CN113059184B - Optimization method for parameters of ingot blank spray forming process - Google Patents
Optimization method for parameters of ingot blank spray forming process Download PDFInfo
- Publication number
- CN113059184B CN113059184B CN202110341349.1A CN202110341349A CN113059184B CN 113059184 B CN113059184 B CN 113059184B CN 202110341349 A CN202110341349 A CN 202110341349A CN 113059184 B CN113059184 B CN 113059184B
- Authority
- CN
- China
- Prior art keywords
- parameters
- spray forming
- diameter
- forming process
- ingot blank
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B22—CASTING; POWDER METALLURGY
- B22F—WORKING METALLIC POWDER; MANUFACTURE OF ARTICLES FROM METALLIC POWDER; MAKING METALLIC POWDER; APPARATUS OR DEVICES SPECIALLY ADAPTED FOR METALLIC POWDER
- B22F3/00—Manufacture of workpieces or articles from metallic powder characterised by the manner of compacting or sintering; Apparatus specially adapted therefor ; Presses and furnaces
- B22F3/115—Manufacture of workpieces or articles from metallic powder characterised by the manner of compacting or sintering; Apparatus specially adapted therefor ; Presses and furnaces by spraying molten metal, i.e. spray sintering, spray casting
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B22—CASTING; POWDER METALLURGY
- B22D—CASTING OF METALS; CASTING OF OTHER SUBSTANCES BY THE SAME PROCESSES OR DEVICES
- B22D23/00—Casting processes not provided for in groups B22D1/00 - B22D21/00
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B22—CASTING; POWDER METALLURGY
- B22D—CASTING OF METALS; CASTING OF OTHER SUBSTANCES BY THE SAME PROCESSES OR DEVICES
- B22D7/00—Casting ingots, e.g. from ferrous metals
- B22D7/005—Casting ingots, e.g. from ferrous metals from non-ferrous metals
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B33—ADDITIVE MANUFACTURING TECHNOLOGY
- B33Y—ADDITIVE MANUFACTURING, i.e. MANUFACTURING OF THREE-DIMENSIONAL [3-D] OBJECTS BY ADDITIVE DEPOSITION, ADDITIVE AGGLOMERATION OR ADDITIVE LAYERING, e.g. BY 3-D PRINTING, STEREOLITHOGRAPHY OR SELECTIVE LASER SINTERING
- B33Y10/00—Processes of additive manufacturing
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B33—ADDITIVE MANUFACTURING TECHNOLOGY
- B33Y—ADDITIVE MANUFACTURING, i.e. MANUFACTURING OF THREE-DIMENSIONAL [3-D] OBJECTS BY ADDITIVE DEPOSITION, ADDITIVE AGGLOMERATION OR ADDITIVE LAYERING, e.g. BY 3-D PRINTING, STEREOLITHOGRAPHY OR SELECTIVE LASER SINTERING
- B33Y50/00—Data acquisition or data processing for additive manufacturing
- B33Y50/02—Data acquisition or data processing for additive manufacturing for controlling or regulating additive manufacturing processes
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B33—ADDITIVE MANUFACTURING TECHNOLOGY
- B33Y—ADDITIVE MANUFACTURING, i.e. MANUFACTURING OF THREE-DIMENSIONAL [3-D] OBJECTS BY ADDITIVE DEPOSITION, ADDITIVE AGGLOMERATION OR ADDITIVE LAYERING, e.g. BY 3-D PRINTING, STEREOLITHOGRAPHY OR SELECTIVE LASER SINTERING
- B33Y80/00—Products made by additive manufacturing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/086—Learning methods using evolutionary algorithms, e.g. genetic algorithms or genetic programming
Abstract
The invention relates to a method for optimizing technological parameters of spray forming of an ingot blank, which comprises the steps of collecting technological parameters in the spray forming production process, measuring diameter values of the ingot blank at different heights, screening out technological parameters with high correlation degree with the diameter of the deposition surface of the ingot blank through correlation analysis, and establishing a prediction model of the diameter of the deposition surface of the ingot blank; calculating the variation of the spray forming process parameter and the variation of the diameter of the deposition surface every second so as to establish a deposition substrate lifting speed optimization model; in the injection molding process of the ingot blank, the process parameters acquired in real time at different moments and in different states are input into the established model, and the injection molding process parameter optimization can be realized by executing an operation program. According to the invention, the optimized model established by the spray forming process data acquired through actual acquisition is closer to the actual production, the scientificity of spray forming process parameter optimization is improved, human factors are reduced, and the automatic control is convenient to realize.
