CN115161445B - Method for optimizing medium-frequency induction heating local postweld heat treatment parameters of 9% Cr hot-strength steel pipeline - Google Patents
Method for optimizing medium-frequency induction heating local postweld heat treatment parameters of 9% Cr hot-strength steel pipeline Download PDFInfo
- Publication number
- CN115161445B CN115161445B CN202210769813.1A CN202210769813A CN115161445B CN 115161445 B CN115161445 B CN 115161445B CN 202210769813 A CN202210769813 A CN 202210769813A CN 115161445 B CN115161445 B CN 115161445B
- Authority
- CN
- China
- Prior art keywords
- heat treatment
- temperature gradient
- model
- parameters
- heating
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000010438 heat treatment Methods 0.000 title claims abstract description 224
- 238000000034 method Methods 0.000 title claims abstract description 57
- 230000006698 induction Effects 0.000 title claims abstract description 49
- 229910000831 Steel Inorganic materials 0.000 title claims abstract description 18
- 239000010959 steel Substances 0.000 title claims abstract description 18
- 238000003466 welding Methods 0.000 claims abstract description 47
- 238000012360 testing method Methods 0.000 claims abstract description 30
- 230000008569 process Effects 0.000 claims abstract description 21
- 238000005457 optimization Methods 0.000 claims abstract description 20
- 238000004364 calculation method Methods 0.000 claims abstract description 17
- 230000002068 genetic effect Effects 0.000 claims abstract description 16
- 230000001052 transient effect Effects 0.000 claims abstract description 14
- 238000012549 training Methods 0.000 claims abstract description 13
- 238000003062 neural network model Methods 0.000 claims abstract description 8
- 238000004321 preservation Methods 0.000 claims description 34
- 239000013598 vector Substances 0.000 claims description 21
- 238000013528 artificial neural network Methods 0.000 claims description 16
- 238000012546 transfer Methods 0.000 claims description 7
- 230000008878 coupling Effects 0.000 claims description 6
- 238000010168 coupling process Methods 0.000 claims description 6
- 238000005859 coupling reaction Methods 0.000 claims description 6
- 230000005284 excitation Effects 0.000 claims description 4
- 238000004458 analytical method Methods 0.000 claims description 3
- 238000005452 bending Methods 0.000 claims description 3
- 239000006185 dispersion Substances 0.000 claims description 3
- 230000035772 mutation Effects 0.000 claims description 3
- 238000010586 diagram Methods 0.000 description 3
- 239000000463 material Substances 0.000 description 3
- 239000010953 base metal Substances 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000006378 damage Effects 0.000 description 2
- 238000012795 verification Methods 0.000 description 2
- 238000007792 addition Methods 0.000 description 1
- 239000000919 ceramic Substances 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000004134 energy conservation Methods 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 230000017525 heat dissipation Effects 0.000 description 1
- 238000009413 insulation Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000003647 oxidation Effects 0.000 description 1
- 238000007254 oxidation reaction Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000003685 thermal hair damage Effects 0.000 description 1
Classifications
-
- 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
- C21D1/34—Methods of heating
- C21D1/42—Induction heating
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/23—Design optimisation, verification or simulation using finite element methods [FEM] or finite difference methods [FDM]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/12—Computing arrangements based on biological models using genetic models
- G06N3/126—Evolutionary algorithms, e.g. genetic algorithms or genetic programming
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2111/00—Details relating to CAD techniques
- G06F2111/06—Multi-objective optimisation, e.g. Pareto optimisation using simulated annealing [SA], ant colony algorithms or genetic algorithms [GA]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/08—Thermal analysis or thermal optimisation
-
- 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
Abstract
The invention discloses a method for optimizing heat treatment parameters after local welding of a 9% Cr hot-strength steel pipeline in medium-frequency induction heating. The method comprises the following steps: analyzing the influence of different heat treatment parameters on radial and axial temperature gradients of the pipeline by performing intermediate frequency induction heating post-heat treatment tests under different heat treatment parameter combinations, and finding out core parameters influencing the temperature gradients; meanwhile, a medium-frequency induction heating post-heat treatment finite element transient state and steady state temperature field calculation model is established, the maximum axial temperature gradient and the radial temperature gradient in the constant temperature stage in the heat treatment process are calculated, a BP neural network model of genetic algorithm parameter adjustment is established, training is carried out, and finally, the input pipeline specification, the maximum axial temperature gradient and the radial temperature gradient are realized, namely, the heat treatment parameter optimization of pipelines with different specifications is completed. The invention can obtain the optimal heat treatment parameter combination on the basis of ensuring the axial and radial temperature gradients, thereby not only ensuring the heat treatment quality, but also improving the engineering efficiency and saving the cost.
