CN109909502A - Online monitoring method of laser additive manufacturing process based on multi-source heterogeneous data - Google Patents
Online monitoring method of laser additive manufacturing process based on multi-source heterogeneous data Download PDFInfo
- Publication number
- CN109909502A CN109909502A CN201910204707.7A CN201910204707A CN109909502A CN 109909502 A CN109909502 A CN 109909502A CN 201910204707 A CN201910204707 A CN 201910204707A CN 109909502 A CN109909502 A CN 109909502A
- Authority
- CN
- China
- Prior art keywords
- formula
- laser
- metal powder
- powder material
- heterogeneous data
- 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
- 238000012544 monitoring process Methods 0.000 title claims abstract description 39
- 238000004519 manufacturing process Methods 0.000 title claims abstract description 32
- 238000000034 method Methods 0.000 title claims abstract description 29
- 239000000654 additive Substances 0.000 title claims 3
- 230000000996 additive effect Effects 0.000 title claims 3
- 239000000463 material Substances 0.000 claims abstract description 59
- 239000000843 powder Substances 0.000 claims abstract description 46
- 238000010309 melting process Methods 0.000 claims abstract description 14
- 238000009826 distribution Methods 0.000 claims abstract description 6
- 239000002184 metal Substances 0.000 claims description 39
- 229910052751 metal Inorganic materials 0.000 claims description 39
- 238000002844 melting Methods 0.000 claims description 7
- 230000008018 melting Effects 0.000 claims description 6
- 230000004927 fusion Effects 0.000 claims description 5
- 230000000007 visual effect Effects 0.000 claims description 5
- 239000007788 liquid Substances 0.000 claims description 3
- 238000003062 neural network model Methods 0.000 claims description 3
- 230000009466 transformation Effects 0.000 claims description 2
- 239000007787 solid Substances 0.000 claims 3
- 230000008878 coupling Effects 0.000 claims 1
- 238000010168 coupling process Methods 0.000 claims 1
- 238000005859 coupling reaction Methods 0.000 claims 1
- 230000007547 defect Effects 0.000 abstract description 5
- 238000004886 process control Methods 0.000 abstract description 3
- 230000008569 process Effects 0.000 description 11
- 238000012545 processing Methods 0.000 description 8
- 230000008859 change Effects 0.000 description 7
- 238000005516 engineering process Methods 0.000 description 5
- 230000007246 mechanism Effects 0.000 description 5
- 238000007906 compression Methods 0.000 description 4
- 230000006835 compression Effects 0.000 description 4
- 238000005259 measurement Methods 0.000 description 4
- 238000005070 sampling Methods 0.000 description 4
- 230000015572 biosynthetic process Effects 0.000 description 3
- 238000007499 fusion processing Methods 0.000 description 3
- 239000012943 hotmelt Substances 0.000 description 3
- 208000037656 Respiratory Sounds Diseases 0.000 description 2
- 229910002114 biscuit porcelain Inorganic materials 0.000 description 2
- 230000007812 deficiency Effects 0.000 description 2
- 239000011551 heat transfer agent Substances 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 238000000465 moulding Methods 0.000 description 2
- 238000012805 post-processing Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 239000000523 sample Substances 0.000 description 2
- 238000005245 sintering Methods 0.000 description 2
- 230000008646 thermal stress Effects 0.000 description 2
- 238000012546 transfer Methods 0.000 description 2
- 230000001052 transient effect Effects 0.000 description 2
- 238000010146 3D printing Methods 0.000 description 1
- 241001269238 Data Species 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 238000005336 cracking Methods 0.000 description 1
- 238000013144 data compression Methods 0.000 description 1
- 238000000354 decomposition reaction Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000010429 evolutionary process Effects 0.000 description 1
- 239000000446 fuel Substances 0.000 description 1
- 238000002309 gasification Methods 0.000 description 1
- 238000010438 heat treatment Methods 0.000 description 1
- 238000010191 image analysis Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000003475 lamination Methods 0.000 description 1
- 238000003754 machining Methods 0.000 description 1
- 239000000155 melt Substances 0.000 description 1
- 230000006855 networking Effects 0.000 description 1
- 230000000649 photocoagulation Effects 0.000 description 1
- 230000005855 radiation Effects 0.000 description 1
- 238000012827 research and development Methods 0.000 description 1
- 238000005488 sandblasting Methods 0.000 description 1
- 230000035882 stress Effects 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P10/00—Technologies related to metal processing
- Y02P10/25—Process efficiency
Landscapes
- Powder Metallurgy (AREA)
Abstract
The invention discloses a kind of on-line monitoring method of laser gain material manufacturing process based on multi-source heterogeneous data, step includes: 1 to establish Laser beam energy distribution；2 obtain the speed of vibration of media；3 obtain the maximized surface temperature of powder bed；4 obtain the width in molten bath；The thermodynamical model of multi- scenarios method in 5 building laser melting process；The sparse coding of 6 multi-source heterogeneous data；7 obtain monitoring model online.The present invention can carry out real-time monitoring and process control in laser gain material manufacturing process, thus when there is tiny flaw with regard to adjust automatically technological parameter to eliminate defect, and then part forming quality is improved, meet actual precision and reliability requirement.
