Method for predicting hydrogen content in steel strip, method for controlling hydrogen content in steel, manufacturing method, method for generating hydrogen content prediction model in steel, and device for predicting hydrogen content in steel

Abstract

Provided are a method for predicting the amount of hydrogen in steel of a steel strip, a method for generating a model for predicting the amount of hydrogen in steel, and a device for predicting the amount of hydrogen in steel of the steel strip with high accuracy. Furthermore, provided are a method for controlling the amount of hydrogen in steel of a steel strip and a manufacturing method for effectively reducing the amount of hydrogen in steel. A method for predicting the amount of hydrogen in steel of a steel strip downstream of a reheating process in a continuous hot-dip coating facility that performs a manufacturing process including an annealing process, a plating process, and a reheating process for the steel strip, comprising: an input data acquisition step for acquiring, as input data, one or more parameters selected from operating parameters of the continuous hot-dip coating facility and phase transformation rate information measured in at least one of the annealing process and the reheating process; and using a model for predicting the amount of hydrogen in steel of the steel strip downstream of the reheating process learned through machine learning, wherein the model for predicting the amount of hydrogen in steel of the steel strip downstream of the reheating process outputs information related to the amount of hydrogen in steel of the steel strip downstream of the reheating process.

Description

Technical Field

[0001] The present disclosure relates to a method for predicting the amount of hydrogen in steel strip, a method for controlling the amount of hydrogen in steel, a manufacturing method, a method for generating a model for predicting the amount of hydrogen in steel, and a device for predicting the amount of hydrogen in steel. Background Art

[0002] In recent years, the use of high-strength steel sheets in the automotive industry has been expanding for lightweighting vehicles to improve fuel efficiency and ensure crash safety. In particular, hot-dip galvanized steel sheets are often used in components that require rust resistance. However, there is room for improvement in the hydrogen embrittlement cracking of high-strength hot-dip galvanized steel sheets and high-strength cold-rolled steel sheets.

[0003] Hydrogen embrittlement cracking is a phenomenon in which steel sheets absorb hydrogen, resulting in a reduction in toughness. It typically occurs when hydrogen intrudes into the steel due to factors such as corrosion while the steel is under stress, leading to sudden damage over a period of time (also known as delayed failure). High-strength steel sheets, in particular, have high yield stresses, leading to increased residual stress from secondary processes such as stamping. This is believed to be a contributing factor, making hydrogen more likely to intrude into the steel.

[0004] Continuous hot-dip galvanizing equipment for producing hot-dip galvanized steel sheets and continuous annealing equipment for producing cold-rolled steel sheets perform heat treatment in a hydrogen-containing atmosphere. During this heat treatment, hydrogen temporarily penetrates the interior of the steel strip. While hydrogen typically escapes from the steel if maintained in a temperature range below 400°C for a certain period of time, there is a risk of delayed failure in such environments if the hydrogen content in the steel on the delivery side of the continuous hot-dip galvanizing and continuous annealing equipment is not sufficiently reduced.

[0005] In contrast, Patent Document 1 discloses a method for producing steel sheet with a tensile strength of 1470 MPa or greater, based on a manufacturing process comprising: a first holding step, in which heat treatment is performed in a predetermined temperature range for a predetermined time in an annealing step, followed by heat treatment in a predetermined temperature range and holding time; and a second holding step, in which the steel strip is immersed in a coating bath and then held in a temperature range of 330-430°C for a predetermined time. The method discloses that by controlling the hydrogen concentration in the furnace within a predetermined range during the annealing step, the first holding step, and the second holding step, the hydrogen content in the steel can be suppressed to 0.40 ppm or less.

[0006] Patent Document 2 discloses a method in which the steel casting and cold rolling processes are controlled to predetermined conditions, followed by an annealing step followed by a pretreatment step of pickling, followed by reheating to a predetermined temperature range, and then plating. Furthermore, a post-treatment method is disclosed in which, after the plating step, the steel is heated in an atmosphere controlled to a predetermined hydrogen concentration and dew point for 30 seconds or longer within a temperature range of 50 to 400°C to reduce the hydrogen content in the steel.

[0007] Patent Document 1: Japanese Patent No. 6631765

[0008] Patent Document 2: Japanese Patent No. 6673534

[0009] The method described in Patent Document 1 specifically controls the temperature, holding time, and hydrogen concentration in the annealing, first holding, and second holding steps for steel sheets with a specific composition and a tensile strength of 1470 MPa or higher. However, this method cannot be applied to steel sheets of other strength grades. Furthermore, the steel sheet described in Patent Document 1 is characterized by a multi-phase internal structure, but the relationship between the internal structure of the steel strip and the hydrogen content in the steel is not described, making it impossible to directly predict the hydrogen content in the steel strip.

[0010] The method described in Patent Document 2 requires combining manufacturing conditions from multiple manufacturing steps. It requires temporarily cooling the steel strip to room temperature after the annealing step and then reheating it before plating. This leaves room for improvement from the perspective of production efficiency. Furthermore, the method described in Patent Document 2 does not directly predict the hydrogen content in the steel strip. Furthermore, the method described in Patent Document 2 targets hot-dip galvanized steel sheets, not cold-rolled steel sheets. Summary of the Invention

[0011] The present disclosure, which was developed to address the above-mentioned issues, aims to provide a method for predicting the hydrogen content in steel strip, a method for generating a hydrogen content prediction model, and a device for predicting the hydrogen content in steel strip with high accuracy. Furthermore, another object of the present disclosure is to provide a method for controlling the hydrogen content in steel strip and a method for manufacturing the same, which utilize the method for predicting the hydrogen content in steel strip to effectively reduce the hydrogen content in steel.

[0012] A method for predicting the amount of hydrogen in a steel strip according to one embodiment of the present disclosure is a method for predicting the amount of hydrogen in the steel strip downstream of the reheating step in a continuous hot-dip coating facility that performs a manufacturing process including an annealing step, a coating step, and a reheating step of the steel strip, comprising:

[0013] an input data acquisition step of acquiring, as input data, one or more parameters selected from the operating parameters of the continuous hot dip coating equipment and phase transformation rate information measured in at least one of the annealing step and the reheating step; and

[0014] The hydrogen content in the steel strip downstream of the reheating process is predicted using a steel hydrogen content prediction model learned through machine learning. The steel hydrogen content prediction model outputs information related to the hydrogen content in the steel strip downstream of the reheating process.

[0015] A method for controlling hydrogen content in a steel strip according to one embodiment of the present disclosure includes:

[0016] The above-mentioned method for predicting the amount of hydrogen in steel strip is used to predict the amount of hydrogen in steel strip on the downstream side of the above-mentioned reheating process. When the predicted amount of hydrogen in steel exceeds a preset upper limit value, one or more operating parameters selected from the operating parameters of the above-mentioned continuous hot-dip coating equipment are reset so that the amount of hydrogen in steel becomes below the above-mentioned upper limit value.

[0017] A method for manufacturing a steel strip according to one embodiment of the present disclosure is a method for manufacturing a steel strip in a continuous hot-dip coating facility that performs a manufacturing process including an annealing step, a coating step, and a reheating step of the steel strip, comprising:

[0018] acquiring, as input data, one or more parameters selected from the operating parameters of the continuous hot-dip coating equipment and phase transformation rate information measured in at least one of the annealing step and the reheating step;

[0019] predicting the amount of hydrogen in steel of the steel strip downstream of the reheating step using a steel hydrogen amount prediction model learned by machine learning, the steel hydrogen amount prediction model outputting information related to the amount of hydrogen in steel of the steel strip downstream of the reheating step as output data; and

[0020] When the predicted hydrogen content in the steel exceeds a preset upper limit, one or more operating parameters selected from the operating parameters of the continuous hot-dip coating equipment are reset so that the hydrogen content in the steel becomes below the upper limit.

[0021] A method for generating a steel strip hydrogen content prediction model according to one embodiment of the present disclosure is for predicting the hydrogen content of a steel strip downstream of a reheating step in a continuous hot-dip coating facility that performs a manufacturing process including an annealing step, a coating step, and a reheating step of the steel strip, the method comprising:

[0022] acquiring, as input performance data, at least one piece of operating performance data selected from the operating performance data of the continuous hot-dip coating equipment and performance data of phase transformation rate information measured in at least one of the annealing step and the reheating step;

[0023] acquiring a plurality of learning data using information related to the amount of hydrogen in the steel strip on the downstream side of the reheating step based on the input performance data as output performance data; and

[0024] A prediction model for the amount of hydrogen in the steel strip is generated by machine learning using the acquired plurality of learning data.

[0025] An apparatus for predicting the amount of hydrogen in steel strip according to one embodiment of the present disclosure is a apparatus for predicting the amount of hydrogen in steel strip downstream of a reheating step in a continuous hot-dip coating facility that performs a manufacturing process including an annealing step, a coating step, and a reheating step of the steel strip, and includes:

[0026] an acquisition unit that acquires one or more parameters selected from the operating parameters of the continuous hot-dip coating equipment and phase transformation rate information measured in at least one of the annealing step and the reheating step; and

[0027] The prediction unit uses a steel hydrogen content prediction model learned through machine learning to predict the steel hydrogen content of the steel strip on the downstream side of the above-mentioned reheating process. The steel hydrogen content prediction model uses information related to the steel hydrogen content of the steel strip on the downstream side of the above-mentioned reheating process as output data.

[0028] A method for predicting the amount of hydrogen in a steel strip according to one embodiment of the present disclosure is a method for predicting the amount of hydrogen in a steel strip downstream of a reheating step in a continuous annealing facility that performs a manufacturing process including an annealing step and a reheating step of the steel strip, comprising:

[0029] an input data acquisition step of acquiring, as input data, one or more parameters selected from the operating parameters of the continuous annealing equipment and phase transformation rate information measured in at least one of the annealing step and the reheating step; and

[0030] The hydrogen content in the steel strip downstream of the reheating process is predicted using a steel hydrogen content prediction model learned through machine learning. The steel hydrogen content prediction model outputs information related to the hydrogen content in the steel strip downstream of the reheating process.

[0031] A method for controlling hydrogen content in a steel strip according to one embodiment of the present disclosure includes:

[0032] The above-mentioned method for predicting the amount of hydrogen in steel strip is used to predict the amount of hydrogen in steel strip on the downstream side of the above-mentioned reheating process. When the predicted amount of hydrogen in steel exceeds a preset upper limit value, one or more operating parameters selected from the operating parameters of the above-mentioned continuous annealing equipment are reset so that the amount of hydrogen in steel becomes below the above-mentioned upper limit value.

[0033] A method for manufacturing a steel strip according to one embodiment of the present disclosure is a method for manufacturing a steel strip in a continuous annealing facility that performs a manufacturing process including an annealing process and a reheating process of the steel strip, comprising:

[0034] acquiring, as input data, one or more parameters selected from operating parameters of the continuous annealing equipment and phase transformation rate information measured in at least one of the annealing step and the reheating step;

[0035] predicting the amount of hydrogen in steel of the steel strip downstream of the reheating step using a steel hydrogen amount prediction model learned by machine learning, the steel hydrogen amount prediction model outputting information related to the amount of hydrogen in steel of the steel strip downstream of the reheating step as output data; and

[0036] When the predicted hydrogen content in the steel exceeds a preset upper limit, one or more operating parameters selected from the operating parameters of the continuous annealing equipment are reset so that the hydrogen content in the steel becomes below the upper limit.

[0037] A method for generating a steel strip hydrogen content prediction model according to one embodiment of the present disclosure is for predicting the hydrogen content of a steel strip downstream of a reheating step in a continuous annealing facility that performs a manufacturing process including an annealing step and a reheating step of the steel strip, the method comprising:

[0038] acquiring, as input performance data, at least one piece of operation performance data selected from the operation performance data of the continuous annealing equipment and performance data of phase transformation rate information measured in at least one of the annealing step and the reheating step;

[0039] acquiring a plurality of learning data using information related to the amount of hydrogen in the steel strip on the downstream side of the reheating step based on the input performance data as output performance data; and

[0040] A prediction model for the amount of hydrogen in the steel strip is generated by machine learning using the acquired plurality of learning data.

[0041] An apparatus for predicting the amount of hydrogen in steel strip according to one embodiment of the present disclosure is a apparatus for predicting the amount of hydrogen in steel strip downstream of the reheating step in a continuous annealing facility that performs a manufacturing process including an annealing step and a reheating step of the steel strip, and includes:

[0042] an acquisition unit that acquires one or more parameters selected from the operating parameters of the continuous annealing equipment and phase transformation rate information measured in at least one of the annealing step and the reheating step; and

[0043] The prediction unit uses a steel hydrogen content prediction model learned through machine learning to predict the steel hydrogen content of the steel strip downstream of the reheating process. The steel hydrogen content prediction model outputs information related to the steel hydrogen content of the steel strip downstream of the reheating process as output data.

[0044] According to the present disclosure, a method for predicting the amount of hydrogen in steel strip, a method for generating a hydrogen prediction model, and a device for predicting the amount of hydrogen in steel strip can be provided, which accurately predict the amount of hydrogen in steel strip. According to the present disclosure, a method for controlling the amount of hydrogen in steel strip and a method for manufacturing the same can be provided, which effectively reduce the amount of hydrogen in steel using the method for predicting the amount of hydrogen in steel. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 This is an example of a continuous hot-dip coating facility and is a diagram showing a hot-dip coating line for manufacturing galvanized steel sheets.

[0046] Figure 2 This is a diagram showing an example of the thermal history of a hot-dip coating line for producing galvanized steel sheets.

[0047] Figure 3 This is a diagram showing a method for generating a prediction model for the amount of hydrogen in steel.

[0048] Figure 4 This is a diagram showing a method for controlling the amount of hydrogen in steel.

[0049] Figure 5 This is a diagram for explaining a device for predicting the amount of hydrogen in steel.

[0050] Figure 6 This is an example of a continuous annealing facility and is a diagram showing a continuous annealing line for producing cold-rolled steel sheets.

[0051] Figure 7 This is a diagram showing an example of the thermal history of a continuous annealing line for producing cold-rolled steel sheets.

[0052] Figure 8 This is a diagram showing a method for generating a prediction model for the amount of hydrogen in steel.

