WO2022083155A1 - Method and system for automatically detecting operation state of blast furnace taphole, and storage medium - Google Patents

Method and system for automatically detecting operation state of blast furnace taphole, and storage medium Download PDF

Info

Publication number
WO2022083155A1
WO2022083155A1 PCT/CN2021/101693 CN2021101693W WO2022083155A1 WO 2022083155 A1 WO2022083155 A1 WO 2022083155A1 CN 2021101693 W CN2021101693 W CN 2021101693W WO 2022083155 A1 WO2022083155 A1 WO 2022083155A1
Authority
WO
WIPO (PCT)
Prior art keywords
iron
taphole
time
visible light
blast furnace
Prior art date
Application number
PCT/CN2021/101693
Other languages
French (fr)
Chinese (zh)
Inventor
吴映江
吴锐夫
徐永斌
Original Assignee
中冶南方工程技术有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 中冶南方工程技术有限公司 filed Critical 中冶南方工程技术有限公司
Publication of WO2022083155A1 publication Critical patent/WO2022083155A1/en

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/50—Context or environment of the image
    • G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—Combinations of networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/10—Office automation; Time management
    • G06Q10/103—Workflow collaboration or project management
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/40—Extraction of image or video features
    • G06V10/56—Extraction of image or video features relating to colour
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
    • Y02P10/00—Technologies related to metal processing
    • Y02P10/20—Recycling

Definitions

  • the invention belongs to the technical field of metallurgical automation, and in particular relates to an automatic detection method, system and storage medium for the working state of a blast furnace taphole.
  • the tap management of blast furnaces is an important part of the daily operation of blast furnaces.
  • the uniformity of tap time and the time of slag exposure are important indicators to measure whether the taphole of the blast furnace is operating normally. Automatic identification is the basis of enterprise production automation and management informatization.
  • the automatic detection of iron mouth state is derived from pattern recognition, and they are all specific applications of computer vision technology in various industries.
  • Computer vision is to replace the visual organ with various imaging systems as input information.
  • the computer replaces the brain to complete the processing and interpretation.
  • the ultimate goal of computer vision is to study the ability of computers to perceive and understand the world like humans, with autonomous environmental adaptation capabilities.
  • there are more and more application scenarios of computer vision in iron and steel enterprises which reduces the labor cost of enterprises to varying degrees and ensures the timeliness of information.
  • the traditional image technology needs to design a large number of artificial features. In a complex production environment, some features may be blocked by certain items and machinery, resulting in a low recognition rate. How to overcome the shortcomings of the existing technology is currently in the field of metallurgical automation technology. Urgent problem to be solved.
  • the object of the present invention is to provide a method, system and storage medium for automatic detection of the working state of a blast furnace taphole, so as to realize automatic recording of tapping time and slag-seeing time, improve accuracy and reduce manpower simultaneously.
  • the present invention provides an automatic detection method for the working state of a blast furnace taphole, comprising the following steps:
  • S2 Collect the image in the visible light camera, and identify the position of the opening machine and the mud bubble in the visible light image;
  • step S6 Judgment according to the temperature of the iron mouth position in step S5: if the temperature of the iron mouth position rises to the first threshold interval of the iron flow, it is considered that the iron mouth has been opened, and the current time is recorded as the iron mouth opening time, and calculate The difference between the start time of the opening machine and the opening time of the taphole, and the difference is the length of the taphole opening;
  • step S8 Judgment according to the temperature of the iron hole position in step S7: if the temperature of the iron hole position drops to the second threshold interval for the solidification of the iron flow, it is considered that the iron hole has been blocked, and the time stored in step S7 is recorded as Iron mouth blocking time;
  • the image in the visible light camera is collected, and the position of the opening machine and the mud bubble in the visible light image is identified, which is identified by the trained YOLO neural network.
  • the image acquisition range of the visible light camera covers the opening machine of the iron mouth, the working position of the mud bubble and the entire slag ditch.
  • the first threshold interval is 1200-1500°C.
  • the second threshold interval is lower than 1000°C.
  • the present invention also provides an automatic detection system for the working state of a blast furnace taphole, which is characterized in that it includes an infrared camera, a visible light camera and a server;
  • the visible light camera and the infrared camera are arranged at the position facing the iron mouth, and are used to monitor the action of the iron stream and related equipment, and collect the video stream and send it to the server;
  • the server runs a computer program, and the computer program is used to execute the automatic detection method for the working state of the blast furnace iron hole as described above.
  • the present invention also provides a computer non-volatile storage medium, which stores a computer program, and the computer program is used to execute the above-mentioned automatic detection method for the working state of a blast furnace taphole.
  • the invention provides a method for automatically detecting the working state of a blast furnace taphole.
  • the method adopts the combination of image recognition technology and process knowledge, realizes automatic recording of iron tapping time and slag viewing time, improves accuracy and reduces manpower.
  • Fig. 1 is the flow chart of the automatic detection method of the blast furnace taphole working state of the present invention.
  • the invention discloses an automatic detection method for the working state of a blast furnace taphole.
  • S2 Collect the image in the visible light camera, and identify the position of the opening machine and the mud bubble in the visible light image;
  • step S6 Judging according to the temperature of the iron mouth position in step S5: if the temperature of the iron mouth position rises to the first threshold interval of the iron flow, it is considered that the iron mouth has been opened, and the current time is recorded as the iron mouth opening time t2, and Calculate the difference between the start time t1 of the opening machine and the opening time t2 of the taphole, which is the length of the taphole opening;
  • step S8 Judgment according to the temperature of the iron hole position in step S7: if the temperature of the iron hole position drops to the second threshold interval for the solidification of the iron flow, it is considered that the iron hole has been blocked, and the time stored in step S7 is recorded as iron The mouth blocking time t3;
  • the image in the visible light camera is collected, and the position of the opening machine and the mud bubble in the visible light image is identified, which is identified through the trained YOLO neural network.
  • the automatic detection of the working state of the blast furnace iron mouth is performed, the motion and temperature of the relevant components are detected by the neural network and the infrared camera, and the time point when the requirement is reached is recorded.
  • the image acquisition range of the visible light camera covers the opening machine of the tap hole, the working position of the mud bubble and the entire slag ditch, so that the monitoring of the blast furnace tap hole can be completed by a single visible light camera.
  • the first threshold interval is 1200-1500° C.
  • the iron flow is in a fluid state, and this interval can be appropriately adjusted according to the different ratios of iron and iron alloys.
  • the second threshold range is lower than 1000°C, and in this temperature range, the iron flow is in a non-fluid state.
  • the invention also provides an automatic detection system for the working state of a blast furnace taphole, which is characterized by comprising an infrared camera, a visible light camera and a server;
  • the visible light camera and the infrared camera are arranged at the position facing the iron mouth, and are used to monitor the action of the iron flow and related equipment, and collect images and send them to the server;
  • the server runs a computer program, and the program is used to execute the above-mentioned automatic detection method for the working state of the blast furnace iron hole.
  • the computer program is stored in a computer non-volatile storage medium, and the computer non-volatile storage medium can be a mechanical hard disk, a solid-state disk, an on-board Flash memory, an external U disk, an optical disk, etc. in a local server or a cloud server.
  • the program can be called and run by at least one processor in a local server (such as an industrial computer system) or a cloud server, and the automatic detection method for the working state of the blast furnace taphole is described above.