Description
Technical field
The invention belongs to sensor and monitoring technical field, more specifically a kind of laser gain material system of big data driving
Make on-line monitoring method.
Background technique
Increasing material manufacturing (3D printing/Quick-forming) technology is gradually changing people's traditional pattern of life and producer
The features such as formula, customization rapid with its, digitlization and networking, is considered that the third time industrial revolution will be pushed.Laser gain material
Manufacturing technology is current application range most one of wide, the maximum metal increasing material manufacturing technique of Practical significance, which utilizes high energy
Laser beam is measured, according to scheduled path, fusing or sintering powder, then shaped after cooled and solidified, in labyrinth, free form surface
There is significant advantage in the difficult processing part manufacturing such as thin-walled, such as high-performance complex component, biology manufacture in aerospace field
Porous labyrinth manufacture and functionally graded material manufacture etc. in field.
However since laser gain material manufacturing process is with processes such as complicated physical chemistry, drip molding has biggish temperature
The defects of gradient and thermal stress, forming process is easy to produce nodularization, hole, crackle, affects the precision and reliability of drip molding,
The easily-deformable cracking of molded parts, lacks the process control of forming quality, seriously hinders the application of laser gain material manufacturing technology.
However, since the dynamic characteristic of laser gain material manufacturing process is complicated, sensor installation difficulty is high and related physical mistake
Journey understands that the even reasons such as deficiency, real-time monitoring and the process control of laser gain material manufacturing process is not easy to carry out, and monitoring model has
Limit, majority are modeled using infrared temperature information with processing quality.But temperature online measurement error is larger, and powder melts
Or the mechanism of production of sintering process defect is complicated, only carries out mass measurement reliability deficiency with temperature information, correlative study still has
Wait be pushed further into.
Although the post-processings such as sandblasting, heat treatment can obtain preferable surface smoothness and reduce fracture and lamination,
Post-processing can bring the variation of part size, for internal structure complex parts, key functional domains and precision component etc., after
The method of processing will be no longer applicable in.Therefore, realize that on-line monitoring, improvement forming quality more close in laser gain material manufacturing process
Key.
Summary of the invention
The present invention is directed to the disadvantages mentioned above/or Improvement requirement of the prior art, provides a kind of based on multi-source heterogeneous data
The on-line monitoring method of laser gain material manufacturing process, to can laser gain material manufacturing process carry out real-time monitoring with it is excessively program-controlled
System, thus when there is tiny flaw with regard to adjust automatically technological parameter to eliminate defect, and then part forming quality is improved, meet
Actual precision and reliability requirement.
