CN103602802A - Method for calculating position of highest temperature point of postweld heat treatment of 9-12% Cr martensitic heat-resistant steel vertical arrangement pipeline - Google Patents
Method for calculating position of highest temperature point of postweld heat treatment of 9-12% Cr martensitic heat-resistant steel vertical arrangement pipeline Download PDFInfo
- Publication number
- CN103602802A CN103602802A CN201310571009.3A CN201310571009A CN103602802A CN 103602802 A CN103602802 A CN 103602802A CN 201310571009 A CN201310571009 A CN 201310571009A CN 103602802 A CN103602802 A CN 103602802A
- Authority
- CN
- China
- Prior art keywords
- heat treatment
- pipeline
- temperature point
- resistant steel
- top temperature
- 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.)
- Pending
Links
Images
Landscapes
- Heat Treatment Of Articles (AREA)
Abstract
The invention relates to a method for calculating position of highest temperature point of postweld heat treatment of a 9-12% Cr martensitic heat-resistant steel vertical arrangement pipeline. The method provided by the invention is characterized by comprising the following steps that 1, a theoretical highest temperature point calculation module is used for establishing T groups of calculation models of postweld heat treatment temperature fields of the 9-12% Cr martensitic heat-resistant steel vertical arrangement pipelines with different sizes under different heating widths, different heat preservation widths, different heat treatment environment temperatures and different heat treatment temperatures on the basis of a heat transfer theory, and calculating the position of the highest temperature point of heat treatment under corresponding conditions through a finite element analysis method; 2, a BP neural network model module; 3, a prediction model creating module; 4, a model correcting module; 5, a highest temperature point determining module. The method provided by the invention can be used for conveniently and quickly calculating the position of the highest temperature point of the post weld heat treatment of the 9-12% Cr martensitic heat-resistant steel vertical arrangement pipeline.
Description
Technical field
The present invention relates to the method for calculation of a kind of pipeline postweld heat treatment top temperature point position, especially relate to the method for calculation that a kind of 9-12%Cr martensite heat-resistant steel is arranged vertically pipeline postweld heat treatment top temperature point position, can calculate easily and fast 9-12%Cr martensite heat-resistant steel and be arranged vertically pipeline postweld heat treatment top temperature point position.
Background technology
9-12%Cr martensite heat-resistant steel is widely used in the members such as posted sides pipeline such as ultra-supercritical boiler main team pipe, header, and welding seam toughness is on the low side is the subject matter occurring 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, the impact of postweld heat treatment temperature (being follow-up mentioned control temperature) butt welded seam is very large, when thermal treatment temp (is noted: be subject to the restriction of weld seam transformation temperature during at 760 ± 10 ℃, thermal treatment temp is difficult to further improve), through constant temperature in short-term, process, more than the ballistic work of weld seam just can reach 41J, when about 740 ℃ heating, reach this index and must significantly increase constant temperature time, when Heating temperature is below 730 ℃ time, extending constant temperature time not only has little effect again, ballistic work is difficult to reach the toughness index of 41J, and significantly increase installation cost, have a strong impact on construction speed.Meanwhile, when thermal treatment temp surpasses Ac1 point, after thermal treatment, organize tempered martensite not yet, welding seam toughness is difficult to reach code requirement.
When pipeline field is installed, be subject to condition restriction generally to adopt local postweld heat treatment.For vertically arranged pipeline, due to the existence of convection current, the top temperature in the width range of heating zone will depart from central position, heating zone.The temperature that is positioned at first side pipe road of weld seam is by higher than lower half side temperature.Therefore, may cause local temperature to surpass Ac1 point during site operation and not reach the situation of thermal effectiveness.Although the inconsistent power loss that flows and cause in order to compensate inner air during construction, can be by center, the middle mind-set heating zone downside skew of heating zone, but for side-play amount how to choose heating zone, so far neither one standard specifications still, during site operation, how choosing by rule of thumb, site operation, in the urgent need to understanding the position of thermal treatment top temperature point, is convenient to install thermopair and is carried out monitoring temperature.