[0053] Figure 9This is a diagram showing a method for controlling the amount of hydrogen in steel. DETAILED DESCRIPTION

[0054] (First embodiment)

[0055] The method for predicting the amount of hydrogen in steel strip according to the first embodiment of the present disclosure predicts the amount of hydrogen in the steel of a hot-dip galvanized steel sheet at the delivery side of a continuous hot-dip coating device. The hot-dip galvanized steel sheet is manufactured by using a continuous hot-dip coating device to heat treat and plate a steel sheet that has been reduced to a specified thickness through a hot rolling process, a pickling process, and a cold rolling process. Here, there is also a case where the above-mentioned cold rolling process is omitted. At least after the hot rolling process, the thin steel sheet is wound into a coil and then subjected to heat treatment, etc. Therefore, in this embodiment, the thin steel sheet is sometimes recorded as a "steel strip."

[0056] Continuous hot-dip galvanizing equipment

[0057] In this embodiment, a continuous hot-dip coating system (CGL) that performs a manufacturing process including an annealing step, a coating step, and a reheating step is targeted. Continuous hot-dip coating systems will be described in detail below with reference to the accompanying drawings.

[0058] Figure 1 This is a schematic diagram showing an example of a continuous hot-dip coating facility for producing hot-dip galvanized steel sheets. Figure 1 The arrow indicates the direction of travel of the steel strip. The continuous hot dip coating equipment is roughly divided into a feed-side device, a furnace body, and a feed-side device. The feed-side device includes a uncoiler 1, a welding machine 2, an electrolytic cleaning device 3, and a feed-side looper roller 4. The furnace body consists of an annealing section, a plating section, and a reheating section. The feed-side device includes a feed-side looper roller 12, a temper rolling device 13, an inspection device 14, and a tension reel 15. The inspection device 14 includes a sample collection device for collecting sample materials from the steel strip for offline determination of the amount of hydrogen in the steel.

[0059] The annealing section includes a heating zone 6, a soaking zone 7, and a cooling zone 8. A preheating zone 5 may be provided upstream of the heating zone 6. The annealing process in this embodiment refers to a heat treatment process performed by the annealing section. More specifically, the annealing process is a process in which the temperature of the steel strip is raised from near room temperature, maintained at a predetermined temperature, and then lowered to a temperature suitable for galvanizing. Furthermore, in a continuous hot-dip galvanizing facility, a plating section is provided downstream of the annealing section. The steel strip, cooled to a predetermined temperature in the cooling zone 8, is immersed in a zinc tank, and the zinc weight per unit area (adhesion) is adjusted by a wiping device 21. The plating process in this embodiment refers to a galvanizing process performed by the plating section. The reheating section downstream of the reheating section includes an alloying zone 17, a holding zone 18, and a final cooling zone 11. An induction heating device is provided in the alloying zone 17. The reheating process in this embodiment refers to a heat treatment process performed by the reheating section.

[0060] The heating zone 6 is used to heat the steel strip to a predetermined temperature within the range of approximately 700-900°C, depending on the type of steel. Direct flame or radiant burners are used in the heating zone 6. The soaking zone 7 maintains the steel strip at a predetermined temperature, providing heating capacity to compensate for heat dissipation from the furnace. The cooling zone 8 cools the steel strip to a temperature of approximately 480°C, suitable for galvanizing, and typically uses gas jet cooling. In this case, the cooling zone 8 can be divided into multiple zones, such as a first cooling zone 8A and a second cooling zone 8B, to control the thermal history of the steel strip during cooling by varying the cooling conditions.

[0061] Furthermore, a mixed gas containing hydrogen, nitrogen, and water vapor is supplied to the interiors of the heating zone 6, soaking zone 7, and cooling zone 8 to adjust the atmosphere during the annealing step. Since the supplied gas contains water vapor, not only the gas composition but also the dew point of the atmosphere during the annealing step is adjusted.

[0062] The coating section consists of a snout 19 connected to the outlet of the cooling belt 8, a galvanizing tank 16, and a wiping device 21. The snout 19 is a rectangular-shaped component that defines the space through which the steel strip passes. A mixed gas containing hydrogen, nitrogen, and water vapor is supplied to the inside to adjust the atmosphere until the steel strip is immersed in the galvanizing tank 16. The galvanizing tank 16 has sink rollers 22 inside. The sink rollers 22 are used to immerse the steel strip passing through the snout 19 downward in the galvanizing tank 16, lifting the steel strip, with molten zinc attached to its surface, above the coating bath. Furthermore, the wiping device 21 blows wiping gas from nozzles located on both sides of the steel strip to scrape off excess molten zinc adhering to the surface of the steel strip and adjust the weight per unit area of ​​the molten zinc.

[0063] A reheating zone (referred to as an alloying zone 17) forming the reheating section is located above (on the downstream side of) the wiping device 21 that forms the plating section. Typically, the temperature of the steel strip that has passed through the wiping device 21 drops to approximately 430°C. Therefore, in the alloying zone 17, the steel strip is heated to a temperature at which a Zn-Fe alloying reaction occurs. The temperature raised in the alloying zone 17 corresponds to the target alloying temperature and varies depending on the alloy composition of the steel sheet, the Al concentration in the plating bath, and other factors, but is typically raised to approximately 500°C. The temperature of the steel strip is then maintained in the holding zone 18 to ensure the time required for the alloying reaction to proceed. Downstream of the holding zone 18 is the final cooling zone 11, which is a device that cools the alloyed steel strip to near room temperature. Similar to the cooling zone 8, the final cooling zone 11 can be divided into multiple cooling zones, such as a first final cooling zone 11A and a second final cooling zone 11B, to control the thermal history of the steel strip during cooling.

[0064] In the continuous hot-dip coating system, thermometers for measuring the surface temperature of the steel strip are installed at multiple locations within the heating zone 6, soaking zone 7, cooling zone 8, alloying zone 17, holding zone 18, and final cooling zone 11, which constitute the annealing section. Furthermore, furnace thermometers are installed to measure not only the surface temperature of the steel strip but also the atmosphere temperature within the furnace in each zone of the annealing and reheating steps. The measured surface and atmosphere temperatures of the steel strip are output to a process computer that controls the continuous hot-dip coating system and provides overall operational control.

[0065] Figure 2 This graph shows the thermal history of a steel strip during the annealing and reheating steps in a continuous hot-dip galvanizing facility used to produce hot-dip galvanized steel sheets. The horizontal axis represents time, and the vertical axis represents the steel strip temperature. The steel strip temperature is, for example, the surface temperature of the steel strip. The graph shows the thermal history of the steel strip as it undergoes an annealing step using a heating zone 6, a soaking zone 7, and a cooling zone 8, followed by a reheating step using an alloying zone 17, a holding zone 18, and a final cooling zone 11 in a coating section. To prevent material variations due to the longitudinal position of the steel strip, the conveyance speed of the steel strip is kept constant during the annealing step. However, when welding steel strips of varying thickness, width, and steel grade, the line speed may vary before and after the weld. Consequently, the shape of the thermal history graph may vary depending on the position of the steel strip being measured. Furthermore, depending on operating conditions, the reheating step using the alloying zone 17, the holding zone 18, and the final cooling zone 11 may not be performed. In this case, the temperature of the steel strip having passed through the coating portion has a substantially constant thermal history at approximately room temperature.

[0066] <Atmosphere gas control>

[0067] The annealing atmosphere is controlled by supplying a mixed gas containing hydrogen, nitrogen, and water vapor into the heating zone 6, soaking zone 7, and cooling zone 8, where the annealing process is performed. The hydrogen contained in the annealing atmosphere affects the amount of hydrogen that enters the steel strip during the annealing process. Therefore, the composition and flow rate of the supplied gas are measured and adjusted and controlled as needed.

[0068] In the heating zone 6, a heating device such as a radiant tube (RT) or an electric heater can be used to indirectly heat the steel strip. Simultaneously with the flow of gas from the soaking zone 7, the cooling zone 8, and the furnace nose 19 into the heating zone 6, a reducing gas or a non-oxidizing gas can be supplied to the heating zone 6. As the reducing gas, an H2-N2 mixed gas is generally used. As such an H2-N2 mixed gas, for example, a gas having a composition of 1 to 20% by volume of H2 and the remainder consisting of N2 and inevitable impurities (dew point: about -60°C) can be cited. In addition, as the non-oxidizing gas, a gas having a composition consisting of N2 and inevitable impurities (dew point: about -60°C) is used. The method of supplying gas to the heating zone 6 is not particularly limited, but it is preferred to supply gas from two or more inlets in the height direction and one or more inlets in the length direction so that the gas is uniformly supplied into the heating zone 6.

[0069] In the soaking zone 7, a radiant tube can be used as a heating mechanism to indirectly heat the steel strip. The average temperature inside the soaking zone 7 is preferably 700 to 900°C. A reducing gas or a non-oxidizing gas is supplied to the soaking zone 7. As the reducing gas, an H2-N2 mixed gas is generally used. For example, a gas having a composition of 1 to 20% by volume of H2 and the remainder consisting of N2 and inevitable impurities (dew point: approximately -60°C) can be used. In addition, as the non-oxidizing gas, a gas having a composition consisting of N2 and inevitable impurities (dew point: approximately -60°C) can be used.

[0070] The cooling zone 8 is equipped with a cooling device, and the steel strip is cooled during the steel strip passing through the cooling zone 8. The aforementioned gas can be supplied to the cooling zone 8 in the same manner as the soaking zone 7. It is preferable to supply gas from two or more inlets in the height direction and two or more inlets in the length direction of the cooling zone 8 so that the gas is uniformly supplied to the cooling zone 8.

[0071] A hydrogen concentration meter and a dew point meter are installed in the heating zone 6, soaking zone 7, and cooling zone 8, where the annealing process is performed, to measure the gas atmosphere within the furnace. The hydrogen concentration meter uses a catalytic combustion sensor that measures the temperature rise of the platinum wire coil caused by catalytic combustion of the gas on the catalyst surface. For example, the XP-3110 combustible gas detector manufactured by Shin Cosmos Electric Co., Ltd. can be used. However, hydrogen concentration meters using other measurement methods, such as those that detect hydrogen concentration based on changes in thermal conductivity caused by gas concentration, can also be used. The dew point meter can be a capacitance type or a mirror-cooled type. For example, the DMT345 dew point converter manufactured by Vaisala can be used.

[0072] The hydrogen concentration meter is preferably set in any of the heating zone 6, soaking zone 7, and cooling zone 8. The hydrogen concentration meter can be set at any location as long as it is in the heating zone 6, soaking zone 7, and cooling zone 8. However, the higher the temperature of the steel strip, the easier it is for the hydrogen in the steel to diffuse. Therefore, the hydrogen concentration meter is preferably set near the delivery side of the heating zone 6 or in the soaking zone 7. In addition, the hydrogen concentration meter can be set at any location, but it is preferred to set multiple hydrogen concentration meters at different locations. This is because: by obtaining multiple hydrogen concentration information, the prediction accuracy of the hydrogen content in the steel is improved. The measured value is output to the process control computer.

[0073] Similarly, the dew point meter is preferably installed in any of the heating zone 6, soaking zone 7, and cooling zone 8. The dew point meter can be installed anywhere, as long as it is in the heating zone 6, soaking zone 7, or cooling zone 8. While the installation location can be anywhere, it is preferable to install multiple dew point meters in different locations. This is because obtaining multiple dew point information improves the accuracy of predicting the hydrogen content in steel. The measured values ​​are output to the process control computer.

[0074] A mixed gas containing hydrogen, nitrogen, and water vapor is supplied to the coating section's nose 19 to control the atmosphere. The hydrogen contained in the atmosphere affects the amount of hydrogen that enters the steel strip within the nose 19. Therefore, the composition and flow rate of the supplied gas are measured and adjusted and controlled as needed.

[0075] A hydrogen concentration meter and a dew point meter are also installed in the furnace nose 19 to measure the gas atmosphere within the furnace nose 19. The hydrogen concentration meter and dew point meter can be installed at any location. While the number of hydrogen concentration meters and dew point meters can be one, it is preferred to install multiple hydrogen concentration meters and dew point meters at different locations. This is because obtaining multiple hydrogen concentration and dew point data improves the accuracy of predicting the hydrogen content in the steel. The measured values ​​are output to the process control computer.

[0076] A mixed gas containing hydrogen, nitrogen, and water vapor is supplied to each zone in the reheating process to control the atmosphere. The hydrogen content in the atmosphere affects the amount of hydrogen that penetrates the steel strip during the reheating process. Therefore, the composition and flow rate of the supplied gas are measured and adjusted and controlled as needed.

[0077] A hydrogen concentration meter and a dew point meter are also installed in the reheating process to measure the gas atmosphere. These meters can be installed at any location. While multiple meters can be installed at one location each, it is preferred to install multiple meters at different locations. This is because obtaining information from multiple hydrogen concentration meters and dew point data improves the accuracy of predicting the hydrogen content in the steel. The measured values ​​are output to the process control computer.

[0078] <Phase change rate meter>

[0079] The phase transformation rate meter 20 is a measuring instrument for measuring the ratio of the austenite phase (γ phase) to the whole as the internal structure of the steel strip in the heat treatment process. In continuous hot-dip galvanizing equipment, the structure of the steel plate is mostly controlled by phase transformation based on the two phase states of specific austenite phase (γ phase) and ferrite phase (α phase). Therefore, as the phase transformation rate meter 20, a phase transformation rate meter 20 using X-ray diffraction can be used. Since the crystal structures of the γ phase and the α phase are different, if X-rays are irradiated, diffraction peaks are generated from each at a unique angle. This is a method of quantifying the phase transformation rate (γ rate) based on the intensity of the diffraction peak. For example, a product called X-CAP made by SMS can be used. In addition, the following method can be used: a magnetic phase transformation rate measuring device composed of a driving coil that generates a magnetic field and a detection coil that measures the magnetic field passing through the steel strip is used as a magnetic detector, that is, a device for measuring the magnetic phase transformation rate of the steel strip to measure the austenite phase ratio. Specifically, the device described in Japanese Patent Application Laid-Open No. 2019-7907 can be used.

[0080] In this embodiment, the phase transformation rate meter 20 for measuring the austenite phase ratio is installed in at least one of the annealing process and the reheating process of the continuous hot dip coating equipment. Figure 1 The phase transformation rate meter 20 is shown as a candidate for installation. Examples of installation locations include the entrance or exit of the soaking zone 7, or the entrance of the cooling zone 8 in the annealing process. Preferably, it is installed at the entrance or exit of the alloying zone 17 in the reheating process. While the phase transformation rate meter 20 can be installed anywhere, it is preferably installed at multiple locations. This is because obtaining multiple phase transformation rate information improves the accuracy of predicting the hydrogen content in steel.

