Hot metal ladle car frame number visual identification system based on Internet

Abstract

The invention discloses a molten iron tank car frame number visual identification system based on the Internet, and relates to the technical field of identification systems. The system comprises an image acquisition module, the signal output end of the image acquisition module is in signal connection with an image processing module, the signal output end of the image processing module is in signal connection with a character recognition module, and the signal output end of the character recognition module is in signal connection with a result output module. The system can improve the working efficiency: the visual identification system based on the Internet can quickly and accurately read the number of the molten iron tank car, so that the time required by manual operation is greatly reduced, the overall efficiency of the production process is remarkably improved, the error rate is reduced, and errors possibly generated by manual identification are avoided; the accuracy and reliability of the frame number information are ensured, and a powerful guarantee is provided for subsequent production management and quality tracing.

Description

Technical Field

[0001] The present invention relates to the technical field of recognition systems, and in particular to an Internet-based molten iron tank frame number visual recognition system. Background Art

[0002] In the steel production process, the management of hot metal ladle is crucial. The traditional method of identifying the ladle frame number mainly relies on manual recording and identification. This method is not only inefficient and prone to human errors, but also requires workers to work harder in harsh production environments. With the rapid development of Internet technology and the continuous advancement of computer vision technology, it is possible to realize the automated and intelligent identification of hot metal ladle frame numbers. Summary of the invention

[0003] The purpose of the present invention is to solve at least one of the technical problems existing in the prior art and to provide an Internet-based molten iron tank frame number visual recognition system that can solve the above-mentioned problem.

[0004] To achieve the above-mentioned purpose, the present invention provides the following technical solutions: an Internet-based molten iron tank frame number visual recognition system, comprising an image acquisition module, a signal output end of the image acquisition module is connected to an image processing module, a signal output end of the image processing module is connected to a character recognition module, and a signal output end of the character recognition module is connected to an output result module.

[0005] Preferably, the molten iron ladle frame number visual recognition system uses a high-resolution industrial camera and a high-definition lens to continuously acquire images of the side of the frame of the molten iron ladle loaded in the monitoring area. After image preprocessing, target positioning, character recognition and other algorithm processing, the recognition result information is transmitted to the secondary information system in real time. The information system matches the recognition result information with other information for each business client to reprocess the information.

[0006] Preferably, the system utilizes optoelectronic technology, machine vision and AI deep learning technology to avoid the difficulty of complex mechanism modeling. The image acquisition device performs AI training on the acquired images to identify and output the frame number. The frame number recognition system for the molten iron tank at the molten iron scale is a technology that uses dynamic video or static images of train frames to automatically recognize frame numbers.

[0007] Preferably, the hardware foundation generally includes image acquisition device, front-end fill light device, waterproof and dustproof protection device, high-speed GPU image processing equipment, etc., and uses deep learning algorithm to perform AI intelligent recognition of the frame number. A complete molten iron scale and molten iron tank frame number recognition system is mainly composed of: mechanical subsystem, image acquisition and processing subsystem, communication subsystem and other modules.

[0008] Preferably, the mechanical subsystem is composed of a mounting bracket, a cabinet, a mounting adjustment device and the like. The purpose of the mechanical structure is to install a fixed image acquisition device, which is installed on the side of the weighing place and includes an air blower, a wiper, and an open window explosion-proof glass opening. The installation structure is designed for the purpose of not affecting the passage of the molten iron tank truck and being able to effectively collect images of the detection area to ensure the best shooting effect.

[0009] Preferably, the image acquisition and processing subsystem is mainly composed of an image sensor, a lens, algorithm processing hardware, algorithm processing software, and a dustproof cover. A 5-megapixel color array sensor is selected, equipped with an ultra-high-definition wide-angle industrial lens to ensure image clarity. The algorithm processing hardware uses a high-performance industrial computer and GPU, and the algorithm processing software is custom-developed software.

[0010] Preferably, the image acquisition and processing software subsystem mainly performs preprocessing, target positioning, and character recognition on the acquired images, and transmits the judgment results through the network.

[0011] Preferably, the system algorithm flow and the system communication adopt industrial Gigabit Ethernet communication mode. The images collected by the camera are transmitted to the visual server via industrial Ethernet, and the recognition results are transmitted to the molten iron tank frame number recognition system at the molten iron scale via Ethernet. The communication sub-system consists of network cables, (transceivers, optical cables) wiring pipes, and power supplies.

