Continuous casting slab quality management analysis system based on 5G edge intelligence

Abstract

The invention discloses a continuous casting slab quality management analysis system based on 5G edge intelligence, and belongs to the technical field of industrial quality management systems, the system comprises a sensor module, a field terminal module, a 5G network communication module, an algorithm acceleration module, a data processing module and a man-machine interaction module; the sensor module is used for collecting continuous casting slab production data; the on-site terminal module is used for preprocessing continuous casting slab production data and transmitting the preprocessed data to the data processing module through the 5G network communication module. Wherein the algorithm acceleration module is used for improving the data transmission speed by adopting a hardware acceleration technology; the data processing module is used for detecting the quality of the continuous casting slab based on the production data; and the man-machine interaction module is used for displaying the quality detection result output by the data processing module. According to the invention, the efficiency and accuracy of quality control of steel manufacturing are improved through integrated multi-modular design.

Description

Technical Field

[0001] The present invention relates to the technical field of industrial quality management systems, and in particular to a continuous casting slab quality management and analysis system based on 5G edge intelligence. Background Art

[0002] The traditional continuous casting slab production process is undergoing an unprecedented intelligent transformation. In particular, in the field of continuous casting slab quality management, the challenges faced include not only how to efficiently identify complex surface defects, but also how to analyze and respond quickly to huge production data in real time to optimize the production process. However, the current quality management system can no longer meet the needs of efficiently identifying complex surface defects and analyzing and responding quickly to huge production data in real time to optimize the production process. Therefore, it is urgent to develop a new quality management analysis system. Summary of the invention

[0003] The present invention provides a continuous casting slab quality management and analysis system based on 5G edge intelligence to solve the technical problem that the current quality management system can no longer meet the needs of efficiently identifying complex surface defects and real-time analysis and rapid response in huge production data to optimize the production process.

[0004] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0005] A continuous casting slab quality management and analysis system based on 5G edge intelligence, including a sensor module, a field terminal module, a 5G network communication module, an algorithm acceleration module, a data processing module and a human-computer interaction module;

[0006] The sensor module is deployed at the continuous casting slab production site to collect the continuous casting slab production data and transmit the collected continuous casting slab production data to the site terminal module;

[0007] The field terminal module is used to pre-process the continuous casting slab production data collected by the sensor module, and transmit the pre-processed continuous casting slab production data to the data processing module by using the 5G network communication module; wherein the algorithm acceleration module is used to use hardware acceleration technology to improve the data transmission speed;

[0008] The data processing module is used to detect the quality of the continuous casting slab based on the continuous casting slab production data;

[0009] The human-computer interaction module is used to display the quality detection result output by the data processing module.

[0010] Furthermore, the continuous casting slab production data includes: continuous casting slab surface image, production line number, steel plate ID, camera number, index number and production time.

[0011] Furthermore, the sensor module collects the surface image of the continuous casting slab through multiple image acquisition terminals, and at the same time exchanges data with the L1, L2 and L3 systems of the continuous casting slab production line through Ethernet to obtain the production line number, steel plate ID, camera number, index number and production time;

[0012] Among them, each image acquisition end is composed of an industrial line scan camera and an LED light source.

[0013] Furthermore, the on-site terminal module is specifically used to package and compress the continuous casting slab production data, and use the 5G network communication module to transmit the packaged and compressed continuous casting slab production data to the data processing module.

[0014] Furthermore, the 5G network communication module is used to play the role of data transmission and connection in the system, opening up the end-to-end process from the field terminal module to the data processing module, so that the continuous casting slab production data collected by the sensor module is converted by the field terminal module + slice grouping network and transmitted to the data processing module.

[0015] Further, the data processing module includes an edge server and an MEC data center; wherein a defective data processing module is deployed on the edge server;

[0016] The MEC data center is used to store, analyze and calculate the continuous casting slab production data uploaded by the on-site terminal module, find abnormal areas on the surface image of the continuous casting slab, perform calculations and analysis on the abnormal areas, determine whether the abnormal area is a defect and the defect category through the defect data processing module, and transmit the continuous casting slab surface image and defect information to the human-computer interaction module for display; wherein, the continuous casting slab production data uploaded by the on-site terminal module is stored in the storage server of the MEC data center, and the storage server performs cyclic storage according to the set storage capacity, and automatically clears unnecessary data when the maximum storage capacity is reached.