[0081] <Information on the amount of hydrogen in steel strip>

[0082] Information related to the amount of hydrogen in steel is obtained by measuring the amount of diffusible hydrogen in steel using an offline hydrogen-in-steel measuring device, using a test piece collected from a steel strip sample collected by the sample collection equipment in the hot-dip galvanizing facility. Any device capable of measuring the amount of hydrogen in steel within a range of 0.01 to 10 ppm can be used. Specifically, a device utilizing temperature-increasing hydrogen analysis using gas chromatography can be used.

[0083] Methods for measuring the amount of hydrogen include gas chromatography mass spectrometry (GC / MS) and temperature desorption spectroscopy (TDS). Apparatuses include GC-4000 Plus from GL Sciences Co., Ltd. and TDS1200 from UBE Scientific Analysis Center Co., Ltd.

[0084] The amount of hydrogen in steel can be measured by the following temperature analysis method. First, a test piece of about 5×30 mm is cut out from the plated steel plate. The test piece is removed from the plating on the surface of the test piece using a groove milling machine (precision grinder) and placed in a quartz tube. Next, after replacing the quartz tube with Ar, the temperature is increased at 200°C / hr, and the hydrogen generated until 400°C is measured by gas chromatography. At this time, the amount of diffusible hydrogen in the steel is the cumulative value of the amount of hydrogen detected in the temperature range of room temperature (25°C) to 400°C.

[0085] The information related to the hydrogen content in the steel strip obtained in this way is sent to the host computer (the computer that gives manufacturing instructions to the process control computer) together with the identification number (coil number) of the steel strip from which the test piece was collected, and the information related to the collection location is also sent to the host computer (the computer that gives manufacturing instructions to the process control computer) as needed.

[0086] <Method for Generating a Prediction Model for Hydrogen Content in Steel>

[0087] Figure 3 A method for generating a steel hydrogen content prediction model for a steel strip according to this embodiment will be described.

[0088] The continuous hot-dip galvanizing equipment's operational performance data, performance data on the steel strip's phase transformation rate measured by the phase transformation rate meter 20, and performance data related to the amount of hydrogen in the steel strip are stored in a database. The details of the continuous hot-dip galvanizing equipment's operational performance data will be discussed later, but performance data selected from the operational performance data held by the process control computer that oversees the operation of the continuous hot-dip galvanizing equipment is sent to the database of the hydrogen content prediction model generation unit. Furthermore, the performance data on the steel strip's phase transformation rate information is the phase transformation rate information obtained from the aforementioned phase transformation rate meter 20. If the phase transformation rate information is stored in the process control computer, it is sent from the process control computer to the database. However, if the phase transformation rate information is not stored in the process control computer, it is sent directly to the database of the hydrogen content prediction model generation unit.

[0089] Information on the amount of hydrogen in steel, such as the coil number of the steel strip, is sent to the database along with accompanying information that can be associated with the actual operating performance data of the continuous hot-dip coating equipment. Furthermore, the performance data related to the amount of hydrogen in the steel of the steel strip is information obtained through offline testing and is stored in a host computer. This information is also sent to the database along with accompanying information that can be associated with the actual operating performance data of the continuous hot-dip coating equipment, such as the coil number of the steel strip. Furthermore, the actual operating performance data of the continuous hot-dip coating equipment, the performance data on the phase change rate information of the steel strip measured by the phase change rate meter 20, and the performance data on the information related to the amount of hydrogen in the steel of the steel strip are associated through the coil number, etc., and stored in the database as a set of data sets. At this time, the data sets stored in the database are obtained as one data set for each steel strip. However, in the case where performance data on information related to the hydrogen content in the steel of the steel strip is obtained at multiple locations such as the front end and the tail end of the steel strip, it is also possible to use the operation performance data of the continuous hot-dip coating equipment and the performance data on the phase transformation rate information of the steel strip obtained at multiple locations such as the front end and the tail end of the steel strip to obtain multiple data sets for each steel strip.

[0090] Furthermore, the database preferably includes one or more parameters selected from among the steel strip property parameters related to the steel strip's chemical composition. Actual performance data for the steel strip property parameters related to the steel strip's chemical composition is stored in a process control computer or a host computer as actual performance values ​​during the steelmaking process, along with the coil number. This data set can be constructed by appropriately transmitting it to the database. By including the steel strip property parameters related to the steel strip's chemical composition as input, the hydrogen content prediction model of this embodiment can be widely applied to steel strips with varying chemical compositions.

[0091] The number of data sets in the database used for generating the hydrogen content in steel prediction model of the present embodiment is preferably 200 or more, more preferably 1000 or more.

[0092] In this embodiment, a database created in this manner is used, and at least one operating performance data selected from the operating performance data of the continuous hot-dip coating equipment and performance data of the phase transformation rate information measured by the phase transformation rate meter 20 installed at one or more points in the annealing process and the reheating process are used as input performance data to generate a prediction model for the hydrogen content in the steel strip that has been learned through machine learning using the input performance data.

[0093] The machine learning method only needs to apply a known learning method, and any machine learning model can be used as long as a practically sufficient prediction accuracy of the amount of hydrogen in steel of the steel plate can be obtained. For example, a known machine learning algorithm based on a neural network including deep learning, convolutional neural network (CNN), recurrent neural network (RNN), etc. can be used. As other algorithms, decision tree learning, random forest, support vector regression, Gaussian process, etc. can be exemplified. In addition, an ensemble model (ensemble model) combining multiple models can also be used. In addition, the hydrogen content in steel prediction model only needs to be appropriately updated using the latest learning data. This is because it can cope with long-term changes in operating conditions of continuous hot dip coating equipment.

[0094] <Operating parameters of continuous hot-dip galvanizing equipment>

[0095] As operating parameters for the continuous hot-dip coating equipment, any operating parameters that affect the amount of hydrogen in the steel strip can be used, in addition to the phase transformation rate information measured by the phase transformation rate meter 20. Operating parameters for the continuous hot-dip coating equipment are broadly classified into operating parameters related to the thermal history of the steel strip and operating parameters related to the atmosphere of the continuous hot-dip coating equipment through which the steel strip passes.

[0096] <Operational parameters related to thermal history>

[0097] If using Figure 2 As an example of the thermal history of the steel strip in the annealing step, the coating step, and the reheating step shown, the following operating parameters in a continuous hot-dip coating facility can be used.

[0098] For example, as the operating parameters of the heating belt 6 , the time and the temperature rise amount of the steel strip passing through the heating belt 6 may be used, or an average temperature rise rate calculated from these values ​​may be used.

[0099] As operating parameters for the soaking zone 7, the average temperature of the steel strip in the soaking zone 7, i.e., the soaking temperature, and the time the steel strip passes through the soaking zone 7, i.e., the soaking time, can be used. As operating parameters for the cooling zone 8, the time the steel strip passes through the first cooling zone 8A and the temperature drop can be used, or an average cooling rate calculated from these values ​​can be used. Furthermore, as operating parameters for the cooling zone 8, the time the steel strip passes through the second cooling zone 8B and the temperature drop can be used, or an average cooling rate calculated from these values ​​can be used.

[0100] Furthermore, the control output values ​​of the heating devices in the heating zone 6 and the cooling devices in the cooling zone 8 may also be used as operating parameters. This is because these operating parameters are used to control the temperature history of the steel strip during the annealing process. Furthermore, the line speed of the steel strip in the soaking zone 7, the average cooling rate in the cooling zone 8, and the injection pressure of cooling devices such as gas jets may also be used. This is because these factors also affect the thermal history of the steel strip.

[0101] As operating parameters in the coating section, the atmosphere temperature inside the nose 19, the bath temperature of the coating bath in the galvanizing tank 16, and the temperature and spray pressure of the gas sprayed toward the steel strip in the wiping device 21 can be used.

[0102] As operating parameters for the alloying strip 17, the temperature rise and transit time measured by radiation thermometers located on the inlet and outlet sides of the induction heating device installed in the alloying strip 17 can be used, or an average temperature rise rate calculated from these values ​​can be used. As operating parameters for the holding strip 18, the average temperature of the steel strip in the holding strip 18 and the time it passes through the holding strip 18 can be used. As operating parameters for the final cooling zone 11, the time it passes through the final cooling zone 11 and the temperature drop can be used, or an average cooling rate calculated from these values ​​can be used. Furthermore, the control output values ​​of the heating device in the alloying strip 17 and the control output values ​​of the cooling device in the final cooling zone 11 can also be used as operating parameters. This is because these operating parameters are used to control the temperature history of the steel strip during the reheating process.

[0103] <Operational parameters related to atmosphere gas>

[0104] As operating parameters in the continuous hot dip coating equipment according to this embodiment, in addition to the above-mentioned operating parameters related to the thermal history of the steel strip, operating parameters related to the atmospheric gas of the continuous hot dip coating equipment through which the steel strip passes may be selected.

[0105] As operating parameters in the annealing section, the gas composition of the atmosphere in each of the heating zone 6, soaking zone 7, and cooling zone 8 can be used. The hydrogen concentration is particularly preferred because it affects the amount of hydrogen that enters the steel strip during the annealing process.

[0106] As an operating parameter in the plating section, the plating thickness controlled by the wiping device 21 can be used. This is because when a steel strip is galvanized, the presence of the film makes it difficult for hydrogen that has penetrated into the steel to escape, but the degree of this difficulty varies depending on the plating thickness.

[0107] Furthermore, as an operating parameter inside the nostril 19 of the coating section, the gas composition of the atmosphere in the nostril 19 can be used. The hydrogen concentration is particularly preferably used because it affects the amount of hydrogen that penetrates into the steel strip inside the nostril 19 .

[0108] As operating parameters in the reheating section, the gas composition of the atmosphere in each of the alloying zone 17, the holding zone 18, and the final cooling zone 11 can be used. The hydrogen concentration is particularly preferred because it affects the ease with which hydrogen in the steel escapes to the outside during the reheating process.

[0109] Furthermore, the concentrations of the gas components within each of the annealing, reheating, and coating sections change due to the H2, N2, and H2O supplied to the nose 19. This changes the dew point within the nose, i.e., the H2O concentration. This influences the H2 concentration in the atmosphere, and the dew point within the nose 19 of the annealing, reheating, and coating sections can be used as an operating parameter in the continuous hot-dip coating system.

[0110] <Selection of operating parameters for continuous hot-dip galvanizing equipment>

[0111] In the present embodiment, one or more operating parameters selected from the above-mentioned operating parameters of the continuous hot-dip coating equipment are used as inputs to the steel hydrogen content prediction model of the steel strip.

[0112] The reason for using operating parameters related to the thermal history of the steel strip in the annealing, coating, and reheating sections is that the diffusion rate of hydrogen in steel is affected by the temperature of the steel strip. Furthermore, a high hydrogen diffusion rate makes it easier for hydrogen to penetrate the surface of the steel strip.

[0113] Furthermore, the time (residence time) that the steel strip spends in each zone (annealing, coating, and reheating) is used as an operating parameter because it affects the amount of hydrogen that enters or exits the steel. Furthermore, the diffusion time of these hydrogen amounts throughout the steel changes.

[0114] At this time, the amount of hydrogen in the steel increases in the annealing section, where the steel strip is maintained at a high temperature, and decreases in the reheating section, where the temperature is maintained at a lower level. Furthermore, the coating of the steel strip surface affects the ease with which hydrogen can escape from the steel. Therefore, as operating parameters related to the thermal history, it is preferable to use a combination of one or more parameters selected from the annealing section operating parameters and one or more parameters selected from the reheating section operating parameters. This is because the amount of hydrogen in the steel of the steel strip detected at the delivery side of the continuous hot-dip coating equipment is significantly affected by the balance between hydrogen intrusion and discharge into the steel. Furthermore, it is even more preferable to use, in addition to these operating parameters, one or more parameters selected from the plating section operating parameters. This is because the balance between hydrogen intrusion and discharge into the steel is affected.

[0115] On the other hand, as mentioned above, operating parameters related to the atmosphere in each of the annealing, plating, and reheating zones are used because hydrogen intrusion and release into steel are affected by the composition of the atmospheric gas. Therefore, in this embodiment, it is preferable to use a combination of one or more parameters selected from the operating parameters related to the thermal history and parameters selected from the operating parameters related to the atmospheric gas. This is because both parameters affect the intrusion and release behavior of hydrogen into steel.

[0116] Regarding the operating parameters of the continuous hot-dip coating system in this embodiment, a set of operating parameters is acquired for each steel strip as learning data, as described above. This is because the information related to the hydrogen content in steel, which serves as the output of the hydrogen content prediction model, is generally collected on a per-strip basis. In this case, while the thermal history data and atmospheric gas data are collected continuously along the length of the steel strip, representative values ​​are calculated for each strip and used as operating parameters for the continuous hot-dip coating system. For example, data collected at a predetermined distance from the leading or trailing end of the strip can be used, or data obtained by averaging the values ​​measured along the length can be used.

[0117] <Phase transition rate information>

[0118] In this embodiment, a phase transformation rate meter 20 for measuring the austenite phase ratio is set in at least one of the annealing process or the reheating process of the continuous hot dip coating equipment, and the measurement results of the phase transformation rate meter 20 are formed into phase transformation rate information to serve as one of the learning data for the above-mentioned hydrogen content prediction model in steel.

[0119] The data obtained by the phase transformation rate meter 20 is continuous data obtained at each sampling period along the length of the steel strip as austenite phase ratio data. However, a representative value is calculated for a single strip and used as actual phase transformation rate information performance data. In this case, the phase transformation rate measurement results, which serve as the output of the hydrogen content in steel prediction model and are measured at a location roughly corresponding to the location where actual performance data related to the hydrogen content in the steel strip is acquired, are preferably used as actual phase transformation rate information performance data. In continuous hot-dip plating equipment, the phase transformation rate of the steel strip may fluctuate along its length. Since the phase transformation rate has a strong correlation with the hydrogen content in the steel strip, aligning the measured phase transformation rate values ​​with the locations where actual hydrogen content data is collected allows for more accurate prediction of the hydrogen content in steel.

[0120] Here, for the prediction of the amount of hydrogen in steel, the ratio of the austenite phase (γ phase) of the steel strip becomes an important parameter. Generally, the diffusion coefficient of hydrogen in the austenite phase is about one order of magnitude smaller than that in the ferrite phase (α phase). Therefore, in a zone where the temperature is maintained at a high temperature and the γ phase is the main component, such as the soaking zone of a continuous hot dip coating equipment, the intrusion of hydrogen from the surrounding atmosphere into the steel is slowed down, and the hydrogen that temporarily intrudes into the steel is difficult to release to the surrounding area. On the other hand, in a zone where an internal structure containing a certain degree of ferrite phase (α phase) is formed, such as the holding zone 18, the intrusion of hydrogen from the surrounding atmosphere into the steel is promoted. However, even if hydrogen temporarily intrudes into the steel, it is easy to release to the surrounding area.

