CN102816917A - Position determining method for postweld heat treatment temperature equivalent points of inner walls of steel pipes with 9 percent of Cr - Google Patents
Position determining method for postweld heat treatment temperature equivalent points of inner walls of steel pipes with 9 percent of Cr Download PDFInfo
- Publication number
- CN102816917A CN102816917A CN2012103322313A CN201210332231A CN102816917A CN 102816917 A CN102816917 A CN 102816917A CN 2012103322313 A CN2012103322313 A CN 2012103322313A CN 201210332231 A CN201210332231 A CN 201210332231A CN 102816917 A CN102816917 A CN 102816917A
- Authority
- CN
- China
- Prior art keywords
- heat treatment
- temperature
- layer
- width
- steel
- 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.)
- Granted
Links
Images
Abstract
The invention relates to a position determining method for postweld heat treatment temperature equivalent points of inner walls of steel pipes with 9 percent of Cr. According to the method, T groups of data of postweld heat treatment temperature equivalent points of the inner walls of pipelines with different sizes under the conditions of different heating widths, different heat preservation widths and different heat treatment ambient temperatures are calculated, and the influences of the sizes of the pipelines, the heating widths, the heat preservation widths, the heat treatment ambient temperatures and controlled temperature on positions of the equivalent points are comprehensively considered, a nerve network based on error back propagation is built, trained and tested; and trained and tested network output thresholds are revised to obtain a method for determining postweld heat treatment temperature equivalent points of the inner walls of the novel martensite heat-resistant thick-walled steel pipelines with 9 percent of Cr according to the actual measurement data of the positions of the equivalent points. By the method, the positions of the temperature equivalent points of the inner walls can be quickly determined to help guiding and opitmizing a heat treatment process, so that the heat treatment quality is improved.
Description
Technical field
The present invention relates to a kind of 9%Cr steel conduit postweld heat treatment inner wall temperature equivalency point location determining method.
Background technology
The novel martensite high temperature steel of 9%Cr mainly comprises T/P92, T/P91 and three kinds of novel martensite high temperature steel of E911; Be widely used in members such as heavy wall pipeline such as ultra-supercritical boiler main team pipe, collection case, welding seam toughness is on the low side to be a subject matter that occurs in this Series Steel pipe welding seam installation process.In order to improve welding seam toughness, must carry out partial heat treatment by butt welded seam.Research both at home and abroad shows that the influence of postweld heat treatment temperature (being the follow-up control temperature of mentioning) butt welded seam is very big, when thermal treatment temp (is annotated: receive the restriction of weld seam transformation temperature during at 760 ± 10 ℃; Thermal treatment temp is difficult to further improve), to handle through constant temperature in short-term, the ballistic work of weld seam just can reach more than the 41J; When about 740 ℃, heating, reach this index must significantly increase constant temperature time, when Heating temperature below 730 ℃ the time; Prolonging constant temperature time more not only has little effect; Ballistic work is difficult to reach the toughness index of 41J, and significantly increases installation cost, has a strong impact on construction speed.
During on-the-spot thermal treatment, receive the restriction of pipeline and postweld heat treatment equipment, thermal source generally can only be arranged in pipeline outer wall, and heat conducts to inwall from outer wall, even reach stable state, inner wall temperature still is lower than outside wall temperature, and promptly inside and outside wall certainly exists certain temperature difference.In order to guarantee the toughness of inwall weld seam, require to dwindle as far as possible the inside and outside wall temperature difference (being controlled in 20 ℃-30 ℃).But along with the raising of vapor temperature and pressure, the thick continuous increase of 9%Cr martensite high temperature steel pipeline parts walls, the design wall thickness of some parts is the highest have been reached more than the 140mm, and the inside and outside wall temperature difference increases.
In the actual engineering; Receive the influence of line size; Can't thermopair be installed at inner-walls of duct inner wall temperature is monitored, generally predict the inner-walls of duct temperature, but the position of equivalency point receive the influence of a plurality of factors such as line size (caliber and wall thickness), width of heating, insulation width, heat treatment environment temperature, control temperature equally through the temperature of measuring outer wall equivalency point position; So the position of equivalency point changes, and be difficult to confirm with method of analysis.Though can pass through the position of the method for experiment to the pipeline postweld heat treatment inner wall temperature equivalency point of specific dimensions pipeline under conditions such as specific heat treatment environment, the cost of experiment is high, the cycle is long, and experimental result does not have general applicability.
Artificial neural network is a nonlinear science that the 80's ends began to develop rapidly; Artificial nerve network model has very strong fault-tolerance, study property, adaptivity and nonlinear mapping ability, is particularly suitable for solving the complicated problems such as uncertainty reasoning, judgement, identification and classification of cause-effect relationship.At present, most widely used in the ferrous metallurgy field is the model (BP model) that has the Multi-layered Feedforward Networks structure and adopt reverse error propagation training method.
