a first-level prompt can be given. When it is further determined that there are people in the dangerous area of ​​the converter platform, a second-level prompt can be given.

[0067] In addition, in order to further prompt the alarm, in the embodiment of the present application, a laser projection device can be used to install a laser projection device at a suitable position on the converter platform, with a fan-shaped angle of 120 degrees extending to the front of the platform with the furnace mouth injection angle as the center, and the 120-degree range is covered by laser projection; the laser projection device is connected to the converter smelting control screen program with a cable, and when the smelting screen status is (smelting, iron addition and scrap steel addition), a signal is triggered, the laser projection emits red and a warning prompt language is displayed on the ground.

[0068] In order to further improve personnel monitoring of dangerous areas in the converter smelting process, in an embodiment of the present application, the range of laser projection can also be set to the range of the marking box in step 120, and the embodiment of the present application does not impose specific restrictions on this.

[0069] In an embodiment of the present application, the target device can also provide real-time data recording and backtracking analysis to provide data support for smelting process optimization.

[0070] In the embodiment of the present application, both the first processing model and the second processing model are trained, and the first processing model is pre-constructed by the following steps: obtaining first training data, the first training data being a historical monitoring screen including annotated points; training the first original model by the first training data to obtain the first processing model. The annotated points can be preset manually in advance so that the first original model can better perform frame annotation and preliminary analysis of the image.

[0071] In an embodiment of the present application, the second processing model is pre-constructed through the following steps: obtaining second training data, where the second training data is a historical monitoring screen including a marked box; and training the second original model through the second training data to obtain a second processing model.

[0072] Figure 2 This is a structural block diagram of a device for monitoring personnel in dangerous areas during converter smelting provided by an embodiment of the present application. Figure 2 As shown, the device 200 for monitoring personnel in a dangerous area during converter smelting provided in an embodiment of the present application includes: an acquisition module 210 , a first processing module 220 , a second processing module 230 and a determination module 240 .

[0073] An acquisition module 210 is used to acquire a to-be-processed screen, wherein the to-be-processed screen is a real-time monitoring screen of a dangerous area in a converter smelting process;

[0074] A first processing module 220 is used to perform frame annotation processing on the to-be-processed picture by using a trained first processing model to obtain first intermediate information, where the first intermediate information is three-dimensional data information, and the content of the first intermediate information is the to-be-processed picture including the annotation frame;

[0075] A second processing module 230 is used to add the coordinates of the person to the first intermediate information through the trained second processing model to obtain second intermediate information;

[0076] The first processing module 220 is further configured to determine whether the coordinates of the person are within the range of the annotation box based on the second intermediate information by using the trained first processing model;

[0077] The determination module 240 is used to determine that there is a person in the dangerous area of ​​the converter platform if the person coordinates are located in the marked box; if the person coordinates are not located in the marked box, determine that there is no person in the dangerous area.

[0078] It should be noted that the embodiment of the device for monitoring personnel in hazardous areas during converter smelting in this specification and the embodiment of the method for monitoring personnel in hazardous areas during converter smelting in this specification are based on the same inventive concept. Therefore, the specific implementation method of this embodiment can refer to the corresponding embodiment of the method for monitoring personnel in hazardous areas during converter smelting in the previous text, and the repeated parts will not be repeated.

[0079] In addition, an embodiment of the present application also provides a personnel monitoring system in a dangerous area during a converter smelting process, wherein the system includes the personnel monitoring device in a dangerous area during a converter smelting process, a camera device, an alarm device, a laser projection device, and an anti-splash retaining wall as described above, wherein the camera device and the laser projection device are installed at the edge of the converter platform, directly opposite to the position of the converter, and the alarm device and the anti-splash retaining wall are installed at the entrance of the converter platform.

[0080] In order to better understand the method and system for monitoring personnel in dangerous areas during the converter smelting process provided in the embodiments of the present application, examples are now given. It should be understood that the examples are not limitations. Figure 3 A conceptual diagram of a personnel monitoring system in a dangerous area during a converter smelting process provided in an embodiment of the present application, such as Figure 3 As shown, in the embodiment of the present application, a certain area in front of the converter is a converter platform, and platform entrances are respectively arranged on both sides of the converter platform, and sound and light alarm prompt devices and splash-proof retaining walls are installed at the entrances to provide alarm prompts to avoid harm to personnel. A high-definition camera and a laser projection device are installed at the midpoint of the converter platform away from the converter side to collect images (i.e., images to be processed) and provide laser prompts.

[0081] To better understand Figure 3 The monitoring system shown is now further exemplified. The method for monitoring personnel in dangerous areas during converter smelting provided in the embodiment of the present application can be implemented by the following steps:

[0082] Step 1: System Configuration

[0083] Install high-performance, high-temperature resistant cameras above the converter platform or at a suitable location to ensure full coverage of the monitoring area.