[0121] In continuous hot-dip coating equipment, the mechanical properties of the steel are controlled by controlling the structure of the steel strip through phase transformation. As the steel strip passes through the annealing section (heating zone 6, soaking zone 7, cooling zone 8), coating section (nose 19, galvanizing tank 16, wiping device 21), and reheating section (alloying zone 17, holding zone 18, final cooling zone 11), the internal structure of the steel strip changes. Therefore, a phase transformation rate meter 20 is used to obtain information about the austenite phase (γ phase) of the steel strip, thereby improving the accuracy of predicting the hydrogen content in the steel strip.

[0122] Furthermore, the phase transformation behavior of the steel strip varies depending on the strength grade and component composition of the steel strip to be produced, and the history of its internal structural transformation also changes. Therefore, when attempting to predict the hydrogen content in different steel grades, it is particularly useful to use the phase transformation rate information from the phase transformation rate meter 20, which reflects information on the internal structure of the steel strip, in a steel hydrogen content prediction model.

[0123] On the other hand, in this embodiment, in addition to using the operating parameters of the continuous hot-dip coating equipment, the reason for using the phase transformation rate information measured by the phase transformation rate meter 20 is as follows. The operating parameters of the continuous hot-dip coating equipment affect the amount of hydrogen in the steel of the steel strip through the recovery, recrystallization, grain growth, precipitation, phase transformation and other processes in the internal structure of the steel strip. However, such changes in the internal structure are not only determined by the operating parameters of the continuous hot-dip coating equipment, but are also affected by the processing history in the previous process, namely the hot rolling process and the cold rolling process. For example, the coiling temperature in the hot rolling process affects the size (distribution) and amount of precipitates as the internal structure of the hot-rolled steel plate, and affects the grain growth and phase transformation behavior in the heat treatment process. In addition, the reduction rate in the cold rolling process affects the recrystallization, grain growth and phase transformation behavior of the annealing process through the strain state accumulated in the internal structure of the cold-rolled steel plate. Therefore, the learning data for the hydrogen content in steel prediction model are only the operating parameters of the continuous hot-dip galvanizing equipment. It is impossible to consider the impact of the operating parameters of the process before such annealing process on the hydrogen content in the steel after the steel strip is heat treated, so it is difficult to predict the hydrogen content in steel.

[0124] By using the phase transformation rate information measured by the phase transformation rate meter 20 during the heating or reheating process as learning data, the influence of operating parameters in the hot rolling and cold rolling processes, the preceding processes of the annealing process, on the hydrogen content in the steel after heat treatment can be considered as indirect information during the process of the continuous hot-dip coating system. This allows the prediction of the hydrogen content in steel to be realized as a steel hydrogen content prediction model.

[0125] In summary, in this embodiment, a phase transformation rate meter 20 for measuring the austenite phase ratio is set in at least one of the annealing process or the reheating process of the continuous hot dip coating equipment, and the measurement results of the phase transformation rate meter 20 are formed into phase transformation rate information to serve as one of the learning data for the above-mentioned hydrogen content prediction model in steel.

[0126] <Property parameters related to the composition of steel strip>

[0127] In this embodiment, the input data for the hydrogen content in steel prediction model preferably includes one or more parameters selected from steel strip property parameters related to the steel strip's chemical composition. This is because the phase transformation behavior and internal structure during the heat treatment process are affected by the steel strip's chemical composition. Furthermore, a prediction model can be generated to predict the hydrogen content in steel strips having various chemical compositions, such as hot-dip galvanized steel sheets produced in continuous hot-dip coating equipment, thereby expanding the scope of application of the hydrogen content in steel prediction model.

[0128] As property parameters related to the composition of the steel strip, the contents of C, Si, and Mn, chemical components contained in the steel strip, can be used. Other property parameters related to the composition of the steel strip can include the contents of Cu, Ni, Cr, Mo, Nb, Ti, V, B, and Zr. However, it is not necessary to use all of these components as property parameters related to the composition of the steel strip. Appropriate selection of a portion is sufficient depending on the type of steel strip being manufactured in the continuous hot-dip coating system.

[0129] C is an element effective in increasing the strength of a steel sheet, and contributes to increasing the strength by forming martensite, which is one of the hard phases in the steel structure.

[0130] Si is an element that contributes primarily to high strength through solid solution strengthening. Its decrease in ductility is relatively small compared to its increase in strength, contributing not only to strength but also to an improved balance between strength and ductility. On the other hand, Si tends to form Si-based oxides on the surface of steel sheets, sometimes causing non-plating. Furthermore, Si stabilizes austenite during annealing, making it more likely to form retained austenite in the final product.

[0131] Mn is effective as an element that contributes to high strength through solid solution strengthening and martensite formation.

[0132] Nb, Ti, V, and Zr contribute to increasing the strength of the steel sheet by forming fine precipitates that form carbides or nitrides (carbonitrides may also form carbonits) with C or N.

[0133] Cu, Ni, Cr, Mo, and B are elements that contribute to increasing the strength by improving hardenability and facilitating the formation of martensite.

[0134] Here, the distribution of these component compositions in the longitudinal direction of the steel strip is substantially constant, and one property parameter can be obtained as performance data for one steel strip.

[0135] Furthermore, in addition to using steel strip property parameters related to its composition, other properties related to the strip's dimensions, such as thickness, width, and length, can also be used as learning data for the hydrogen content prediction model of this embodiment. This is because these properties affect heat conduction within the continuous hot-dip coating facility. Therefore, even with the same furnace atmosphere temperature, variations in the steel sheet temperature can affect the hydrogen content in the steel strip.

[0136] <Method for controlling hydrogen content in steel strip>

[0137] Figure 4 A method for controlling the amount of hydrogen in a steel strip using the above-mentioned method for predicting the amount of hydrogen in steel will be described.

[0138] The implementation of the method for controlling the amount of hydrogen in steel in this embodiment differs depending on the installation position of the phase change rate meter 20 installed in at least one of the annealing process or the reheating process of the continuous hot dip coating equipment. Specifically, as the phase change rate information used in the input of the prediction model for the amount of hydrogen in steel generated as described above, when a plurality of phase change rate meters 20 are installed, a band upstream of the phase change rate meter 20 installed on the most downstream side and a band downstream thereof are divided. The band from the feed side of the continuous hot dip coating equipment to the above-mentioned phase change rate meter 20 is called the hydrogen content in steel identification band. In addition, the band downstream of the above-mentioned phase change rate meter 20 is called the hydrogen content in steel control band. And, at the moment when the front end portion of the steel strip, which is the object of the prediction of the amount of hydrogen in steel, reaches the position of the above-mentioned phase change rate meter 20 and obtains the phase change rate information of the steel strip, the process starts. Figure 4 The control flow shown.

[0139] At this point, for the steel strip being controlled for hydrogen content, the actual operating performance data of the continuous hot-dip coating system obtained in the hydrogen content identification zone of the continuous hot-dip coating system and the phase transformation rate information measured by the phase transformation rate meter 20 serve as input data for the hydrogen content prediction model. The step of acquiring this input data is sometimes referred to as an input data acquisition step. In the input data acquisition step, actual operating performance data of the continuous hot-dip coating system in the hydrogen content control zone at that point or the set values ​​of the operating conditions of the continuous hot-dip coating system may also be acquired as input data for the hydrogen content prediction model. Using this acquired data as input, the hydrogen content prediction model is used to predict the hydrogen content of the steel strip downstream of the reheating process.

[0140] On the other hand, in this embodiment, an upper limit value for the hydrogen content in the steel strip is also set in the host computer, and the predicted hydrogen content in the steel strip is compared with this upper limit value. For steel materials used in environments where hydrogen embrittlement cracking may become a practical problem, the upper limit value for the hydrogen content in the steel strip is preferably set to a value that allows for a certain margin relative to the target value for reducing the hydrogen content in the steel strip to a level that does not cause operational problems. For example, the upper limit value for the hydrogen content in the steel strip can be set to 0.40 ppm.

[0141] At this point, the operating condition setting unit of the continuous hot-dip coating equipment compares the upper limit of hydrogen content in steel, which has been pre-set as described above, with the predicted result of hydrogen content in steel. If the predicted hydrogen content in steel is below the upper limit, the operating conditions of the continuous hot-dip coating equipment are determined without changing the initial settings and transmitted to the control unit of the continuous hot-dip coating equipment. On the other hand, if the predicted hydrogen content in steel exceeds the upper limit, the operating conditions in the aforementioned hydrogen content control zone are reset.

[0142] Specifically, in a continuous hot-dip coating system, if the phase change rate meter 20 located on the most downstream side (hereinafter referred to as the most downstream side among the phase change rate meters 20 that provide the phase change rate information used as the input of the hydrogen content prediction model in steel) is located at the outlet of the soaking zone 7 in the annealing process, the area from the inlet side of the continuous hot-dip coating system to the outlet of the soaking zone 7 becomes the hydrogen content identification zone in steel, and the area downstream of the outlet of the soaking zone 7 becomes the hydrogen content control zone in steel. At this time, when the leading end of the steel strip reaches the outlet of the soaking zone 7 and the phase change rate information is obtained by the phase change rate meter 20, the process starts. Figure 4 The flow of controlling the amount of hydrogen in steel is shown. In this case, in the hydrogen content control zone, operating conditions that can be used to control the amount of hydrogen in steel can be reset, including those selected from the cooling conditions in the cooling zone 8 (first cooling zone 8A and second cooling zone 8B), the atmosphere temperature inside the furnace nose 19 in the coating section, the spray pressure of the wiping device 21, the reheating conditions in the alloying zone 17, the holding temperature and holding time in the holding zone 18, and the cooling rate in the final cooling zone 11. The reset operating conditions are not necessarily limited to those used as inputs to the hydrogen content prediction model.

[0143] On the other hand, when the phase transformation rate meter 20 on the most downstream side is set at the inlet or outlet of the alloying zone 17, since the hydrogen content control zone in the steel is limited to the zone after the holding zone 18 or the final cooling zone 11, the operating conditions reset in the continuous hot dip coating equipment are limited to the holding time in the holding zone 18, the mixing ratio of the atmospheric gas components in the holding zone 18, the cooling rate in the final cooling zone 11, etc.

[0144] Therefore, the position of the phase transformation rate meter 20, located on the far downstream side and serving as an input to the hydrogen content in steel prediction model, can be appropriately determined by balancing the degree of freedom in resetting operating conditions with the prediction accuracy of the hydrogen content in steel prediction model. Specifically, while lengthening the hydrogen content in steel identification zone improves the prediction accuracy of the hydrogen content in steel, the degree of freedom in resetting operating conditions in the hydrogen content in steel control zone decreases. Conversely, shortening the hydrogen content in steel identification zone decreases the prediction accuracy of the hydrogen content in steel, but increases the degree of freedom in resetting operating conditions in the hydrogen content in steel control zone.

[0145] Here, the hydrogen in the steel strip having an internal structure mainly composed of γ phase is not easily released. If the ratio of α phase becomes larger, hydrogen is easily released. Therefore, it is preferred that the hydrogen content control zone in steel, which is used to effectively reduce the hydrogen content in steel, is set on the downstream side of the cooling zone 8 in the annealing section. As mentioned above, when multiple phase change rate meters 20 are set in the continuous hot dip coating equipment, it is preferred to use the phase change rate meter 20 on the most downstream side as a reference to divide the hydrogen content identification zone in steel and the hydrogen content control zone in steel. However, the phase change rate meter 20 used to divide the hydrogen content identification zone in steel and the hydrogen content control zone in steel does not necessarily have to be the phase change rate meter 20 on the most downstream side. The hydrogen content identification zone in steel and the hydrogen content control zone in steel can also be divided based on any phase change rate meter selected from the multiple phase change rate meters 20.

[0146] <Estimation device for hydrogen content in steel>

[0147] Figure 5 1 is a diagram showing the configuration of a device for predicting the amount of hydrogen in steel. The device for predicting the amount of hydrogen in steel includes an acquisition unit, an output unit, a storage unit, and a prediction unit.

[0148] The acquisition unit, for example, includes any interface capable of acquiring the hydrogen content in steel prediction model generated by the machine learning unit from the hydrogen content in steel prediction model generation device. For example, the acquisition unit may include a communication interface for acquiring the hydrogen content in steel prediction model from the hydrogen content in steel prediction model generation device. In this case, the acquisition unit may receive the hydrogen content in steel prediction model from the machine learning unit according to a prescribed communication protocol.

[0149] In addition, the acquisition unit acquires the operating conditions of the continuous hot dip coating equipment from, for example, a process control computer or a host computer. For example, the acquisition unit may include a communication interface for acquiring the operating conditions.

[0150] The acquisition unit may also acquire input information based on user operations. In this case, the device for predicting the amount of hydrogen in steel further includes an input unit, which includes one or more input interfaces for detecting user input and acquiring input information based on the user's operations. For example, the input unit may be a physical key, an electrostatic capacitance key, a touch screen integrated with the display of the output unit, or a microphone for receiving voice input, but is not limited thereto. For example, the input unit receives input regarding the operating conditions of the hydrogen content in steel prediction model acquired by the acquisition unit from the device for generating the hydrogen content in steel prediction model.

[0151] The storage unit includes at least one semiconductor memory, at least one magnetic memory, at least one optical memory, or a combination of at least two of these. The storage unit functions as, for example, a main memory device, an auxiliary memory device, or a cache memory. The storage unit stores arbitrary information used for the operation of the hydrogen content in steel prediction device. The storage unit stores, for example, a hydrogen content in steel prediction model acquired by the acquisition unit from a hydrogen content in steel prediction model generation device, operating conditions acquired by the acquisition unit from a host computer, and hydrogen content in steel information predicted by the prediction unit. For example, the storage unit can store system programs and application programs.

[0152] The prediction unit includes one or more processors. In one embodiment, the "processor" is a general-purpose processor or a dedicated processor customized for a specific process, but is not limited to these. The prediction unit is communicatively connected to the various components that make up the hydrogen content in steel prediction device to control the overall operation of the hydrogen content in steel prediction device.

[0153] The prediction unit can be any general-purpose electronic device such as a PC (Personal Computer) or a smartphone, but is not limited thereto and may be one or more mutually communicative server devices or other electronic devices dedicated to the hydrogen content in steel prediction system.

[0154] The prediction unit calculates a predicted value of the amount of hydrogen in steel based on the operating conditions acquired via the acquisition unit and based on the hydrogen amount in steel prediction model acquired from the hydrogen amount in steel prediction model generation device.