Description
Technical Field
The invention belongs to the technical field of heat-resistant steel welding, and particularly relates to an optimization method for an optimal combination of heat treatment parameters after medium-frequency induction heating welding of 9% Cr heat-resistant steel pipelines, which can be suitable for optimizing the heat treatment parameters after medium-frequency induction heating welding of novel 9% Cr steel pipelines with different specifications such as P91, P92, P93 and G115.
Background
The novel 9% Cr heat-strength steel is an ideal material for manufacturing important thick-wall parts such as a header, a main steam pipe and the like of a super (super) critical thermal power unit due to good heat conductivity, high-temperature oxidation resistance and high-temperature creep resistance. The thermal generator set pipeline structure is complex, the pipeline connection is usually carried out by adopting a fusion welding method, the instantaneous high temperature generated in the welding process is concentrated at the welding position, the pipeline joint structure is easy to deteriorate, the mechanical property is poor, and meanwhile, the safety operation of the parts is also influenced due to the residual stress generated by the temperature gradient between the welding joint and the nearby area. Therefore, the novel 9% Cr hot strength steel pipe must be heat treated after welding. The conventional local postweld heat treatment method used in field welding is flexible ceramic resistance heating, and has the defects of low heating power, low heating rate, poor heating uniformity and large thermal damage to a base metal. The intermediate frequency induction heating heat treatment method has the advantages of high heating speed, good heating uniformity and small damage to the base metal, and is applied to the postweld heat treatment of the novel 9% Cr steel thick-wall pipeline in recent years.
In the intermediate frequency induction heating post-heat treatment process, the induction coil generates induction current on the outer surface of the pipeline, the induction current generates joule heat to heat the outer wall of the pipeline, and heat is transferred to the inner wall and other parts of the pipeline by a heat transfer method, so that a certain temperature gradient exists in the axial direction and the radial direction of the pipeline. Because the temperature constant interval of the heat treatment of the novel 9% Cr heat-strength steel is narrower, the heat treatment temperature of the inner wall is insufficient due to the overlarge radial temperature gradient, and the heat treatment quality is affected; and the excessive axial temperature gradient can generate new residual stress to influence the safe service of the pipeline. In order to meet the control requirements of the temperature gradient, the combination of post-weld heat treatment parameters (heating width, heat preservation width, alternating current frequency, etc.) must be optimized. Although the power industry standard DL/T819-2019 recommends a method for selecting part of heat treatment parameters, according to related researches, the recommended heating width is often larger, the heating rate is often smaller, and recommended values for parameters such as alternating current frequency, coil turns, coil gaps and the like are not given, so that the selection of parameters such as heating width, heat preservation width, heating rate, alternating current frequency, coil turns, coil gaps and the like in engineering is too conservative, and the heat treatment cost is increased. Therefore, it is necessary to invent a novel optimization method for the heat treatment parameters after the local welding of the medium-frequency induction heating of the 9% Cr heat-strength steel pipeline, and the precise selection of the heat treatment parameters during the on-site welding construction is guided.
Disclosure of Invention
The invention aims to provide an optimization method for the medium-frequency induction heating local postweld heat treatment parameters of a 9% Cr hot-strength steel pipeline, which obtains the optimal heat treatment parameter combination, guides engineering application and reduces the heat treatment cost under the condition of ensuring the heat treatment quality.
In order to solve the technical problems, the invention adopts the following technical scheme:
the method for optimizing the heat treatment parameters after the local welding of the medium-frequency induction heating of the 9% Cr heat-resistant steel pipeline comprises the following steps:
step 1, performing medium frequency induction heating post-heat treatment tests of N groups of pipelines with different specifications under different heat treatment parameters, recording the temperatures of different characteristic points at different times, analyzing the influence of different heat treatment parameters on radial and axial temperature gradients of the pipelines through a comparison test, and obtaining main parameters affecting the temperature gradients, wherein the main parameters are as follows: pipe diameter, pipe wall thickness, heating width, heat preservation width, alternating current frequency;
step 2, establishing and verifying a medium-frequency induction post-heat-welding heat treatment temperature field model according to the post-welding heat treatment test data obtained in the step 1, and calculating radial and axial temperature gradients of pipelines with different specifications under different heating widths, heat preservation widths and alternating current frequencies according to the temperature field model;
and 3, determining an optimization principle, namely that the axial temperature gradient is smaller than 2.1, the radial temperature gradient is smaller than 1.027, combining the optimization principle according to the calculation result obtained in the step 2, taking the pipeline specification, the pipeline radial direction, the axial temperature gradient and the radial temperature gradient as input vectors, taking the heating width, the heat preservation width and the alternating current frequency as output vectors, establishing a BP neural network model subjected to genetic algorithm parameter adjustment, and finally optimizing the parameters of the local post-welding heat treatment of the pipeline medium-frequency induction heating of different specifications through the model.