Summary of the invention
The present invention to solve the problem that prior art exists; Under the novel martensite high temperature steel of 9%Cr posted sides pipeline size (caliber and wall thickness), width of heating, insulation width, heat treatment environment temperature, the known condition of control temperature; The method of a kind of fast prediction pipeline postweld heat treatment inner wall temperature equivalency point position is provided; For the monitoring of inner-walls of duct temperature, ensure thermal treatment quality in the convenient on-the-spot heat treatment process.
It is to solve existing problem in the prior art that the present invention has a purpose again; Provide a kind of solved in the engineering to lose time, increase cost when adopting experimental technique to confirm the equivalency point position and experimental result does not have definite method of the novel martensite high temperature steel of a kind of 9%Cr posted sides pipeline postweld heat treatment inner wall temperature equivalency point of general applicability.
Above-mentioned technical problem of the present invention mainly is able to solve through following technical proposals:
A kind of 9%Cr steel conduit postweld heat treatment inner wall temperature equivalency point location determining method is characterized in that, comprises following step:
Step 3, predictive model is set up module, utilizes the gained data calculated that the BP neural network is carried out training and testing, obtains the model that can predict the novel martensite high temperature steel of 9%Cr posted sides pipeline postweld heat treatment inner wall temperature equivalency point position;
Step 5, the equivalency point position determination module, analysis conduit size (caliber and wall thickness), width of heating, insulation width, heat treatment environment temperature, control temperature are input to the position that revised model is confirmed pipeline postweld heat treatment inner wall temperature equivalency point.
In above-mentioned 9%Cr steel conduit postweld heat treatment inner wall temperature equivalency point location determining method; In the described step 1; The heat place calculation model for temperature field of T group different size pipeline under different heating width, different insulation width, different heat treatment envrionment temperature, different control temperature in the foundation; Adopt finite element analysis software that the postweld heat treatment temperature field is calculated, and obtain the position of equivalency point, concrete grammar is:
According to the applicable cases of the novel martensite high temperature steel of 9%Cr, choose the line size scope; According to domestic and international heat treatment technics rules,, choose width of heating and insulation width range for the pipeline calculating heating zone width of certain specification, the size of insulation width; According to the control temperature and the heat treatment environment temperature conditions of the novel martensite high temperature steel of 9%Cr, select the scope of control temperature and heat treatment environment temperature.Set up the novel martensite high temperature steel of T group 9%Cr pipeline postweld heat treatment temperature field theoretical calculation model, calculate line size (caliber and wall thickness), width of heating, insulation width, control temperature and heat treatment environment temperature equivalent point position effects through the utilization finite element software.As when analyzing the influencing of control temperature, control temperature is typically chosen in 760 ± 10 ℃, therefore; Get 750 ℃, 765 ℃, 780 ℃ respectively; Other conditions remain unchanged, and the process FEM calculation obtains the position of equivalency point, the influence of other factors of analysis that use the same method.Method of calculation are following:
Step 1.1 in finite element software, is set up the novel martensite high temperature steel of 9%Cr postweld heat treatment calculation model for temperature field;
Step 1.2, definition starting condition, final condition are found the solution;
Step 1.3 after calculating is accomplished, checks that in preprocessor inner-walls of duct temperature and pipeline outer wall axial temperature distribute, and through contrast, calculates the equivalency point position.
In above-mentioned 9%Cr steel conduit postweld heat treatment inner wall temperature equivalency point location determining method, in the said step 2, the concrete grammar of setting up based on the error back propagation neural network is:
Step 2.1, definition input layer and output layer
The numerical value of choosing line size (caliber and wall thickness), width of heating, insulation width, control temperature and heat treatment environment temperature is as input variable, so the neuron number of this network input layer is 6; With the output as network model of the size of pipeline postweld heat treatment inner wall temperature equivalency point position under the different condition, so the output layer neuron number is 1.
Step 2.2 is selected the latent number of plies and latent layer unit number: adopt single latent layer, and definite the number of hidden nodes is 10.
Step 2.3, other Determination of Parameters: the transport function of the latent layer of latent layer is unipolarity S type function: f (x)=1/ (1+e
-x), the transport function of output layer is linear function: f (x)=x, makes network export any value, and frequency of training is 1800 times, and the error target is 1, and the selection sample number is T, N learning sample wherein, T-N test sample book.
In above-mentioned 9%Cr steel conduit postweld heat treatment inner wall temperature equivalency point location determining method; In the said step 2; Comprise an input layer, a middle layer and an output layer based on the error back propagation neural network; Input layer has 6 neurones, and there are 10 neurones in the middle layer, and output layer has 1 neurone; The transport function in the middle layer of said predictive model is a unipolarity S type function, and the transport function of output layer is a linear function, makes network export any value; It is following to carrying out the concrete steps of training and testing based on the error back propagation neural network in the step 2 that step 1 is obtained T group equivalency point position data:
Step 3.1; Set weights and threshold value and frequency of training; And weights and threshold value are carried out initialize, and win T-N group sample in the T group sample at random as learning sample, N group sample is as test sample book; Input T-N group learning sample, said sample are that the T that obtains in the step 1 organizes the position of equivalency point and the heat-treat condition of the novel martensite high temperature steel of T group 9%Cr;
Step 3.2; Computational grid output; Obtain the weights and the threshold value of each layer in the reverse transmittance nerve network; And the weights of each layer and the modifying factor of threshold value in the calculating reverse transmittance nerve network, according to T-N group equivalency point position calculation value that obtains in the step 1 and network output computational grid output error, said network output error is the comparison difference that network that the T-N group equivalency point position calculation value that obtains in the step 1 and this step calculate is exported;
Step 3.3 judges whether to reach maximum frequency of training, and selects to carry out following steps according to whether reaching maximum frequency of training:
Select performing step 1,, judge that whether the network output error is less than anticipation error in step 3.2 if do not reach maximum frequency of training as yet; If less than anticipation error; Then training finishes, and preserves in the step 3.2 weights of each layer and threshold value in the reverse transmittance nerve network simultaneously, obtains predictive model undetermined; If greater than anticipation error, revise after weights and the threshold value of each layer in the reverse transmittance nerve network step repeat 3.2. wherein modifying factor adopt step 3.The modifying factor of calculating in 2;
Select performing step 2, if reach maximum frequency of training, then this reverse transmittance nerve network can not be restrained in given frequency of training, and training finishes;
Step 3.4; N is organized test sample book import the predictive model of selecting in the performing step 1 undetermined one by one; If predicated error shows this predictive model undetermined and can be used in the novel martensite high temperature steel of prediction 9%Cr postweld heat treatment inner wall temperature equivalency point position that promptly this predictive model undetermined promptly is a resulting predictive model in the step 3 when being lower than prescribed level; Otherwise this predictive model undetermined does not meet, and finishes whole steps.
In above-mentioned 9%Cr steel conduit postweld heat treatment inner wall temperature equivalency point location determining method; In the described step 4; The measured data of experiment and the Model Calculation value of the novel martensite high temperature steel of 9%Cr posted sides pipeline postweld heat treatment inner wall temperature equivalency point position are compared, and correction model output layer threshold values.
Therefore, the present invention has following advantage: 1. not only can be used for confirming the position of different size pipeline equivalence under Different Heat Treatment Conditions, for the monitoring of inner-walls of duct temperature, ensure thermal treatment quality in the convenient on-the-spot heat treatment process; 2. solved and lost time, increased cost when experimental technique is confirmed the equivalency point position and experimental result does not have the problem of general applicability.
Description of drawings
The BP neural network model figure that uses among Fig. 1 the present invention.
BP neural network training schema among Fig. 2 the present invention.
BP neural network training graphicerrors among Fig. 3 the present invention.
Embodiment
Through embodiment,, do further bright specifically below to technical scheme of the present invention in conjunction with accompanying drawing.
9%Cr steel conduit postweld heat treatment inner wall temperature equivalency point location determining method of the present invention may further comprise the steps.
According to the applicable cases of the novel martensite high temperature steel of 9%Cr, choose the line size scope; According to domestic and international heat treatment technics rules,, choose width of heating and insulation width range for the pipeline calculating heating zone width of certain specification, the size of insulation width; According to the control temperature and the heat treatment environment temperature conditions of the novel martensite high temperature steel of 9%Cr, select the scope of control temperature and heat treatment environment temperature.Set up the novel martensite high temperature steel of T group 9%Cr pipeline postweld heat treatment temperature field theoretical calculation model; Calculate line size (caliber and wall thickness), width of heating, insulation width, control temperature and heat treatment environment temperature equivalent point position effects through the utilization finite element software, method of calculation are following:
Step 1.1 in finite element software, is set up the novel martensite high temperature steel of 9%Cr postweld heat treatment calculation model for temperature field;
Step 1.2, definition starting condition, final condition are found the solution;
Step 1.3 after calculating is accomplished, checks that in preprocessor inner-walls of duct temperature and pipeline outer wall axial temperature distribute, and through contrast, calculates the equivalency point position.
1) design of input layer and output layer
The numerical value of choosing line size (caliber and wall thickness), width of heating, insulation width, control temperature and heat treatment environment temperature is as input variable, so the neuron number of this network input layer is 6; With the output as network model of the size of pipeline postweld heat treatment inner wall temperature equivalency point position under the different condition, so the output layer neuron number is 1.
2) selection of the latent number of plies and latent layer unit number
1989, Robert Hecht-Nielson proved for a continuous function in any closed interval and can approach with the BP network of a latent layer.N ties up the Continuous Mappings that m ties up because one 3 layers BP network can be accomplished arbitrarily; So this model adopts single latent layer; And the selection of the number of hidden nodes is the problem of a more complicated, repeatedly attempts in conjunction with experimental formula and through the author, confirms that at last the number of hidden nodes is 10.
3) other Determination of Parameters
The transport function of the latent layer of latent layer is unipolarity S type function: f (x)=1/ (1+e
-x), the transport function of output layer is linear function: f (x)=x, makes network export any value, and frequency of training is 1800 times, and the error target is 1, and the selection sample number is T, N learning sample wherein, T-N test sample book.
In this step, comprise an input layer, a middle layer and an output layer based on the error back propagation neural network, input layer has 6 neurones, and there are 10 neurones in the middle layer, and output layer has 1 neurone; The transport function in the middle layer of said predictive model is a unipolarity S type function, and the transport function of output layer is a linear function, makes network export any value, and structure iron is shown in accompanying drawing 1.
Step 3, predictive model is set up module, utilizes the gained data calculated that the BP neural network is carried out training and testing, obtains the model that can predict the novel martensite high temperature steel of 9%Cr posted sides pipeline postweld heat treatment inner wall temperature equivalency point position; It is following to carrying out the concrete steps of training and testing based on the error back propagation neural network in the step 2 to obtain T group equivalency point position data for step 1:
Step 3.1; Set weights and threshold value and frequency of training; And weights and threshold value are carried out initialize, and win T-N group sample in the T group sample at random as learning sample, N group sample is as test sample book; Input T-N group learning sample, said sample are that the T that obtains in the step 1 organizes the position of equivalency point and the heat-treat condition of the novel martensite high temperature steel of T group 9%Cr;
Step 3.2; Computational grid output; Obtain the weights and the threshold value of each layer in the reverse transmittance nerve network; And the weights of each layer and the modifying factor of threshold value in the calculating reverse transmittance nerve network, according to T-N group equivalency point position calculation value that obtains in the step 1 and network output computational grid output error, said network output error is the comparison difference that network that the T-N group equivalency point position calculation value that obtains in the step 1 and this step calculate is exported;
Step 3.3 judges whether to reach maximum frequency of training, and selects to carry out following steps according to whether reaching maximum frequency of training:
Select performing step 1,, judge that whether the network output error is less than anticipation error in step 3.2 if do not reach maximum frequency of training as yet; If less than anticipation error; Then training finishes, and preserves in the step 3.2 weights of each layer and threshold value in the reverse transmittance nerve network simultaneously, obtains predictive model undetermined; If greater than anticipation error, revise after weights and the threshold value of each layer in the reverse transmittance nerve network step repeat 3.2. wherein modifying factor adopt step 3.The modifying factor of calculating in 2;
Select performing step 2, if reach maximum frequency of training, then this reverse transmittance nerve network can not be restrained in given frequency of training, and training finishes;
Step 3.4; N is organized test sample book import the predictive model of selecting in the performing step 1 undetermined one by one; If predicated error shows this predictive model undetermined and can be used in the novel martensite high temperature steel of prediction 9%Cr postweld heat treatment inner wall temperature equivalency point position that promptly this predictive model undetermined promptly is a resulting predictive model in the step 3 when being lower than prescribed level; Otherwise this predictive model undetermined does not meet, and finishes whole steps.
In the present embodiment; Training and test are meant that calculating under 7250 groups of different conditions of gained 7200 groups in the novel martensite high temperature steel of the 9%Cr pipeline postweld heat treatment inner wall temperature equivalency point position data with the front finite element software tests the BP network that trains as test sample book with the novel martensite high temperature steel of 9%Cr pipeline postweld heat treatment inner wall temperature equivalency point position data under 50 groups of different conditions of remainder as the model training of learning sample to being set up.Network model network using error backpropagation algorithm is trained; The training flow process is shown in accompanying drawing 2;, the output error of neural network can stop training after the repetition training when reaching 1mm; Training error figure shows that network model can be used for predicting the novel martensite high temperature steel of 9%Cr posted sides pipeline postweld heat treatment inner wall temperature equivalency point position when neural network is lower than prescribed level to the predicated error of 50 groups of test sample books shown in accompanying drawing 3.
Step 5, the equivalency point position determination module, analysis conduit size (caliber and wall thickness), width of heating, insulation width, heat treatment environment temperature, control temperature are input to the position that revised model is confirmed pipeline postweld heat treatment inner wall temperature equivalency point.
