CN113076570B - Additive repairing and remanufacturing reverse modeling design and reverse planning method - Google Patents
Additive repairing and remanufacturing reverse modeling design and reverse planning method Download PDFInfo
- Publication number
- CN113076570B CN113076570B CN202110257078.1A CN202110257078A CN113076570B CN 113076570 B CN113076570 B CN 113076570B CN 202110257078 A CN202110257078 A CN 202110257078A CN 113076570 B CN113076570 B CN 113076570B
- Authority
- CN
- China
- Prior art keywords
- repair
- remanufacturing
- reverse
- repairing
- performance
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/18—Manufacturability analysis or optimisation for manufacturability
Abstract
The invention discloses an additive repairing and remanufacturing reverse modeling design and reverse planning method, which obtains the related data of 'base material, repairing process and performance' through experiments and model calculation; developing an additive repairing and remanufacturing database under a Windows operating system by adopting a Qt programming architecture; based on a deep learning neural network architecture, a reverse inversion mapping relation of 'enabling service performance, repairing process and repairing material' is established, the service performance and damaged building matrix material are taken as input, the repairing material and the process are taken as output, and the rapid and accurate determination of damaged part additive repairing and remanufacturing repairing material and the process is realized. The invention realizes inversion design and reverse planning of 'enabling the service performance, repairing process and repairing material' aiming at the actual process of site material increase repairing and remanufacturing; the method breaks through the problems of forward design of the traditional component, process and performance and reverse process separation of actual additive repair and remanufacturing, and solves the problem of on-site rapid repair system of equipment damaged parts.
Description
Technical Field
The invention belongs to the technical field of additive repairing and remanufacturing, and particularly relates to a additive repairing and remanufacturing reverse modeling and reverse planning method.
Background
The field repair and remanufacturing of large heavy-duty parts in the fields of energy, machinery, aviation and the like and the field quick repair of parts in special environments such as open sea, tunnels and the like are key bottleneck problems which restrict the running efficiency/benefit of important engineering in China for a long time. In contrast to the traditional forward design, which determines the functional mode of the product by the material performance, the on-site material-adding repair and remanufacturing reverse modeling design is used for deducting the structural organization and components of the material according to the requirement of repairing the service performance of the product, and then selecting a reverse deduction process of a proper processing technology.
At present, researches on additive repair and remanufacturing mainly aim at forward design of 'composition, process and performance', because the internal relation of the process is linear, and the internal response relation can be established through derivation of a physical model. However, for the inversion process of 'enabling the service performance, repairing process and material property', the inversion design and reverse planning have great difficulty, and related research is still lacking at present. Therefore, how to realize additive repair, remanufacturing reverse modeling and reverse planning, so as to meet the on-site first-aid repair of equipment in a specific environment is a great technical problem existing nowadays.
Disclosure of Invention
In view of this, the present invention provides an additive repair and remanufacturing reverse design and reverse planning method, which is based on an additive repair and remanufacturing database (including damaged part matrix materials, repair materials, service performance, microstructure, repair process data) and combines a deep learning neural network architecture to realize the additive repair and remanufacturing reverse design and reverse planning.
Therefore, the invention provides the following technical scheme:
an additive repair and remanufacturing reverse modeling and reverse planning method comprising the steps of:
acquiring and arranging source data to obtain related data of 'matrix material, repair process and performance'; the source data at least comprises a matrix material, a repair process and post-repair performance data;
establishing an additive repair and remanufacturing database based on the correlation data;
based on the additive repairing and remanufacturing database, establishing a reverse inversion mapping relation model based on a deep learning neural network architecture, wherein the reverse inversion mapping relation model reflects a reverse inversion mapping relation of 'enabling service performance, repairing process and repairing material', and the reverse inversion mapping relation model takes a matrix material and enabling service performance as input and takes repairing material and process as output;
determining the base material of the damaged part and the service performance after repair;
and inputting the base material and the repaired service performance of the damaged part into the inverse inversion mapping relation model to obtain the material-increasing repair and remanufacturing repair material and process of the damaged part.