[0155] The output unit supplies the predicted value of the amount of hydrogen in the steel supplied from the prediction unit to an operating condition setting device described later.

[0156] The output unit may include one or more output interfaces for outputting information to notify the user. The output interface is, for example, a display. The display is, for example, an LCD or an organic EL display. The output unit outputs data obtained by the operation of the device for predicting the amount of hydrogen in steel. The output unit may also be connected to the device for predicting the amount of hydrogen in steel as an external output device instead of being equipped in the device for predicting the amount of hydrogen in steel. As a connection method, for example, any method such as USB, HDMI (registered trademark) or Bluetooth (registered trademark) can be used. For example, the output unit is a display that outputs information through images or a speaker that outputs information through sounds, but is not limited to them. For example, the output unit prompts the user with the predicted value of the amount of hydrogen in steel predicted by the prediction unit. The user can appropriately set the operating conditions of the continuous hot-dip galvanizing equipment based on the predicted value of the information on the amount of hydrogen in steel prompted by the output unit.

[0157] A more preferred embodiment of the above-described hydrogen content prediction device for a steel strip is a terminal device comprising a tablet terminal, the terminal device having an input unit for acquiring input information based on user operations and a display unit for displaying the hydrogen content in steel based on the prediction unit. The terminal device acquires the user input information from the input unit and uses the acquired input information to update some or all of the operating parameters of the continuous hot-dip coating system already input into the hydrogen content prediction device. Specifically, when the prediction unit of the hydrogen content prediction device predicts the hydrogen content of a steel strip being processed in the continuous hot-dip coating system, the operator in charge of operations uses the tablet terminal to modify some of the operating parameters of the continuous hot-dip coating system already input into the acquisition unit. In this case, the acquisition unit retains the original input data for those operating parameters of the continuous hot-dip coating system that have not been modified from the tablet terminal, and only modifies those operating parameters that have been modified. Consequently, the acquisition unit generates new input data for the hydrogen content prediction model, and the prediction unit calculates a predicted value for the hydrogen content in steel based on this input data. Then, the calculated predicted value of the amount of hydrogen in the steel is displayed on the display unit of the terminal via the output unit.

[0158] This allows the operator or factory manager of the continuous hot-dip coating facility to immediately check the predicted value of the hydrogen content in steel when the operating parameters of the continuous hot-dip coating facility are changed, and to quickly change to appropriate operating conditions.

[0159] (Example of the first embodiment)

[0160] Hereinafter, this embodiment will be described in detail using examples.

[0161] exist Figure 1 In the hot-dip galvanizing equipment shown in the figure, 200 rolls of hot-dip galvanized steel sheets (the upper limit of the hydrogen content in steel is 0.40ppm) are manufactured. At this time, the performance data of the attribute information of the steel sheets loaded into the hot-dip galvanizing equipment and the operation performance data of the operation parameters in the hot-dip galvanizing equipment are used as input performance data, and the hydrogen content in the steel sheets on the delivery side of the hot-dip galvanizing equipment is used as output performance data to obtain a plurality of learning data. By machine learning using the obtained plurality of learning data, a plurality of learning data are obtained. Figure 3 The method shown generates a steel hydrogen content prediction model that uses information on the steel hydrogen content of a steel strip on the downstream side of the reheating process as output data.

[0162] When generating the hydrogen content prediction model in steel, the C, Si, and Mn contents of the steel strip were used as inputs to the property parameters of the steel strip related to the composition of the steel strip. In addition, the temperature of the steel plate in the soaking zone 7 and the conveying speed of the steel strip tip when passing through the soaking zone 7, which are the actual operating performance data of the continuous hot-dip coating equipment, were used as inputs. Figure 1 Phase transformation rate meters 20 are installed in-line at two locations in the continuous hot-dip coating system, at the outlet of the soaking zone 7 and the inlet of the holding zone 18. Actual performance data on phase transformation rate information measured based on these phase transformation rates is used as input performance data. Furthermore, in this embodiment, the set values ​​of the steel strip thickness and width are used as additional inputs to generate the hydrogen content prediction model.

[0163] Here, the hydrogen content in the steel strip obtained as learning data is obtained by a temperature-increasing hydrogen analysis method using gas chromatography using a test piece collected after the steel strip passes through a hot-dip galvanizing facility.

[0164] The hydrogen content prediction model in steel generated in this way is applied to Figure 4 The hydrogen content prediction unit in the hydrogen content control in steel shown produced 100 coils of hot-dip galvanized steel sheets. That is, the hydrogen content prediction method for steel strip using the hydrogen content prediction model is applied to the hydrogen content control method and manufacturing method for steel strip.

[0165] At this time, the aforementioned steel hydrogen content prediction model was used to predict the hydrogen content in the steel sheets at the outlet of the hot-dip galvanizing facility. The hot-dip galvanizing facility's operating parameters were reset to ensure that the predicted hydrogen content fell within a pre-set upper limit (in this case, 0.40 ppm). The phase transformation rate meter 20, located on the far downstream side, was located at the entrance of the holding belt 18. Therefore, the area from the inlet of the continuous hot-dip galvanizing facility to the entrance of the holding belt 18 became the steel hydrogen content assessment zone, while the area downstream of the entrance of the holding belt 18 became the steel hydrogen content control zone. Figure 4 The process shown begins after the leading end of the steel strip reaches the entrance of the holding zone 18. In the steel hydrogen content control zone, the holding temperature and holding time in the holding zone 18 and the cooling rate in the cooling zone 8 are reset as the operating conditions used to control the hydrogen content in the steel. The hydrogen content in the steel obtained through the steel hydrogen content measurement test of these steel strips is then collected. The results show that 95% of the steel strips have a hydrogen content below the upper limit (0.40 ppm).

[0166] On the other hand, as a comparative example, the same experiment was conducted by the method described in Patent Document 1. As a result, the steel strip having a hydrogen content below the upper limit of 65% was found.

[0167] (Second embodiment)

[0168] The second embodiment of the present disclosure predicts the hydrogen content in steel strip. This method estimates the hydrogen content in cold-rolled steel sheets at the outlet of a continuous annealing facility. The cold-rolled steel sheets are produced by heat-treating steel sheets reduced to a predetermined thickness through hot rolling, pickling, and cold rolling in a continuous annealing facility. At least after the hot rolling process, the thin steel sheets are coiled and then subjected to heat treatment. Therefore, in this embodiment, these thin steel sheets are sometimes referred to as "steel strip."

[0169] Continuous annealing equipment

[0170] In this embodiment, the continuous annealing facility is a continuous annealing facility (CAL) that performs a manufacturing process including an annealing step and a reheating step.

[0171] Figure 6 This is a schematic diagram showing an example of a continuous annealing facility for producing cold-rolled steel sheets. Figure 6 The arrows indicate the direction of steel strip travel. The continuous annealing equipment is broadly divided into the feed-side equipment, the furnace section, and the discharge-side equipment. The feed-side equipment includes an uncoiler 1, a welding machine 2, an electrolytic cleaning device 3, and feed-side looper rollers 4. The furnace section consists of an annealing section and a reheating section. The discharge-side equipment includes a discharge-side looper roller 12, a temper rolling machine 13, an inspection machine 14, and a tension coiler 15. The inspection machine 14 includes a sampling device for collecting sample material from the steel strip for offline determination of the hydrogen content in the steel.

[0172] The annealing section includes a heating zone 6, a soaking zone 7, and a cooling zone 8, and sometimes includes a preheating zone 5 upstream of the heating zone 6. The annealing process in this embodiment refers to a heat treatment process performed by the annealing section. More specifically, the annealing process is a process in which the temperature of the steel strip is raised from near room temperature, maintained at a predetermined temperature, and then lowered to near room temperature. The reheating section includes a reheating zone 9, an overaging zone 10, and a final cooling zone 11, with an induction heating device being arranged in the reheating zone 9. The reheating process in this embodiment refers to a heat treatment process performed by the reheating section. More specifically, the reheating process is a process in which the steel strip that has passed through the cooling zone 8 is subjected to an overaging treatment.

[0173] The heating zone 6 is used to heat the steel strip to a predetermined temperature between 600°C and 900°C, depending on the steel type. Direct-fire or radiant burners are used in the heating zone 6. These heaters offer high heating capacity and relatively fast response, making it easy to adjust the heating profile when changing the heating cycle. The soaking zone 7 maintains the steel strip at a predetermined temperature, providing sufficient heating capacity to compensate for heat dissipation from the furnace.

[0174] The cooling zone 8 is a device for cooling the steel strip to a specified temperature, and gas jet cooling, roller cooling, water cooling (water quenching), etc. are used as cooling methods. Gas jet cooling is a cooling method in which gas is blown from a nozzle onto the surface of the steel strip. Roller cooling is a cooling method in which the steel strip is cooled by contacting it with a water-cooled roller. Water cooling is a cooling method in which the steel strip is cooled by immersing it in a water-cooling tank provided on the downstream side of the soaking zone 7. These cooling devices have different cooling rates for the steel strip, so the cooling zone 8 can be divided into a plurality of areas such as the first cooling zone 8A and the second cooling zone 8B. By combining different cooling methods or changing the cooling conditions of the same cooling method, the thermal history of the steel strip during cooling can be controlled.

[0175] Furthermore, a mixed gas containing hydrogen, nitrogen, and water vapor is supplied to the interiors of the heating zone 6, soaking zone 7, and cooling zone 8 to adjust the atmosphere during the annealing step. Since the supplied gas contains water vapor, not only the gas composition but also the dew point of the atmosphere during the annealing step is adjusted.

[0176] The reheating zone 9 is located downstream of the cooling zone 8. After cooling the steel strip to a predetermined temperature in the cooling zone 8, it is reheated to approximately 300-400°C using an induction heater. The overaging zone 10 performs an overaging treatment, holding the reheated steel strip for a predetermined period of time. The final cooling zone 11 is used to finally cool the overaged steel strip to near room temperature. Similar to the cooling zone 8, the final cooling zone 11 can be divided into multiple cooling zones, such as a first final cooling zone 11A and a second final cooling zone 11B, to control the thermal history of the steel strip during cooling.

[0177] In the continuous annealing facility, thermometers for measuring the surface temperature of the steel strip are installed at multiple locations within the heating zone 6, soaking zone 7, cooling zone 8, reheating zone 9, overaging zone 10, and final cooling zone 11, which constitute the annealing section. In particular, in the cooling zone 8, where the temperature of the steel strip varies significantly, thermometers are installed at the entry and exit sides of the cooling zone. The surface temperatures of the steel strip at these locations are measured to calculate the actual cooling rate of the cooling zone 8. For example, a radiation thermometer is used as the thermometer, which continuously measures the surface temperature of the steel strip at the center of the strip width. The thermometer is not limited to a radiation thermometer; another example is a profile radiation thermometer, which measures the temperature distribution across the strip width. Furthermore, a furnace thermometer is installed to measure not only the surface temperature of the steel strip but also the atmosphere temperature within the furnace in each zone of the annealing and reheating steps. The measured surface and atmosphere temperatures of the steel strip are output to a process control computer, which controls the continuous annealing facility and provides overall operational control.

[0178] Figure 7This graph shows the thermal history of a steel strip during the annealing and reheating steps in a continuous annealing facility used to produce cold-rolled steel sheet. The horizontal axis represents time, and the vertical axis represents the steel strip temperature. The steel strip temperature is, for example, the surface temperature of the steel strip. The graph shows the thermal history of the steel strip as it undergoes an annealing step in a heating zone 6, a soaking zone 7, and a cooling zone 8, followed by a reheating step in a reheating zone 9, an over-aging zone 10, and a final cooling zone 11. To prevent material variations due to the longitudinal position of the steel strip, the conveyance speed of the steel strip is kept constant during the annealing step. However, when welding steel strips of varying thickness, width, and steel grade, the line speed may vary before and after the weld. Consequently, the shape of the thermal history graph may vary depending on the position of the steel strip being measured. Furthermore, depending on operating conditions, the reheating step in the reheating zone 9, over-aging zone 10, and final cooling zone 11 may not be performed. In such cases, the temperature of the steel strip after passing through the cooling zone 8 remains approximately constant at room temperature.

[0179] <Atmosphere gas control>

[0180] The annealing atmosphere is controlled by supplying a mixed gas containing hydrogen, nitrogen, and water vapor into the heating zone 6, soaking zone 7, and cooling zone 8, where the annealing process is performed. The hydrogen contained in the annealing atmosphere affects the amount of hydrogen that enters the steel strip during the annealing process. Therefore, the composition and flow rate of the supplied gas are measured and adjusted and controlled as needed.

[0181] In the heating zone 6, a heating device such as a radiant tube (RT) or an electric heater can be used to indirectly heat the steel strip. Simultaneously with the flow of gas from the soaking zone 7 and the cooling zone 8 into the heating zone 6, a reducing gas or a non-oxidizing gas can be supplied to the heating zone 6. As a reducing gas, an H2-N2 mixed gas is generally used. As such an H2-N2 mixed gas, for example, a gas having a composition of 1 to 20% by volume of H2 and the remainder consisting of N2 and inevitable impurities (dew point: about -60°C) can be cited. In addition, as a non-oxidizing gas, a gas having a composition consisting of N2 and inevitable impurities (dew point: about -60°C) is used. The method of supplying gas to the heating zone 6 is not particularly limited, but it is preferred to supply gas from two or more inlets in the height direction and one or more inlets in the length direction so that the gas is uniformly supplied into the heating zone 6.

[0182] In the soaking zone 7, a radiant tube can be used as a heating mechanism to indirectly heat the steel strip. The average temperature inside the soaking zone 7 is preferably 700 to 900°C. A reducing gas or a non-oxidizing gas is supplied to the soaking zone 7. As the reducing gas, an H2-N2 mixed gas is generally used. For example, a gas having a composition of 1 to 20% by volume of H2 and the remainder consisting of N2 and inevitable impurities (dew point: approximately -60°C) can be used. In addition, as the non-oxidizing gas, a gas having a composition consisting of N2 and inevitable impurities (dew point: approximately -60°C) can be used.

[0183] The cooling zone 8 is equipped with a cooling device, and the steel strip is cooled during the steel strip passing through the cooling zone 8. The aforementioned gas can be supplied to the cooling zone 8 in the same manner as the soaking zone 7. It is preferable to supply gas from two or more inlets in the height direction and two or more inlets in the length direction of the cooling zone 8 so that the gas is uniformly supplied to the cooling zone 8.