Description
Technical Field
The invention relates to the technical field of spray forming process parameter optimization, in particular to an optimization method of deposition substrate lifting speed process parameters with complex incidence relation in an inclined multi-nozzle scanning spray forming aluminum alloy ingot blank process.
Background
The Al-Zn-Mg-Cu series aluminum alloy (7000 series aluminum alloy) has the advantages of high hardness, high strength, fracture toughness, good corrosion resistance and the like, is widely applied to high-strength structural parts such as airplane wings, airframes and the like, and gradually becomes a key base material in the field of aerospace.
The existing methods for preparing aluminum alloy comprise: the method comprises the following steps of ingot metallurgy, powder metallurgy, spray forming and the like, wherein a blank formed by the ingot metallurgy method is in an as-cast structure, and has the problems of loose material interior, coarse grains and the like. The powder metallurgy method requires many processes such as preparing alloy powder, pressure compacting, sintering and the like to form lines, and oxidation of alloy materials is easy to occur in the whole preparation process.
Spray forming belongs to a new generation of alloy rapid solidification technology, and is between ingot metallurgy and powder metallurgy. The main development of solidification technology is to increase the solidification rate of the melt, mainly by refining the melt solidification unit to increase the heat dissipation rate. The solidification technology goes through the die casting stage and develops into a semi-continuous casting technology, the solidification units of which are from centimeter level to millimeter level, and as a new generation of solidification technology, the solidification units of the injection molding technology can reach micron level.
The basic process of spray forming is that the metal melt is impacted by high-pressure inert gas (usually nitrogen or argon) to be broken and atomized into fine metal droplets, a droplet atomizing cone is formed under the drive of the inert gas, and the droplets are deposited on a deposition substrate in a semi-solid state after flying cooling and fused to form a compact blank.
The uniqueness of the spray forming process lies in the rapid solidification process, which is mainly divided into two stages of atomization and deposition, wherein the atomization (rapid solidification) of the metal melt and the deposition (dynamic dense solidification) of the atomized droplets are combined, and the blanks are directly prepared from the liquid metal. The spray deposition can actually be formed as a superposition of semi-solid deposited layers.
An important direction of the development of the spray forming process is the large specification of the blank, the inclined multi-nozzle scanning spray forming process is one of the main methods for realizing the large specification of the blank, the process involves a plurality of process parameters, and the fluctuation of the process parameters has great influence on the metal atomization process, the material deposition distribution state and the semi-solid solidification and deposition state.
In the existing spray forming process parameter optimization method, the process parameters of initial setting are often optimized and calculated through a spray deposition theoretical process, or most of the process parameters are analyzed and optimized aiming at the spray forming process of an ingot blank with a smaller size. However, the existing optimization method is difficult to meet the requirement of controlling the dimensional stability of the large-size ingot blank in the spray forming process in engineering implementation because the spray deposition needs longer time and the process factors influencing the deposition growth of the ingot blank are more.
Disclosure of Invention
The invention aims to provide a method for optimizing the technological parameters of ingot blank spray forming, which is used for analyzing and excavating data through the technological parameters acquired on an actual industrial production line to obtain a technological parameter optimization model, solving the problem that the lifting speed of a deposition substrate does not have a reference value in the blank spray forming process and providing technological guarantee for the spray forming of large-size aluminum alloy blanks in a semisolid deposition mode.
In order to achieve the purpose, the technical scheme provided by the invention is as follows:
a method for optimizing technological parameters of spray forming of an ingot blank obtains technological parameters on a spray forming production line, wherein the technological parameters comprise controllable parameters and process parameters; according to two stages, optimizing the spray forming process parameters according to the acquired process parameter data: the first stage, according to the process data acquired on the production line, the relation between the process parameters and the diameter of the deposition surface of the ingot blank is searched, and a diameter prediction model and a parameter optimization model are established; and in the second stage, acquiring spray forming process parameters in real time in the machining process, and optimizing the spray forming process parameters by using the optimization model established in the first stage.