[0084] The camera is connected to the image processing unit via a high-temperature and durable cable. The image processing unit is equipped with high-performance computing resources to support high-speed image data processing and deep learning model operations.

[0085] Step 2: Image acquisition and preprocessing

[0086] The camera collects image data inside the converter's hazardous area in real time and transmits it to the image processing unit (on the target device).

[0087] The image processing unit first preprocesses the acquired image, including brightness adjustment, contrast enhancement, denoising and other steps to improve the image quality and provide clearer input data for subsequent image recognition.

[0088] Step 3: Traditional CV technology processing

[0089] After the converter triggers the detection signal, it sends the detection signal to the technical processor, and uses traditional CV technology to perform preliminary analysis on the preprocessed image, including dangerous area edge detection, morphological operations (such as dilation and corrosion), etc., to highlight the key features in the image, such as people and vehicle movement.

[0090] Brightness detection is used to identify dangerous areas in the image, which are usually related to people or vehicles.

[0091] Step 4: Deep learning model application

[0092] A deep learning model based on a convolutional neural network (CNN) was trained to identify specific smelting personnel and vehicles in images, such as people and vehicles entering.

[0093] The CNN model is trained using a large number of labeled images of smelting hazardous areas on the converter platform to learn the relationship between the complex features in the images and the smelting hazardous areas.

[0094] Combining the image features processed by traditional CV technology and the deep features of the CNN model, the fusion algorithm is used to reduce false detection and improve the accuracy and reliability of monitoring.

[0095] Step 5: Real-time monitoring and feedback

[0096] The image processing unit determines the smelting status of the dangerous area of ​​the converter platform in real time based on the analysis results of the CNN model and traditional CV technology, and feeds back to the operator through the control system interface.

[0097] The system interface sends an alarm message to the operation interface through feedback signals, prompting the operator that someone has entered the dangerous area during the smelting, iron and scrap steel mixing operations.

[0098] Step 6: Alarm Device

[0099] The safety sound and light alarm reminder at the converter entrance is connected with the converter smelting screen status (smelting, iron addition and scrap steel addition) by a signal line. The above three states trigger alarm prompt information.

[0100] Step 7: Laser Projection Device

[0101] Install the laser projection equipment at the appropriate position of the converter platform, extend a 120-degree fan-shaped angle to the front of the platform with the furnace mouth injection angle as the center, and cover the 120-degree range with laser projection.

[0102] Use a cable to connect the laser projection device to the converter smelting control screen program. When the smelting screen status is (smelting, iron addition and scrap steel addition), the signal is triggered, the laser projection emits red and a warning prompt language is displayed on the ground.

[0103] Step 8: Splashback

[0104] A splash-proof retaining wall is built with refractory materials at the end of the passage leading to the converter platform to prevent molten metal from splashing into the passage and causing harm to personnel on duty during converter smelting, iron mixing, and adding scrap steel.

[0105] The system supports real-time data recording and retrospective analysis, providing data support for smelting process optimization.

[0106] The embodiment of the present application collects whether there are people entering during smelting, adding scrap steel, and adding iron by installing a durable high-temperature camera within 120 degrees of the splashing of the converter platform furnace mouth, applies deep learning technology to analyze the image, issues an alarm prompt and records the people entering during the smelting cycle, thereby achieving precise control of the personnel in the dangerous area of ​​smelting on the converter platform. Specifically, the embodiment of the present application combines the traditional computer vision (CV) technology and the deep learning model of the converter smelting dangerous area smelting personnel and vehicle status method. The method collects images of the dangerous area by installing a high-performance camera in the dangerous area of ​​the converter platform, and uses the convolutional neural network (CNN) model and the traditional CV technology to jointly analyze and process the image data, so as to achieve accurate and real-time monitoring of the status of smelting personnel and vehicles in the dangerous area of ​​the converter platform.

[0107] Figure 4 This is a structural block diagram of an electronic device provided in an embodiment of the present application. Figure 4 As shown, the electronic device provided in the embodiment of the present application includes a processor 410 and a memory 420, wherein the memory is used to store instructions executable by the processor; wherein the processor is configured to execute the instructions to implement as shown in Figure 1 The method of personnel monitoring in hazardous areas during converter smelting process is shown.

[0108] In an exemplary embodiment, the electronic device may be implemented by one or more application specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors or other electronic components to perform the above methods.

[0109] In an exemplary embodiment, a non-transitory computer-readable storage medium including instructions is also provided, such as a memory including instructions, and the instructions can be executed by a processor of the device to complete the above method. For example, the non-transitory computer-readable storage medium can be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, and an optical data storage device. The non-transitory computer-readable storage medium, when the instructions in the storage medium are executed by the processor of the electronic device, enables the electronic device to perform the above method. Figure 1 The method of personnel monitoring in hazardous areas during converter smelting process is shown.