Artificial neural network is a nonlinear science that the 80's ends started 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 problems such as Uncertainty Reasoning, judgement, identification and classification of cause-effect relationship complexity.
Open day is on December 12nd, 2012, publication number is in the Chinese patent of 102816917A, a kind of 9%Cr steel conduit postweld heat treatment inner wall temperature equivalency point location determining method is disclosed, this calculates T group different size pipeline at different heating width, different insulation width, the data of the pipeline postweld heat treatment inner wall temperature equivalency point position under different heat treatment ambient temperature conditions, consider line size, width of heating, insulation width, heat treatment environment temperature, the impact of control temperature on inner wall temperature equivalency point position, the neural network of foundation based on error back propagation also carried out training and testing to it, the last measured data in conjunction with equivalency point position, the network output threshold values that training and testing is good is revised to the method that can be used for determining the novel martensite heat-resistant steel posted sides pipeline of 9%Cr postweld heat treatment inner wall temperature equivalency point position that obtains, the method is that 9%Cr steel conduit postweld heat treatment inner wall temperature equivalency point position is calculated, it is intended at pipeline outer wall, find a position fast by the method, the temperature of this position in heat treatment process is identical with weld seam center inner wall temperature, with this, inner wall temperature is monitored, the object that is the method is by a bit internal wall temperature of outer wall, to monitor in heat treatment process.
Summary of the invention
The object of the invention is to overcome above shortcomings in prior art, having solved in engineering makes thermal treatment not reach the hidden danger of requirement because top temperature point position may surpass Ac1 point, provide a kind of fast and easy to calculate the position that 9-12%Cr martensite heat-resistant steel is arranged vertically pipeline postweld heat treatment top temperature point, the 9-12%Cr martensite heat-resistant steel of being convenient to that this position is monitored is arranged vertically the method for calculation of pipeline postweld heat treatment top temperature point position.
The present invention addresses the above problem adopted technical scheme: this 9-12%Cr martensite heat-resistant steel is arranged vertically the method for calculation of pipeline postweld heat treatment top temperature point position, it is characterized in that: comprise the following steps:
Step 2, BP neural network model module, consider the impacts of factor on top temperature point position such as line size, width of heating, insulation width, heat treatment environment temperature, thermal treatment temp and side-play amount, according to the calculation result in step 1, set up neural network model;
Step 3, predictive model is set up module, utilizes the data of calculating gained to carry out training and testing to BP neural network model, obtains one for predicting that 9-12%Cr martensite heat-resistant steel is arranged vertically the method for the local postweld heat treatment top temperature point of pipeline position;
Step 4, model correcting module, the model that the prediction 9-12%Cr martensite heat-resistant steel of gained is arranged vertically to the local postweld heat treatment top temperature point of pipeline position in conjunction with experiment the data obtained is revised;
Step 5, top temperature point determination module, analysis conduit size, width of heating, insulation width, heat treatment environment temperature, control temperature, side-play amount is input to revised model and calculates the position that 9-12%Cr martensite heat-resistant steel is arranged vertically the local postweld heat treatment top temperature point of pipeline.
As preferably, in step 1 of the present invention, the thermal treatment temp field computation model of T group different size pipeline under different heating width, different insulation width, different heat treatment envrionment temperature, different control temperature and different side-play amount in foundation, based on finite element analysis software, calculate, concrete grammar is:
According to the applicable cases of 9-12%Cr martensite heat-resistant steel pipeline, choose line size scope; According to domestic and international heat treatment technics rules, for the pipeline of certain specification, calculate the size of heating zone width, insulation width, choose width of heating and insulation width range; According to control temperature and heat treatment environment temperature conditions, select the scope of control temperature and heat treatment environment temperature; According to site operation experience, select the scope of side-play amount; Set up T group 9-12%Cr martensite heat-resistant steel pipeline postweld heat treatment temperature field theoretical calculation model, by using finite element software to calculate line size, width of heating, insulation width, control temperature, heat treatment environment temperature and the impact of side-play amount on top temperature point position, calculation procedure is as follows:
Step 1.1, in finite element software, sets up 9-12%Cr martensite heat-resistant steel and is arranged vertically pipeline postweld heat treatment calculation model for temperature field;
Step 1.2, definition material properties, starting condition, final condition, solve;
Step 1.3 after having calculated, is checked pipeline axial, radially and circumferential temperature distribution in preprocessor, by contrast, calculates the position of top temperature point.