The controllable parameters comprise the rotating speed of the deposition substrate, the lifting speed of the deposition substrate, the liquid level height of the leakage ladle, the rotating speed of the leakage ladle dumping device and the air exhaust speed of the deposition chamber.
The process parameters include: deposition chamber pressure, deposition chamber temperature, alloy solution temperature, droplet temperature, and gas line pressure.
In the first stage of optimizing the spray forming process parameters, an ingot deposition surface diameter prediction model and a spray forming process parameter optimization model are established, and the method comprises the following steps:
the method comprises the following steps: collecting technological parameters of an industrial production line at different moments and measuring diameter values of prepared ingot blanks at different heights;
step two: screening out process parameters with high correlation degree with the diameter value of the ingot blank by applying a Pearson correlation coefficient and significance test;
step three: normalizing the process parameters with high degree of correlation with the diameter value of the ingot blank obtained in the step two; different orders of magnitude and units exist among the spray forming process parameters, and non-dimensionalization treatment is carried out through normalization to keep all the process parameters in the same order of magnitude;
step four: determining basic elements of a prediction model structure and a genetic algorithm of the ingot blank diameter;
step five: calculating the parameter variation of the current moment corresponding to the previous moment according to the spray forming process parameters acquired in the step one, and calculating the diameter variation of the deposition surface of the ingot blank; carrying out normalization processing after obtaining input parameters and output parameters of the spray forming process parameter optimization model;
step six: determining input and output parameters of the spray forming process parameter optimization model, a model structure and basic elements of a genetic algorithm, and establishing the optimization model.
Further, in the fourth step, the basic elements of the network model structure and the genetic algorithm include the number of neurons in the input layer and the output layer of the network, the number of network layers, an activation function, a training function, a population coding mode, the number of termination iterations, a population scale, an individual fitness function and a genetic operator, wherein the genetic operator includes selection, intersection and variation probability.
In the second stage of optimizing the spray forming process parameters, the lifting speed of the deposition substrate is optimized on line in the spray forming processing process according to the established ingot blank deposition surface diameter prediction model and the spray forming process parameter optimization model, and the specific steps are as follows:
the method comprises the following steps: collecting technological parameters in real time in the spray forming process, normalizing the technological parameters with high correlation degree with the diameter value of the ingot blank by using a diameter prediction model, inputting the normalized technological parameters into the prediction model, and outputting the model to obtain a predicted diameter value;
step two: calculating the variation of the process parameters at the current moment compared with the variation at the previous moment, and calculating the diameter variation with the previous moment;
step three: applying a spray forming process parameter optimization model, normalizing the process parameter variation and the diameter variation, inputting the normalized process parameter variation and the normalized diameter variation into the optimization model, and outputting the model to obtain the reference variation of the lifting speed of the deposition substrate;
step four: and adjusting the lifting speed of the deposition substrate according to the optimized speed reference value.
Compared with the prior art, the invention has the beneficial effects that:
the invention discloses a method for optimizing parameters of an ingot blank spray forming process, which is a method suitable for a spray forming industrial production line and capable of optimizing the lifting speed of a deposition substrate on line.
According to the invention, the reasonable diameter prediction model and the deposition substrate speed optimization model are established by utilizing the process parameters acquired on the spray forming industrial production line at different processing moments and under different process states, so that the spray forming process parameter optimization is more reasonable and scientific, and the method is suitable for the modern spray forming automatic production line.
The spray forming process parameter optimization method provided by the invention establishes the obtained optimization model through the data such as temperature, pressure and the like acquired on the actual production line, is closer to the actual production, improves the scientificity of spray forming process parameter optimization, reduces human factors and is convenient for realizing automatic control.
The spray forming process parameter optimization method provided by the invention can realize real-time display of spray forming process parameters and display and regulation of the lifting speed reference value of the deposition substrate after the optimization system is networked with an MES system of an enterprise.