According to the above scheme, the feature points in the step 1 are as follows: the center point of the inner wall and the outer wall of the pipeline welding seam and the edge of the heating area of the outer wall.
According to the above scheme, the different heat treatment parameters in the step 1 are respectively: heating width, number of turns of induction coil, heat preservation width, alternating current frequency, gap between coil and heat preservation layer, alternating current size, temperature rise and fall speed and constant temperature time.
According to the above scheme, in the step 2, the specification of the 9% cr heat-strength steel pipeline is selected as follows: pipe inside diameter: 300-1200mm, wall thickness of pipeline: 30-140 mm; the alternating current frequency is 1kHz-8kHz, and the heating width and the heat preservation width are selected according to the DL/L-819 standard.
According to the above scheme, in the step 3, the method for determining the optimization principle is as follows: the maximum allowable radial temperature gradient is determined to be 1.027 and the maximum allowable axial temperature gradient is determined to be 2.1 according to the temperature difference between the inner wall and the outer wall and the control of the maximum bending stress.
According to the above scheme, in the step 1, intermediate frequency induction heating local postweld heat treatment tests under different heat treatment parameters are respectively performed to obtain main parameters affecting the temperature gradient, and the specific method is as follows:
step 1.1, under the condition of keeping other heat treatment parameters unchanged, selecting 3 groups of different heating widths by adjusting the coil turn spacing of an induction coil, and reading the temperatures of the center point of the inner wall and the outer wall of a pipeline welding seam and the edge of a heating zone of the outer wall in real time to obtain the maximum axial temperature gradient in the heat treatment process and the radial temperature gradient when the heat treatment reaches a constant temperature steady state;
step 1.2, under the condition of keeping other heat treatment parameters unchanged, selecting 3 groups of different turns of induction coils by adjusting the turn intervals of the induction coils, and reading the temperatures of the central point of the inner wall and the outer wall of the pipeline welding seam and the edge of the heating zone of the outer wall in real time to obtain the maximum axial temperature gradient in the heat treatment process and the radial temperature gradient when the heat treatment reaches a constant temperature steady state;
step 1.3, respectively selecting 3 groups of different heat preservation width, alternating current frequency, coil-heat preservation layer clearance, alternating current size, temperature rise and fall speed and constant temperature time parameters under the condition of keeping other heat treatment parameters unchanged, and reading the center point of the inner wall and the outer wall of the pipeline welding seam and the edge temperature of the heating zone of the outer wall in real time to obtain the maximum axial temperature gradient in the heat treatment process and the radial temperature gradient when the heat treatment reaches a constant temperature steady state;
step 1.4, according to the test results of the steps 1.1-1.3, obtaining heat treatment parameters which have obvious influence on the maximum axial temperature gradient in the heat treatment process and the radial temperature gradient when the heat treatment reaches a constant temperature steady state, specifically: heating width, heat preservation width and alternating current frequency.
According to the above scheme, in the step 2, according to the post-welding heat treatment test data obtained in the step 1, a medium frequency induction heating post-welding heat treatment temperature field model is established, verification is performed, and finally, the maximum axial temperature gradient in the heat treatment process and the radial temperature gradient when the heat treatment reaches a constant temperature steady state under different heat treatment parameters are calculated through the model, and the specific method is as follows:
step 2.1, coupling by utilizing an electromagnetic model and a heat transfer model through finite element software, inputting transient time domain excitation to obtain a transient model of post-welding heat treatment, reading a maximum axial temperature gradient in the heat treatment process according to the transient model, verifying with a test result, adjusting related calculation parameters if the error is greater than 1%, and carrying out the next step if the error is less than 1%;
step 2.2, coupling by utilizing an electromagnetic model and a heat transfer model through finite element software, carrying out steady-state solving to obtain a steady-state model of post-welding heat treatment, reading radial temperature gradient when the heat treatment reaches a constant-temperature steady state according to the steady-state model, verifying with a test result, adjusting related calculation parameters if the error is greater than 1%, and carrying out the next step if the error is less than 1%;
and 2.3, calculating the magnitudes of axial temperature gradients and radial temperature gradients of N groups of pipelines with different specifications according to the transient model and the steady-state model of the postweld heat treatment temperature field in the steps 2.1 and 2.2 under different heating widths, heat preservation widths and alternating current frequencies.