As preferably, in step 2 of the present invention, the concrete steps of setting up based on error back propagation neural network are:
Step 2.1, definition input layer and output layer: choose the numerical value of line size, width of heating, insulation width, control temperature, heat treatment environment temperature and side-play amount as input variable, so the neuron number of this network input layer is 7; Using the position of pipeline postweld heat treatment top temperature point under different condition as the output of network model, so output layer neuron number is 1;
Step 2.2, selects hidden layer number and Hidden unit number: this model adopts single hidden layer, and the number of hidden nodes is 12;
Step 2.3, the determining of other parameters: the transport function of hidden 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 1835 times, and error target is 0.5, and selection sample number is T, N learning sample wherein, T-N test sample book.
As preferably, in step 2 of the present invention, based on error back propagation neural network, comprise an input layer, a middle layer and an output layer, input layer has 7 neurones, and there are 12 neurones in middle layer, and output layer has 1 neurone; The transport function in the middle layer of predictive model is unipolarity S type function, and the transport function of output layer is linear function, makes network export any value; By step 1, obtain T group side-play amount size data as follows to carrying out the concrete steps of training and testing based on error back propagation neural network in step 2:
Step 3.1, set weights, threshold value and frequency of training, and weights and threshold value are carried out to initialize, the T-N winning at random in T group sample organizes sample as learning sample, N group sample is as test sample book, input T-N group learning sample, described sample is that the T obtaining in step 1 organizes the data of top temperature point position and the heat-treat condition that T group 9-12%Cr martensite heat-resistant steel is arranged vertically pipeline;
Step 3.2, computational grid output, obtain weights and the threshold value of each layer in reverse transmittance nerve network, and calculate the weights of each layer and the modifying factor of threshold value in reverse transmittance nerve network, according to the calculated value of the T-N group top temperature point position obtaining in step 1 and network output computational grid output error, described network output error is the comparison difference that the network of the T-N top temperature point position calculation value that obtains in step 1 and the calculating of this step 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 execution step 1, if not yet reach maximum frequency of training, whether judgement network output error in step 3.2 is less than anticipation error, if be less than anticipation error, training finishes, and preserves in step 3.2 weights of each layer and threshold value in reverse transmittance nerve network simultaneously, obtains predictive model undetermined; If be greater than anticipation error, repeating step 3.2 after the weights of each layer and threshold value in correction reverse transmittance nerve network, wherein modifying factor adopts the modifying factor of calculating in step 3.2;
Select execution step 2, if reach maximum frequency of training, this reverse transmittance nerve network can not be restrained in given frequency of training, and training finishes;
Step 3.4, N is organized to test sample book one by one in the predictive model undetermined of input selection execution step 1, if predicated error is during lower than prescribed level, show that this predictive model undetermined can be used in prediction 9-12%Cr martensite heat-resistant steel and is arranged vertically pipeline postweld heat treatment top temperature point position, this predictive model undetermined is resulting predictive model in step 3; Otherwise this predictive model undetermined does not meet, and finishes whole step.
As preferably, in step 4 of the present invention, the measured data of experiment and the model calculated value that 9-12%Cr martensite heat-resistant steel are arranged vertically to pipeline postweld heat treatment top temperature point position contrast, and correction model output layer threshold values.
As preferably, line size vial footpath of the present invention and wall thickness.
The present invention compared with prior art, has the following advantages and effect: 1) frontier nature, and there is no document both at home and abroad and carry out related description or research to being arranged vertically the calculating of the position of pipeline postweld heat treatment top temperature point, lack guiding normative document.2) economy, the present invention can calculate the position of top temperature point in heat treatment process rapidly, has avoided expensive experiment and long experimental period.3) reliability, adopts the present invention to determine suitable thermal treatment process, can effectively ensure thermal treatment quality, improves the operating reliability of pipe fitting.4) convenience, the present invention can calculate thermal treatment top temperature point position fast, can help to instruct and optimize thermal treatment process.5) accuracy is high, and computed information of the present invention and measured value are more consistent, and Error Absolute Value is less than 10mm.