To achieve the above object of the invention, the present invention adopts the following technical scheme:
A kind of the characteristics of on-line monitoring method of the laser gain material manufacturing process based on multi-source heterogeneous data of the present invention be by
Following steps carry out:
Step 1 establishes the Laser beam energy distribution I (r) based on Gaussian Profile using formula (1):
In formula (1), r is distance of the point on laser facula to laser spot center, and ω is the radius of laser facula, and Φ is
The central energy density of laser facula；
Step 2 obtains the speed u of vibration of media using formula (2):
In formula (2), α is absorptivity of the metal powder material to laser；γ is the adiabatic exponent of gas, ρ0For metal powder
The density of material；
Step 3 obtains the maximized surface temperature T of powder bed using formula (3)m:
In formula (3), K is Boltzmann constant；K is the thermal coefficient of metal powder material；V is the molten of metal powder material
Change speed；C is the hot melt ratio of metal powder material；
Step 4 obtains the width δ in molten bath using formula (4)w:
In formula (4), Δ HlvIt is metal powder material from solid-state to gaseous calorific potential；TlvIt is metal powder material from admittedly
State is to gaseous equilibrium temperature；TslThe equilibrium temperature for being metal powder material from solid-state to liquid；
The thermodynamical model of multi- scenarios method in step 5, building laser melting process:
Step 5.1 is established using an apex angle of powder bed as origin O, with the two sides difference being connected with the origin O
For X-axis and Y-axis, rectangular coordinate system O-XY is established；
Step 5.2 establishes temperature field finite element model in laser melting process using formula (5):
In formula (5), a is the thermal diffusivity of metal powder material, and T (t) is the transient temperature of t moment metal powder material,
▽2For Laplace operator；For the steady temperature field not changed over time, there are ▽2T (x, y, z)=0；T (x, y, z) be
The temperature of metal powder material at point (x, y, z)；
Step 5.3 obtains the temperature gradient in laser-irradiated domain along normal direction n using formula (6)
The sparse coding of step 6, multi-source heterogeneous data:
Step 6.1 does not obtain the multi-source heterogeneous data that temperature, sound and picture signal are constituted by sensor components,
It is denoted as f；
Step 6.2 obtains transformed multi-source heterogeneous data to the multi-source heterogeneous data f progress Fast Fourier Transform (FFT)
fT；
Step 6.3, using redundant dictionary Φ to the transformed multi-source heterogeneous data fTIt is reconstructed, obtains formula (8)
Shown in transformed multi-source heterogeneous data fTRarefaction representation, and pass through optimal l shown in formula (7)0Norm come constrain it is sparse because
Sub- f 'TNumber:
s.t.fT=Φ f 'T,fT∈Rk (8)
In formula (8), RkIndicate the real number field of k dimension；Φf′TIt indicates the signal atom set obtained after sparse coding, and has: Indicate the l-th signal atom obtained after sparse coding；L indicates that signal is former
Sub- number；
Step 7, to the signal atom set obtained after sparse codingCarry out Fusion Features
Obtain observation sequence V={ v1,v2,...,vi,...,vn, viFor the observation data of i-th of visual layers；I=1,2 ..., n；N table
Show the number of plies of visual layers；
Step 8 is obtained monitoring model online E (V, H | θ) using formula (8), and with the monitoring model online E (V, H | θ)
Realize the on-line monitoring to laser gain material manufacturing process:
In formula (8), θ={ wij,ai,bjIt is parameter about RBM neural network model, wherein wijIndicate i-th it is visible
The connection weight of layer and j-th of hidden layer, aiIndicate the biasing of i-th of visible layer, bjIndicate the biasing of j-th of hidden layer, hjIt indicates
J-th of hidden layer；H indicates the set of hidden layer, and m indicates the number of plies of hidden layer.
Compared with the prior art, the beneficial effects of the present invention are embodied in:
1, the present invention probes into sound, temperature and figure in laser gain material manufacturing process with the methods of signal processing, image analysis
As feature of the signal under different machining states, its relationship generated with defect in process is analyzed, laser gain material is disclosed
The Physical Mechanism of manufacturing process；New metal powder is established to the absorbing model of laser light source, and laser melting process is carried out
Thermodynamics emulation analyzes machined parameters to the affecting laws of processing temperature, to realize that the feedback control of the process provides research base
Plinth；It is handled by source signal Fusion Features, improves the accuracy of the online quality-monitoring of process.To laser in the present invention
The on-line monitoring of increasing material manufacturing forming process is also the core of research and development labyrinth metal parts high-precision high quality manufacturing equipment
One of technology is therefore particularly suitable for metal increases material manufacturing technology in the applied field in the fields such as space flight, medical treatment and material manufacture
It closes.
2, the present invention is based on the analyses to metal increasing material manufacturing forming physical process, in conjunction with the multi-modal of monitoring information itself
Characteristic studies the consistency of the fusion of multi-source sensing data and multidimensional Heterogeneous Information expression in monitoring, utilizes the number of sparse decomposition
Theory carries out sparse coding to foreign peoples' heat transfer agent such as temperature, sound, image, while realizing compression, the denoising to information
With the character representation of consistency, excavated in multi-source heterogeneous data relevance, solve to multi-source heterogeneous information depth
The basic premise practised and merged.