[0110] The present application also provides a computer program product, including a computer program, which, when executed by a processor, Figure 1 The method of personnel monitoring in hazardous areas during converter smelting process is shown.

[0111] In the above description, the technical details such as the patterning of each layer are not described in detail. However, those skilled in the art should understand that various technical means can be used to form layers, regions, etc. of desired shapes. In addition, in order to form the same structure, those skilled in the art can also design methods that are not completely the same as the methods described above. In addition, although the various embodiments are described above separately, this does not mean that the measures in the various embodiments cannot be used in combination to advantage.

[0112] Although the preferred embodiments of the present application have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications falling within the scope of the present application.

[0113] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

Claims

1. A method for monitoring personnel in dangerous areas during converter smelting, characterized in that: include: Obtaining a picture to be processed, wherein the picture to be processed is a real-time monitoring picture for a converter platform; Performing frame annotation processing on the to-be-processed picture by using the trained first processing model to obtain first intermediate information, where the first intermediate information is three-dimensional data information, and the content of the first intermediate information is the to-be-processed picture including the annotation frame; Adding the coordinates of the person to the first intermediate information through the trained second processing model to obtain second intermediate information; Based on the second intermediate information, judging whether the coordinates of the person are within the range of the annotation box by using the trained first processing model; If the personnel coordinates are within the marked frame, it is determined that there is a person in the dangerous area of ​​the converter platform; If the coordinates of the person are not located in the marking box, it is determined that there is no person in the dangerous area.

2. The method according to claim 1, characterized in that The step of performing frame labeling processing on the to-be-processed picture by using the trained first processing model to obtain first intermediate information includes: Performing image preprocessing on the to-be-processed image by using the trained first processing model to obtain a first intermediate image; Performing frame labeling processing on the first intermediate picture by using the first algorithm in the trained first processing model to obtain a second intermediate picture; The second intermediate picture is converted into first intermediate information by using the trained first processing model.

3. The method according to claim 1, characterized in that The adding the coordinates of the person to the first intermediate information by using the trained second processing model to obtain the second intermediate information includes: Performing convolution processing on the first intermediate information through the trained second processing model to identify coordinate information of the person in the first intermediate information; The first intermediate information including the coordinate information is used as the second intermediate information.

4. The method according to claim 1, characterized in that: The determining, based on the second intermediate information, whether the coordinates of the person are within the range of the annotation box by using the trained first processing model includes: Based on the second intermediate information, judging by the second algorithm in the trained first processing model whether the coordinates of the person are within the range of the annotation box; The second intermediate information is converted into a result image, and the result image is output.

5. The method according to claim 1, characterized in that: If the coordinates of the person are located in the marked box, determining that there is a person in the dangerous area includes: Acquire the screen status of converter smelting in the to-be-processed screen; If the screen status indicates that the converter smelting process is in one of smelting, iron addition and scrap steel addition, and the personnel coordinates are within the range of the marking box, it is determined that there are personnel in the dangerous area of ​​the converter platform.

6. The method according to claim 1, characterized in that The first processing model is pre-constructed by the following steps: Acquire first training data, where the first training data is a historical monitoring screen including annotated points; Training the first original model using the first training data to obtain a first processed model; The second processing model is pre-constructed by the following steps: Acquire second training data, where the second training data is a historical monitoring screen including a marked frame; The second original model is trained using the second training data to obtain a second processed model.

7. A personnel monitoring device in a dangerous area during converter smelting, characterized in that: The device comprises: An acquisition module is used to acquire a to-be-processed screen, wherein the to-be-processed screen is a real-time monitoring screen of a dangerous area in a converter smelting process; A first processing module is used to perform frame annotation processing on the to-be-processed picture by using a trained first processing model to obtain first intermediate information, where the first intermediate information is three-dimensional data information, and the content of the first intermediate information is the to-be-processed picture including the annotation frame; A second processing module, configured to add the coordinates of the person to the first intermediate information by using a trained second processing model to obtain second intermediate information; The first processing module is further used to determine whether the coordinates of the person are within the range of the annotation box based on the second intermediate information through the trained first processing model; The determination module is used to determine that there is a person in the dangerous area of ​​the converter platform if the person coordinates are located in the marked box; if the person coordinates are not located in the marked box, determine that there is no person in the dangerous area.

8. A personnel monitoring system in dangerous areas during converter smelting, characterized in that: The system includes the device as described in claim 7, a camera device, an alarm device, a laser projection device and an anti-splashback wall, wherein the camera device and the laser projection device are installed on the edge of the converter platform, facing the position of the converter, and the alarm device and the anti-splashback wall are installed at the entrance of the converter platform.

9. An electronic device, characterized in that: include: processor; A memory for storing instructions executed by the processor; The processor is configured to execute the instructions to implement the method according to any one of claims 1 to 6. 10 . A storage medium, when instructions in the storage medium are executed by a processor of an electronic device, the electronic device is enabled to execute the method according to claim 1 .

Images