Drawings
FIG. 1 is a flow chart of the modeling of a prediction model of the diameter of the deposition surface of an ingot.
FIG. 2 is a flow chart of a deposition substrate lifting speed optimization model.
FIG. 3 is a schematic diagram of an online optimization method for process parameters.
FIG. 4 is a schematic diagram of the overall structure of the parameter optimization system.
Detailed Description
The foregoing aspects of the present invention are described in further detail below by way of examples, but it should not be construed that the scope of the subject matter of the present invention is limited to the following examples, and that all the technologies realized based on the above aspects of the present invention are within the scope of the present invention.
In the description of the present invention, it is also to be noted that: the embodiment of the present invention will be described by way of example of the multi-nozzle spray forming of a 7XXX series aluminum alloy, but the present invention is not limited thereto in any way.
A method for optimizing parameters of an ingot blank spray forming process is specifically carried out according to the following steps:
the method comprises the following steps: collecting technological parameters of the aluminum alloy multi-nozzle spray forming production line at different moments, and collecting one piece of data every second. The data collected includes: and storing the data into a local database, wherein the data comprise the pressure of the deposition chamber, the temperature of the deposition chamber, the actual liquid level of a drain ladle, the temperature of aluminum water, the pressure of a nozzle pipeline, the rotating speed of a deposition substrate, the lifting speed of the deposition substrate, the exhaust speed of the deposition chamber and the like.
Step two: after the injection molding of the aluminum alloy ingot blank is finished, the diameter values of the ingot blank are measured at different heights, the diameter values corresponding to different moments are completed by a linear interpolation method, the diameter values at different moments are deposition surfaces of the ingot blank at different moments, and the diameter values are stored in a local database along with the collected process parameter values after the calculation is finished.
Step three: and (3) screening the process parameters with higher degree of correlation with the diameter value of the deposition surface of the ingot blank by using a Pearson correlation coefficient and significance test, and obtaining the six process parameters with higher correlation after analysis, wherein the correlation comprises the following steps: the pressure of the deposition chamber, the temperature of the deposition chamber, the actual liquid level of the drain ladle, the temperature of the molten aluminum, the pressure of a nozzle pipeline and the exhaust speed of the deposition chamber. And normalizing the values of the six process parameters and the diameter value of the deposition surface of the ingot blank to be between 0 and 1 by using dispersion standardization, so that the process parameters are in a uniform order of magnitude, and the solving efficiency of a subsequent model is improved.
Step four: and establishing a prediction model of the diameter of the deposition surface of the ingot blank, and predicting the diameter value of the deposition surface at different moments and in different states.
The method for establishing the prediction model of the diameter of the deposition surface of the ingot blank comprises the following steps:
(1) and according to the third step, selecting six process parameters with high correlation degree with the diameter value of the deposition surface of the ingot blank as input parameters of the prediction model, and using the diameter value of the deposition surface of the ingot blank as output parameters. The BP neural network of the single hidden layer can approach any continuous function in a closed interval, so that the number of layers of the ingot blank deposition surface diameter prediction model is determined to be three;
(2) the number of nodes of the input layer is 6, the number of nodes of the output layer is 1, the number of nodes of the hidden layer is between [4 and 24] can be obtained according to an empirical formula, training is carried out by constructing networks with different numbers of nodes of the hidden layer, and the prediction errors of the model are compared. When the number of hidden layer nodes is 15, the error is minimum, so that the model is determined to be a three-layer BP neural network of 6-15-1;
(3) the neural network input layer and the hidden layer adopt Sigmoid functions, and the hidden layer and the output layer adopt linear purelin functions. And selecting a thingda function, a thingdx function and a thindm function as the training functions for network training respectively by the training functions, and selecting the thindm with the minimum error as the training function after comparing the errors of the models. The learning rate of the network is selected to be 0.2, the momentum factor is selected to be 0.9, the network target error is selected to be 0.00001, and the maximum learning frequency is selected to be 10000;
(4) the structure of the prediction model of the diameter of the deposition surface of the ingot blank is 6-15-1, and the basic elements for determining the genetic algorithm are as follows: the population scale is 40, the number of times of terminating iteration is 60, the coding mode is decimal coding, the fitness function is the mean square error of the network training data set, the selection operator adopts a roulette method, the cross probability is 0.4, and the variation probability is 0.1;
(5) and training the GA-BP neural network to obtain a prediction model of the ingot blank deposition surface diameter, and storing the obtained model and the maximum value of the input and output parameters into a local database.