Specific embodiment
In the present embodiment, a kind of on-line monitoring method of the laser gain material manufacturing process based on multi-source heterogeneous data is by such as
Lower step carries out:
During selective laser melting, laser and metal powder interaction generate fusing, gasification and the mistake rebuild
Journey.There is multiple signal sources, including acoustical signal, plasmon signal, ultrasonic wave, infra-red radiation in this laser melting process
With electric signal etc..The formation of these signals has tight association with variation and the formation and variation in molten bath, and Study of Laser melted
Sound, temperature, image in journey, which are formed, and change mechanism is for the Thermodynamic Law for disclosing laser melting process important meaning
Justice.
Sound, temperature, image in Study of Laser fusion process are formed and change mechanism, establishes laser using Gaussian Profile
When Laser beam energy distribution, with establish disclose laser melting process Thermodynamic Law basis.
Step 1 establishes the Laser beam energy distribution I (r) based on Gaussian Profile using formula (1):
In formula (1), r is distance of the point on laser facula to laser spot center, and ω is the radius of laser facula, and Φ is
The central energy density of laser facula；
Step 2 obtains the speed u of vibration of media using formula (2):
In formula (2), α is absorptivity of the metal powder material to laser；γ is the adiabatic exponent of gas, ρ0For metal powder
The density of material；
Fuel factor can promptly occur due to absorbing high-power laser beam, surface temperature can rapidly rise to fusing temperature
Degree.Maximized surface temperature TmIt can change with thermal coefficient k, the hot melt ratio c of burn-off rate v and material, so having:
Step 3 obtains the maximized surface temperature T of powder bed using formula (3)m:
In formula (3), K is Boltzmann constant；K is the thermal coefficient of metal powder material；V is the molten of metal powder material
Change speed；C is the hot melt ratio of metal powder material；
Step 4 obtains the width δ in molten bath using formula (4)w:
In formula (4), Δ HlvIt is metal powder material from solid-state to gaseous calorific potential；TlvIt is metal powder material from admittedly
State is to gaseous equilibrium temperature；TslThe equilibrium temperature for being metal powder material from solid-state to liquid；
The substances such as sound, temperature, the width and maximized surface temperature in the variation of image and molten bath and plasma fly
Splash directly related, and the variation and the nodularization degree of selective laser melting part, hole in molten bath, temperature and plasma
Rate, residual stress association.It is generated by the sound to selective laser melting, temperature, picture signal and is studied with change mechanism, looked for
The key factor of selective laser melting part quality is influenced out and acquires key signal relevant to quality, to use more sensings
Device monitors part quality on-line and provides reliable theoretical foundation.
The thermodynamical model of multi- scenarios method in step 5, building laser melting process:
The thermodynamics and dynamics analytic modell analytical model based on laser photocoagulation multi- scenarios method is established, is disclosed in powder evolutionary process
Various phenomenons, such as hole formation, molten bath flowing, and propose a kind of new thinking, by based on physical process numerical model with
Monitoring system based on multi-source data is mutually confirmed, and realizes more acurrate more reliable on-line monitoring.Laser is along the road Fen Xing
Diameter is scanned on powder bed, and heat transfer process includes radiating, between the convection current and bisque and base station between bisque and environment
Heat transfer, the latent energy of fusing are very big.The variation of pulverulence and the variation of corresponding hot attribute can all make hot biography
The process of passing becomes complicated.
Step 5.1 is established using an apex angle of powder bed as origin O, is respectively X with two sides being connected with origin O
Axis and Y-axis establish rectangular coordinate system O-XY；
Step 5.2 establishes temperature field finite element model in laser melting process using formula (5):
In formula (5), a is the thermal diffusivity of metal powder material, and T (t) is the transient temperature of t moment metal powder material,For Laplace operator；For the steady temperature field not changed over time, existT (x, y, z) be
The temperature of metal powder material at point (x, y, z)；
Step 5.3 obtains the temperature gradient in laser-irradiated domain along normal direction n using formula (6)
Enthalpy and boundary condition are changed according to physical condition, study the variation of temperature field of molten pool to laser fusing zero
The influence of part uniformity and thermal stress.In this way, by the sound of Thermodynamics modeling and monitoring to laser melting process, temperature,
Picture signal corroborates each other, and the reliability of laser melting process monitoring can be enhanced, and to realize that selectivity swashs from now on
The feedback control of light fusion process and fusing compensation provide theoretical foundation.
