FORM 2
THE PATENTS ACT, 1970 (39 of 1970) & THE PATENTS RULES, 2003
COMPLETE SPECIFICATION (See section 10, rule 13) 1. Title of the invention: SYSTEM AND METHOD FOR THERMAL MONITORING AND
PROVIDING ADVISORY CONTROL FOR STEEL LADLE OPERATIONS
2. App lica nt(s)
NAME NATIONALITY ADDRESS
TATA CONSULTANCY Indian Nirmal Building, 9th Floor,
SERVICES LIMITED Nariman Point, Mumbai,
Maharashtra 400021, India
3. Preamble to the description
COMPLETE SPECIFICATION
The following specification describes the invention and the manner in which it is to be
performed.

TECHNICAL FIELD
[0001] The disclosure herein generally relate to ladle operations, and
more particularly, to thermal monitoring and providing advisory control for ladle operations.
BACKGROUND
[0002] Generally, ladles are used to maneuver chemical composition,
inclusion content and temperature of liquid steel in secondary steel making in a steel plant. Ladle is a vessel made up of steel shell and refractory layers that holds and facilitates the processing of liquid steel. Ladle operations are broadly categorized into two sets – (i) refining operations, where chemistry, cleanliness and temperature are adjusted and (ii) transport operations, that involve tapping of molten metal into the ladle and other ladle steel operations like holding and teeming operations. Total duration of the ladle operations is often long and leads to significant heat loss from the liquid steel. Disproportionate superheat of liquid steel at caster may result in problems such as caster-strand breakout or nozzle clogging. Superheat is difference between the temperature of liquid steel at the caster and a corresponding liquidus temperature of the steel. The liquidus temperature is the temperature above which steel remains in completely liquid form. FIG. 1 illustrates a schematic flow of ladle operations in a typical secondary steel making cycle. The ladle operations in secondary steel making include multiple processes

like tapping, refining, holding, teeming and waiting. The ladle used for the first time in ladle operations is called as a green ladle. Green ladle is pre¬heated to a required temperature before initiating the tapping procedure. Inadequate liquid steel temperature before the teeming operation may require the ladle to be sent for re-arcing, that causes significant revenue losses for the steel plant. On the other hand, excessive liquid steel temperature may delay the ladle teeming, wastage of energy, reduced productivity and hamper the continuity of the casting process. The heat loss occurring during the transfer processes post refining operation, that is during holding and teeming is critical in maintaining the desired range of caster superheat. Monitoring and sound control of temperature is required during the ladle operations to meet the caster superheat requirements for a good quality product. A large number of ladles are circulating in the plant simultaneously, each at a different thermal state owing to the processes. After teeming process is completed in a ladle, the ladle is cleaned and then put for re-use depending upon the requirement. The waiting time post the teeming has a profound effect on the heat carried by the ladle refractory that affects the next cycle.
[0003] Therefore there is a need for monitoring the temperature of the
liquid and the refractory layers of all the ladles in a steel plant continuously to ensure efficient operation of ladle. This monitoring and knowledge of heat loss is also vital for providing advisory control such as assisting the selection of the ladle from the available ladles for the next cycle of process in ladle

operations as well as ensuring proper casting superheat by controlling the arcing intensity and duration as per the anticipated heat losses.
SUMMARY
[0004] Embodiments of the present disclosure present technological
improvements as solutions to one or more of the above-mentioned technical problems recognized by the inventors in conventional systems. For example, in one embodiment, a method for thermal monitoring and providing advisory control for ladle operations is disclosed. The method includes collecting geometrical and operational data related to one or more ladles and liquid steel in a steel plant. Further, a plurality of computational models are generated and integrated based on the geometrical and operational data. Furthermore, one or more influential parameters of the ladle steel operations that affect temperature of liquid steel at various stages of the ladle operations are identified through a systematic parametric study using the integrated computational models. Subsequently, one or more mathematical operational rules are generated for prediction and control of the temperature of the liquid steel and the ladles based on the integrated computational models. Subsequently, surrogate models based on the influential parameters for predicting at least one of (a) liquid steel temperature and (b) refractory temperature of the plurality of ladles (c) heat loss in liquid steel during a specific ladle operation are generated based on the integrated computational models and the mathematical operational rules by considering at least one of

a refractory thermal status and a ladle cycling status/heat number. Further from the generated surrogate models, thermal monitoring and advisory control are provided for ladle operations.
[0005] In another embodiment, a system for thermal monitoring and
providing advisory control for ladle operations is disclosed. The system includes at least one processor, and a memory communicatively coupled to the at least one processor, wherein the memory comprises of several modules. The modules include, a surrogate generation module that receive geometrical and operational data related to one or more ladles in a steel plant. Further, a plurality of computational models are generated and integrated based on the geometrical and operational data. Furthermore, one or more influential parameters of the ladle steel operations that affect temperature of liquid steel at various stages of the ladle operations are identified through a systematic parametric study using the integrated computational models. Subsequently, one or more mathematical operational rules for prediction and control of the temperature of the liquid steel and the ladles based on the integrated computational models. Subsequently, surrogate models for the influential parameters for predicting at least one of (a) liquid steel temperature and (b) refractory temperature of the plurality of ladles (c) heat loss in liquid steel during a specific ladle operation are generated based on the integrated computational models and the mathematical operational rules by considering at least one of a refractory status and a cycling status. The system further consist of a steel thermal monitoring module for providing a real time

monitoring for liquid steel temperature for at least one casting line based on the surrogate models and the mathematical operational rules. The system further consists of a ladle thermal tracking module for selecting a ladle from one or more ladles based on the surrogate models and the thermal tracking module and an arcing advice module for arcing advice for the selected ladle based on the surrogate models and the thermal tracking module.
[0006] It is to be understood that both the foregoing general description
and the following detailed description are explanatory only and are not restrictive of the invention, as claimed.