[0017] Furthermore, the defect data processing module adopts a deep learning method based on artificial intelligence to detect slab defects. It first uses a generative adversarial network to enhance samples, and then uses EfficientNet as a classification priority network based on the rough classification and defect location of defects using YOLOv5.

[0018] Furthermore, the acceleration principle of the algorithm acceleration module is: to build a heterogeneous computing platform based on 5G edge computing with cloud, edge and end working together; in the heterogeneous computing platform, the defect data processing module is deployed on the edge device; the problem of low efficiency of field programmable gate array kernel program in data transmission is solved through the parallel optimization technology of high-level synthesis tools in the field programmable gate array module; a heterogeneous computing system based on CPU-GPU-FPGA is used to increase the speed of data transmission between devices, and solve the delay problem of data transmission between computing units in the heterogeneous computing platform; and a method of deploying deep learning models on edge devices is used to solve the problem of limited computing resources and energy consumption in MEC data centers.

[0019] Furthermore, the human-computer interaction module is deployed on the HMI terminal to display the surface image of the slab taken by a single camera, the surface image of the entire slab, and the defect distribution of the entire slab surface.

[0020] Furthermore, the human-computer interaction module also includes a defect linkage function unit and a remote monitoring unit;

[0021] The defect linkage functional unit is used to realize the position linkage between the slab surface defect and the slab surface image;

[0022] The remote monitoring unit is used for allowing a remote engineer station to view defect analysis and detection images via a network.

[0023] The beneficial effects brought about by the technical solution provided by the present invention include at least:

[0024] The present invention utilizes the efficient data flow of the 5G network and combines it with MEC technology to effectively reduce data processing delays and improve response speed. With the support of the data center, the system can accurately identify defect categories and provide immediate feedback on quality assessment results by intelligently analyzing a large amount of collected continuous casting slab surface data. The algorithm acceleration module uses advanced hardware acceleration technology to increase the speed of data transmission and ensure efficient defect detection and quality assessment. Through the human-computer interaction interface, the system provides intuitive operation and analysis tools to facilitate real-time monitoring of production quality, adjustment of production process parameters, and intelligent management and control of the quality of continuous casting slabs. The present invention makes full use of the advantages of 5G edge computing to provide a highly integrated, responsive, and intelligent quality management solution for the continuous casting slab manufacturing industry, and promotes the digitalization and intelligentization of the steel manufacturing industry. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0026] Figure 1 It is an overall data logic control flow chart of a continuous casting slab quality management and analysis system based on 5G edge intelligence provided by an embodiment of the present invention;

[0027] Figure 2 is a diagram of a data processing and transmission process provided by an embodiment of the present invention;

[0028] Figure 3 It is a schematic diagram of model deployment, training and application of a data center provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0029] In order to make the objectives, technical solutions and advantages of the present invention more clear, the embodiments of the present invention will be further described in detail below with reference to the accompanying drawings.

[0030] First of all, it should be noted that in the embodiments of the present invention, words such as "exemplarily" and "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "exemplary" in the present invention should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of the word "exemplarily" is intended to present the concept in a concrete way. In addition, in the embodiments of the present invention, the meaning expressed by "and / or" can be both, or it can be either of the two.

[0031] This embodiment provides a continuous casting slab quality management and analysis system based on 5G edge intelligence, which aims to use the most cutting-edge information and communication technology to reshape the quality control system of steel manufacturing. The continuous casting slab quality management and analysis system uses the 5G network as the data transmission framework to realize the data flow of the overall system, and uses the data communication between the edge intelligent device and the edge computing layer to realize the direct training of the deep learning algorithm on the edge cloud. At the same time, it combines the network deployment method of 5G edge computing in the industrial Internet scenario, mobile edge computing technology (MEC) and data center to realize intelligent stainless steel quality management and analysis. Specifically, Figure 1 As shown, the continuous casting slab quality management and analysis system based on 5G edge intelligence includes: a sensor module, a field terminal module, a 5G network communication module, an algorithm acceleration module, a data processing module and a human-computer interaction module.

[0032] The sensor module is deployed at the continuous casting slab production site to collect the continuous casting slab production data and transmit the collected continuous casting slab production data to the site terminal module;

[0033] The field terminal module is used to pre-process the continuous casting slab production data collected by the sensor module, and transmit the pre-processed continuous casting slab production data to the data processing module by using the 5G network communication module; wherein the algorithm acceleration module is used to use hardware acceleration technology to improve the data transmission speed;

[0034] Specifically, in this embodiment, the continuous casting slab production data includes: continuous casting slab surface image, production line number, steel plate ID, camera number, index number, production time and other data information. The sensor module collects high-speed moving continuous casting slab surface images through an image acquisition terminal composed of n industrial line scan cameras and n high-brightness water-cooled LED light sources, and at the same time exchanges data with the L1, L2, and L3 systems of the production line through Ethernet to obtain data information such as production line number, steel plate ID, camera number, index number and production time. After the information is packaged and processed by the on-site terminal module, the data is compressed and then uploaded to the data processing module through the 5G network communication module. Figure 2 shown.

[0035] Among them, the 5G network communication module plays a core data transmission and connection role in the entire data flow. Through this virtual network, the end-to-end process from data collection to data processing is opened up. The collected data is converted by the client equipment (CPE) + slice packet network (SPN) and transmitted to the data processing module.

[0036] The data processing module is used to detect the quality of the continuous casting slab based on the continuous casting slab production data;

[0037] Specifically, in this embodiment, the data processing module includes an edge server and an MEC data center; wherein a defective data processing module is deployed on the edge server.

[0038] The MEC data center is used to store, analyze and calculate the continuous casting slab production data uploaded by the on-site terminal module, find abnormal areas on the surface image of the continuous casting slab, perform calculations and analysis on the abnormal areas, and use the defect data processing module and a dedicated continuous casting slab defect image recognition algorithm program to determine whether the abnormal area is a defect and the defect category, and transmit the continuous casting slab surface image and defect information to the human-computer interaction module for display; wherein, the continuous casting slab production data uploaded by the on-site terminal module is transmitted via the 5G network and stored in the storage server of the MEC data center, and the storage server performs cyclic storage according to the set storage capacity, and automatically cleans up unnecessary data when the maximum storage capacity is reached. Among them, the model deployment, training and application process of the data center is as follows: Figure 3 shown.

[0039] The defect data processing module uses a deep learning method based on artificial intelligence to detect and identify steel plate defects. First, a generative adversarial network (GAN) is used to enhance samples. Then, based on the use of the YOLOv5 network for rough classification and defect location, EfficientNet with strong feature extraction capabilities and small model parameters is used as the classification priority network. Its feature extraction of images is more in line with the needs of defect classification.

[0040] Furthermore, the core idea of ​​the algorithm acceleration module is: to build an efficient industrial Internet model based on 5G edge computing with collaborative work of cloud, edge and end; to deploy the defect data processing module on the edge device in the heterogeneous computing platform of 5G edge computing; to solve the problem of low efficiency of field programmable gate array (FPGA) kernel program in data transmission through the parallel optimization technology of high-level synthesis tool (HLS) in field programmable gate array (FPGA) module; to use a heterogeneous computing system based on CPU-GPU-FPGA to improve the speed of data transmission between devices and solve the delay problem of data transmission between computing units in heterogeneous computing platforms; to use the method of deploying deep learning models on edge devices to solve the problems of limited MEC computing resources and energy consumption.

[0041] The human-computer interaction module is used to display the quality detection result output by the data processing module;

[0042] Specifically, in this embodiment, the human-computer interaction module is mainly deployed in the HMI terminal, and a complete set of configurations consisting of a high-performance host and a high-definition display can be used to display the slab image collected by a single camera of the system, the entire plate surface image, the defect distribution of the entire plate surface, and other functions. Among them, the front-end data processing terminal takes into account the preprocessing of the camera image and the defect detection function. The HMI terminal includes two major functional modules: the image analysis console and the defect analysis console. The position linkage of the defect and the steel plate image can be realized through the defect linkage function. The remote engineer station can view the defect analysis automatic detection screen through the network.

[0043] In summary, this embodiment provides a continuous casting slab quality management and analysis system based on 5G edge intelligence. The system utilizes the efficient data flow of the 5G network and combines MEC technology to effectively reduce data processing delays and improve response speed. With the support of the data center, the system can accurately identify defect categories and provide immediate feedback on quality assessment results by intelligently analyzing a large amount of collected continuous casting slab surface data. The algorithm acceleration module uses advanced hardware acceleration technology to increase the speed of data transmission and ensure efficient defect detection and quality assessment. Through the human-computer interaction interface, the system provides intuitive operation and analysis tools to facilitate real-time monitoring of production quality, adjustment of production process parameters, and intelligent management and control of the quality of continuous casting slabs. The present invention makes full use of the advantages of 5G edge computing to provide a highly integrated, responsive, and intelligent quality management solution for the continuous casting slab manufacturing industry, and promotes the digitalization and intelligentization of the steel manufacturing industry.

[0044] In addition, it should be noted that the present invention can be provided as a method, an apparatus or a computer program product. Therefore, the embodiment of the present invention can be in the form of a full or partial hardware embodiment, a full or partial software embodiment or an embodiment combining software and hardware. Moreover, when implemented using software, the embodiment of the present invention can be in the form of a computer program product implemented on one or more computer-usable storage media containing computer-usable program codes. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present invention is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center by wired (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center containing one or more available media sets. The available medium may be a magnetic medium (eg, a floppy disk, a hard disk, a magnetic tape), an optical medium (eg, a DVD), or a semiconductor medium. The semiconductor medium may be a solid state drive.

[0045] The embodiments of the present invention are described with reference to the flowcharts and / or block diagrams of the methods, terminal devices (systems), and computer program products according to the embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of the processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, an embedded processor, or other programmable data processing terminal device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing terminal device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0046] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing terminal device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce a manufactured product including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1These computer program instructions can also be loaded onto a computer or other programmable data processing terminal device, so that a series of operation steps are executed on the computer or other programmable terminal device to produce a computer-implemented process, so that the instructions executed on the computer or other programmable terminal device provide for implementing the process in the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0047] It should also be noted that, in this article, the terms "include", "comprise" or any other variant thereof are intended to cover non-exclusive inclusion, so that a process, method, article or terminal device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or terminal device. In the absence of further restrictions, the elements defined by the sentence "include one..." do not exclude the existence of other identical elements in the process, method, article or terminal device including the elements. In addition, the term "and / or" is only a description of the association relationship of the associated objects, indicating that there may be three relationships, for example, A and / or B, which can represent: A exists alone, A and B exist at the same time, and B exists alone, where A and B can be singular or plural. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship, but it may also indicate an "and / or" relationship, which can be understood by referring to the context before and after. "At least one" means one or more, and "more" means two or more. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b or c can mean: a, b, c, ab, ac, bc, or abc, where a, b, c can be single or plural.

[0048] In addition, it can be understood that in various embodiments of the present invention, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0049] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0050] In several embodiments provided by the present invention, it should be understood that the disclosed equipment, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of functional modules / units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point, the coupling or direct coupling or communication connection between each other shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms. The unit described as a separate component may or may not be physically separated, and the component displayed as a unit may or may not be a physical unit, that is, it may be located in one place, or it may be distributed on multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the scheme of this embodiment. In addition, each functional unit in each embodiment of the present invention can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit.

[0051] If the method is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0052] Finally, it should be noted that the above is only a preferred embodiment of the present invention. It should be pointed out that although the preferred embodiment of the present invention has been described, for ordinary technicians in this technical field, once the basic creative concept of the present invention is known, several improvements and modifications can be made without departing from the principles of the present invention. These improvements and modifications should also be regarded as the protection scope of the present invention. Therefore, the attached claims are intended to be interpreted as including the preferred embodiment and all changes and modifications that fall within the scope of the embodiments of the present invention.

Claims

1. A continuous casting slab quality management and analysis system based on 5G edge intelligence, characterized in that: The continuous casting slab quality management and analysis system based on 5G edge intelligence includes: a sensor module, a field terminal module, a 5G network communication module, an algorithm acceleration module, a data processing module and a human-computer interaction module; The sensor module is deployed at the continuous casting slab production site to collect the continuous casting slab production data and transmit the collected continuous casting slab production data to the site terminal module; The field terminal module is used to pre-process the continuous casting slab production data collected by the sensor module, and transmit the pre-processed continuous casting slab production data to the data processing module by using the 5G network communication module; wherein the algorithm acceleration module is used to use hardware acceleration technology to improve the data transmission speed; The data processing module is used to detect the quality of the continuous casting slab based on the continuous casting slab production data; The human-computer interaction module is used to display the quality detection result output by the data processing module.

2. The continuous casting slab quality management and analysis system based on 5G edge intelligence according to claim 1 is characterized in that: The continuous casting slab production data includes: continuous casting slab surface image, production line number, steel plate ID, camera number, index number and production time.

3. The continuous casting slab quality management and analysis system based on 5G edge intelligence according to claim 2 is characterized in that: The sensor module collects the surface image of the continuous casting slab through multiple image acquisition terminals, and exchanges data with the L1, L2 and L3 systems of the continuous casting slab production line through Ethernet to obtain the production line number, steel plate ID, camera number, index number and production time; Among them, each image acquisition end is composed of an industrial line scan camera and an LED light source.

4. The continuous casting slab quality management and analysis system based on 5G edge intelligence according to claim 1, characterized in that: The on-site terminal module is specifically used to package and compress the continuous casting slab production data, and use the 5G network communication module to transmit the packaged and compressed continuous casting slab production data to the data processing module.

5. The continuous casting slab quality management and analysis system based on 5G edge intelligence according to claim 1, characterized in that: The 5G network communication module is used to play the role of data transmission and connection in the system, opening up the end-to-end process from the field terminal module to the data processing module, so that the continuous casting slab production data collected by the sensor module is converted by the field terminal module + slice grouping network and transmitted to the data processing module.

6. The continuous casting slab quality management and analysis system based on 5G edge intelligence according to claim 2, characterized in that: The data processing module includes an edge server and an MEC data center; wherein a defective data processing module is deployed on the edge server; The MEC data center is used to store, analyze and calculate the continuous casting slab production data uploaded by the on-site terminal module, find abnormal areas on the surface image of the continuous casting slab, perform calculations and analysis on the abnormal areas, determine whether the abnormal area is a defect and the defect category through the defect data processing module, and transmit the continuous casting slab surface image and defect information to the human-computer interaction module for display; wherein, the continuous casting slab production data uploaded by the on-site terminal module is stored in the storage server of the MEC data center, and the storage server performs cyclic storage according to the set storage capacity, and automatically clears unnecessary data when the maximum storage capacity is reached.

7. The continuous casting slab quality management and analysis system based on 5G edge intelligence according to claim 6, characterized in that: The defect data processing module uses a deep learning method based on artificial intelligence to detect slab defects. It first uses a generative adversarial network to enhance samples, and then uses EfficientNet as a classification priority network based on the rough classification and defect location of YOLOv5.

8. The continuous casting slab quality management and analysis system based on 5G edge intelligence according to claim 6, characterized in that: The acceleration principle of the algorithm acceleration module is: building a heterogeneous computing platform based on 5G edge computing with cloud, edge and end working in collaboration; in the heterogeneous computing platform, deploying the defect data processing module on the edge device; Solve the problem of low efficiency of field programmable gate array kernel program in data transmission through parallel optimization technology of high-level synthesis tools in field programmable gate array modules; use heterogeneous computing system based on CPU-GPU-FPGA to improve the speed of data transmission between devices and solve the delay problem of data transmission between computing units in the heterogeneous computing platform; The method of deploying deep learning models on edge devices is used to solve the problems of limited computing resources and energy consumption in MEC data centers.

9. The continuous casting slab quality management and analysis system based on 5G edge intelligence according to claim 6, characterized in that: The human-computer interaction module is deployed on the HMI terminal and is used to display the surface image of the slab taken by a single camera, the surface image of the entire slab, and the defect distribution of the entire slab surface.

10. The continuous casting slab quality management and analysis system based on 5G edge intelligence according to claim 9, characterized in that: The human-computer interaction module also includes a defect linkage function unit and a remote monitoring unit; The defect linkage functional unit is used to realize the position linkage between the slab surface defect and the slab surface image; The remote monitoring unit is used for allowing a remote engineer station to view defect analysis and detection images via a network.

Images