Further, acquiring and arranging source data to obtain related data of 'base material, repair process and performance', wherein the related data comprises the following steps:
considering the diversity of damaged parts in the aspects of material types, expression forms and treatment processes, aiming at the difference of heterogeneous material interface matching and molten pool metallurgical behaviors in the process of additive repair and remanufacturing, and aiming at the repair processes of different heat sources, carrying out additive repair and remanufacturing experiments to obtain the associated data of 'base material, repair process and performance'.
Further, acquiring and arranging source data to obtain related data of 'base material, repair process and performance', wherein the related data comprises the following steps:
and obtaining the related data of 'base material-repair process-performance' through a heat source model, a tissue evolution model and a performance prediction model of different processes in the additive repair and remanufacturing processes.
Further, building an additive repair and remanufacturing database based on the correlation data, comprising:
and developing an additive repairing and remanufacturing database under a Windows operating system by adopting a Qt programming architecture.
Further, the service performance of the repaired part is determined by the service performance of the undamaged part, and the service performance of the repaired part is not lower than 90% of the service performance of the undamaged part.
Further, the repair material includes a plurality of intensive repair materials;
the repairing process comprises electric arc, laser and plasma;
properties include hardness, yield strength, tensile strength, and frictional wear.
The invention has the following beneficial effects:
the invention breaks through the forward design traditional thought of 'composition, process and performance' in the traditional additive repairing and remanufacturing field, establishes an additive repairing and remanufacturing database based on the actual process of additive repairing and remanufacturing, and merges a deep learning neural network architecture, realizes the inversion design and reverse planning of 'enabling performance, repairing process and material property', and solves the problem of rapidly repairing a system on site of equipment damaged parts.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings may be obtained according to the drawings without inventive effort to a person skilled in the art.
FIG. 1 is a flow chart of an additive repair and remanufacturing reverse modeling and reverse planning method according to one embodiment of the present invention;
FIG. 2 is a block diagram of a reverse inversion mapping model in an embodiment of the invention.
Detailed Description
In order that those skilled in the art will better understand the present invention, a technical solution in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in which it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present invention without making any inventive effort, shall fall within the scope of the present invention.
It should be noted that the terms "first," "second," and the like in the description and the claims of the present invention and the above figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments of the invention described herein may be implemented in sequences other than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
Referring to fig. 1, a flow chart of an additive repair and remanufacturing reverse design and reverse programming method according to an embodiment of the invention is shown, the method comprising the steps of:
step 1: acquiring and arranging source data to obtain related data of 'matrix material, repair process and performance'; the source data includes at least a base material, a repair process, and post-repair performance data.
The data sources of the invention are divided into experimental data and model calculation data, and the purpose is to obtain the related data of 'base material, repairing process and performance' through experiments and model calculation. The matrix material relates to common damaged piece materials such as iron base, aluminum base, titanium base and the like, the repairing material comprises various intensive repairing materials, the repairing process comprises electric arc, laser, plasma and the like, and the performances comprise hardness, yield strength, tensile strength, friction and wear and the like.
Data source one: experimental data
In the early stage, considering the diversity of damaged parts in the aspects of material types, expression forms, treatment processes and the like, aiming at the differences of heterogeneous material interface matching and molten pool metallurgical behaviors in the repairing and remanufacturing process and the repairing processes of different heat sources such as laser, electric arc, plasma and the like, 7 intensive iron-based, aluminum-based and titanium-based alloy powders or wires are designed and prepared in the embodiment of the invention, 14 representative substrates are selected for carrying out additive repairing tests, and basic data of matrix materials, repairing processes and performances are obtained, as shown in table 1.
TABLE 1
And a second data source: model calculation data
And obtaining repairing materials, processes, microstructures and performance data through a heat source model, a microstructure model and a performance prediction model of different processes (laser, electric arc, plasma and the like) in the additive repairing and remanufacturing processes.
1. And (3) a heat source model:
(1) Arc heat source:
front hemisphere:
rear hemisphere:
where q=ηui, ηheat source efficiency. x, y and z represent coordinate positions, and a, b and c areHalf-axis length f of heat source ellipsoid shape 1 、f 2 The heat distribution functions of the front ellipsoid and the rear ellipsoid are respectively f 1 +f 2 ＝2。
(2) Laser heat source:
wherein f is a heat distribution function; a. c, z, μ are hollow shape parameters, x, y, z represent coordinate positions.
2. Microstructure model:
(1) Grain size:
in which Q in The activation energy is diffusion of grain boundary; d is the grain size; l (L) 0 The center point distance between the initial adjacent grains is the center point distance; gamma ray 0 Is a material parameter; t is absolute temperature; r is Boltzmann constant.
(2) Phase volume fraction:
wherein T is absolute temperature; t (T) sus Is the phase transition temperature; v is a material parameter.
(3) Dislocation density:
wherein ρ is the instantaneous dislocation density, ρ i For initial dislocation density ρ max Is the dislocation density at the dislocation saturation state. Thus, the regularized dislocation density of the initial stage
0, saturation regularized dislocation density->
1 is shown in the specification; A. n is a material parameter; c is the diffusion coefficient affecting dislocation motion; c (C) 0 Absolute zero is the dislocation motion diffusion coefficient; />
Is the strain rate; r is Boltzmann constant; q (Q) dis Is the thermal activation energy of the dislocation.
3. Performance prediction model:
in sigma w Sum the total intensity contributions; sigma (sigma) i Contributing to the strength of the pure material; sigma (sigma) dis Intensity contributions due to dislocation density variations; sigma (sigma) r Strengthening the contribution to the strength for the second phase; sigma (sigma) ss Is a contribution of solid solution strengthening; AA. BB, C dis 、C ss 、ω、ω 1 、ω 2 、ω 3 、ω 4 、ω 5 、β 1 、β 2 、β 3 Gamma is a material parameter and Hv is vickers hardness.
Step 2: establishing an additive repair and remanufacturing database based on the correlation data;
based on the experimental and model calculation data in the step 1, a Qt programming framework is adopted to develop an additive repairing and remanufacturing database under a Windows operating system, wherein the database comprises damaged part matrix materials, repairing processes and performance related data.
Step 3: based on the additive repairing and remanufacturing database, establishing a reverse inversion mapping relation model based on a deep learning neural network architecture;
and (3) taking the additive repairing and remanufacturing database established in the step (2) as a data basis, establishing a reverse inversion mapping relation model reflecting a reverse inversion mapping relation of 'enabling service performance, repairing process and repairing material', wherein the reverse inversion mapping relation model takes a matrix material and enabling service performance as inputs and takes repairing material and process as outputs based on a deep learning neural network architecture (figure 2).
Step 4: determining the base material of the damaged part and the service performance after repair;
the service performance of the repaired part is finally determined by the service performance of the undamaged part, and the performance of the repaired part is required to be not lower than 90% of the performance of the undamaged part.
Step 5: inversion design and reverse planning of additive repairing and remanufacturing processes;
inputting the base material and the repaired service performance of the damaged part obtained in the step 4 into the reverse inversion mapping relation model to obtain the material-adding repairing and remanufacturing repairing material and process of the damaged part, thereby realizing the rapid and accurate determination of the material-adding repairing and remanufacturing repairing material and process of the damaged part.
The invention breaks through the forward design traditional thought of 'composition, process and performance' in the traditional additive repairing and remanufacturing field, establishes an additive repairing and remanufacturing database based on the actual process of additive repairing and remanufacturing, fuses a deep learning neural network architecture, realizes inversion design and reverse planning of 'enabling performance, repairing process and material property', and solves the problem of rapidly repairing a system on site of equipment damaged parts.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and not for limiting the same; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some or all of the technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit of the invention.
Claims (6)
1. An additive repair and remanufacturing reverse modeling and reverse planning method, comprising the steps of:
acquiring and arranging source data to obtain related data of 'matrix material, repair process and performance'; the source data at least comprises a matrix material, a repair process and post-repair performance data;
establishing an additive repair and remanufacturing database based on the correlation data;
based on the additive repairing and remanufacturing database, establishing a reverse inversion mapping relation model based on a deep learning neural network architecture, wherein the reverse inversion mapping relation model reflects a reverse inversion mapping relation of 'enabling service performance, repairing process and repairing material', and the reverse inversion mapping relation model takes a matrix material and enabling service performance as input and takes repairing material and process as output;
determining the base material of the damaged part and the service performance after repair;
and inputting the base material and the repaired service performance of the damaged part into the inverse inversion mapping relation model to obtain the material-increasing repair and remanufacturing repair material and process of the damaged part.
2. The method for additive repair and remanufacturing reverse modeling and reverse planning according to claim 1, wherein obtaining and arranging source data to obtain associated data of "base material→repair process→performance" comprises:
considering the diversity of damaged parts in the aspects of material types, expression forms and treatment processes, aiming at the difference of heterogeneous material interface matching and molten pool metallurgical behaviors in the process of additive repair and remanufacturing, and aiming at the repair processes of different heat sources, carrying out additive repair and remanufacturing experiments to obtain the associated data of 'base material, repair process and performance'.
3. The method for additive repair and remanufacturing reverse design and reverse programming according to claim 1 or 2, wherein obtaining and sorting source data to obtain associated data of "base material→repair process→performance" comprises:
and obtaining the related data of 'base material-repair process-performance' through a heat source model, a tissue evolution model and a performance prediction model of different processes in the additive repair and remanufacturing processes.
4. The additive repair and remanufacturing reverse engineering and reverse planning method of claim 1, wherein building an additive repair and remanufacturing database based on the correlation data comprises:
and developing an additive repairing and remanufacturing database under a Windows operating system by adopting a Qt programming architecture.
5. The method of claim 1, wherein the performance after repair is determined by the performance of undamaged parts, and the performance after repair is not less than 90% of the performance of undamaged parts.
6. The method of additive repair and remanufacturing of a reverse design and reverse programming of claim 1, wherein the repair material comprises a plurality of intensive repair materials;
the repairing process comprises electric arc, laser and plasma;
properties include hardness, yield strength, tensile strength, and frictional wear.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110257078.1A CN113076570B (en) | 2021-03-09 | 2021-03-09 | Additive repairing and remanufacturing reverse modeling design and reverse planning method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110257078.1A CN113076570B (en) | 2021-03-09 | 2021-03-09 | Additive repairing and remanufacturing reverse modeling design and reverse planning method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113076570A CN113076570A (en) | 2021-07-06 |
| CN113076570B true CN113076570B (en) | 2023-05-16 |
Family
ID=76612185
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110257078.1A Active CN113076570B (en) | 2021-03-09 | 2021-03-09 | Additive repairing and remanufacturing reverse modeling design and reverse planning method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113076570B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114872325A (en) * | 2022-04-27 | 2022-08-09 | 河北水利电力学院 | Additive remanufacturing method, additive remanufacturing device, electronic apparatus, storage medium, and program product |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5561173A (en) * | 1990-06-19 | 1996-10-01 | Carolyn M. Dry | Self-repairing, reinforced matrix materials |
| CN1807685A (en) * | 2005-12-09 | 2006-07-26 | 浙江工业大学 | Nano coating process for metal surface |
| CN108446414A (en) * | 2017-12-22 | 2018-08-24 | 北京工业大学 | A kind of backward-predicted method by 3D printing porous structure random defect |
| CN111781584A (en) * | 2020-07-14 | 2020-10-16 | 中国人民解放军陆军装甲兵学院 | Based on target radiation O2Passive distance measuring method of absorption correlation K distribution method |
| CN111859577A (en) * | 2020-07-27 | 2020-10-30 | 江苏科技大学 | Direct layering method for laser additive repair |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160325372A1 (en) * | 2015-05-05 | 2016-11-10 | Caterpillar Inc. | Low heat input weld repair of cast iron |
| US11752547B2 (en) * | 2017-06-30 | 2023-09-12 | Norsk Titanium As | Solidification refinement and general phase transformation control through application of in situ gas jet impingement in metal additive manufacturing |
| US11898226B2 (en) * | 2019-02-26 | 2024-02-13 | Ut-Battelle, Llc | Additive manufacturing process for producing aluminum-boron carbide metal matrix composites |
-
2021
- 2021-03-09 CN CN202110257078.1A patent/CN113076570B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5561173A (en) * | 1990-06-19 | 1996-10-01 | Carolyn M. Dry | Self-repairing, reinforced matrix materials |
| CN1807685A (en) * | 2005-12-09 | 2006-07-26 | 浙江工业大学 | Nano coating process for metal surface |
| CN108446414A (en) * | 2017-12-22 | 2018-08-24 | 北京工业大学 | A kind of backward-predicted method by 3D printing porous structure random defect |
| CN111781584A (en) * | 2020-07-14 | 2020-10-16 | 中国人民解放军陆军装甲兵学院 | Based on target radiation O2Passive distance measuring method of absorption correlation K distribution method |
| CN111859577A (en) * | 2020-07-27 | 2020-10-30 | 江苏科技大学 | Direct layering method for laser additive repair |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113076570A (en) | 2021-07-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Olson | Designing a new material world | |
| Babbar et al. | Application of hybrid nature-inspired algorithm: Single and bi-objective constrained optimization of magnetic abrasive finishing process parameters | |
| McDowell | Simulation-based strategies for microstructure-sensitive fatigue modeling | |
| Karnik et al. | Delamination analysis in high speed drilling of carbon fiber reinforced plastics (CFRP) using artificial neural network model | |
| Zhang et al. | Cohesive zone modeling of dynamic failure in homogeneous and functionally graded materials | |
| Kuehmann et al. | Computational materials design and engineering | |
| Pessard et al. | A mechanistic approach to the Kitagawa–Takahashi diagram using a multiaxial probabilistic framework | |
| CN113076570B (en) | Additive repairing and remanufacturing reverse modeling design and reverse planning method | |
| Kumar Padhi et al. | Solid particle erosion behavior of BFS-filled epoxy–SGF composites using Taguchi's experimental design and ANN | |
| Lin | Selection of material models for predicting necking in superplastic forming | |
| Patel et al. | Multi-objective optimization of squeeze casting process using genetic algorithm and particle swarm optimization | |
| Kolednik et al. | Cracks in inhomogeneous materials: Comprehensive assessment using the configurational forces concept | |
| Heimann | Better quality control: stochastic approaches to optimize properties and performance of plasma-sprayed coatings | |
| Glavicic et al. | Integrated computational materials engineering of titanium: current capabilities being developed under the metals affordability initiative | |
| McBride et al. | Modelling tensile properties of gamma-based titanium aluminides using artificial neural network | |
| Nellippallil et al. | Inverse thermo-mechanical processing (ITMP) design of a steel rod during hot rolling process | |
| Shikalgar et al. | Analysis of p-SPT specimens using Gurson parameters ascertained by Artificial Neural Network | |
| Kulkarni et al. | Microstructural optimization of alloys using a genetic algorithm | |
| CN105785963B (en) | A kind of steel-making continuous casting dispatching method based on artificial bee colony algorithm | |
| Ogi et al. | A probabilistic approach for transverse crack evolution in a composite laminate under variable amplitude cyclic loading | |
| Faheem et al. | A sustainable ecofriendly additive manufacturing approach of repairing and coating on the substrate: cold spray | |
| Zhecheva et al. | Simulation of microhardness profiles of titanium alloys after surface nitriding using artificial neural network | |
| Caseiro et al. | Thermomechanical modelling strategies for multiphase steels | |
| Singhal et al. | Simulation of mechanical properties of stir cast aluminum matrix composites through Artificial Neural Networks (ANN) | |
| Vorel et al. | Material-Technological Modelling of Controlled Cooling of Closed die Forgings from Finish Forging Temperature |
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 |