The sparse coding of step 6, multi-source heterogeneous data:
The consistency that the research of sparse coding obtains multi-source heterogeneous monitoring information indicates, while realizing data compression, improves
The pace of learning and accuracy of identification of depth network.Traditionally sampling thheorem, for high-frequency characteristic information common in monitoring, such as
The higher harmonic wave components such as acoustic emission signal, ultrasonic signal need to obtain with several megahertzs of sample frequency, for the reality for monitoring system
When property brings difficulty.In addition, the computationally intensive of the high dimensional datas such as temperature pattern processing, speed are slow, it is unfavorable for depth DBN model
Training.
According to the compression sensing theory that Candes and Donoho was proposed in 2006, signal compression and sampling are merged into
Row, by the study of redundant dictionary, obtains the rarefaction representation (measured value) of signal, the measurement data amount of such signal will be substantially less that
Data volume required for traditional sampling method improves real-time processing speed.Since monitoring signals are nearly all not dilute in time domain
Thin, thus this states the theoretical compression sampling for being not directly applicable monitoring signals.But we can pass through fast Fourier
Transformation carries out rarefaction representation, then by one it is super it is suitable determine equation (redundant dictionary), one optimal norm problem of solution reconstructs
Sparse signal.
Step 6.1 does not obtain the multi-source heterogeneous data that temperature, sound and picture signal are constituted by sensor components,
It is denoted as f；
Step 6.2 obtains transformed multi-source heterogeneous data f to multi-source heterogeneous data f progress Fast Fourier Transform (FFT)T；
Step 6.3, using redundant dictionary Φ to transformed multi-source heterogeneous data fTIt is reconstructed, obtains shown in formula (8)
Transformed multi-source heterogeneous data fTRarefaction representation, and pass through optimal l shown in formula (7)0Norm constrains the sparse factor
f′TNumber:
s.t.fT=Φ f 'T,fT∈Rk (8)
In formula (8), RkIndicate the real number field of k dimension；Φf′TIt indicates the signal atom set obtained after sparse coding, and has: Indicate the l-th signal atom obtained after sparse coding；L indicates that signal is former
Sub- number；The sparse degree of signal is higher, and measurement data needed for recovering original signal using above formula also will be fewer.Multi-source is different
The heat transfer agent of structure obtains the sparse expression of consistency after through redundant dictionary.In addition, the monitoring low for signal-to-noise ratio
Signal can use dictionary learning method based on rarefaction representation, consider the original for learning pure noise Yu the signal containing noise respectively
Son, and noise is separated using the correlation of atom.
The information of the selective laser melting process of multi-sensor collection is complicated and diversified.The selective laser of part is molten
The state for changing quality and fusion process has direct relationship, and the corresponding state change such as nodularization, hole and crackle can be lain in
In temperature, sound and image information.Using artificial intelligence later development, establishing has associative memory, self-adaptive processing energy
The depth confidence neural network (DBN) of power, so as to comprehensive, complete information be obtained, to the part of selective laser melting
Quality carries out fast and accurately on-line condition monitoring.
Step 7, to the signal atom set obtained after sparse codingCarry out Fusion Features
Obtain observation sequence V={ v1,v2,...,vi,...,vn, viFor the observation data of i-th of visual layers；I=1,2 ..., n；N table
Show the number of plies of visual layers；
Step 8 is obtained monitoring model online E (V, H | θ) using formula (8), and is realized with monitoring model online E (V, H | θ)
To the on-line monitoring of laser gain material manufacturing process:
In formula (8), θ={ wij,ai,bjIt is parameter about RBM neural network model, wherein wijIndicate i-th it is visible
The connection weight of layer and j-th of hidden layer, aiIndicate the biasing of i-th of visible layer, bjIndicate the biasing of j-th of hidden layer, hjIt indicates
J-th of hidden layer；H indicates the set of hidden layer, and m indicates the number of plies of hidden layer.
Claims (1)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910204707.7A CN109909502B (en) | 2019-03-18 | 2019-03-18 | Online monitoring method for laser additive manufacturing process based on multi-source heterogeneous data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910204707.7A CN109909502B (en) | 2019-03-18 | 2019-03-18 | Online monitoring method for laser additive manufacturing process based on multi-source heterogeneous data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109909502A true CN109909502A (en) | 2019-06-21 |
| CN109909502B CN109909502B (en) | 2021-04-27 |
Family
ID=66965365
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910204707.7A Active CN109909502B (en) | 2019-03-18 | 2019-03-18 | Online monitoring method for laser additive manufacturing process based on multi-source heterogeneous data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109909502B (en) |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110490866A (en) * | 2019-08-22 | 2019-11-22 | 四川大学 | Metal based on depth characteristic fusion increases material forming dimension real-time predicting method |
| CN110605393A (en) * | 2019-09-25 | 2019-12-24 | 中国兵器装备集团自动化研究所 | Laser three-dimensional forming process detection method and system and application |
| CN110942150A (en) * | 2019-11-09 | 2020-03-31 | 上海航天设备制造总厂有限公司 | Intelligent diagnosis method for forming failure of parts of selective laser melting equipment |
| CN111283192A (en) * | 2020-01-22 | 2020-06-16 | 南京理工大学 | Laser powder bed melting additive manufacturing molten pool monitoring and pore control method |
| CN111504980A (en) * | 2020-04-26 | 2020-08-07 | 长春工业大学 | L IBS online monitoring device and method in metal additive manufacturing process |
| CN112122741A (en) * | 2020-08-14 | 2020-12-25 | 江苏理工学院 | A welding bead forming control system and parameter optimization method in arc additive manufacturing process |
| CN113172242A (en) * | 2021-04-27 | 2021-07-27 | 武汉科技大学 | A kind of selective laser forming real-time monitoring device and forming method |
| CN115115578A (en) * | 2022-05-23 | 2022-09-27 | 厦门宇电自动化科技有限公司 | Defect detection method and system in additive manufacturing process |
| CN115138867A (en) * | 2022-07-22 | 2022-10-04 | 南京航空航天大学 | Device and method for monitoring, feeding back and optimizing molding quality of gradient material manufactured by laser additive in real time |
| CN115266951A (en) * | 2022-07-28 | 2022-11-01 | 上海理工大学 | Real-time online monitoring method and system for internal defects in selective laser melting process |
| WO2023224528A1 (en) * | 2022-05-19 | 2023-11-23 | Cellink Bioprinting Ab | Multi-sensor evaluation of a printing process |
Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102519387A (en) * | 2011-10-27 | 2012-06-27 | 哈尔滨工业大学 | Visual inspection method of electron beam welding pool shape parameter |
| CN202576563U (en) * | 2012-05-30 | 2012-12-05 | 上海海事大学 | Laser cladding real-time monitoring system based on zigbee wireless sensing technology |
| CN103506756A (en) * | 2013-09-11 | 2014-01-15 | 上海交通大学 | Laser lap welding gap detecting system and laser lap welding gap detecting method based on molten pool image visual sensing |
| CN105855743A (en) * | 2016-05-04 | 2016-08-17 | 华中科技大学 | On-line monitoring system and method for weld pool dynamic process |
| CN107328391A (en) * | 2017-06-28 | 2017-11-07 | 武汉理工大学 | A kind of multi-sensor cooperation monitoring device and method for broadband laser cladding |
| CN107992904A (en) * | 2017-12-22 | 2018-05-04 | 重庆邮电大学 | Forest Ecology man-machine interaction method based on Multi-source Information Fusion |
| CN108038266A (en) * | 2017-11-17 | 2018-05-15 | 西安铂力特增材技术股份有限公司 | A kind of method for numerical simulation of selective laser repair process |
| CN108062432A (en) * | 2017-11-17 | 2018-05-22 | 西安铂力特增材技术股份有限公司 | A kind of method for numerical simulation of selective laser fusion process |
| US20180264551A1 (en) * | 2017-03-15 | 2018-09-20 | David Masayuki ISHIKAWA | Additive Manufacturing Having Energy Beam and Lamp Array |
| WO2018183003A1 (en) * | 2017-03-31 | 2018-10-04 | Konica Minolta Laboratory U.S.A., Inc. | 3d imaging by multiple sensors during 3d printing |
| JP2018184623A (en) * | 2017-04-24 | 2018-11-22 | 株式会社東芝 | Inherent strain calculation device for laminated molding, inherent strain calculation method therefor, inherent strain calculation program therefor, analysis device therefor, analysis method therefor, and lamination molding device |