Step five: calculating the parameter variation of the current moment corresponding to the previous moment, which is mainly as follows: the device comprises a deposition chamber pressure variable quantity, a deposition chamber temperature variable quantity, a drain ladle liquid level variable quantity, a nozzle pipeline pressure variable quantity, an ingot blank deposition surface diameter variable quantity and a deposition substrate lifting speed variable quantity. The first five parameters are input parameters of the network, and the variation of the lifting speed is output parameters. And storing the calculated variable quantity into a local database, and normalizing the data to be between [0 and 1] by using the edge difference normalization.
Step six: and establishing a deposition substrate lifting speed optimization model, and calculating to obtain a reference speed optimization adjustment value at different processing moments and in different states.
The method for establishing the deposition substrate lifting speed optimization model comprises the following steps:
(1) selecting a neural network with a single hidden layer, determining a three-layer BP neural network with an optimization model of 5-10-1 according to the selection of input and output parameters in the step five and through error comparison, wherein the number of nodes of the input layer, the hidden layer and the output layer is respectively 5, 10 and 1;
(2) the neural network input layer and the hidden layer select a Sigmoid function, the hidden layer and the output layer use a purelin function, and the training function selects a trailing dm function with the minimum error. The learning rate of the network is selected to be 0.2, the momentum factor is 0.9, the network target error is 0.0001, and the maximum learning frequency is 10000;
(3) the structure of the deposition substrate lifting speed optimization model is 5-10-1, and the basic elements for determining the genetic algorithm are as follows: the population scale is 40, the number of termination iterations is 60, the coding mode is decimal coding, the individual fitness function is the mean square error of the network training data sample, the selection function is a roulette method, the cross probability is 0.4, and the variation probability is 0.1.
(4) And training the network to obtain a deposition substrate lifting speed optimization model, and storing the obtained model and the maximum value of the input and output parameters into a local database.
Step seven: the method comprises the following steps of optimizing the lifting speed of the deposition substrate on line in the spray forming process:
(1) collecting the technological parameters needed by the model in real time, still collecting a piece of data at an interval of one second, and storing the obtained data into a local database;
(2) reading the ingot blank deposition substrate diameter prediction model obtained by training in the fourth step and stored in a local database, inputting the acquired data into the model, calculating to obtain a predicted diameter value and storing the predicted diameter value into the local database;
(3) calculating the process parameter variation at the current moment and the diameter variation calculated by the ingot blank deposition surface diameter prediction model, reading a deposition substrate lifting speed optimization model stored in a local database, and inputting the variation into the model to calculate the speed variation;
(4) and adding the calculated speed variation to the current speed to obtain the optimized reference lifting speed, and further adjusting the lifting speed of the deposition substrate.
The above description is only a preferred embodiment of the present invention, and should not be taken as limiting the invention in any way, and any person skilled in the art can make any simple modification, equivalent replacement, and improvement on the above embodiment without departing from the technical spirit of the present invention, and still fall within the protection scope of the technical solution of the present invention.