According to the above scheme, in the step 3, according to the calculation result obtained in the step 2, a BP neural network model for parameter adjustment by genetic algorithm is established, and an optimization method for optimal combination of heat treatment parameters after medium-frequency induction heating welding of pipelines with different specifications is obtained by the model, and the specific method is as follows:
step 3.1, optimizing the weight and the threshold value of the BP neural network through a genetic algorithm, and obtaining the weight and the threshold value suitable for the BP neural network through adjusting the population scale, the individual range, the crossover and mutation probability and the iteration times of the genetic algorithm;
step 3.2, normalizing the calculation result in the step 2, taking the pipeline specification, the pipeline radial and axial temperature gradients as input vectors, taking the heating width, the heat preservation width and the alternating current frequency as output vectors, and selecting a B group as training data and the rest C group as test data from the input vectors and the output vectors which are in one-to-one correspondence;
step 3.3, setting a BP neural network by using the weight and the threshold value obtained in the step 3.1, setting expected errors and dispersion constants, inputting the training data of the group B into the BP neural network, training the network, and finally inputting the test data of the group C into the trained model for error analysis, wherein if the errors reach a specified level, the obtained model is the optimal selection model of the required optimal technological parameters; if the error is larger, returning to the step 3.1, and readjusting the related parameters of the genetic algorithm;
and 3.4, inputting the pipe diameter and the wall thickness of the target pipeline in the model, and selecting a radial temperature gradient and an axial temperature gradient to be controlled according to an optimization principle to obtain the optimal medium-frequency induction heating local postweld heat treatment parameter combination.
The beneficial effects of the invention are as follows:
the invention provides an optimization method of heat treatment parameters after medium-frequency induction heating local welding of 9% Cr heat-strength steel pipes, which comprises the steps of firstly analyzing the influence of different heat treatment parameters on radial and axial temperature gradients of the pipes by performing medium-frequency induction heating post-heat treatment tests under different heat treatment parameter combinations, and finding out core parameters influencing the temperature gradients; simultaneously, using data obtained by a post-welding heat treatment test, establishing a medium-frequency induction post-heating heat treatment finite element transient state and steady state temperature field calculation model, and calculating the maximum axial temperature gradient (namely axial temperature gradient) and the radial temperature gradient (namely radial temperature gradient) of a constant temperature stage in the heat treatment process of N groups of pipelines with different specifications under different heat treatment parameters through the model; establishing a BP neural network model of genetic algorithm parameter adjustment by using the calculated data, training the model, and finally realizing the input pipeline specification, the maximum axial temperature gradient and the radial temperature gradient, thereby completing the optimization of heat treatment parameters of pipelines with different specifications; the invention can obtain the optimal combination of heat treatment parameters (heating width, heat preservation width and alternating current frequency) on the basis of ensuring the axial and radial temperature gradients, has high accuracy, can adopt more reasonable post-welding heat treatment parameters on the premise of ensuring safe service, ensures the heat treatment quality, improves the engineering efficiency and saves the cost.
Drawings
Fig. 1 is a diagram of training results of an artificial neural network according to an embodiment of the present invention.
Fig. 2 is an input/output schematic diagram of a BP neural network according to an embodiment of the present invention.
Detailed Description
The technical scheme of the invention is further specifically described below by way of examples and with reference to the accompanying drawings.
The embodiment of the invention provides an optimization method for heat treatment parameters after local welding of medium-frequency induction heating of a 9% Cr hot-strength steel pipeline, which comprises the following steps:
in the step 1, P91 pipelines with OD 40X 85mm X1300 mm are selected, and initial heat treatment parameters are as follows: the heating width is 600mm, the heat preservation width is 900mm, the number of turns of the induction coil is 17, the turn-to-turn distance is 30mm, the gap between the coil and the heat preservation material is 40mm, the constant temperature time is 2.5 hours, the alternating current size is 100A, the alternating current frequency is 1500HZ, and the heating rate is 100 ℃/h. And respectively carrying out intermediate frequency induction heating local postweld heat treatment tests under different heat treatment parameters to obtain main parameters influencing the temperature gradient, wherein the specific method comprises the following steps of:
step 1.1, under the condition of keeping other heat treatment parameters unchanged, selecting heating widths of 600mm, 800mm and 1000mm by adjusting the coil intervals of the induction coils, and reading the temperatures of the central points of the inner wall and the outer wall of the pipeline welding seam and the edge of the heating zone of the outer wall in real time to obtain the maximum axial temperature gradient in the heat treatment process and the radial temperature gradient when the heat treatment reaches a constant temperature steady state;
step 1.2, under the condition of keeping other heat treatment parameters unchanged, selecting the number of turns of the induction coil to be 17, 25 and 33 by adjusting the turn distance of the induction coil, and reading the temperatures of the central point of the inner wall and the outer wall of the pipeline welding seam and the edge of the heating zone of the outer wall in real time to obtain the maximum axial temperature gradient in the heat treatment process and the radial temperature gradient when the heat treatment reaches a constant temperature steady state;
under the condition of keeping other heat treatment parameters unchanged, respectively selecting parameters with heat preservation widths of 900mm, 1200mm and 1500mm, alternating current frequencies of 1500Hz, 2000Hz and 2500Hz, gaps between a coil and a heat preservation layer of 20mm, 40mm and 60mm, alternating current sizes of 100A, 150A and 200A, heating temperature increasing and decreasing rates of 100 ℃/h, 150 ℃/h and 200 ℃/h, constant temperature time of 2.5h, 3.5h, 4.5h and the like, and reading the central point of the inner wall and the edge temperature of a heating area of the outer wall of a pipeline welding seam in real time to obtain the maximum axial temperature gradient in the heat treatment process and the radial temperature gradient when the heat treatment reaches a constant temperature steady state;
step 1.4, according to the test results of the steps 1.1-1.3, obtaining heat treatment parameters which have obvious influence on the maximum axial temperature gradient in the heat treatment process and the radial temperature gradient when the heat treatment reaches a constant temperature steady state, specifically: heating width, heat preservation width and alternating current frequency.