| CN109034391A (en) * | 2018-08-17 | 2018-12-18 | 王玲 | The multi-source heterogeneous information RBM network integration framework and fusion method of automatic Pilot |
| US20190004497A1 (en) * | 2017-06-30 | 2019-01-03 | Norsk Titanium As | Technologies of controlling additive manufacturing systems |
| CN109447939A (en) * | 2018-07-10 | 2019-03-08 | 南京理工大学 | Weld width prediction method before molten bath based on mixed spectra vision shapes |
-
2019
- 2019-03-18 CN CN201910204707.7A patent/CN109909502B/en active Active
Patent Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102519387A (en) * | 2011-10-27 | 2012-06-27 | 哈尔滨工业大学 | Visual inspection method of electron beam welding pool shape parameter |
| CN202576563U (en) * | 2012-05-30 | 2012-12-05 | 上海海事大学 | Laser cladding real-time monitoring system based on zigbee wireless sensing technology |
| CN103506756A (en) * | 2013-09-11 | 2014-01-15 | 上海交通大学 | Laser lap welding gap detecting system and laser lap welding gap detecting method based on molten pool image visual sensing |
| CN105855743A (en) * | 2016-05-04 | 2016-08-17 | 华中科技大学 | On-line monitoring system and method for weld pool dynamic process |
| US20180264551A1 (en) * | 2017-03-15 | 2018-09-20 | David Masayuki ISHIKAWA | Additive Manufacturing Having Energy Beam and Lamp Array |
| WO2018183003A1 (en) * | 2017-03-31 | 2018-10-04 | Konica Minolta Laboratory U.S.A., Inc. | 3d imaging by multiple sensors during 3d printing |
| JP2018184623A (en) * | 2017-04-24 | 2018-11-22 | 株式会社東芝 | Inherent strain calculation device for laminated molding, inherent strain calculation method therefor, inherent strain calculation program therefor, analysis device therefor, analysis method therefor, and lamination molding device |
| CN107328391A (en) * | 2017-06-28 | 2017-11-07 | 武汉理工大学 | A kind of multi-sensor cooperation monitoring device and method for broadband laser cladding |
| US20190004497A1 (en) * | 2017-06-30 | 2019-01-03 | Norsk Titanium As | Technologies of controlling additive manufacturing systems |
| CN108038266A (en) * | 2017-11-17 | 2018-05-15 | 西安铂力特增材技术股份有限公司 | A kind of method for numerical simulation of selective laser repair process |
| CN108062432A (en) * | 2017-11-17 | 2018-05-22 | 西安铂力特增材技术股份有限公司 | A kind of method for numerical simulation of selective laser fusion process |
| CN107992904A (en) * | 2017-12-22 | 2018-05-04 | 重庆邮电大学 | Forest Ecology man-machine interaction method based on Multi-source Information Fusion |
| CN109447939A (en) * | 2018-07-10 | 2019-03-08 | 南京理工大学 | Weld width prediction method before molten bath based on mixed spectra vision shapes |
| CN109034391A (en) * | 2018-08-17 | 2018-12-18 | 王玲 | The multi-source heterogeneous information RBM network integration framework and fusion method of automatic Pilot |
Non-Patent Citations (5)
| Title |
|---|
| CULLEN, J. D.等: "Multisensor fusion for on line monitoring of the quality of spot welding in automotive industry", 《MEASUREMENT》 * |
| VANDONE, AMBRA; BARALDO, STEFANO; VALENTE, ANNA: "Multisensor Data Fusion for Additive Manufacturing Process Control", 《IEEE ROBOTICS AND AUTOMATION LETTERS》 * |
| 孙燕: "盘形激光焊接状态多传感信息融合在线检测", 《中国优秀硕士学位论文全文数据库工程科技I辑》 * |
| 成雅徽: "GH4169合金粉末选区激光熔化成形数值模拟及试验研究", 《中国优秀硕士学位论文全文数据库工程科技I辑》 * |
| 黄铭: "激光熔覆过程温度场数值模拟及其应用", 《中国优秀硕士学位论文全文数据库工程科技Ⅰ辑》 * |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110490866A (en) * | 2019-08-22 | 2019-11-22 | 四川大学 | Metal based on depth characteristic fusion increases material forming dimension real-time predicting method |
| CN110605393A (en) * | 2019-09-25 | 2019-12-24 | 中国兵器装备集团自动化研究所 | Laser three-dimensional forming process detection method and system and application |
| CN110942150A (en) * | 2019-11-09 | 2020-03-31 | 上海航天设备制造总厂有限公司 | Intelligent diagnosis method for forming failure of parts of selective laser melting equipment |
| CN111283192A (en) * | 2020-01-22 | 2020-06-16 | 南京理工大学 | Laser powder bed melting additive manufacturing molten pool monitoring and pore control method |
| CN111283192B (en) * | 2020-01-22 | 2021-08-31 | 南京理工大学 | A method of laser powder bed fusion additive manufacturing molten pool monitoring and pore control |
