WO2021250957A1 - 熱処理レールの硬度予測方法、熱処理方法、硬度予測装置、熱処理装置、製造方法、製造設備、並びに、硬度予測モデルの生成方法 - Google Patents
熱処理レールの硬度予測方法、熱処理方法、硬度予測装置、熱処理装置、製造方法、製造設備、並びに、硬度予測モデルの生成方法 Download PDFInfo
- Publication number
- WO2021250957A1 WO2021250957A1 PCT/JP2021/009060 JP2021009060W WO2021250957A1 WO 2021250957 A1 WO2021250957 A1 WO 2021250957A1 JP 2021009060 W JP2021009060 W JP 2021009060W WO 2021250957 A1 WO2021250957 A1 WO 2021250957A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- rail
- hardness
- cooling
- heat treatment
- heat
- Prior art date
Links
- 238000000034 method Methods 0.000 title claims description 98
- 238000004519 manufacturing process Methods 0.000 title claims description 26
- 238000007669 thermal treatment Methods 0.000 title abstract 3
- 238000001816 cooling Methods 0.000 claims abstract description 513
- 238000009826 distribution Methods 0.000 claims abstract description 59
- 229910001566 austenite Inorganic materials 0.000 claims abstract description 36
- 238000010801 machine learning Methods 0.000 claims abstract description 18
- 238000004364 calculation method Methods 0.000 claims description 153
- 238000010438 heat treatment Methods 0.000 claims description 116
- 238000002347 injection Methods 0.000 claims description 61
- 239000007924 injection Substances 0.000 claims description 61
- 230000009466 transformation Effects 0.000 claims description 48
- 238000012546 transfer Methods 0.000 claims description 46
- 230000008569 process Effects 0.000 claims description 18
- 239000002826 coolant Substances 0.000 claims description 16
- 238000012549 training Methods 0.000 claims description 12
- 238000007637 random forest analysis Methods 0.000 claims description 3
- 238000003062 neural network model Methods 0.000 claims description 2
- 238000005096 rolling process Methods 0.000 description 19
- 229910000831 Steel Inorganic materials 0.000 description 15
- 238000004458 analytical method Methods 0.000 description 15
- 230000008859 change Effects 0.000 description 15
- 239000010959 steel Substances 0.000 description 15
- 229910001562 pearlite Inorganic materials 0.000 description 14
- 239000000463 material Substances 0.000 description 12
- 230000020169 heat generation Effects 0.000 description 11
- 239000000203 mixture Substances 0.000 description 11
- 229910001563 bainite Inorganic materials 0.000 description 8
- 230000006399 behavior Effects 0.000 description 7
- 239000002344 surface layer Substances 0.000 description 7
- 238000005520 cutting process Methods 0.000 description 6
- 230000007423 decrease Effects 0.000 description 6
- 238000005259 measurement Methods 0.000 description 6
- 239000000126 substance Substances 0.000 description 6
- 238000010586 diagram Methods 0.000 description 5
- 238000005098 hot rolling Methods 0.000 description 5
- 229910000734 martensite Inorganic materials 0.000 description 5
- XEEYBQQBJWHFJM-UHFFFAOYSA-N Iron Chemical compound [Fe] XEEYBQQBJWHFJM-UHFFFAOYSA-N 0.000 description 4
- 230000002159 abnormal effect Effects 0.000 description 4
- 230000000052 comparative effect Effects 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 description 3
- 238000009529 body temperature measurement Methods 0.000 description 3
- 229910052799 carbon Inorganic materials 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000002474 experimental method Methods 0.000 description 3
- 230000007246 mechanism Effects 0.000 description 3
- 239000002245 particle Substances 0.000 description 3
- 238000010583 slow cooling Methods 0.000 description 3
- 238000004781 supercooling Methods 0.000 description 3
- 230000015572 biosynthetic process Effects 0.000 description 2
- 229910001567 cementite Inorganic materials 0.000 description 2
- 238000013135 deep learning Methods 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 229910052742 iron Inorganic materials 0.000 description 2
- KSOKAHYVTMZFBJ-UHFFFAOYSA-N iron;methane Chemical compound C.[Fe].[Fe].[Fe] KSOKAHYVTMZFBJ-UHFFFAOYSA-N 0.000 description 2
- 230000008520 organization Effects 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 2
- 238000007546 Brinell hardness test Methods 0.000 description 1
- 229910001035 Soft ferrite Inorganic materials 0.000 description 1
- 210000001015 abdomen Anatomy 0.000 description 1
- 230000003187 abdominal effect Effects 0.000 description 1
- 238000005299 abrasion Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000013145 classification model Methods 0.000 description 1
- 238000009749 continuous casting Methods 0.000 description 1
- 239000000498 cooling water Substances 0.000 description 1
- 239000013078 crystal Substances 0.000 description 1
- 238000003066 decision tree Methods 0.000 description 1
- 238000013136 deep learning model Methods 0.000 description 1
- 238000006073 displacement reaction Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000005206 flow analysis Methods 0.000 description 1
- 239000012530 fluid Substances 0.000 description 1
- 238000007542 hardness measurement Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 239000010410 layer Substances 0.000 description 1
- 238000007477 logistic regression Methods 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 239000003595 mist Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000000704 physical effect Effects 0.000 description 1
- 230000000541 pulsatile effect Effects 0.000 description 1
- 239000003507 refrigerant Substances 0.000 description 1
- 238000003303 reheating Methods 0.000 description 1
- 230000000452 restraining effect Effects 0.000 description 1
- -1 rolling conditions Inorganic materials 0.000 description 1
- 239000000243 solution Substances 0.000 description 1
- 238000003860 storage Methods 0.000 description 1
- 238000005728 strengthening Methods 0.000 description 1
- 230000001629 suppression Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000000844 transformation Methods 0.000 description 1
- 230000001131 transforming effect Effects 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
- 238000011179 visual inspection Methods 0.000 description 1
- 229910000859 α-Fe Inorganic materials 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N3/00—Investigating strength properties of solid materials by application of mechanical stress
- G01N3/40—Investigating hardness or rebound hardness
- G01N3/54—Performing tests at high or low temperatures
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N3/00—Investigating strength properties of solid materials by application of mechanical stress
- G01N3/40—Investigating hardness or rebound hardness
-
- C—CHEMISTRY; METALLURGY
- C21—METALLURGY OF IRON
- C21D—MODIFYING THE PHYSICAL STRUCTURE OF FERROUS METALS; GENERAL DEVICES FOR HEAT TREATMENT OF FERROUS OR NON-FERROUS METALS OR ALLOYS; MAKING METAL MALLEABLE, e.g. BY DECARBURISATION OR TEMPERING
- C21D1/00—General methods or devices for heat treatment, e.g. annealing, hardening, quenching or tempering
- C21D1/18—Hardening; Quenching with or without subsequent tempering
-
- C—CHEMISTRY; METALLURGY
- C21—METALLURGY OF IRON
- C21D—MODIFYING THE PHYSICAL STRUCTURE OF FERROUS METALS; GENERAL DEVICES FOR HEAT TREATMENT OF FERROUS OR NON-FERROUS METALS OR ALLOYS; MAKING METAL MALLEABLE, e.g. BY DECARBURISATION OR TEMPERING
- C21D1/00—General methods or devices for heat treatment, e.g. annealing, hardening, quenching or tempering
- C21D1/62—Quenching devices
- C21D1/667—Quenching devices for spray quenching
-
- C—CHEMISTRY; METALLURGY
- C21—METALLURGY OF IRON
- C21D—MODIFYING THE PHYSICAL STRUCTURE OF FERROUS METALS; GENERAL DEVICES FOR HEAT TREATMENT OF FERROUS OR NON-FERROUS METALS OR ALLOYS; MAKING METAL MALLEABLE, e.g. BY DECARBURISATION OR TEMPERING
- C21D11/00—Process control or regulation for heat treatments
- C21D11/005—Process control or regulation for heat treatments for cooling
-
- C—CHEMISTRY; METALLURGY
- C21—METALLURGY OF IRON
- C21D—MODIFYING THE PHYSICAL STRUCTURE OF FERROUS METALS; GENERAL DEVICES FOR HEAT TREATMENT OF FERROUS OR NON-FERROUS METALS OR ALLOYS; MAKING METAL MALLEABLE, e.g. BY DECARBURISATION OR TEMPERING
- C21D9/00—Heat treatment, e.g. annealing, hardening, quenching or tempering, adapted for particular articles; Furnaces therefor
- C21D9/04—Heat treatment, e.g. annealing, hardening, quenching or tempering, adapted for particular articles; Furnaces therefor for rails
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N25/00—Investigating or analyzing materials by the use of thermal means
- G01N25/18—Investigating or analyzing materials by the use of thermal means by investigating thermal conductivity
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- C—CHEMISTRY; METALLURGY
- C21—METALLURGY OF IRON
- C21D—MODIFYING THE PHYSICAL STRUCTURE OF FERROUS METALS; GENERAL DEVICES FOR HEAT TREATMENT OF FERROUS OR NON-FERROUS METALS OR ALLOYS; MAKING METAL MALLEABLE, e.g. BY DECARBURISATION OR TEMPERING
- C21D1/00—General methods or devices for heat treatment, e.g. annealing, hardening, quenching or tempering
- C21D1/56—General methods or devices for heat treatment, e.g. annealing, hardening, quenching or tempering characterised by the quenching agents
- C21D1/613—Gases; Liquefied or solidified normally gaseous material
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N2203/00—Investigating strength properties of solid materials by application of mechanical stress
- G01N2203/0058—Kind of property studied
- G01N2203/0076—Hardness, compressibility or resistance to crushing
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N2203/00—Investigating strength properties of solid materials by application of mechanical stress
- G01N2203/0098—Tests specified by its name, e.g. Charpy, Brinnel, Mullen
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N2203/00—Investigating strength properties of solid materials by application of mechanical stress
- G01N2203/02—Details not specific for a particular testing method
- G01N2203/0202—Control of the test
- G01N2203/0212—Theories, calculations
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N2203/00—Investigating strength properties of solid materials by application of mechanical stress
- G01N2203/02—Details not specific for a particular testing method
- G01N2203/0202—Control of the test
- G01N2203/0212—Theories, calculations
- G01N2203/0216—Finite elements
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N2203/00—Investigating strength properties of solid materials by application of mechanical stress
- G01N2203/02—Details not specific for a particular testing method
- G01N2203/022—Environment of the test
- G01N2203/0222—Temperature
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N3/00—Investigating strength properties of solid materials by application of mechanical stress
- G01N3/40—Investigating hardness or rebound hardness
- G01N3/42—Investigating hardness or rebound hardness by performing impressions under a steady load by indentors, e.g. sphere, pyramid
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
- G06N20/10—Machine learning using kernel methods, e.g. support vector machines [SVM]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
- G06N20/20—Ensemble learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/09—Supervised learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/01—Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P10/00—Technologies related to metal processing
- Y02P10/25—Process efficiency
Definitions
- the present invention is a technique for manufacturing a heat treatment rail having a heat treatment step of performing forced cooling on a rail having a high temperature higher than the austenite region temperature.
- INDUSTRIAL APPLICABILITY The present invention is particularly suitable for manufacturing a heat-treated rail for transportation railways, in which a rail heated to a temperature above the austenite region is forcibly cooled to obtain a rail having at least a rail head having excellent hardness uniformity. be.
- forced cooling may be performed on rails manufactured by hot rolling for the purpose of improving quality such as hardness and toughness.
- This forced cooling (heat treatment step) is performed, for example, on a rail immediately after rolling is completed at a temperature in the austenite region or higher, or a rail that is reheated after rolling and allowing to cool to a temperature equal to or higher than the austenite region temperature. That is, forced cooling is performed on the rails above the austenite temperature range.
- a rail manufactured through a heat treatment step is also referred to as a heat treatment rail.
- the transportation railroad used at the natural resource mining site has a larger loading capacity of freight cars than the general passenger railroad.
- the rails are heavily worn and the rails need to be replaced frequently.
- rail replacement not only increases work costs and replacement cost, but also reduces the line utilization rate. Therefore, there is a demand to reduce the frequency of rail replacement. In other words, transportation railroads are required to use rails with higher wear resistance.
- the hardness distribution in the region inside the cross section from the rail surface to the predetermined depth (hereinafter, also simply referred to as “inside”) is higher than the predetermined hardness value. ..
- the crystal structure in the region is a pearlite structure. The reason is that the bainite structure has low wear resistance even if it has the same hardness as the pearlite structure, and the martensite structure has low toughness.
- the distance between the ferrite and cementite layers (lamellar) that make up the structure fine is effective to make the distance between the ferrite and cementite layers (lamellar) that make up the structure fine. Then, in order to obtain a fine lamellar, it is necessary to proceed with transformation in a supercooled state in which a rail above the austenite region temperature is cooled at a high cooling rate (cold rate) to a temperature sufficiently lower than the equilibrium transformation temperature. ..
- the cooling speed is excessive, it may be transformed into a bainite structure or a martensite structure, and the characteristics may be deteriorated.
- the rail is cooled mainly on the surface of the rail head, which is the most important in terms of quality.
- the transformation start time also differs between the surface and the inside, so it is necessary to control the structure inside the rail by controlling the cooling capacity according to the time difference.
- Patent Document 1 describes a first forced cooling that performs forced cooling from a temperature range of 750 ° C. or higher to 600 to 450 ° C. at a cooling rate of 4 to 15 ° C./sec, and then temporarily stops the forced cooling. A method of performing forced cooling again after terminating the pearlite transformation is disclosed.
- Patent Document 2 discloses a method of changing the conditions of forced cooling while determining the start timing and end timing of transformation heat generation from the start of cooling based on the temperature measurement result of the rail surface.
- Patent Document 3 a steel piece used as a rail material is used as a relational expression of the hardness at a representative point inside the rail set in advance, the carbon equivalent, the injection flow rate of the cooling medium, the injection pressure, and the injection distance.
- a method of setting the injection distance between the cooling nozzle and the rail head based on the carbon equivalent of carbon content, and setting the cooling time from the surface temperature of the top of the rail (surface temperature before the start of cooling) measured on the inlet side of the cooling equipment. is disclosed.
- Patent Document 4 has a numerical, mechanical, and metallurgical embedded model as a process model in the control device, and predicts the temperature history, microstructure change, and mechanical properties inside the rail. , A method of setting cooling conditions for each cooling zone based on the prediction result is disclosed.
- Patent Document 1 defines the start and end of the first forced cooling and the start and end of the second forced cooling as the forced cooling conditions of the heated rail.
- the cooling conditions are set in advance by the method described in Patent Document 1 if the composition of the steel pieces of the rail material varies or the cooling start temperature varies, the internal hardness of the rail after the heat treatment varies. There is a problem that
- the method described in Patent Document 2 is a method capable of considering the influence of fluctuation factors such as material variation and cooling start temperature in that the cooling conditions are changed based on the temperature measurement result of the rail surface during forced cooling.
- the cooling conditions are changed only based on the surface temperature of the rail head, and the cooling conditions are not necessarily changed to reflect the temperature change and the structure change inside the rail.
- Patent Document 4 inputs transformation prediction online by inputting the chemical composition of rail steel, rolling conditions, austenite particle size before cooling, expected transformation behavior, geometric shape of rail cross section, temperature distribution, and target mechanical properties. It is described that the final mechanical characteristics are predicted by performing heat transfer analysis including, and the cooling conditions are reviewed as necessary.
- the present invention has been made in view of the above points, and provides a technique for controlling a desired structure from the rail surface to the inside to enable heat treatment of a rail having a stable hardness distribution. With the goal.
- one aspect of the present invention is a rail hardness prediction method for predicting the hardness of the rail after a heat treatment step in which a rail having a temperature equal to or higher than the austenite region temperature is forcibly cooled by a cooling facility.
- a cooling condition data set that has at least the surface temperature of the rail before the start of cooling and the operating conditions of the above cooling equipment for forced cooling as input data
- the hardness of at least the inside of the rail head of the rail after forced cooling is determined.
- the internal hardness calculation model which is a physical model for calculation as output data
- a plurality of sets of training data consisting of the above cooling condition data set and the output data of the above hardness are acquired, and the acquired multiple sets of data are acquired.
- a hardness prediction model is generated in advance using the cooling condition data set as at least input data and information on the hardness inside the rail after forced cooling as output data, and using the hardness prediction model.
- the gist is to predict the hardness of the rail after the heat treatment step based on the information on the hardness inside the rail for a set of cooling condition data sets set as the cooling conditions of the heat treatment step.
- one aspect of the present invention is a heat treatment method for a heat treatment rail having a heat treatment step of forcibly cooling a rail having a temperature equal to or higher than the austenite region temperature with a cooling facility, and measures the surface temperature of the rail before the start of cooling.
- the hardness inside the rail was predicted and predicted by the heat treatment rail hardness prediction method according to one aspect of the present invention, using the measured surface temperature of the rail.
- the gist is to reset the operating conditions of the cooling equipment so that the predicted hardness inside the rail falls within the target hardness range.
- the hardness of the rail after the rail having a temperature equal to or higher than the austenite region temperature is forcibly cooled by the cooling equipment is forced to be the surface temperature of the rail before the start of cooling in the cooling equipment. It is a method of generating a hardness prediction model for obtaining from a cooling condition data set having at least the operating conditions of the cooling equipment for cooling, and at least the rail after forced cooling using the cooling condition data set as input data.
- the internal hardness calculation model which is a physical model for calculating the internal hardness of the rail head as output data
- a plurality of sets of training data consisting of the above cooling condition data set and the output data of the above hardness are acquired.
- a hardness prediction model is generated in advance using the cooling condition data set as at least input data and information on the hardness inside the rail after forced cooling as output data.
- the gist is that.
- one aspect of the present invention is a method for manufacturing a heat-treated rail, which has a heat-treating method for the heat-treated rail according to the first aspect of the present invention.
- one aspect of the present invention is a rail hardness predicting device for predicting the hardness of the rail after a heat treatment step of forcibly cooling the rail having a temperature equal to or higher than the austenite region temperature with a cooling facility, and is a rail hardness predicting device before the start of cooling.
- the cooling condition data set having at least the surface temperature of the rail and the operating conditions of the above cooling equipment for forced cooling is used as input data, and at least the hardness inside the rail head of the rail after forced cooling is calculated as output data.
- a database that stores a plurality of sets of training data consisting of the above cooling condition data set and the output data of the above hardness calculated using the internal hardness calculation model, which is a physical model for the above, and the above-mentioned multiple sets of training.
- a hardness prediction model generator that generates a hardness prediction model that uses the cooling condition data set as at least input data and information about the hardness inside the rail after forced cooling as output data, and cooling start.
- Inside the rail for a set of cooling condition data sets set as cooling conditions for the heat treatment step using a thermometer that measures the surface temperature of the previous rail the measurements measured by the thermometer and the hardness prediction model. It is a gist to include a hardness prediction unit for predicting the hardness of the rail after the heat treatment step based on the information on the hardness of the above.
- one aspect of the present invention is a rail heat treatment apparatus having a heat treatment step of forcibly cooling a rail having a temperature equal to or higher than the austenite region temperature by a cooling facility, and before starting cooling of the rail in the cooling facility.
- the hardness prediction unit for predicting the hardness inside the rail and the hardness inside the rail predicted by the hardness prediction unit are outside the target hardness range by the hardness prediction device for the heat-treated rail according to one aspect of the present invention.
- the gist is to provide an operating condition resetting unit for resetting the operating conditions of the cooling equipment so that the predicted hardness inside the rail falls within the target hardness range.
- one aspect of the present invention is a heat treatment rail manufacturing facility provided with the heat treatment apparatus for the heat treatment rail according to the first aspect of the present invention.
- the term “inside the rail” as used herein refers to a region inside the cross section from the rail surface to a predetermined depth.
- a process of calculating the hardness distribution data (learning data) inside the rail after forced cooling for a plurality of cooling conditions which is a process with a large calculation load using heat transfer analysis or the like, is performed. Since it can be executed offline, it can be executed with high accuracy. Then, according to the aspect of the present invention, a hardness prediction model for obtaining data on the hardness distribution inside the rail after forced cooling with respect to the cooling conditions is obtained by machine learning based on the accurate learning data. Therefore, according to the aspect of the present invention, for example, it is possible to appropriately control the structure of the region from the head surface to the inside of the heat-treated rail, and the hardness of each rail to be manufactured varies and the length of the rail is long. It is possible to manufacture heat-treated rails with less variation in quality by reducing variation in hardness in the direction.
- FIG. 1 It is a schematic diagram which shows the manufacturing equipment of the heat treatment rail which concerns on embodiment based on this invention. It is a figure explaining the arrangement of the header and the like for cooling in the cooling equipment which concerns on embodiment based on this invention. It is a figure explaining the forced cooling part of a rail. It is a figure which shows the example of the control method of a heat treatment, (a) is a figure which explains the cooling condition in the one-step cooling method, (b), (c) are the multi-step cooling method. It is a figure explaining the relationship between the surface temperature and transformation behavior by a one-step cooling method. It is a figure explaining the relationship between the surface temperature and transformation behavior by the two-step step method which concerns on embodiment based on this invention.
- FIG. 1 is a schematic view showing an example of a heat treatment rail manufacturing facility 2 for manufacturing a heat treatment rail 1.
- the manufacturing equipment 2 shown in FIG. 1 includes a heating furnace 11, a rolling mill 3, a cutting machine 4, a cooling equipment 7, and a cooling floor 10, and these equipments, in this order, convey rail materials (pass lines). It is arranged along.
- the heating furnace 11 executes a process of heating steel pieces produced by a continuous casting facility or the like so as to have a temperature in the austenite region or higher on the entrance side of the cooling facility 7, for example. However, this does not apply if the cooling facility 7 has a reheating process as a pre-process.
- the rolling mill 3 is a hot rolling facility that forms and stretches a steel piece heated in a heating furnace 11 into a desired rail shape by a plurality of rolling passes.
- the rolling mill 3 is usually composed of a plurality of rolling stands.
- the cutting machine 4 is a facility for dividing the long rail 1 stretched by the rolling mill 3 in the longitudinal direction, and is appropriately used according to the rail length as a product and the length of the rolled material.
- the rolling length of about 100 m may be transferred to the cooling equipment 7 without being divided, or the length per piece may be cut (sawed) to a length of, for example, about 25 m. ) And then transported.
- the cooling facility 7 is a facility for forcibly cooling the rail 1 having a high temperature equal to or higher than the austenite region temperature, which will be described later.
- the cooling equipment 7 is installed along the pass line of the rail 1 in the production line. However, the cooling equipment 7 does not necessarily have to be installed on the transfer line from the rolling mill 3.
- the cooling equipment 7 is provided in an area different from the hot rolling equipment, and the hot-rolled rail 1 is reheated to a temperature above the austenite region in a heating furnace and then transported to the cooling equipment 7. There may be.
- the cooling equipment 7 is composed of a plurality of cooling zones arranged along the longitudinal direction of the rail 1 to be cooled, and the cooling zone to be used is set according to the length of the rail 1.
- the cooling conditions (operating conditions) of each cooling zone can be set individually. Details of the cooling equipment 7 will be described later.
- thermometer 8 is provided at a position on the inlet side of the cooling equipment 7 (a position between the cutting machine 4 and the cooling equipment 7), and detects the rail temperature before the start of cooling.
- the measurement result measured by the thermometer 8 is sent to the control device 6 that controls the cooling equipment 7.
- the thermometer 8 measures, for example, at least the surface temperature of the head of the rail 1.
- a thermometer 9 for detecting the temperature of the surface of the rail 1 after the end of forced cooling may be installed at a position on the downstream side of the cooling equipment 7 (outlet side of the cooling equipment 7). In this case, the validity of the prediction result of the control device 6 can be determined by comparing the temperature after the forced cooling predicted by the control device 6 with the temperature measured by the thermometer 9.
- the rail 1 forcibly cooled by the cooling facility 7 is conveyed to the cooling floor 10.
- the cooling floor 10 has, for example, a role of straightening the rail 1 so as not to bend and a role of uniformly cooling the rail 1. Further, on the cooling floor 10, visual inspection, weight measurement, and the like of the manufactured rail 1 are appropriately performed.
- the cooling equipment 7 of the present embodiment is configured to forcibly cool the head and foot of the rail 1 carried to the processing position by a cooling medium injected from the cooling header.
- a cooling header is provided for each cooling zone.
- FIG. 2 is a diagram showing a schematic diagram of an arrangement example of a cooling header included in the cooling equipment 7 as viewed from a rail cross section. That is, as shown in FIG. 2, the cooling header of the present embodiment is for cooling the crown cooling header 71 and the head side cooling header 72 for cooling the head 101 of the rail 1, and the foot 103 of the rail 1.
- the sole cooling header 73 is provided. If necessary, an abdominal cooling header for cooling the abdomen 102 of the rail 1 may be further provided. Further, the crown cooling header 71 and the head cooling header 72 are collectively referred to as a “head cooling header”.
- the head-top cooling header 71, the head-side cooling header 72, and the sole cooling header 73 are used as a cooling medium source via piping, respectively.
- the cooling medium is ejected from a plurality of nozzles which are connected and are not shown. Further, the pipe is provided with a valve for control.
- the cooling method adopted by the cooling equipment 7 of the present embodiment is pulsatile cooling.
- Impulsive cooling is a method of injecting compressed air as a cooling medium, which can achieve a cooling rate suitable for the present invention and has little fluctuation in cooling capacity with respect to the surface temperature of the material to be cooled.
- the cooling method in the present embodiment is not limited to the impulse cooling, and may be a water cooling method including mist cooling.
- each cooling header is as follows, that is, the nozzle of the cooling header 71 is arranged above the head 101 of the rail 1 along the longitudinal direction of the rail 1.
- the nozzle of the cooling header 71 injects a cooling medium (air) toward the upper surface (top surface) 1011 of the head 101 shown in FIG.
- the nozzles of the cooling header 72 are arranged along the longitudinal direction of the rail 1 on both sides of the head 101 of the rail 1 at the processing position.
- the nozzle of the cooling header 72 injects a cooling medium (air) toward the side surface (head side surface) 1012 of the head 101 shown in FIG.
- the nozzle of the foot sole cooling header 73 is arranged along the longitudinal direction of the rail 1 below the foot portion 103 of the rail 1 at the processing position.
- the nozzle of the foot sole cooling header 73 injects a cooling medium (air) toward the back surface (foot back surface) 1031 of the foot portion 103 shown in FIG.
- the nozzle type is preferably a group jet composed of a plurality of circular tube nozzles or a slit nozzle composed of slits having rectangular gaps.
- the cooling capacity heat transfer coefficient
- each of the cooling headers 71, 72, and 73 has a configuration in which the pressure can be controlled in order to control the injection of the cooling medium (air).
- the cooling equipment 7 provides a moving mechanism for each cooling header whose distance from the surface of the rail 1 can be adjusted. I have.
- the position adjusting mechanism of each of these headers includes an electric actuator, an air cylinder, a hydraulic cylinder, and the like.
- an electric actuator is suitable from the viewpoint of positioning accuracy.
- a range finder for example, a laser displacement meter (not shown) for measuring the distance from the surface of the rail 1 to each cooling header is provided. Then, the injection distance of each cooling header during cooling can be controlled according to the set value.
- it is equipped with a restraining device that holds the foot 103 of the rail 1 and restrains the deformation in the vertical and horizontal directions so that the rail 1 is deformed due to heat shrinkage during cooling and the distance from the header does not change. (Not shown).
- the cooling equipment 7 includes a head thermometer 74 and a foot thermometer 75.
- the head thermometer 74 is provided above the head 101 of the rail 1 and measures the surface temperature of the head 101 (for example, one point in the crown surface 1011).
- the foot thermometer 75 is provided below the foot 103 of the rail 1 and measures the surface temperature of the foot 103 (for example, one point in the foot back surface 1031).
- a plurality of these two types of thermometers 74 and 75 are installed in the cooling facility 7 in the longitudinal direction, and the temperature history of each part during cooling can be monitored by these two types of thermometers 74 and 75. can.
- thermometer (not shown) for monitoring the temperature of the injected air (cooling medium) may be installed in a plurality of headers. This is because the injection temperature also affects the cooling capacity.
- the injection pressure, injection distance, injection position, injection time, and the like of the cooling medium injected toward the rail 1 in the cooling equipment 7 are controlled by the control device 6, and the cooling conditions can be adjusted.
- Examples of the heat treatment (forced cooling) control method include a one-step cooling method (FIG. 4 (a)), a two-step step method (FIG. 4 (b)), and a three-step step method (FIG. 4 (b)) as shown in FIG.
- There is a multi-step method such as FIG. 4 (c)).
- the one-stage cooling method is a method in which cooling is performed under constant conditions from the start of cooling to the end of cooling by setting the injection flow rate, pressure, and injection distance of the cooling header as cooling conditions.
- the multi-step method is a method in which the cooling conditions are set to two stages (front stage and rear stage) or three or more stages from the start of cooling, and the cooling conditions are changed stepwise with the passage of time.
- the multi-step method is adopted.
- the injection flow rate, pressure, and injection distance of the cooling header are determined in each step, and the timing for shifting to the next step is determined.
- the cooling conditions may be set as a function of time so that the cooling conditions that change with the passage of time can be specified. ..
- Cooling conditions can be set individually for each cooling zone divided in the longitudinal direction. Further, in the head side cooling header 72, the cooling conditions of the left and right cooling headers may be set to different conditions. Further, the injection flow rate, pressure, and injection distance of the cooling header may be changed in a stepped manner individually or in combination of two or more conditions. However, when changing by combining two or more conditions, a plurality of conditions are changed at the same time according to the time step of FIG.
- the transformation from austenite to pearlite occurs in a temperature range of about 550 ° C to 730 ° C. In practice, it is desirable to transform in the temperature range of 570 to 590 ° C. in order to achieve both suppression of bainite and high hardness.
- the cooling of the preceding step is, for example, cooling from the start of cooling to before the surface starts transformation, and the cooling rate of the preceding step. Should be set in the range of 4 to 6 ° C / sec. If the cooling rate is slower than this range, it will be transformed at high temperature and the hardness will decrease. Further, if the cooling rate is faster than this range, bainite transformation may occur.
- FIG. 5 schematically shows an example of structural changes in the surface layer of the rail 1 head.
- FIG. 5 shows an example in which a one-stage cooling method in which the cooling conditions are kept constant from the start to the end of forced cooling is applied as a control method for heat treatment.
- a rapid temperature rise ⁇ T 80 to 120 ° C.
- the cooling rate decreases at a position about 5 to 10 mm inside from the surface, and the supercooling degree decreases, so that the hardness inside the rail 1 after the heat treatment also decreases. It ends up. That is, if the heat treatment control method is the one-stage cooling method, the hardness inside the rail 1 after the heat treatment may not be the desired hardness.
- the cooling capacity can be increased in accordance with the transformation heat generation in the subsequent step after the surface transformation heat generation starts.
- the temperature rise due to the transformation heat generation can be suppressed, and the pearlite structure on the surface is less likely to soften.
- the cooling rate in the subsequent step is too high, the surface will be strongly cooled without completing the pearlite transformation, and some bainite structures may be generated. Therefore, in the subsequent step, it is desirable that the average cooling rate from the start of transformation heat generation on the surface to the end of cooling is in the range of 1 to 2 ° C./sec.
- the transformation start time (time at which the cooling curve intersects the pearlite transformation start curve P) shown in FIGS. 5 and 6 changes depending on the cooling start temperature. Further, if the shape of the rail 1 changes, the mass of the head changes. Therefore, even if the same cooling conditions are set, the required cooling rate and cooling capacity change. Therefore, it is necessary to control not only the timing of switching the cooling condition from slow cooling to strong cooling by the control device 6 but also the cooling capacity by the injection pressure and the injection distance of each step. Furthermore, since the transformation curve shown in FIGS. 5 and 6 changes depending on the chemical composition of the rail steel and the austenite grain size before cooling, the cooling conditions are set to the components contained in the steel pieces of the rail material and the austenite grain size before cooling. It may be changed according to the pass schedule of the rolling mill 3 which has an influence.
- the present embodiment has a hardness prediction device 20.
- the hardness prediction device 20 is for realizing a hardness prediction method for the heat-treated rail 1 that predicts the hardness of the rail 1 after the heat treatment step in which the rail 1 having a temperature equal to or higher than the austenite region temperature is forcibly cooled by the cooling equipment 7. It is a device of. As shown in FIG. 7, the hardness prediction device 20 includes a basic data acquisition unit 21, a database 23 (storage unit), a hardness prediction model generation unit 24, and a hardness prediction unit 26. The hardness prediction unit 26 is used online and is incorporated in the control device 6.
- a set of data of cooling conditions having at least the surface temperature of the rail 1 before the start of cooling in the cooling equipment 7 and the operating conditions of the cooling equipment 7 is referred to as a cooling condition data set.
- the cooling condition data set used offline includes numerical information corresponding to the temperature information acquired by the thermometer 8 arranged on the inlet side of the cooling equipment 7 as the surface temperature of the rail 1 before the start of cooling. Further, as the operating conditions of the cooling equipment 7, the injection flow rate, injection pressure, injection distance and switching timing of each cooling header in each step from the start of cooling to the end of cooling (for example, from the start of cooling to the switching of each step). Time) is included.
- the cooling condition data set may include input information of the heat treatment for cooling other than the surface temperature of the rail 1 before the start of cooling and the operating conditions of the cooling equipment 7.
- the basic data acquisition unit 21 is an internal hardness calculation which is a physical model for calculating at least the hardness inside the head of the rail 1 after forced cooling as output data by using the offline cooling condition data set as input data. Have a model.
- the execution of the numerical calculation using the internal hardness calculation model is performed by the internal hardness offline calculation unit 22.
- the basic data acquisition unit 21 individually executes an offline calculation by the internal hardness offline calculation unit 22 for the plurality of cooling condition data sets, and performs the above-mentioned cooling condition data set as input data and the output data.
- the basic data acquisition unit 21 stores the acquired learning data in the database 23.
- the internal hardness data which is the output data calculated by the internal hardness offline calculation unit 22, is represented by the internal hardness distribution in a region from at least the surface of the rail 1 to a preset depth.
- the preset depth is, for example, 10 mm or more and 50 mm or less.
- the preset depth is set to, for example, a limit value or more of a wear depth that can withstand practical use even if the surface layer of the rail 1 head is worn. Conventionally, it is preferably 1 inch (25.4 mm).
- the basic data acquisition unit 21 of the present embodiment is executed offline, and after the heat treatment step, a set of cooling condition data sets consisting of at least the surface temperature before the start of cooling and the operating conditions of the cooling equipment 7 is used as input data. It has an internal hardness offline calculation unit 22 that executes numerical calculation using the hardness distribution inside the rail 1 as output data, and variously changes the cooling condition data set to calculate the hardness distribution inside the rail 1 for each cooling condition data set. Then, it has a function of sending the learning data showing the relationship between the obtained cooling condition data set and the hardness distribution to the database 23.
- configuration data such as a plurality of cooling condition data sets or data such as surface temperature before the start of cooling that constitutes the cooling condition data set may be stored in the database 23 in advance.
- a range of temperature conditions is set based on past operating conditions, conditions of the rail 1 to be manufactured in the future, and the like, and the values within the set range are determined.
- the plurality of cooling condition data sets to be used do not necessarily have to be stored in advance in the database 23, and may be configured to be directly input to the internal hardness offline calculation unit 22.
- the internal hardness offline calculation unit 22 includes a heat transfer coefficient calculation unit 22A, a heat conduction coefficient calculation unit 22B, a structure calculation unit 22C, and a hardness calculation unit 22D.
- the calculation from the start of cooling to the end of cooling is performed in the order of heat transfer coefficient calculation, heat conduction calculation, and microstructure calculation unit 22C, and the final microstructure calculation. It can be obtained by calculating the hardness from the result.
- the heat transfer coefficient calculation unit 22A calculates the heat transfer coefficient on the surface of the rail 1 during the heat treatment.
- the heat transfer coefficient calculation unit 22A of the present embodiment calculates heat transfer coefficients at a plurality of locations on the surface of the head of the rail 1.
- the heat transfer coefficient calculation unit 22A of the present embodiment calculates the heat transfer coefficient of the surface of the rail 1 by a numerical fluid dynamics method such as a finite volume method by inputting the operation parameters of the cooling facility 7 and the rail shape.
- the finite volume method is a method in which a region to be analyzed is divided into a finite number of control volumes, and an integral-type physical quantity conservation equation is applied to each volume.
- the heat transfer coefficient may be calculated by an experimental formula for forced convection obtained from a cooling experiment regarding the relationship between dimensionless quantities such as the Nusselt number and the Reynolds number.
- each of the surface of the rail 1 head surface is determined according to the injection flow rate, injection pressure, injection distance, and switching timing of each cooling header in each step from the start of cooling to the end of cooling. Obtain the time-series heat transfer coefficient (distribution of heat transfer coefficient that changes with time) at the position. Further, the temperature of the injected refrigerant may be included in the variable.
- the heat conduction calculation unit 22B performs heat conduction calculation inside the rail 1 by heat treatment, for example, heat conduction calculation in a two-dimensional cross section of the rail 1, using the heat transfer coefficient calculated by the heat transfer coefficient calculation unit 22A as a boundary condition. .. As a heat conduction calculation, for example, the temperature distribution in the cross section is obtained.
- the heat conduction calculation unit 22B of the present embodiment uses a numerical heat transfer analysis method such as a finite element method with the heat transfer coefficient at each position on the surface of the head of the rail 1 output by the heat transfer coefficient calculation unit 22A as a boundary condition. Then, the temperature history (heat conduction calculation) inside the rail 1 from the start of cooling to the end of cooling is calculated. Further, values such as thermal conductivity, specific heat, and density as physical property values required for heat conduction calculation are appropriately changed according to the component composition of the target rail 1.
- the above two calculation units 22A and 22B may be a method of calculating the heat conduction calculation unit 22B for calculating the temperature field by using the calculation result by the heat transfer coefficient calculation unit 22A for calculating the flow field. Sufficient calculation accuracy can be obtained. However, if it is desired to further improve the calculation accuracy, coupled analysis may be performed in consideration of the interaction between the flow field and the temperature field. Although the calculation accuracy is improved in the coupled analysis, it is practically difficult to apply it in the online analysis because the calculation load increases. However, in the present invention, the load increase is allowed because these analyzes are executed offline. ..
- the structure calculation unit 22C predicts the structure in the cross section of the rail 1 in consideration of the phase transformation from the temperature distribution inside the rail 1 based on the temperature history calculation calculated by the heat conduction calculation unit 22B.
- the texture prediction in the cross section is, for example, the tissue distribution in the cross section.
- the structure calculation unit 22C of the present embodiment predicts the structure at each position in the rail 1 cross section in consideration of the phase transformation from the temperature history inside the rail 1 obtained by the heat conduction calculation unit 22B. Since the behavior of the phase transformation changes depending on the component composition of the steel to be heat-treated and the austenite grain size before the start of cooling, the calculation is performed for each component composition corresponding to the standard of the target rail 1. Further, the austenite particle size changes depending on the pass schedule in the rolling mill 3 and the time required from the end of rolling to the start of forced cooling. Therefore, the microstructure may be calculated for each of these operating conditions, and a microstructure prediction model for predicting the austenite particle size before the start of forced cooling may be further added.
- the structure calculation unit 22C of the present embodiment performs a phase transformation calculation incorporating dynamic phase transformation characteristics such as a change in the phase transformation start temperature and a change in the progress rate of the phase transformation according to the cooling rate.
- the microstructure calculation unit 22C and the heat conduction calculation unit 22B be coupled.
- the method by Ito et al. Iron and steel, 64 (11), S806, 1978, or iron and steel, 65 (8), A185-A188, 1979).
- a known calculation formula described in the above can be used.
- the hardness calculation unit 22D calculates the hardness distribution in the cross section of the rail 1 from the structure distribution based on the structure prediction of each cross section calculated by the structure calculation unit 22C.
- the hardness calculation unit 22D of the present embodiment calculates the predicted hardness using the relational expression between each structure and the hardness with the chemical composition and the degree of supercooling as inputs.
- the pearlite structure is a lamellar structure in which plate-like soft ferrite and hard cementite are layered, and it is known that there is a strong correlation between lamellar spacing and hardness.
- R The method by Marder et al. (The Effect of Morphology on the Strength of Pearlite: Met. Trans. A, 7A (1976), 365-372) can be used.
- an experimental formula obtained in advance by an experiment or the like may be used as the relational expression between the chemical composition, the degree of supercooling and the hardness of each structure.
- ⁇ Database 23> Using the internal hardness offline calculation unit 22, the surface temperature of the rail 1 before the start of cooling as the cooling condition data set, and the injection flow rate and injection pressure of each cooling header from the start of cooling to the end of cooling as the operating conditions of the cooling equipment 7. , Generate a data set with various changes in the injection distance and the switching timing of the cooling step. Further, the result of calculating the hardness distribution inside the rail 1 corresponding to each data set is stored in the database 23 as learning data.
- the hardness distribution inside the rail 1 which is the calculation result is expressed by the hardness data corresponding to each position (coordinates in the cross section) in the cross section of the rail 1 head 101.
- the hardness data of the hardness distribution is not a continuous value, but a discrete value according to the element division used in the calculation of the heat conduction calculation unit 22B and the structure calculation unit 22C.
- the hardness data extracted at a pitch of about 1 to 5 mm may be averaged from the calculation results for each pitch.
- the position and hardness data in the vertical direction from the crown surface 1011 may be used as the hardness distribution inside the rail 1.
- data on the position and hardness diagonally advanced from the head angle portion may be used.
- representative positions in the internal direction from the surface several representative points such as depths of 2, 5, 10, 15, 20, and 25 mm are used, and the corresponding hardness data is used as the hardness distribution inside the rail 1. be able to.
- a diagram showing the hardness distribution in the cross section of the rail 1 with contour lines or color-coded image data may be defined as the hardness distribution inside the rail 1.
- machine learning means such as deep learning can generate a hardness prediction model 25 using an image as output data.
- the cooling condition data set which is the input data when constructing the database 23, may be changed within the range with reference to the past operation results. Further, within the range of the equipment specifications of each cooling header of the cooling equipment 7, the input conditions for the calculation are appropriately changed, and the calculation is performed by the internal hardness offline calculation unit 22.
- the learning data to be stored may be a set of 500 or more input data (cooling condition data set) and output data (hardness calculation result). Preferably, 2000 or more learning data are generated.
- the hardness prediction model generation unit 24 uses the cooling condition data set as at least input data by machine learning using a plurality of sets of learning data stored in the database 23, and provides information on the hardness inside the rail 1 after forced cooling. Is generated as the output data of the hardness prediction model 25. The generation of the hardness prediction model 25 is performed offline.
- the machine learning model to be used may be any model as long as the hardness can be predicted with the accuracy required for practical use.
- a machine learning model for example, a commonly used neural network (including deep learning), decision tree learning, random forest, support vector regression, or the like may be used. Further, an ensemble model in which a plurality of models are combined may be used.
- the hardness prediction model 25 it is determined not the hardness value of the rail 1 but whether or not it is within the allowable range of the predetermined hardness distribution, and the result is binarized as pass / fail and output.
- a machine learning model as data may be used. At that time, it is preferable to use a classification model such as the k-nearest neighbor method or logistic regression.
- the manufacturing equipment 2 for the rail 1 of the present embodiment includes a control device 6 for controlling the cooling conditions of the rail 1.
- the control device 6 acquires the shape, chemical composition, target hardness (internal distribution), and reference cooling conditions of the rail 1 from the host computer 5, calculates the operating conditions for realizing them, and transfers the cooling control device. Issue a command and determine the operating parameters of the cooling equipment 7.
- the configuration of the control device 6 in this embodiment is shown in FIG.
- the control device 6 includes an operating condition initial setting unit 61, a hardness prediction unit 26, an operating condition determination unit 62, and an operating condition resetting unit 63 of the cooling equipment 7.
- the operating condition initial setting unit 61 presets the injection pressure, the injection distance, the injection position, and the switching timing of the cooling header so as not to generate an abnormal structure such as a bainite structure or a martensite structure while satisfying the target hardness distribution. I will do it.
- These cooling conditions can be determined offline by an empirical rule based on past operation results, a method shown in Patent Documents 1 to 3, and the like. Further, using the basic data acquisition unit 21, appropriate cooling conditions for obtaining the target hardness are determined in advance for the representative values of the rail type, standard, dimensions, and chemical composition of the rail 1, and these conditions are cooled. It may be set in the operation condition initial setting unit 61 of the equipment 7.
- the hardness prediction unit 26 of the rail 1 after the heat treatment step is based on the hardness inside the rail 1 with respect to a set of cooling condition data sets set as cooling conditions of the heat treatment step, which is obtained by using the hardness prediction model 25. Predict hardness.
- the hardness prediction unit 26 of the present embodiment uses the surface temperature of the rail 1 head measured by the thermometer 8 on the entry side of the cooling equipment 7 and the cooling condition of the cooling header set by the operation condition initial setting unit 61. To configure the cooling condition data set.
- the hardness prediction unit 26 predicts the hardness distribution inside the rail 1 after the heat treatment is completed by using the hardness prediction model 25 generated offline using the cooling condition data set generated online as input data.
- the hardness prediction unit 26 updates the initial setting of the operating condition based on the information after the resetting, and after the heat treatment is completed again. Predict the hardness distribution inside the rail 1.
- the operating condition determination unit 62 compares the hardness distribution inside the rail 1 obtained by the hardness prediction unit 26 with the target range of the hardness distribution inside the rail 1 received from the host computer 5.
- the target hardness inside the rail 1 can be set so as to satisfy the hardness range defined in JISE1120 (2007), for example, as shown in FIG.
- JISE1120 the upper and lower limit values of the surface hardness of the rail 1 head, the upper limit value of the internal hardness, and the lower limit value at a predetermined depth position (reference point) are defined.
- the position of the reference point is a position at a distance of 11 mm from the surface.
- FIG. 11 is a diagram showing an example when the hardness is out of the target hardness range.
- the internal hardness of the rail 1 head decreases as the distance from the surface toward the inside increases. Therefore, as shown in FIG. 12, a target curve of the hardness distribution from the surface layer of the rail 1 to a certain depth may be set, and the difference from the hardness may be set within a certain range. At that time, within the permissible range of the target curve of the hardness distribution, the above standard of JISE1120 shall be satisfied.
- the operating condition determination unit 62 shifts to the operating condition resetting unit 63.
- the operating condition resetting unit 63 resets the cooling conditions. To reset the cooling conditions, specifically, the injection flow rate, injection pressure, injection distance, switching timing of the cooling step, or a plurality of operating parameters of each cooling header in each step from the start of cooling to the end of cooling. Reset.
- the reset operating parameters are used by the hardness prediction unit 26. As a result, the operation parameters are modified so that the predicted hardness distribution inside the rail 1 falls within the target hardness range.
- the trained model is generated in advance offline and the hardness is predicted using the generated trained model, the output of the hardness prediction result for one cooling condition data set can be executed in a short time. That is, it is possible to reset in a short time as a whole even if the recalculation is performed several times to a dozen times.
- the cooling control unit 64 executes the forced cooling process in the cooling equipment 7 under the operating conditions in which the hardness distribution inside the rail 1 determined by the hardness prediction unit 26 is determined to be in the target range. That is, the cooling control unit 64 controls to execute forced cooling at the switching timing of the injection flow rate, the injection pressure, the injection distance, and the cooling step of each cooling header, which is predicted to have a hardness within the target range.
- the cooling condition change command may be adjusted.
- the setting of the operating conditions of the cooling equipment 7 can be carried out for each header divided in the longitudinal direction of the rail 1.
- the speed at which the tail end of the rail 1 passes through the rolling mill during rolling is not constant, the amount of cooling due to contact with the roll, roll cooling water, and descaling water is large, and the temperature is higher than that of the stationary portion in the center of the longitudinal axis. Easy to drop. Therefore, the temperature distribution in the longitudinal direction of the rail 1 is measured by the thermometer 8 on the entry side of the cooling equipment 7, and the above method is applied to each position of the cooling header divided in the longitudinal direction to apply the above method to each position in the longitudinal direction. Control the cooling conditions individually. As a result, even if the cooling start temperature is distributed in the longitudinal direction, the rail 1 having uniform hardness in the longitudinal direction can be manufactured after the cooling is completed.
- the internal hardness offline calculation unit 22 which is calculated in advance by a calculation formula based on a physical model, is executed offline.
- a process of calculating the hardness distribution data (learning data) inside the rail 1 after forced cooling for a plurality of cooling conditions which is a process with a large calculation load using heat transfer analysis or the like, is performed.
- a hardness prediction model 25 for obtaining data on the hardness distribution inside the rail 1 after forced cooling with respect to cooling conditions is obtained by machine learning based on a large number of highly accurate learning data. Then, online, by executing the hardness prediction by the hardness prediction model 25, it becomes possible to output the hardness prediction result by the internal hardness offline calculation unit 22 that performs a complicated calculation at an extremely high speed.
- the learning data in the database 23 can be created separately from the online operation of the cooling equipment 7. Therefore, the data set can be accumulated in the database 23 at any time, and the hardness prediction model 25 can be updated periodically (for example, once a month). As a result, the number of data sets that are the basis of the hardness prediction model 25 is increased, and the accuracy of the output result of the trained model is improved.
- the values of the cooling condition data set can be set intentionally, so statistical bias is unlikely to occur in the cooling condition data set, and the data is suitable for machine learning. Become. Therefore, as the number of data sets increases, the accuracy improves.
- the present embodiment is a method for predicting the hardness of the rail 1 after the heat treatment step of forcibly cooling the rail 1 having a temperature equal to or higher than the austenite region temperature by the cooling facility 7.
- a cooling condition data set having at least the surface temperature of the rail 1 before the start of cooling and the operating conditions of the cooling facility 7 for forced cooling as input data
- the inside of at least the rail 1 head of the rail 1 after the forced cooling is acquired and acquired.
- a hardness prediction model 25 having the cooling condition data set as at least input data and the hardness inside the rail 1 after forced cooling as output data is generated in advance, and the hardness prediction is performed.
- the hardness of the rail 1 after the heat treatment step is predicted based on the hardness inside the rail 1 with respect to a set of cooling condition data sets set as the cooling conditions of the heat treatment step obtained by using the model 25.
- the hardness predictor 20 of the rail 1 that predicts the hardness of the rail 1 after the heat treatment step of forcibly cooling the rail 1 having a temperature equal to or higher than the austenite region temperature by the cooling facility 7, and is a rail before the start of cooling.
- the input data is a cooling condition data set having at least the surface temperature of 1 and the operating conditions of the cooling facility 7 for forced cooling
- the output data is the hardness inside at least the head of the rail 1 after the forced cooling.
- a database 23 that stores a plurality of sets of training data consisting of the cooling condition data set and the output data of the hardness, which is calculated using the internal hardness calculation model, which is a physical model for calculating the above, and the plurality of data.
- a hardness prediction model generation unit 24 that generates a hardness prediction model 25 using the cooling condition data set as at least input data and the hardness inside the rail 1 after forced cooling as output data by machine learning using a set of learning data. And, using the hardness prediction model 25, the hardness prediction that predicts the hardness of the rail 1 after the heat treatment step based on the hardness inside the rail 1 for a set of cooling condition data sets set as the cooling conditions of the heat treatment step.
- a hardness prediction device 20 of the heat treatment rail 1 provided with the unit 26 is used.
- high-precision hardness prediction can be executed online in a short time, so forced cooling (heat treatment) is executed under operating conditions with the hardness inside the rail 1 as the target hardness range.
- forced cooling heat treatment
- the heat treatment rail 1 can be manufactured by reducing the hardness variation and suppressing the quality variation.
- the output data calculated using the internal hardness calculation model is a hardness distribution in a region from at least the surface of the rail 1 to a preset depth. According to this configuration, it is possible to more reliably predict the hardness for heat treatment.
- the internal hardness calculation model includes a heat transfer coefficient calculation unit 22A for calculating the heat transfer coefficient of the surface of the rail 1 during heat treatment using the cooling facility 7, and a heat transfer coefficient calculation unit.
- the heat conduction calculation unit 22B that calculates the temperature history inside the rail 1 by the heat treatment and the inside of the rail 1 based on the temperature history calculation calculated by the heat conduction calculation unit 22B.
- 22D is provided with a hardness calculation unit 22D for calculating the hardness of the above. According to this configuration, it is possible to more reliably predict the hardness for heat treatment.
- the present embodiment is a heat treatment method for a heat treatment rail 1 having a heat treatment step of forcibly cooling the rail 1 having a temperature equal to or higher than the austenite region temperature by the cooling facility 7, and the rail 1 in the cooling facility 7 is described above.
- the hardness inside the rail 1 is predicted by the hardness prediction method for the heat-treated rail 1 of the present embodiment, and when the predicted hardness inside the rail 1 is outside the target hardness range, the predicted rail 1 is predicted.
- the operating conditions of the cooling equipment 7 are reset so that the internal hardness falls within the target hardness range.
- the heat treatment apparatus of the heat treatment rail 1 provided with the above is used.
- forced cooling heat treatment
- the hardness inside the rail 1 as the target hardness range.
- the heat treatment rail 1 can be manufactured by reducing the hardness variation and suppressing the quality variation.
- the operating conditions of the cooling equipment 7 to be reset are the injection pressure, the injection distance, the injection position, and the injection time of the cooling medium injected toward the rail 1 in the cooling equipment 7. , Includes at least one operating condition. According to this configuration, it is possible to more reliably set the operating conditions in which the hardness inside the rail 1 is the target hardness range.
- the cooling facility 7 has a plurality of cooling zones arranged along the longitudinal direction of the rail 1 to be cooled, and the operating conditions of the cooling facility 7 are reset for each of them. Reset the operating conditions individually for each cooling zone. According to this configuration, it is possible to set the operating conditions in which the hardness inside the rail 1 is the target hardness range in more detail.
- the hardness of the rail 1 after the rail 1 having a temperature equal to or higher than the austenite region temperature is forcibly cooled by the cooling facility 7 is set to the hardness of the rail 1 before the start of cooling by the cooling facility 7. It is a method of generating a hardness prediction model 25 for obtaining from a cooling condition data set having at least a surface temperature and operating conditions of the cooling equipment 7 for forced cooling, and the forced cooling condition data set is used as input data. Learning consisting of the above cooling condition data set and the above hardness output data using the internal hardness calculation model, which is a physical model for calculating at least the internal hardness of the rail 1 head after cooling as output data. A plurality of sets of data are acquired, and by machine learning using the acquired multiple sets of learning data, the cooling condition data set is at least input data, and the hardness inside the rail 1 after forced cooling is used as output data.
- the prediction model 25 is generated in advance.
- the hardness prediction model 25 may be, for example, a neural network model (including a deep learning model), a random forest, or a model trained by SVM regression.
- the output data calculated using the internal hardness calculation model is a hardness distribution in a region from at least the surface of the rail 1 to a preset depth
- the output data of the hardness prediction model 25 is also , At least the hardness distribution data in the region from the surface of the rail 1 to the preset depth.
- a method for manufacturing a heat treatment rail 1 having a heat treatment method for the heat treatment rail 1 according to the embodiment for example, a facility for manufacturing a heat treatment rail 1 having a heat treatment apparatus for the heat treatment rail 1 of the embodiment is provided. According to this configuration, it is possible to manufacture a rail having an excellent hardness uniformity at least on the surface layer of the rail head.
- the heat-treated rail 1 was manufactured using the rail 1 manufacturing facility 2 (see FIG. 1).
- the rail 1 of a plurality of rails and the standard was forcibly cooled, and after air-cooling to room temperature, the hardness distribution in the structure of the head and the cross section was evaluated.
- 20 heat-treated rails 1 were manufactured, and the variation in each was evaluated.
- the target rail 1 was a total of four types, two types of rails (JIS 60 kg rail and 50 kg N rail) and two types of standards (high hardness rail H and normal hardness rail L).
- the target value of the inlet temperature by the inlet thermometer 8 of the cooling equipment 7 is set to 750 ° C., and the cooling conditions set in advance by offline calculation are operated so that the target hardness distribution can be obtained for the above four types of rails 1. It was set as the indicated value of the condition initial setting unit 61.
- the cooling condition the cooling is performed by the two-step method, and the set value of the injection pressure in the first step and the second step and the switching time from the first step to the second step are set according to the type of the rail 1 to be heat-treated. In the table, "fixed" indicates the standard condition).
- the hardness prediction model 25 used corresponds to the four types of rails 1 of Examples 1 to 4, and the hardness prediction model 25 corresponding to each is generated.
- the database 23 used to generate the hardness prediction model 25 shows the relationship between the structure and hardness by experiments using a one-stage cooling method in which the injection flow rate and pressure of the cooling nozzles are variously changed using a laboratory-level cooling experimental device. It was created by a regression equation.
- the number of data used to generate the hardness prediction model 25 was 500.
- the variation in each of the 20 rails 1 and the temperature variation depending on the position in one rail are combined between the temperature measurement value by the inlet thermometer 8 and the target temperature. There was a variation of ⁇ 30 to + 10 ° C.
- the cooling condition used was the fixed pattern set by the operating condition initial setting unit 61.
- the actual measurement value by the inlet thermometer and the cooling condition set in advance by the operating condition initial setting unit 61 are used as the cooling condition data set, and the hardness distribution inside the rail 1 is predicted to be the target. It was determined whether or not it was within the hardness range.
- the target hardness shown in FIG. 10 the "lower limit” and the “upper limit” of the surface hardness are defined in Table 1, the "lower limit" at the "reference point", and the internal “overall”. Specified by the "upper limit" of.
- the injection pressure in the front step the injection pressure in the rear step (adjusted within the range of "injection pressure adjustment amount” in the table), and the timing of transition from the front step to the rear step (“injection time adjustment amount” in the table). ”Has been modified).
- the injection distance was set to be constant (15 mm) during cooling regardless of the track type in both the examples and the comparative examples.
- the rail 1 was removed from the restraint device, transported to the cooling floor 10, and air-cooled to room temperature. Then, the rail 1 air-cooled to room temperature was cut, and the structure of the head was observed and the hardness test was performed.
- the head tissue was evaluated by observing the cut surface of the sample with an SEM (scanning electron microscope).
- the hardness was evaluated by a Brinell hardness test at each depth position of 0 to 20 mm from the crown surface. Regarding the measurement results of hardness, the maximum value and the minimum value in 100 data were evaluated.
- Cooling equipment 1 Heat treatment rail 2 Manufacturing equipment 3 Rolling machine 4 Cutting machine 5 Upper computer 6 Control device 7 Cooling equipment 8 Thermometer 10 Cooling bed 11 Heating furnace 20 Hardness prediction device 21 Basic data acquisition unit 22 Internal hardness offline calculation unit 22A Heat transfer coefficient calculation Part 22B Heat conduction calculation unit 22C Organization calculation unit 22D Hardness calculation unit 23 Database 24 Hardness prediction model generation unit 25 Hardness prediction model 26 Hardness prediction unit 61 Operating condition initial setting unit 62 Operating condition determination unit 63 Operating condition resetting unit 64 Cooling control Part 71 Head cooling header 72 Head cooling header 73 Foot cooling header 74 Head thermometer 75 Foot thermometer
Landscapes
- Chemical & Material Sciences (AREA)
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Thermal Sciences (AREA)
- Crystallography & Structural Chemistry (AREA)
- Mechanical Engineering (AREA)
- Materials Engineering (AREA)
- Metallurgy (AREA)
- Organic Chemistry (AREA)
- General Physics & Mathematics (AREA)
- Pathology (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Immunology (AREA)
- Health & Medical Sciences (AREA)
- Theoretical Computer Science (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Data Mining & Analysis (AREA)
- Computing Systems (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Mathematical Physics (AREA)
- Artificial Intelligence (AREA)
- Heat Treatment Of Articles (AREA)
- Control Of Heat Treatment Processes (AREA)
- Heat Treatments In General, Especially Conveying And Cooling (AREA)
- Metal Rolling (AREA)
- General Factory Administration (AREA)
Abstract
Description
特に、冷却設備の入側における素材の条件は、鋼片毎に変動がある。このため、進行が速く発熱の大きいパーライト変態を、表面から内部にわたって安定的に制御することは、オンラインでの伝熱解析(物理モデルによる数値計算)を用いた処理では難しい。
ここで、上述の通り、本明細書で「レール内部」とは、レール表面から所定深さまでの断面内部の領域を指す。
このため、本発明の態様によれば、例えば、熱処理レールの頭部表面から内部にかけての領域に対する組織制御を適切に実行することが可能となり、製造するレール毎の硬度のばらつきや、レールの長手方向の硬度ばらつきを低減して、品質ばらつきを抑えた熱処理レールの製造が可能となる。
(熱処理レールの製造設備2)
図1は、熱処理レール1を製造する熱処理レールの製造設備2の一例を示す模式図である。図1に示す製造設備2は、加熱炉11、圧延機3、切断機4、冷却設備7、及び冷却床10を備え、これらの設備が、この順番に、レール材の搬送方向(パスライン)に沿って配置されている。
加熱炉11は、連続鋳造設備などで作製した鋼片を、例えば、冷却設備7の入側においてオーステナイト域温度以上となるように加熱する処理を実行する。もっとも、冷却設備7の前工程として再加熱する処理を有する場合には、その限りではない。
圧延機3は、加熱炉11において加熱された鋼片を複数の圧延パスにより、所望のレール形状に造形・延伸する熱間圧延の設備である。圧延機3は、通常、複数の圧延スタンドから構成される。
切断機4は、圧延機3によって延伸された長尺のレール1を長手方向に分割するための設備であり、製品としてのレール長と圧延材の長さに応じて適宜使用される。製造設備2としては、例えば、100m程度の圧延長のままで分割することなく冷却設備7に搬送される場合もあれば、1本当りの長さが例えば25m程度の長さに切断(鋸断)した後に搬送される場合もある。
冷却設備7は、オーステナイト域温度以上の高温のレール1に対し、後述する強制冷却を行う設備である。冷却設備7は、製造ライン内のレール1のパスラインに沿って設置される。
ただし、冷却設備7は、必ずしも圧延機3からの搬送ライン上に設置する構成でなくても良い。例えば、冷却設備7を、熱間圧延設備とは別のエリアに設け、熱間圧延されたレール1を、加熱炉でオーステナイト域温度以上に再加熱してから、冷却設備7に搬送する構成であってもよい。
冷却設備7は、冷却対象となるレール1の長手方向に沿って配置された複数の冷却ゾーンで構成されており、レール1の長さに応じて使用する冷却ゾーンを設定する。各冷却ゾーンの冷却条件(操業条件)は個別に設定可能となっている。
冷却設備7の詳細については、後述する。
温度計8は、冷却設備7の入口側の位置(切断機4と冷却設備7との間の位置)に設けられ、冷却開始前のレール温度を検出する。温度計8が測定した測定結果は、冷却設備7を制御する制御装置6に送られる。温度計8は、例えば、少なくともレール1の頭部の表面温度を測定する。
また、冷却設備7の下流側の位置(冷却設備7の出口側)に、強制冷却終了後のレール1表面の温度を検出するための温度計9を設置してもよい。この場合、制御装置6において予測された強制冷却終了後の温度と、温度計9が測定した温度とを比較することで、制御装置6の予測結果の妥当性を判定することができる。
冷却設備7で強制冷却されたレール1は、冷却床10に搬送される。
冷却床10は、例えば、レール1が曲がらないように矯正する役目や均一に冷却する役目がある。また、冷却床10で、製造したレール1の目視検査、重量測定などについても適宜実行される。
本実施形態の冷却設備7では、処理位置まで搬入されたレール1の頭部及び足部を、冷却ヘッダから噴射される冷却媒体によって、強制冷却する構成となっている。冷却ヘッダは、冷却ゾーン毎に設けられる。
図2は、冷却設備7が有する冷却ヘッダの配置例を、レール断面からみた模式図で示す図である。すなわち、本実施形態の冷却ヘッダは、図2に示すように、レール1の頭部101を冷却するための頭頂冷却ヘッダ71及び頭側冷却ヘッダ72と、レール1の足部103を冷却するための足裏冷却ヘッダ73とを備える。なお、必要に応じてレール1の腹部102を冷却するための腹部冷却ヘッダを更に備えてもよい。また、頭頂冷却ヘッダ71と頭側冷却ヘッダ72とを総称して「頭部冷却ヘッダ」と呼ぶ。
ここで、本実施形態の冷却設備7が採用する冷却方式は、衝風冷却とする。衝風冷却は、本発明に適した冷却速度を達成可能で、被冷却材の表面温度に対する冷却能力の変動が少ない、圧縮空気を冷却媒体として噴射する方式である。ただし、本実施形態における冷却方式は、衝風冷却に限定されるものではなく、ミスト冷却を含む水冷方式でもよい。
ここで、冷却設備7でレール1に向けて噴射される冷却媒体の噴射圧力、噴射距離、噴射位置、及び噴射時間などが制御装置6によって制御されて、冷却条件が調整可能となっている。
次に、冷却設備7による強制冷却の処理(熱処理)の原理その他に関し、説明する。
ここで、強制冷却前のレール1は、オーステナイト域温度以上に加熱されているものとする。そして、冷却設備7では、この高温のレール1に対し、冷却条件に基づき強制冷却を実行する。この強制冷却によって、レール1の表面及び内部の温度変化や変態が進行し、頭部冷却ヘッダによる冷却条件を随時変更することで、熱処理後のレール1内部の組織を制御することができる。
多段ステップ法の場合には、各ステップで冷却ヘッダの噴射流量、圧力、噴射距離を決定すると共に、次ステップへ移行するタイミングを決定する。ただし、冷却条件の変更は時間経過に対応して、必ずしも多段ステップ法を採用する必要はなく、時間経過とともに変化する冷却条件が特定できるように、冷却条件を時間の関数として設定してもよい。
ここで、レール1の素材として広く用いられる共析鋼では、オーステナイトからパーライトへの変態は概ね550℃~730℃の温度域で起こる。実際には、ベイナイトの抑制と高硬度を両立するために、570~590℃の温度域で変態させることが望ましい。
本実施形態は、硬度予測装置20を有する。硬度予測装置20は、オーステナイト域温度以上の温度となっているレール1を、冷却設備7で強制冷却を施す熱処理工程後のレール1の硬度を予測する熱処理レール1の硬度予測方法を実現するための装置である。
硬度予測装置20は、図7に示すように、基礎データ取得部21と、データベース23(記憶部)と、硬度予測モデル生成部24と、硬度予測部26とを備える。硬度予測部26は、オンラインで使用され、制御装置6に組み込まれている。
ここで、冷却設備7での冷却開始前のレール1の表面温度及び冷却設備7の操業条件を少なくとも有する冷却条件のデータの組を、冷却条件データセットと記載する。
冷却条件データセットは、冷却開始前のレール1の表面温度、及び冷却設備7の操業条件以外の、冷却のための熱処理の入力情報を含んでいても良い。
基礎データ取得部21は、オフラインでの冷却条件データセットを入力データとして、強制冷却後のレール1の少なくともレール1頭部の内部の硬度を出力データとして演算するための物理モデルである内部硬度演算モデルを有する。本実施形態では、内部硬度演算モデルを用いた数値計算の実行は、内部硬度オフライン計算部22で行われる。
そして、基礎データ取得部21は、複数の冷却条件データセットについて、個々に、内部硬度オフライン計算部22によるオフラインでの演算を実行して、入力データとしての冷却条件データセットと出力データとしての上記レール1内部の硬度情報とからなる学習用データを複数組、取得する。基礎データ取得部21は、取得した学習用データをデータベース23に格納する。
内部硬度オフライン計算部22は、図8に示すように、熱伝達係数計算部22A、熱伝導計算部22B、組織計算部22C、硬度計算部22Dを備える。この内部硬度オフライン計算部22による物理モデルに基づく硬度計算は、冷却開始から冷却終了までの計算を、熱伝達係数計算、熱伝導計算、組織計算部22Cの処理の順に行い、最終的な組織計算結果から硬度計算を行うことで求めることができる。
演算するレール1の箇所は、必ずしもレール1の表面全体に対して実行する必要はない。本実施形態の内部硬度オフライン計算部22は、少なくとも、均一の硬度が一番要求されるレール1頭部の硬度を演算する場合とする。
また、冷却条件データセットから硬度分布を求める内部硬度オフライン計算部22の計算式は、公知のモデル式を採用してもよい。
熱伝達係数計算部22Aは、熱処理中のレール1表面における熱伝達係数を計算する。本実施形態の熱伝達係数計算部22Aは、レール1頭部表面における複数箇所の熱伝達係数を演算する。
本実施形態の熱伝達係数計算部22Aは、冷却設備7の操業パラメータ及びレール形状を入力として有限体積法などの数値流体力学手法によって、レール1表面の熱伝達係数を算出する。有限体積法は、解析対象となる領域を有限個のコントロールボリュームに分割し、各ボリュームに対して積分形の物理量の保存方程式を適用する方法である。ただし、ヌッセルト数やレイノルズ数などの無次元量の関係を冷却実験から求めた強制対流に関する実験式により、熱伝達係数を算出してもよい。
熱伝導計算部22Bは、熱伝達係数計算部22Aにより算出された熱伝達係数を境界条件として、熱処理による上記レール1内部の熱伝導計算、例えばレール1の2次元断面内の熱伝導計算を行う。熱伝導計算として、例えば、断面内の温度分布を求める。
本実施形態の熱伝導計算部22Bは、熱伝達係数計算部22Aで出力されたレール1頭部表面の各位置における熱伝達係数を境界条件とし、有限要素法などの数値伝熱解析手法を用いて、冷却開始から冷却終了までのレール1内部の温度履歴(熱伝導計算)を算出する。また、熱伝導計算に必要な物性値としての熱伝導率、比熱、密度などの値は、対象とするレール1の成分組成に応じて適宜変更する。
組織計算部22Cは、熱伝導計算部22Bが算出する温度履歴計算に基づくレール1内部の温度分布から、相変態を考慮した上記レール1の断面内の組織予測を行う。断面内の組織予測は、例えば断面内の組織分布である。
ここで、温度履歴が相変態に影響を与えるだけでなく、変態発熱によって温度履歴も影響を受けることから、組織計算部22Cと上記の熱伝導計算部22Bは連成解析とすることが望ましい。組織計算部22Cにおける変態挙動の計算には、例えば、伊藤らによる方法(鉄と鋼、64(11),S806,1978年、又は鉄と鋼、65(8),A185-A188,1979年)などに記載の、公知の計算式を用いることができる。
硬度計算部22Dは、組織計算部22Cが算出した各断面の組織予測に基づく組織分布から、レール1の断面内の硬度分布を算出する。
本実施形態の硬度計算部22Dでは、化学組成や過冷度を入力とした各組織と硬度との関係式を用いて予測硬度を算出する。例えば、パーライト組織は、板状の軟質なフェライトと硬質なセメンタイトが層状をなすラメラー構造であり、ラメラー間隔と硬度の間に強い相関があることが知られており、例えば、A. R. Marderらによる方法(The Effect of Morphology on the Strength of Pearlite: Met. Trans. A, 7A (1976),365-372)を用いることができる。また、化学組成、過冷度と各組織の硬度の関係式は事前に実験などで求めた実験式を用いてもよい。
内部硬度オフライン計算部22を用いて、冷却条件データセットとして、レール1の冷却開始前の表面温度、及び冷却設備7の操業条件として冷却開始から冷却終了までの各冷却ヘッダの噴射流量、噴射圧力、噴射距離及び冷却ステップの切替えタイミングを種々変更したデータセットを生成する。また、各データセットに対応したレール1内部における硬度分布を計算した結果は、学習用データとしてデータベース23に蓄積される。
ここで、計算結果であるレール1内部の硬度分布は、レール1頭部101の断面内の各位置(断面内の座標)に対応した硬度データで表現する。ただし、硬度分布の硬度データは、連続的な値ではなく、熱伝導計算部22Bや組織計算部22Cの計算で用いた要素分割に応じた離散的な値である。
データベース23を構築する際の入力データとなる冷却条件データセットは、過去の操業実績を参照して、その範囲内で冷却条件を変化させればよい。また、冷却設備7の各冷却ヘッダの設備仕様の範囲内で、適宜計算の入力条件を変更して内部硬度オフライン計算部22による計算を行う。
格納する学習用データとしては、500個以上の入力データ(冷却条件データセット)と出力データ(硬度計算結果)の組があればよい。好ましくは2000個以上の学習用データを生成する。
硬度予測モデル生成部24では、データベース23に保存されている複数組の学習用データを用いた機械学習により、上記冷却条件データセットを少なくとも入力データとし上記強制冷却後のレール1内部の硬度に関する情報を出力データとする硬度予測モデル25を生成する。硬度予測モデル25の生成は、オフラインで実行される。
使用する機械学習モデルは、実用上必要な精度での硬度予測が可能であれば、いずれのモデルでもよい。機械学習モデルとして、例えば、一般的に用いられるニューラルネットワーク(ディープラーニングを含む)、決定木学習、ランダムフォレスト、サポートベクター回帰などを用いればよい。また複数のモデルを組み合わせたアンサンブルモデルを用いてもよい。
本実施形態のレール1の製造設備2は、図1に示すように、レール1の冷却条件を制御するための制御装置6を備える。
制御装置6は上位コンピュータ5から、レール1の形状、化学組成、目標とする硬度(内部の分布)、基準冷却条件を取得し、それを実現するための操業条件を算出して冷却制御装置へ指令を出し、冷却設備7の操業パラメータを決定する。
本実施形態における制御装置6の構成を図9に示す。
制御装置6は、図9に示すように、冷却設備7の操業条件初期設定部61、硬度予測部26、操業条件判定部62、操業条件再設定部63を備える。
操業条件初期設定部61は、目標硬度分布を満たしつつベイナイト組織やマルテンサイト組織のような異常組織を生じないように、冷却ヘッダの噴射圧力や噴射距離、噴射位置及びそれらの切替えタイミングを予め設定しておく。これらの冷却条件は、過去の操業結果に基づく経験則や特許文献1~3に示されている方法などにより、オフラインで決定しておくことができる。また、基礎データ取得部21を用いて、レール1の軌種、規格、寸法、化学組成の代表値に対して、目標硬度を得るための適正な冷却条件を予め決定し、これらの条件を冷却設備7の操業条件初期設定部61に設定してもよい。
硬度予測部26は、硬度予測モデル25を用いて求められる、上記熱処理工程の冷却条件として設定される一組の冷却条件データセットに対するレール1内部の硬度に基づき、上記熱処理工程後のレール1の硬度を予測する。
本実施形態の硬度予測部26は、冷却設備7入側の温度計8により計測されたレール1頭部の表面温度と、操業条件初期設定部61により設定された冷却ヘッダの冷却条件とを用いて、冷却条件データセットを構成する。硬度予測部26は、オンラインで生成した冷却条件データセットを入力データとして、オフラインで生成した硬度予測モデル25を用いて、熱処理終了後のレール1内部における硬度分布を予測する。
また、硬度予測部26は、操業条件再設定部63で操業条件の再設定が実行された場合は、その再設定後の情報に基づき操業条件の初期設定を更新して、再度、熱処理終了後のレール1内部における硬度分布を予測する。
操業条件判定部62は、硬度予測部26が求めたレール1内部における硬度分布を、上位コンピュータ5から受け取ったレール1内部の硬度分布の目標範囲と比較する。
ここで、レール1内部の目標硬度とは、例えば図10に示すように、JISE1120(2007)に定められている硬度範囲を満たすものとして設定することができる。ここで、JISE1120は、レール1頭部の表面硬度の上下限値及び内部硬度の上限値と所定の深さ位置(基準点)における下限値が規定されている。
ここで、基準点の位置は、表面から11mmの距離にある位置である。
ここで、レール1頭部の内部硬度は、表面から内部に向かって離れるほど低下するのが一般的な特徴である。このため、図12に示すように、レール1の表層から一定深さまでの硬度分布の目標曲線を設定し、その硬度からの差が一定の範囲に入るように設定してもよい。その際、硬度分布の目標曲線の許容範囲内では、上記JISE1120の規格を満足するものとする。
Σn i=1(Bi -BPi)2 < α ・・・(1)
操業条件判定部62は、予測されるレール1内部硬度が、予め設定された目標硬度範囲に入らない場合には、操業条件再設定部63に移行する。
操業条件再設定部63は、冷却条件を再設定する。
冷却条件の再設定は、具体的には、冷却開始から冷却終了までの各ステップにおける各冷却ヘッダの噴射流量、噴射圧力、噴射距離、冷却ステップの切替えタイミングのいずれか、又は複数の操業パラメータを再設定する。
再設定された操業パラメータは、硬度予測部26で用いられる。
これによって、予測されるレール1内部における硬度分布が、目標硬度範囲に収まるように操業パラメータの修正が実行されることになる。
ここで、冷却条件の再設定には、数回から十数回の硬度分布予測が必要となる。しかしながら、予めオフラインで学習済みモデルを生成し、その生成した学習済みモデルを用いて硬度予測をするため、一つの冷却条件データセットに対する硬度予測結果の出力が短時間で実行可能である。すなわち、数回から十数回の再計算を行っても全体としては短時間で再設定が可能である。
冷却制御部64は、硬度予測部26が求めたレール1内部における硬度分布が目標範囲と判定された操業条件で、冷却設備7での強制冷却処理を実行する。
すなわち、冷却制御部64は、目標範囲内の硬度となると予測される各冷却ヘッダの噴射流量、噴射圧力、噴射距離及び冷却ステップの切替えタイミングで強制冷却を実行する制御を行う。
ここで、冷却設備7の弁の開閉には数秒程度の時間を要する場合があり、噴射距離を変更する場合にも数秒の遅れが発生するため、各冷却ヘッダの冷却条件の変更に要する応答時間を考慮して、冷却条件の変更指令を調整してもよい。
予め物理モデルに基づく計算式で演算する内部硬度オフライン計算部22の実行をオフラインで行う。これによって、本実施形態では、伝熱解析等を用いた計算負荷が大きな処理となる、複数の冷却条件に対する強制冷却後のレール1内部の硬度分布のデータ(学習用データ)を演算する処理を、精度良く実行することができる。
更に、本実施形態では、その精度の良い多数の学習用データに基づき、冷却条件に対する強制冷却後のレール1内部の硬度分布のデータを求めるための、硬度予測モデル25を、機械学習で求める。
そして、オンラインでは、その硬度予測モデル25によって硬度の予測を実行することで、複雑な計算を行う内部硬度オフライン計算部22による硬度予測結果を極めて高速に出力することが可能となる。
(1)本実施形態は、オーステナイト域温度以上の温度となっているレール1を冷却設備7で強制冷却する熱処理工程後の上記レール1の硬度を予測するレール1の硬度予測方法であって、冷却開始前のレール1の表面温度と強制冷却のための上記冷却設備7の操業条件とを少なくとも有する冷却条件データセットを入力データとして、上記強制冷却後のレール1の少なくともレール1頭部の内部の硬度を出力データとして演算するための物理モデルである内部硬度演算モデルを用いて、上記冷却条件データセットと上記硬度の出力データとからなる学習用データを複数組、取得しておき、取得した複数組の学習用データを用いた機械学習により、上記冷却条件データセットを少なくとも入力データとし上記強制冷却後のレール1内部の硬度を出力データとする硬度予測モデル25を予め生成し、上記硬度予測モデル25を用いて求められる、上記熱処理工程の冷却条件として設定される一組の冷却条件データセットに対するレール1内部の硬度に基づき、上記熱処理工程後のレール1の硬度を予測する。
この構成によれば、より確実に熱処理のための硬度予測が可能となる。
この構成によれば、より確実に熱処理のための硬度予測が可能となる。
この構成によれば、レール1内部の硬度を目標硬度範囲とする操業条件を、より確実に設定可能となる。
この構成によれば、レール1内部の硬度を目標硬度範囲とする操業条件を、より細かく設定可能となる。
上記硬度予測モデル25は、例えば、ニューラルネットワークモデル(ディープラーニングのモデルを含む)、ランダムフォレスト、又はSVM回帰で学習されたモデルとすればよい。
この構成によれば、少なくともレール頭部の表層が硬度の均一性に優れたレールを製造するための情報を高精度で得ることが可能となる。
この構成によれば、少なくともレール頭部の表層が硬度の均一性に優れたレールを製造可能となる。
レール1の製造設備2(図1参照)を用いて、熱処理レール1の製造を行った。
本実施例では、複数軌種、規格のレール1の強制冷却を行い、室温まで空冷した後で頭部の組織及び断面内の硬度分布を評価した。なお、各実施例、各比較例において、それぞれ20本ずつの熱処理レール1を製造し、それぞれのばらつきを評価した。
対象としたレール1は、軌種2種類(JIS60kgレールと50kgNレール)と規格2種類(高硬度レールHと通常硬度レールL)の合計4種類とした。そして、約900℃で熱間圧延を終了した後、圧延長のまま(切断することなく)、オンラインに設置された冷却設備7で強制冷却を行った。なお、本実施例に用いた鋼種のオーステナイト温度は760℃、平衡変態温度が720℃であった。
冷却条件としては2ステップ法による冷却として、前段ステップと後段ステップにおける噴射圧の設定値及び、前段ステップから後段ステップへの切替え時間については、それぞれ熱処理を行うレール1の種類に応じて設定した(表中「固定」として基準となる条件を表す)。
このとき、実際の操業では、入側温度計8による温度測定値と上記目標温度との間には、20本のレール1毎のばらつきと、1本レール内の位置による温度ばらつきを合わせて、-30~+10℃のばらつきが生じていた。
表1に、実験条件及び評価結果を示す。
一方、比較例では、冷却設備7の入側温度が目標温度に近かった条件では熱処理が適切に行われ目標通りの硬度と組織が得られたが、目標温度から外れたものは硬度のばらつきが大きく、異常組織の生成が見られるものもあった。
2 製造設備
3 圧延機
4 切断機
5 上位コンピュータ
6 制御装置
7 冷却設備
8 温度計
10 冷却床
11 加熱炉
20 硬度予測装置
21 基礎データ取得部
22 内部硬度オフライン計算部
22A 熱伝達係数計算部
22B 熱伝導計算部
22C 組織計算部
22D 硬度計算部
23 データベース
24 硬度予測モデル生成部
25 硬度予測モデル
26 硬度予測部
61 操業条件初期設定部
62 操業条件判定部
63 操業条件再設定部
64 冷却制御部
71 頭頂冷却ヘッダ
72 頭側冷却ヘッダ
73 足裏冷却ヘッダ
74 頭部温度計
75 足部温度計
Claims (16)
- オーステナイト域温度以上の温度となっているレールを冷却設備で強制冷却する熱処理工程後の上記レールの硬度を予測するレールの硬度予測方法であって、
冷却開始前のレールの表面温度と強制冷却のための上記冷却設備の操業条件とを少なくとも有する冷却条件データセットを入力データとして、上記強制冷却後のレールの少なくともレール頭部の内部の硬度を出力データとして演算するための物理モデルである内部硬度演算モデルを用いて、上記冷却条件データセットと上記硬度の出力データとからなる学習用データを複数組、取得しておき、
取得した複数組の学習用データを用いた機械学習により、上記冷却条件データセットを少なくとも入力データとし上記強制冷却後のレール内部の硬度に関する情報を出力データとする硬度予測モデルを予め生成し、
上記硬度予測モデルを用いて求められる、上記熱処理工程の冷却条件として設定される一組の冷却条件データセットに対するレール内部の硬度に関する情報に基づき、上記熱処理工程後のレールの硬度を予測する、
ことを特徴とする熱処理レールの硬度予測方法。 - 上記内部硬度演算モデルを用いて演算される出力データは、少なくともレール表面から予め設定した深さまでの領域における硬度分布であることを特徴とする請求項1に記載した熱処理レールの硬度予測方法。
- 上記内部硬度演算モデルは、
上記冷却設備を用いた熱処理の際のレール表面の熱伝達係数を計算する熱伝達係数計算部と、
上記熱伝達係数計算部が算出した熱伝達係数を境界条件として、上記熱処理による上記レール内部の温度履歴計算を行う熱伝導計算部と、
上記熱伝導計算部が算出した温度履歴計算に基づくレール内部の温度分布から、相変態を考慮したレール内部の組織予測を行う組織計算部と、
上記組織計算部が算出したレール内部の組織予測に基づくレール内部の組織分布から、レール内部の硬度を算出する硬度計算部と、
を備えることを特徴とする請求項1又は請求項2に記載した熱処理レールの硬度予測方法。 - オーステナイト域温度以上の温度になっているレールを冷却設備で強制冷却する熱処理工程を有する熱処理レールの熱処理方法であって、
冷却開始前のレールの表面温度を測定し、
上記冷却設備でのレールの冷却開始前に、測定したレールの表面温度を用いて、請求項1~請求項3のいずれか1項に記載の熱処理レールの硬度予測方法によって、レール内部の硬度を予測し、
予測したレール内部の硬度が目標とする硬度の範囲外の場合、予測したレール内部の硬度が目標とする硬度の範囲内に収まるように、上記冷却設備の操業条件を再設定することを特徴とする熱処理レールの熱処理方法。 - 上記再設定する冷却設備の操業条件は、上記冷却設備でレールに向けて噴射される冷却媒体の噴射圧力、噴射距離、噴射位置、及び噴射時間のうち、少なくとも一つの操業条件を含むことを特徴とする請求項4に記載した熱処理レールの熱処理方法。
- 上記冷却設備は、冷却対象のレールの長手方向に沿って配置された複数の冷却ゾーンを有し、
上記冷却設備の操業条件の再設定は、その各冷却ゾーン毎に個別に操業条件の再設定を実行することを特徴とする請求項4又は請求項5に記載した熱処理レールの熱処理方法。 - オーステナイト域温度以上の温度となっているレールを冷却設備で強制冷却した後の上記レールの硬度を、上記冷却設備での冷却開始前のレールの表面温度と強制冷却のための上記冷却設備の操業条件とを少なくとも有する冷却条件データセットから求めるための硬度予測モデルの生成方法であって、
上記冷却条件データセットを入力データとして、上記強制冷却後のレールの少なくともレール頭部の内部の硬度を出力データとして演算するための物理モデルである内部硬度演算モデルを用いて、上記冷却条件データセットと上記硬度の出力データとからなる学習用データを複数組、取得し、
取得した複数組の学習用データを用いた機械学習により、上記冷却条件データセットを少なくとも入力データとし上記強制冷却後のレール内部の硬度に関する情報を出力データとする硬度予測モデルを予め生成する、
ことを特徴とする硬度予測モデルの生成方法。 - 上記内部硬度演算モデルを用いて演算される出力データは、少なくともレール表面から予め設定した深さまでの領域における硬度分布であることを特徴とする請求項7に記載した硬度予測モデルの生成方法。
- 上記硬度予測モデルは、ニューラルネットワークモデル、ランダムフォレスト、又はSVM回帰で学習されたモデルであることを特徴とする請求項7又は請求項8に記載した硬度予測モデルの生成方法。
- 請求項4~請求項6のいずれ1項に記載の熱処理レールの熱処理方法を有する、熱処理レールの製造方法。
- オーステナイト域温度以上の温度となっているレールを冷却設備で強制冷却する熱処理工程後の上記レールの硬度を予測するレールの硬度予測装置であって、
冷却開始前のレールの表面温度と強制冷却のための上記冷却設備の操業条件とを少なくとも有する冷却条件データセットを入力データとして、上記強制冷却後のレールの少なくともレール頭部の内部の硬度を出力データとして演算するための物理モデルである内部硬度演算モデルを用いて演算した、上記冷却条件データセットと上記硬度の出力データとからなる学習用データを複数組、格納しているデータベースと、
上記複数組の学習用データを用いた機械学習により、上記冷却条件データセットを少なくとも入力データとし上記強制冷却後のレール内部の硬度に関する情報を出力データとする硬度予測モデルを生成する硬度予測モデル生成部と、
冷却開始前のレールの表面温度を測定する温度計と、
上記温度計が測定した測定値と上記硬度予測モデルを用いて、上記熱処理工程の冷却条件として設定される一組の冷却条件データセットに対するレール内部の硬度に関する情報に基づき、上記熱処理工程後のレールの硬度を予測する硬度予測部と、
を備えることを特徴とする熱処理レールの硬度予測装置。 - 上記内部硬度演算モデルを用いて演算される出力データは、少なくともレール表面から予め設定した深さまでの領域における硬度分布であることを特徴とする請求項11に記載した熱処理レールの硬度予測装置。
- 上記内部硬度演算モデルは、
上記冷却設備を用いた熱処理の際のレール表面の熱伝達係数を計算する熱伝達係数計算部と、
上記熱伝達係数計算部が算出した熱伝達係数を境界条件として、上記熱処理による上記レール内部の温度履歴計算を行う熱伝導計算部と、
上記熱伝導計算部が算出した温度履歴計算に基づくレール内部の温度分布から、相変態を考慮したレール内部の組織予測を行う組織計算部と、
上記組織計算部が算出したレール内部の組織予測に基づくレール内部の組織分布から、レール内部の硬度を算出する硬度計算部と、
を備えることを特徴とする請求項11又は請求項12に記載した熱処理レールの硬度予測装置。 - オーステナイト域温度以上の温度になっているレールを冷却設備で強制冷却する熱処理工程を有するレールの熱処理装置であって、
上記冷却設備でのレールの冷却開始前に、請求項11~請求項13のいずれか1項に記載の熱処理レールの硬度予測装置によって、レール内部の硬度を予測する硬度予測部と、
上記硬度予測部が予測したレール内部の硬度が目標とする硬度の範囲外の場合、予測したレール内部の硬度が目標とする硬度の範囲内に収まるように、上記冷却設備の操業条件を再設定する操業条件再設定部と、
を備えることを特徴とする熱処理レールの熱処理装置。 - 上記再設定する冷却設備の操業条件は、上記冷却設備でレールに向けて噴射される冷却媒体の噴射圧力、噴射距離、噴射位置、及び噴射時間のうち、少なくとも一つの操業条件を含むことを特徴とする請求項14に記載した熱処理レールの熱処理装置。
- 請求項14又は請求項15に記載の熱処理レールの熱処理装置を備える熱処理レールの製造設備。
Priority Applications (7)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202180041784.0A CN115917288A (zh) | 2020-06-10 | 2021-03-08 | 热处理轨道的硬度预测方法、热处理方法、硬度预测装置、热处理装置、制造方法、制造设备、以及硬度预测模型的生成方法 |
EP21820925.2A EP4166682A4 (en) | 2020-06-10 | 2021-03-08 | METHOD FOR PREDICTING HARDNESS OF HEAT-TREATED RAIL, HEAT-TREATING METHOD, HARDNESS PREDICTING DEVICE, HEAT-TREATING DEVICE, MANUFACTURING METHOD, MANUFACTURING FACILITIES, AND METHOD FOR GENERATING HARDNESS PREDICTION MODEL |
CA3186874A CA3186874A1 (en) | 2020-06-10 | 2021-03-08 | Hardness prediction method of heat hardened rail, thermal treatment method, hardness prediction device, thermal treatment device, manufacturing method, manufacturing facilities, and generating method of hardness prediction model |
BR112022025159A BR112022025159A2 (pt) | 2020-06-10 | 2021-03-08 | Método de previsão de dureza de trilho tratado termicamente, método de tratamento térmico, dispositivo de previsão de dureza, dispositivo de tratamento térmico, método de fabricação, instalações de fabricação, e método de geração de modelo de previsão de dureza |
AU2021288876A AU2021288876B2 (en) | 2020-06-10 | 2021-03-08 | Hardness prediction method of heat hardened rail, thermal treatment method, hardness prediction device, thermal treatment device, manufacturing method, manufacturing facilities, and generating method of hardness prediction model |
KR1020227042338A KR20230005985A (ko) | 2020-06-10 | 2021-03-08 | 열처리 레일의 경도 예측 방법, 열처리 방법, 경도 예측 장치, 열처리 장치, 제조 방법, 제조 설비, 및 경도 예측 모델의 생성 방법 |
US18/009,523 US20230221231A1 (en) | 2020-06-10 | 2021-03-08 | Hardness prediction method of heat hardened rail, thermal treatment method, hardness prediction device, thermal treatment device, manufacturing method, manufacturing facilities, and generating method of hardness prediction model |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2020100895A JP7294243B2 (ja) | 2020-06-10 | 2020-06-10 | 熱処理レールの硬度予測方法、熱処理方法、硬度予測装置、熱処理装置、製造方法、製造設備、並びに、硬度予測モデルの生成方法 |
JP2020-100895 | 2020-06-10 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2021250957A1 true WO2021250957A1 (ja) | 2021-12-16 |
Family
ID=78845487
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/JP2021/009060 WO2021250957A1 (ja) | 2020-06-10 | 2021-03-08 | 熱処理レールの硬度予測方法、熱処理方法、硬度予測装置、熱処理装置、製造方法、製造設備、並びに、硬度予測モデルの生成方法 |
Country Status (9)
Country | Link |
---|---|
US (1) | US20230221231A1 (ja) |
EP (1) | EP4166682A4 (ja) |
JP (1) | JP7294243B2 (ja) |
KR (1) | KR20230005985A (ja) |
CN (1) | CN115917288A (ja) |
AU (1) | AU2021288876B2 (ja) |
BR (1) | BR112022025159A2 (ja) |
CA (1) | CA3186874A1 (ja) |
WO (1) | WO2021250957A1 (ja) |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH09227942A (ja) * | 1996-02-27 | 1997-09-02 | Nkk Corp | レールの熱処理方法 |
JP2005315703A (ja) * | 2004-04-28 | 2005-11-10 | Nippon Steel Corp | 鋼材の材質予測方法 |
JP2015523467A (ja) * | 2012-06-11 | 2015-08-13 | シーメンス ソシエタ ペル アツィオーニSiemens S.p.A. | レールの熱処理のための方法及びシステム |
JP2020100895A (ja) | 2018-12-19 | 2020-07-02 | ユニチカ株式会社 | 鉄ニッケルナノワイヤーの製造方法 |
Family Cites Families (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
DE1492461A1 (de) | 1964-11-30 | 1970-02-12 | American Sterilizer Co | Sterilisierverfahren |
JPS58140029A (ja) | 1982-02-15 | 1983-08-19 | Toyo Soda Mfg Co Ltd | エチレンのオキシ塩素化法 |
JPS61149436A (ja) | 1984-12-24 | 1986-07-08 | Nippon Steel Corp | レ−ルの熱処理方法 |
DE102012020844A1 (de) * | 2012-10-24 | 2014-04-24 | Thyssenkrupp Gft Gleistechnik Gmbh | Verfahren zur thermomechanischen Behandlung von warmgewalzten Profilen |
CN105074019B (zh) | 2013-03-28 | 2017-03-08 | 杰富意钢铁株式会社 | 钢轨的制造方法和制造装置 |
-
2020
- 2020-06-10 JP JP2020100895A patent/JP7294243B2/ja active Active
-
2021
- 2021-03-08 CA CA3186874A patent/CA3186874A1/en active Pending
- 2021-03-08 EP EP21820925.2A patent/EP4166682A4/en active Pending
- 2021-03-08 US US18/009,523 patent/US20230221231A1/en active Pending
- 2021-03-08 BR BR112022025159A patent/BR112022025159A2/pt unknown
- 2021-03-08 CN CN202180041784.0A patent/CN115917288A/zh active Pending
- 2021-03-08 KR KR1020227042338A patent/KR20230005985A/ko unknown
- 2021-03-08 AU AU2021288876A patent/AU2021288876B2/en active Active
- 2021-03-08 WO PCT/JP2021/009060 patent/WO2021250957A1/ja active Application Filing
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH09227942A (ja) * | 1996-02-27 | 1997-09-02 | Nkk Corp | レールの熱処理方法 |
JP2005315703A (ja) * | 2004-04-28 | 2005-11-10 | Nippon Steel Corp | 鋼材の材質予測方法 |
JP2015523467A (ja) * | 2012-06-11 | 2015-08-13 | シーメンス ソシエタ ペル アツィオーニSiemens S.p.A. | レールの熱処理のための方法及びシステム |
JP2020100895A (ja) | 2018-12-19 | 2020-07-02 | ユニチカ株式会社 | 鉄ニッケルナノワイヤーの製造方法 |
Non-Patent Citations (5)
Title |
---|
"Heat Transfer Engineering Material", 2009, JAPAN SOCIETY OF MECHANICAL ENGINEERS |
A. R. MARDER ET AL., THE EFFECT OF MORPHOLOGY ON THE STRENGTH OF PEARLITE: MET. TRANS. A, vol. 7A, 1976, pages 365 - 372 |
IRON AND STEEL, vol. 65, no. 8, 1979, pages A185 - A188 |
ITO ET AL., IRON AND STEEL, vol. 64, no. 11, 1978, pages S806 |
See also references of EP4166682A4 |
Also Published As
Publication number | Publication date |
---|---|
US20230221231A1 (en) | 2023-07-13 |
AU2021288876A1 (en) | 2023-01-19 |
JP7294243B2 (ja) | 2023-06-20 |
AU2021288876B2 (en) | 2024-01-04 |
EP4166682A4 (en) | 2023-11-29 |
CA3186874A1 (en) | 2021-12-16 |
CN115917288A (zh) | 2023-04-04 |
KR20230005985A (ko) | 2023-01-10 |
EP4166682A1 (en) | 2023-04-19 |
BR112022025159A2 (pt) | 2022-12-27 |
JP2021195577A (ja) | 2021-12-27 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
RU2637197C2 (ru) | Способ и система для термической обработки рельсов | |
JP6658895B2 (ja) | レールの冷却装置及び製造方法 | |
JP6068146B2 (ja) | 設定値計算装置、設定値計算方法、及び設定値計算プログラム | |
Du et al. | Construction of a machine-learning-based prediction model for mechanical properties of ultra-fine-grained Fe–C alloy | |
JP2014000593A (ja) | 熱延鋼板の温度むら予測方法、平坦度制御方法、温度むら制御方法、及び、製造方法 | |
JP6558060B2 (ja) | 厚鋼板の冷却制御方法、冷却制御装置、製造方法、および、製造装置 | |
WO2021250957A1 (ja) | 熱処理レールの硬度予測方法、熱処理方法、硬度予測装置、熱処理装置、製造方法、製造設備、並びに、硬度予測モデルの生成方法 | |
Lee et al. | Review of accelerated cooling of steel plate | |
JP7287416B2 (ja) | 厚鋼板の製造仕様決定支援装置および製造仕様探索方法、コンピュータプログラム、コンピュータ読み取り可能な記録媒体ならびに厚鋼板の製造方法 | |
Ogoltcov et al. | Practical Use of Computer Model STAN 2000 for Improvement and Creation of Regimes for Hot Rolling of Steels on SEVERSTAL Mill 2000 | |
JP5482365B2 (ja) | 鋼板の冷却方法、製造方法および製造設備 | |
EP3626358A1 (en) | Device and method for cooling steel material | |
Kundu et al. | Modelling of microstructure and heat transfer during controlled cooling of low carbon wire rod | |
JP7513046B2 (ja) | 表層硬度予測モデル及びこれを用いた鋼板の表層硬度を予測制御する方法、制御指令装置、鋼板製造ライン、並びに鋼板製造方法 | |
WO2022209320A1 (ja) | 鋼板の材質予測モデルの生成方法、材質予測方法、製造方法、及び製造設備 | |
JP7556027B2 (ja) | 鋼板の形状予測方法、形状制御方法、製造方法、形状予測モデルの生成方法、及び製造設備 | |
Ogoltcov et al. | Computer model STAN 2000 and its use in practice of steels hot rolling on mill 2000 of Severstal | |
WO2024189790A1 (ja) | 圧延製品の材質特性予測装置 | |
JP2010221270A (ja) | 熱間圧延設備における圧延材水冷方法 | |
Mukhopadhyay et al. | Automation systems for heat treatment and controlled cooling of plates and bars | |
Nardini | Development of a thermomechanical and metallurgical model in order to design a predictive control tool in line | |
Alexey1a et al. | Practical Use of Computer Model STAN 2000 for Improvement and Creation of Regimes for Hot Rolling of Steels on SEVERSTAL Mill 2000. |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 21820925 Country of ref document: EP Kind code of ref document: A1 |
|
ENP | Entry into the national phase |
Ref document number: 20227042338 Country of ref document: KR Kind code of ref document: A |
|
ENP | Entry into the national phase |
Ref document number: 3186874 Country of ref document: CA |
|
WWE | Wipo information: entry into national phase |
Ref document number: 202217071319 Country of ref document: IN |
|
REG | Reference to national code |
Ref country code: BR Ref legal event code: B01A Ref document number: 112022025159 Country of ref document: BR |
|
ENP | Entry into the national phase |
Ref document number: 112022025159 Country of ref document: BR Kind code of ref document: A2 Effective date: 20221208 |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
ENP | Entry into the national phase |
Ref document number: 2021820925 Country of ref document: EP Effective date: 20230110 |
|
ENP | Entry into the national phase |
Ref document number: 2021288876 Country of ref document: AU Date of ref document: 20210308 Kind code of ref document: A |