Step 2, according to the post-welding heat treatment test data obtained in the step 1, establishing a medium-frequency induction post-heating heat treatment temperature field model, verifying, and finally calculating the maximum axial temperature gradient in the heat treatment process under different heat treatment parameters and the radial temperature gradient when the heat treatment reaches a constant temperature steady state through the model, wherein the specific method comprises the following steps:
step 2.1, coupling by utilizing an electromagnetic model and a heat transfer model through finite element software, inputting transient time domain excitation to obtain a transient model of post-welding heat treatment, reading a maximum axial temperature gradient in the heat treatment process according to the transient model, verifying with a test result, adjusting related calculation parameters (such as a heat dissipation coefficient, an air flow rate, a grid size, excitation frequency and other finite element model parameters) if the error is greater than 1%, and performing the next step if the error is less than 1%;
step 2.2, coupling by utilizing an electromagnetic model and a heat transfer model through finite element software, carrying out steady-state solving to obtain a steady-state model of post-welding heat treatment, reading radial temperature gradient when the heat treatment reaches a constant-temperature steady state according to the steady-state model, verifying with a test result, adjusting related calculation parameters if the error is greater than 1%, and carrying out the next step if the error is less than 1%;
and 2.3, calculating the sizes of the axial temperature gradient and the radial temperature gradient of the postweld heat treatment according to the transient model and the steady model of the postweld heat treatment temperature field in the steps 2.1 and 2.2, wherein the pipe diameter of the pipeline is 300-1200mm (10 groups), the wall thickness is 30-140mm (12 groups), the alternating current frequency is 1kHz-8kHz (8 groups), and the heating width and the heat preservation width are selected according to the DL/L-819 standard. Based on the calculation result, 960 sets of data are obtained.
Step 3, according to the calculation result (namely 960 groups of data) obtained in the step 2, establishing a BP neural network model which is subjected to parameter adjustment through a genetic algorithm, and obtaining an optimization method of medium-frequency induction heating local postweld heat treatment parameters of pipelines with different specifications through the model, wherein the specific method comprises the following steps:
step 3.1, optimizing the weight and the threshold value of the BP neural network through a genetic algorithm, and obtaining the weight and the threshold value suitable for the BP neural network through adjusting the population scale, the individual range, the crossover and mutation probability and the iteration times of the genetic algorithm;
step 3.2, normalizing the calculation result in the step 2, wherein the normalization equation is as follows:
in which x is 0 For normalized data, x p As data set vector, x max Is the maximum value of the vector, x min As a minimum value of the vector is set,is the vector average. The pipeline specification, the radial temperature gradient and the axial temperature gradient of the pipeline are taken as input vectors, the heating width, the heat preservation width and the alternating current frequency are taken as output vectors, and the two vectors are in one-to-one correspondenceSelecting 880 groups from the input vector and the output vector as training data, and the rest 80 groups as test data;
step 3.3, setting a BP neural network by using the weight and the threshold value obtained in the step 3.1, setting an expected error of 0.0001 and a dispersion constant of 0.8, inputting 880 sets of training data obtained in the step 3.2 into the BP neural network, training the network (shown in an artificial neural network training result figure 1), and finally inputting 80 sets of test data obtained in the step 3.2 into a trained model for error analysis, wherein if the error is less than 1%, the obtained model is an optimal model of the required optimal technological parameters; if the error is larger, repeating the step 3.1, and readjusting the related parameters of the genetic algorithm.
Step 3.4, inputting the pipe diameter and the wall thickness of a target pipeline in the BP neural network model, and determining that the maximum allowable radial temperature gradient is 1.027 and the axial temperature gradient is 2.1 according to the control of the temperature difference between the inner wall and the outer wall and the maximum bending stress, so as to obtain an intermediate frequency induction heating local postweld heat treatment parameter optimization model; the input and output schematic diagram of the BP neural network is shown in figure 2.
