Description:TECHNICAL FIELD
[0001] The present disclosure relates generally to a field of metallurgy. Particularly, but not exclusively, the disclosure relates to a continuous casting process. Embodiments of the disclosure disclose a system and algorithm based on gradient boosting method for real-time detection of a sticker in a mould during the continuous casting process.
BACKGROUND
[0002] Background description includes information that may be useful in understanding the present subject matter. It is not an admission that any of the information provided herein is prior art or relevant to the presently claimed subject matter, or that any publication specifically or implicitly referenced is prior art.
[0003] Continuous casting process is a metallurgical process involving the continuous supply of liquid metal, also referred to as a molten metal, into a mould. The molten metal may be solidified into a semi-finished slab. The continuous casting process is a critical link in steelmaking, that produces a steel slab as an end result. In the continuous casting process, liquid steel is continuously tapped into a mould, which may be rectangular in shape. The walls of the mould may be cooled by continuously supplying a coolant such as water, and an inner surface of each of the wall may be coated with a lubricating medium. When the liquid steel is tapped into the mould, the liquid steel that comes in contact with the lubricating medium of the mould solidifies to form a solid shell, while rest of the liquid steel may remain in liquid or semi-liquid state, thus forming a steel slab. The steel slab may be continuously extracted from the mould and may be directly subject to one or more secondary metallurgical operations.
[0004] During the continuous casting process, abnormalities like sticker formation may be developed. Generally, a sticker formation may be initiated when molten metal such as liquid steel sticks to walls of the mould due to loss of lubrication between solidifying strand and mould wall On the other hand, the sticker may also be formed due to poor heat transfer due to presence of hydrogen in steel. The formation of stickers in the mould may weaken the shell of the casted steel slab or may form an underdeveloped shell. Due to the underdevelopment or weakening of the shell, the casted steel slab may not be able to sustain ferro static pressure, thereby resulting in the breakout of liquid steel in the steel slab. Such breakouts may cause extreme loss of time, money and resources during the casting.
[0005] With on-going efforts, many techniques have been proposed to indicate abnormalities during the continuous casting process. The existing techniques may include Breakout Prevention System (BPS) that may detect casting abnormalities such as stickers and cracks to prevent breakouts. The BPS uses temperature inputs, casting speed, steel chemistry, mould level, mould width and the like to determine breakoutability index that determines the tendency of breakout using an intelligent computational logic. The intelligent computational logic maps physical phenomenon reflected in temperature time series to a fault severity or in other words breakoutability index, using a computational associative matrix. An independent intelligent computational unit is created for each type of the breakouts such as stickers, cracks and thin shells.
[0006] However, such existing techniques use temperature inputs received from adjacent thermocouples configured in the mould, which may work for detecting a well-developed sticker, but fails to detect mild stickers. Also, these existing techniques completely rely on the breakoutability index detected by the intelligent computational logic to trigger an alarm. Also, the breakoutability index may falsely determine the presence of a sticker in most of the scenarios, due to variation of temperature, the occurrence of peritectic reactions which exhibit a similar behaviour on the temperature patterns as that of a sticker formation. Therefore, these techniques may trigger numerous false alarms, thus affecting the continuous casting process.
[0007] Therefore, by implementing the existing techniques, the breakoutability detection may be error-prone and may lead to numerous false alarms due to the configuration of inaccurate threshold limits, the occurrence of peritectic reactions that exhibit temperature variations similar to that of casting abnormalities, the occurrence of mild stickers that are difficult to detect and the like. The existing techniques do not provide a mechanism to reduce or eliminate false alarms triggered due to each of the above-mentioned attributes.
[0008] Accordingly, there is a need for methods and systems that can overcome one or more limitations stated above or any other limitation associated with the conventional arts.
OBJECTS OF THE DISCLOSURE
[0009] Some of the objects of the present disclosure, which at least one embodiment herein satisfy, are listed hereinbelow.
[0010] A general object of the present disclosure is to provide a system and a method for real-time detection of a sticker in a mould during the continuous casting process.
[0011] An object of the present disclosure is to provide a method and apparatus to capture mild-sticker patterns in Breakout Prevention systems for continuous slab casting.
[0012] An object of the present disclosure is to provide a method and apparatus to capture mild-sticker patterns in Breakout Prevention systems for continuous stab casting, in which mild-sticker signatures are captured without increasing the number of false alarms, based on the temperature patterns of stickers with less strength.
[0013] These and other objects and advantages of the present invention will be apparent to those skilled in the art after a consideration of the following detailed description taken in conjunction with the accompanying drawings in which a preferred form of the present invention is illustrated.
SUMMARY
[0014] This summary is provided to introduce concepts related to systems and methods for real-time detection of a sticker in a mould during the continuous casting process. The concepts are further described below in the detailed description. This summary is not intended to identify key features or essential features of the claimed subject matter, nor is it intended to be used to limit the scope of the claimed subject matter.
[0015] The present disclosure relates to a gradient boosting method (GBM) based breakout detection system for real-time detection of a sticker in a mould during a continuous casting process. The system includes a plurality of thermocouples arranged at each of a plurality of layers of the mould; and a control unit, associated with the plurality of thermocouples, configured to receive real-time temperature variation patterns from the plurality of thermocouples; determine discrete variables of a sticker signature in the real-time temperature variation patterns; modify the discrete variables of the signature sticker by nearing their values to the determined possibility of occurrence of the sticker; perform a core probability calculation on the modified discrete variable using a Gradient Boosting Machine (GBM) algorithm/unit; and apply user-defined filters on an output of the GBM algorithm/unit to remove data received from abnormal thermocouples. In an aspect, the GBM algorithm/model/unit is established based on various historical patterns of sticker.
[0016] In an aspect, the temperature inputs include the rate of the rise of the temperature and magnitude rise of the temperature.
[0017] In an aspect, the predefined time interval for receiving the temperature inputs is one second.
[0018] In an aspect, the discrete variables of the sticker signature comprises one or more of an amplitude of the temperature, a slope of the temperature, a rise in the temperature, a fall in the temperature, a time taken for rise in the temperature, a time taken for fall in the temperature, a cross-over of the temperatures, and a change in casting speed. This list of discrete variables should not be considered as a limitation. Those skilled in the art can appreciate that other varibales of the sticker signature which are not mentioned here can considered for the implementation of the present disclosure.
[0019] In an aspect, the control unit modifies the discrete variables, including the amplitude of the temperature, by taking the amplitude based on slope change and then subtracting fluctuations occurred previous to the determined possibility of occurrence of the sticker.
[0020] In an aspect, the control unit modifies the discrete variables, including the cross-over of the temperatures, by using the temperature difference just before the sticker occurance considered in the previous modifications of the discrete variables.
[0021] In an aspect, the user-defined filters are based on a relationship between physical properties of elements involved in the continuous casting process.
[0022] In an aspect, the plurality of layers of the mould includes a first layer, a second layer, a third layer and a fourth layer, along a vertical segment of the mould.
[0023] In an aspect, the control unit is further configured to trigger an alarm upon indicating the presence of the sticker in the mould, for initiating one or more rectifying actions.
[0024] The present disclosure further relates to a method for real-time detection of a sticker in a mould during a continuous casting process. The method includes receiving, at a control unit, real-time temperature variation patterns from the plurality of thermocouples in response to affirmative indication of occurrence of the sticker by a GBM algorithm/unit; determining, by the control unit, discrete variables of a sticker signature in the real-time temperature variation patterns; modifying, by the control unit, the discrete variables by nearing their values to the determined possibility of occurrence of the sticker; performing, by the control unit, a core probability calculation on the modified discrete variables using Gradient Boosting Machine (GBM) algorithm/unit; and applying, by the control unit, user-defined filters on an output of the GBM algorithm/unit to remove data received from abnormal thermocouples.
[0025] In an aspect, the temperature inputs include the rate of the rise of the temperature and magnitude rise of the temperature.
[0026] In an aspect, the predetermined time interval for receiving the temperature inputs is one second.
[0027] In an asecpt, the discrete variables of the sticker signature comprises one or more of an amplitude of the temperature, a slope of the temperature, a rise in the temperature, a fall in the temperature, a time taken for rise in the temperature, a time taken for fall in the temperature, a cross-over of the temperatures, and a change in casting speed. This list of discrete variables should not be considered as a limitation. Those skilled in the art can appreciate that other varibales of the sticker signature which are not mentioned here can considered for the implementation of the present disclosure.
[0028] In an aspect, when discrete variables include the amplitude of the temperature, the method includes modifying the discrete variables by taking the amplitude based on slope change and then subtracting fluctuations occurred previous to the determined possibility of occurrence of the sticker.
[0029] In an aspect, when the discrete variables include the cross-over of the temperatures, the method includes modifying the discrete variables by using the temperature difference considered in the previous modifications of the discrete variables.
[0030] In an aspect, the user-defined filters are based on the relationship of physical properties of elements involved in the continuous casting process.
[0031] In an aspect, the plurality of layers of the mould includes a first layer, a second layer, a third layer, and a fourth layer, along a vertical segment of the mould.
[0032] In an aspect, the method includes triggering an alarm upon indicating the presence of the sticker in the mould for initiating one or more rectifying actions.
[0033] Various objects, features, aspects, and advantages of the inventive subject matter will become more apparent from the following detailed description of preferred embodiments, along with the accompanying drawing figures in which like numerals represent like components.
[0034] It is to be understood that the aspects and embodiments of the disclosure described above may be used in any combination with each other. Several of the aspects and embodiments may be combined to form a further embodiment of the disclosure.
[0035] The foregoing summary is illustrative only and is not intended to be in any way limiting. In addition to the illustrative aspects, embodiments, and features described above, further aspects, embodiments, and features will become apparent by reference to the drawings and the following detailed description.
BRIEF DESCRIPTION OF THE DRAWINGS
[0036] 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. 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 figures to reference like features and components. Some embodiments of system and/or methods in accordance with embodiments of the present subject matter are now described, by way of example only, and with reference to the accompanying figures, in which:
[0037] FIG. 1A illustrates an exemplary system for real-time detection of a sticker in a mould during continuous casting process, in accordance with an embodiment of the present disclosure;
[0038] FIG. 1B illustrates an exemplary representation of four layers of a mould in accordance with some embodiments of the present disclosure;
[0039] FIG. 2A illustrates a detailed block diagram of components of a system for real-time detection of a sticker in a mould during a continuous casting process in accordance with an embodiment of the present disclosure;
[0040] FIG. 2B illustrates shows an exemplary computational associative matrix in accordance with an embodiment of the present disclosure;
[0041] FIG. 3A illustrates an exemplary step of modifying a variable received by the system for real-time detection of a sticker in a mould, in accordance with an embodiment of the present disclosure;
[0042] FIG. 3B illustrates an exemplary step of core probability calculation on the modified variable using Gradient Boosting Machine (GBM) model, in accordance with an embodiment of the present disclosure; and
[0043] FIG. 4 illustrates a method for real-time detection of a sticker in a mould during a continuous casting process, according to an embodiment of the present disclosure.
[0044] It should be appreciated by those skilled in the art that any block diagrams herein represent conceptual views of illustrative systems embodying the principles of the present subject matter. Similarly, it will be appreciated that any flow charts, flow diagrams, state transition diagrams, pseudo code, and the like represent various processes which may be substantially represented in computer-readable medium and executed by a computer or processor, whether or not such computer or processor is explicitly shown.

DETAILED DESCRIPTION
[0045] In the present document, the word "exemplary" is used herein to mean "serving as an example, instance, or illustration." Any embodiment or implementation of the present subject matter described herein as "exemplary" is not necessarily to be construed as preferred or advantageous over other embodiments.
[0046] While the disclosure is susceptible to various modifications and alternative forms, specific embodiment thereof has been shown by way of example in the drawings and will be described in detail below. It should be understood, however that it is not intended to limit the disclosure to the forms disclosed, but on the contrary, the disclosure is to cover all modifications, equivalents, and alternatives falling within the scope of the disclosure.
[0047] The terms “comprises”, “comprising”, “includes” or any other variations thereof, are intended to cover a non-exclusive inclusion, such that a setup, device or method that includes a list of components or steps does not include only those components or steps but may include other components or steps not expressly listed or inherent to such setup or device or method. In other words, one or more elements in a system or apparatus proceeded by “comprises… a” does not, without more constraints, preclude the existence of other elements or additional elements in the system or method.
[0048] Disclosed herein are a system and a method for real-time detection of a sticker in a mould during a continuous casting process. In the present disclosure, sticker generally means a completely developed sticker, until otherwise specified. Generally, the sticker may be formed in the mould when mould powder or lubricant does not penetrate into gaps of the mould properly. The formation and propagation of the sticker in the mould attenuate growth of solid shell during the continuous casting process. The solid shell is formed when liquid steel tapped into the mould comes in contact with a lubricating medium present on walls of the mould. Due to the presence of the sticker, the solid shell may be underdeveloped. When the under-developed solid shell exits the mould, ferro static pressure of the liquid steel surrounded by the solid shell may lead to a breakout of the liquid steel. Breakout of such solid shell cannot be prevented, and it may lead to various challenges during the continuous casting process. Also, avoiding the formation of stickers in the mould may not be possible during the continuous casting process, however, early detection of the presence of the stickers may help in avoiding the breakout of the liquid steel by performing rectifying actions such as reducing casting speed. In some embodiments, reducing the casting speed may allow the liquid steel to occupy the mould for a longer duration, thus enabling strong and complete development of solid shell that can withstand the ferro static pressure.
[0049] Therefore, to detect the presence of the stickers, the system disclosed in the present disclosure may comprise a plurality of thermocouples arranged at each of a plurality of layers of the mould. Further, a Gradient Boosting Machine (GBM) model/algorithm/unit implemented in the system may receive data pertaining to temperature as temperature inputs from the plurality of thermocouples to determine a breakoutability index. In some embodiments, the temperature inputs may include, but not limited to, rise (slope) of temperature and magnitude rise (amplitude) of the temperature. In some embodiments, the breakoutability index may indicate the probability of the presence of a sticker in the mould. Existing techniques known in the art may confirm the presence of the sticker directly based on the breakoutability index, without verifying the correctness of the breakoutability index, thereby leading to false alarms. However, the present disclosure eliminates/reduces the occurrence of false alarms by further refining the breakoutability index prior to confirming the presence of the sticker.
[0050] In some embodiments, refining the breakoutability index comprises evaluating discrete variables of a sticker signature in real-time temperature variation patterns received from the plurality of thermocouples. In an aspect, the discrete variables of the sticker signature may include, but not limited to, one or more of an amplitude of the temperature, a slope of the temperature, a rise in the temperature, a fall in the temperature, a time taken for rise in the temperature, and a time taken for fall in the temperature, a cross-over of the temperatures, and a change in casting speed. This list of discrete variables should not be considered as a limitation. Those skilled in the art can appreciate that other varibales of the sticker signature which are not mentioned here can considered for the implementation of the present disclosure.
[0051] In some embodiments, the discrete variables of the signature sticker are modified by nearing their values to the determined possibility of occurrence of the sticker. On the modified discrete variables, a core probability calculation is performed using a Gradient Boosting Machine (GBM) model/algorithm/unit.
[0052] Further, to remove data received from the abnormal thermocouple, user-defined filters are applied on the output of the GBM model.
[0053] Thus, various embodiments and implementations of the present disclosure provide mandatory discrete variables of the sticker signature, which when occur in real-time, confirms the presence of the sticker in the mould. In some embodiments, refining of the breakoutability index enables detecting the presence of the sticker with 100% accuracy and also reduces the false alarms triggered due to the occurrence of events such as peritectic reactions, mould level fluctuation, casting speed variations and the like.
[0054] Further, the present disclosure discloses determining the presence of the mild stickers in the mould. In some embodiments, the mild stickers referred herein may be underdeveloped stickers which are in initial stages of formation. Generally, mild stickers are difficult to be detected due to extremely slow propagation in the mould. Therefore, detecting the mild sticker may facilitate early detection of sticker formation.
[0055] Therefore, the present disclosure completely eliminates false alarms triggered due to the occurrence of peritectic reactions. Also, the system eliminates false alarms and helps in accurate determination of the presence of the sticker, including mild stickers, makes the present disclosure extremely reliable.
[0056] In the following detailed description of the embodiments of the disclosure, reference is made to the accompanying drawings that form a part hereof, and in which are shown by way of illustration specific embodiments in which the disclosure may be practised. These embodiments are described in sufficient detail to enable those skilled in the art to practice the disclosure, and it is to be understood that other embodiments may be utilized and that changes may be made without departing from the scope of the present disclosure. The following description is, therefore, not to be taken in a limiting sense.
[0057] Hereinafter, a description of an embodiment with several components in communication with each other does not imply that all such components are required. On the contrary, a variety of optional components are described to illustrate the wide variety of possible embodiments of the present disclosure.
[0058] FIG. 1A shows an exemplary breakout detection system 100 for real-time detection of a sticker in a mould during the continuous casting process in accordance with an embodiment of the present disclosure.
[0059] The system 100 includes a mould 102, thermocouple 1041 to thermocouple 104n (also referred to as a plurality of thermocouples 104), a GBM algorithm/unit 106 and a control unit 108. The present disclosure may be described in accordance with a continuous casting process of a steel slab. However, this should not be construed as a limitation to the present disclosure, since the present disclosure may be applicable to the continuous casting process of metals or alloys other than steel.
[0060] The mould 102 may be a solid structure that allows the flow of a molten metal tapped into the mould 102. As an example, the molten metal may be liquid steel which may be continuously tapped into the mould 102, to form a steel slab. As an example, the mould 102 may be rectangular in shape defining a mould cavity in an inner surface. The mould 102 may be configured with a cooling arrangement on an outer surface. A coolant like water may be continuously circulated through the cooling arrangement to cool the inner surface of the mould 102. The temperature difference between the inner surface of the mould 102 and the molten metal results in solidification of at least an outer layer of the molten metal. The plurality of thermocouples 104 may be configured on the outer surface of the mould 102.
[0061] In an aspect, the GBM algorithm/unit 106 may receive data pertaining to temperature as temperature inputs from the plurality of thermocouples 103 via a communication network (not shown in the FIG. 1A). As an example, the communication network may be at least one of a wired communication network and a wireless communication network. As an example, the temperature inputs may include, but not limited to, rate of the rise of the temperature and magnitude rise of the temperature. In some aspects, the GBM algorithm/unit 106 may receive the temperature inputs at a predefined time interval. As an example, the predefined time interval for receiving the temperature inputs may be one second. Further, the GBM algorithm/unit 106 may use the temperature inputs to determine a breakoutability index, which is indicative of an occurrence of a sticker, based on predefined threshold breakoutability.
[0062] Further, the control unit 108 associated with the plurality of thermocouples 104 may be associated with an Input/Output (I/O) interface(s) 110 and a memory 112 as shown in the FIG. 1A. In some aspect, the interface(s) 110 and the memory 112 may be communicatively coupled with a processor(s) 114.
[0063] In alternative aspects, the I/O interface 110 and the memory 112 may be present within the control unit 107.
[0064] The I/O interface 110 may receive real-time temperature variation patterns from the plurality of thermocouples 104 arranged at each of plurality of layers of the mould 102. In some aspects, the plurality of layers represents a number of rows in which the plurality of thermocouples 104 are arranged on the mould 102. As an example, if the plurality of thermocouples is arranged in four rows on the mould 102, then the plurality of layers of the mould 102 would be four. An exemplary representation of the four layers of the mould 102 is shown in the FIG. 1B. The present disclosure is described by considering four layers of the mould 102 comprising a first layer 102a, a second layer 102b, a third layer 102c and a fourth layer 102d. However, this should not be construed as a limitation, since the present disclosure would be applicable to more than or less than four layers.
[0065] Further, the I/O interface 110 may receive the breakoutability index from the GBM algorithm/unit 106. In some aspects, the GBM algorithm/unit 106 may be externally associated with the control unit 108 as shown in the FIG.1A. In some other aspects, the GBM algorithm/unit 106 may be integrated in the control unit 108. In some aspects, the real-time temperature variation patterns and the breakoutability index received by the I/O interface 110 may be stored in the memory 112.
[0066] Further, the control unit 108 may determine, the possibility of occurrence of the sticker, in each of the plurality of layers, by evaluating discrete variables of a sticker signature in the real-time temperature variation patterns. In some aspects, the discrete variables of the sticker signature may include, but not limited to, an amplitude of the temperature, a slope of the temperature, a rise in the temperature, a fall in the temperature, a time taken for rise in the temperature, and a time taken for fall in the temperature, a cross-over of the temperatures, and a change in casting speed. In some aspects, the cross-over of the temperatures may indicate the intersection of temperature values received from the plurality of thermocouples 104 arranged in different layers of the plurality of layers. Further, when the evaluation of the discrete variables of the sticker signature yields a positive result indicating the possibility of occurrence of the sticker, the control unit 108 may modify the discrete variables of the signature sticker by nearing their values to the determined possibility of occurrence of the sticker, perform a core probability calculation on the modified discrete variables using Gradient Boosting Machine (GBM) model, and apply user-defined filters on an output of the GBM model to remove data received from abnormal thermocouples. Further, in some aspects, the control unit 108 may trigger an alarm upon indicating the presence of the sticker in the mould (101), for initiating one or more rectifying actions.
[0067] However, in case the evaluation of the discrete variables of the sticker signature yields a negative result indicating no possibility of occurrence of the sticker, the control unit 108 may discard the breakoutability index and continue with next cycle. In some aspects, when the evaluation of the condition of the sticker is negative, but the breakoutability index is high, then the temperature variations may have occurred due to the influence of peritectic reactions.
[0068] Yet further, with the modifications in the discrete variables of the signature sticker, the control unit 108 may determine mild stickers that slowly propagate in the mould 102. Mild stickers mark the initial formation stages of the sticker. Therefore, determining mild stickers enable early detection of the stickers, that is a most preferable stage to initiate damage control or remedial actions, since controlling the mild stickers may be relatively easy than controlling a completely developed sticker. Determining the mild stickers based on the modified discrete variables of the signature sticker concept is explained in detail as part of FIG. 2A.
[0069] FIG. 2A shows a detailed block diagram of components of a system 100 for real-time detection of a sticker in a mould 102 during a continuous casting process in accordance with some embodiments of the present disclosure.
[0070] The system 100 includes the processor(s) 114, the interface(s) 110, the memory 112, and thermocouples 104.
[0071] The processor(s) 114 may be implemented as one or more microprocessors, microcomputers, microcontrollers, digital signal processors, logic circuitries, and/or any devices that manipulate data based on operational instructions.
[0072] Among other capabilities, the one or more processor(s) 114 are configured to fetch and execute computer-readable instructions and one or more routines stored in the memory 112. The memory 112 may store one or more computer-readable instructions or routines, which may be fetched and executed to manage warehouse over a network service. The memory 112 may include any non-transitory storage device including, for example, volatile memory such as RAM, or non-volatile memory such as EPROM, flash memory, and the like.
[0073] The interface(s) 110 may include a variety of interfaces, for example, interfaces for data input and output devices referred to as I/O devices, storage devices, and the like. The interface(s) 110 may facilitate communication of the system 100 with various devices coupled to the system 100. The interface(s) 110 may also provide a communication pathway for one or more components of the system 100. Examples of such components include, but are not limited to, processing unit(s) 202 and data 204.
[0074] The processing unit(s) 202 may be implemented as a combination of hardware and programming (for example, programmable instructions) to implement one or more functionalities of the processing unit(s) 202. In examples described herein, such combinations of hardware and programming may be implemented in several different ways. For example, the programming for the processing unit(s) 202 may be processor-executable instructions stored on a non-transitory machine-readable storage medium and the hardware for the processing unit(s) 202 may include a processing resource (for example, one or more processors), to execute such instructions. In the present examples, the machine-readable storage medium may store instructions that, when executed by the processing resource, implement the processing unit(s) 202. In such examples, the system 100 may include the machine-readable storage medium storing the instructions and the processing resource to execute the instructions or the machine-readable storage medium may be separate but accessible to the system 100 and the processing resource. In other examples, the processing unit(s) 202 may be implemented by electronic circuitry.
[0075] In an aspect, the processing unit(s) 202 may include the GBM algorithm/unit 106, the control unit 108, and other unit(s) 206. The other UNITS(s) 206 may implement functionalities that supplement applications or functions performed by the system 100 or the processing unit(s) 202.
[0076] Further, the data 204 may include input data 208, pre-stored data 210, and other data 212 that is either stored or generated as a result of functionalities implemented by any of the components of the processing unit(s) 202. In some aspects, the data 204 may be stored in the memory 112 in the form of various data structures. Additionally, data 204 can be organized using data models, such as relational or hierarchical data models. The other data 212 may be stored data, including temporary data and temporary files, generated by the processing unit(s) 202 for performing the various functions of the system 100.
[0077] In operation, referring to the description of the FIG. 1A, the GBM algorithm/unit 106 associated with the plurality of thermocouples 104 may determine the breakoutability index based on the predefined breakoutability data.
[0078] In some aspects, upon receiving the temperature inputs from the plurality of thermocouples 104, the GBM algorithm/unit 106 may determine a plurality of input temperature sets corresponding to the temperature inputs received from each of the plurality of thermocouples 104, and may correlate the determined plurality of input temperature sets and the corresponding degrees of membership with the associative matrix as shown in the FIG. 2B. Based on the correlation, the GBM algorithm/unit 106 may determine a plurality of output breakoutability sets corresponding to the plurality of input temperature sets in accordance with the corresponding degrees of membership. Further, the GBM algorithm/unit 106 may determine a breakoutability index corresponding to the determined plurality of output breakoutability sets. The breakoutability index may indicate the occurrence of a sticker in the mould 102.
[0079] For indicating the occurrence of the sticker in the mould 102, the GBM algorithm/unit 106 may de-fuzzify the breakoutability index i.e. the breakoutability index may be converted into a form that the temperature inputs were initially received by the GBM algorithm/unit 106. In an aspect, the breakoutability index may be a numerical value ranging from 0 to 100, where value “0” may indicate the absence of the sticker and value “100” may indicate the presence of a most severe sticker in the mould 102.
[0080] In some aspects, upon affirmative indication of the occurrence of the sticker by the GBM algorithm/unit 106, the control unit 108 may receive the breakoutability index from the GBM algorithm/unit 106. Further, the control unit 108 may receive real-time temperature variation patterns from a plurality of thermocouples 104 arranged in a plurality of layers on the mould 102. The plurality of layers may include, but not limited to, the first layer 102a, the second layer 102b, the third layer 102c and the fourth layer 102d. The breakoutability index and the temperature variation patterns received by the control unit 108 may be stored as the input data 208. Exemplary temperature variation patterns may be as shown in FIG.3A.
[0081] In some aspects, the control unit 108 may determine the possibility of occurrence of the sticker, in each of the plurality of layers, by evaluating discrete variables of a sticker signature in the real-time temperature variation patterns. In some aspects, the variations of the sticker signature may include, but not limited to, an amplitude of the temperature, a slope of the temperature, a rise in the temperature, a fall in the temperature, a time taken for rise in the temperature, and a time taken for fall in the temperature, a cross-over of the temperatures, and a change in casting speed. As an example, consider a sticker originates at the meniscus of the mould 102 and descends downward along a vertical segment of the plurality of thermocouples 104 belonging to the plurality of layers. When a sticker occurs in the mould 102, the real-time temperature variation patterns may show significant rise and fall in the temperature and also the cross-over of the temperatures as shown in the FIG. 3A, which otherwise would be flat. Therefore, as the sticker descends downwards through the plurality of layers of the mould 102, different conditions of a rise in the temperature, fall in the temperature and the cross-over of the temperatures may be observed.
[0082] Then, the control unit 108 may modify the discrete variables of the signature sticker by nearing their values to the determined possibility of occurrence of the sticker. For example, in case the discrete variable is the amplitude of the temperature, the control unit 108 may measure the amplitude based on slope change (slope change is shown with reference numeral 302) and then subtract fluctuations (the previous fluctuation is shown with reference numeral 304) occurred previous to the determined possibility of occurrence of the sticker. In this way, measurement process of the control unit 108 becomes flexible and dynamic in comparison to the state of the measurement process in which a fixed 60 seconds time frame was analysed to ascertain an average amplitude of the signature sticker. In another example, where the discrete variable is the cross-over of the temperatures, the control unit 108 modifies the discrete variable by using the temperature difference considered in the previous ascertainment of or modification of the cross-over of the temperatures
[0083] Further, the control unit 108 may perform a core probability calculation on the modified discrete variables using Gradient Boosting Machine (GBM) model to provide a classified output as shown in FIG. 3B. On the output of the GBM model, the control unit 108 may apply user-defined filters. In an aspect, the user-defined filters are based on the relationship of physical properties of elements involved in the continuous casting process. For instance, in case a layer 1 of mould is thinner in comparison to a layer 2, the user-defined filter can be “layer 2 amplitude will be higher than layer 1”. Accordingly, layer 2’ amplitudes higher than the layer 1’ amplitude will be considered to trigger an alarm and data received from abnormal thermocouples will be removed.
[0084] Further, upon triggering of the alarm by the control unit 108, one or more rectifying actions may have been performed. For instance, the one or more rectifying actions may be reducing casting speed such that the liquid steel may get sufficient time to stay in the mould 102, thereby resulting in the formation of a thick shell. In some other embodiments, the one or more rectifying actions may include troubleshooting techniques such as enhancing lubrication to remove the sticker from the mould 102 prior to the next cycle of the continuous casting process.
[0085] FIG. 4 illustrates a method 400 for real-time detection of a sticker in a mould during a continuous casting process, according to an embodiment of the present disclosure. The order in which the method 400 is described is not intended to be construed as a limitation, and any number of the described method blocks can be combined in any appropriate order to carry out the method 400 or an alternative method. Additionally, individual blocks may be deleted from the method 400 without departing from the scope of the subject matter described herein.
[0086] At block 402, the method 400 includes receiving, at a control unit 108, real-time temperature variation patterns from the plurality of thermocouples 104.
[0087] At block 404, the method 400 includes determining, by the control unit 108, discrete variables of a sticker signature in the real-time temperature variation patterns. In an aspect, the discrete variables of the sticker signature comprises one or more of an amplitude of the temperature, a slope of the temperature, a rise in the temperature, a fall in the temperature, a time taken for rise in the temperature, a time taken for fall in the temperature, a cross-over of the temperatures, and a change in casting speed. Those skilled in the art can appreciate that other varibales of the sticker signature which are not mentioned here can considered for the implementation of the present disclosure.
[0088] At block 406, the method 400 includes modifying, by the control unit 108, the discrete variables by nearing their values to the determined possibility of occurrence of the sticker;
[0089] At block 408, the method 400 includes performing, by the control unit 108, a core probability calculation on the modified discrete variables using a Gradient Boosting Machine (GBM) unit 106.
[0090] At block 410, the method 400 includes applying, by the control unit 108, user-defined filters on an output of the GBM unit 106 to remove data received from abnormal thermocouples.
Equivalents:
[0091] A description of an embodiment with several components in communication with each other does not imply that all such components are required. On the contrary, a variety of optional components are described to illustrate the wide variety of possible embodiments of the invention. When a single device or article is described herein, it will be apparent that more than one device/article (whether or not they cooperate) may be used in place of a single device/article. Similarly, where more than one device or article is described herein (whether or not they cooperate), it will be apparent that a single device/article may be used in place of the more than one device or article or a different number of devices/articles may be used instead of the shown number of devices or programs. The functionality and/or the features of a device may be alternatively embodied by one or more other devices which are not explicitly described as having such functionality/features. Thus, other embodiments of the invention need not include the device itself.
[0092] The specification has described a system and a method for real-time detection of a sticker in a mould during a continuous casting process. The illustrated steps are set out to explain the exemplary embodiments shown, and it should be anticipated that on-going 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 art(s) 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.
[0093] Finally, the language used in the specification has been principally selected for readability and instructional purposes, and it may not have been selected to delineate or circumscribe the inventive subject matter. It is therefore intended that the scope of the invention be limited not by this detailed description, but rather by any claims that issue on an application based here on. Accordingly, the embodiments of the present invention are intended to be illustrative, but not limiting, of the scope of the invention, which is set forth in the following claims.
Referral numerals

Reference Number Description
100 System
102 Mould
102a First layer
102b Second layer
102c Third layer
102d Fourth layer
104 Plurality of thermocouples
106 GBM Algorithm/Unit
108 Control unit
110 I/O interface
112 Memory
114 Processor
202 Processing Unit
204 Data
208 Input data
210 Pre-stored data
212 Other data
302 Temperature Amplitude
304 Previous Fluctuation

Claims:1. A breakout detection system (100) for real-time detection of a sticker in a mould (102) during a continuous casting process, the system (100) comprising:
a plurality of thermocouples (104) arranged at each of a plurality of layers of the mould (102);
a control unit (108) associated with the plurality of thermocouples (104), configured to:
receive real-time temperature variation patterns from the plurality of thermocouples (104);
determine discrete variables of a sticker signature in the real-time temperature variation patterns;
modify the discrete variables of the signature sticker by nearing their values to the determined possibility of occurrence of the sticker;
perform a core probability calculation on the modified discrete variables using a Gradient Boosting Machine (GBM) unit (106); and
apply user-defined filters on an output of the GBM unit (106) to remove data received from abnormal thermocouples.

2. .The system (100) as claimed in claim 1, wherein the predefined time interval for receiving the temperature inputs is one second.

3. The system (100) as claimed in claim 1, wherein the discrete variables of the sticker signature comprises one or more of an amplitude of the temperature, a slope of the temperature, a rise in the temperature, a fall in the temperature, a time taken for rise in the temperature, a time taken for fall in the temperature, a cross-over of the temperatures, and a change in casting speed.

4. The system (100) as claimed in claim 3, wherein the control unit (108) modifies the discrete variables, including the amplitude of the temperature, by taking the amplitude based on slope change and then subtracting fluctuations occurred previous to the determined possibility of occurrence of the sticker.

5. The system (100) as claimed in claim 3, wherein the control unit (108) modifies the discrete variables, including the cross-over of the temperatures, by using the temperature difference prior to sticker event.

6. The system (100) as claimed in claim 1, wherein the user-defined filters are based on the relationship of physical properties of elements involved in the continuous casting process.

7. The system (100) as claimed in claim 1, wherein the plurality of layers of the mould (102) comprises a first layer (102a), a second layer (102b), a third layer (102c) and a fourth layer (102d), along a vertical segment of the mould (102).

8. The system (100) as claimed in claim 1, wherein the control unit (108) is further configured to trigger an alarm upon indicating the presence of the sticker in the mould (102), for initiating one or more rectifying actions.

9. A method for real-time detection of a sticker in a mould (102) during a continuous casting process, the method comprising:
receiving, at a control unit (108), real-time temperature variation patterns from the plurality of thermocouples (104)
determining, by the control unit (108), a discrete variables of a sticker signature in the real-time temperature variation patterns;
modifying, by the control unit (108), the discrete variables by nearing their values to the determined possibility of occurrence of the sticker;
performing, by the control unit (108), a core probability calculation on the modified discrete variables using a Gradient Boosting Machine (GBM) unit (106); and
applying, by the control unit (108), user-defined filters on an output of the Gradient Boosting Machine (GBM) unit (106) to remove data received from abnormal thermocouples.

10. The method as claimed in claim 9, wherein the temperature inputs comprise rate of the rise of the temperature and magnitude rise of the temperature.

11. The method as claimed in claim 9, wherein the predetermined time interval for receiving the temperature inputs is one second.

12. The method as claimed in claim 9, wherein the discrete variables of the sticker signature comprises one or more of an amplitude of the temperature, a slope of the temperature, a rise in the temperature, a fall in the temperature, a time taken for rise in the temperature, a time taken for fall in the temperature, a cross-over of the temperatures, and a change in casting speed

13. The method as claimed in claim 12, wherein the modifying the discrete variables, including the amplitude of the temperature, comprising taking the amplitude based on slope change and then subtracting fluctuations occurred previous to the determined possibility of occurrence of the sticker.

14. The method as claimed in claim 12, wherein modifying the discrete variables, including the cross-over of the temperatures, comprising using the temperature difference considered in the previous modifications of the discrete variables.

15. The method as claimed in claim 9, wherein the user-defined filters are based on the relationship of physical properties of elements involved in the continuous casting process.

16. The method as claimed in claim 9, wherein the plurality of layers of the mould (102) comprises a first layer (102a), a second layer (102b), a third layer (102c) and a fourth layer (102d), along a vertical segment of the mould (102).

17. The method as claimed in claim 9 further comprises triggering an alarm upon indicating the presence of the sticker in the mould (102) for initiating one or more rectifying actions.