Choose line size (caliber and wall thickness), heating zone width, insulation belt width, heat treatment environment temperature and control temperature among the present invention as input parameter, the scope of application is following:
Internal diameter of the pipeline (radius): 100mm-500mm;
Pipeline wall thickness: 30mm-140mm;
Heating zone width: 360mm-1472mm;
Insulation belt width: 560mm-2521mm;
Heat treatment environment temperature :-10 ℃-30 ℃;
Control temperature: 750 ℃-780 ℃.
Be the concrete experimental data that adopts method of the present invention to implement below:
BP neural net method involved in the present invention and experimental technique are confirmed the comparison of 9%Cr martensite high temperature steel posted sides pipeline postweld heat treatment inner wall temperature equivalency point position:
Size (caliber and wall thickness), heating zone width, insulation belt width, heat treatment environment temperature and the control temperature of the 9%Cr martensite high temperature steel pipeline of three kinds of specifications shown in analysis and the recorder 1; The numerical value of each influence factor is input in the model calculates, can calculate the position of pipeline postweld heat treatment inner wall temperature equivalency point under this condition fast.Through experiment the position of pipeline postweld heat treatment inner wall temperature equivalency point is surveyed in addition, to verify the precision of this model.Calculation result and measured result with gained of the present invention in this example are as shown in table 2 below.
The postweld heat treatment parameter of table 1 9%Cr martensite high temperature steel pipeline
| Pipeline specifications/mm | Width of heating/mm | Insulation width/mm | Envrionment temperature/
 |
Control temperature/
 |
| ID296*65 | 510 | 750 | 13 | 755 |
| ID430*90 | 937 | 1137 | 10 | 756 |
| ID288*110 | 866 | 1066 | 15 | 765 |
Table 2 adopts the inventive method and measured data to compare
| Pipeline specifications/mm | The inventive method/mm | Measured value/mm | Error/mm |
| ID296*65 | 114 | 108 | 6 |
| ID430*90 | 146 | 153 | -7 |
| ID288*110 | 207 | 200 | 7 |
Calculation result shows, the method computed information and the measured value of the novel martensite high temperature steel of the definite 9%Cr posted sides pipeline postweld heat treatment inner wall temperature equivalency point position that proposes with the present invention are more consistent, and Error Absolute Value is less than 10mm.Comparing with experimental technique obviously has plurality of advantages, except that determining the novel martensite high temperature steel of 9%Cr posted sides pipeline postweld heat treatment inner wall temperature equivalency point position quickly and easily, also practices thrift lot of test time, test materials and cost.
Specific embodiment described herein only is that the present invention's spirit is illustrated.Person of ordinary skill in the field of the present invention can make various modifications or replenishes or adopt similar mode to substitute described specific embodiment, but can't depart from spirit of the present invention or surmount the defined scope of appended claims.
Claims (5)
1. a 9%Cr steel conduit postweld heat treatment inner wall temperature equivalency point location determining method is characterized in that, may further comprise the steps:
Step 1; Set up the upward heat place calculation model for temperature field of T group different size pipeline under different heating width, different insulation width, different heat treatment envrionment temperature, different control temperature, the position of calculating the postweld heat treatment inner wall temperature equivalency point of each group model by equivalency point situation theory computing module;
Step 2; Set up module by neural network and combine line size, width of heating, insulation width, heat treatment environment temperature, control temperature, set up based on the error back propagation neural network to the novel martensite high temperature steel of 9%Cr posted sides pipeline postweld heat treatment inner wall temperature equivalency point position effects;
Step 3; Set up module by predictive model and utilize the gained data calculated, obtain the model that to predict the novel martensite high temperature steel of 9%Cr posted sides pipeline postweld heat treatment inner wall temperature equivalency point position carrying out training and testing based on the error back propagation neural network;
Step 4; Combine the measured data of experiment of the novel martensite high temperature steel of 9%Cr posted sides pipeline postweld heat treatment inner wall temperature equivalency point position by the model correcting module, the model of definite 9%Cr martensite high temperature steel pipeline postweld heat treatment inner wall temperature equivalency point position of gained is revised;
Step 5 by equivalency point position determination module analysis conduit size (caliber and wall thickness), width of heating, insulation width, heat treatment environment temperature, control temperature, is input to the position that revised model is confirmed pipeline postweld heat treatment inner wall temperature equivalency point.
2. 9%Cr steel conduit postweld heat treatment inner wall temperature equivalency point location determining method according to claim 1; It is characterized in that; In the described step 1; The heat place calculation model for temperature field of T group different size pipeline under different heating width, different insulation width, different heat treatment envrionment temperature, different control temperature calculated based on finite element analysis software in the foundation, and concrete grammar is:
According to the applicable cases of the novel martensite high temperature steel of 9%Cr, choose the line size scope; According to domestic and international heat treatment technics rules,, choose width of heating and insulation width range for the pipeline calculating heating zone width of certain specification, the size of insulation width; According to the control temperature and the heat treatment environment temperature conditions of the novel martensite high temperature steel of 9%Cr, select the scope of control temperature and heat treatment environment temperature; Set up the novel martensite high temperature steel of T group 9%Cr pipeline postweld heat treatment temperature field theoretical calculation model; Calculate line size, width of heating, insulation width, control temperature and heat treatment environment temperature equivalent point position effects through the utilization finite element software, method of calculation are following:
Step 1.1 in finite element software, is set up the novel martensite high temperature steel of 9%Cr postweld heat treatment calculation model for temperature field;
Step 1.2, definition starting condition, final condition are found the solution;
Step 1.3 after calculating is accomplished, checks that in preprocessor inner-walls of duct temperature and pipeline outer wall axial temperature distribute, and through contrast, calculates the equivalency point position.
3. 9%Cr steel conduit postweld heat treatment inner wall temperature equivalency point location determining method according to claim 1 is characterized in that, in the said step 2, the concrete grammar of setting up based on the error back propagation neural network is:
Step 2.1, definition input layer and output layer:
The numerical value of choosing line size, width of heating, insulation width, control temperature and heat treatment environment temperature is as input variable, so the neuron number of this network input layer is 6; With the output as network model of the size of pipeline postweld heat treatment inner wall temperature equivalency point position under the different condition, so the output layer neuron number is 1;
Step 2.2 is selected the latent number of plies and latent layer unit number: adopt single latent layer, and definite the number of hidden nodes is 10;
Step 2.3, other Determination of Parameters: the transport function of the latent layer of latent layer is unipolarity S type function: f (x)=1/ (1+e
-x), the transport function of output layer is linear function: f (x)=x, makes network export any value, and frequency of training is 1800 times, and the error target is 1, and the selection sample number is T, N learning sample wherein, T-N test sample book.
4. 9%Cr steel conduit postweld heat treatment inner wall temperature equivalency point location determining method according to claim 1; It is characterized in that; In the said step 2, comprise an input layer, a middle layer and an output layer based on the error back propagation neural network, input layer has 6 neurones; There are 10 neurones in the middle layer, and output layer has 1 neurone; The transport function in the middle layer of said predictive model is a unipolarity S type function, and the transport function of output layer is a linear function, makes network export any value; It is following to carrying out the concrete steps of training and testing based on the error back propagation neural network in the step 2 that step 1 is obtained T group equivalency point position data:
Step 3.1; Set weights and threshold value and frequency of training; And weights and threshold value are carried out initialize, and win T-N group sample in the T group sample at random as learning sample, N group sample is as test sample book; Input T-N group learning sample, said sample are that the T that obtains in the step 1 organizes the position of equivalency point and the heat-treat condition of the novel martensite high temperature steel of T group 9%Cr;
Step 3.2; Computational grid output; Obtain the weights and the threshold value of each layer in the reverse transmittance nerve network; And the weights of each layer and the modifying factor of threshold value in the calculating reverse transmittance nerve network, according to T-N group equivalency point position calculation value that obtains in the step 1 and network output computational grid output error, said network output error is the comparison difference that network that the T-N group equivalency point position calculation value that obtains in the step 1 and this step calculate is exported;
Step 3.3 judges whether to reach maximum frequency of training, and selects to carry out following steps according to whether reaching maximum frequency of training:
Select performing step 1,, judge that whether the network output error is less than anticipation error in step 3.2 if do not reach maximum frequency of training as yet; If less than anticipation error; Then training finishes, and preserves in the step 3.2 weights of each layer and threshold value in the reverse transmittance nerve network simultaneously, obtains predictive model undetermined; If greater than anticipation error, revise after weights and the threshold value of each layer in the reverse transmittance nerve network step repeat 3.2. wherein modifying factor adopt the modifying factor of calculating in the step 3.2;
Select performing step 2, if reach maximum frequency of training, then this reverse transmittance nerve network can not be restrained in given frequency of training, and training finishes;
Step 3.4; N is organized test sample book import the predictive model of selecting in the performing step 1 undetermined one by one; If predicated error shows this predictive model undetermined and can be used in the novel martensite high temperature steel of prediction 9%Cr postweld heat treatment inner wall temperature equivalency point position that promptly this predictive model undetermined promptly is a resulting predictive model in the step 3 when being lower than prescribed level; Otherwise this predictive model undetermined does not meet, and finishes whole steps.
5. 9%Cr steel conduit postweld heat treatment inner wall temperature equivalency point location determining method according to claim 1; It is characterized in that; In the described step 4; The measured data of experiment and the Model Calculation value of the novel martensite high temperature steel of 9%Cr posted sides pipeline postweld heat treatment inner wall temperature equivalency point position are compared, and correction model output layer threshold values.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210332231.3A CN102816917B (en) | 2012-09-11 | 2012-09-11 | Position determining method for postweld heat treatment temperature equivalent points of inner walls of steel pipes with 9 percent of Cr |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210332231.3A CN102816917B (en) | 2012-09-11 | 2012-09-11 | Position determining method for postweld heat treatment temperature equivalent points of inner walls of steel pipes with 9 percent of Cr |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN102816917A true CN102816917A (en) | 2012-12-12 |
| CN102816917B CN102816917B (en) | 2014-12-17 |
Family
ID=47301361
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201210332231.3A Active CN102816917B (en) | 2012-09-11 | 2012-09-11 | Position determining method for postweld heat treatment temperature equivalent points of inner walls of steel pipes with 9 percent of Cr |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102816917B (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103602802A (en) * | 2013-11-15 | 2014-02-26 | 华电电力科学研究院 | Method for calculating position of highest temperature point of postweld heat treatment of 9-12% Cr martensitic heat-resistant steel vertical arrangement pipeline |
| CN103602803A (en) * | 2013-11-15 | 2014-02-26 | 华电电力科学研究院 | Method for arranging postweld heat treatment heater band of 9-12% Cr martensitic heat-resistant steel vertical arrangement pipeline |
| CN107688700A (en) * | 2017-08-22 | 2018-02-13 | 武汉大学 | A kind of 9%Cr refractory steel pipeline post weld heat treatment heating power computational methods |
| CN107881318A (en) * | 2017-11-15 | 2018-04-06 | 武汉大学 | A kind of method of optimization design 9%Cr refractory steel pipeline post weld heat treatment number of partitions |
| CN110309572A (en) * | 2019-06-24 | 2019-10-08 | 武汉大学 | The method for determining 9%Cr steel conduit local post weld heat treatment minimum width of heating |
| CN110530541A (en) * | 2019-08-29 | 2019-12-03 | 中国石油大学(华东) | One kind can accurately simulate large pressurized vessel post weld heat treatment temperature field computation method |
| 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 |
| WO2020155966A1 (en) * | 2019-01-31 | 2020-08-06 | 中国石油大学(华东) | Control method for welding stress and distortion in local post weld heat treatment of ultra-large pressure vessel |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2005315703A (en) * | 2004-04-28 | 2005-11-10 | Nippon Steel Corp | Method for predicting material in steel material |
| CN101139652A (en) * | 2007-10-26 | 2008-03-12 | 武汉钢铁(集团)公司 | Off-line prediction method for bell-type furnace steel roll annealing process |
| CN101158674A (en) * | 2007-11-15 | 2008-04-09 | 天津市市政工程设计研究院 | Method for predicting chlorophyll a concentration in water based on BP nerval net |
| CN102393884A (en) * | 2011-10-12 | 2012-03-28 | 杭州电子科技大学 | Hot continuous rolling electromagnetic induction heating temperature prediction method based on BP (back-propagation) neural network |
-
2012
- 2012-09-11 CN CN201210332231.3A patent/CN102816917B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2005315703A (en) * | 2004-04-28 | 2005-11-10 | Nippon Steel Corp | Method for predicting material in steel material |
| CN101139652A (en) * | 2007-10-26 | 2008-03-12 | 武汉钢铁(集团)公司 | Off-line prediction method for bell-type furnace steel roll annealing process |
| CN101158674A (en) * | 2007-11-15 | 2008-04-09 | 天津市市政工程设计研究院 | Method for predicting chlorophyll a concentration in water based on BP nerval net |
| CN102393884A (en) * | 2011-10-12 | 2012-03-28 | 杭州电子科技大学 | Hot continuous rolling electromagnetic induction heating temperature prediction method based on BP (back-propagation) neural network |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103602802A (en) * | 2013-11-15 | 2014-02-26 | 华电电力科学研究院 | Method for calculating position of highest temperature point of postweld heat treatment of 9-12% Cr martensitic heat-resistant steel vertical arrangement pipeline |
| CN103602803A (en) * | 2013-11-15 | 2014-02-26 | 华电电力科学研究院 | Method for arranging postweld heat treatment heater band of 9-12% Cr martensitic heat-resistant steel vertical arrangement pipeline |
| CN107688700A (en) * | 2017-08-22 | 2018-02-13 | 武汉大学 | A kind of 9%Cr refractory steel pipeline post weld heat treatment heating power computational methods |
| CN107688700B (en) * | 2017-08-22 | 2020-08-11 | 武汉大学 | Method for calculating heating power of postweld heat treatment of 9% Cr hot-strength steel pipeline |
| CN107881318A (en) * | 2017-11-15 | 2018-04-06 | 武汉大学 | A kind of method of optimization design 9%Cr refractory steel pipeline post weld heat treatment number of partitions |
| WO2020155966A1 (en) * | 2019-01-31 | 2020-08-06 | 中国石油大学(华东) | Control method for welding stress and distortion in local post weld heat treatment of ultra-large pressure vessel |
| CN110309572A (en) * | 2019-06-24 | 2019-10-08 | 武汉大学 | The method for determining 9%Cr steel conduit local post weld heat treatment minimum width of heating |
| CN110309572B (en) * | 2019-06-24 | 2020-12-18 | 武汉大学 | Method for determining minimum heating width of local postweld heat treatment of 9% Cr steel pipeline |
| CN110530541A (en) * | 2019-08-29 | 2019-12-03 | 中国石油大学(华东) | One kind can accurately simulate large pressurized vessel post weld heat treatment temperature field computation method |
| CN110530541B (en) * | 2019-08-29 | 2020-12-25 | 中国石油大学(华东) | Calculation method capable of accurately simulating postweld heat treatment temperature field of large pressure container |
| 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 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN102816917B (en) | 2014-12-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102816917B (en) | Position determining method for postweld heat treatment temperature equivalent points of inner walls of steel pipes with 9 percent of Cr | |
| CN102719644B (en) | Forecasting method of inner and outer wall temperature difference of 9% Cr martensitic steel thick wall pipeline in heat treatment | |
| Sterjovski et al. | Artificial neural networks for modelling the mechanical properties of steels in various applications | |
| Mandal et al. | Constitutive flow behaviour of austenitic stainless steels under hot deformation: artificial neural network modelling to understand, evaluate and predict | |
| Zendehboudi et al. | Robust predictive models for estimating frost deposition on horizontal and parallel surfaces | |
| CN110807540A (en) | Method for predicting corrosion rate in natural gas pipeline | |
| Garcin et al. | Microstructure model for the heat-affected zone of X80 linepipe steel | |
| CN103602803A (en) | Method for arranging postweld heat treatment heater band of 9-12% Cr martensitic heat-resistant steel vertical arrangement pipeline | |
| Dupin et al. | Modeling static and dynamic kinetics of microstructure evolution in type 316 stainless steel | |
| CN102663498B (en) | Method for forecasting Ac1 point of martensite refractory-steel weld metal with 9 percent of Cr | |
| CN102799938B (en) | Optimizing method of 9% martensite steel pipeline postweld heat treatment heating width | |
| Azimzadegan et al. | An artificial neural-network model for impact properties in X70 pipeline steels | |
| Langbauer et al. | Modelling of thermal shrinkage of seamless steel pipes using artificial neural networks (ANN) focussing on the influence of the ANN architecture | |
| Wu et al. | Comparisons of different data-driven modeling techniques for predicting tensile strength of X70 pipeline steels | |
| Madhav et al. | Analysis of UOE forming process accounting for Bauschinger effect and welding | |
| Ghazanfari et al. | Investigation of residual stress and optimization of welding process parameters to decrease tensile residual stress in the flash butt welded UIC60 rail | |
| CN103602802A (en) | Method for calculating position of highest temperature point of postweld heat treatment of 9-12% Cr martensitic heat-resistant steel vertical arrangement pipeline | |
| Lu et al. | Theory and machine learning modeling for burst pressure estimation of pipeline with multipoint corrosion | |
| Goyal et al. | Mechanistic approach for prediction of creep deformation, damage and rupture life of different Cr–Mo ferritic steels | |
| Sekercioglu et al. | Development of the positive mean stress diagrams using genetic algorithm approach | |
| Yang et al. | A Bayesian‐based Reliability Estimation Approach for Corrosion Fatigue Crack Growth Utilizing the Random Walk | |
| Skubisz et al. | Estimation of heat transfer coefficient of forced-air cooling and its experimental validation in controlled processing of forgings | |
| Peet et al. | Neural network modelling of hot deformation of austenite | |
| Spindler et al. | Creep fatigue behaviour of type 321 stainless steel at 650 C | |
| CN103063736B (en) | Method for online detecting thermal aging condition of duplex stainless steel and system thereof |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| C56 | Change in the name or address of the patentee | ||
| CP01 | Change in the name or title of a patent holder |
Address after: Xu Xiang Nan Xiao Zhuang Cun Xiao Zhuang 061300 Cangzhou city Hebei County of Yanshan Province Patentee after: HEBEI CANG HAI NUCLEAR EQUIPMENT TECHNOLOGY CO., LTD. Patentee after: Wuhan University Patentee after: Tianjin Electric Power Construction Company of China Energy Engineering Group Address before: Xu Xiang Nan Xiao Zhuang Cun Xiao Zhuang 061300 Cangzhou city Hebei County of Yanshan Province Patentee before: Hebei Canghai Pipe Fitting Group Co., Ltd. Patentee before: Wuhan University Patentee before: Tianjin Electric Power Construction Company of China Energy Engineering Group |