The invention selects the specification (pipe diameter and wall thickness) of the pipeline and the alternating current frequency as variable parameters, and the application range is as follows:
pipeline material: novel 9% Cr hot strength steel;
pipe inside diameter: 300-1200 mm;
wall thickness of the pipeline: 30-140 mm;
ac frequency: 1-8 kHz.
Examples
For the P91 pipeline with the specification of OD540 multiplied by 85mm, the optimal heat treatment parameter (heating width, heat preservation width and alternating current frequency) combination of the local postweld heat treatment of the medium-frequency induction heating is calculated according to the method of the invention. And performing a post-welding heat treatment test of the pipeline by using the optimal heat treatment parameter set, actually measuring the maximum axial temperature gradient and the radial temperature gradient of the pipeline, and comparing the measured maximum axial temperature gradient and the radial temperature gradient with calculated values to verify the accuracy of the invention. The comparison results are shown in Table 1, and it can be seen that the difference between the predicted values and the test values of the axial and radial temperature gradients is small, which indicates that the heat treatment parameter optimization results obtained by the invention are very accurate. By using the method, more reasonable post-welding heat treatment parameters can be adopted on the premise of ensuring safe service, thereby being beneficial to saving cost and improving efficiency.
TABLE 1 verification of the accuracy of the optimization results of the post-weld Heat treatment parameters of the invention
TABLE 2 comparison of the invention with the recommended values of the existing standards
| Parameters of heat treatment | Width of heating/mm | Width/mm of insulation | Alternating current frequency/kHz |
| The invention is obtained | 584 | 821 | 5.3 |
| DL/T819-2019 recommended value | 850 | 1190 | Has no recommended value |
The result shows that the heating width and the heat preservation width obtained by the invention are smaller than the electric power industry standard, the recommended value of the alternating current frequency is given, and the reduction amplitude is very obvious for the pipeline with the specification. Therefore, the invention can reduce damage to the pipe, reduce cost and achieve the aim of safety and energy conservation.
The specific embodiments described herein are offered by way of example only to illustrate the spirit of the invention. Those skilled in the art may make various modifications or additions to the described embodiments or substitutions thereof without departing from the spirit of the invention or exceeding the scope of the invention as defined in the accompanying claims.
Claims (6)
1. A method for optimizing heat treatment parameters after local welding of medium-frequency induction heating of a 9% Cr heat-resistant steel pipeline, which is characterized by comprising the following steps:
step 1, performing medium frequency induction heating post-heat treatment tests of N groups of pipelines with different specifications under different heat treatment parameters, recording the temperatures of different characteristic points at different times, analyzing the influence of different heat treatment parameters on radial and axial temperature gradients of the pipelines through a comparison test, and obtaining main parameters affecting the temperature gradients, wherein the main parameters are as follows: pipe diameter, pipe wall thickness, heating width, heat preservation width, alternating current frequency;
step 2, establishing and verifying a medium-frequency induction post-heat-welding heat treatment temperature field model according to the post-welding heat treatment test data obtained in the step 1, and calculating radial and axial temperature gradients of pipelines with different specifications under different heating widths, heat preservation widths and alternating current frequencies according to the temperature field model; the method comprises the following steps:
step 2.1, coupling by utilizing an electromagnetic model and a heat transfer model through finite element software, inputting transient time domain excitation to obtain a transient model of post-welding heat treatment, reading a maximum axial temperature gradient in the heat treatment process according to the transient model, verifying with a test result, adjusting related calculation parameters if the error is greater than 1%, and carrying out the next step if the error is less than 1%;
step 2.2, coupling by utilizing an electromagnetic model and a heat transfer model through finite element software, carrying out steady-state solving to obtain a steady-state model of the postweld heat treatment, reading radial temperature gradient when the heat treatment reaches a constant-temperature steady state according to the steady-state model, adjusting related calculation parameters if the error is greater than 1%, and carrying out the next step if the error is less than 1%;
step 2.3, calculating N groups of pipelines with different specifications according to the transient model and the steady-state model of the postweld heat treatment temperature field in the steps 2.1 and 2.2, and under different heating widths, heat preservation widths and alternating current frequencies, the magnitudes of axial temperature gradients and radial temperature gradients;
and 3, determining an optimization principle, namely determining that the axial temperature gradient is smaller than 2.1 and the radial temperature gradient is smaller than 1.027 according to the control of the temperature difference between the inner wall and the outer wall and the maximum bending stress, combining the optimization principle according to the calculation result obtained in the step 2, taking the pipeline specification, the pipeline radial direction, the axial temperature gradient and the radial temperature gradient as input vectors, taking the heating width, the heat preservation width and the alternating current frequency as output vectors, establishing a BP neural network model subjected to genetic algorithm parameter adjustment, and finally optimizing the local post-welding heat treatment parameters of the pipelines with different specifications through the model.
2. The method according to claim 1, wherein the feature points in step 1 are: the center point of the inner wall and the outer wall of the pipeline welding seam and the edge of the heating area of the outer wall.
3. The method according to claim 1, wherein the different heat treatment parameters in step 1 are respectively: heating width, number of turns of induction coil, heat preservation width, alternating current frequency, gap between coil and heat preservation layer, alternating current size, temperature rise and fall speed and constant temperature time.
4. The method according to claim 1, wherein in the step 2, the specification of the 9% cr heat pipe is selected as follows: pipe inside diameter: 300-1200mm, wall thickness of pipeline: 30-140 mm; the alternating current frequency is 1kHz-8kHz, and the heating width and the heat preservation width are selected according to the DL/L-819 standard.
5. The method according to claim 1, wherein in step 1, intermediate frequency induction heating local postweld heat treatment tests under different heat treatment parameters are performed respectively to obtain main parameters affecting temperature gradient, and the specific method is as follows:
step 1.1, under the condition of keeping other heat treatment parameters unchanged, selecting 3 groups of different heating widths by adjusting the coil turn spacing of an induction coil, and reading the temperatures of the center point of the inner wall and the outer wall of a pipeline welding seam and the edge of a heating zone of the outer wall in real time to obtain the maximum axial temperature gradient in the heat treatment process and the radial temperature gradient when the heat treatment reaches a constant temperature steady state;
step 1.2, under the condition of keeping other heat treatment parameters unchanged, selecting 3 groups of different turns of induction coils by adjusting the turn intervals of the induction coils, and reading the temperatures of the central point of the inner wall and the outer wall of the pipeline welding seam and the edge of the heating zone of the outer wall in real time to obtain the maximum axial temperature gradient in the heat treatment process and the radial temperature gradient when the heat treatment reaches a constant temperature steady state;
step 1.3, respectively selecting 3 groups of different heat preservation width, alternating current frequency, coil-heat preservation layer clearance, alternating current size, temperature rise and fall speed and constant temperature time parameters under the condition of keeping other heat treatment parameters unchanged, and reading the center point of the inner wall and the outer wall of the pipeline welding seam and the edge temperature of the heating zone of the outer wall in real time to obtain the maximum axial temperature gradient in the heat treatment process and the radial temperature gradient when the heat treatment reaches a constant temperature steady state;
step 1.4, according to the test results of the steps 1.1-1.3, obtaining heat treatment parameters which have obvious influence on the maximum axial temperature gradient in the heat treatment process and the radial temperature gradient when the heat treatment reaches a constant temperature steady state, specifically: heating width, heat preservation width and alternating current frequency.
6. The method according to claim 1, wherein in the step 3, according to the calculation result obtained in the step 2, a BP neural network model for parameter adjustment by genetic algorithm is established, and an optimization method for optimal combination of heat treatment parameters after medium frequency induction heating welding of pipelines with different specifications is obtained by the model, and the specific method is as follows:
step 3.1, optimizing the weight and the threshold value of the BP neural network through a genetic algorithm, and obtaining the weight and the threshold value suitable for the BP neural network through adjusting the population scale, the individual range, the crossover and mutation probability and the iteration times of the genetic algorithm;
step 3.2, normalizing the calculation result in the step 2, taking the pipeline specification, the pipeline radial and axial temperature gradients as input vectors, taking the heating width, the heat preservation width and the alternating current frequency as output vectors, and selecting a B group as training data and the rest C group as test data from the input vectors and the output vectors which are in one-to-one correspondence;
step 3.3, setting a BP neural network by using the weight and the threshold value obtained in the step 3.1, setting expected errors and dispersion constants, inputting the training data of the group B into the BP neural network, training the network, and finally inputting the test data of the group C into the trained model for error analysis, wherein if the errors reach a specified level, the obtained model is the optimal selection model of the required optimal technological parameters; if the error is larger, returning to the step 3.1, and readjusting the related parameters of the genetic algorithm;
and 3.4, inputting the pipe diameter and the wall thickness of the target pipeline in the model, and selecting a radial temperature gradient and an axial temperature gradient to be controlled according to an optimization principle to obtain the optimal medium-frequency induction heating local postweld heat treatment parameter combination.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210769813.1A CN115161445B (en) | 2022-06-30 | 2022-06-30 | Method for optimizing medium-frequency induction heating local postweld heat treatment parameters of 9% Cr hot-strength steel pipeline |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210769813.1A CN115161445B (en) | 2022-06-30 | 2022-06-30 | Method for optimizing medium-frequency induction heating local postweld heat treatment parameters of 9% Cr hot-strength steel pipeline |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115161445A CN115161445A (en) | 2022-10-11 |
| CN115161445B true CN115161445B (en) | 2024-02-27 |
Family
ID=83488679
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210769813.1A Active CN115161445B (en) | 2022-06-30 | 2022-06-30 | Method for optimizing medium-frequency induction heating local postweld heat treatment parameters of 9% Cr hot-strength steel pipeline |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115161445B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2386365A1 (en) * | 2010-05-06 | 2011-11-16 | Siemens Aktiengesellschaft | Operational method for a finishing train with prediction of transport speed |
| CN106909727A (en) * | 2017-02-20 | 2017-06-30 | 武汉理工大学 | Laser welding temperature field Finite Element Method based on BP neural network and Genetic Algorithms |
| CN110846490A (en) * | 2019-11-26 | 2020-02-28 | 江苏方天电力技术有限公司 | Optimization calculation method for postweld heat treatment heating rate of 9% Cr hot-strength steel pipeline |
| CN111187884A (en) * | 2020-02-19 | 2020-05-22 | 燕山大学 | Method for optimizing medium-frequency induction heating heat source of welded pipe |
-
2022
- 2022-06-30 CN CN202210769813.1A patent/CN115161445B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2386365A1 (en) * | 2010-05-06 | 2011-11-16 | Siemens Aktiengesellschaft | Operational method for a finishing train with prediction of transport speed |
| CN102939173A (en) * | 2010-05-06 | 2013-02-20 | 西门子公司 | Operating method for a production line with prediction of the command speed |
| CN106909727A (en) * | 2017-02-20 | 2017-06-30 | 武汉理工大学 | Laser welding temperature field Finite Element Method based on BP neural network and Genetic Algorithms |
| CN110846490A (en) * | 2019-11-26 | 2020-02-28 | 江苏方天电力技术有限公司 | Optimization calculation method for postweld heat treatment heating rate of 9% Cr hot-strength steel pipeline |
| CN111187884A (en) * | 2020-02-19 | 2020-05-22 | 燕山大学 | Method for optimizing medium-frequency induction heating heat source of welded pipe |
Non-Patent Citations (1)
| Title |
|---|
| 新型9%Cr热强钢厚壁管道焊接-热处理温度场/应力场特性研究及应用;胡磊;中国优秀博士学位论文全文数据库（工程科技I辑）(第6期);第B022-46页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115161445A (en) | 2022-10-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102189158B (en) | Process for bending X100 steel grade large-caliber bent pipe through intermediate frequency induction heating | |
| CN103388065B (en) | Large-diameter support roller integral induction heating system and control method thereof | |
| CN104694716B (en) | A kind of pipeline welding heat treatment Frequency Induction Heating technique and device | |
| CN112725572B (en) | Main and auxiliary induction heating local heat treatment method | |
| CN202447439U (en) | Hot roll forming device for titanium tube | |
| CN108220782A (en) | A kind of on-line continuous production, the adjustable coiled tubing of performance dynamic and preparation method thereof | |
| CN115161445B (en) | Method for optimizing medium-frequency induction heating local postweld heat treatment parameters of 9% Cr hot-strength steel pipeline | |
| CN108009329B (en) | Method for determining minimum pipeline length of 9% Cr hot-strength steel pipeline welding process evaluation | |
| KR102075245B1 (en) | Prediction apparatus for iron loss reduction of electric steel sheet | |
| CN109593941A (en) | A kind of rail induction normalizing method | |
| CN111074194B (en) | Remelting method in boiler membrane type water-cooled wall heating surface anticorrosive coating atmosphere furnace | |
| CN111187884B (en) | Method for optimizing medium-frequency induction heating heat source of welded pipe | |
| CN110399694B (en) | Method for analyzing and eliminating hidden defects of welded pipe | |
| CN110846490B (en) | Optimization calculation method for postweld heat treatment heating rate of 9% Cr hot-strength steel pipeline | |
| CN109508513B (en) | Post-welding heat treatment method for Cr-Mo steel pipe with strong air flow in pipe | |
| CN112176175A (en) | TP347 thick-wall pipeline stabilizing heat treatment method | |
| CN111992855A (en) | Welding and combined heat treatment method for martensite heat-resistant steel G115 large-diameter thick-wall pipeline | |
| JP4333282B2 (en) | Manufacturing method of high-strength steel sheet | |
| Boudreault et al. | A new robotic process for in situ heat treatment on large steel components | |
| JP5298081B2 (en) | Pipe residual stress improvement method and construction management method | |
| CN110836828A (en) | Method for measuring core cooling speed in normalizing process of thick-wall P91 steel pipe | |
| CN106399664B (en) | A kind of rotary heating furnace heating process optimization method | |
| JPS60197823A (en) | Method and device for heating for improving residual stress in welded joint part of piping | |
| CN113388797B (en) | Water-cooled wall with heating surface provided with different-frequency induction cladding coating and preparation method thereof | |
| CN110309572B (en) | Method for determining minimum heating width of local postweld heat treatment of 9% Cr steel pipeline |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |