Molten iron composition control method and molten iron smelting system
Patent Information
- Application Number
- CN202610916258.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2026-06-24
- Publication Date
- 2026-09-18
AI Technical Summary
然而，回收的磷生铁中碳、硅、锰、磷、硫等元素含量因来源不同而差异巨大，且无法提前准确估量
Smart Images
Figure CN122773065A_ABST
Abstract
Description
Technical Field
[0001] This disclosure relates to the field of iron smelting technology, and more specifically, to a method for controlling the composition of molten iron and an iron smelting system. Background Technology
[0002] In the anode assembly workshop, the smelting of pig iron largely utilizes recycled scrap electrodes and waste conductor rods as raw materials. However, the content of elements such as carbon, silicon, manganese, phosphorus, and sulfur in the recycled pig iron varies greatly depending on the source, and cannot be accurately estimated in advance. This "unknowability" of raw material composition poses a significant challenge to the precise control of the molten iron composition. Summary of the Invention
[0003] In view of this, the present disclosure provides a method for controlling the composition of molten iron and a molten iron smelting system.
[0004] One aspect of this disclosure provides a method for controlling molten iron composition, comprising: performing reverse calculation of raw material deviation based on molten iron composition deviation data of the current furnace batch, determining the equivalent raw material deviation amount of each of multiple raw materials for the current furnace batch, wherein the molten iron composition deviation data indicates the difference between the measured values and expected values of multiple elements in the molten iron, the raw materials are used to smelt molten iron in an induction furnace, and the equivalent raw material deviation amount indicates the difference between the input amount of the raw material and the actual demand amount; for each raw material, based on the equivalent raw material deviation amount composed of the equivalent raw material deviation amount of the current furnace batch and the historical equivalent raw material deviation amounts of multiple historical furnace batches... The differential sequence determines the equivalent raw material deviation trend information; according to the update strategy matching the equivalent raw material deviation trend information, based on the equivalent raw material deviation of the current heat, the historical cumulative raw material deviation of the previous heat is updated to determine the cumulative raw material deviation of the current heat; and based on the raw material compensation amount of the next heat determined by the cumulative raw material deviation of the current heat, the basic input amount of raw materials for the next heat is compensated to determine the target input amount of raw materials for the next heat. The basic input amount is determined by following the raw material conservation principle and based on the expected data of the molten iron composition of the next heat.
[0005] According to embodiments of this disclosure, based on the iron composition deviation data of the current furnace, a reverse calculation of raw material deviation is performed to determine the equivalent raw material deviation of each of the multiple raw materials for the current furnace. This includes: for each element in the iron, determining the content ratio of the element in the target raw material and the element's yield, wherein the target raw material is used to obtain the element in the iron during smelting, and the target raw material is determined from multiple raw materials; and based on the element deviation data of the elements in the iron composition deviation data of the current furnace, the content ratio of the elements in the raw materials, the element's yield, and the expected iron composition data of the current furnace, determining the equivalent raw material deviation of the raw materials for the current furnace.
[0006] According to embodiments of this disclosure, based on the equivalent raw material deviation trend information, the historical cumulative raw material deviation of the previous furnace is updated according to the equivalent raw material deviation of the current furnace to determine the cumulative raw material deviation of the current furnace. This includes: when the trend type indicated by the equivalent raw material deviation trend information includes a full-volume unidirectional shift, the equivalent raw material deviation of the current furnace and the historical cumulative raw material deviation of the previous furnace are accumulated according to a full-volume enhancement update strategy to determine the cumulative raw material deviation of the current furnace. The long-term unidirectional shift indicates that the values of multiple equivalent raw material deviations from different furnaces are all greater than or all less than a predetermined value; when the trend type indicated by the equivalent raw material deviation trend information includes random fluctuations... According to the attenuation update strategy, the historical cumulative deviation of raw materials in the previous heat is attenuated using an adjustment factor to determine the cumulative deviation of raw materials in the current heat. Random fluctuation indicates that the values of multiple equivalent raw material deviations in different heats are different in sign. When the trend type indicated by the equivalent raw material deviation trend information includes local same-direction shift, the equivalent raw material deviation of the current heat and the historical cumulative deviation of raw materials in the previous heat are weighted and accumulated according to the local update strategy to determine the cumulative deviation of raw materials in the current heat. Short-term same-direction shift indicates that the values of multiple equivalent raw material deviations in different heats are all greater than or all less than the predetermined value, and the number of heats in which local same-direction shift occurs is less than the number of heats in which full same-direction shift occurs.
[0007] According to embodiments of this disclosure, the method further includes: determining a decay factor for adjusting the cumulative deviation of the current heat based on an equivalent raw material deviation sequence; adjusting the cumulative raw material deviation of the current heat based on the decay factor of the current heat; and determining the raw material compensation amount for the next heat.
[0008] According to embodiments of this disclosure, determining an attenuation factor for adjusting the cumulative deviation of a current furnace based on an equivalent raw material deviation sequence includes: determining a set of deviation change parameters based on multiple element deviation data of the same element in different furnaces; and determining an attenuation factor that matches the set of deviation change parameters.
[0009] According to embodiments of this disclosure, determining an attenuation factor that matches a set of deviation change parameters includes: using the attenuation factor that matches the set of deviation change parameters as an initial attenuation factor; adjusting the initial attenuation factor based on equivalent raw material deviation trend information to obtain an adjusted attenuation factor; and determining the attenuation factor based on the adjusted attenuation factors of each of the multiple raw materials.
[0010] According to embodiments of this disclosure, based on the raw material compensation amount for the next heat determined by the cumulative raw material deviation of the current heat, the basic input amount of raw materials for the next heat is compensated to determine the target input amount of raw materials for the next heat. This includes: determining the initial compensation input amount of raw materials for the next heat based on the raw material compensation amount and the basic input amount of the next heat; determining the target input amount of raw materials for the next heat based on the process reference amount if the initial compensation input amount for the next heat does not match the process reference amount, wherein the process reference amount is determined based on the safety performance conditions and equipment performance conditions of smelting molten iron; and determining the target input amount based on the initial compensation input amount if the initial compensation input amount matches the process reference amount.
[0011] According to embodiments of this disclosure, the method further includes: determining the elemental material balance equation for each element based on the expected data of the molten iron composition of the next heat, the yield of each element, and the content of each element in the recovered pig iron from the current heat, and using the basic input amount of each raw material for the next heat as an unknown; determining the raw material material balance equation based on the basic input amount of each raw material for the next heat and the expected data of the molten iron composition of the next heat; and determining the basic input amount of each raw material for the next heat based on the elemental material balance equation and the raw material material balance equation.
[0012] According to embodiments of this disclosure, the method further includes: if the deviation data of molten iron composition in the current heat matches a predetermined deviation threshold, the basic input amount of raw materials for the next heat is used as the target input amount of raw materials for the next heat.
[0013] Another aspect of this disclosure provides an iron smelting system, comprising: an intermediate frequency furnace configured to smelt fed raw materials to produce molten iron; a controller configured to determine the target input amount of each raw material for the next heat based on measured data of the molten iron composition of the current heat and expected data of the molten iron composition of the current heat, wherein the measured data of the molten iron composition of the current heat is obtained by measuring the composition of the molten iron in the intermediate frequency furnace for the current heat; and a feeder configured to feed each raw material into the intermediate frequency furnace according to the target input amount of each raw material for the next heat. Attached Figure Description
[0014] The above and other objects, features and advantages of this disclosure will become clearer from the following description of embodiments with reference to the accompanying drawings, in which:
[0015] Figure 1 An exemplary system architecture for a hot metal smelting system to which this disclosure can be applied is illustrated schematically;
[0016] Figure 2 A flowchart illustrating a method for controlling molten iron composition according to an embodiment of the present disclosure is shown schematically.
[0017] Figure 3A An equivalent raw material deviation curve showing a full-volume unidirectional offset trend is schematically illustrated according to an embodiment of the present disclosure;
[0018] Figure 3B An equivalent raw material deviation curve exhibiting a random fluctuation trend is schematically shown according to an embodiment of the present disclosure;
[0019] Figure 3C An equivalent raw material deviation curve showing a partial unidirectional shift is schematically illustrated according to an embodiment of the present disclosure;
[0020] Figure 4 A flowchart illustrating a method for controlling molten iron composition according to another embodiment of this disclosure is shown schematically; and
[0021] Figure 5 A block diagram of an electronic device suitable for implementing a method for controlling the composition of molten iron according to an embodiment of the present disclosure is shown schematically. Detailed Implementation
[0022] The embodiments of the present disclosure will now be described with reference to the accompanying drawings. However, it should be understood that these descriptions are exemplary only and are not intended to limit the scope of the disclosure. In the following detailed description, numerous specific details are set forth to provide a thorough understanding of the embodiments of the present disclosure for ease of explanation. However, it will be apparent that one or more embodiments may be practiced without these specific details. Furthermore, descriptions of well-known structures and techniques are omitted in the following description to avoid unnecessarily obscuring the concepts of the present disclosure.
[0023] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit this disclosure. The terms “comprising,” “including,” etc., as used herein indicate the presence of the stated features, steps, operations, and / or components, but do not exclude the presence or addition of one or more other features, steps, operations, or components.
[0024] All terms used herein (including technical and scientific terms) have the meanings commonly understood by those skilled in the art, unless otherwise defined. It should be noted that the terms used herein are to be interpreted in a manner consistent with the context of this specification, and not in an idealized or overly rigid way.
[0025] When using expressions such as "at least one of A, B and C", they should generally be interpreted in accordance with the meaning that is commonly understood by those skilled in the art (e.g., "a system having at least one of A, B and C" should include, but is not limited to, a system having A alone, a system having B alone, a system having C alone, a system having A and B, a system having A and C, a system having B and C, and / or a system having A, B and C, etc.).
[0026] This disclosure provides a method for controlling molten iron composition, comprising: performing reverse calculation of raw material deviation based on molten iron composition deviation data of the current furnace, and determining the equivalent raw material deviation amount of each of multiple raw materials for the current furnace, wherein the molten iron composition deviation data indicates the difference between the measured values and expected values of multiple elements in the molten iron, the raw materials are used to smelt molten iron in an induction furnace, and the equivalent raw material deviation amount indicates the difference between the input amount of the raw material and the actual demand amount. For each raw material, based on the equivalent raw material deviation amount sequence composed of the equivalent raw material deviation amount of the current furnace and the historical equivalent raw material deviation amounts of multiple historical furnaces, the equivalent raw material deviation trend information of the raw material is determined. According to an update strategy matching the equivalent raw material deviation trend information, based on the equivalent raw material deviation amount of the current furnace, the historical cumulative raw material deviation amount of the previous furnace is updated to determine the cumulative raw material deviation amount of the current furnace. Based on the raw material compensation amount for the next heat determined by the cumulative deviation of raw materials in the current heat, the basic input amount of raw materials for the next heat is compensated, and the target input amount of raw materials for the next heat is determined. The basic input amount is determined by following the principle of raw material conservation and based on the expected data of molten iron composition for the next heat.
[0027] This control method can be integrated into the controller of the molten iron smelting system to precisely control the amount of raw materials added to the medium-frequency furnace by the feeder, so that the measured data of molten iron composition is close to the expected data of molten iron composition.
[0028] Figure 1 An exemplary system architecture 100 of an iron smelting system according to an embodiment of the present disclosure is illustrated schematically. It should be noted that... Figure 1 The examples shown are merely examples of system architectures that can be applied to the embodiments of this disclosure, in order to help those skilled in the art understand the technical content of this disclosure, but do not mean that the embodiments of this disclosure cannot be used in other devices, systems, environments or scenarios.
[0029] like Figure 1 As shown, the system architecture 100 according to this embodiment may include: an intermediate frequency furnace 101, a controller 102, and a feeder 103.
[0030] The medium-frequency furnace 101 is configured to smelt the input raw materials to produce molten iron.
[0031] The controller 102 is configured to execute the hot metal composition control method provided in this embodiment of the present disclosure based on the measured data of the hot metal composition of the current heat and the expected data of the hot metal composition of the current heat, and to determine the target input amount of each raw material for the next heat.
[0032] The expected data for the molten iron composition of the current heat includes the expected content of each component in the molten iron, which is the target data. The measured data for the molten iron composition of the current heat is based on the composition measurement of the molten iron in the current heat of medium-frequency furnace 101, and is the actual data.
[0033] The feeder 103 is configured to feed each raw material into the intermediate frequency furnace 101 according to the target input amount for the next heat. The target input amount of each raw material for the next heat is fed into the intermediate frequency furnace for smelting to obtain molten iron with the desired composition data.
[0034] The main task of the intermediate frequency furnace in the anode assembly workshop is to melt molten iron to cast anode steel claw protective rings. To ensure that the physical properties (such as hardness and brittleness) of the anode steel claw protective rings are consistent, the process specifications require that the carbon, silicon, manganese and other elemental compositions of the molten iron be kept stable at a pre-set expected value for a long period of time in order to ensure the requirements of process implementation.
[0035] The controller can be used to perform the following actions based on the molten iron generated by the medium-frequency furnace. Figure 2 The illustrated method for controlling the composition of molten iron determines the target input amount of each raw material for the next heat, ensuring it meets expectations. Based on this, the feeder is controlled to input each raw material into the induction furnace according to the target input amount for the next heat, thereby improving the long-term stability of the molten iron's composition.
[0036] Figure 2 A flowchart illustrating a method for controlling the composition of molten iron according to an embodiment of the present disclosure is shown.
[0037] like Figure 2 As shown, the method includes operations S201 to S204.
[0038] In operation S201, based on the hot metal composition deviation data of the current furnace, the raw material deviation is calculated in reverse to determine the equivalent raw material deviation of each of the multiple raw materials for the current furnace.
[0039] Iron composition deviation data indicates the difference between the measured and expected values of multiple elements in molten iron. Equivalent raw material deviation indicates the difference between the amount of raw material input and the actual demand.
[0040] Taking the process of smelting molten iron in an intermediate frequency furnace using recycled materials, carbon raisers, ferrosilicon, ferromanganese and other raw materials as an example, the elements in the molten iron include carbon (C), silicon (Si), manganese (Mn) and other elements.
[0041] Based on the expected composition data for the current furnace run, such as the expected values for carbon, silicon, and manganese, material conservation calculations can be performed to determine the input quantity of each raw material for the current furnace run. Then, according to the input quantity of each raw material for the current furnace run, they are fed into the induction furnace for smelting to obtain molten iron. After the molten iron is purified and reaches the predetermined temperature, samples are taken using a sampling device, and the content of each element in the molten iron for the current furnace run is detected using an analyzer to obtain measured data of the molten iron composition. For example, the measured data of the molten iron composition for the current furnace run includes the measured values of carbon, silicon, and manganese. Based on the differences between the measured values and expected values of multiple elements in the molten iron, the deviation data of the molten iron composition for the current furnace run is determined, such as the elemental deviation data for carbon, silicon, and manganese.
[0042] Based on the elemental deviation data of each element, the raw material deviation can be calculated in reverse, thereby determining the equivalent raw material deviation of the input raw materials.
[0043] For example, if the elemental deviation data for carbon in the molten iron composition deviation data indicates that the measured value is greater than the expected value, it can be determined that the amount of raw material recarburizer added is excessive. Conversely, if the elemental deviation data for carbon in the molten iron composition deviation data indicates that the measured value is less than the expected value, it can be determined that the amount of raw material recarburizer added is insufficient.
[0044] Based on the principle of material conservation, material conversions can be performed to determine the equivalent raw material deviation for each raw material in the current furnace batch. For example, based on the elemental deviation data of carbon, the equivalent raw material deviation of the recarburizer can be determined. Consistent with the carbon conversion method, the equivalent raw material deviation of ferrosilicon can also be determined based on the elemental deviation data of silicon. Similarly, the equivalent raw material deviation of ferromanganese can be determined based on the elemental deviation data of manganese.
[0045] In operation S202, for each raw material, the equivalent raw material deviation trend information is determined based on the equivalent raw material deviation sequence composed of the equivalent raw material deviation of the current furnace and the historical equivalent raw material deviation of multiple historical furnaces.
[0046] In the actual production scenario of an induction furnace in an anode assembly workshop, recycled materials, such as solid pig iron, are a batch of waste. The characteristics of the recycled materials from several consecutive furnaces are similar, and thus the feeding and targets between multiple furnace batches are highly similar and follow a predictable pattern. If the content of the recycled material in the previous furnace was higher than expected, it means that "the overall carbon content of the recycled material currently being used may be higher than expected."
[0047] The deviation trend information of equivalent raw materials can be determined based on the equivalent raw material deviation sequence. By analyzing the deviation trend indicated by this information, patterns can be identified, guiding the dynamic adjustment of subsequent raw material addition amounts. This eliminates the need to predict "future raw material composition," fundamentally transforming the control basis from unreliable "predicted values" to reliable "historical measured values." This feedback loop is entirely based on the deterministic principle of material conservation and measured data, eliminating prediction errors at the source.
[0048] In operation S203, following an update strategy that matches the equivalent raw material deviation trend information, the historical cumulative raw material deviation of the previous furnace is updated based on the equivalent raw material deviation of the current furnace to determine the cumulative raw material deviation of the current furnace.
[0049] Multiple candidate update strategies can be pre-determined, and the equivalent raw material deviation trend information can be used for screening. The update strategy that matches the equivalent raw material deviation trend information can be determined from the multiple candidate update strategies, thereby improving the diversity and universality of update strategies.
[0050] By using an update strategy that matches the deviation trend information of equivalent raw materials, the deviation amount can be accumulated: the equivalent raw material deviation amounts of multiple furnaces are accumulated to form a raw material accumulated deviation amount with "memory" function, ensuring that the continuous deviation is continuously corrected and achieving zero steady-state error convergence.
[0051] In operation S204, based on the raw material compensation amount for the next heat determined by the cumulative raw material deviation of the current heat, the basic input amount of raw materials for the next heat is compensated, and the target input amount of raw materials for the next heat is determined.
[0052] The cumulative raw material deviation of the current heat can be used as the raw material compensation amount for the next heat. However, it is not limited to this. The cumulative raw material deviation of the current heat can also be combined with a correction factor to determine the raw material compensation amount for the next heat.
[0053] The base input is determined based on the expected hot metal composition data for the next heat, according to the principle of raw material conservation. By compensating the base input for the next heat with the raw material compensation amount, the actual raw material input can be made to match the expected hot metal composition data.
[0054] According to embodiments of this disclosure, a novel feedback control strategy of "correcting the unknown with the known and driving convergence with deviation" is adopted. This strategy can be implemented without relying on accurate prediction of unknown raw material composition. Instead, it can convert the already occurring, deterministic deviation data of molten iron composition into "equivalent raw material deviation" through the principle of material balance. In the next batch of feed, the cumulative deviation is used to adjust the raw material compensation amount, thereby driving the molten iron composition to converge to the desired data in cross-batch production in a forced, rapid, and stable manner.
[0055] In relevant examples, a deep learning model can be used to train the ability to predict composition changes in future furnace batches, resulting in a composition prediction model. This model then predicts the composition changes in future furnace batches, and the optimal feed rate is calculated based on the predicted values.
[0056] Compared with this method, the molten iron composition control method provided in this disclosure can avoid lag and insufficient accuracy in composition control when the raw material composition fluctuates drastically.
[0057] According to embodiments of this disclosure, for example, Figure 2 The illustrated operation S201, based on the iron composition deviation data of the current heat, performs a reverse calculation of raw material deviation to determine the equivalent raw material deviation of each of the multiple raw materials for the current heat. This may include: for each element in the iron, determining the content ratio of the element in the target raw material and the element's yield, wherein the target raw material is used to obtain the element in the iron during smelting, and the target raw material is determined from multiple raw materials. Based on the element deviation data of the elements in the iron composition deviation data of the current heat, the content ratio of the elements in the raw materials, the element's yield, and the expected iron composition data of the current heat, the equivalent raw material deviation of the raw materials for the current heat is determined.
[0058] Taking carbon (C), silicon (Si), and manganese (Mn) as the main controlling elements for molten iron, and raw materials such as recarburizers, ferrosilicon, ferromanganese, and recycled materials as examples, Table 1 defines and explains the parameters. Among them, recarburizers, ferrosilicon, and ferromanganese are the raw materials whose target input amounts for the next heat are to be adjusted.
[0059] Table 1 - Parameter Definitions
[0060]
[0061] Taking the deviation between the measured value of carbon in the current furnace and the expected value as an example, the "carbon element deviation data" is converted into the "equivalent raw material deviation of the carbon additive".
[0062] Let P be the effective content ratio of the carbon raiser. carb The yield is η C , This represents the elemental deviation data for carbon.
[0063] The equivalent raw material deviation of the recarburizer in the current furnace batch is expressed as follows: (Unit: kg), see the following formula for details.
[0064] .
[0065] like If ΔM > 0, then ΔMcarb(k) A positive value means "equivalent to adding more". "Carbonizer".
[0066] like If ΔM < 0, then ΔM carb(k) A negative value means "equivalent to adding less". "Carbonizer".
[0067] The elemental deviation data for carbon in the current furnace can be determined as follows. For example, suppose that the k-th furnace smelting is completed, and the measured value of carbon is... The expected value of carbon is .
[0068] Elemental deviation data for carbon .
[0069] > 0: The carbon content is too high, indicating that "too much carbon has been added to this furnace".
[0070] < 0: The carbon content is too low, indicating that "too little carbon was added" to this furnace.
[0071] Optionally, the methods for determining the equivalent raw material deviation of ferrosilicon used to obtain silicon in molten iron and the equivalent raw material deviation of manganese used to obtain manganese in molten iron are similar to those for determining the equivalent raw material deviation of carburizing agent, and will not be repeated here.
[0072] According to embodiments of this disclosure, by converting the original deviation data into equivalent raw material deviation amounts, the quantification capability of raw material addition can be improved, thereby improving the correction accuracy and precision of raw material addition amounts.
[0073] According to embodiments of this disclosure, for example, Figure 2 The operation S202 shown, based on the equivalent raw material deviation sequence composed of the equivalent raw material deviation of the current furnace and the historical equivalent raw material deviations of multiple historical furnaces, determines the equivalent raw material deviation trend information. This may include: determining the equivalent raw material deviation curve based on the equivalent raw material deviation sequence; and determining the equivalent raw material deviation trend information based on the trend type indicated by the equivalent raw material deviation curve.
[0074] With the furnace number as the horizontal axis and the equivalent raw material deviation as the vertical axis, multiple equivalent raw material deviation points can be marked on a two-dimensional coordinate graph based on the equivalent raw material deviation sequence.
[0075] Curve fitting can be performed based on multiple equivalent raw material deviation points to obtain the equivalent raw material deviation curve.
[0076] According to embodiments of this disclosure, the equivalent raw material deviation trend information of the raw material is determined based on the equivalent raw material deviation curve, thereby improving the visualization of the equivalent raw material deviation trend information. In addition, multiple data of the equivalent raw material deviation quantity sequence are used for trend identification, thereby improving the identification accuracy and effectiveness.
[0077] According to embodiments of this disclosure, for example, Figure 2 Operation S203, as shown, updates the historical cumulative raw material deviation of the previous furnace based on the equivalent raw material deviation of the current furnace using an update strategy that matches the equivalent raw material deviation trend information. This determines the current furnace's cumulative raw material deviation by: If the trend type indicated by the equivalent raw material deviation trend information includes a full-volume unidirectional shift, then using a full-volume enhancement update strategy, the equivalent raw material deviation of the current furnace and the historical cumulative raw material deviation of the previous furnace are accumulated to determine the current furnace's cumulative raw material deviation. Here, a long-term unidirectional shift indicates that the values of multiple equivalent raw material deviations from different furnaces are all greater than or less than a predetermined value. If the trend type indicated by the equivalent raw material deviation trend information includes random fluctuations, then using a decay update strategy, the historical cumulative raw material deviation of the previous furnace is decayed using an adjustment factor to determine the current furnace's cumulative raw material deviation. Here, random fluctuations indicate that the values of multiple equivalent raw material deviations from different furnaces have different positive and negative values. When the trend type indicated by the equivalent raw material deviation trend information includes local same-direction offset, the equivalent raw material deviation of the current furnace and the historical cumulative raw material deviation of the previous furnace are weighted and accumulated according to the local update strategy to determine the cumulative raw material deviation of the current furnace. Among them, the short-term same-direction offset indicates that the values of multiple equivalent raw material deviations of different furnaces are all greater than or less than the predetermined value, and the number of furnaces in which local same-direction offset occurs is less than the number of furnaces in which full same-direction offset occurs.
[0078] Optionally, the predetermined value can be 0.
[0079] Figure 3A An equivalent raw material deviation curve showing a full-volume unidirectional offset trend is schematically illustrated according to an embodiment of the present disclosure.
[0080] like Figure 3A As shown, when multiple furnaces exhibit "same-direction deviation", the ordinates of all points on the equivalent raw material deviation curve are in the same direction and are greater than 0.
[0081] For example, greater than 0 or less than 0.
[0082] When the trend type shows a uniform shift in the same direction across the entire quantity, it means that the material being processed on-site has an overall elemental content that is either too high or too low. In this case, full accumulation can be used to strengthen memory and accelerate convergence, thereby forming a strong and continuous compensation.
[0083] The equivalent raw material deviation of the current furnace batch Cumulative deviation of historical raw materials from the previous batch Accumulate the data to determine the cumulative raw material deviation for the current furnace batch. The result can be determined using the following formula.
[0084] .
[0085] Figure 3B An equivalent raw material deviation curve exhibiting a random fluctuation trend is schematically shown according to an embodiment of the present disclosure.
[0086] like Figure 3B As shown, when multiple furnaces experience "disorderly jumps", the vertical coordinates of each point on the equivalent raw material deviation curve fluctuate randomly. For example, the value of the equivalent raw material deviation in the first furnace is greater than 0, the value of the equivalent raw material deviation in the second furnace is less than 0, and the value of the equivalent raw material deviation in the third furnace is greater than 0 again.
[0087] When the trend exhibits random fluctuations, it means there is no discernible pattern, and historical data is unreliable. In this case, without introducing new biases, and by attenuating the accumulated biases of existing raw materials, potentially erroneous memories are gradually released, achieving active filtering.
[0088] Using regulatory factors Cumulative deviation of historical raw materials from the previous batch Perform attenuation to determine the cumulative raw material deviation for the current furnace batch. The result can be determined using the following formula.
[0089] .
[0090] Figure 3C The diagram illustrates an equivalent feed deviation curve with a partial unidirectional offset according to an embodiment of the present disclosure.
[0091] like Figure 3C As shown, when multiple furnaces exhibit "same-direction deviation", the vertical coordinates of all points on the equivalent raw material deviation curve are in the same direction, for example, greater than 0 or less than 0.
[0092] When the trend shows a localized unidirectional deviation, the number of furnaces exhibiting this phenomenon is not reliable enough. For example, historical deviations are unreliable; the previous furnace's higher yield was merely due to the accidental use of specific recycled materials, while the next furnace's recycled materials are likely to be normal. If a large amount of raw material is added based on historical deviations at this point, it could artificially create a significant reverse deviation. In such cases, a weighted cumulative approach is preferable and more cautious.
[0093] The equivalent raw material deviation of the current furnace batch Cumulative deviation of historical raw materials from the previous batch Perform weighted accumulation to determine the cumulative raw material deviation for the current furnace. The result can be determined using the following formula.
[0094] .
[0095] The above method can be used to determine the trend type. However, it is not limited to this. The following cumulative counting method can also be used, as long as it can determine the trend type.
[0096] Define the trend marker Trend(k):
[0097] If e(k) and e(k-1) have the same sign, then Trend(k) = 1.
[0098] If e(k) and e(k-1) have opposite signs, then Trend(k) = 0.
[0099] Define a continuous in-direction counter Counter(k):
[0100] If Trend(k) = 1, then Counter(k) = Counter(k-1) + 1.
[0101] If Trend(k) = 0, then Counter(k) = 0 (reset).
[0102] If Counter(k) is greater than or equal to 2, it indicates that multiple consecutive furnace batches have shown a unidirectional deviation with either higher or lower content.
[0103] According to embodiments of this disclosure, different update strategies are employed under different trend types, combined with the coupling effect of alloy addition, to ensure control safety. Furthermore, concretizing the simple "size-speed" logic as a multi-dimensional adaptive decision based on the degree of deviation and trend type expands the range for determining the cumulative deviation, making the determination more targeted, effective, and rapid.
[0104] According to embodiments of this disclosure, when performing such Figure 2 Before operation S204, the hot metal composition control method may further include: determining a decay factor for the current heat to adjust the cumulative deviation based on an equivalent raw material deviation sequence; adjusting the cumulative raw material deviation for the current heat based on the decay factor; and determining the raw material compensation amount for the next heat.
[0105] The attenuation factor, acting as an intelligent regulator, can be dynamically adjusted. For example, based on multi-dimensional state information such as the current equivalent raw material deviation trend, equivalent raw material deviation data, and the consistency of deviations in consecutive furnaces, a coefficient between 0 and 1 is calculated in real time as the attenuation factor. This factor is used to dynamically weight the cumulative raw material deviation of the current furnace. When the equivalent raw material deviation data is large and divergent, the coefficient approaches 1, enabling a rapid and full-force response; when the equivalent raw material deviation data is small or converges on its own, the coefficient takes a smaller value, allowing the system to become smoother and more stable, avoiding over-adjustment.
[0106] Cumulative deviation of raw materials in the current furnace k After the update, the raw material compensation amount will be calculated for the next heat (e.g., the (k+1)th heat). At that time, the cumulative deviation of raw materials in the current furnace k will be combined with the dynamic attenuation factor. For combination, see the following formula.
[0107] .
[0108] According to embodiments of this disclosure, the equivalent raw material deviation is obtained by performing a reverse material balance calculation on the iron composition deviation data of the current heat, essentially indicating how much raw material was added too much or too little in the current heat. The cumulative raw material deviation is a conditional summation of the increments from all historical single heats. Based on trend consistency, the system intelligently determines whether to add, reduce, or reset, essentially representing the sum of the "unpaid bills" from all past heats. The equivalent raw material deviation serves as the "increment," and the cumulative raw material deviation serves as the "stock." The increment is incorporated into the stock of the cumulative deviation to form the updated basis for total compensation. This improves the accuracy and effectiveness of raw material compensation.
[0109] According to embodiments of this disclosure, determining an attenuation factor for adjusting the cumulative deviation in the current furnace based on an equivalent raw material deviation sequence may include: determining a set of deviation variation parameters based on multiple element deviation data from different furnaces; and determining an attenuation factor that matches the set of deviation variation parameters from a plurality of candidate attenuation factors.
[0110] The deviation change parameter group can include the amount of deviation change and the relative value of deviation.
[0111] The change in deviation Δe_k: Δe_k = e(k) - e(k-1).
[0112] The change in deviation reflects the convergence or divergence trend of element deviation data among multiple furnaces. If e(k) - e(k-1) have the same sign and a large absolute value, it indicates that the deviation is worsening; if the signs are opposite, it indicates that it is converging on its own.
[0113] The relative deviation value r_k: r_k = |e_k| / T.
[0114] Where T is the allowable component tolerance bandwidth for that element (e.g., if the target is ±0.05%, then T = 0.05%). The adjustment scale for different elements is unified using relative values.
[0115] Determining the attenuation factor that matches the set of deviation variation parameters from multiple candidate attenuation factors can include setting α = 1.0 if |r_k| > 0.8 and e(k)*Δe_k > 0.
[0116] The deviation change parameter group indicates that the components are seriously exceeding the standard and the trend continues to worsen, requiring full compensation without any attenuation.
[0117] If |r_k| > 0.8 and e(k) *Δe_k≤0, then α = 0.8.
[0118] The deviation change parameter group indicates a large deviation but is already in rapid regression. Appropriately reduce the compensation amount to avoid "overshooting".
[0119] If 0.3 < |r_k|≤0.8 and e(k)*Δe_k>0, then α = 0.6 + 0.4 * (|r_k| - 0.3) / 0.5, indicating that it increases linearly between 0.6 and 1.0, and the larger the deviation, the more aggressive the compensation.
[0120] If 0.3 < |r_k|≤0.8 and e(k)*Δe_k≤0, then α= 0.5, indicating that the compensation is based on a fixed low-to-medium intensity and relies on natural regression of the trend.
[0121] If |r_k|≤0.3, then α=0.2, indicating that the target is close, and only a small correction is needed to prevent normal analysis noise from causing back-and-forth fluctuations.
[0122] If |e_k| < L_dead (e.g., the analyzer repeatability limit), then α = 0, which is considered to have reached the target, so the compensation is frozen and the formula is locked.
[0123] According to embodiments of this disclosure, different attenuation factors are determined based on different deviation change group parameters, thereby making the determined attenuation factors targeted and effective, and improving the accuracy of the raw material compensation amount determined using the attenuation factors.
[0124] According to embodiments of this disclosure, determining an attenuation factor that matches a set of deviation change parameters includes: using the attenuation factor that matches the set of deviation change parameters as an initial attenuation factor; adjusting the initial attenuation factor based on equivalent raw material deviation trend information to obtain an adjusted attenuation factor; and determining the attenuation factor based on the adjusted attenuation factors of each of the multiple raw materials.
[0125] A "trend consistency coefficient" β can be introduced: β = (number of furnaces with continuous same-direction deviation - 1) / N_max. Where N_max represents the number of furnaces in the equivalent raw material deviation sequence.
[0126] The adjusted attenuation factor is denoted as α_final and is determined by the formula α_final = min(1.0, α * (1 + β)).
[0127] It can also perform synergistic regulation of multiple elements. For example, carbon, silicon, and manganese are the main controlled elements in pig iron with phosphorus. The adjusted attenuation factor α_C for carbon, the adjusted attenuation factor α_Si for silicon, and the adjusted attenuation factor α_Mn for manganese can be calculated independently according to the above formula. The smallest of these can be taken as the global attenuation factor to ensure that when a strong correction is made to a certain element, the content of other elements will not be excessively affected by the addition of a large amount of a single raw material.
[0128] The attenuation factor α_global = min(α_C, α_Si, α_Mn).
[0129] According to embodiments of this disclosure, the deviation change parameter group, the equivalent raw material deviation trend information, and the adjusted attenuation factors of each of the multiple raw materials are all used as reference data, thereby making the determination of the attenuation factors effective, accurate, and fast.
[0130] According to embodiments of this disclosure, for example, Figure 2 Operation S204, as shown, involves compensating the base input of raw materials for the next heat based on the raw material compensation amount determined by the cumulative raw material deviation of the current heat, and determining the target input amount of raw materials for the next heat. This can include: determining the initial compensation input amount of raw materials for the next heat based on the raw material compensation amount and the base input amount of the next heat. If the initial compensation input amount for the next heat does not match the process reference amount, the target input amount for the next heat is determined based on the process reference amount, which is determined based on the safety performance conditions and equipment performance conditions of molten iron. If the initial compensation input amount matches the process reference amount, the target input amount is determined based on the initial compensation input amount.
[0131] After multiplying the attenuation factor by the cumulative deviation of the raw materials to obtain the raw material compensation amount, it is also necessary to set the upper limit of the raw material compensation amount U_max and the lower limit of the raw material compensation amount U_min as process reference amounts to prevent the problem of adding excessive regulators in subsequent furnaces due to a single abnormally large deviation.
[0132] For example, if the raw material compensation amount exceeds the upper limit U_max, the process reference amount (the upper limit U_max) can be directly used as the raw material compensation amount to achieve anti-saturation. This strategy takes into account the coupling effect of alloy addition, ensuring the safety of control.
[0133] According to embodiments of this disclosure, in order to cope with extreme working conditions in actual production, an anti-integral saturation mechanism is used to set upper and lower limits for the final output raw material compensation amount, so as to prevent the control amount from overflowing the safe range due to a single abnormal large deviation or long-term accumulation, and to reasonably handle the excess part.
[0134] According to embodiments of this disclosure, when performing such Figure 2 Before operation S204, the hot metal control method may further include: determining the elemental material balance equation for each element based on the expected hot metal composition data for the next heat, the yield of each element, and the content of each element in the recovered pig iron from the current heat, using the basic input amount of each raw material for the next heat as unknowns. The raw material material balance equation is determined based on the basic input amount of each raw material for the next heat and the expected hot metal composition data for the next heat. The basic input amount of each raw material for the next heat is determined based on the elemental material balance equation and the raw material material balance equation.
[0135] Elemental material balance equations can include material balance equations for carbon, silicon, and manganese.
[0136] Material balance equation for carbon element: .
[0137] Material balance equation for silicon: .
[0138] Material balance equation for manganese: .
[0139] Raw material balance equation: + + + = .
[0140] By solving the system of equations, the basic input amounts of carbon raiser, ferrosilicon, and ferromanganese for the next heat can be obtained.
[0141] According to embodiments of this disclosure, the basic input amount of raw materials is determined by utilizing the principles of element balance and raw material balance, which can improve the effectiveness of the results while reducing the computational difficulty.
[0142] Figure 4 A flowchart illustrating a method for controlling the composition of molten iron according to another embodiment of the present disclosure is shown.
[0143] like Figure 4 As shown, Figure 4 As shown, the method includes operations S401 to S406.
[0144] In operation S401, determine whether the hot metal composition deviation data for the current heat matches a predetermined deviation threshold. If they match, proceed to operation S402; otherwise, proceed to operation S403.
[0145] In operation S402, if the deviation data of molten iron composition in the current heat matches the predetermined deviation threshold, the basic input amount of raw materials for the next heat is used as the target input amount of raw materials for the next heat.
[0146] In operation S403, if the hot metal composition deviation data of the current furnace does not match the predetermined deviation threshold, the raw material deviation is calculated in reverse based on the hot metal composition deviation data of the current furnace to determine the equivalent raw material deviation amount of each of the multiple raw materials in the current furnace.
[0147] In operation S404, for each raw material, the equivalent raw material deviation trend information is determined based on the equivalent raw material deviation sequence composed of the equivalent raw material deviation of the current furnace and the historical equivalent raw material deviation of multiple historical furnaces.
[0148] In operation S405, following an update strategy that matches the equivalent raw material deviation trend information, the historical cumulative raw material deviation of the previous heat is updated based on the equivalent raw material deviation of the current heat, and the cumulative raw material deviation of the current heat is determined.
[0149] In operation S406, based on the raw material compensation amount for the next heat determined by the cumulative raw material deviation of the current heat, the basic input amount of raw materials for the next heat is compensated, and the target input amount of raw materials for the next heat is determined. The basic input amount is determined by following the principle of raw material conservation and based on the expected data of the molten iron composition for the next heat.
[0150] Detection errors can be set for testing instruments, such as those used to measure the composition of molten iron. For example, if the accuracy of a thermal analyzer in measuring the carbon content in molten iron is ±0.02%, then theoretically, fluctuations within ±0.02% may simply be noise rather than a true change in composition. Therefore, a predetermined deviation threshold can be set so that deviations in molten iron composition within this threshold are within an acceptable range of normal systematic errors, preventing the controller from overreacting to "noise."
[0151] According to embodiments of this disclosure, a predetermined deviation threshold is set for the molten iron composition deviation data. If the molten iron composition deviation data falls within the predetermined deviation threshold, the two are determined to be a match; otherwise, they are considered a mismatch. This expands the tolerance range for raw material deviations, thereby improving the operational stability of the molten iron smelting system.
[0152] Any one or more of the modules, submodules, units, and subunits according to embodiments of the present disclosure, or at least part of the functions of any one or more of them, can be implemented in one module. Any one or more of the modules, submodules, units, and subunits according to embodiments of the present disclosure can be implemented by dividing them into multiple modules. Any one or more of the modules, submodules, units, and subunits according to embodiments of the present disclosure can be at least partially implemented as hardware circuitry, such as a Field-Programmable Gate Array (FPGA), a Programmable Logic Array (PLA), a System-on-Chip, a System-on-a-Substrate, a System-on-Package, an Application-Specific Integrated Circuit (ASIC), or implemented in hardware or firmware by any other reasonable means of integrating or packaging circuitry, or implemented in software, hardware, or firmware, or in any suitable combination of any of these three implementation methods. Alternatively, one or more of the modules, submodules, units, and subunits according to embodiments of the present disclosure can be at least partially implemented as computer program modules, which, when run, can perform corresponding functions.
[0153] Figure 5 A block diagram of an electronic device suitable for implementing the methods described above, according to embodiments of the present disclosure, is illustrated schematically. Figure 5 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of the embodiments disclosed herein.
[0154] like Figure 5 As shown, an electronic device 500 according to an embodiment of this disclosure includes a processor 501, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 502 or a program loaded from a storage portion 508 into a random access memory (RAM) 503. The processor 501 may include, for example, a general-purpose microprocessor (e.g., a CPU), an instruction set processor and / or an associated chipset and / or a special-purpose microprocessor (e.g., an application-specific integrated circuit (ASIC)), etc. The processor 501 may also include onboard memory for caching purposes. The processor 501 may include a single processing unit or multiple processing units for performing different actions of the method flow according to an embodiment of this disclosure.
[0155] RAM 503 stores various programs and data required for the operation of electronic device 500. Processor 501, ROM 502, and RAM 503 are interconnected via bus 504. Processor 501 performs various operations of the method flow according to embodiments of the present disclosure by executing programs in ROM 502 and / or RAM 503. It should be noted that the programs may also be stored in one or more memories other than ROM 502 and RAM 503. Processor 501 may also perform various operations of the method flow according to embodiments of the present disclosure by executing programs stored in said one or more memories.
[0156] According to embodiments of this disclosure, the electronic device 500 may further include an input / output (I / O) interface 505, which is also connected to a bus 504. The electronic device 500 may also include one or more of the following components connected to the input / output (I / O) interface 505: an input section 506 including a keyboard, mouse, etc.; an output section 507 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 508 including a hard disk, etc.; and a communication section 509 including a network interface card such as a LAN card, modem, etc. The communication section 509 performs communication processing via a network such as the Internet. A drive 510 is also connected to the input / output (I / O) interface 505 as needed. A removable medium 511, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed on the drive 510 as needed so that computer programs read from it can be installed into the storage section 508 as needed.
[0157] According to embodiments of this disclosure, the method flow according to embodiments of this disclosure can be implemented as a computer software program. For example, embodiments of this disclosure include a computer program product comprising a computer program carried on a computer-readable storage medium, the computer program containing program code for performing the methods shown in the flowchart. In such embodiments, the computer program can be downloaded and installed from a network via communication section 509, and / or installed from removable medium 511. When the computer program is executed by processor 501, it performs the functions defined in the system of embodiments of this disclosure. According to embodiments of this disclosure, the systems, devices, apparatuses, modules, units, etc., described above can be implemented by computer program modules.
[0158] This disclosure also provides a computer-readable storage medium, which may be included in the device / apparatus / system described in the above embodiments; or it may exist independently and not assembled into the device / apparatus / system. The computer-readable storage medium carries one or more programs that, when executed, implement the method according to the embodiments of this disclosure.
[0159] According to embodiments of this disclosure, the computer-readable storage medium can be a non-volatile computer-readable storage medium. Examples include, but are not limited to: portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this disclosure, the computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.
[0160] For example, according to embodiments of this disclosure, a computer-readable storage medium may include the ROM 502 and / or RAM 503 described above and / or one or more memories other than ROM 502 and RAM 503.
[0161] Embodiments of this disclosure also include a computer program product comprising a computer program containing program code for performing the methods provided in the embodiments of this disclosure. When the computer program product is run on an electronic device, the program code is used to enable the electronic device to implement the molten iron composition control method provided in the embodiments of this disclosure.
[0162] When the computer program is executed by the processor 501, it performs the functions defined in the system / apparatus of this disclosure embodiments. According to embodiments of this disclosure, the systems, apparatuses, modules, units, etc., described above can be implemented by computer program modules.
[0163] In one embodiment, the computer program may rely on a tangible storage medium such as an optical storage device or a magnetic storage device. In another embodiment, the computer program may also be transmitted and distributed in the form of signals over a network medium, and may be downloaded and installed via the communication section 509, and / or installed from a removable medium 511. The program code contained in the computer program can be transmitted using any suitable network medium, including but not limited to: wireless, wired, etc., or any suitable combination thereof.
[0164] According to embodiments of this disclosure, program code for executing the computer programs provided in embodiments of this disclosure can be written in any combination of one or more programming languages. Specifically, these computational programs can be implemented using high-level procedural and / or object-oriented programming languages, and / or assembly / machine languages. Programming languages include, but are not limited to, languages such as Java, C++, Python, "C", or similar programming languages. The program code can execute entirely on a user's computing device, partially on a user's device, partially on a remote computing device, or entirely on a remote computing device or server. In cases involving remote computing devices, the remote computing device can be connected to the user's computing device via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computing device (e.g., via the Internet using an Internet service provider).
[0165] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram or flowchart, and combinations of blocks in a block diagram or flowchart, may be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions. Those skilled in the art will understand that the features described in the various embodiments of the present disclosure can be combined and / or combined in various ways, even if such combinations are not explicitly described in the present disclosure. In particular, the features described in the various embodiments of this disclosure can be combined and / or combined in various ways without departing from the spirit and teachings of this disclosure. All such combinations and / or combinations fall within the scope of this disclosure.
[0166] The embodiments of this disclosure have been described above. However, these embodiments are for illustrative purposes only and are not intended to limit the scope of this disclosure. Although various embodiments have been described above, this does not mean that the measures in the various embodiments cannot be used advantageously in combination. Various substitutions and modifications can be made by those skilled in the art without departing from the scope of this disclosure, and all such substitutions and modifications should fall within the scope of this disclosure.
Claims
1. A method for controlling the composition of molten iron, comprising: Based on the hot metal composition deviation data of the current furnace, the raw material deviation is calculated in reverse to determine the equivalent raw material deviation of each of the multiple raw materials in the current furnace. The hot metal composition deviation data indicates the difference between the measured value and the expected value of each of the multiple elements in the hot metal. The raw materials are used to smelt hot metal in an induction furnace. The equivalent raw material deviation indicates the difference between the input amount of the raw materials and the actual demand amount. For each raw material, the equivalent raw material deviation trend information is determined based on the equivalent raw material deviation sequence composed of the equivalent raw material deviation of the current furnace and the historical equivalent raw material deviation of multiple historical furnaces. Following an update strategy that matches the equivalent raw material deviation trend information, based on the equivalent raw material deviation of the current heat, the historical cumulative raw material deviation of the previous heat is updated to determine the cumulative raw material deviation of the current heat; and Based on the raw material compensation amount for the next heat determined by the cumulative raw material deviation of the current heat, the basic input amount of the raw material for the next heat is compensated, and the target input amount of the raw material for the next heat is determined. The basic input amount is determined by following the principle of raw material conservation and based on the expected data of the molten iron composition for the next heat.
2. The method according to claim 1, wherein, The method involves performing reverse calculation of raw material deviations based on the current furnace hot metal composition deviation data to determine the equivalent raw material deviation for each of the multiple raw materials in the current furnace, including: For each element in the molten iron, determine the content ratio of the element in the target raw material and the yield of the element, wherein the target raw material is used in smelting to obtain the element in the molten iron, and the target raw material is determined from a plurality of raw materials; and Based on the elemental deviation data of the element in the hot metal composition deviation data of the current furnace, the content ratio of the element in the raw material, the yield of the element, and the expected hot metal composition data of the current furnace, the equivalent raw material deviation of the raw material for the current furnace is determined.
3. The method according to claim 1, wherein, The step of updating the historical cumulative raw material deviation of the previous furnace based on the equivalent raw material deviation of the current furnace, according to an update strategy that matches the equivalent raw material deviation trend information, and determining the cumulative raw material deviation of the current furnace, includes: When the trend type indicated by the equivalent raw material deviation trend information includes full-volume same-direction offset, the equivalent raw material deviation of the current furnace and the historical cumulative raw material deviation of the previous furnace are accumulated according to the full-volume enhancement update strategy to determine the cumulative raw material deviation of the current furnace. The long-term same-direction offset indicates that the values of multiple equivalent raw material deviations of different furnaces are all greater than a predetermined value or all less than a predetermined value. When the trend type indicated by the equivalent raw material deviation trend information includes random fluctuations, the historical cumulative raw material deviation of the previous heat is attenuated using an adjustment factor according to the attenuation update strategy to determine the cumulative raw material deviation of the current heat. The random fluctuations indicate that the values of multiple equivalent raw material deviations in different heats have different signs. When the trend type indicated by the equivalent raw material deviation trend information includes local same-direction offset, the equivalent raw material deviation of the current furnace and the historical cumulative raw material deviation of the previous furnace are weighted and accumulated according to the local update strategy to determine the cumulative raw material deviation of the current furnace. The short-term same-direction offset indicates that the values of multiple equivalent raw material deviations of different furnaces are all greater than or less than a predetermined value, and the number of furnaces in which the local same-direction offset occurs is less than the number of furnaces in which the full same-direction offset occurs.
4. The method according to claim 1, further comprising: Based on the equivalent raw material deviation sequence, a decay factor for adjusting the cumulative deviation in the current furnace is determined. as well as Based on the attenuation factor of the current furnace, the cumulative deviation of raw materials for the current furnace is adjusted to determine the raw material compensation amount for the next furnace.
5. The method according to claim 4, wherein, The step of determining the attenuation factor for adjusting the cumulative deviation in the current furnace based on the equivalent raw material deviation sequence includes: Based on the deviation data of the same element from different furnace batches, a set of deviation variation parameters is determined. Determine the attenuation factor that matches the set of deviation change parameters.
6. The method according to claim 1, wherein, Determining the attenuation factor that matches the set of deviation change parameters includes: The attenuation factor that matches the set of deviation change parameters is used as the initial attenuation factor; Based on the equivalent raw material deviation trend information, the initial attenuation factor is adjusted to obtain the adjusted attenuation factor; and The attenuation factor is determined based on the adjusted attenuation factors of each of the aforementioned raw materials.
7. The method according to claim 1, wherein, The process of compensating the base input of the raw materials for the next heat based on the raw material compensation amount determined by the cumulative raw material deviation of the current heat, and determining the target input amount of the raw materials for the next heat, includes: Based on the raw material compensation amount for the next batch and the basic input amount for the next batch, the initial compensation input amount for the raw material for the next batch is determined. If the initial compensation input for the next heat does not match the process reference input, the target input for the next heat is determined based on the process reference input, wherein the process reference input is determined based on the safety performance conditions and equipment performance conditions of the molten iron; and When the initial compensation input matches the process reference input, the target input is determined based on the initial compensation input.
8. The method according to claim 1, further comprising: Based on the expected composition data of the molten iron in the next heat, the yield of each element, and the content of each element in the recovered phosphorus pig iron of the current heat, and with the basic input amount of each raw material in the next heat as the unknown, the element material balance equation of each element is determined. Based on the basic input amount of each element in the next heat and the expected data of the molten iron composition in the next heat, the raw material balance equation is determined. as well as Based on the elemental material balance equations and the raw material material balance equations for each of the aforementioned elements, the basic input amount for the next batch of each of the aforementioned raw materials is determined.
9. The method according to claim 1, further comprising: If the deviation data of molten iron composition in the current heat matches a predetermined deviation threshold, the basic input amount of the raw material for the next heat shall be used as the target input amount of the raw material for the next heat.
10. An iron smelting system, comprising: An intermediate frequency furnace is configured to smelt the raw materials input into the furnace to produce molten iron. The controller is configured to perform the method as described in any one of claims 1 to 9, based on the measured data of the molten iron composition of the current furnace and the expected data of the molten iron composition of the current furnace, to determine the target input amount of each raw material for the next furnace, wherein the measured data of the molten iron composition of the current furnace is obtained by measuring the composition of the molten iron of the current furnace in the medium frequency furnace. as well as The feeder is configured to feed the medium-frequency furnace according to the target input amount of each of the raw materials for the next batch.