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Business, Economics & Management (AREA)
  • Strategic Management (AREA)
  • Data Mining & Analysis (AREA)
  • Human Resources & Organizations (AREA)
  • Multimedia (AREA)
  • Mathematical Physics (AREA)
  • Biophysics (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Biomedical Technology (AREA)
  • Evolutionary Computation (AREA)
  • Software Systems (AREA)
  • Computational Linguistics (AREA)
  • General Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Health & Medical Sciences (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Marketing (AREA)
  • Economics (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Tourism & Hospitality (AREA)
  • General Business, Economics & Management (AREA)
  • Waste-Gas Treatment And Other Accessory Devices For Furnaces (AREA)
  • Blast Furnaces (AREA)

Abstract

A method and system for automatically detecting the operation state of a blast furnace taphole, and a storage medium, relating to the field of metallurgical automation. The method comprises the following steps: installing an infrared camera and a visible light camera at a position directly facing a taphole, and performing image acquisition; acquiring an image from the visible light camera, and detecting the positions of a taphole drilling machine and a clay gun in said image from the visible light camera; and acquiring an image from the infrared camera, calibrating a taphole position for the infrared camera, and determining the temperature at the taphole position. Image detection is performed to detect the relative positions of the taphole drilling machine and the taphole and the temperature at the taphole position, so as to accurately record an operation start time of the taphole drilling machine, a taphole drilling time, a taphole plugging time, a slag observation time, etc., thereby achieving real-time management of blast furnace tapping.