[0012] Compared with the prior art, the present invention has the following beneficial effects:

[0013] (1) The Internet-based molten iron ladle frame number visual recognition system can improve work efficiency: the Internet-based visual recognition system can quickly and accurately read the molten iron ladle frame number, greatly reducing the time required for manual operation, significantly improving the overall efficiency of the production process, and reducing the error rate: avoiding the errors that may be caused by manual recognition, ensuring the accuracy and reliability of the frame number information, and providing strong guarantees for subsequent production management and quality traceability. Real-time data transmission and sharing: Through the Internet, the recognized frame number information can be transmitted to the production management system in real time, realizing data sharing between departments, and facilitating timely decision-making and adjustment of production plans.

[0014] (2) The Internet-based molten iron ladle frame number visual recognition system can effectively reduce the labor intensity of workers: workers do not need to perform tedious frame number recognition work in harsh environments, which reduces work risks and labor intensity and improves production management level: accurate frame number recognition helps to achieve refined management of molten iron ladle, optimize production processes, and improve the overall quality and safety of steel production.

[0015] (3) The Internet-based molten iron tank frame number visual recognition system facilitates quality traceability: once a product quality problem or production accident occurs, the frame number can be quickly traced back to the relevant molten iron tank and production links to find out the cause and take corresponding measures. At the same time, it can adapt to harsh environments: the visual recognition system is not affected by harsh environmental factors such as high temperature and dust, can work stably, ensure production continuity, and reduce costs: it reduces labor costs and economic losses caused by misidentification, and improves the company's economic benefits and market competitiveness. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The present invention is further described below in conjunction with the accompanying drawings and embodiments:

[0017] Figure 1 It is the identification workflow diagram of the present invention;

[0018] Figure 2 It is the principle diagram of the identification system of the present invention;

[0019] Figure 3 is a system algorithm flow chart of the present invention;

[0020] Figure 4 It is a recognition rate definition diagram of the present invention;

[0021] Figure 5 It is a schematic diagram of specific parameters of the present invention;

[0022] Figure 6 This is a schematic diagram of the single-point installation of the present invention. DETAILED DESCRIPTION

[0023] This section will describe in detail the specific embodiments of the present invention. The preferred embodiments of the present invention are shown in the accompanying drawings. The purpose of the accompanying drawings is to supplement the description of the text part of the specification with graphics, so that people can intuitively and vividly understand each technical feature and the overall technical solution of the present invention, but it cannot be understood as a limitation on the scope of protection of the present invention.

[0024] In the description of the present invention, it should be understood that descriptions involving orientations, such as up, down, front, back, left, right, etc., and orientations or positional relationships indicated are based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply 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 understood as a limitation on the present invention.

[0025] In the description of the present invention, "greater than", "less than", "exceed" etc. are understood as not including the number itself, and "above", "below", "within" etc. are understood as including the number itself. If there is a description of "first" or "second", it is only used for the purpose of distinguishing technical features, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features or implicitly indicating the order of the indicated technical features.

[0026] In the description of the present invention, unless otherwise clearly defined, terms such as setting, installing, connecting, etc. should be understood in a broad sense, and technicians in the relevant technical field can reasonably determine the specific meanings of the above terms in the present invention based on the specific content of the technical solution.

[0027] See also Figure 1-6 The present invention provides a technical solution: a molten iron tank frame number visual recognition system based on the Internet, comprising an image acquisition module, a signal output end of the image acquisition module is connected to an image processing module, a signal output end of the image processing module is connected to a character recognition module, and a signal output end of the character recognition module is connected to an output result module;

[0028] Furthermore, the ladle frame number visual recognition system uses a high-resolution industrial camera and a high-definition lens to continuously obtain images of the side of the frame of the ladle loaded with ladle in the monitoring area. After image preprocessing, target positioning, character recognition and other algorithm processing, the recognition result information is transmitted to the secondary information system in real time. The information system matches the recognition result information with other information for each business client to reprocess the information.

[0029] Furthermore, this system uses optoelectronic technology, machine vision and AI deep learning technology to avoid the difficulty of complex mechanism modeling. The image acquisition device conducts AI training on the acquired images, recognizes and outputs the frame number. The frame number recognition system of the molten iron tank at the molten iron scale is a technology that uses dynamic video or static images of train frames to automatically recognize frame numbers.

[0030] The hardware foundation generally includes image acquisition devices, front-end fill light devices, waterproof and dustproof protection devices, high-speed GPU image processing equipment, etc., and uses deep learning algorithms to perform AI intelligent recognition of the frame number. A complete molten iron scale weighing iron tank frame number recognition system is mainly composed of: mechanical subsystem, image acquisition and processing subsystem, communication subsystem and other modules;

[0031] Mechanical subsystem: It is composed of mounting brackets, cabinets, mounting adjustment devices, etc. The purpose of the mechanical structure is to install fixed image acquisition equipment, which is installed on the side of the weighing place. It includes air blowing, wipers, and window explosion-proof glass openings. The installation structure is designed for the purpose of not affecting the passage of molten iron tank cars and effectively collecting images of the detection area to ensure the best shooting effect;

[0032] The image acquisition and processing subsystem is mainly composed of image sensors, lenses, algorithm processing hardware, algorithm processing software, and dustproof covers. A 5-megapixel color array sensor is selected, equipped with an ultra-high-definition wide-angle industrial lens to ensure image clarity. The algorithm processing hardware uses a high-performance industrial computer and GPU, and the algorithm processing software is custom-developed software.

[0033] The image acquisition and processing software subsystem mainly performs preprocessing, target positioning, and character recognition on the acquired images, and transmits the judgment results through the network;

[0034] For further information, please refer to Figure 3 ,System algorithm flow,The system communication adopts industrial Gigabit Ethernet communication. The images collected by the camera are transmitted to the visual server through industrial Ethernet, and the recognition results are transmitted to the molten iron tank frame number recognition system at the molten iron scale through Ethernet. The communication sub-system consists of network cables, (transceivers, optical cables) wiring pipelines, and power supplies;

[0035] Further, for Example 1, please refer to Figure 5 , Figure 6 An image acquisition device is deployed on the side of the iron water scale to ensure that the frame number recognition camera can cover the iron water tank frame identification plate area on a track. These cameras transmit the collected image data to the visual server arranged in the operation room in real time. The frame number visual recognition system on the visual server calls the algorithm module to complete the detection process and transmits the recognition result information to the measurement system;

[0036] The installation position of the camera can be fine-tuned according to the actual situation on site. The camera is connected to the industrial Ethernet network where the visual server is located via a Gigabit network (network cable or optical fiber), and the visual server is then connected to the molten iron weighing system via a network cable.

[0037] Furthermore, if the assessment indicators and process flow are standardized, it is necessary to install a high-definition industrial camera and an adaptive light source as an image acquisition device on the side of each weighing place to meet the needs;

[0038] The molten iron tank frame number recognition system at the molten iron scale meets the on-site speed requirements. The train speed does not exceed 12km / h and moves at a constant speed.

[0039] The object to be identified is the frame number of the hot metal tank, and the recognition rate must reach more than 99%;

[0040] For the definition of recognition rate, please refer to Figure 4

[0041] Among them, the detection unit is the detection result feedback cycle, which can be a time cycle or a frame number cycle, depending on the feedback result requirements of the superior system (such as feedback of detection results once every 1s, feedback of detection results once every 3 frames of images), and the detection unit result is obtained based on the feedback of the detection unit single-frame image detection category determination result.

[0042] This system must have an interface for communication with the metering system to meet the monitoring needs of identifying the frame number of the molten iron tank at the molten iron weighing point.

[0043] Furthermore, the system can improve work efficiency: the Internet-based visual recognition system can quickly and accurately read the frame number of the molten iron tank, greatly reducing the time required for manual operation, significantly improving the overall efficiency of the production process, and reducing the error rate: avoiding possible errors caused by manual identification, ensuring the accuracy and reliability of the frame number information, and providing strong guarantees for subsequent production management and quality traceability, real-time data transmission and sharing: through the Internet, the identified frame number information can be transmitted to the production management system in real time, realizing data sharing between departments, and facilitating timely decision-making and adjustment of production plans.

[0044] Furthermore, the system can effectively reduce the labor intensity of workers: workers do not need to perform tedious frame number identification work in harsh environments, which reduces work risks and labor intensity and improves production management level: accurate frame number identification helps to achieve refined management of molten iron tanks, optimize production processes, and improve the overall quality and safety of steel production.

[0045] Furthermore, the system facilitates quality traceability: once product quality problems or production accidents occur, the frame number can be quickly traced back to the relevant molten iron tanks and production links, the causes can be identified and corresponding measures can be taken. At the same time, it can adapt to harsh environments: the visual recognition system is not affected by harsh environmental factors such as high temperature and dust, can work stably, ensure production continuity, and reduce costs: it reduces labor costs and economic losses caused by misidentification, and improves the company's economic benefits and market competitiveness.

[0046] The embodiments of the present invention are described in detail above with reference to the accompanying drawings. However, the present invention is not limited to the above embodiments. Various changes can be made within the knowledge scope of ordinary technicians in the technical field without departing from the purpose of the present invention.

Claims

1. An Internet-based molten iron tank frame number visual recognition system, comprising an image acquisition module, characterized in that: The signal output end of the image acquisition module is connected to the image processing module, the signal output end of the image processing module is connected to the character recognition module, and the signal output end of the character recognition module is connected to the output result module.

2. The Internet-based molten iron tank frame number visual recognition system according to claim 1, characterized in that: The molten iron ladle frame number visual recognition system uses a high-resolution industrial camera and a high-definition lens to continuously acquire images of the side of the frame of the molten iron ladle loaded in the monitoring area. After image preprocessing, target positioning, character recognition and other algorithm processing, the recognition result information is transmitted to the secondary information system in real time. The information system matches the recognition result information with other information for each business client to reprocess the information.

3. The Internet-based molten iron tank frame number visual recognition system according to claim 1 is characterized in that: The system uses optoelectronic technology, machine vision and AI deep learning technology to avoid the difficulties of complex mechanism modeling. The image acquisition device performs AI training on the acquired images to identify and output the frame number. The frame number recognition system for the molten iron tank at the molten iron scale is a technology that uses dynamic video or static images of train frames to automatically recognize frame numbers.

4. The Internet-based molten iron tank frame number visual recognition system according to claim 1 is characterized in that: The hardware foundation generally includes image acquisition devices, front-end fill light devices, waterproof and dustproof protection devices, high-speed GPU image processing equipment, etc., and uses deep learning algorithms to perform AI intelligent recognition of the frame number. A complete molten iron scale and molten iron tank frame number recognition system is mainly composed of: mechanical subsystem, image acquisition and processing subsystem, communication subsystem and other modules.

5. The Internet-based molten iron tank frame number visual recognition system according to claim 4 is characterized in that: The mechanical subsystem is composed of a mounting bracket, a cabinet, a mounting adjustment device and other parts. The purpose of the mechanical structure is to install a fixed image acquisition device, which is installed on the side of the weighing place and includes an air blower, a wiper, and an open window explosion-proof glass opening. The installation structure is designed for the purpose of not affecting the passage of the molten iron tank truck and being able to effectively collect images of the detection area to ensure the best shooting effect.

6. The Internet-based molten iron tank frame number visual recognition system according to claim 4 is characterized in that: The image acquisition and processing subsystem is mainly composed of an image sensor, a lens, algorithm processing hardware, algorithm processing software, and a dustproof cover. A 5-megapixel color array sensor is selected, equipped with an ultra-high-definition wide-angle industrial lens to ensure image clarity. The algorithm processing hardware uses a high-performance industrial computer and GPU, and the algorithm processing software is custom-developed software.

7. The Internet-based molten iron tank frame number visual recognition system according to claim 4 is characterized in that: The image acquisition and processing software subsystem mainly performs preprocessing, target positioning, and character recognition on the acquired images, and transmits the judgment results through the network.

8. The Internet-based molten iron tank frame number visual recognition system according to claim 1 is characterized by: System algorithm flow, system communication adopts industrial Gigabit Ethernet communication mode, the images collected by the camera are transmitted to the visual server via industrial Ethernet, and the recognition results are transmitted to the molten iron tank frame number recognition system at the molten iron scale via Ethernet. The communication sub-system consists of network cables, (transceivers, optical cables) wiring pipes, and power supplies.

Images