The “one-click steelmaking” – no intervention rate reaches more than 95%

In front of the converter steelmaking operation desk, the production staff holds the mouse and clicks the “Blow Start” button. The smart steelmaking system controls the oxygen lance to automatically lower and start blowing, materials are automatically added, bottom blowing is automatically controlled, and the oxygen lance is controlled according to the return to dryness and slag overflow. The actual furnace conditions are automatically adjusted to the gun position and the auxiliary gun is automatically measured, without manual intervention until the end of blowing;

Click the “Start Tapping” button, and the smart steelmaking system controls the tilting of the converter, the automatic follow-up of the ladle car, and the alarm and stop when tapping is abnormal. No manual intervention is required until the end of tapping… This is Shougang Jingtang Iron and Steel on February 25, 2024. The actual production scene of converter No. 8 in the rolling operation department. The converter smart steelmaking system has greatly improved the intelligence level of converter production and reduced the labour intensity of production personnel.

In February 2023, converter No. 8 in the steel rolling operation department began to realize automatic control of each step one after another; in August 2023, each functional module was put into use and completed linkage operation, finally realizing wireless terminal control of steelmaking. The converter smart steelmaking system realizes intelligent control of the entire process of converter blowing, steel tapping, slag splashing and slag tapping. The utilization rate exceeds 90%, and the process-free intervention rate is over 95%. After evaluation by the expert team, the system’s technical level has reached the international advanced level.


converter smelting, smart steelmaking


Realizing intelligent converter smelting has overcome many difficulties


For a long time, there have been problems such as the complex and changeable structure of the converter charge, the unstable composition of raw and auxiliary materials, the inability to monitor the reactions in the furnace in real-time, and the serious “black box” phenomenon, which mainly rely on the judgment and solution of personnel experience. Intelligentization of converter steelmaking operations is the current mainstream trend, but the research and development of converter smart steelmaking systems faces many difficulties:

The converter smelting process is a complex high-temperature physical and chemical reaction involving solid, liquid, and gas multi-phase substances in an open reactor, including multiple key stages such as blowing, tapping, slag splashing, and slag tapping. Each stage is interconnected. , but the actual furnace conditions and the content and methods of automatic control vary greatly;

There are many converter production control equipment, many types of materials, and many production media. The control of this equipment, the addition of materials, and the control of media all need to implement model calculation and automatic control;

Information such as sounds and images generated during the production process, as well as numerous data types such as distance, flow, weight, composition, and temperature measured by various sensors, all need to be incorporated into the computing model.


The converter smart steelmaking system has two major advantages:


1. Establish an advanced sensing system to realize intelligent control of the smelting process.


According to different scenarios, a variety of high-definition digital cameras are installed to monitor the entire converter smelting process. Visual recognition is used, combined with flue gas analysis, sonar, sub-gun detection, slag detection, sensors and other technologies to establish blowing, and tapping, The perception system for production process control such as slag splashing and slag discharging incorporates production information into the metallurgical model.

2. It is a combination of a deep learning model and a mechanism model to achieve intelligent control of the entire converter production process.


Deep learning methods are used to process image information at each stage of blowing, tapping, slag splashing, and slag discharging to realize the transformation of unstructured and non-indexed data into structured and indexed data; a static calculation model based on metallurgical mechanisms is used to decarbonize dynamic models, alloy calculation models, etc. are used to realize the calculation of process control parameters such as the amount of material added and the amount of oxygen added; the control model based on production control and safety regulations is used to realize automated control of the entire production process.

In terms of intelligent control of the converter-blowing process, the system uses image recognition as the core technology to comprehensively analyze the flame intensity at the taphole and furnace mouth to form a flame index. It integrates flue gas, sonar, and furnace mouth slag overflow information to form four major based on the judgment, the oxygen lance is controlled based on this, so that the converter blowing process is in an ideal and stable smelting state, and the problem of high probability of blowing splash and backdrying is solved. At the same time, good slagging improves the dephosphorization rate of the converter, and the phosphorus content in the final molten steel reaches a minimum of 0.003%.

In terms of intelligent control of the converter tapping process, the system uses image recognition as the core technology to identify the position of the converter ladle along the molten steel during the tapping process. At the same time, it calculates the “tapping flow rate per second” to determine the safety status of the tapping in real time to ensure that the tapping process is in the fastest tapping state under “maximum static pressure”, while ensuring the safety of the tapping process.

In terms of intelligent control of the converter slag splashing process, automatic control of slag splashing is achieved by combining static models with dynamic intelligent control. In the static stage, the slag splashing mode table is executed. After slagging, the slag particle parameters are identified according to the furnace mouth camera, and the gun position and material addition are dynamically adjusted to complete the slag splashing operation. By using the automatic slag splashing function, the slag splashing time is shortened by 18 seconds to 1 minute, and the slag splashing furnace protection effect is stable.

In terms of intelligent control of the converter slag discharging process, by calculating the corresponding relationship between the shaking angle of the furnace and the position of the slag tank truck, the tilting of the converter and the synchronous operation of the slag tank truck are controlled to ensure that the slag is poured into the slag tank; at the same time, the camera vision system is used to monitor the slag pouring situation. When the slag flow is abnormal, the switch control is promptly prompted to realize automatic slag discharge from the converter in a safe state. Through the automatic slag discharge function, the slag output under the furnace is reduced by 2.1 tons/day compared with before it was put into use, which reduces the frequency of cleaning the slag tanker truck and the slag under the furnace.

The converter smart steelmaking system realizes intelligent control of the entire process of converter blowing, steel tapping, slag splashing and slag discharging, transforming the original frequent manual control into computer-intelligent control. On-site operators can start automation with “one-click” control of the process and complete the smelting without intervention midway. The converter smart steelmaking system improves production stability and product stability, increasing the proportion of direct steel tapping by approximately 26%, shortening the smelting cycle by 2 minutes and 28 seconds, and reducing steel material consumption indicators by approximately 2.9 kg/ton.

Overall, the converter smart steelmaking system has improved the intelligence level of steelmaking production, achieved significant economic benefits, reduced the labour intensity of production personnel, and achieved good results in the fields of safety and environmental protection, becoming an intelligent steelmaking production system. This excellent example of application also marks that Shougang Jingtang has truly realized the “one-click steelmaking” converter intelligent smelting.

Leave a Reply

Your email address will not be published. Required fields are marked *

With machine vision as the core, DBM can provide intelligent equipment R&D, manufacturing and transformation services such as unmanned factories in the metallurgical industry and other industries, machine vision, and robot application design.

Find Your Plant

Tell us your needs and a technician will contact you immediately.

Customer testimonials

Friendship Link

We are committed to becoming a “leader in visual applications”, advocating the core values of “integrity, cooperation, innovation, expertise, and excellence”, taking the road of “technology shaping the brand, innovation leading the industry”, and attaching importance to the investment in scientific research and technology. The research and development of new products and the construction of the team make unremitting efforts for the goal of scientific and technological development.

We have been supplied to world’s top steel manufacturer Arcelormittal, TATA Steel, EZZ steel etc. We do OEM for Concast and Danieli for a long time

Metallurgical Intelligence
Change the way of manufacturing

Save labor, improve working environment, improve efficiency, reduce error rate and save cost!

Металлургический интеллект
Изменить способ производства

Сэкономьте труд, улучшите рабочую среду, повысьте эффективность, уменьшите количество ошибок и снизьте затраты!