Description:TECHNICAL FIELD
The present subject matter described herein, in general, relates to steelmaking, and more particularly to the process of oxygen blowing in steel making.

BACKGROUND
Primary steel is the basic form of steel to which various alloying agents are added to achieve a desired property grade. One of the main operations in steelmaking involves a Basic Oxygen Furnace (BOF) plant which is essentially a refining process used for converting pig iron into primary steel. During such refining process, oxygen is injected onto the molten iron from top, using a water-cooled lance to obtain the primary steel. The amount of oxygen required in steel making process is highly dynamic and depends primarily on the level of dissolved impurity present in the pig iron. Blowing inadequate oxygen results in higher impurity level in steel. Conversely, blowing extra oxygen causes increased dissolved oxygen in the molten steel bath which invites yield loss and higher processing cost in downstream operations.
Determining the exact oxygen volume has always been a problem. Availability of bath chemistry and temperature is not available throughout the process, and is obtained only after a sample is taken via a probe inserted after the blow end. Therefore, blow termination is dependent on an operator’s skill to stop the blow at the right moment which the operator manages by continuously observing readings of a waste gas analyser used for providing information of CO, CO2, and O2blown in the waste gas. The perception of the accurate end-point differs among the operators which increases chances of human error and leads to non-standardised process.
For estimating the oxygen volume, most of the conventional techniques rely on output of a device called Sublance, which is used for measuring temperature, carbon, and oxygen content of molten bath in-between the oxygen blowing process. US Patent 4474361 describes computing required oxygen by comparing a difference between estimated and actual slag oxygen content where the actual value is the output of a Sublance. US Patent 4150973 describes an elaborate formulation for predicting temperature and carbon in the bath by using Sublance parameters and could achieve an impressive hit rate of both the parameters. Chinese Patent102965462A describes a BOF endpoint automatic control device and control method using Sublance measurements, and predicting molten steel carbon content and molten steel temperature. Japanese Patent 2006233324A and Chinese Patent 101845531A describe similar principle as Chinese Patent 102965462A.
In view of the above stated problem, there arises a need to develop a system and a method using which an adequate amount of oxygen to be used in steel making process could be determined. Particularly, a system and a method that does not rely on Sublance measurements to predict steel carbon for Endpoint control are required.

SUMMARY
Before the present systems and methods for oxygen blow termination in steel making, are described, it is to be understood that this application is not limited to the particular systems, and methodologies described, as there can be multiple possible embodiments which are not expressly illustrated in the present disclosures. It is also to be understood that the terminology used in the description is for the purpose of describing the particular implementations or versions or embodiments only, and is not intended to limit the scope of the present application.
This summary is provided to introduce aspects related to a system and a method for oxygen blow termination in steel making. This summary is not intended to identify essential features of the claimed subject matter nor is it intended for use in determining or limiting the scope of the claimed subject matter.
In one implementation, a method for blow termination in steel making is disclosed. In one aspect, the method includes determining if Carbon value of molten iron has reached a predetermined carbon value defined on a Dynamic Carbon Curve (DCC). The DCC is dynamically set by a data model developed by learning upon details of several blowing processes. The method further includes providing a signal to a lance for oxygen blow termination when the carbon value on the DCC reaches the predetermined Carbon Value.
A DCC may be prepared based on hot metal chemistry of carbon and silicon, oxygen blown, TBM flow rate, venturi opening, and feature engineered Blow Termination Index (BTI) variables. The BTI is determined using Waste Gas CO, Waste Gas CO2, and Waste Gas Temperature.
In another implementation, a system for blow termination in steel making is disclosed. In one aspect, the system includes a plurality of devices connected in a hierarchical manner to collect and process data received from a Basic Oxygen Furnace (BOF) plant. The plurality of devices are programmed to determine if Carbon value of molten iron has reached a predetermined carbon value defined on a Dynamic Carbon Curve (DCC). The DCC is dynamically set by a data model developed by learning upon details of several blowing processes. The plurality of devices are further programmed to provide a signal to a lance for blow termination when the carbon value on the DCC reaches the predetermined Carbon Value.
The plurality of devices may prepare a DCC based on hot metal chemistry of carbon and silicon, oxygen blown, TBM flow rate, venturi opening, and feature engineered Blow Termination Index (BTI) variables. The BTI is determined using Waste Gas CO, Waste Gas CO2, and Waste Gas Temperature.

BRIEF DESCRIPTION OF THE DRAWINGS
The foregoing detailed description of embodiments is better understood when read in conjunction with the appended drawings. For the purpose of illustrating of the present subject matter, an example of construction of the present subject matter is provided as figures; however, the invention is not limited to the specific method and system disclosed in the document and the figures.
The present subject matter is described in detail with reference to the accompanying figures. In the figures, the left-most digit(s) of a reference number identifies the figure in which the reference number first appears. The same numbers are used throughout the drawings to refer various features of the present subject matter.
Figure 1 illustrates a connection diagram of a system for oxygen blow termination in steel making, in accordance with an embodiment of the present subject matter.
Figure 2 illustrates a flow chart of a method for oxygen blow termination in steel making, in accordance with an embodiment of the present subject matter.
Figure 3 illustrates progression of Blow Termination Index (BTI) and Dynamic Carbon Curve with blowing process, in accordance with an embodiment of the present subject matter.

DETAILED DESCRIPTION
Some embodiments of this disclosure, illustrating all its features, will now be discussed in detail. The words "comprising," "having," "containing," and "including," and other forms thereof, are intended to be equivalent in meaning and be open ended in that an item or items following any one of these words is not meant to be an exhaustive listing of such item or items, or meant to be limited to only the listed item or items. It must also be noted that as used herein and in the appended claims, the singular forms "a," "an," and "the" include plural references unless the context clearly dictates otherwise. Although any systems and methods for modifying data cleansing techniques for oxygen blow termination in steel making, similar or equivalent to those described herein can be used in the practice or testing of embodiments of the present disclosure, the exemplary, systems and methods for oxygen blow termination in steel making are now described. The disclosed embodiments for blow termination in steel making are merely examples of the disclosure, which may be embodied in various forms.
An automated method of blowing optimum oxygen is described by current invention. An end-point is determined using a predetermined carbon value on a Dynamic Carbon Curve (DCC)(). The DCC is derived using hot metal chemistry of carbon and silicon, oxygen blown, TBM flow rate, venturi opening, and feature engineered Blow Termination Index (BTI) variables. The BTI is dependent on the waste gas parameters such as CO and CO2 concentration and hood temperature. The invention describes automation of oxygen lance, designed to stop the blow based on the attaining pre-determined carbon value on the DCC. A statistical self-tuning algorithm for attaining the threshold predetermined carbon value on DCC is devised to tackle the problem of long-term as well as short term process/equipment drifts, and to ensure meeting desired carbon content in steel. Using feature engineering techniques on BTI and other important input parameters like Hot metal chemistry, oxygen, etc, current invention predicts the end-point bath carbon content with a hit rate of 89% in ±0.01% of actual carbon achieved.
Referring now to Figure 1, a connection diagram 100 of a system for oxygen blow termination in steel making, in accordance with an embodiment of the present subject matter may be described.
The connection diagram 100 includes a Basic Oxygen Furnace (BOF) plant 102 connected with a level1 Programmable Logic Controller (PLC) 104. The level1 PLC 104 monitors the steel making operation going on inside the BOF plant 102. The level1 PLC 104 is further connected to an OPC server 106. The OPC server 106 functions as a link between thelevel1 PLC 104 and a level2 automation server 108. The OPC server 106 comprises two sub-modules, a read module and a send module. The read module fetches data at predefined intervals, such as 3 seconds via OPC communication from level1 PLC 104. The send module is a TCP/IP client program that sends the 3seconds data to the level2 automation server 108.
The level2 automation server 108 comprises two sub-modules, a receive module and a send module. The receive module receives the 3seconds data and invokes a database module of a database 110. The send module relays instructions related to oxygen set-point and blow termination from the database module to a write module of the OPC server 106.
The database module of the database 110 includes a procedure that writes the 3seconds data to tables. The database module also invokes the DCC module and transmits its output to the write module of the OPC server 106 via the send module of the level2 automation server 108, for automatic blow termination. The database module is also used by HMI module for continuously displaying results on a user device 112. The database 110 further includes a /DCC Module which is a DB function containing/DCC algorithm. The DCC Module collects the data at 3seconds interval from the database module, processes the data, and generates the Dynamic Carbon Curve (DCC).
The OPC server 106 also includes an OPC write module which consists of 2 sub-modules, a communication healthiness module and an OPC write module. The communication healthiness module ensures healthy OPC communication and generates alarms in cases of outage. The OPC write module receives the oxygen set points and DCC values from the send module of the level2 automation server 108, and writes them into command tags of the PLC 104 for execution.
A user device 114 includes an HMI module that acts a web server for hosting webpages. A user may connect to web output of the web server and can visualise progress of the oxygen blowing process.
It should be understood that the OPC server 106, the level2 automation server 108, the user device 112, and the user device 114 correspond to computing devices. It may be understood that the OPC server 106, the level2 automation server 108, the user device 112, and the user device 114 may also be implemented in a variety of computing systems, such as a laptop computer, a desktop computer, a notebook, a workstation, a mainframe computer, a server, a network server, a cloud-based computing environment, or a mobile and the like.
In one implementation, the OPC server 106, the level2 automation server 108, the user device 112, and the user device 114 may be connected with each other using a communication network that may be a wireless network, a wired network, or a combination thereof. The communication network can be implemented as one of the different types of networks, such as intranet, Local Area Network (LAN), Wireless Personal Area Network (WPAN), Wireless Local Area Network (WLAN), wide area network (WAN), the internet, and the like. The communication network may either be a dedicated network or a shared network. The shared network represents an association of the different types of networks that use a variety of protocols, for example, MQ Telemetry Transport (MQTT), Extensible Messaging and Presence Protocol (XMPP), Hypertext Transfer Protocol (HTTP), Transmission Control Protocol/Internet Protocol (TCP/IP), Wireless Application Protocol (WAP), and the like, to communicate with one another. Further, the communication network may include a variety of network devices, including routers, bridges, servers, computing devices, storage devices, and the like.
The memory of the database 110, amongst other things, serves as a repository for storing data processed, received, and generated by one or more of modules. The memory may include any computer-readable medium or computer program product known in the art including, for example, volatile memory, such as Static Random Access Memory (SRAM) and Dynamic Random Access Memory (DRAM), and/or non-volatile memory, such as Read Only Memory (ROM), Erasable Programmable ROM (EPROM), Electrically Erasable and Programmable ROM (EEPROM), flash memories, hard disks, optical disks, and magnetic tapes.
In one implementation, data related to all variables that might impact the carbon concentration in steel was collected. Such data was collected for a sufficient time period, for example 3 months. Such data was screened to remove any inconsistencies or aberrations. Missing data was imputed using explicit modelling approach. Depending on a type and predictability of data, it was either imputed with its mean or with its regression(-ally) derived substitute. After cleaning the data and treating of missing data, several new features were engineered depending on the nature of the attribute. For example, data comprised both continuous and batch-wise categories. From continuous data like waste gas generation profiles, various information such as mean, median, area, and slopes were extracted and feature engineering approaches such as time-averaging and data binning were applied. New features obtained through the feature engineering were appended with existing data set to obtain a final dataset. Blow Termination Index (BTI) is one such feature that is derived through the feature engineering.
On the final dataset, variable correlation was checked to remove highly correlated predictor attributes. On 70% of the final dataset, a Regression Machine Learning algorithm was trained to develop a data model alternatively referred as Dynamic Carbon Curve. Remaining 30% of the final dataset was tested on the data model to study its accuracy. The curve was validated on another one month dataset which was different from the set on which the curve was developed and tested.
Referring now to Figure 2, a method 200 for oxygen blow termination in steel making is described, in accordance with an embodiment of the present subject matter. The method 200 may be described in the general context of computer executable instructions. Generally, computer executable instructions can include routines, programs, objects, components, data structures, procedures, modules, functions, etc., that perform particular functions or implement particular abstract data types.
The order in which the method 200 for oxygen blow termination in steel making is described is not intended to be construed as a limitation, and any number of the described method blocks can be combined in any order to implement the method 200 or alternate methods. Additionally, individual blocks may be deleted from the method 200 without departing from the spirit and scope of the subject matter described herein. Furthermore, the method can be implemented in any suitable hardware, software, firmware, or combination thereof. However, for ease of explanation, in the embodiments described below, the method 200 may be considered to be implemented in the above described system.
At block 202, communication healthiness of connected and dependent systems is determined. Signalling between command giving and command executing systems is periodically determined using TCP/IP server-client applications. In case a problem or outage occurs, blowing process may be interrupted and/or alarms may be generated, at block 204. Once all the communication is identified to be functioning properly, starting of the blowing process may be determined, at block 206. Real time capturing of data may be stopped at block 208, when blow is not started. When blow is identified to be started at block 206, data of important process as well as waste gas analyser parameters is captured in a real-time, at predefined intervals, such as every 3 seconds, at block 210. Such data is captured till end of the blowing process, and is stored in a database.
At block 212, it is determined if difference of Oxygen Set-point and Current Oxygen is greater than 300 Nm3. Thereupon, it will be determined if Carbon value of molten iron has reached a predetermined carbon value defined on the DCC, at block 214.
At block 212, if it is determined that the difference of Oxygen Set-point and Current Oxygen is lesser than 300 Nm3, then the Oxygen set point may be raised by another 500Nm3, and oxygen will be kept on blowing, at block 216.
It should be appreciated that the thresholds of 300Nm3and 500 Nm3 utilized at blocks 212 and 216 depends on case to case basis and can be varied as per the requirement.
The DCC is expressed by:
DCC = f(hot metal chemistry of carbon and silicon,oxygen blown, TBM flow rate, venturi opening, and feature engineered Blow Termination Index (BTI) variables)
And
BTI=f(Waste Gas CO, Waste Gas CO2, and Waste Gas Temperature)
If carbon value of molten iron has not reached a predetermined carbon value defined on a DCC, the blowing of the oxygen will continue till the value is achieved. Once the carbon value is achieved, a trigger signal to Lance will be sent to blow the termination, at block 218.
Figure 3 illustrates progression of BTI and DCC with Blowing process. Using a pre-set oxygen value, DCC is invoked which generates the predicted carbon value till an end of the blowing process. As soon as the carbon value of molten iron has reached a predetermined carbon value DCC value, , the blowing process is terminated through a series of commands executed by the software module architecture. Fig. 3 also shows the actual carbon achieved in the process which is approximately equal to the predicted carbon at the end of the blowing process. One can witness the minimal difference of Actual Carbon value and the Predicted Carbon value in the FIG. 3.
In some embodiments, DCC may be predicted continuously near an end of the blowing process, for example around 80% completion of the blowing process.DCC is a function of several parameters as mentioned through below equation.
DCC =f( Hot Metal Chemistry(Carbon,Silicon),Oxygen Blown,TBM flow rate,
venturi opening,feature engineered BTI variables)
BTI is a function of several parameters mentioned in the below equation.
BTI = f (Waste Gas CO, Waste Gas CO2, and Waste Gas Temperature)
Although implementations for methods and systems for oxygen blow termination in steel making have been described in language specific to structural features and/or methods, it is to be understood that the appended claims are not necessarily limited to the specific features or methods described. Rather, the specific features and methods are disclosed as examples of implementations for blow termination in steel making.

Claims:WE CLAIM:
1. A method for oxygen blow termination in steel making, the method comprising:
determining if Carbon value of molten iron has reached a predetermined carbon value defined on a Dynamic Carbon Curve (DCC), the DCC being dynamically set by a data model developed by learning upon details of several blowing processes; and
providing a signal to a lance for oxygen blow termination when the carbon value on the DCC reaches the predetermined Carbon Value.

2. The method as claimed in claim 1, wherein the DCC is based on hot metal chemistry of carbon and silicon, oxygen blown, TBM flow rate, venturi opening, and feature engineered Blow Termination Index (BTI) variables.

3. The method as claimed in claim 2, wherein the BTI is determined using Waste Gas CO, Waste Gas CO2, and Waste Gas Temperature.

4. A system for blow termination in steel making, the system comprising:
a plurality of devices connected in a hierarchical manner to collect and process data received from a Basic Oxygen Furnace (BOF) plant, wherein the plurality of devices are programmed to perform steps of:
determining if Carbon value of molten iron has reached a predetermined carbon value defined on a Dynamic Carbon Curve (DCC), the DCC being dynamically set by a data model developed by learning upon details of several blowing processes; and
providing a signal to a lance for blow termination when the carbon value on the DCC reaches the predetermined Carbon Value.

5. The system as claimed in claim 5, wherein the DCC is based on hot metal chemistry of carbon and silicon, oxygen blown, TBM flow rate, venturi opening, and feature engineered Blow Termination Index (BTI) variables.

6. The system as claimed in claim 5, wherein the BTI is determined using Waste Gas CO, Waste Gas CO2, and Waste Gas Temperature.