[0184] A hydrogen concentration meter and a dew point meter are installed in the heating zone 6, soaking zone 7, and cooling zone 8, where the annealing process is performed, to measure the gas atmosphere within the furnace. The hydrogen concentration meter uses a catalytic combustion sensor that measures the temperature rise of the platinum wire coil caused by catalytic combustion of the gas on the catalyst surface. For example, the XP-3110 combustible gas detector manufactured by Shin Cosmos Electric Co., Ltd. can be used. However, hydrogen concentration meters using other measurement methods, such as those that detect hydrogen concentration based on changes in thermal conductivity caused by gas concentration, can also be used. The dew point meter can be a capacitance type or a mirror-cooled type. For example, the DMT345 dew point converter manufactured by Vaisala can be used.

[0185] The hydrogen concentration meter is preferably set in any of the heating zone 6, soaking zone 7, and cooling zone 8. The hydrogen concentration meter can be set at any location as long as it is in the heating zone 6, soaking zone 7, and cooling zone 8. However, the higher the temperature of the steel strip, the easier it is for hydrogen in the steel to diffuse. Therefore, the hydrogen concentration meter is preferably set near the delivery side of the heating zone 6 or the soaking zone 7. In addition, the hydrogen concentration meter can be set at any location, but it is preferred to set multiple hydrogen concentration meters at different locations. This is because: by obtaining multiple hydrogen concentration information, the prediction accuracy of the hydrogen content in the steel is improved. The measured value is output to the process control computer.

[0186] Similarly, the dew point meter is preferably installed in any of the heating zone 6, soaking zone 7, and cooling zone 8. The dew point meter can be installed anywhere, as long as it is in the heating zone 6, soaking zone 7, or cooling zone 8. While the installation location can be anywhere, it is preferable to install multiple dew point meters in different locations. This is because obtaining multiple dew point information improves the accuracy of predicting the hydrogen content in steel. The measured values ​​are output to the process control computer.

[0187] A mixed gas containing hydrogen, nitrogen, and water vapor is supplied to each zone in the reheating process to control the atmosphere. The hydrogen content in the atmosphere affects the amount of hydrogen that penetrates the steel strip during the reheating process. Therefore, the composition and flow rate of the supplied gas are measured and adjusted and controlled as needed.

[0188] A hydrogen concentration meter and a dew point meter are also installed in the reheating process to measure the gas atmosphere. These meters can be installed at any location. While multiple meters can be installed at one location each, it is preferred to install multiple meters at different locations. This is because obtaining information from multiple hydrogen concentration meters and dew point data improves the accuracy of predicting the hydrogen content in the steel. The measured values ​​are output to the process control computer.

[0189] <Phase change rate meter>

[0190] The phase transformation rate meter 20 is a measuring instrument for measuring the ratio of the austenite phase (γ phase) to the whole as the internal structure of the steel strip in the heat treatment process. In continuous annealing equipment, the structure of the steel plate is often controlled by phase transformation based on the two phase states of the specific austenite phase (γ phase) and the ferrite phase (α phase). Therefore, as the phase transformation rate meter 20, a phase transformation rate meter 20 using X-ray diffraction can be used. Since the crystal structures of the γ phase and the α phase are different, if X-rays are irradiated, diffraction peaks are generated from each at a unique angle. This is a method of quantifying the phase transformation rate (γ rate) based on the intensity of the diffraction peak. For example, a product called X-CAP manufactured by SMS can be used. In addition, the following method can be used: a magnetic phase transformation rate measuring device composed of a driving coil that generates a magnetic field and a detection coil that measures the magnetic field passing through the steel strip is used as a magnetic detector, that is, a device for measuring the magnetic phase transformation rate of the steel strip to measure the austenite phase ratio. Specifically, the device described in Japanese Patent Application Laid-Open No. 2019-7907 can be used.

[0191] In this embodiment, the phase transformation rate meter 20 for measuring the austenite phase ratio is installed in at least one of the annealing process and the reheating process of the continuous annealing equipment. Figure 6 The phase transformation rate meter 20 is shown as a candidate for installation. Examples of installation locations include the entrance or exit of the soaking zone 7, or the entrance of the cooling zone 8 in the annealing process. It is preferably installed at the entrance or exit of the reheating zone 9 in the reheating process. While the phase transformation rate meter 20 can be installed anywhere, it is preferably installed at multiple locations. This is because obtaining multiple phase transformation rate information improves the accuracy of predicting the hydrogen content in steel.

[0192] <Information on the amount of hydrogen in steel strip>

[0193] Information related to the amount of hydrogen in steel is obtained by measuring the amount of diffusible hydrogen in steel using a test piece collected from a steel strip sample collected by the sampling equipment in the continuous annealing facility. Any device capable of measuring the amount of hydrogen in steel within a range of 0.01 to 10 ppm can be used. Specifically, a device utilizing temperature-increasing hydrogen analysis using gas chromatography can be used.

[0194] Methods for measuring the amount of hydrogen include gas chromatography mass spectrometry (GC / MS) and temperature desorption spectroscopy (TDS). Apparatuses include GC-4000 Plus from GL Sciences Co., Ltd. and TDS1200 from UBE Scientific Analysis Center Co., Ltd.

[0195] The amount of hydrogen in steel can be measured by the following temperature analysis method. First, a test piece of about 5×30 mm is cut from a cold-rolled steel plate. The surface of the test piece is removed using a groove milling machine (precision grinder) and placed in a quartz tube. Next, after replacing the quartz tube with Ar, the temperature is increased at 200°C / hr, and the hydrogen generated until 400°C is measured by gas chromatography. At this time, the amount of diffusible hydrogen in the steel is the cumulative value of the amount of hydrogen detected in the temperature range of room temperature (25°C) to 400°C.

[0196] The information related to the hydrogen content in the steel strip obtained in this way is sent to the host computer (the computer that gives manufacturing instructions to the process control computer) together with the identification number (coil number) of the steel strip from which the test piece was collected, and the information related to the collection location is also sent to the host computer (the computer that gives manufacturing instructions to the process control computer) as needed.

[0197] <Method for Generating a Prediction Model for Hydrogen Content in Steel>

[0198] Figure 8 A method for generating a steel hydrogen content prediction model for a steel strip according to this embodiment will be described.

[0199] The continuous annealing equipment's operational performance data, performance data on the steel strip's phase transformation rate measured by the phase transformation rate meter 20, and performance data related to the steel strip's hydrogen content are stored in a database. While the details of the continuous annealing equipment's operational performance data will be discussed later, selected performance data from the operational performance data stored in the process control computer that oversees the operation of the continuous annealing equipment is sent to the database of the hydrogen content prediction model generation unit. Furthermore, the performance data on the steel strip's phase transformation rate information is the phase transformation rate information obtained from the aforementioned phase transformation rate meter 20. If the phase transformation rate information is stored in the process control computer, it is sent from the process control computer to the database. However, if the phase transformation rate information is not stored in the process control computer, it is sent directly to the database of the hydrogen content prediction model generation unit.

[0200] Information on the amount of hydrogen in the steel, such as the coil number of the steel strip, is sent to the database along with accompanying information that can be associated with the actual operating performance data of the continuous annealing equipment. Furthermore, the performance data related to the amount of hydrogen in the steel of the steel strip is information obtained through offline testing and is stored in a host computer. This information is also sent to the database along with accompanying information that can be associated with the actual operating performance data of the continuous annealing equipment, such as the coil number of the steel strip. Furthermore, the actual operating performance data of the continuous annealing equipment, the performance data on the phase transformation rate of the steel strip measured by the phase transformation rate meter 20, and the performance data on the amount of hydrogen in the steel of the steel strip are associated through the coil number, etc., and stored in the database as a set of data sets. In this case, the data sets stored in the database are obtained one data set per steel strip. However, when performance data on information related to the hydrogen content in the steel of the steel strip is obtained at multiple locations such as the front end and tail end of the steel strip, it is also possible to use the operating performance data of the continuous annealing equipment and the performance data on the phase transformation rate information of the steel strip obtained at multiple locations such as the front end and tail end of the steel strip to obtain multiple data sets for each steel strip.

[0201] Furthermore, the database preferably includes one or more parameters selected from among the steel strip property parameters related to the steel strip's chemical composition. Actual performance data for the steel strip property parameters related to the steel strip's chemical composition is stored in a process control computer or a host computer as actual performance values ​​during the steelmaking process, along with the coil number. This data set can be constructed by appropriately transmitting it to the database. By including the steel strip property parameters related to the steel strip's chemical composition as input, the hydrogen content prediction model of this embodiment can be widely applied to steel strips with varying chemical compositions.

[0202] The number of data sets in the database used for generating the hydrogen content in steel prediction model of the present embodiment is preferably 200 or more, more preferably 1000 or more.

[0203] In this embodiment, a database created in this manner is used, and at least one piece of operating performance data selected from the operating performance data of the continuous annealing equipment and performance data of phase transformation rate information measured by a phase transformation rate meter 20 installed at one or more points in the annealing process and the reheating process are used as input performance data to generate a prediction model for the hydrogen content in the steel strip learned through machine learning using the input performance data.

[0204] The machine learning method can be any machine learning method as long as it applies a known learning method. As long as a practically sufficient prediction accuracy of the amount of hydrogen in steel of a steel plate can be obtained, any machine learning model can be used. For example, a known machine learning algorithm based on a neural network including deep learning, a convolutional neural network (CNN), a recurrent neural network (RNN), etc. can be used. As other algorithms, decision tree learning, random forest, support vector regression, Gaussian process, etc. can be exemplified. In addition, an integrated model combining multiple models can also be used. In addition, the prediction model for the amount of hydrogen in steel can be appropriately updated using the latest learning data. This is because it can cope with long-term changes in the operating conditions of the continuous annealing equipment.

[0205] <Continuous annealing equipment operating parameters>

[0206] As operating parameters in the continuous annealing equipment, any operating parameters that affect the amount of hydrogen in the steel strip can be used, in addition to the phase transformation rate information measured by the phase transformation rate meter 20. Operating parameters in the continuous annealing equipment are broadly classified into operating parameters related to the thermal history of the steel strip and operating parameters related to the atmosphere gas in the continuous annealing equipment through which the steel strip passes.

[0207] <Operational parameters related to thermal history>

[0208] If using Figure 7 As an example of the thermal history of the steel strip in the annealing step and the reheating step shown, the following operating parameters in the continuous annealing equipment can be used.

[0209] For example, as the operating parameters of the heating belt 6 , the time and the temperature rise amount of the steel strip passing through the heating belt 6 may be used, or an average temperature rise rate calculated from these values ​​may be used.

[0210] As operating parameters for the soaking zone 7, the average temperature of the steel strip in the soaking zone 7, i.e., the soaking temperature, and the time the steel strip passes through the soaking zone 7, i.e., the soaking time, can be used. As operating parameters for the cooling zone 8, the time the steel strip passes through the first cooling zone 8A and the temperature drop can be used, or an average cooling rate calculated from these values ​​can be used. Furthermore, as operating parameters for the cooling zone 8, the time the steel strip passes through the second cooling zone 8B and the temperature drop can be used, or an average cooling rate calculated from these values ​​can be used.

[0211] Furthermore, the control output values ​​of the heating devices in the heating zone 6 and the cooling devices in the cooling zone 8 may also be used as operating parameters. This is because these operating parameters are used to control the temperature history of the steel strip during the annealing process. Furthermore, the line speed of the steel strip in the soaking zone 7, the average cooling rate in the cooling zone 8, and the injection pressure of cooling devices such as gas jets may also be used. This is because these factors also affect the thermal history of the steel strip.

[0212] As operating parameters for the reheating zone 9, the temperature rise and transit time measured by radiation thermometers located on the inlet and outlet sides of the induction heating device installed in the reheating zone 9 can be used, or an average temperature rise rate calculated from these values ​​can be used. As operating parameters for the over-aging zone 10, the average temperature of the steel strip in the over-aging zone 10 and the time it takes to pass through the over-aging zone 10 can be used. As operating parameters for the final cooling zone 11, the time it takes to pass through the final cooling zone 11 and the temperature drop can be used, or an average cooling rate calculated from these values ​​can be used. Furthermore, the control output value of the heating device in the reheating zone 9 and the control output value of the cooling device in the final cooling zone 11 can also be used as operating parameters. This is because these operating parameters are used to control the temperature history of the steel strip during the reheating process.

[0213] <Operational parameters related to atmosphere gas>

[0214] As the operating parameters in the continuous annealing equipment according to the present embodiment, in addition to the operating parameters related to the thermal history of the steel strip as described above, operating parameters related to the atmospheric gas in the continuous annealing equipment through which the steel strip passes may be selected.

[0215] As operating parameters in the annealing section, the gas composition of the atmosphere in each of the heating zone 6, soaking zone 7, and cooling zone 8 can be used. The hydrogen concentration is particularly preferred because it affects the amount of hydrogen that enters the steel strip during the annealing process.

[0216] As operating parameters in the reheating section, the gas composition of the atmosphere in each of the reheating zone 9, the overaging zone 10, and the final cooling zone 11 can be used. The hydrogen concentration is particularly preferred because it affects the ease with which hydrogen in the steel escapes during the reheating process.

[0217] Furthermore, the concentrations of the gas components within the annealing and reheating sections change due to the H2, N2, and H2O supplied to them, causing the dew point within them to change, that is, the H2O concentration to change. This affects the H2 concentration in the atmosphere, so the dew point of the annealing and reheating sections can also be used as an operating parameter in the continuous annealing equipment.

[0218] <Selection of operating parameters for continuous annealing equipment>

[0219] In the present embodiment, one or more operating parameters selected from the above-mentioned operating parameters of the continuous annealing equipment are used as inputs to the steel hydrogen content prediction model of the steel strip.

[0220] The reason for using operating parameters related to the thermal history of the steel strip in the annealing and reheating sections is that the diffusion rate of hydrogen in steel is affected by the temperature of the steel strip. Furthermore, a high hydrogen diffusion rate makes it easier for hydrogen to penetrate the surface of the steel strip.

[0221] The time (residence time) that the steel strip spends in each zone during the annealing and reheating sections is used as a second operating parameter because it affects the amount of hydrogen that enters or exits the steel and also because the diffusion time of these hydrogen amounts throughout the steel changes.

[0222] At this time, the amount of hydrogen in the steel increases in the annealing section, where the steel strip is maintained at a high temperature, and decreases in the reheating section, where the temperature is maintained at a lower level. Therefore, it is preferable to use a combination of one or more parameters selected from the annealing section operating parameters and one or more parameters selected from the reheating section operating parameters as operating parameters related to the thermal history. This is because the amount of hydrogen in the steel strip, as measured at the delivery side of the continuous annealing equipment, is significantly affected by the balance between hydrogen ingress and egress into the steel.

[0223] On the other hand, as mentioned above, operating parameters related to the atmosphere in the annealing and reheating zones are used because hydrogen intrusion and release into steel are affected by the composition of the atmospheric gas. Therefore, in this embodiment, it is preferable to use a combination of one or more parameters selected from the operating parameters related to the thermal history and parameters selected from the operating parameters related to the atmospheric gas. This is because both parameters affect the intrusion and release behavior of hydrogen into steel.

[0224] Regarding the operating parameters of the continuous annealing equipment in this embodiment, a set of operating parameters is acquired for each steel strip as learning data, as described above. This is because the information related to the hydrogen content in steel, which serves as the output of the hydrogen content prediction model, is generally collected on a per-strip basis. In this case, while the thermal history data and atmospheric gas data are collected continuously along the length of the steel strip, representative values ​​are calculated for each steel strip and used as operating parameters for the continuous annealing equipment. For example, data collected at a location a predetermined distance from the leading or trailing end of the steel strip can be used, or data obtained by averaging the values ​​measured along the length can be used.

[0225] <Phase transition rate information>

[0226] In this embodiment, a phase transformation rate meter 20 for measuring the austenite phase ratio is installed in at least one of the annealing process or the reheating process of the continuous annealing equipment, and the measurement results of the phase transformation rate meter 20 are formed into phase transformation rate information, which is used as one of the learning data for the above-mentioned hydrogen content prediction model in steel.

[0227] The data obtained by the phase transformation rate meter 20 is continuous data obtained at each sampling period along the length of the steel strip as austenite phase ratio data. However, a representative value is calculated for a single strip and used as actual phase transformation rate information performance data. In this case, the phase transformation rate measurement results, which serve as the output of the hydrogen content in steel prediction model and are measured at a location approximately corresponding to the location where actual performance data related to the hydrogen content in the steel strip is acquired, are preferably used as actual phase transformation rate information performance data. In continuous annealing equipment, the phase transformation rate of the steel strip may fluctuate along its length. Since the phase transformation rate has a strong correlation with the hydrogen content in the steel strip, aligning the measured phase transformation rate values ​​with the locations where actual hydrogen content data is collected allows for more accurate prediction of the hydrogen content in steel.

[0228] Here, the ratio of the austenite phase (γ phase) in the steel strip becomes an important parameter for predicting the amount of hydrogen in the steel. Generally, the diffusion coefficient of hydrogen in the austenite phase is about one order of magnitude smaller than that in the ferrite phase (α phase). Therefore, in a zone maintained at a high temperature, such as the soaking zone of a continuous annealing equipment, where the γ phase is the main component, the intrusion of hydrogen from the surrounding atmosphere into the steel is slow, and hydrogen that temporarily intrudes into the steel is difficult to release to the surrounding area. On the other hand, in a zone with an internal structure containing a certain degree of ferrite phase (α phase), such as the over-aged zone 10, the intrusion of hydrogen from the surrounding atmosphere into the steel is promoted. However, even if hydrogen temporarily intrudes into the steel, it is easily released to the surrounding area.

[0229] In the continuous annealing equipment, the mechanical properties of the steel are controlled by utilizing the structural control of the phase transformation of the steel strip. As the steel strip passes through the annealing section (heating zone 6, soaking zone 7, cooling zone 8) and the reheating section (reheating zone 9, overaging zone 10, final cooling zone 11), the internal structure of the steel strip changes. Therefore, a phase transformation rate meter 20 is used to obtain information about the austenite phase (γ phase) of the steel strip, thereby improving the prediction accuracy of the hydrogen content in the steel strip.

[0230] Furthermore, the phase transformation behavior of the steel strip varies depending on the strength grade and component composition of the steel strip to be produced, and the history of its internal structural transformation also changes. Therefore, when attempting to predict the hydrogen content in different steel grades, it is particularly useful to use the phase transformation rate information from the phase transformation rate meter 20, which reflects information on the internal structure of the steel strip, in a steel hydrogen content prediction model.

[0231] On the other hand, in this embodiment, the reason for using the phase transformation rate information measured by the phase transformation rate meter 20 in addition to the operating parameters of the continuous annealing equipment is as follows. The operating parameters of the continuous annealing equipment affect the amount of hydrogen in the steel of the steel strip through the recovery, recrystallization, grain growth, precipitation, phase transformation and other processes in the internal structure of the steel strip. However, such changes in the internal structure are not only determined by the operating parameters of the continuous annealing equipment, but are also affected by the processing history in the previous processes, namely the hot rolling process and the cold rolling process. For example, the coiling temperature in the hot rolling process affects the size (distribution) and amount of precipitates as the internal structure of the hot-rolled steel plate, and affects the grain growth and phase transformation behavior in the heat treatment process. In addition, the reduction rate in the cold rolling process affects the recrystallization, grain growth and phase transformation behavior of the annealing process through the strain state accumulated in the internal structure of the cold-rolled steel plate. Therefore, the learning data for the hydrogen content prediction model in steel are only the operating parameters of the continuous annealing equipment. It is impossible to consider the impact of the operating parameters of the process before such annealing process on the hydrogen content in the steel after the steel strip is heat treated. Therefore, it is difficult to predict the hydrogen content in steel.

[0232] By using the phase transformation rate information measured by the phase transformation rate meter 20 during the heating or reheating process as learning data, the influence of operating parameters in the hot and cold rolling processes, the preceding processes of the annealing process, on the hydrogen content in the steel after heat treatment of the steel strip can be considered as indirect information during the continuous annealing process. This allows the prediction of the hydrogen content in steel to be realized as a steel hydrogen content prediction model.

[0233] In summary, in this embodiment, a phase transformation meter 20 for measuring the austenite phase ratio is set in at least one of the annealing process or the reheating process of the continuous annealing equipment, and the measurement results of the phase transformation meter 20 are formed into phase transformation rate information, which serves as one of the learning data for the above-mentioned hydrogen content prediction model in steel.

[0234] <Property parameters related to the composition of steel strip>

[0235] In this embodiment, the input data for the hydrogen content in steel prediction model preferably includes one or more parameters selected from steel strip property parameters related to the steel strip's chemical composition. This is because the phase transformation behavior and internal structure during the heat treatment process are affected by the steel strip's chemical composition. Furthermore, this allows the generation of a hydrogen content in steel prediction model that can predict the hydrogen content in steel strips having various chemical compositions, such as cold-rolled steel sheets produced in continuous annealing equipment, thereby expanding the scope of application of the hydrogen content in steel prediction model.

[0236] As property parameters related to the composition of the steel strip, the contents of C, Si, and Mn, which are chemical components contained in the steel strip, can be used. Other property parameters related to the composition of the steel strip can include the contents of Cu, Ni, Cr, Mo, Nb, Ti, V, B, and Zr. However, it is not necessary to use all of these components as property parameters related to the composition of the steel strip. It is sufficient to appropriately select a portion based on the type of steel strip being manufactured in the continuous annealing facility.

[0237] C is an element effective in increasing the strength of a steel sheet, and contributes to increasing the strength by forming martensite, which is one of the hard phases in the steel structure.

[0238] Si is an element that contributes primarily to higher strength through solid solution strengthening. Its decrease in ductility is relatively small compared to its increase in strength, contributing not only to strength but also to an improved balance between strength and ductility. On the other hand, Si tends to form Si-based oxides on the steel sheet surface, stabilizing austenite during annealing and contributing to the formation of retained austenite in the final product.

[0239] Mn is effective as an element that contributes to increasing strength through solid solution strengthening and martensite formation.

[0240] Nb, Ti, V, and Zr contribute to increasing the strength of the steel sheet by forming fine precipitates that form carbides or nitrides (carbonitrides may also form carbonits) with C or N.

[0241] Cu, Ni, Cr, Mo, and B are elements that contribute to increasing the strength by improving the hardenability and facilitating the formation of martensite.

[0242] Here, the distribution of these component compositions in the longitudinal direction of the steel strip is substantially constant, and one property parameter can be obtained as performance data for one steel strip.

[0243] Furthermore, in addition to using steel strip property parameters related to its composition, other properties related to the strip's dimensions, such as thickness, width, and length, can also be used as learning data for the hydrogen content prediction model of this embodiment. This is because these properties affect the thermal conductivity within the continuous annealing equipment. Therefore, even at the same furnace atmosphere temperature, variations in the steel strip temperature can affect the hydrogen content in the steel strip.

[0244] <Method for controlling hydrogen content in steel strip>

[0245] Figure 9 A method for controlling the amount of hydrogen in a steel strip using the above-mentioned method for predicting the amount of hydrogen in steel will be described.

[0246] The implementation of the method for controlling the amount of hydrogen in steel in this embodiment differs depending on the installation position of the phase transformation rate meter 20 installed in at least one of the annealing process or the reheating process of the continuous annealing equipment. Specifically, when a plurality of phase transformation rate meters 20 are installed as the phase transformation rate information used in the input of the prediction model of the amount of hydrogen in steel generated as described above, a band upstream of the phase transformation rate meter 20 installed on the most downstream side and a band downstream thereof are divided. The band from the feed side of the continuous annealing equipment to the above-mentioned phase transformation rate meter 20 is called the hydrogen content in steel identification band. In addition, the band downstream of the above-mentioned phase transformation rate meter 20 is called the hydrogen content in steel control band. And, at the moment when the front end portion of the steel strip, which is the object of the prediction of the amount of hydrogen in steel, reaches the position of the above-mentioned phase transformation rate meter 20 and obtains the phase transformation rate information of the steel strip, the process starts. Figure 9 The control flow shown.

[0247] At this point, for the steel strip to be controlled for hydrogen content, the continuous annealing equipment's operational performance data obtained in the continuous annealing equipment's hydrogen content identification zone and the phase transformation rate information measured by the phase transformation rate meter 20 serve as input data for the hydrogen content prediction model. The step of acquiring this input data is sometimes referred to as an input data acquisition step. In the input data acquisition step, actual operational performance data for the continuous annealing equipment in the hydrogen content control zone at that point or the set values ​​for the continuous annealing equipment's operating conditions may also be acquired as input data for the hydrogen content prediction model. Using this acquired data as input, the hydrogen content prediction model is used to predict the hydrogen content of the steel strip downstream of the reheating process.

[0248] On the other hand, in this embodiment, an upper limit value for the hydrogen content in the steel strip is also set in the host computer, and the predicted hydrogen content in the steel strip is compared with this upper limit value. For steel materials used in environments where hydrogen embrittlement cracking may become a practical problem, the upper limit value for the hydrogen content in the steel strip is preferably set to a value that allows for a certain margin relative to the target value for reducing the hydrogen content in the steel strip to a level that does not cause operational problems. For example, the upper limit value for the hydrogen content in the steel strip can be set to 0.30 ppm.

[0249] At this time, the operating condition setting unit of the continuous annealing equipment compares the upper limit of the hydrogen content in steel, which has been set in advance as described above, with the predicted result of the hydrogen content in steel. If the predicted hydrogen content in steel is below the upper limit, the operating conditions of the continuous annealing equipment are determined while maintaining the initial settings and transmitted to the control unit of the continuous annealing equipment. On the other hand, if the predicted hydrogen content in steel exceeds the upper limit, the operating conditions in the aforementioned hydrogen content control zone are reset.

[0250] Specifically, in a continuous annealing facility, if the phase transformation rate meter 20 (hereinafter referred to as the phase transformation rate meter 20 that provides the phase transformation rate information used as the input of the hydrogen content prediction model in steel) located at the outlet of the soaking zone 7 in the annealing process is located, the zone from the feed side of the continuous annealing facility to the outlet of the soaking zone 7 becomes the hydrogen content identification zone in steel, and the zone downstream of the outlet of the soaking zone 7 becomes the hydrogen content control zone in steel. At this time, when the leading end of the steel strip reaches the outlet of the soaking zone 7 and the phase transformation rate meter 20 obtains the phase transformation rate information, the process starts. Figure 9 The flow of controlling the amount of hydrogen in steel is shown. In this case, in the hydrogen content control zone, operating conditions that can be used to control the amount of hydrogen in steel can be reset, including the cooling conditions in the cooling zone 8 (the first cooling zone 8A and the second cooling zone 8B), the reheating conditions in the reheating zone 9, the holding temperature and holding time in the overaging zone 10, and the cooling rate in the final cooling zone 11. The reset operating conditions are not necessarily limited to those used as inputs to the hydrogen content prediction model.

[0251] On the other hand, when the phase transformation rate meter 20 on the most downstream side is set at the inlet or outlet of the reheating zone 9, since the hydrogen content control zone in the steel is limited to the zone after the over-aging zone 10 or the final cooling zone 11, the operating conditions reset in the continuous annealing equipment are limited to the holding time in the over-aging zone 10, the mixing ratio of the atmospheric gas components in the over-aging zone 10, the cooling rate in the final cooling zone 11, etc.

[0252] Therefore, the position of the phase transformation rate meter 20, located on the far downstream side and serving as an input to the hydrogen content in steel prediction model, can be appropriately determined by balancing the degree of freedom in resetting operating conditions with the prediction accuracy of the hydrogen content in steel prediction model. Specifically, while lengthening the hydrogen content in steel identification zone improves the prediction accuracy of the hydrogen content in steel, the degree of freedom in resetting operating conditions in the hydrogen content in steel control zone decreases. Conversely, shortening the hydrogen content in steel identification zone decreases the prediction accuracy of the hydrogen content in steel, but increases the degree of freedom in resetting operating conditions in the hydrogen content in steel control zone.

[0253] Here, the hydrogen in the steel strip having an internal structure mainly composed of γ phase is not easily released. If the ratio of α phase becomes larger, hydrogen is easily released. Therefore, it is preferred that the hydrogen content control zone in steel, which is used to effectively reduce the hydrogen content in steel, is set on the downstream side of the cooling zone 8 in the annealing section. As mentioned above, when multiple phase change rate meters 20 are set in the continuous annealing equipment, it is preferred to use the phase change rate meter 20 on the most downstream side as a reference to divide the hydrogen content identification zone in steel and the hydrogen content control zone in steel. However, the phase change rate meter 20 used to divide the hydrogen content identification zone in steel and the hydrogen content control zone in steel does not necessarily have to be the phase change rate meter 20 on the most downstream side. The hydrogen content identification zone in steel and the hydrogen content control zone in steel can also be divided based on any phase change rate meter selected from the multiple phase change rate meters 20.

[0254] <Estimation device for hydrogen content in steel>

[0255] The structure of the device for predicting the amount of hydrogen in steel is the same as that of the first embodiment (see Figure 5 ) However, the “continuous hot-dip coating equipment” in the description of the device for estimating the amount of hydrogen in steel according to the first embodiment is replaced by “continuous annealing equipment”.

[0256] (Example of the second embodiment)

[0257] Hereinafter, this embodiment will be described in detail using examples.

[0258] exist Figure 6 In the continuous annealing equipment shown in the figure, 200 coils of cold-rolled steel sheets (the upper limit of hydrogen content in steel is 0.30ppm) are manufactured. At this time, the performance data of the attribute information of the steel sheets loaded into the continuous annealing equipment and the operation performance data of the operation parameters in the continuous annealing equipment are used as input performance data, and the hydrogen content in the steel sheets on the delivery side of the continuous annealing equipment is used as output performance data to obtain a plurality of learning data. By machine learning using the obtained plurality of learning data, a plurality of learning data are obtained. Figure 8 The method shown generates a steel hydrogen content prediction model having information on the steel hydrogen content of the steel strip on the downstream side of the reheating process as output data.

[0259] When generating the hydrogen content prediction model in steel, the C, Si, and Mn contents of the steel strip were used as inputs to the property parameters of the steel strip related to the composition of the steel strip. In addition, the steel plate temperature in the soaking zone 7 and the conveying speed of the steel strip tip when passing through the soaking zone 7 were used as inputs as the actual operating performance data of the continuous annealing equipment. Figure 6 Phase transformation rate meters 20 are installed in-line at two locations within the continuous annealing equipment, at the exit of the soaking zone 7 and the entrance of the overaging zone 10. Actual performance data on phase transformation rate information measured based on these phase transformation rates is used as input performance data. Furthermore, in this embodiment, the set values ​​for the steel strip thickness and width are used as additional inputs to generate a hydrogen content prediction model.

[0260] Here, the hydrogen content in the steel strip acquired as learning data is obtained by a temperature-increasing hydrogen analysis method using gas chromatography using a test piece collected after the steel strip passes through the continuous annealing equipment.

[0261] The hydrogen content prediction model in steel generated in this way is applied to Figure 9 The hydrogen content prediction unit in the hydrogen content control in steel shown produced 100 coils of cold-rolled steel sheets. That is, the hydrogen content prediction method for steel strip using the hydrogen content prediction model is applied to the hydrogen content control method and manufacturing method of steel strip.

[0262] At this time, the aforementioned steel hydrogen content prediction model was used to predict the hydrogen content of the steel plate at the discharge side of the continuous annealing equipment. The operating parameters of the continuous annealing equipment were reset so that the predicted hydrogen content in the steel fell within a pre-set upper limit (in this case, 0.30 ppm). At this time, the phase transformation rate meter 20 on the most downstream side was installed at the entrance of the over-aging zone 10. Therefore, the area from the discharge side of the continuous annealing equipment to the entrance of the over-aging zone 10 became the steel hydrogen content assessment zone, and the area downstream of the entrance of the over-aging zone 10 became the steel hydrogen content control zone. Figure 9 The process shown begins after the leading end of the steel strip reaches the entrance of the overaging zone 10. In the hydrogen content control zone, the operating conditions used to control the hydrogen content in the steel were reset: the holding temperature and holding time in the overaging zone 10, and the cooling rate in the cooling zone 8. The hydrogen content in the steel strips, obtained through hydrogen content measurement tests, was then collected. The results showed that 98% of the steel strips fell below the upper limit of hydrogen content (0.30 ppm).

[0263] On the other hand, as a comparative example, a continuous annealing facility without the aforementioned steel hydrogen content prediction unit was operated without resetting the operating conditions of the continuous annealing facility. As a result, 75% of the steel strips fell below the upper limit of the steel hydrogen content.

[0264] As described above, by applying the method for predicting the amount of hydrogen in steel according to the present disclosure, direct prediction is performed using the aforementioned machine learning model, thereby enabling the amount of hydrogen in steel strip to be predicted with high accuracy and effectively reduced.

[0265] Description of Reference Numerals

[0266] 1… Uncoiler; 2… Welding machine; 3… Electrolytic cleaning device; 4… Feed-side looper roller; 5… Preheating zone; 6… Heating zone; 7… Soaking zone; 8… Cooling zone; 8A… First cooling zone; 8B… Second cooling zone; 9… Reheating zone; 10… Overaging zone; 11… Final cooling zone; 11A… First final cooling zone; 11B… Second final cooling zone; 12… Feed-side looper roller; 13… Temper rolling equipment; 14… Inspection equipment; 15… Tension coiler; 16… Galvanizing tank; 17… Alloying strip; 18… Insulation zone; 19… Nose; 20… Phase transformation rate meter; 21… Wiping device; 22… Guide roller.

Claims

1. A method for predicting the amount of hydrogen in steel strip, wherein the steel strip is located downstream of the reheating step in a continuous hot-dip coating facility that performs a manufacturing process including an annealing step, a coating step, and a reheating step. The method for predicting the amount of hydrogen in steel strip is characterized by comprising: an input data acquisition step of acquiring, as input data, one or more parameters selected from operating parameters of the continuous hot-dip coating equipment related to the atmosphere gas or the thermal history of the steel strip, and information on the austenite phase ratio, i.e., the phase transformation rate, of the steel strip measured in at least one of the annealing step and the reheating step; and The hydrogen content in the steel strip downstream of the reheating process is predicted using a steel hydrogen content prediction model learned by machine learning. The steel hydrogen content prediction model outputs information related to the hydrogen content in the steel strip downstream of the reheating process.

2. The method for predicting hydrogen content in steel strip according to claim 1, characterized in that: The input data acquisition step further acquires one or more parameters selected from attribute parameters of the steel strip related to the chemical composition of the steel strip as the input data.

3. A method for controlling hydrogen content in steel strip, characterized in that: The method for predicting the amount of hydrogen in steel of a steel strip according to claim 1 or 2 is used to predict the amount of hydrogen in steel of the steel strip on the downstream side of the reheating process. When the predicted amount of hydrogen in steel exceeds a preset upper limit value, one or more operating parameters selected from the operating parameters of the continuous hot-dip coating equipment related to the atmosphere gas or the thermal history of the steel strip are reset so that the amount of hydrogen in steel becomes below the upper limit value.

4. A method for producing a steel strip in a continuous hot-dip coating facility that performs a production process including an annealing step, a coating step, and a reheating step of the steel strip, The method for manufacturing the steel strip is characterized by comprising: acquiring, as input data, one or more parameters selected from operating parameters of the continuous hot-dip coating equipment related to the atmosphere gas or the thermal history of the steel strip, and information on the austenite phase ratio, i.e., the phase transformation rate, of the steel strip measured in at least one of the annealing step and the reheating step; predicting the amount of hydrogen in steel of the steel strip downstream of the reheating process using a steel-hydrogen amount prediction model learned by machine learning, the steel-hydrogen amount prediction model outputting information related to the amount of hydrogen in steel of the steel strip downstream of the reheating process as output data; and When the predicted hydrogen content in the steel exceeds a pre-set upper limit value, one or more operating parameters selected from the operating parameters of the continuous hot-dip coating equipment related to the atmosphere gas or the thermal history of the steel strip are reset so that the hydrogen content in the steel becomes below the upper limit value.

5. A method for generating a steel strip hydrogen content prediction model, the steel strip hydrogen content prediction model being used to predict the hydrogen content in the steel strip, the steel strip being a steel strip downstream of the reheating step in a continuous hot-dip coating facility that performs a manufacturing process including an annealing step, a coating step, and a reheating step. The method for generating a prediction model for hydrogen content in steel strip is characterized by comprising: acquiring, as input performance data, at least one piece of operating performance data selected from at least one piece of operating performance data related to the atmosphere gas or the thermal history of the steel strip of the continuous hot-dip coating equipment and performance data of information on the austenite phase ratio, i.e., the transformation rate, of the steel strip measured in at least one of the annealing step and the reheating step; acquiring a plurality of learning data using information related to the amount of hydrogen in the steel strip on the downstream side of the reheating step based on the input performance data as output performance data; as well as A prediction model for the amount of hydrogen in the steel strip is generated by machine learning using the acquired plurality of learning data.

6. The method for generating a prediction model for hydrogen content in steel strip according to claim 5, characterized in that: As the machine learning, an algorithm selected from neural network, decision tree learning, random forest, and support vector regression is used.

7. A device for predicting the amount of hydrogen in a steel strip, for predicting the amount of hydrogen in the steel strip, wherein the steel strip is a steel strip downstream of the reheating step in a continuous hot-dip coating facility that performs a manufacturing process including an annealing step, a coating step, and a reheating step. The device for predicting hydrogen content in steel strip is characterized by comprising: an acquisition unit that acquires one or more parameters selected from operating parameters of the continuous hot-dip coating equipment related to the atmosphere gas or the thermal history of the steel strip and information on the austenite phase ratio, i.e., phase transformation rate, of the steel strip measured in at least one of the annealing step and the reheating step; and The prediction unit predicts the amount of hydrogen in the steel strip downstream of the reheating process using a steel hydrogen amount prediction model learned through machine learning, wherein the steel hydrogen amount prediction model outputs information related to the steel hydrogen amount in the steel strip downstream of the reheating process.

8. The device for predicting hydrogen content in steel strip according to claim 7, characterized in that: The invention further includes a terminal device having: an input unit for acquiring input information based on a user's operation; and a display unit for displaying the hydrogen content in the steel predicted by the prediction unit. The acquisition unit updates part or all of the operating parameters of the continuous hot dip coating equipment according to the input information acquired from the input unit. The display unit displays the hydrogen content in the steel predicted by the prediction unit using the updated operating parameters.

9. A method for predicting the amount of hydrogen in steel strip, wherein the steel strip is a steel strip downstream of the reheating step in a continuous annealing facility that performs a manufacturing process including an annealing step and a reheating step of the steel strip, The method for predicting the amount of hydrogen in steel strip is characterized by comprising: an input data acquisition step of acquiring, as input data, one or more parameters selected from operating parameters of the continuous annealing equipment related to the atmosphere gas or the thermal history of the steel strip, and information on the austenite phase ratio, i.e., the phase transformation rate, of the steel strip measured in at least one of the annealing step and the reheating step; and The hydrogen content in the steel strip downstream of the reheating process is predicted using a steel hydrogen content prediction model learned by machine learning. The steel hydrogen content prediction model outputs information related to the hydrogen content in the steel strip downstream of the reheating process.

10. The method for predicting hydrogen content in steel strip according to claim 9, characterized in that: The input data acquisition step further acquires one or more parameters selected from attribute parameters of the steel strip related to the chemical composition of the steel strip as the input data.

11. A method for controlling hydrogen content in steel strip, characterized in that: The method for predicting the amount of hydrogen in steel of a steel strip according to claim 9 or 10 is used to predict the amount of hydrogen in steel of the steel strip on the downstream side of the reheating process. When the predicted amount of hydrogen in steel exceeds a preset upper limit value, one or more operating parameters selected from the operating parameters of the continuous annealing equipment related to the atmosphere gas or the thermal history of the steel strip are reset so that the amount of hydrogen in steel becomes below the upper limit value.

12. A method for manufacturing a steel strip in a continuous annealing facility that performs a manufacturing process including an annealing process and a reheating process of the steel strip, The method for manufacturing the steel strip is characterized by comprising: acquiring, as input data, one or more parameters selected from operating parameters of the continuous annealing equipment related to the atmosphere gas or the thermal history of the steel strip, and information on the austenite phase ratio, i.e., the phase transformation rate, of the steel strip measured in at least one of the annealing step and the reheating step; predicting the amount of hydrogen in steel of the steel strip downstream of the reheating process using a steel-hydrogen amount prediction model learned by machine learning, the steel-hydrogen amount prediction model outputting information related to the amount of hydrogen in steel of the steel strip downstream of the reheating process as output data; and When the predicted hydrogen content in the steel exceeds a preset upper limit, one or more operating parameters selected from the operating parameters of the continuous annealing equipment related to the atmosphere gas or the thermal history of the steel strip are reset so that the hydrogen content in the steel becomes below the upper limit.

13. A method for generating a steel strip hydrogen content prediction model, the steel strip hydrogen content prediction model being used to predict the hydrogen content of a steel strip downstream of a reheating step in a continuous annealing facility that performs a manufacturing process including an annealing step and a reheating step. The method for generating a prediction model for hydrogen content in steel strip is characterized by comprising: acquiring, as input performance data, at least one piece of operating performance data selected from at least one piece of operating performance data related to the atmosphere gas or the thermal history of the steel strip of the continuous annealing equipment and performance data of information on the austenite phase ratio, i.e., the transformation rate, of the steel strip measured in at least one of the annealing step and the reheating step; acquiring a plurality of learning data using information related to the amount of hydrogen in the steel strip on the downstream side of the reheating step based on the input performance data as output performance data; as well as A prediction model for the amount of hydrogen in the steel strip is generated by machine learning using the acquired plurality of learning data.

14. The method for generating a prediction model for hydrogen content in steel strip according to claim 13, wherein: As the machine learning, an algorithm selected from neural network, decision tree learning, random forest, and support vector regression is used.

15. A device for predicting the amount of hydrogen in a steel strip, for predicting the amount of hydrogen in the steel strip, wherein the steel strip is a steel strip downstream of the reheating step in a continuous annealing facility that performs a manufacturing process including an annealing step and a reheating step of the steel strip. The device for predicting hydrogen content in steel strip is characterized by comprising: an acquisition unit that acquires one or more parameters selected from operating parameters of the continuous annealing equipment related to the atmosphere gas or the thermal history of the steel strip and information on the austenite phase ratio, i.e., phase transformation rate, of the steel strip measured in at least one of the annealing step and the reheating step; and The prediction unit predicts the amount of hydrogen in the steel strip downstream of the reheating process using a steel hydrogen amount prediction model learned through machine learning, wherein the steel hydrogen amount prediction model outputs information related to the steel hydrogen amount in the steel strip downstream of the reheating process.

16. The device for predicting hydrogen content in steel strip according to claim 15, characterized in that: The invention further includes a terminal device having: an input unit for acquiring input information based on a user's operation; and a display unit for displaying the hydrogen content in the steel predicted by the prediction unit. The acquisition unit updates part or all of the operating parameters of the continuous annealing equipment based on the input information acquired from the input unit. The display unit displays the hydrogen content in the steel predicted by the prediction unit using the updated operating parameters.

Images