Claims (4)
1. A method for optimizing parameters of an ingot blank spray forming process is characterized by comprising the following steps: acquiring technological parameters on a spray forming production line, wherein the technological parameters comprise controllable parameters and process parameters; according to the acquired process parameter data, optimizing the spray forming process parameters according to two stages: the first stage, according to the collected process data of the spray forming process, searching the relation between the process parameters and the diameter of the deposition surface of the ingot blank, and establishing a diameter prediction model and a parameter optimization model; the second stage, collecting spray forming technological parameters in real time in the processing process, and optimizing spray forming deposition parameters by using the parameter optimization model established in the first stage;
in the first stage of optimizing the spray forming process parameters, an ingot deposition surface diameter prediction model and a spray forming process parameter optimization model are established, and the method comprises the following steps:
step 1-1: collecting technological parameters of an industrial production line at different moments and measuring diameter values of prepared ingot blanks at different heights;
step 1-2: screening out process parameters with high correlation degree with the diameter value of the ingot blank by applying a Pearson correlation coefficient and significance test;
step 1-3: normalizing the process parameters which are obtained in the step 1-2 and have high correlation degree with the diameter value of the ingot blank; different orders of magnitude and units exist among the spray forming process parameters, and non-dimensionalization treatment is carried out through normalization so that all the process parameters are in the same order of magnitude;
step 1-4: determining basic elements of a prediction model structure and a genetic algorithm of the ingot blank diameter;
step 1-5: calculating the parameter variation of the current moment corresponding to the previous moment according to the spray forming process parameters acquired in the step 1-1, and calculating the diameter variation of the deposition surface of the ingot blank; carrying out normalization processing after obtaining input parameters and output parameters of the spray forming process parameter optimization model;
step 1-6: determining input and output parameters of a spray forming process parameter optimization model, a model structure and basic elements of a genetic algorithm, and establishing the optimization model;
in the second stage of optimizing the spray forming process parameters, the lifting speed of the deposition substrate is optimized on line in the spray forming processing process according to the established ingot blank deposition surface diameter prediction model and the spray forming process parameter optimization model, and the specific steps are as follows:
step 2-1: collecting technological parameters in real time in the spray forming process, normalizing the technological parameters with high correlation degree with the diameter value of the ingot blank by using a diameter prediction model, inputting the normalized technological parameters into the prediction model, and outputting the model to obtain a predicted diameter value;
step 2-2: calculating the variation of the process parameters at the current moment compared with the variation at the previous moment, and calculating the diameter variation with the previous moment;
step 2-3: applying a spray forming process parameter optimization model, normalizing the process parameter variation and the diameter variation, inputting the normalized process parameter variation and the normalized diameter variation into the optimization model, and outputting the model to obtain the deposition substrate lifting speed reference variation;
step 2-4: and adjusting the lifting speed of the deposition substrate according to the optimized speed reference value.
2. The method for optimizing parameters of a spray forming process of an ingot blank according to claim 1, wherein the method comprises the following steps: the controllable parameters comprise the rotating speed of the deposition substrate, the lifting speed of the deposition substrate, the rotating speed of the leaky ladle dumping device and the air exhaust speed of the deposition chamber.
3. The method for optimizing parameters of a spray forming process of an ingot blank according to claim 1, wherein the method comprises the following steps: the process parameters include: the nozzle spray nozzle comprises a nozzle, a nozzle, a nozzle, a nozzle, and a nozzle.
4. The method for optimizing parameters of a spray forming process of an ingot blank according to claim 1, wherein the method comprises the following steps: in steps 1-4, the basic elements of the adopted network model structure and genetic algorithm include the number of neurons in the input layer and the output layer of the network, the number of network layers, an activation function, a training function, a population coding mode, the number of termination iterations, the population scale, an individual fitness function and a genetic operator, wherein the genetic operator includes selection, intersection and variation probability.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110341349.1A CN113059184B (en) | 2021-03-30 | 2021-03-30 | Optimization method for parameters of ingot blank spray forming process |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110341349.1A CN113059184B (en) | 2021-03-30 | 2021-03-30 | Optimization method for parameters of ingot blank spray forming process |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113059184A CN113059184A (en) | 2021-07-02 |
| CN113059184B true CN113059184B (en) | 2022-08-05 |
Family
ID=76564683
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110341349.1A Active CN113059184B (en) | 2021-03-30 | 2021-03-30 | Optimization method for parameters of ingot blank spray forming process |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113059184B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116275124B (en) * | 2023-05-11 | 2023-08-01 | 四川大学 | Laser additive manufacturing partition control method based on model-free self-adaptive iterative learning |
Family Cites Families (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20060229852A1 (en) * | 2005-04-08 | 2006-10-12 | Caterpillar Inc. | Zeta statistic process method and system |
| GB201510220D0 (en) * | 2015-06-11 | 2015-07-29 | Renishaw Plc | Additive manufacturing apparatus and method |
| CN105108147A (en) * | 2015-09-21 | 2015-12-02 | 江苏豪然喷射成形合金有限公司 | Production process for achieving ingot blank continuous spray deposition |
| CN105345004B (en) * | 2015-10-15 | 2018-09-14 | 江苏豪然喷射成形合金有限公司 | A method of it utilizes and is injected into the standby three-dimensional big specification aluminium lithium alloy billet of shape |
| CN105170980B (en) * | 2015-10-20 | 2017-04-12 | 江苏豪然喷射成形合金有限公司 | Method for establishing inclined twin-jet-nozzle scanning spray forming technological parameters |
| DE102019200482A1 (en) * | 2019-01-16 | 2020-07-16 | Robert Bosch Gmbh | Method and device for the automated machining of a workpiece with a machine tool |
| CN111408721A (en) * | 2020-04-03 | 2020-07-14 | 北京机科国创轻量化科学研究院有限公司 | Aluminum alloy semi-solid state melting three-dimensional direct-writing forming method |
| CN112375946B (en) * | 2020-10-27 | 2021-08-13 | 湖南农业大学 | High Mg2Si-aluminum alloy, design and rapid solidification preparation method and application thereof |
| CN112329275B (en) * | 2021-01-04 | 2021-04-02 | 四川大学 | Laser metal additive deposition fusion state real-time prediction method and system |
-
2021
- 2021-03-30 CN CN202110341349.1A patent/CN113059184B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN113059184A (en) | 2021-07-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112427624B (en) | Casting and forging double-control forming system based on digital twinning and parameter optimization method | |
| CN111353656A (en) | Steel enterprise oxygen load prediction method based on production plan | |
| CN113059184B (en) | Optimization method for parameters of ingot blank spray forming process | |
| CN103019103B (en) | Simulation optimization method of fuzzy control variable heating temperatures in directional solidification process | |
| Ming et al. | Soft computing models and intelligent optimization system in electro-discharge machining of SiC/Al composites | |
| CN103942422B (en) | Granular-computation-based long-term prediction method for converter gas holder positions in metallurgy industry | |
| CN102508965B (en) | Adaptive variable-speed drawing simulation method for directional solidification blade production | |
| Ohdar et al. | Prediction of the process parameters of metal powder preform forging using artificial neural network (ANN) | |
| CN115121771B (en) | Intelligent ultrasonic continuous casting method and measuring and controlling device for metal section | |
| CN107832983B (en) | Casting smelting batch planning and scheduling method based on dynamic programming and genetic algorithm | |
| CN111676365A (en) | LSTM-based method for predicting annealing temperature set value of transition steel coil | |
| CN116882585A (en) | Genetic algorithm and neural network coupled aluminum alloy hub low-pressure casting process optimization method | |
| CN111832215A (en) | Method for on-line predicting steel plate structure performance | |
| CN108509719A (en) | A kind of ironcasting based on BP neural network breaks core prediction technique and system | |
| CN109240203B (en) | Multi-model-based continuous casting billet constant weight control method | |
| CN112185474B (en) | Numerical simulation method for directional solidification process of Ti-45% Al alloy | |
| CN116384254A (en) | Error correction method and system for predicting molten steel temperature of LF refining furnace | |
| Antonova et al. | Development of simulation model of continuous casting machine with dry change of steel ladles | |
| CN116070519A (en) | DADOS (digital data aided design) optimization design cloud system-based lightweight design method for upper beam of certain large combined press | |
| CN113240096A (en) | Casting cylinder cover micro-structure prediction method based on rough set and neural network | |
| CN114117684A (en) | Selective laser melting forming 316L stainless steel abrasion prediction method based on machine learning | |
| Zhang et al. | Optimizing casting parameters of ingot based on neural network and genetic algorithm | |
| CN102479259A (en) | Optimization of laser strengthening process for mold surface | |
| Chen et al. | Additive manufacturing of high value Ti components: opportunities and challenges | |
| CN107273635A (en) | A kind of online planing method of contour forging technique for controlling nickel-base alloy microstructure to be distributed |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |