CN115329475A - Part preparation method and equipment based on partition multi-stage cryogenic treatment - Google Patents
Part preparation method and equipment based on partition multi-stage cryogenic treatment Download PDFInfo
- Publication number
- CN115329475A CN115329475A CN202210837481.6A CN202210837481A CN115329475A CN 115329475 A CN115329475 A CN 115329475A CN 202210837481 A CN202210837481 A CN 202210837481A CN 115329475 A CN115329475 A CN 115329475A
- Authority
- CN
- China
- Prior art keywords
- cryogenic treatment
- treatment
- cryogenic
- neural network
- target part
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/10—Geometric CAD
- G06F30/17—Mechanical parametric or variational design
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—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
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/12—Computing arrangements based on biological models using genetic models
- G06N3/126—Evolutionary algorithms, e.g. genetic algorithms or genetic programming
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2111/00—Details relating to CAD techniques
- G06F2111/10—Numerical modelling
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Biophysics (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Software Systems (AREA)
- Computing Systems (AREA)
- General Health & Medical Sciences (AREA)
- Mathematical Physics (AREA)
- Geometry (AREA)
- Biomedical Technology (AREA)
- Molecular Biology (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Physiology (AREA)
- Computer Hardware Design (AREA)
- Medical Informatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Genetics & Genomics (AREA)
- Computational Mathematics (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention belongs to the technical field related to cryogenic treatment, and discloses a part preparation method and equipment based on partitioned multistage cryogenic treatment, which comprises the following steps: (1) Establishing a nonlinear mapping relation between the parameters of the multilevel cryogenic process, the microstructure and the performance through a neural network; (2) Dividing the target part into a plurality of sub-regions, and reversely deducing multi-stage cryogenic treatment parameters required by each sub-region so as to obtain a series of cryogenic process parameter distribution combinations corresponding to the interior of the target part; (3) Carrying out high-flux numerical simulation on the partitioned multistage cryogenic treatment process to determine the optimal cryogenic treatment parameter combination of different areas in the target part; (4) And carrying out partitioned independent cryogenic treatment on the part to be treated to obtain the target part. The invention solves the technical problems of low applicability and complex process of the cryogenic treatment of parts in the prior art.
Description
Technical Field
The invention belongs to the technical field related to cryogenic treatment, and particularly relates to a part preparation method and equipment based on partitioned multistage cryogenic treatment.
Background
The light-weight structural parts, such as a blisk, a turbine disk and the like can reduce weight by about 30%, and the thrust-weight ratio and the use reliability of the engine are improved. The blisk and turbine disk parts have larger temperature gradient and stress gradient along the radial direction, different areas have different requirements on material performance, the blade stress has excellent high-cycle fatigue resistance, and the disk body stress has high-temperature creep resistance and damage tolerance performance. The working temperature of the disc spoke of the turbine disc is relatively low, and the fine grain structure better meets the requirements of high yield strength and low cycle fatigue performance of the disc spoke; the relatively high rim temperature and the high creep and damage tolerance of the macrocrystalline structure avoids possible microcracks in the mortise. In order to further exert the performance potential of parts such as blisks, proper alloy materials and structural states are selected according to actual service environments of different regions of the parts, so that scientists propose the design idea of double-performance blisks and turbine discs, break through the inertial thinking that the traditional hot working technology pursues uniform structures, and develop a series of single-alloy double-performance or double-alloy gradient structure parts with gradient microstructure characteristics.
The manufacturing method of the prior gradient structure metal parts, particularly the representative parts such as a double-performance blisk, a turbine disk and the like mainly comprises a welding method, a sectional temperature control forging method and a sectional temperature control heat treatment method. The welding method can realize the connection of different materials, but the biggest problem is that the connection area is often a weak link of the whole component, which is a great hidden danger for the high-speed rotating part of the aeroengine with high reliability and long service life. Compared with a partitioned temperature control forging process, the partitioned temperature control heat treatment process is adopted, a stable and controllable temperature gradient is formed between the blade and the disc body more easily, so that the required double structures are obtained, the operation of the process is relatively easy, and the consistency is good. After the traditional heat treatment, the material still has some defects, such as unstable structure, higher thermal stress and structure stress, uneven structure and the like after quenching, which all deteriorate the material performance and further affect the service life of the material. Generally, the problems are difficult to solve by a single heat treatment process, and the deep cooling treatment as an important additional process of the heat treatment can effectively perform secondary optimization on the performance of the material after the heat treatment, and has a remarkable effect of prolonging the service life of the material.
The cryogenic treatment is that the material (or the workpiece) is placed in a certain low-temperature environment (below minus 130 ℃), and the material is treated by controlling the process parameters such as the cryogenic treatment temperature, the temperature rise and fall rate, the heat preservation time, the treatment times and the like, so that the microstructure of the material is subjected to irreversible transformation in different degrees, and the aim of improving the comprehensive performance is fulfilled. Researches show that the cryogenic treatment has obvious modification effect on materials such as die steel, high-temperature alloy, titanium alloy, hard alloy, amorphous alloy, high-entropy alloy and the like, and has the effects of promoting transformation of residual austenite, refining crystal grains, improving dislocation density, promoting generation of twin and sub-crystal tissues, promoting phase transformation and carbide precipitation, promoting generation of textures and the like.
For the parts with gradient structures, the requirements of different parts on structures and even different alloy types exist, and the requirements on cryogenic treatment are greatly different. The common cryogenic treatment mode for the parts adopts a heat insulation material to wrap a region which is not subjected to cryogenic treatment at a certain stage, and the common cryogenic treatment mode usually needs multiple working procedures, is complex in working procedure and has poor effect. The existing cryogenic treatment process and device are only suitable for single-material and uniform parts, and are difficult to meet the cryogenic requirements of different areas of parts with gradient structures, such as a dual-performance bladed disk, a turbine disk and the like.
Disclosure of Invention
Aiming at the defects or improvement requirements of the prior art, the invention provides a part preparation method and equipment based on partitioned multistage cryogenic treatment, the preparation method obtains parts with corresponding organization characteristics and performance distribution by controlling the temperature gradient field distribution in a sample in the multistage cryogenic treatment process, and differential cryogenic treatment of different regions of the parts can be realized by optimizing process parameters such as temperature, heat preservation time and the like in the multistage cryogenic treatment process, so that target organization and performance distribution are obtained, and the technical problems of low applicability and complex process of the cryogenic treatment of the parts in the prior art are solved.
In order to achieve the above object, according to one aspect of the present invention, there is provided a method for manufacturing a part based on a partitioned multistage cryogenic treatment, the method mainly comprising the steps of:
(1) Obtaining a tissue-performance evolution rule of material components of a target part through a multi-stage cryogenic treatment experiment, and establishing a non-linear mapping relation between multi-stage cryogenic process parameters, microstructures and performance through a neural network;
(2) Dividing the target part into a plurality of sub-regions according to the organization performance distribution requirement of the target part, and reversely deducing multi-stage cryogenic treatment parameters required by each sub-region by combining the obtained nonlinear mapping relation, thereby obtaining a series of cryogenic process parameter distribution combinations corresponding to the interior of the target part when the multi-stage cryogenic treatment is adopted for the target part;
(3) Carrying out high flux numerical simulation on the partition multistage cryogenic treatment process by combining the obtained cryogenic process parameter distribution combination, and determining the cryogenic treatment process parameter combination corresponding to the structural performance distribution requirement that the temperature distribution or the microstructure distribution is closest to the target part during the numerical simulation as the optimal cryogenic treatment parameter combination of different areas in the target part;
(4) And performing partition independent type cryogenic treatment on the part to be treated by combining the geometric partition area of the target part and the optimal cryogenic treatment parameter combination to obtain the target part.
Further, the acquisition of the tissue-property evolution law of the material composition of the target part comprises the following steps: use the material of target part as initial experimental object, in the cryogenic treatment parameter range that sets up in advance, set up orthogonal experiment or single factor test, it is right under different cryogenic treatment process parameter conditions initial experimental object carries out multistage cryogenic treatment to carry out microstructure characteristic and capability test to the sample that cryogenic treatment obtained, obtain microstructure characteristic parameter and performance data in the sample under different cryogenic treatment parameter conditions, and then obtain multistage cryogenic treatment process parameter-microstructure-performance database.
Further, the multi-stage cryogenic treatment refers to a process of carrying out heat preservation and temperature rise and drop processes for a plurality of times from the initial treatment temperature to the lowest treatment temperature; the microstructural characteristic parameters include one or more of grain size, dislocation density, volume fraction of retained austenite, size and volume fraction of carbide phase; the multi-stage cryogenic treatment process parameters comprise one or more of temperature, heat preservation time, temperature rise and drop rate and treatment times.
Further, the established nonlinear mapping relation between the multi-stage cryogenic process parameters, the microstructure and the performance comprises a cryogenic treatment process parameter-microstructure relation model, a microstructure-performance relation model and a cryogenic treatment process parameter-performance relation model.
Furthermore, each relation model is described by adopting a BP neural network model containing a plurality of hidden layers, wherein the establishment of the non-linear mapping relation between the cryogenic process parameters and the microstructure comprises the following steps:
taking a set of cryogenic process parameters obtained by a multistage cryogenic treatment experiment as input, taking an obtained microstructure characteristic parameter set as output, constructing and training a BP neural network model containing multiple hidden layers, and selecting appropriate excitation functions for the hidden layers and the output layers; optimizing the initial weight and threshold of the BP neural network by using a genetic algorithm to obtain the weight and threshold of the optimal individual; and assigning the obtained weight and threshold of the optimal individual to the BP neural network model, and updating the weight and threshold of each hidden layer by using an error inverse propagation algorithm in the training process until the cost function J is less than the set precision or reaches the maximum iteration number, and finishing the training.
Further to this, the excitation functions of the hidden layers all select the logistic function, and the excitation functions of the output layers select the linear function g (x) = x.
Further, optimizing the initial weight and threshold of the BP neural network by adopting a genetic algorithm, and specifically comprising the following steps:
s1: firstly, determining the weight value and the number of threshold values of the neural network according to the topological graph of the BP neural network model, and following the following formula:
wherein N is um I represents the i-th layer neuron, H is the total number of weight values and threshold values i The number of nodes of the i-th layer neuron;
s2: adopting a real number coding mode to carry out coding operation on the weight threshold value of the neural network, initializing a population, randomly taking values of the initial weight threshold value between (-1, 1), and setting a fitness function of the population as F1;
wherein F1 is the fitness value, ρ 1 is the enhancement phase component predicted by the neural network using the initial weight and the threshold, η 1 is the enhancement phase volume fraction predicted by the neural network using the initial weight and the threshold, δ 1 is the enhancement phase average size predicted by the neural network using the initial weight and the threshold, ρ 0 For enhancing the phase composition expectation, η 0 To enhance the phase volume fraction expectation, δ 0 Desired value for average size of the enhancement phase;
s3: calculating the fitness value of all individuals in the population, and selecting the individuals with high fitness from the parents by using a roulette algorithm to generate the next generation of individuals, wherein the probability of each selected individual follows the following formula:
wherein p is k Probability of being selected for the kth individual, F k Is the fitness value of the kth individual, and K is the total number of individuals in the population;
s4: carrying out cross operation on individuals in the population, setting the cross probability as pc, carrying out cross operation if a random number is generated and is smaller than the cross probability, randomly selecting two individuals and randomly selecting a cross position during cross, and carrying out cross operation according to the following formula:
wherein, a kj Is the real number of the kth chromosome at position j, a lj Is the real number of the l-th chromosome at position j, b is a random number between (0, 1);
s5: carrying out mutation operation on individuals in the population, setting the mutation probability as pm, carrying out mutation operation if a random number is generated and is smaller than the mutation probability, randomly selecting one individual and randomly selecting a mutation site during mutation, and carrying out mutation operation according to the following formula:
wherein, a ij Is the real number of the ith chromosome at position j, G is the current iteration number, f (G) is the variation factor, G max To the maximum number of iterations, a max Is a ij Upper limit of value, a min Is a ij The lower limit of the value, r and r' are random numbers between (0, 1);
s6: and (5) circulating the steps S3 to S5 until a satisfactory fitness value is obtained or a limited iteration number is reached, and outputting an optimal individual, namely an individual with the maximum fitness value.
According to another aspect of the invention, a part preparation apparatus based on partitioned multistage cryogenic treatment is provided, which prepares a part by using the part preparation method based on partitioned multistage cryogenic treatment as described above; the equipment is formed with a plurality of independent subzero treatment chambers, and each subzero treatment chamber can independently treat a section region of preparation part for subzero treatment.
Furthermore, each cryogenic treatment chamber is respectively provided with an independent resistance heating wire, a temperature sensor, an inlet pipe and an outlet pipe of a cooling medium and a moving mechanism, so that each cryogenic treatment chamber can independently work to carry out cryogenic treatment on a local area of the target part.
Furthermore, the equipment also comprises a plurality of heat insulation plates, and an accommodating cavity is formed in the equipment, and the heat insulation plates are arranged in the accommodating cavity at intervals so as to divide the accommodating cavity into a plurality of independent cryogenic treatment chambers; the heat insulation plate is also used for bearing parts to be prepared; and each heat insulation plate is connected with one moving mechanism, and the moving mechanism is used for driving the heat insulation plates to move so as to change the space size of the cryogenic treatment chambers on the two sides of the heat insulation plates.
Generally, compared with the prior art, the part preparation method and equipment based on partitioned multistage cryogenic treatment provided by the invention mainly have the following beneficial effects:
1. the preparation method comprises the steps of utilizing the fact that the microstructure and performance evolution of a metal material during cryogenic treatment directly depend on the temperature field distribution during cryogenic treatment, reversely deducing the gradient temperature field distribution required by the multi-stage cryogenic treatment of the target part according to the microstructure and performance requirements of the target part, determining a geometric partition scheme capable of obtaining the target gradient temperature field distribution through numerical simulation, finally adopting reversely deduced multi-stage cryogenic treatment parameters and geometric partition scheme, adjusting the space of each chamber of a cryogenic treatment device, setting the cryogenic treatment program of each chamber, and obtaining the target part.
2. The invention adopts a multi-stage cooling mode, compared with the traditional modes of directly immersing cooling media such as liquid nitrogen and the like, the invention has small thermal shock to parts, is not easy to generate cracks and deformation in the treatment process, and is suitable for thin-wall parts and brittle materials; meanwhile, aiming at the cryogenic treatment requirements of different areas of the part, a partition cryogenic treatment mode is adopted, the microstructure and mechanical property regulation and control of the whole part can be completed through one-time cryogenic treatment, the cryogenic treatment process of the part is obviously simplified, the treatment efficiency is improved, the microstructure and mechanical property transition between different areas is good, the interface stress concentration in the service process of the part can be avoided, and the service life of the whole part is prolonged.
3. According to the invention, orthogonal experiments or single-factor experiments of multi-stage cryogenic treatment are firstly carried out on material components of a target part to obtain microstructures and performance data of the target part under different cryogenic treatment parameters, then, the neural network technology is utilized to establish complex nonlinear mapping relations of the cryogenic treatment parameters such as temperature, heat preservation time, temperature rise and fall rate, treatment times, microstructure parameters such as grain size, dislocation density, residual austenite volume fraction, carbide and other precipitated phase volume fractions and performance parameters such as yield strength, room temperature plasticity, fracture strength, bending strength, hardness and the like by means of the experimental data, so that the cryogenic treatment parameters and complex influence rules between microstructures and performance can be comprehensively reflected, a required gradient temperature field can be reversely deduced, technological parameters can be optimized, the times of the pre-experiments can be reduced, and the rapid and intelligent formulation of the part partition multi-stage cryogenic treatment process can be realized.
4. This equipment changes the single cavity of traditional cryogenic device into the multi-chamber design, and each cavity is independent accuse temperature, the space is nimble adjustable and set up the insulating layer between each cavity, can satisfy the cryogenic demand of the complicated shape part that single alloy gradient tissue or many alloy tissue are constituteed, is showing and has simplified the cryogenic treatment process, and the cryogenic treatment effect is better.
Drawings
FIG. 1 is a schematic flow diagram of a part preparation method based on partitioned multistage cryogenic treatment provided by the invention;
FIG. 2 is a schematic structural diagram of a part manufacturing apparatus based on partitioned multi-stage cryogenic treatment according to an embodiment of the present invention;
FIG. 3 is a sectional view of the part manufacturing apparatus based on the divisional multi-stage cryogenic treatment in FIG. 2;
FIG. 4 is a partial schematic view of the part manufacturing apparatus based on zoned multi-stage cryogenic treatment of FIG. 2;
FIG. 5 is a schematic view of the part manufacturing apparatus based on partitioned multi-stage cryogenic treatment in FIG. 2 in an open-closed state;
FIG. 6 is a schematic structural diagram of a part manufacturing apparatus based on partitioned multistage cryogenic treatment according to another embodiment of the present invention;
FIG. 7 is a sectional view of the part manufacturing apparatus based on the divisional multi-stage cryogenic treatment in FIG. 6;
FIG. 8 is a partial schematic view of the part manufacturing apparatus based on zoned multi-stage cryogenic treatment of FIG. 6;
FIG. 9 is a schematic diagram of the part manufacturing apparatus based on the zone-specific multi-stage cryogenic treatment in FIG. 6 in an open/close state.
The same reference numbers will be used throughout the drawings to refer to the same elements or structures, wherein: 1-an upper pipeline chamber, 2-an upper chamber, 3-a lower chamber, 4-a lower pipeline chamber, 5-a connecting mechanism, 6-a liquid nitrogen pipe, 7-a moving mechanism, 8-a heat insulation layer, 9-a resistance heating wire, 10-a thermocouple, 11-a plate-shaped gradient structure part, 12-a thermocouple signal wire, 13-a temperature control system, 14-a heat insulation plate and 15-a disc-shaped gradient structure part.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention. In addition, the technical features involved in the embodiments of the present invention described below may be combined with each other as long as they do not conflict with each other.
Referring to fig. 1, the invention provides a part preparation method based on partition multistage cryogenic treatment, which can realize flexible setting of microstructure of parts, fast optimization of performance partitions, better continuity of structure performance among different areas, small thermal shock generated by multistage treatment, difficulty in cracking of parts in a treatment process, and wide range of applicable part types and materials. The preparation method can be used for preparing parts with gradient structures and uniform structures.
The invention provides a part preparation method based on partitioned multistage cryogenic treatment, which mainly comprises the following steps:
the method comprises the steps of firstly, obtaining a tissue-performance evolution rule of material components of a target part through a multi-stage cryogenic treatment experiment, and establishing a non-linear mapping relation between multi-stage cryogenic process parameters, microstructures and performances through a neural network.
The method for obtaining the tissue-performance evolution law of the material components of the target part through a multi-stage cryogenic treatment experiment specifically comprises the following steps: use the material of target part as initial experimental object, in the cryogenic treatment parameter range that sets up in advance, set up orthogonal experiment or single factor test, it is right under different cryogenic treatment process parameter conditions initial experimental object carries out multistage cryogenic treatment to carry out microstructure characteristic and capability test to the sample that cryogenic treatment obtained, obtain microstructure characteristic parameter and performance data in the sample under different cryogenic treatment parameter conditions, and then obtain multistage cryogenic treatment process parameter-microstructure-performance database.
The multi-stage cryogenic treatment refers to a process of carrying out heat preservation and temperature rise and drop processes for a plurality of times from the initial treatment temperature to the lowest treatment temperature. The microstructural characteristic parameters include one or more of grain size, dislocation density, volume fraction of retained austenite, size and volume fraction of carbide phase. The multi-stage cryogenic treatment process parameters comprise one or more of temperature, heat preservation time, temperature rise and drop rate and treatment times. The property data includes mechanical properties of the material, such as yield strength, fracture strength, and electromagnetic properties, such as one or more of electrical conductivity, magnetic permeability, and thermal conductivity.
Phase composition and dislocation density in the cryogenic treatment sample are determined through X-ray diffraction analysis (XRD), and grain size, residual austenite volume fraction, size and volume fraction of carbide phase and the like in the cryogenic treatment sample are obtained through a metallographic microscope or scanning electron microscope, EBSD and other means.
The established non-linear mapping relation between the cryogenic treatment process parameter-microstructure-performance of the material component of the target part comprises 3 relation models such as a cryogenic treatment process parameter-microstructure relation model, a microstructure-performance relation model, a cryogenic treatment process parameter-performance relation model and the like.
Each relation model is described by a BP neural network model comprising a plurality of hidden layers, wherein the establishment of the non-linear mapping relation between the cryogenic process parameters and the microstructure comprises the following steps:
taking a set of cryogenic process parameters obtained by the multistage cryogenic treatment experiment as input, taking an obtained microstructure characteristic parameter set as output, constructing and training a BP neural network model containing multiple hidden layers, and selecting appropriate excitation functions for each hidden layer and each output layer; optimizing the initial weight and threshold of the BP neural network by using a genetic algorithm to obtain the weight and threshold of the optimal individual; and assigning the obtained weight and threshold of the optimal individual to the BP neural network model, and updating the weight and threshold of each hidden layer by using an error inverse propagation algorithm in the training process until the cost function J is less than the set precision or reaches the maximum iteration number, and finishing the training.
The excitation functions of the hidden layers are all selected from a logistic function, and the excitation function of the output layer is selected from a linear function g (x) = x.
Optimizing the initial weight and threshold of the BP neural network by adopting a genetic algorithm, and specifically comprising the following steps:
s1: firstly, determining the weight value and the number of threshold values of the neural network according to the topological graph of the BP neural network model, and following the following formula:
wherein N is um I represents the i-th layer neuron, H is the total number of weight values and threshold values i The number of nodes of the i-th layer neuron;
s2: adopting a real number coding mode to carry out coding operation on the weight threshold value of the neural network, initializing a population, randomly taking values of the initial weight threshold value between (-1, 1), and setting a fitness function of the population as F1;
wherein F1 is a fitness value, ρ 1 is an enhanced phase component predicted by the neural network using an initial weight and a threshold, η 1 is an enhanced phase volume fraction predicted by the neural network using an initial weight and a threshold, δ 1 is an enhanced phase average size predicted by the neural network using an initial weight and a threshold, ρ 0 For enhancing the phase composition expectation, η 0 To enhance the phase volume fraction expectation, δ 0 Desired value for average size of the enhancement phase;
s3: calculating the fitness value of all individuals in the population, and selecting the individuals with high fitness from the parents by using a roulette algorithm to generate the next generation of individuals, wherein the probability of each selected individual follows the following formula:
wherein p is k Probability of being selected for the kth individual, F k Is the fitness value of the kth individual, and K is the total number of individuals in the population;
s4: carrying out cross operation on individuals in the population, setting the cross probability as pc, carrying out cross operation if a random number is generated and is smaller than the cross probability, randomly selecting two individuals and randomly selecting a cross position during cross, and carrying out cross operation according to the following formula:
wherein, a kj Is the real number of the kth chromosome at position j, a lj Is the real number of the l-th chromosome at position j, b is a random number between (0, 1);
s5: carrying out mutation operation on individuals in the population, setting the mutation probability as pm, carrying out mutation operation if a random number is generated and is smaller than the mutation probability, randomly selecting one individual and randomly selecting a mutation site during mutation, and carrying out mutation operation according to the following formula:
wherein, a ij Is the real number of the ith chromosome at position j, G is the current iteration number, f (G) is the variation factor, G max To the maximum number of iterations, a max Is a ij Upper limit of value, a min Is a ij The lower limit of the value, r and r' are random numbers between (0, 1);
s6: and (5) circulating the steps S3 to S5 until a satisfactory fitness value is obtained or a limited iteration number is reached, and outputting an optimal individual, namely the individual with the maximum fitness value.
Dividing the target part into a plurality of sub-regions according to the organization performance distribution requirement of the target part, and reversely deducing multi-stage cryogenic treatment parameters required by each sub-region by combining the obtained nonlinear mapping relation, thereby obtaining a series of cryogenic process parameter distribution combinations corresponding to the interior of the target part when the multi-stage cryogenic treatment is adopted for the target part.
And thirdly, performing high-flux numerical simulation on the partition multistage cryogenic treatment process by combining the obtained cryogenic process parameter distribution combination, and determining the cryogenic treatment process parameter combination corresponding to the structure performance distribution requirement that the temperature distribution or the microstructure distribution is closest to the target part during numerical simulation as the optimal cryogenic treatment parameter combination of different areas in the target part.
The multistage cryogenic treatment process is subjected to heat transfer simulation or heat transfer-microstructure coupling simulation by using commercial numerical simulation software such as Deform, abaqus, ansys or Comsol in numerical simulation.
And step four, performing partitioned independent cryogenic treatment on the part to be treated by combining the geometric partition area of the target part and the optimal cryogenic treatment parameter combination to obtain the target part.
The present invention is further described in detail below with reference to several examples.
Example 1
The target part is a high-temperature alloy GH2132 dual-performance plate-shaped part, the working temperature of the middle part of the part is low, the size of the structural grains is required to be small, sufficient strength, creep resistance and fatigue resistance are guaranteed, the working temperature borne by the edge part is high, the coarse grain structure is required, and room-temperature plasticity, creep resistance and fatigue expansion resistance are guaranteed. Therefore, different areas of the target plate-like part are required to have different grain size microstructures to obtain corresponding mechanical properties. According to the actual service working condition of the part, the target gradient structure part is divided into 4 characteristic regions, the crystal grains at the central part are in an ultra-fine crystal structure, the average crystal grains are smaller than 1 mu m, the edge part is in a coarse crystal grain structure, the average crystal grain size is 100 mu m, and the crystal grain size in the middle region is gradually transited. Meanwhile, the Vickers hardness of the central part is not less than 380HV, the tensile strength at room temperature is not less than 800MPa, the tensile plasticity at room temperature is not less than 20 percent, the Vickers hardness of the edge area is not less than 300HV, the tensile strength at room temperature is not less than 500MPa, and the tensile plasticity at room temperature is not less than 40 percent. The partition multi-stage cryogenic treatment method comprises the following steps:
(1) The tissue-performance evolution law of the high-temperature alloy GH2132 is obtained through a multistage cryogenic treatment experiment, the parameters of the multistage cryogenic treatment process are selected from temperature, and a two-stage temperature curve comprises temperature T 1 And T 2 The microstructure parameters are selected as grain size and the performance parameters are selected as dimensionHardness, tensile strength and room temperature tensile plasticity. And establishing a nonlinear mapping relation between the multi-stage cryogenic process parameters, the microstructure and the performance through a BP neural network.
The subzero treatment temperature is set to-50 ℃, to-75 ℃, to-100 ℃, to-125 ℃, to-150 ℃, to-175 ℃ and to-196 ℃, the heat preservation time is 1h, the temperature rise and fall speed is 50 ℃/min, and the treatment frequency is 1. And (4) shooting a metallographic picture after metallographic grinding and polishing to determine the average grain size after multistage cryogenic treatment, and counting the grain size distribution and the average grain size through ImageJ image software. The Vickers Hardness was measured by a 430SVD Vickers Hardness tester of Wilson Hardness, USA, with a load of 1kg, and the Hardness was measured at 5 points per sample, and the average value of the maximum and minimum values of the data was taken as the Hardness of the sample. The tensile bar stock is a standard tensile sample with the diameter of 10mm, a room-temperature quasi-static tensile experiment is carried out by specifically referring to the requirements of GB/T228-2010 metal material room-temperature tensile test method, and room-temperature tensile strength and room-temperature tensile plasticity data are counted.
Establishing a nonlinear mapping relation among temperature, grain size, vickers hardness, tensile strength at room temperature and tensile plasticity at room temperature through a BP neural network, and taking experimental data obtained by a pre-experiment as a training sample until ideal prediction precision is achieved.
(2) Dividing the target gradient structure plate-shaped part into 4 characteristic regions according to the actual service working condition of the part, reversely deducing the multi-stage cryogenic treatment parameters required by each sub-region by combining the obtained nonlinear mapping relation, and further obtaining a series of cryogenic process parameter distribution combinations inside the target part when the multi-stage cryogenic treatment is adopted.
(3) And (3) combining the step (2) to obtain a series of cryogenic process parameter combinations in the target part, and performing high-flux numerical simulation on the partitioned multistage cryogenic treatment process, wherein the numerical simulation adopts comsol software. And determining the sub-zero treatment process parameter combination corresponding to the structure performance distribution requirement that the temperature distribution or the microstructure distribution is closest to the target part in the numerical simulation as the optimal sub-zero treatment parameter combination of different areas in the target part. In this embodiment, the sub-regions are subjected to multi-stage cryogenic treatmentIs region I: t is a unit of 1 At-175 ℃ and T 2 At-196 ℃, zone ii: t is 1 At-150 ℃ and T 2 Is-175 ℃, zone iii: t is 1 At-125 ℃ and T 2 Is-150 ℃, region iv: t is 1 At-100 ℃ T 2 Is-125 ℃. The temperature rising and reducing speed is unified to be 50 ℃/min, and the heat preservation time of each temperature stage is 1h.
(4) Combining the step target gradient structure plate part geometric partition area and the optimal subzero treatment parameter combination determined in the step (3), adjusting each chamber geometric space of the multi-chamber partition subzero treatment device, and carrying out partition independent subzero treatment on each chamber according to the optimal subzero treatment parameter determined in the step (3) so as to obtain the target gradient structure plate part.
Example 2
The target part is a high-temperature alloy GH2132 dual-performance disc-shaped part, the working temperature of the middle part of the same part is low, the size of the structural grains is required to be small, sufficient strength, creep resistance and fatigue resistance are guaranteed, the working temperature born by the edge part is high, the coarse grain structure is required, and room-temperature plasticity, creep resistance and fatigue expansion resistance are guaranteed. Therefore, different areas of the target plate-like part are required to have microstructures with different grain sizes to obtain corresponding mechanical properties. According to the actual service condition of the part, the target gradient structure part is divided into 3 characteristic areas, the crystal grains at the central part are ultra-fine crystal structures, the average crystal grains are smaller than 1 mu m, the edge part is a coarse crystal grain structure, the average crystal grain size is 100 mu m, and the crystal grain size of the middle area is gradually transited. Meanwhile, the Vickers hardness of the central part is not less than 380HV, the tensile strength at room temperature is not less than 800MPa, the tensile plasticity at room temperature is not less than 20 percent, the Vickers hardness of the edge area is not less than 300HV, the tensile strength at room temperature is not less than 500MPa, and the tensile plasticity at room temperature is not less than 40 percent.
And obtaining experimental data samples through a pre-experiment, and training the neural network by using the data samples until ideal prediction precision is achieved. And reversely deducing the multi-stage cryogenic treatment parameters of each region according to the nonlinear mapping relation between the process parameters, the organization and the performance established by the neural network. Determining the optimal process parameter combination by combining high-flux numerical simulation; and carrying out cryogenic treatment on the target gradient structure part by using a partitioned multistage cryogenic treatment device suitable for the disc part, and taking out the part after the treatment is finished so as to obtain the target gradient structure disc part with the gradient grain structure.
The invention also provides part preparation equipment based on the partition multi-stage cryogenic treatment, and the equipment adopts the part preparation method based on the partition multi-stage cryogenic treatment to prepare parts. The equipment is formed with a plurality of independent cryogenic treatment chambers, and each cryogenic treatment chamber can independently treat a section of region of preparation part for cryogenic treatment.
Referring to fig. 2, 3, 4 and 5, a part preparation apparatus based on a partitioned multistage cryogenic treatment according to an embodiment of the present invention includes an upper pipeline chamber 1, an upper chamber 2, a lower chamber 3, a lower pipeline chamber 4, a connection mechanism 5, a liquid nitrogen pipe 6, a moving mechanism 7, a heat insulation layer 8, a resistance heating wire 9, a thermocouple 10, a thermocouple signal line 12, a temperature control system 13 and a heat insulation plate 14.
The upper pipeline chamber 1, the upper chamber 2, the lower chamber 3 and the lower pipeline chamber 4 are sequentially connected together through a connecting mechanism 5 from top to bottom, the upper pipeline chamber 1 is fixedly connected with the upper chamber 2, the lower chamber 3 is fixedly connected with the lower pipeline chamber 4, and the upper chamber 2 is rotatably connected with one side of the lower chamber 3. The upper pipeline chamber 1 and the lower pipeline chamber 4 are both box bodies, the upper chamber 2 and the lower chamber 3 are rectangular frames, and the structures and the sizes of the upper chamber and the lower chamber correspond to each other respectively so as to realize closing.
The upper cavity 2 is provided with a first accommodating cavity, the lower cavity 3 is provided with a second accommodating cavity, and when the upper cavity 2 abuts against the lower cavity 3 through rotation, the first accommodating cavity and the second accommodating cavity are communicated to form an accommodating cavity. The first intracavity interval of acceping is provided with a plurality of heat insulating boards 14, the second is acceptd the chamber and is also provided with a plurality of heat insulating boards 14 at intervals, the first quantity and the position of acceping the intracavity heat insulating board 14 with the second is acceptd the quantity and the position of intracavity heat insulating board 14 and is corresponded respectively, in order to with it cuts apart into a plurality of independent cryogenic treatment cavities to accept the chamber. The two opposite heat insulation plates 14 are respectively provided with an accommodating groove, the shape and the size of a clamping groove formed by the two accommodating grooves are corresponding to the shape and the size of an area corresponding to a part to be manufactured, and the clamping groove is used for clamping the corresponding area of the part so as to conveniently and independently carry out cryogenic treatment on the area. In the present embodiment, the part to be prepared is a plate-like gradient structure part 11.
Two ends of each subzero treatment chamber are respectively and symmetrically provided with a resistance heating wire 9 and a thermocouple 10. The inner wall of each cryogenic treatment chamber is laid with a heat insulation layer 8, and the heat insulation layer 8 can be a vacuum heat insulation plate, an aerogel felt, an aluminum silicate fiber and the like; the cooling media of different cryogenic treatment chambers are isolated by sealing gaskets between the inner walls, and the contact parts of the inner walls and parts use conformal gaskets to ensure the sealing performance between the chambers, and the gaskets can be rubber gaskets, asbestos gaskets and the like with poor heat-conducting property and good sealing effect.
Each heat insulation plate 14 is respectively connected with a moving mechanism 7, and the moving mechanism 7 is used for supporting and driving the heat insulation plates 14 to move so as to change the space of the cryogenic treatment chambers on the two sides of the heat insulation plates 14. The thermocouple 10 is connected to the temperature control system 13 through a thermocouple signal line 12, and the temperature control system 13 is further connected to the resistance heating wire 9, a cooling medium supply system and an inlet pipe connected to the cooling medium supply system.
In this embodiment, the cooling medium may be liquid nitrogen, liquid helium, or a mixed liquid or gas of liquid nitrogen, liquid helium, alcohol, or other medium, and the cooling medium is introduced into the cryogenic treatment chamber through the cooling pipe; the temperature sensors can be thermocouples which are symmetrically arranged at two ends of a gradient part to be subjected to cryogenic treatment, and can also be other types of temperature sensors, the temperature of the cryogenic treatment chamber is determined as the average value of the temperature measurement values of the two temperature sensors, and the temperature control system controls the temperature of the corresponding cryogenic treatment chamber by adjusting the electric heating power of the corresponding resistance heating wire and the flow of the cooling medium; the moving mechanism is responsible for adjusting the position of the heat insulation inner wall between the chambers, flexibly adjusting the space size of each chamber and supporting and moving parts in the deep cooling device.
Referring to fig. 6, 7, 8 and 9, the apparatus for manufacturing a part according to another embodiment of the present invention is substantially the same as the apparatus for manufacturing a part according to the above embodiment, except for the shape of the heat-insulating plate and the arrangement of the liquid nitrogen pipe. The part to be prepared in the embodiment is a disk-shaped gradient structure part 15, the heat insulation plate is correspondingly formed by arc-shaped sheets, two opposite ends of each arc-shaped sheet are overlapped and connected into a circle, and then the two ends of each arc-shaped sheet are respectively arranged in the first accommodating cavity and the second accommodating cavity, the heat insulation plates in the first accommodating cavity are coaxially arranged, the heat insulation plates in the second accommodating cavity are also coaxially arranged, and the accommodating cavities are divided into a plurality of annular deep cooling treatment chambers. The size of the non-overlapping area at the two opposite ends of the arc-shaped sheet is changed to change the space size of the corresponding cryogenic treatment chamber. The outlet pipe and the inlet pipe are respectively communicated with the corresponding cryogenic treatment chambers through the straight branch pipes.
It will be understood by those skilled in the art that the foregoing is only a preferred embodiment of the present invention, and is not intended to limit the invention, and that any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the scope of the present invention.
Claims (10)
1. A part preparation method based on partition multi-stage cryogenic treatment is characterized by comprising the following steps:
(1) Obtaining a tissue-performance evolution rule of material components of a target part through a multi-stage cryogenic treatment experiment, and establishing a non-linear mapping relation between multi-stage cryogenic process parameters, microstructures and performance through a neural network;
(2) Dividing the target part into a plurality of sub-regions according to the tissue performance distribution requirement of the target part, and reversely deducing the multi-stage cryogenic treatment parameters required by each sub-region by combining the obtained nonlinear mapping relation so as to further obtain a series of cryogenic process parameter distribution combinations corresponding to the interior of the target part when the multi-stage cryogenic treatment is adopted for treating the target part;
(3) Performing high-flux numerical simulation on the multi-stage cryogenic treatment process by combining the obtained cryogenic process parameter distribution combination, and determining the cryogenic treatment process parameter combination corresponding to the structure performance distribution requirement that the temperature distribution or the microstructure distribution is closest to the target part during numerical simulation as the optimal cryogenic treatment parameter combination of different areas in the target part;
(4) And carrying out partitioned independent cryogenic treatment on the part to be treated by combining the geometric division area of the target part and the optimal cryogenic treatment parameter combination to obtain the target part.
2. The method for manufacturing a part according to claim 1, wherein the method comprises: the acquisition of the tissue-performance evolution law of the material composition of the target part comprises the following steps: the method comprises the steps of setting an orthogonal experiment or a single-factor experiment in a preset subzero treatment parameter range by using a material of a target part as an initial experimental object, carrying out multistage subzero treatment on the initial experimental object under different subzero treatment process parameter conditions, carrying out microstructure characterization and performance test on a sample obtained by subzero treatment, obtaining microstructure characteristic parameters and performance data in the sample under different subzero treatment parameter conditions, and further obtaining a multistage subzero treatment process parameter-microstructure-performance database.
3. The method for producing a part according to claim 2, wherein: the multi-stage cryogenic treatment refers to a process of carrying out heat preservation and temperature rise and drop processes for a plurality of times from the initial treatment temperature to the lowest treatment temperature; the microstructural characteristic parameters include one or more of grain size, dislocation density, volume fraction of retained austenite, size and volume fraction of carbide phases; the multi-stage sub-zero treatment process parameters comprise one or more of temperature, heat preservation time, temperature rise and fall rate and treatment times.
4. The method for producing a part according to claim 1, wherein the method comprises: the established nonlinear mapping relation among the multi-stage cryogenic process parameters, the microstructures and the performances comprises a cryogenic treatment process parameter-microstructure relation model, a microstructure-performance relation model and a cryogenic treatment process parameter-performance relation model.
5. The method for manufacturing a part according to claim 4, wherein the method comprises: each relation model is described by adopting a BP neural network model containing a plurality of hidden layers, wherein the establishment of the cryogenic process parameter-microstructure nonlinear mapping relation comprises the following steps:
taking a set of cryogenic process parameters obtained by a multistage cryogenic treatment experiment as input, taking an obtained microstructure characteristic parameter set as output, constructing and training a BP neural network model containing multiple hidden layers, and selecting appropriate excitation functions for the hidden layers and the output layers; optimizing the initial weight and threshold of the BP neural network by using a genetic algorithm to obtain the weight and threshold of the optimal individual; and assigning the obtained weight and threshold of the optimal individual to the BP neural network model, and updating the weight and threshold of each hidden layer by using an error inverse propagation algorithm in the training process until the cost function J is less than the set precision or the maximum iteration number is reached, and ending the training.
6. The method of claim 5, wherein the method comprises: the excitation functions of the hidden layers are all chosen as logistic functions, and the excitation functions of the output layers are chosen as linear functions g (x) = x.
7. The method of claim 5, wherein the method comprises: optimizing the initial weight and threshold of the BP neural network by adopting a genetic algorithm, and specifically comprising the following steps:
s1: firstly, determining the weight value and the number of threshold values of the neural network according to the topological graph of the BP neural network model, and following the following formula:
wherein N is um I represents the i-th layer neuron, H is the total number of weight values and threshold values i The number of nodes of the i-th layer neuron;
s2: adopting a real number coding mode to carry out coding operation on the weight threshold value of the neural network, initializing a population, randomly taking values of the initial weight threshold value between (-1, 1), and setting a fitness function of the population as F1;
wherein F1 is a fitness value, ρ 1 is an enhanced phase component predicted by the neural network using an initial weight and a threshold, η 1 is an enhanced phase volume fraction predicted by the neural network using an initial weight and a threshold, δ 1 is an enhanced phase average size predicted by the neural network using an initial weight and a threshold, ρ 0 For enhancing the phase composition expectation, η 0 To enhance the phase volume fraction expectation, δ 0 Desired value for average size of the enhancement phase;
s3: calculating the fitness values of all individuals in the population, performing selection operation by using a roulette algorithm, selecting individuals with high fitness from parent generations to generate individuals of next generation, wherein the probability of each selected individual follows the following formula:
wherein p is k Probability of being selected for the kth individual, F k Is the fitness value of the kth individual, and K is the total number of individuals in the population;
s4: carrying out cross operation on individuals in the population, setting the cross probability as pc, carrying out cross operation if a random number is generated and is smaller than the cross probability, randomly selecting two individuals and randomly selecting a cross position during cross, and carrying out cross operation according to the following formula:
wherein, a kj Is the real number of the kth chromosome at position j, a lj Is the real number of the l-th chromosome at position j, b is a random number between (0, 1);
s5: carrying out mutation operation on individuals in the population, setting the mutation probability as pm, carrying out mutation operation if a random number is generated and is smaller than the mutation probability, randomly selecting one individual and randomly selecting a mutation site during mutation, and carrying out mutation operation according to the following formula:
wherein, a ij Is the real number of the ith chromosome at position j, G is the current iteration number, f (G) is the variation factor, G max To the maximum number of iterations, a max Is a ij Upper limit of value, a min Is a ij The lower limit of the value, r and r' are random numbers between (0, 1);
s6: and (5) circulating the steps S3 to S5 until a satisfactory fitness value is obtained or a limited iteration number is reached, and outputting an optimal individual, namely the individual with the maximum fitness value.
8. A part preparation equipment based on partition multistage cryogenic treatment is characterized in that: the apparatus prepares the part by using the part preparation method based on the divisional multi-stage cryogenic treatment according to any one of claims 1 to 7; the equipment is formed with a plurality of independent cryogenic treatment chambers, and each cryogenic treatment chamber can independently treat a section of region of preparation part for cryogenic treatment.
9. The apparatus for preparing a part according to claim 8, wherein: each cryogenic treatment chamber is respectively provided with an independent resistance heating wire, a temperature sensor, an inlet pipe and an outlet pipe of a cooling medium and a moving mechanism, so that each cryogenic treatment chamber can independently work to carry out cryogenic treatment on a local area of a target part.
10. The apparatus for preparing a part according to claim 9, wherein: the equipment also comprises a plurality of heat insulation plates, and an accommodating cavity is formed in the equipment, and the heat insulation plates are arranged in the accommodating cavity at intervals so as to divide the accommodating cavity into a plurality of independent deep cooling treatment cavities; the heat insulation plate is also used for bearing parts to be prepared; and each heat insulation plate is connected with one moving mechanism, and the moving mechanism is used for driving the heat insulation plates to move so as to change the space size of the cryogenic treatment chambers on the two sides of the heat insulation plates.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210837481.6A CN115329475B (en) | 2022-07-15 | 2022-07-15 | Part preparation method and equipment based on zoned multistage cryogenic treatment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210837481.6A CN115329475B (en) | 2022-07-15 | 2022-07-15 | Part preparation method and equipment based on zoned multistage cryogenic treatment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115329475A true CN115329475A (en) | 2022-11-11 |
| CN115329475B CN115329475B (en) | 2023-04-25 |
Family
ID=83918203
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210837481.6A Active CN115329475B (en) | 2022-07-15 | 2022-07-15 | Part preparation method and equipment based on zoned multistage cryogenic treatment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115329475B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120168039A1 (en) * | 2009-07-03 | 2012-07-05 | Snecma | Cryogenic treatment of martensitic steel with mixed hardening |
| CN104133969A (en) * | 2014-05-12 | 2014-11-05 | 北京航空航天大学 | Method for calculating adsorption capture area of liquid helium cryogenic pump of vacuum plume experimental system |
| RU163939U1 (en) * | 2016-02-24 | 2016-08-20 | Федеральное государственное бюджетное образовательное учреждение высшего профессионального образования "Южно-Уральский государственный университет" (национальный исследовательский университет) (ФГБОУ ВПО "ЮУрГУ" (НИУ)) | EJECTION COOLER COOLER IN COMBINED ENGINES |
| US20180028250A1 (en) * | 2016-07-26 | 2018-02-01 | Csa Medical, Inc. | Method & apparatus to perform cryotherapy |
-
2022
- 2022-07-15 CN CN202210837481.6A patent/CN115329475B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120168039A1 (en) * | 2009-07-03 | 2012-07-05 | Snecma | Cryogenic treatment of martensitic steel with mixed hardening |
| CN104133969A (en) * | 2014-05-12 | 2014-11-05 | 北京航空航天大学 | Method for calculating adsorption capture area of liquid helium cryogenic pump of vacuum plume experimental system |
| RU163939U1 (en) * | 2016-02-24 | 2016-08-20 | Федеральное государственное бюджетное образовательное учреждение высшего профессионального образования "Южно-Уральский государственный университет" (национальный исследовательский университет) (ФГБОУ ВПО "ЮУрГУ" (НИУ)) | EJECTION COOLER COOLER IN COMBINED ENGINES |
| US20180028250A1 (en) * | 2016-07-26 | 2018-02-01 | Csa Medical, Inc. | Method & apparatus to perform cryotherapy |
Non-Patent Citations (2)
| Title |
|---|
| WU ZHISHENG等: "Effect of deep cryogenic treatment on electrode life and microstructure for spot welding hot dip galvanized steel", 《MATERIALS & DESIGN》 * |
| 管晓光等: "深冷处理对WE43A异质焊补接头组织及性能影响研究", 《电焊机》 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115329475B (en) | 2023-04-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Fang et al. | Characterization of texture and grain boundary character distributions of selective laser melted Inconel 625 alloy | |
| Rong-Ji et al. | Optimizing process parameters for selective laser sintering based on neural network and genetic algorithm | |
| Li et al. | Modeling hot deformation behavior of low-cost Ti-2Al-9.2 Mo-2Fe beta titanium alloy using a deep neural network | |
| CN112935251B (en) | Preparation method of amorphous alloy gradient composite material | |
| CN101429637B (en) | Biphase titanium alloy thermal treatment method for acquiring two-state organization with raft-shape primary alpha phase | |
| CN107937842B (en) | A kind of heat treatment method of Al-Zn-Mg-Cu aluminium alloy | |
| CN105177259A (en) | Method for rapidly promoting deformation to induce martensite transformation | |
| CN115329475A (en) | Part preparation method and equipment based on partition multi-stage cryogenic treatment | |
| Wu et al. | Synthesis of large-scale multistream heat exchanger networks based on stream pseudo temperature | |
| CN116312890A (en) | Method for screening high-hardness high-entropy alloy by aid of particle swarm optimization algorithm and machine learning | |
| Li et al. | Springback and tensile strength of 2A97 aluminum alloy during age forming | |
| CN101275180A (en) | Method for eliminating defective structure in structural alloy steel and tool steel substrate by using impulse current | |
| Furrer et al. | Optimizing the heat treatment of Ni-based superalloy turbine discs | |
| Zheng et al. | Application of genetic algorithm to enhance the predictive stability of BP-ANN constitutive model for GH4169 superalloy | |
| CN106521380A (en) | Hot quenching new process and application of large-size high-strength aluminum alloy forgings | |
| CN115061435A (en) | Machine learning method for rapidly predicting hardness of high-entropy alloy and preparation process thereof | |
| Kumar et al. | Study on hot deformation behavior of high carbon low alloy steel by constitutive and ann modeling and development of processing maps | |
| KR20190136571A (en) | Prediction apparatus for iron loss reduction of electric steel sheet | |
| Goodhart et al. | A bilinear self-tuning controller for industrial heating plant | |
| Mazurkiewicz | Knowledge transfer mechanisms for advanced surface engineering technologies | |
| CN113642218B (en) | Determination system and determination method for critical heating rate of steel plate quenching treatment | |
| CN114990501B (en) | High-throughput sample preparation equipment and data-driven aluminum alloy composition design method | |
| Campos et al. | Database-driven semigrand canonical Monte Carlo method: Application to segregation isotherm on defects in alloys | |
| CN118675661A (en) | Method for predicting microstructure evolution in thermal shock load action process based on cellular automaton | |
| Imanian et al. | Optimize additive manufacturing post-build heat treatment and hot ISO-static pressing process using an integrated computational materials engineering framework |
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 |