The present invention is arranged vertically outer wall top temperature in pipeline postweld heat treatment process to 9-12%Cr martensite heat-resistant steel to calculate.For being arranged vertically pipeline, due to the existence of convection current, in heat treatment process, outer wall top temperature point departs from weld seam center, thereby may cause local temperature to surpass A
c1point and do not reach thermal effectiveness.Calculate the position that can occur top temperature in heat treatment process by the present invention, thereby the temperature to this position is monitored in heat treatment process, prevents that this position temperature from surpassing A
c1point, and then ensure thermal treatment quality.The present invention seeks in heat treatment process, outer wall top temperature point position to be calculated, thereby this position temperature is monitored.
Accompanying drawing explanation
Fig. 1 embodiment of the present invention 9-12%Cr martensite heat-resistant steel is arranged vertically the neural network model figure using in the method for calculation of pipeline postweld heat treatment top temperature point position.
Fig. 2 embodiment of the present invention 9-12%Cr martensite heat-resistant steel is arranged vertically network training schema in the method for calculation of pipeline postweld heat treatment top temperature point position.
Fig. 3 embodiment of the present invention 9-12%Cr martensite heat-resistant steel is arranged vertically network training graphicerrors in the method for calculation of pipeline postweld heat treatment top temperature point position.
Embodiment
Below in conjunction with accompanying drawing and by embodiment, the present invention is described in further detail, and following examples are explanation of the invention and the present invention is not limited to following examples.
Embodiment.
Referring to Fig. 1 to Fig. 3, the method for calculation that in the present embodiment, 9-12%Cr martensite heat-resistant steel is arranged vertically pipeline postweld heat treatment top temperature point position comprise the following steps.
According to the applicable cases of 9-12%Cr martensite heat-resistant steel pipeline, choose line size scope; According to domestic and international heat treatment technics rules, for the pipeline of certain specification, calculate the size of heating zone width, insulation width, choose width of heating and insulation width range; According to control temperature and heat treatment environment temperature conditions, select the scope of control temperature and heat treatment environment temperature; According to site operation experience, select the scope of side-play amount.Set up T group 9-12%Cr martensite heat-resistant steel pipeline postweld heat treatment temperature field theoretical calculation model, by using finite element software to calculate line size (caliber and wall thickness), width of heating, insulation width, control temperature, heat treatment environment temperature and the impact of side-play amount on top temperature point position, method of calculation are as follows.
Step 1.1, in finite element software, sets up 9-12%Cr martensite heat-resistant steel and is arranged vertically pipeline postweld heat treatment calculation model for temperature field.
Step 1.2, definition material properties, starting condition and final condition also solves.
Step 1.3 after having calculated, is checked pipeline axial, radially and circumferential temperature distribution in preprocessor, by contrast, calculates the position of top temperature point.
Step 2, neural network model module.Consider the impacts of factor on top temperature point position such as line size (caliber and wall thickness), width of heating, insulation width, heat treatment environment temperature, thermal treatment temp, side-play amount, according to the calculation result in step 1, set up neural network model.
Step 2.1, definition input layer and output layer: choose the numerical value of line size (caliber and wall thickness), width of heating, insulation width, control temperature, heat treatment environment temperature and side-play amount as input variable, so the neuron number of this network input layer is 7; Using the position of pipeline postweld heat treatment top temperature point under different condition as the output of network model, so output layer neuron number is 1.
Step 2.2, selects hidden layer number and Hidden unit number: 1989, Robert Hecht-Nielson proved for a continuous function in any closed interval and can approach with the BP network of a hidden layer.Because the BP network of 3 layers can complete n arbitrarily and tie up the Continuous Mappings that m ties up, therefore this model adopts single hidden layer, and the selection of the number of hidden nodes is the problem of a more complicated, in conjunction with experimental formula and through author, repeatedly attempt, finally determine that the number of hidden nodes is 12.
Step 2.3, the determining of other parameters: the transport function of hidden layer hidden 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 3000 times, and error target is 1, and selection sample number is T, N learning sample wherein, T-N test sample book.
Step 3, predictive model is set up module.Utilize the data of calculating gained to carry out training and testing to BP neural network model, obtain one and can predict that 9-12%Cr martensite heat-resistant steel is arranged vertically the method for the local postweld heat treatment top temperature point of pipeline position.
Step 3.1, set weights, threshold value and frequency of training, and weights and threshold value are carried out to initialize, the T-N winning at random in T group sample organizes sample as learning sample, N group sample is as test sample book, input T-N group learning sample, sample is the data of T group top temperature point position and the heat-treat condition of T group 9-12%Cr martensite heat-resistant steel pipeline obtaining in step 1.
Step 3.2, computational grid output, obtain weights and the threshold value of each layer in reverse transmittance nerve network, and calculate the weights of each layer and the modifying factor of threshold value in reverse transmittance nerve network, according to the calculated value of the T-N group top temperature point position obtaining in step 1 and network output computational grid output error, network output error is the comparison difference that the network of the T-N top temperature point position calculation value that obtains in step 1 and the calculating of this step is exported.
Step 3.3, judge whether to reach maximum frequency of training, and according to whether reaching maximum frequency of training selection execution following steps: select execution step 1, if not yet reach maximum frequency of training, whether judgement network output error in step 3.2 is less than anticipation error, if be less than anticipation error, training finishes, preserve in step 3.2 weights of each layer and threshold value in reverse transmittance nerve network simultaneously, obtain predictive model undetermined; If be greater than anticipation error, revise after the weights and threshold value of each layer in reverse transmittance nerve network, repeating step 3.2, wherein modifying factor adopts the modifying factor of calculating in step 3.2.Select execution step 2, if reach maximum frequency of training, this reverse transmittance nerve network can not be restrained in given frequency of training, and training finishes.
Step 3.4, N is organized to test sample book one by one in the predictive model undetermined of input selection execution step 1, if predicated error is during lower than prescribed level, show that this predictive model undetermined can be used in prediction 9-12%Cr martensite heat-resistant steel pipeline and is arranged vertically posted sides pipeline postweld heat treatment top temperature point position, this predictive model undetermined is resulting predictive model in step 3; Otherwise this predictive model undetermined does not meet, and finishes whole step.
In the present embodiment, training and test refer to finite element software above calculate 9-12%Cr martensite heat-resistant steel under 43300 groups of different conditions of gained be arranged vertically in pipeline postweld heat treatment top temperature point position data 43200 groups as learning sample to set up model training, with 9-12%Cr martensite heat-resistant steel under 100 groups of different conditions of remainder, be arranged vertically pipeline postweld heat treatment top temperature point position data and as test sample book, the BP network training tested.Network model network using error backpropagation algorithm is trained, training flow process as shown in Figure 2, after repetition training when the output error of neural network reaches 1mm, get final product deconditioning, training error figure as shown in Figure 3, when neural network during lower than prescribed level, shows that network model can be used for predicting that 9-12%Cr martensite heat-resistant steel is arranged vertically pipeline postweld heat treatment top temperature point position to the predicated error of 50 groups of test sample books.
In the present invention, choose line size (caliber and wall thickness), heating zone width, insulation belt width, heat treatment environment temperature, control temperature, side-play amount as input parameter, the scope of application is as follows:
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 ℃-50 ℃;
Control temperature: 740 ℃-780 ℃;
Side-play amount: 0mm-300mm.
The top temperature skew heating zone width between centers within the scope of pipeline postweld heat treatment heating zone that is arranged vertically of Neural Network model predictive result involved in the present invention and actual measurement contrasts.
P92 line size (caliber, wall thickness), heat treatment environment temperature, thermal treatment temp, width of heating, insulation width numerical value shown in analysis and recorder 1 are input in neural network model and calculate, and can calculate fast postweld heat treatment heating zone, vertical deployment tube road side-play amount size under this condition.By experiment pipeline is determined in the heating zone side-play amount that changes condition in addition, to verify the precision of this neural network model.As shown in table 2 below with measured result with predicting the outcome of gained of the present invention in this example.
Calculation result shows, the method for calculation computed information and the measured value that with a kind of 9-12%Cr martensite heat-resistant steel that the present invention proposes, are arranged vertically pipeline postweld heat treatment top temperature point position are more consistent, and Error Absolute Value is less than 10mm.Comparing with experimental technique obviously has conveniently, simple and directly can save the advantages such as a large amount of test periods, test materials and cost.
Although the present invention with embodiment openly as above; but it is not in order to limit protection scope of the present invention; any technician who is familiar with this technology, not departing from change and the retouching of doing in the spirit and scope of the present invention, all should belong to protection scope of the present invention.
Claims (6)
1. 9-12%Cr martensite heat-resistant steel is arranged vertically method of calculation for pipeline postweld heat treatment top temperature point position, it is characterized in that: comprise the following steps:
Step 1, top temperature point Theoretical Calculation module, under this module, based on heat transfer theory, set up the computation model that T group different size 9-12%Cr martensite heat-resistant steel is arranged vertically the postweld heat treatment temperature field of pipeline under different heating width, different insulation width, different heat treatment envrionment temperature, different heat treatment control temperature and different side-play amount, adopt finite element method to calculate the position of thermal treatment top temperature point under respective conditions;
Step 2, BP neural network model module, consider the impacts of factor on top temperature point position such as line size, width of heating, insulation width, heat treatment environment temperature, thermal treatment temp and side-play amount, according to the calculation result in step 1, set up neural network model;
Step 3, predictive model is set up module, utilizes the data of calculating gained to carry out training and testing to BP neural network model, obtains one for predicting that 9-12%Cr martensite heat-resistant steel is arranged vertically the method for the local postweld heat treatment top temperature point of pipeline position;
Step 4, model correcting module, the model that the prediction 9-12%Cr martensite heat-resistant steel of gained is arranged vertically to the local postweld heat treatment top temperature point of pipeline position in conjunction with experiment the data obtained is revised;
Step 5, top temperature point determination module, analysis conduit size, width of heating, insulation width, heat treatment environment temperature, control temperature, side-play amount is input to revised model and calculates the position that 9-12%Cr martensite heat-resistant steel is arranged vertically the local postweld heat treatment top temperature point of pipeline.
2. 9-12%Cr martensite heat-resistant steel according to claim 1 is arranged vertically the method for calculation of pipeline postweld heat treatment top temperature point position, it is characterized in that: in described step 1, the thermal treatment temp field computation model of T group different size pipeline under different heating width, different insulation width, different heat treatment envrionment temperature, different control temperature and different side-play amount in foundation, based on finite element analysis software, calculate, concrete grammar is:
According to the applicable cases of 9-12%Cr martensite heat-resistant steel pipeline, choose line size scope; According to domestic and international heat treatment technics rules, for the pipeline of certain specification, calculate the size of heating zone width, insulation width, choose width of heating and insulation width range; According to control temperature and heat treatment environment temperature conditions, select the scope of control temperature and heat treatment environment temperature; According to site operation experience, select the scope of side-play amount; Set up T group 9-12%Cr martensite heat-resistant steel pipeline postweld heat treatment temperature field theoretical calculation model, by using finite element software to calculate line size, width of heating, insulation width, control temperature, heat treatment environment temperature and the impact of side-play amount on top temperature point position, calculation procedure is as follows:
Step 1.1, in finite element software, sets up 9-12%Cr martensite heat-resistant steel and is arranged vertically pipeline postweld heat treatment calculation model for temperature field;
Step 1.2, definition material properties, starting condition, final condition, solve;
Step 1.3 after having calculated, is checked pipeline axial, radially and circumferential temperature distribution in preprocessor, by contrast, calculates the position of top temperature point.
3. 9-12%Cr martensite heat-resistant steel according to claim 1 is arranged vertically the method for calculation of pipeline postweld heat treatment top temperature point position, it is characterized in that: in described step 2, the concrete steps of setting up based on error back propagation neural network are:
Step 2.1, definition input layer and output layer: choose the numerical value of line size, width of heating, insulation width, control temperature, heat treatment environment temperature and side-play amount as input variable, so the neuron number of this network input layer is 7; Using the position of pipeline postweld heat treatment top temperature point under different condition as the output of network model, so output layer neuron number is 1;
Step 2.2, selects hidden layer number and Hidden unit number: this model adopts single hidden layer, and the number of hidden nodes is 12;
Step 2.3, the determining of other parameters: the transport function of hidden 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 1835 times, and error target is 0.5, and selection sample number is T, N learning sample wherein, T-N test sample book.
4. 9-12%Cr martensite heat-resistant steel according to claim 1 is arranged vertically the method for calculation of pipeline postweld heat treatment top temperature point position, it is characterized in that: in described step 2, based on error back propagation neural network, comprise an input layer, a middle layer and an output layer, input layer has 7 neurones, there are 12 neurones in middle layer, and output layer has 1 neurone; The transport function in the middle layer of predictive model is unipolarity S type function, and the transport function of output layer is linear function, makes network export any value; By step 1, obtain T group side-play amount size data as follows to carrying out the concrete steps of training and testing based on error back propagation neural network in step 2:
Step 3.1, set weights, threshold value and frequency of training, and weights and threshold value are carried out to initialize, the T-N winning at random in T group sample organizes sample as learning sample, N group sample is as test sample book, input T-N group learning sample, described sample is that the T obtaining in step 1 organizes the data of top temperature point position and the heat-treat condition that T group 9-12%Cr martensite heat-resistant steel is arranged vertically pipeline;
Step 3.2, computational grid output, obtain weights and the threshold value of each layer in reverse transmittance nerve network, and calculate the weights of each layer and the modifying factor of threshold value in reverse transmittance nerve network, according to the calculated value of the T-N group top temperature point position obtaining in step 1 and network output computational grid output error, described network output error is the comparison difference that the network of the T-N top temperature point position calculation value that obtains in step 1 and the calculating of this step 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 execution step 1, if not yet reach maximum frequency of training, whether judgement network output error in step 3.2 is less than anticipation error, if be less than anticipation error, training finishes, and preserves in step 3.2 weights of each layer and threshold value in reverse transmittance nerve network simultaneously, obtains predictive model undetermined; If be greater than anticipation error, repeating step 3.2 after the weights of each layer and threshold value in correction reverse transmittance nerve network, wherein modifying factor adopts the modifying factor of calculating in step 3.2;
Select execution step 2, if reach maximum frequency of training, this reverse transmittance nerve network can not be restrained in given frequency of training, and training finishes;
Step 3.4, N is organized to test sample book one by one in the predictive model undetermined of input selection execution step 1, if predicated error is during lower than prescribed level, show that this predictive model undetermined can be used in prediction 9-12%Cr martensite heat-resistant steel and is arranged vertically pipeline postweld heat treatment top temperature point position, this predictive model undetermined is resulting predictive model in step 3; Otherwise this predictive model undetermined does not meet, and finishes whole step.
5. 9-12%Cr martensite heat-resistant steel according to claim 1 is arranged vertically the method for calculation of pipeline postweld heat treatment top temperature point position, it is characterized in that: in described step 4, the measured data of experiment and the model calculated value that 9-12%Cr martensite heat-resistant steel are arranged vertically to pipeline postweld heat treatment top temperature point position contrast, and correction model output layer threshold values.
6. 9-12%Cr martensite heat-resistant steel according to claim 1 is arranged vertically the method for calculation of pipeline postweld heat treatment top temperature point position, it is characterized in that: described line size vial footpath and wall thickness.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310571009.3A CN103602802A (en) | 2013-11-15 | 2013-11-15 | Method for calculating position of highest temperature point of postweld heat treatment of 9-12% Cr martensitic heat-resistant steel vertical arrangement pipeline |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310571009.3A CN103602802A (en) | 2013-11-15 | 2013-11-15 | Method for calculating position of highest temperature point of postweld heat treatment of 9-12% Cr martensitic heat-resistant steel vertical arrangement pipeline |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN103602802A true CN103602802A (en) | 2014-02-26 |
Family
ID=50121065
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201310571009.3A Pending CN103602802A (en) | 2013-11-15 | 2013-11-15 | Method for calculating position of highest temperature point of postweld heat treatment of 9-12% Cr martensitic heat-resistant steel vertical arrangement pipeline |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103602802A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| CN111161806A (en) * | 2019-12-30 | 2020-05-15 | 国电科学技术研究院有限公司 | Method for calculating oxide film thickness of martensite heat-resistant steel under supercritical high-temperature steam |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102816917A (en) * | 2012-09-11 | 2012-12-12 | 河北沧海重工股份有限公司 | Position determining method for postweld heat treatment temperature equivalent points of inner walls of steel pipes with 9 percent of Cr |
-
2013
- 2013-11-15 CN CN201310571009.3A patent/CN103602802A/en active Pending
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102816917A (en) * | 2012-09-11 | 2012-12-12 | 河北沧海重工股份有限公司 | Position determining method for postweld heat treatment temperature equivalent points of inner walls of steel pipes with 9 percent of Cr |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| CN111161806A (en) * | 2019-12-30 | 2020-05-15 | 国电科学技术研究院有限公司 | Method for calculating oxide film thickness of martensite heat-resistant steel under supercritical high-temperature steam |
| CN111161806B (en) * | 2019-12-30 | 2023-10-17 | 国家能源集团科学技术研究院有限公司 | Method for calculating oxide film thickness of martensitic heat-resistant steel under supercritical high-temperature steam |
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 | |
| CN109583585B (en) | Construction method of power station boiler wall temperature prediction neural network model | |
| Yang et al. | A novel model-based fault detection method for temperature sensor using fractal correlation dimension | |
| CN103602803A (en) | Method for arranging postweld heat treatment heater band of 9-12% Cr martensitic heat-resistant steel vertical arrangement pipeline | |
| CN105181744B (en) | A kind of computational methods and the anti-spontaneous combustion monitoring system of coal yard of dump ignition phase | |
| CN103854057B (en) | A kind of comprehensive safety evaluation system being applied to inservice pressure vessel | |
| Wei et al. | Modeling method for predicting seepage of RCC dams considering time‐varying and lag effect | |
| CN102521439A (en) | Method for calculating quenching medium heat exchange coefficient by combining finite element method with inverse heat conduction method | |
| CN111783354A (en) | Flow-induced corrosion characteristic prediction and service life evaluation method of RBF neural network model | |
| 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 | |
| Arif et al. | Development of residual stress during manufacturing of spiral welded pipes | |
| Zhu et al. | Structural Safety Monitoring of High Arch Dam Using Improved ABC‐BP Model | |
| CN102799938B (en) | Optimizing method of 9% martensite steel pipeline postweld heat treatment heating width | |
| Lu et al. | Theory and machine learning modeling for burst pressure estimation of pipeline with multipoint corrosion | |
| 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 | |
| Wild et al. | Modelling and experimental model validation for a pusher-type reheating furnace | |
| CN103225882B (en) | Based on the early warning of the flue gas waste heat recovery apparatus of conduction oil and control system and method | |
| CN108009329A (en) | A kind of method of the definite minimum duct length of 9%Cr refractory steel pipeline welding process evaluation | |
| CN107881318A (en) | A kind of method of optimization design 9%Cr refractory steel pipeline post weld heat treatment number of partitions | |
| Vasudevan et al. | Genetic algorithm for optimisation of A-TIG welding process for modified 9Cr–1Mo steel | |
| CN110472332A (en) | The evaluation method of nuclear leve pipeline fatigue damage based on wind-structure interaction | |
| Skubisz et al. | Estimation of heat transfer coefficient of forced-air cooling and its experimental validation in controlled processing of forgings | |
| CN103337000B (en) | A kind of safe monitoring and pre-alarming method of oil-gas gathering and transportation system | |
| 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 | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C12 | Rejection of a patent application after its publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20140226 |