BRIEF DESCRIPTION OF THE DRAWINGS
[0007] The accompanying drawings, which are incorporated in and
constitute a part of this disclosure, illustrate exemplary embodiments and,
together with the description, serve to explain the disclosed principles:
[0008] FIG. 1 illustrates a schematic flow of ladle operations in a typical
secondary steel making;
[0009] FIG. 2 illustrates a system for thermal monitoring and providing
advisory control for ladle operations, according to some embodiments of the present subject matter;
[0010] FIG. 3 illustrates a schematic flow of integrated modeling of ladle
operations, according to some embodiment of the present subject matter;
[0011] FIG. 4 is a flow chart explaining the method for identifying
influential parameters and building a knowledge database for generating mathematic operational rules, according to some embodiments of the present subject matter;
[0012] FIG. 5 illustrates a flowchart for the method of creating a
surrogate model for predicting the liquid steel temperature, according to some embodiment of the present subject matter;

[0013] FIG. 6 illustrates a side view of refractory layer of a ladle and the
variations of temperature at different locations, according to some embodiment of the present subject matter;
[0014] FIG. 7 shows a schematic of the user inputs and predicted outputs
of real-time monitoring system, according to some embodiment of the present subject matter;
[0015] FIG. 8 is an illustration for selecting a ladle from available ladles
in steel making, according to some embodiment of the present subject matter;
[0016] FIG. 9 is a flow chart explaining the advisory arcing decision
making, according to some embodiment of the present subject matter; and
[0017] FIG. 10 is a flow chart illustrating a method for thermal
monitoring and providing advisory control for ladle operations, according to some embodiment of the present subject matter.

DETAILED DESCRIPTION OF EMBODIMENTS
[0018] Exemplary embodiments are described with reference to the
accompanying drawings. In the figures, the left-most digit(s) of a reference number identifies the figure in which the reference number first appears. Wherever convenient, the same reference numbers are used throughout the drawings to refer to the same or like parts. While examples and features of disclosed principles are described herein, modifications, adaptations, and other implementations are possible without departing from the spirit and scope of the disclosed embodiments. It is intended that the following detailed description be considered as exemplary only, with the true scope and spirit being indicated by the following claims.
[0019] System and method for thermal monitoring and providing
advisory control for steel ladle operations is disclosed. The system can be implemented in a variety of computing devices. The computing devices that can implement the described system include, but are not limited to, desktop computers, laptops or other portable computers, multiprocessor systems, microprocessor based programmable consumer electronics, laptops, network computers, minicomputers, mainframe computers, and the like. Although the description herein is with reference to certain computing systems, the system may be implemented in other devices, albeit with a few variations, as will be understood by a person skilled in the art.

[0020] In the present disclosure, system and method for thermal
monitoring and providing advisory control for steel ladle operations is disclosed. The method includes collecting geometrical and operational data of one or more ladles. Further, computational models are generated for all the processes involved in secondary steel making based on the collected geometrical and operational data and subsequently integrating the computational models. Subsequently, sensitivity analysis is performed to identify one or more influential parameters using the integrated computational models. Further mathematical operational rules are generated and surrogated models are generated for predicting the arcing intensity and duration required for maintaining liquid steel temperature during a specific ladle operation. Based on the surrogated models obtained, thermal monitoring and advisory control is provided for the ladle operations.
[0021] The manner in which the described system is implemented to
enable thermal monitoring and providing advisory control for ladle operations
has been explained in detail with respect to the following figures. While
aspects of the described system can be implemented in any number of
different computing systems, transmission environments, and/or
configurations, the embodiments are described in the context of the following exemplary system.
[0022] FIG. 2 schematically illustrates a system 200 for thermal
monitoring and providing advisory control for steel ladle operations, according to an embodiment of the present disclosure. As shown in FIG. 2,

the system 200 includes one or more processor(s) 202 and a memory 204 communicatively coupled to each other. The memory 204 includes a surrogate model generation module 206, a steel thermal monitoring module 208, a ladle thermal tracking module 210, a ladle select assist module 212 and an arcing advice module 214. The surrogate model generation module 206 generates surrogate models for the influential parameters for predicting at least one of (a) liquid steel temperature and (b) refractory temperature of the plurality of ladles (c) heat loss in liquid steel during a specific ladle operation. In an example, the influential parameters include initial ladle thermal status, waiting time, holding time, chemical additional and others parameters. The method for determining influential parameters is explained in FIG. 4. The steel thermal monitoring module 208 monitors the liquid steel in the ladle operations. The ladle thermal tracking module 210 tracks all the ladles present in the steel plant. The ladle select assist module 212 assists in selecting the ladle for the next cycle of secondary steel making operations from the available ladles. The arcing advice module 214 provides the arcing heat input required for the selected ladle, so as to ensure proper steel temperature. The modules, surrogate model generation module 206, steel thermal monitoring module 208, ladle thermal tracking module 210, ladle select assist module 212 and arcing advice module 214 are explained in detail in the following specification.
[0023] The system 200 also includes interface(s) 216. Although FIG. 2
shows example components of the system 200, in other implementations, the

system 200 may contain fewer components, additional components, different
components, or differently arranged components than depicted in FIG. 2.
[0024] The processor(s) 202 and the memory 204 may be
communicatively coupled by a system bus. The processor(s) 202 may include circuitry implementing, among others, audio and logic functions associated with the communication. The processor 202 may include, among other things, a clock, an arithmetic logic unit (ALU) and logic gates configured to support operation of the processor(s) 202. The processor(s) 202 can be a single processing unit or a number of units, all of which include multiple computing units. The processor(s) 202 may be implemented as one or more microprocessors, microcomputers, microcontrollers, digital signal processors, central processing units, state machines, logic circuitries, and/or any devices that manipulate signals based on operational instructions. Among other capabilities, the processor(s) 202 is configured to fetch and execute computer-readable instructions and data stored in the memory 204.
[0025] The functions of the various elements shown in the figure,
including any functional blocks labeled as “processor(s)”, may be provided through the use of dedicated hardware as well as hardware capable of executing software in association with appropriate software. When provided by a processor, the functions may be provided by a single dedicated processor, by a single shared processor, or by a plurality of individual processors, some of which may be shared. Moreover, explicit use of the term “processor” should not be construed to refer exclusively to hardware capable

of executing software, and may implicitly include, without limitation, digital signal processor (DSP) hardware, network processor, application specific integrated circuit (ASIC), field programmable gate array (FPGA), read only memory (ROM) for storing software, random access memory (RAM), and non-volatile storage. Other hardware, conventional, and/or custom, may also be included.
[0026] The interface(s) 216 may include a variety of software and
hardware interfaces, for example, interfaces for peripheral device(s), such as a
keyboard, a mouse, an external memory, and a printer. The interface(s) 216
can facilitate multiple communications within a wide variety of networks and
protocol types, including wired networks, for example, local area network
(LAN), cable, etc., and wireless networks, such as Wireless LAN (WLAN),
cellular, or satellite. For the purpose, the interface(s) 216 may include one or
more ports for connecting the system 200 to other network devices.
[0027] The memory 204 may include any computer-readable medium
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, flash memories, hard disks, optical disks, and magnetic tapes. The memory 204, may store any number of pieces of information, and data, used by the system 200 to monitor ladles and provide advisory control. The memory 204 may be configured to store information, data, applications, instructions or the like for system 200 to carry out various

functions in accordance with various example embodiments. Additionally or alternatively, the memory 204 may be configured to store instructions which when executed by the processor 202 causes the system 200 to behave in a manner as described in various embodiments The module 206 include routines, programs, objects, components, data structures, etc., which perform particular tasks or implement particular abstract data types.
[0028] In an embodiment, the surrogate model generation module 206 is
disclosed. In the surrogate model generation module 206, the geometrical and
operational data of all the existing ladles in the steel plant are collected. The
geometrical and operational data includes the design details of all the ladles
including the refractory layers and the dimensions of the refractory layers.
The examples of design details for ladles include, but are not limited to,
diameter of ladle, height of the ladle, capacity of the ladle, thickness and
materials of the refractory layer. The geometrical and operational data further
includes ladle construction material details and typical ranges of operational
parameters like preheating temperature, steel height, durations of different
operations, incoming liquid steel temperatures from primary steel making like
basic oxygen furnace (BOF), desired output temperatures, slag weight, etc.
[0029] Subsequently, a plurality of computational models are developed
for each individual process in secondary steel making based on the geometrical and operational data received. The computational models are utilized to predict the liquid steel temperature and refractory temperature variation in space and time for given input process parameters of the ladle.

The computational models may include geometry creation, meshing, numerical solution, post-processing the results and validation with experimental measurements. The computational models are further validated with respect to the plant measurements. The computational models are subsequently integrated and an integrated model. The integrated model allows (i) a study of interdependence of influential parameters in single cycle and (ii) to analyze the effect of ladle parameters in temperature between different cycles of different ladle operations. The present disclosure takes a holistic approach and integrates the models of each of the ladle operations together to study and extract required information. The method of integration of different cycles include integrating output of first ladle process as an input to the second ladle process or output of second ladle process as an input to the first ladle process. FIG. 3 illustrates a schematic flow of integrated modelling of ladle operations of different cycles. Integrated model not only allows study of interdependence of parameters in single cycle but also allows us to study and analyze the effect of ladle parameters of the first cycle on the steel temperature of the second cycle. For example, the refractory temperature distribution predicted by a waiting model in cycle 1 is used as initial refractory temperature distribution for the tapping model in cycle 2. Similarly, the models are integrated with each other in sequence. This allows to deduce the effect of a parameter such as waiting time in cycle 1 on the teeming steel temperature in cycle 2. The integration of models with each other makes the computational workflow re-usable and enables easy to plug-

and-play of different models. The integrated workflow is re-used repeatedly depending upon the circulation of ladle.
Building knowledge database:
[0030] In an embodiment, influential parameters that affect the ladle
operations are identified by the integrated computational models. A
knowledge database comprising one or more operational mathematical rules
is built for the influential parameters. In an embodiment, FIG. 4 is a flow
chart 400 explaining the method for identifying influential parameters and
building a knowledge database for generating mathematical operational rules.
At block 402, influential input parameters are identified. At block 404,
sensitivity of final temperature is analyzed for each parameter using
integrated computational model. Subsequently, at block 406, key knowledge
elements affecting the final output steel temperature are identified. At block
408, key knowledge rules are formulated for quantifying the effect
mathematically. The method for identifying key knowledge elements and
formulating key knowledge rules is explained in the following embodiments.
[0031] In an embodiment, a method for identifying influential parameters
is disclosed. At various stages of ladle operations, one or more parameters affect the liquid steel temperature at various stages of ladle. The one or more parameters that affect the liquid steel temperature are called as influential parameters. The influential parameters are identified for each ladle by

performing sensitivity analysis. In an embodiment, the method for sensitivity analysis includes analyzing effect and evolution of refractory temperature profile on the liquid steel temperature. Initially, a new ladle at room temperature is considered and a preheating model is used to estimate the final temperature profile for a given hot face temperature.
[0032] Generally, the influential parameters include incoming initial
refractory thermal status of empty ladle, liquid steel temperature from BOF (Basic Oxygen Furnace), time periods of different ladle operations, types of chemical additions and amounts of chemical additions, amount of arcing and slag weight among others. After identifying the influential parameters, integrated simulations are run to find the sensitivity of liquid steel temperature to the influential parameters. The sensitivity is determined by varying each parameter over a chosen range and keeping all the other parameters at constant and subsequently, the variation in the final steel temperature is observed. The variation in all the influential parameters is considered to segregate the influential parameters that have high influence on the liquid steel temperature and influential parameters that have negligible influence on the liquid steel temperature. The influential parameters with high influence are considered for further analysis and the influential parameters with negligible influence are disregarded.
[0033] In an example embodiment, a final temperature profile is obtained
at the end of preheating period. The final temperature profile obtained at the end of preheating period is used as an initial condition for tapping. The other

influential parameters are kept as constant till the end of teeming. Teeming is the process where the liquid steel is tapped from the bottom of the ladle into the tundish for casting. The simulation is run a number of times for different preheating temperature (hot face temperature) while other parameters are maintained at constant to analyze the effect of pre-heating on the final liquid steel temperature. To assess the effect of refractory temperature on the liquid steel temperature in case of a circulating ladle, the temperature profile of the refractory at the end of teeming period is used as an initial condition for the waiting period and the integrated simulations are run again for entire cycle of ladle operations. Further, a fixed amount of thickness is reduced after every fixed number of ladle circulations, to represent the wearing of the refractory layer. Such sensitivity analysis is performed on different ladles in the steel plant. Generally, all the ladles in the steel plant have similar characteristics. However if all the ladles in the steel plant are not with same characteristics, one or more models are built for performing sensitivity analysis to analyze the effect of refractory of ladle in circulation.
[0034] Subsequently, in another embodiment, key observations from
computational study are taken and put into mathematical rules and knowledge in the advisory control mechanism as well as real-time monitoring system. The examples for key knowledge elements are provided below.
1. Holding time, waiting time, teeming rate, slag thickness and arcing have profound effect on the liquid steel streaming

temperature and the heat loss in the liquid steel at various operations.
2. The initial status of refractory of a ladle (at the end of teeming in previous cycle) which is in circulation does not have large influence on the steel streaming temperature, if the waiting time during maintenance in current cycle is more than 30 minutes. In other words, the effect of the refractory temperature post teeming in last cycle has limited effect on the liquid steel heat loss in the next cycle. This is a key finding which comes from computational studies and is very useful in advisory control for arcing.
3. Another knowledge element example is that, if the ladle is not in circulation and is preheated from green state, then more losses take place and the heat loss varies with degree of preheating.
4. Another important knowledge element is though the heat lost by steel due to colder initial state of refractory during tapping can be made up during arcing, the heat loss during the holding and teeming is largely affected by the initial status of the refractory. Therefore, arcing decision should take into account not only the current steel and refractory temperatures but also the refractory initial status at the start of the tapping operation of the current cycle.
[0035] A generic relationship between key knowledge elements like
initial ladle thermal status, waiting time, slag weight, holding time and

teeming rate can be quantified using computational models. For determining a generic relationship of a given casting line, the BOF temperature and typical duration of tapping, refining are considered as similar. The relationship is generated in the form of a function below. For a ladle not in circulation, the relationship is as follows.
ΔT holding-teeming = fn1 (initial ladle thermal status, waiting time, slag weight, holding time, teeming rate) However, if the ladle is in circulation, the effect of initial thermal status of refractory is diminished, hence the relationship for a ladle that is in circulation is given below.
ΔT holding-teeming = fn2 (heat number, waiting time, slag weight, holding time, teeming rate) Such rules derived from the sensitivity/parametric study using integrated computational models are further used in formulating the surrogate models for prediction of heat loss, liquid steel temperature or the refractory temperature profile.
[0036] The knowledge of effect of a particular parameter in a particular
situation helps in reducing the effort required for developing rules and prediction module. For example, the exact knowledge of effect of refractory initial status on the current steel cycle, in two cases; 1) ladle in circulation 2) preheated ladle, simplifies the thermal predictor module development. Such insights also reduce the amount of data required for developing the model. Pure data based models (without any knowledge elements) may need large

amounts of data (experimental or computational). Utilizing the knowledge created above reduces the data requirement for building the rules and computational prediction models.
Building surrogate models
[0037] In an embodiment, a large number of simulations are run using
design of experiment technique (example – full factorial or Taguchi) and data is extracted to find the deterministic function fn mentioned above using techniques like a multivariate regression technique. These functions are the surrogate models which predict the liquid steel temperature, heat loss or refractory temperature for given influential parameters in real or near real¬time.
[0038] In an embodiment, one or more surrogate models are built to
predict the liquid steel temperature, temperature of refractory ladle and the
heat loss in liquid steel during a specific ladle operation. The surrogate
models are generated based on the integrated computational models and the
mathematical operational rules. In an embodiment the surrogate models also
include considering at least one of a refractory status and a cycling status.
[0039] In an embodiment of the present subject matter, a method for
building one or more surrogate models for predicting liquid steel temperature is disclosed. The liquid steel temperature prediction is used to monitor the ladle operations. In an embodiment, a surrogate model for liquid steel

temperature prediction is built based on the knowledge gathered using computational models that provide the liquid steel temperature at a given point of time as a function of process parameters.
[0040] FIG. 5 is a flow chart 500 explaining the method of creating a
surrogate model for the liquid steel temperature prediction. At block 502, a
range of values for key input parameters are identified. At block 504, input
set of experiments is generated using the design of experiment techniques. At
block 506, output steel temperature data is generated by utilizing design of
experiments using integrated computational module. At block 508,
relationship formulation fn is formulated between output and input
parameters using multivariate regression or a similar technique. At block 510,
the fn is used to test sample cases against results of computational models.
[0041] A (generic) relationship is quantified using computational models,
assuming, that for a given casting line, the BOF temperature and typical duration of tapping, refining remain similar, -For a green preheated ladle,
Tsteel_teeming = fn3 (initial ladle thermal status, waiting time, slag weight, holding time, teeming rate)
The initial thermal status here in case of preheated ladle is expressed in terms of hot face temperature of the ladle. However, if the ladle is in circulation, the effect of initial thermal status of refractory is diminished (based on knowledge gathered during the previous step), hence

Tsteel_teeming = fn4 (heat number, waiting time, slag weight, holding time, teeming rate)
[0042] In the above mentioned processes, the knowledge obtained related
to effects of input process parameters like refractory thermal status and cycling status are considered to build the surrogate models. A Taguchi method or full factorial method is used for design of experiments to generate the data required for building the surrogate models. The key input process parameters identified during the knowledge creation are used to create a set of data using DoE on computational model. The data generated for experiments is used to train the function fn3 and fn4 using a plurality of techniques like multivariate regression or ANN (Artificial neural network).
[0043] In an embodiment, an example for generation of surrogate model
for prediction of liquid steel temperature is disclosed. A particular ladle geometry and its materials of construction are considered to be constant. It is assumed that the ladle under consideration is under circulation. Also, for the given casting ladle cycle, BOF steel temperature, tapping time, refining time, chemical additions do not vary significantly. Following are the assumed values of these constants.
T BOF = 1840 K
Taping time= 7 mins
Refining time = 30 mins
[0044] Based on the thermal insights obtained from computational
modeling, the refractory initial condition is not significantly affecting the

current teeming cycle. Therefore, following input process parameters are considered as variables –
a) Empty ladle waiting time before tapping
b) Molten steel temperature at the end of refining (Representing Arcing intensity and duration)
c) Slag thickness (representative of slag weight)
d) Holding time
e) Teeming rate
[0045] Using Taguchi method of design of experiments, following table
of input combinations is generated as experiments for the above mentioned variables.

Waiting
Time
(min) Molten steel
temperature at
the end of
refining (K) Holding Time (m) Slag
Thicknes
s (m) Teeming
Rate (ton/min)
Expt 1 30 1830 5 0.05 2
Expt 2 30 1845 10 0.07 3
Expt 3 30 1860 20 0.09 4
Expt 4 30 1880 30 0.12 5
Expt 5 60 1830 10 0.09 5
In the example embodiment performed in table 1, integrated computational model is performed to obtain steel streaming temperature for each of the experiments. The output temperature is a time temperature curve, therefore, the temperature is captured at different percentage of teeming as showing in the below table.

Empty % of ladle Expt1 Expt2 Expt3 Expt4 Expt5

Temperature of liquid steel at the outlet of ladle during teeming (K) 0 1823. 3 1833. 2 1837. 5 1844. 7 1817. 9

10 1817. 2 1829. 7 1838. 1 1851. 1 1815. 9

20 1812. 3 1827. 7 1839 1854. 2 1815. 5

30 1808. 5 1825. 7 1838. 3 1854. 7 1814. 6

40 1805. 2 1823. 9 1837. 4 1854. 6 1813. 6

50 1802 1822 1836. 5 1854 1812. 7

60 1798. 7 1820. 2 1835. 2 1853. 5 1811. 9

70 1794. 8 1818. 1 1834 1852. 7 1811. 2

80 1790. 2 1815. 8 1832. 7 1852 1810. 2

90 1783 1813 1831. 5 1851. 1 1809. 3

100 1762. 2 1803 1826. 4 1849 1806
[0046] Each of the temperature column is mapped against corresponding
inputs and a regression coefficient for each of the temperature is obtained.
Y = a1*x1 + a1*x1 + a1*x1 + a1*x1 + a1*x1 + b
Y – Teeming temperature at start of teeming a1, a2, a3, a4, a5 – Regression coefficients b – regression constant
x1, x2, x3, x4, x5 – Inputs mentioned above An example for starting temperature of teeming (0% drained ladle) is shown below.

T0 = 153.46 - 0.03727 x (Waiting Time) + 0.9153 x (Molten steel temperature at the end of refining) - 1.04587 x (Holding Time) + 10.83593 x (Slag Thickness) + 0.352605 x (Teeming Rate)
The regression coefficients obtained here are generic and are used for complete ladle design and considered constants do not change significantly. Once the regression coefficients are obtained, temperature (Y) can be predicted for given set of inputs (x1-x5), which provides the real-time prediction. Different such functions are trained for prediction of temperature of steel at various stages as a function of input process parameters. Full temperature profile for temperature of liquid steel stream during teeming is predicted with the help of such technique. This allows the operator to change the other casting parameters such as casting speed and cooling rates based on the predicted steel temperature in real-time, to ensure safety, quality and productivity of the cast product.
[0047] In another example embodiment, a method for building a
surrogate model for ladle refractory temperature prediction is disclosed. The ladle refractory has a plurality of layers and there is a temperature variation within the plurality of layers. FIG. 6 illustrates a side refractory layer of a ladle and the variations of temperature at different locations, according to some embodiment of the present subject matter. The temperature at M1 is different from temperature at M2, which is different from the temperature at other locations like M3 and so on. Temperatures at discrete points as shown

in the FIG. 6, is predicted based on the integrated computational model. Similar method of DoE as mentioned above is followed and a surrogate model is developed for temperature prediction at each of the points. The temperature profiles at the end of teeming in one cycle, at the end of waiting period after the cycle and before start of tapping of the next consecutive cycle is considered for subsequent losses in the molten steel. Hence a temperature prediction system is built for ladle refractory that is used in ladle thermal tracking module.
[0048] In an embodiment, the technique for building a surrogate model
for ladle refractory temperature prediction utilizes the same techniques of building a surrogate model for steel temperature prediction. Experiment data is generated using the integrated computational models and is used to train the surrogate model for ladle temperature prediction.
[0049] The knowledge gathered in refractory temperature profile
prediction using integrated model is used to decide a plurality of locations on
refractory layers for the temperature prediction. It is observed that for a
circulating ladle, the temperature variations in the refractory layers is
restricted to first layer i.e., working lining. However, during teeming and
empty waiting period, side refractory layers undergo differential cooling.
Therefore more predictor points are considered as shown in FIG. 6.
[0050] In an embodiment, a similar surrogate model is built for predicting
the heat loss in liquid steel during different operations for a given values of

influential parameters. The surrogate model for predicting the heat loss in liquid steel is used for the arcing advice module.
[0051] In an embodiment, based on the surrogate models built to predict
the liquid steel temperature, temperature of refractory ladle and the heat loss in liquid steel during a specific ladle operation, one or more modules are built for providing a thermal monitoring and providing an advisory control for the ladle steel operations. The one or more modules are the steel thermal monitoring module 208, the ladle thermal tracking module 210, the ladle select assistant module 212 and an arcing advice module 214.
[0052] In an embodiment, FIG. 7 shows a schematic of the real-time
monitoring system, according to some embodiment of the present subject matter. The inputs are initial ladle thermal status, waiting time, T steel BOF, arcing, chemical additions, holding time, slag weight, teeming time. The inputs for additional ladle processes can also include like degassing (may be included by adequate modeling). The input of initial thermal status of ladle in case of a preheated ladle is represented through hot face temperature of the ladle refractory. The inputs are either manually entered by the operator or obtained automatically from the plant data collection system. In the knowledge gathered from the computational simulations, the effect of initial refractory need not be included in case of cycling ladle. This reduces the effort of tracking the ladle temperature post last cycle’s teeming. Based on different functions devised for temperature predictions at different operations, (based on the training data from computational models), liquid steel thermal

status can be continuously tracked at every process like tapping, refining, holding and teeming as shown in FIG. 7. Continuous online monitoring enables avoiding breakouts or nozzle clogging. Online prediction based monitoring reduces the number of measurements (frequency and location) required in the plant otherwise. Therefore, it saves a lot of re-work, costs and helps increasing productivity.
[0053] In ladle thermal tracking module 210, as number of ladles are
operating simultaneously on a steel plant, there is a need to keep track of the thermal status of all the ladles all the time. The tracking is done through the surrogate models built for the ladle refractory temperature prediction. The input for the ladle thermal tracking module 210 are the anticipated or actual plant parameters such as BOF steel temperature, time periods of the processes, number of heats ladle has seen. The surrogate models for ladle refractory temperature prediction is used to predict the ladle refractory temperatures. Based on this, ladle temperature at different operations such as at the end of maintainance or start of tapping can be predicted and tracked. The functions used are similar to ones created for steel temperature. The online tracking reduces the need of large number of sensors that otherwise may be required for tracking. With the help of online prediction model, the cost and effort of tracking the thermal status can be reduced. In addition, since the work environment on the plant is hazardous, it is not posible to measure the temperature at every operation. The ladle thermal tracking module 210 makes it easier to track the thermal status of ladle at a given

juncture. The prediction based ladle thermal tracking also reduces the frequency of plant measurements and also the number of locations at which measurements are required. This directly results in reduction of number of sensors, labor and hence the cost.
[0054] A method for ladle select assistant module 212 and arcing advice
module 214 are disclosed in the present disclosure. The thermal status of the ladle before tapping has an effect on the heat loss in the liquid steel in the subsequent operations. A ladle at normal temperature abosrbs more heat from the liquid steel and therefore causes more loss in the liquid steel temperature. Therefore there is a need for extra arcing to be done for the more loss caused in the liquid steel temperature. On the other hand, a warmer ladle reduces the heat loss from liquid steel. Furthermore, a particular casting line may be expecting a longer holding time, that may result in more heat loss from the liquid. In such a case, a warmer ladle should be selected so that the arcing is minimal. The re-use of the ladle in repetitive cycles makes the liquid steel temperature in ongoing cycle dependent on the previous cycle parameters. An example is effect of initial thermal status of the ladle on the steel processing cycle. Depending upon whether the ladle is in circulation or preheated new ladle, this effect is different. The effect cannot be judged simply by plant experience or through standalone computational models alone. The embodiments of the present disclosure enables the system 200 to capture this knowledge using integrated modeling approach for doing sensitivity analysis.

[0055] Therefore, the selection of ladle from the pool of ladles waiting at
the maintainane for new charge is a decision made based on the expected heat loss (based on anticipated process parameters) and the thermal status of the existing ladles. The ladle thermal tracking module 210 and the surrogate models for estimating the heat loss in liquid steel are used to assist the operator in deciding which ladle should be used for which casting line. The operator makes the choice by estimating the thermal performance of each awaiting ladle for given anticipated process parameters. The loop can also be optimized to find the most suitable ladle for given casting line. FIG. 8 is an illustration of selecting a ladle from the available ladles for the next cycle of steel making. This also considers the temperature of the ladles and based on the temperature of the ladle, the selection of the ladle for the next cycle is done. In FIG. 8, the ladles L4, L5,L6,L11 and L10 are the available ladles. Therefore the operator computes the arcing required for each of the available ladles and determines the ladle with the minimum arcing required for the steel making.
[0056] In an embodiment, a method for determining the arcing required
for a given ladle is disclosed. Once the refining operation is finished, the ladle undergoes holding and teeming operation, that are relatively longer processes and result in more heat loss from the liquid steel. There is very little or no chance of recovery if the steel temperature obatined is not within the desirable range. Therefore, the arcing during refining period becomes a key controllable manipulator of liquid steel temperature at the end of teeming.

The intensity of arcing is determined based on the temperature drop functions devised earlier to meet the final temperature. A surrogate model for delta T prediction is built on similar lines to the temperature predictor (delta T can be obtained based on the thermal predictor module as well). After a ladle is selected, the liquid steel temperature predictor is used to estimate the temperature of liquid steel at the end of refining with a standard arcing. The initial thermal status of ladle and the current anticipated parameters such as holding time and teeming time etc. are used to estimate the anticipated heat loss from liquid steel during holding and teeming. The final temperature is compared with required superheat band and appropriate arcing intensity and duration is derived, so that the steel temperature falls in the required superheat band. An example calculation of the arcing required is depicted below.
[0057] Assuming, for given BOF steel temperature and tapping-refining
durations in a cycle,
[0058] For a green preheated ladle,
ΔTholding-teeming = fn1 (initial hot face temperature after preheating, waiting time, slag weight, anticipated holding time, and planned teeming rate)
Arcing Required = F (Tsteel_Teem required - ΔTholding-teeming) If the ladle is in circulation, the effect of initial thermal status of refractory is diminished, hence

ΔTholding-teeming = fn2 (heat number, waiting time, slag weight, anticipated holding time, and planned teeming rate)
Arcing Required = F (TsteelTeem required - ΔTholding-teeming) [0059] Therefore, the system 200 assists in ladle selection and advises the arcing temperature required based on the value determined for “Arcing Required” for the available ladles.
[0060] FIG. 9 is a flow chart explaining the advisory decision making, according to some embodiment of the present subject matter. The advisory decision making assists the operatoor by providing “Arcing required” value for a ladle from all the available ladles for a given casting line. Based on the arcing intensity and duration requirement predicted, the operator can decide the ladle to be selected for that particular casting line and further decide the arcing parameters for the selected ladle in the particular casting line. At block 902, parameters pertaining to waiting, teeming and refining operations are taken as input. Further at block 904, steel temperature in a particular ladle is predicted at the end of refining. At block 906, anticipated holding and teeming process parameters are taken as input. Further at block 908, required superheat is inputted into the system 200. At block 910, it is determined whether the selected ladle is in circulation. Further at block 912, if the selected ladle is not in circulation, delta T is calculated based on preheat temperature, holding parameters,teeming parameters and so on. Subsequently, at block 914, arcing required is calculated and recommended acordingly to the selected ladle. However, if the ladle is not in circulation, at block 916,

delta T is calculated based on waiting time, holding parameters, teeming parameters and so on. Subsequently, at block 918, arcing required for the ladle for the next process is calculated and recommended.
[0061] FIG. 10 is a flow chart 1000 illustrating a method for thermal
monitoring and providing advisory control for steel ladle operations, according to some embodiment of the present disclosure. At block 1002, geometrical and operational data related to all the ladles are collected. At block 1004, computational models are generated and integrated based on the geometrical and operational data of ladles. At block 1006, one or more influential parameters of the ladle operations that affect the temperature of the liquid steel and ladle refractories are identified. At block 1008, one or more operational rules for prediction and control of the temperature of liquid steel and ladles refractories are generated. Subsequently, at block 1010, one or more surrogate models are generated for the influential parameters for predicting at least one of (a) liquid steel temperature and (b) refractory temperature of the plurality of ladles (c) heat loss in liquid steel during a specific ladle operation. At block 1012, based on the surrogated models, thermal monitoring and advisory control is provided.
[0062] It is to be understood that the scope of the protection is extended
to such a program and in addition to a computer-readable means having a message therein; such computer-readable storage means contain program-code means for implementation of one or more steps of the method, when the program runs on a server or mobile device or any suitable programmable

device. The hardware device can be any kind of device which can be programmed including e.g. any kind of computer like a server or a personal computer, or the like, or any combination thereof. The device may also include means which could be e.g. hardware means like e.g. an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or a combination of hardware and software means, e.g. an ASIC and an FPGA, or at least one microprocessor and at least one memory with software modules located therein. Thus, the means can include both hardware means and software means. The method embodiments described herein could be implemented in hardware and software. The device may also include software means. Alternatively, the embodiments may be implemented on different hardware devices, e.g. using a plurality of CPUs.
[0063] The embodiments herein can comprise hardware and software
elements. The embodiments that are implemented in software include but are not limited to, firmware, resident software, microcode, etc. The functions performed by various modules described herein may be implemented in other modules or combinations of other modules. For the purposes of this description, a computer-usable or computer readable medium can be any apparatus that can comprise, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device.
[0064] The illustrated steps are set out to explain the exemplary
embodiments shown, and it should be anticipated that ongoing technological

development will change the manner in which particular functions are
performed. These examples are presented herein for purposes of illustration,
and not limitation. Further, the boundaries of the functional building blocks
have been arbitrarily defined herein for the convenience of the description.
Alternative boundaries can be defined so long as the specified functions and
relationships thereof are appropriately performed. Alternatives (including
equivalents, extensions, variations, deviations, etc., of those described herein)
will be apparent to persons skilled in the relevant arts based on the teachings
contained herein. Such alternatives fall within the scope and spirit of the
disclosed embodiments. Also, the words “comprising,” “having,”
“containing,” and “including,” and other similar forms 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.
[0065] Furthermore, one or more computer-readable storage media may
be utilized in implementing embodiments consistent with the present disclosure. A computer-readable storage medium refers to any type of physical memory on which information or data readable by a processor may be stored. Thus, a computer-readable storage medium may store instructions for execution by one or more processors, including instructions for causing

the processor(s) to perform steps or stages consistent with the embodiments
described herein. The term “computer-readable medium” should be
understood to include tangible items and exclude carrier waves and transient signals, i.e., be non-transitory. Examples include random access memory (RAM), read-only memory (ROM), volatile memory, nonvolatile memory, hard drives, CD ROMs, DVDs, flash drives, disks, and any other known physical storage media.
[0066] It is intended that the disclosure and examples be considered as
exemplary only, with a true scope and spirit of disclosed embodiments being indicated by the following claims.

I/We Claim:
1. A method for thermal monitoring and providing advisory control for ladle
operations, the method comprising of:
collecting geometrical and operational data related to one or more ladles and liquid steel in a steel plant;
generating and integrating a plurality of computational models based on the geometrical and operational data of the ladles and the liquid steel in the steel plant;
identifying one or more influential parameters of the ladle steel operations that affect temperature of liquid steel at various stages of the ladle operations, through a systematic parametric study using the integrated computational models;
generating one or more mathematical operational rules for prediction and control of the temperature of the liquid steel and the ladles based on the integrated computational models;
generating a surrogate model for the influential parameters for predicting at least one of (a) liquid steel temperature and (b) refractory temperature of the plurality of ladles, and (c) heat loss in liquid steel during a specific ladle operation, based on the integrated computational models and the mathematical operational rules by considering at least one of a refractory status and a cycling status; and
providing a thermal monitoring and providing an advisory control for the ladle steel operations.
2. The method as claimed in claim 1, wherein the computational models
include geometry creation, meshing, numerical solution, post-processing
the results of computational simulations and validation with experimental
measurements of computational simulations.

3. The method as claimed in claim 1, wherein integrating the computational models include integrating output of a first computational model with an input of a second computational model or integrating input of the first computational model with output of the second computational model
4. The method as claimed in claim 1, wherein the influential parameters include incoming initial ladle refractory thermal status, liquid steel temperature from primary steel making operations such as basic oxygen furnace (BOF), time periods of different ladle operations, type and amount of chemical additions, intensity and time of arcing and slag weight.
5. The method as claimed in claim 1, further comprising determining one or more monitoring points in a refractory layer of the one or more ladles based on the systematic parameter study.
6. The method as claimed in claim 5, wherein the surrogate model for predicting the ladle refractory temperature is based on a temperature being estimated at one or more points of the refractory layer.
7. The method as claimed in claim 1 wherein, providing the thermal monitoring include at least one of (a) providing a real time monitoring for liquid steel temperature for at least one casting line, based on the surrogate models for liquid steel temperature prediction and (b) providing a real time thermal tracking for at least one ladle, based on the surrogate models for the ladle refractory temperature prediction and advisory control include at least one of (a) advisory control for selecting a ladle from one or more ladles, based on the surrogate models and the thermal tracking of the ladle and (b) arcing advice for the selected ladle based on the surrogate models and thermal monitoring module.
8. A system for thermal monitoring and providing advisory control for ladle steel operations, the system comprising of:
at least one processor; and
a memory communicatively coupled to the at least one processor, wherein the memory comprises

a surrogate model generation module to :
collect geometrical and operational data related to one or more ladles and liquid steel in a steel plant
generate and integrate a plurality of computational models based on the geometrical and operational data of the ladle and liquid steel in the steel plant
identify one or more influential parameters of ladle operations that affect the liquid steel temperature at various stages of ladle steel operations, through a systematic parametric study using integrated computational models
generate one or more mathematical operational rules for prediction and control of the temperature of the liquid steel and the ladles based on the computational models
generate a surrogate model for the varying parameters for predicting at least one of (a) liquid steel temperature and (b) refractory temperature of the plurality of ladles and (c) heat loss during a specific ladle operation, based on the integrated computational models and the mathematical operational rules; a steel thermal monitoring module for providing a real time monitoring for liquid steel temperature for at least one casting line based on the surrogate models for liquid steel temperature prediction
a ladle thermal tracking module for providing a real time thermal tracking for at least one ladle, based on the surrogate models for the ladle refractory temperature prediction
a ladle select assist module for selecting a ladle from one or more ladles based on the surrogate models and the thermal tracking module and
an arcing advice module for arcing advice for the selected ladle based on the surrogate models and the thermal tracking module

9. The system as claimed in claim 8, wherein the computational models include geometry creation, meshing, numerical solution, post-processing the results of computational simulations and validation with experimental measurements of computational simulations.
10. The system as claimed in claim 8, wherein integrating the computational models include integrating output of a first computational model with input of a second computational model or integrating input of the first computational model with output of the second computational model.
11. The system as claimed in claim 8, wherein the influential parameters include incoming initial ladle refractory thermal status, liquid steel temperature from primary steel making operations like BOF, time periods of different ladle operations, chemical additions, amount of arcing and slag weight
12. The system as claimed in claim 8, further comprising determining one or more points in a refractory layer of the one or more ladles based on the systematic parameter study.
13. The system as claimed in claim 12, wherein the surrogate model for predicting the ladle refractory temperature is based on a temperature being estimated at one or more points of the refractory layer.