Description

一种高炉铁口工作状态的自动检测方法、***及存储介质Method, system and storage medium for automatic detection of working state of blast furnace taphole 技术领域technical field
本发明属于冶金自动化技术领域，具体涉及高炉铁口工作状态的自动检测方法、***及存储介质。The invention belongs to the technical field of metallurgical automation, and in particular relates to an automatic detection method, system and storage medium for the working state of a blast furnace taphole.
背景技术Background technique
在钢铁行业中，高炉的出铁管理是高炉日常操作中的重要组成部分，出铁时间的均匀性和见渣时间的早晚是衡量高炉铁口运行是否正常的重要标志，因此对出铁时间的自动化识别是企业生产自动化，管理信息化的基础。In the iron and steel industry, the tap management of blast furnaces is an important part of the daily operation of blast furnaces. The uniformity of tap time and the time of slag exposure are important indicators to measure whether the taphole of the blast furnace is operating normally. Automatic identification is the basis of enterprise production automation and management informatization.
目前炼铁厂普遍采用的记录开铁口、堵铁口时间和见渣时间的方式为人工判断，然后在电脑上输入相应的时间。由于高炉上的工作节奏快，事情多，经常不能在第一时间记录，导致记录的时间不准等问题。At present, the method commonly used in ironmaking plants to record the time of opening, plugging and slag viewing is manual judgment, and then input the corresponding time on the computer. Due to the fast pace of work on the blast furnace and many things, it is often impossible to record at the first time, resulting in inaccurate recording time and other problems.
铁口状态的自动检测是从模式识别中衍生而来的，他们都是计算机视觉技术在各种行业中的具体应用。计算机视觉就是用各种成像***替代视觉器官作为输入信息。由计算机来替代大脑完成处理和解释。计算机视觉的最终目标是研究计算机能像人一样来感知和理解世界，具有自主的环境适应能力。目前，在钢铁企业中计算机视觉的应用场景越来越多，在不同程度上减少了企业的人力成本，也保证了信息的及时性。但是传统的图像技术需要设计大量的人工特征，在复杂的生产环境有一些特征可能会被某些物品及机械遮挡，造成识别率不高等问题，如何克服现有技术的不足是目前冶金自动化技术领域亟需解决的问题。The automatic detection of iron mouth state is derived from pattern recognition, and they are all specific applications of computer vision technology in various industries. Computer vision is to replace the visual organ with various imaging systems as input information. The computer replaces the brain to complete the processing and interpretation. The ultimate goal of computer vision is to study the ability of computers to perceive and understand the world like humans, with autonomous environmental adaptation capabilities. At present, there are more and more application scenarios of computer vision in iron and steel enterprises, which reduces the labor cost of enterprises to varying degrees and ensures the timeliness of information. However, the traditional image technology needs to design a large number of artificial features. In a complex production environment, some features may be blocked by certain items and machinery, resulting in a low recognition rate. How to overcome the shortcomings of the existing technology is currently in the field of metallurgical automation technology. Urgent problem to be solved.
发明内容SUMMARY OF THE INVENTION
有鉴于现有技术的不足，本发明的目的在于提供一种高炉铁口工作状态的自动检测方法、***及存储介质，实现对出铁时间和见渣时间的自动记录，提高准确性同时减少人力。In view of the deficiencies of the prior art, the object of the present invention is to provide a method, system and storage medium for automatic detection of the working state of a blast furnace taphole, so as to realize automatic recording of tapping time and slag-seeing time, improve accuracy and reduce manpower simultaneously. .
为实现上述目的，本发明提供了一种高炉铁口工作状态的自动检测方法，包括如下步骤：In order to achieve the above purpose, the present invention provides an automatic detection method for the working state of a blast furnace taphole, comprising the following steps:
S1：在正对铁口的位置安装红外摄像头和可见光摄像头，进行图像采集；S1: Install an infrared camera and a visible light camera at the position facing the iron mouth for image acquisition;
S2：采集可见光摄像头中的图像，识别可见光图像中的开口机和泥泡的位置；S2: Collect the image in the visible light camera, and identify the position of the opening machine and the mud bubble in the visible light image;
S3：采集红外摄像头中的图像，标定红外摄像头中的铁口位置，及识别所述铁口位置的温度；S3: collecting the image in the infrared camera, calibrating the iron hole position in the infrared camera, and identifying the temperature of the iron hole position;
S4：当检测到开口机转动到铁口的位置时，认为开口机开始开铁口，记录当前时间为开口机开始作业时间；S4: When it is detected that the opening machine rotates to the position of the iron mouth, it is considered that the opening machine starts to open the iron hole, and the current time is recorded as the time when the opening machine starts to operate;
S5：当检测到开口机离开铁口位置后，检测铁口位置的温度；S5: When it is detected that the opening machine leaves the iron hole position, the temperature of the iron hole position is detected;
S6：根据步骤S5中的铁口位置的温度判定：如果铁口位置的温度上升到铁流流动的第一阈值区间，则视为铁口已经打开，记录当前时间为铁口打开时间，并且计算开口机开始作业时间到铁口打开时间的差值，所述差值为开铁口时长；S6: Judgment according to the temperature of the iron mouth position in step S5: if the temperature of the iron mouth position rises to the first threshold interval of the iron flow, it is considered that the iron mouth has been opened, and the current time is recorded as the iron mouth opening time, and calculate The difference between the start time of the opening machine and the opening time of the taphole, and the difference is the length of the taphole opening;
S7：当检测到泥炮转动到铁口位置，储存此刻的时间，一段时间后泥炮离开铁口位置时，检测铁口位置的温度；S7: When it is detected that the mud gun rotates to the iron mouth position, the time at the moment is stored, and when the mud gun leaves the iron mouth position after a period of time, the temperature of the iron mouth position is detected;
S8：根据步骤S7中的铁口位置的温度判定：如果铁口位置的温度下降到铁流凝固的第二阈值区间，则视为铁口已经堵上，则记录步骤S7中已储存的时间为铁口堵口时间；S8: Judgment according to the temperature of the iron hole position in step S7: if the temperature of the iron hole position drops to the second threshold interval for the solidification of the iron flow, it is considered that the iron hole has been blocked, and the time stored in step S7 is recorded as Iron mouth blocking time;
S9：提取渣沟位置的可见光图像，对其进行颜色检测，当整个渣沟都变为红色或者红黄复合色的时候，视为铁口见渣，记录当前时间为铁口见渣时间。S9: Extract the visible light image of the position of the slag ditch, and perform color detection on it. When the entire slag ditch becomes red or red-yellow composite color, it is regarded as the slag at the iron mouth, and the current time is recorded as the time when the iron mouth sees the slag.
进一步的，所述步骤S2中采集可见光摄像头中的图像，识别可见光图像中的开口机和泥泡的位置，是通过已训练的YOLO神经网络进行识别的。Further, in the step S2, the image in the visible light camera is collected, and the position of the opening machine and the mud bubble in the visible light image is identified, which is identified by the trained YOLO neural network.
进一步的，所述可见光摄像头的图像采集范围覆盖铁口的开口机、泥泡的工作位置和整条渣沟。Further, the image acquisition range of the visible light camera covers the opening machine of the iron mouth, the working position of the mud bubble and the entire slag ditch.
进一步的，所述第一阈值区间为1200-1500℃。Further, the first threshold interval is 1200-1500°C.
进一步的，所述第二阈值区间为低于1000℃。Further, the second threshold interval is lower than 1000°C.
为实现上述目的，本发明还提供了一种高炉铁口工作状态的自动检测***，其特征在于：包括红外摄像头、可见光摄像头和服务器；In order to achieve the above object, the present invention also provides an automatic detection system for the working state of a blast furnace taphole, which is characterized in that it includes an infrared camera, a visible light camera and a server;
所述可见光摄像头和红外摄像头设置于正对铁口的位置，用于监视铁流和相关设备的动作，并采集视频流发送给服务器；The visible light camera and the infrared camera are arranged at the position facing the iron mouth, and are used to monitor the action of the iron stream and related equipment, and collect the video stream and send it to the server;
所述服务器运行有一段计算机程序，所述计算机程序用于执行如上所述的高炉铁口工作状态的自动检测方法中。The server runs a computer program, and the computer program is used to execute the automatic detection method for the working state of the blast furnace iron hole as described above.
为实现上述目的，本发明还提供了一种计算机非易失存储介质，存储有一段计算机程序，所述计算机程序用于执行如上所述的高炉铁口工作状态的自动检测方法。In order to achieve the above object, the present invention also provides a computer non-volatile storage medium, which stores a computer program, and the computer program is used to execute the above-mentioned automatic detection method for the working state of a blast furnace taphole.
技术效果：Technical effect:
本发明提供一种自动检测高炉铁口工作状态的方法，该方法采用图像识别的技术和工艺知识结合的方式，实现对出铁时间和见渣时间的自动记录，提高准确性同时减少人力。The invention provides a method for automatically detecting the working state of a blast furnace taphole. The method adopts the combination of image recognition technology and process knowledge, realizes automatic recording of iron tapping time and slag viewing time, improves accuracy and reduces manpower.
附图说明Description of drawings
图1为本发明的高炉铁口工作状态的自动检测方法流程图。Fig. 1 is the flow chart of the automatic detection method of the blast furnace taphole working state of the present invention.
具体实施方式Detailed ways
为进一步说明各实施例，本发明提供有附图。这些附图为本发明揭露内容的一部分，其主要用以说明实施例，并可配合说明书的相关描述来解释实施例的运作原理。配合参考这些内容，本领域普通技术人员应能理解其他可能的实施方式以及本发明的优点。图中的组件并未按比例绘制，而类似的组件符号通常用来表示类似的组件。To further illustrate the various embodiments, the present invention is provided with the accompanying drawings. These drawings are a part of the disclosure of the present invention, which are mainly used to illustrate the embodiments, and can be used in conjunction with the relevant description of the specification to explain the operation principles of the embodiments. With reference to these contents, one of ordinary skill in the art will understand other possible embodiments and advantages of the present invention. Components in the figures are not drawn to scale, and similar component symbols are often used to represent similar components.
现结合附图和具体实施方式对本发明进一步说明。The present invention will now be further described with reference to the accompanying drawings and specific embodiments.
本发明公开了一种高炉铁口工作状态的自动检测方法，The invention discloses an automatic detection method for the working state of a blast furnace taphole.
包括如下步骤：It includes the following steps:
S1：在正对铁口的位置安装红外摄像头和可见光摄像头，进行图像采集；S1: Install an infrared camera and a visible light camera at the position facing the iron mouth for image acquisition;
S2：采集可见光摄像头中的图像，识别可见光图像中的开口机和泥泡的位置；S2: Collect the image in the visible light camera, and identify the position of the opening machine and the mud bubble in the visible light image;
S3：采集红外摄像头中的图像，标定红外摄像头中的铁口位置，及识别所述铁口位置的温度；S3: collecting the image in the infrared camera, calibrating the iron hole position in the infrared camera, and identifying the temperature of the iron hole position;
S4：当检测到开口机转动到铁口的位置时，认为开口机开始开铁口，记录当前时间为开口机开始作业时间t1；S4: When it is detected that the opening machine has turned to the position of the iron hole, it is considered that the opening machine starts to open the iron hole, and the current time is recorded as the opening machine start operation time t1;
S5：当检测到开口机离开铁口位置后，检测铁口位置的温度；S5: When it is detected that the opening machine leaves the iron hole position, the temperature of the iron hole position is detected;
S6：根据步骤S5中的铁口位置的温度判定：如果铁口位置的温度上升到铁流流动的第一阈值区间，则视为铁口已经打开，记录当前时间为铁口打开时间t2，并且计算开口机开始作业时间t1到铁口打开时间t2的差值，此为开铁口时长；S6: Judging according to the temperature of the iron mouth position in step S5: if the temperature of the iron mouth position rises to the first threshold interval of the iron flow, it is considered that the iron mouth has been opened, and the current time is recorded as the iron mouth opening time t2, and Calculate the difference between the start time t1 of the opening machine and the opening time t2 of the taphole, which is the length of the taphole opening;
S7：当检测到泥炮转动到铁口位置，储存此刻的时间，一段时间后泥炮离开铁口位置时，检测铁口位置的温度；S7: When it is detected that the mud gun rotates to the iron mouth position, the time at the moment is stored, and when the mud gun leaves the iron mouth position after a period of time, the temperature of the iron mouth position is detected;
S8：根据步骤S7中的铁口位置的温度判定：如果铁口位置的温度下降到铁流凝固的第二阈值区间，则视为铁口已经堵上，则记录步骤S7已储存的时间为铁口堵口时间t3；S8: Judgment according to the temperature of the iron hole position in step S7: if the temperature of the iron hole position drops to the second threshold interval for the solidification of the iron flow, it is considered that the iron hole has been blocked, and the time stored in step S7 is recorded as iron The mouth blocking time t3;
S9：提取渣沟位置的可见光图像，对其进行颜色检测，当整个渣沟都变为红色或者红黄复合色的时候，视为铁口见渣，并记录当前时间为铁口见渣时间t4。S9: Extract the visible light image of the position of the slag ditch, and perform color detection on it. When the entire slag ditch turns red or red-yellow composite color, it is considered that slag is seen at the iron mouth, and the current time is recorded as the time t4 when the iron mouth sees slag. .
优选的，所述步骤S2中采集可见光摄像头中的图像，识别可见光图像中的开口机和泥泡的位置，是通过已训练的YOLO神经网络进行识别的。Preferably, in the step S2, the image in the visible light camera is collected, and the position of the opening machine and the mud bubble in the visible light image is identified, which is identified through the trained YOLO neural network.
在执行高炉铁口工作状态的自动检测前，需要先进行图像识别的神经网络训练和位置标定，如图1所示，包括以下几个步骤：Before performing the automatic detection of the working state of the blast furnace taphole, it is necessary to perform neural network training and position calibration for image recognition, as shown in Figure 1, including the following steps:
采集大量的可见光图像，标定开口机、泥炮和铁口的位置，制作成数据集；Collect a large number of visible light images, calibrate the positions of the opening machine, mud gun and iron mouth, and make a data set;
构建如YOLO等神经网络，利用上述数据集进行神经网络训练；Build neural networks such as YOLO, and use the above data sets for neural network training;
采集红外图像，在红外摄像头中标定高炉铁口的位置。Collect infrared images, and calibrate the position of the blast furnace iron mouth in the infrared camera.
在完成以上准备工作后，执行高炉铁口工作状态的自动检测，利用神经网络和红外摄像头检测相关部件的动作和温度，记录达到要求时的时刻点。After completing the above preparations, the automatic detection of the working state of the blast furnace iron mouth is performed, the motion and temperature of the relevant components are detected by the neural network and the infrared camera, and the time point when the requirement is reached is recorded.
优选的，所述可见光摄像头的图像采集范围覆盖铁口的开口机、泥泡的工作位置和整条渣沟，这样可以通过单个可见光摄像头即可完成高炉铁口的监视。Preferably, the image acquisition range of the visible light camera covers the opening machine of the tap hole, the working position of the mud bubble and the entire slag ditch, so that the monitoring of the blast furnace tap hole can be completed by a single visible light camera.
优选的，所述第一阈值区间为1200-1500℃，在该温度区间，铁流为流体状态，该区间可根据铁及铁合金的配比不同做适度调整。Preferably, the first threshold interval is 1200-1500° C. In this temperature interval, the iron flow is in a fluid state, and this interval can be appropriately adjusted according to the different ratios of iron and iron alloys.
进一步的，所述第二阈值区间为低于1000℃，在该温度区间，铁流为非流体状态。Further, the second threshold range is lower than 1000°C, and in this temperature range, the iron flow is in a non-fluid state.
本发明还提供了一种高炉铁口工作状态的自动检测***，其特征在于：包括红外摄像头、可见光摄像头和服务器；The invention also provides an automatic detection system for the working state of a blast furnace taphole, which is characterized by comprising an infrared camera, a visible light camera and a server;
所述可见光摄像头和红外摄像头设置于正对铁口的位置，用于监视铁流和相关设备的动作，并采集图像发送给服务器；The visible light camera and the infrared camera are arranged at the position facing the iron mouth, and are used to monitor the action of the iron flow and related equipment, and collect images and send them to the server;
所述服务器运行有一段计算机程序，所述程序用于执行如上所述的高炉铁口工作状态的自动检测方法。The server runs a computer program, and the program is used to execute the above-mentioned automatic detection method for the working state of the blast furnace iron hole.
计算机程序存储于计算机非易失存储介质中，该计算机非易失存储介质可以是本地服务器或云服务器中的机械硬盘、固态硬盘、板载Flash存储器、外接的U盘、光盘等装置，该计算机程序可以被本地服务器(如工控机***)或云服务器中的至少一个处理器调用并运行，如上所述的高炉铁口工作状态的自动检测方法。The computer program is stored in a computer non-volatile storage medium, and the computer non-volatile storage medium can be a mechanical hard disk, a solid-state disk, an on-board Flash memory, an external U disk, an optical disk, etc. in a local server or a cloud server. The program can be called and run by at least one processor in a local server (such as an industrial computer system) or a cloud server, and the automatic detection method for the working state of the blast furnace taphole is described above.
尽管结合优选实施方案具体展示和介绍了本发明，但所属领域的技术人员应该明白，在不脱离所附权利要求书所限定的本发明的精神和范围内，在形式上和细节上可以对本发明做出各种变化，均为本发明的保护范围。Although the present invention has been particularly shown and described in connection with preferred embodiments, it will be understood by those skilled in the art that changes in form and detail may be made to the present invention without departing from the spirit and scope of the invention as defined by the appended claims. Various changes are made within the protection scope of the present invention.

Claims (7)

  1. 一种高炉铁口工作状态的自动检测方法，其特征在于，包括如下步骤：A kind of automatic detection method of blast furnace taphole working state, is characterized in that, comprises the following steps:
    S1：在正对铁口的位置安装红外摄像头和可见光摄像头，进行图像采集；S1: Install an infrared camera and a visible light camera at the position facing the iron mouth for image acquisition;
    S2：采集可见光摄像头中的图像，识别可见光图像中的开口机和泥泡的位置；S2: Collect the image in the visible light camera, and identify the position of the opening machine and the mud bubble in the visible light image;
    S3：采集红外摄像头中的图像，标定红外摄像头中的铁口位置，及识别所述铁口位置的温度；S3: collecting the image in the infrared camera, calibrating the iron hole position in the infrared camera, and identifying the temperature of the iron hole position;
    S4：当检测到开口机转动到铁口的位置时，认为开口机开始开铁口，记录当前时间为开口机开始作业时间；S4: When it is detected that the opening machine rotates to the position of the iron mouth, it is considered that the opening machine starts to open the iron hole, and the current time is recorded as the time when the opening machine starts to operate;
    S5：当检测到开口机离开铁口位置后，检测铁口位置的温度；S5: When it is detected that the opening machine leaves the iron hole position, the temperature of the iron hole position is detected;
    S6：根据步骤S5中的铁口位置的温度判定：如果铁口位置的温度上升到铁流流动的第一阈值区间，则视为铁口已经打开，记录当前时间为铁口打开时间，并且计算开口机开始作业时间到铁口打开时间的差值，所述差值为开铁口时长；S6: Judgment according to the temperature of the iron mouth position in step S5: if the temperature of the iron mouth position rises to the first threshold interval of the iron flow, it is considered that the iron mouth has been opened, and the current time is recorded as the iron mouth opening time, and calculate The difference between the start time of the opening machine and the opening time of the taphole, and the difference is the length of the taphole opening;
    S7：当检测到泥炮转动到铁口位置，储存此刻的时间，一段时间后泥炮离开铁口位置时，检测铁口位置的温度；S7: When it is detected that the mud gun rotates to the iron mouth position, the time at the moment is stored, and when the mud gun leaves the iron mouth position after a period of time, the temperature of the iron mouth position is detected;
    S8：根据步骤S7中的铁口位置的温度判定：如果铁口位置的温度下降到铁流凝固的第二阈值区间，则视为铁口已经堵上，则记录步骤S7中已储存的时间为铁口堵口时间；S8: Judgment according to the temperature of the iron hole position in step S7: if the temperature of the iron hole position drops to the second threshold interval for the solidification of the iron flow, it is considered that the iron hole has been blocked, and the time stored in step S7 is recorded as Iron mouth blocking time;
    S9：提取渣沟位置的可见光图像，对其进行颜色检测，当整个渣沟都变为红色或者红黄复合色的时候，视为铁口见渣，并记录当前时间为铁口见渣时间。S9: Extract the visible light image of the position of the slag ditch, and perform color detection on it. When the entire slag ditch turns red or red-yellow composite color, it is deemed that the slag is seen at the iron mouth, and the current time is recorded as the time when the iron mouth sees the slag.
  2. 如权利要求1所述的高炉铁口工作状态的自动检测方法，其特征在于：所述S2中采集可见光摄像头中的图像，识别可见光图像中的开口机和泥泡的位置，是通过已训练的YOLO神经网络进行识别的。The automatic detection method for the working state of a blast furnace taphole according to claim 1, wherein: in the step S2, the image in the visible light camera is collected, and the positions of the opening machine and the mud bubble in the visible light image are identified by the trained method. YOLO neural network for recognition.
  3. 如权利要求1所述的高炉铁口工作状态的自动检测方法，其特征在于：所述可见光摄像头的图像采集范围覆盖铁口的开口机、泥泡的工作位置和整条渣沟。The automatic detection method for the working state of the blast furnace taphole according to claim 1, wherein the image acquisition range of the visible light camera covers the taphole opening machine, the working position of the mud bubble and the entire slag ditch.
  4. 如权利要求1所述的高炉铁口工作状态的自动检测方法，其特征在于：所述第一阈值区间为1200-1500℃。The automatic detection method for the working state of a blast furnace taphole according to claim 1, wherein the first threshold interval is 1200-1500°C.
  5. 如权利要求1所述的高炉铁口工作状态的自动检测方法，其特征在于：所述第二阈值区间为低于1000℃。The automatic detection method for the working state of a blast furnace taphole according to claim 1, wherein the second threshold interval is lower than 1000°C.
  6. 一种高炉铁口工作状态的自动检测***，其特征在于：包括红外摄像头、可见光摄像头和服务器；An automatic detection system for the working state of a blast furnace taphole, which is characterized in that it comprises an infrared camera, a visible light camera and a server;
    所述可见光摄像头和红外摄像头设置于正对铁口的位置，用于监视铁流和相关设备的动作，并采集图像发送给服务器；The visible light camera and the infrared camera are arranged at the position facing the iron mouth, and are used to monitor the action of the iron flow and related equipment, and collect images and send them to the server;
    所述服务器运行有一计算机段程序，所述计算机程序用于执行如权利要求1-5任一项所 述的高炉铁口工作状态的自动检测方法。The server runs a computer segment program, and the computer program is used to execute the automatic detection method for the working state of the blast furnace taphole according to any one of claims 1-5.
  7. 一种计算机非易失存储介质，其特征在于，存储有一段计算机程序，所述计算机程序用于执行如权利要求1-5任一项所述的高炉铁口工作状态的自动检测方法。A computer non-volatile storage medium is characterized in that a section of computer program is stored, and the computer program is used to execute the automatic detection method for the working state of a blast furnace iron mouth according to any one of claims 1-5.
PCT/CN2021/101693 2020-10-22 2021-06-23 Method and system for automatically detecting operation state of blast furnace taphole, and storage medium WO2022083155A1 (en)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202011138001.4A CN112257590B (en) 2020-10-22 2020-10-22 Automatic detection method, system and storage medium for working state of blast furnace tap hole
CN202011138001.4 2020-10-22

Publications (1)

Publication Number Publication Date
WO2022083155A1 true WO2022083155A1 (en) 2022-04-28

Family

ID=74263971

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/101693 WO2022083155A1 (en) 2020-10-22 2021-06-23 Method and system for automatically detecting operation state of blast furnace taphole, and storage medium

Country Status (2)

Country Link
CN (1) CN112257590B (en)
WO (1) WO2022083155A1 (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115074473A (en) * 2022-06-17 2022-09-20 马鞍山钢铁股份有限公司 Remote intelligent maintenance system and method for mud beating mechanism
WO2024060284A1 (en) * 2022-09-21 2024-03-28 中冶南方工程技术有限公司 Identification method and device for temperature distribution of blast furnace top burden surface, and storage medium

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112257590B (en) * 2020-10-22 2023-08-01 中冶南方工程技术有限公司 Automatic detection method, system and storage medium for working state of blast furnace tap hole
CN114187280A (en) * 2021-12-14 2022-03-15 重庆赛迪奇智人工智能科技有限公司 Method and device for detecting iron receiving state
CN115612765B (en) * 2022-10-14 2023-05-26 合肥视展光电科技有限公司 Real-time detection control method and system for blast furnace tapping state

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102081396A (en) * 2010-12-31 2011-06-01 北京交通大学 Multi-sensor concentrated control method for full-automatic blast furnace dedusting fan control system
CN110184401A (en) * 2019-05-10 2019-08-30 柳州钢铁股份有限公司 Tap cinder iron state online test method
US20200172989A1 (en) * 2017-09-27 2020-06-04 International Business Machines Corporation Manufacturing process control with deep learning-based predictive model for hot metal temperature of blast furnace
CN111492070A (en) * 2017-12-19 2020-08-04 株式会社Posco Furnace condition control apparatus and method
CN111593151A (en) * 2020-04-30 2020-08-28 柳州钢铁股份有限公司 On-line detection method for depth of blast furnace tap hole
CN112257590A (en) * 2020-10-22 2021-01-22 中冶南方工程技术有限公司 Automatic detection method and system for working state of blast furnace taphole and storage medium

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP4926790B2 (en) * 2007-04-03 2012-05-09 新日本製鐵株式会社 Blast furnace operation method
WO2015015936A1 (en) * 2013-07-29 2015-02-05 Ｊｆｅスチール株式会社 Abnormality detection method and blast-furnace operation method
CN104141021B (en) * 2014-08-28 2015-11-11 中冶南方工程技术有限公司 A kind of method of blast furnace open hole and blast furnace open hole device systems
CN110175716A (en) * 2019-05-27 2019-08-27 中冶赛迪重庆信息技术有限公司 State change and gravimetric analysis sensing method, equipment and medium towards blast furnace casting
CN111254243B (en) * 2020-03-11 2020-11-24 中南大学 Method and system for intelligently determining iron notch blocking time in blast furnace tapping process

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102081396A (en) * 2010-12-31 2011-06-01 北京交通大学 Multi-sensor concentrated control method for full-automatic blast furnace dedusting fan control system
US20200172989A1 (en) * 2017-09-27 2020-06-04 International Business Machines Corporation Manufacturing process control with deep learning-based predictive model for hot metal temperature of blast furnace
CN111492070A (en) * 2017-12-19 2020-08-04 株式会社Posco Furnace condition control apparatus and method
CN110184401A (en) * 2019-05-10 2019-08-30 柳州钢铁股份有限公司 Tap cinder iron state online test method
CN111593151A (en) * 2020-04-30 2020-08-28 柳州钢铁股份有限公司 On-line detection method for depth of blast furnace tap hole
CN112257590A (en) * 2020-10-22 2021-01-22 中冶南方工程技术有限公司 Automatic detection method and system for working state of blast furnace taphole and storage medium

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115074473A (en) * 2022-06-17 2022-09-20 马鞍山钢铁股份有限公司 Remote intelligent maintenance system and method for mud beating mechanism
WO2024060284A1 (en) * 2022-09-21 2024-03-28 中冶南方工程技术有限公司 Identification method and device for temperature distribution of blast furnace top burden surface, and storage medium

Also Published As

Publication number Publication date
CN112257590A (en) 2021-01-22
CN112257590B (en) 2023-08-01

Similar Documents

Publication Publication Date Title
WO2022083155A1 (en) Method and system for automatically detecting operation state of blast furnace taphole, and storage medium
Yang et al. Vision-based tower crane tracking for understanding construction activity
US10937144B2 (en) Pipe feature identification using pipe inspection data analysis
JP6763367B2 (en) Gas leak position estimation device, gas leak position estimation system, gas leak position estimation method and gas leak position estimation program
US11378387B2 (en) System and method for locating, measuring, counting, and aiding in the handling of drill pipes
CN104408406B (en) Personnel based on frame difference method and background subtraction leave the post detection method
CN110084092B (en) Method and system for temperature measurement using machine learning algorithm
EP3514525B1 (en) Interactive semi-automated borescope video analysis and damage assessment system and method of use
CN100394147C (en) Water level meter with digital video frequency
CN109488888B (en) Metal pipeline leakage monitoring method based on infrared temperature field multivariate analysis
WO2017057780A1 (en) Data collection device, method, and program for display panel or control panel
CN111593151B (en) On-line detection method for depth of blast furnace tap hole
CN110570633A (en) chemical production process monitoring and early warning system based on VR technology
AU2014204524A1 (en) Flare stack monitoring
CN104680145A (en) Method and device for detecting door opening/closing state change
CN109724993A (en) Detection method, device and the storage medium of the degree of image recognition apparatus
JP2018077837A (en) Position recognition method and system, and abnormality determination method and system
CN108364306B (en) Visual real-time detection method for high-speed periodic motion
CN116168345B (en) Fire detection method and related equipment
RU2814807C1 (en) Method for automatic detection of operating condition, its system and storage medium for taphole for blast furnace
CN104281846A (en) Instrument data collecting method based on visual identity
CN116310121A (en) Digital twin system and method for slag skin of iron-making blast furnace
CN105095897A (en) Gradient image and similarity weight based digit identification method
JP2015130698A (en) Information output device, detection device, program, and information output method
CN112116195A (en) Railway beam production process identification method based on example segmentation

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 21881575

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 21881575

Country of ref document: EP

Kind code of ref document: A1