| CN111504980B (en) * | 2020-04-26 | 2021-04-16 | 长春工业大学 | A LIBS online monitoring device and method for metal additive manufacturing process |
| CN111504980A (en) * | 2020-04-26 | 2020-08-07 | 长春工业大学 | L IBS online monitoring device and method in metal additive manufacturing process |
| CN112122741A (en) * | 2020-08-14 | 2020-12-25 | 江苏理工学院 | A welding bead forming control system and parameter optimization method in arc additive manufacturing process |
| CN113172242A (en) * | 2021-04-27 | 2021-07-27 | 武汉科技大学 | A kind of selective laser forming real-time monitoring device and forming method |
| CN113172242B (en) * | 2021-04-27 | 2021-12-28 | 武汉科技大学 | A kind of real-time monitoring device and realization method of selective laser melting forming |
| WO2023224528A1 (en) * | 2022-05-19 | 2023-11-23 | Cellink Bioprinting Ab | Multi-sensor evaluation of a printing process |
| CN115115578A (en) * | 2022-05-23 | 2022-09-27 | 厦门宇电自动化科技有限公司 | Defect detection method and system in additive manufacturing process |
| CN115138867A (en) * | 2022-07-22 | 2022-10-04 | 南京航空航天大学 | Device and method for monitoring, feeding back and optimizing molding quality of gradient material manufactured by laser additive in real time |
| CN115138867B (en) * | 2022-07-22 | 2024-04-26 | 南京航空航天大学 | A device and method for real-time monitoring, feedback and optimization of the forming quality of gradient materials in laser additive manufacturing |
| CN115266951A (en) * | 2022-07-28 | 2022-11-01 | 上海理工大学 | Real-time online monitoring method and system for internal defects in selective laser melting process |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109909502B (en) | 2021-04-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109909502A (en) | Online monitoring method of laser additive manufacturing process based on multi-source heterogeneous data | |
| CN111283192B (en) | A method of laser powder bed fusion additive manufacturing molten pool monitoring and pore control | |
| Zhou et al. | Modeling and simulation of metal selective laser melting process: A critical review | |
| CN109142434A (en) | A kind of transient state body heat source measurement method of thermal coefficient, thermal diffusivity | |
| Doodi et al. | An experimental and numerical investigation on the performance of novel hybrid bio-inspired 3D printed lattice structures for stiffness and energy absorption applications | |
| CN108723366A (en) | A kind of electron beam fuse transition state keeps system and keeping method | |
| Long et al. | Numerical simulation of thermal behavior during laser metal deposition shaping | |
| Ren et al. | A physics-informed two-level machine-learning model for predicting melt-pool size in laser powder bed fusion | |
| Staiano et al. | Experimental study on hydrodynamic performances of naval propellers to adopt new additive manufacturing processes | |
| CN111666663A (en) | SLM thermal stress rapid calculation method | |
| Wu et al. | Deformation prediction and experimental study of 316l stainless steel thin-walled parts processed by additive-subtractive hybrid manufacturing | |
| Zhu et al. | Optimization of dilution rate of laser cladding repair based on deep learning | |
| Liu et al. | Characterization method of surface crack based on laser thermography | |
| Zhang et al. | Machine learning applications for quality improvement in laser powder bed fusion: A state-of-the-art review | |
| Shi et al. | Accurate temperature characterization and experimental verification in the PCB drilling process | |
| Kessler et al. | Basic design rules of unit cells for additive manufactured lattice structures | |
| Heider et al. | Application of a neural network to improve an automated thermoplastic tow-placement process | |
| Wang et al. | Parameters impact analysis of CFRP defect detection system based on line laser scanning thermography | |
| CN114386303A (en) | Method for establishing numerical prediction model of laser melting deposition residual stress | |
| CN114273671A (en) | A dual-beam laser powder bed fusion simulation method | |
| Kumar et al. | Numerical modeling of selective laser melting: influence of process parameters on the melt pool geometry | |
| Guo et al. | Physics-informed Kolmogorov-Arnold Network with Chebyshev polynomials for fluid mechanics | |
| CN112699592A (en) | Method for simulating surface heat transfer coefficient of metal additive forming part based on heat flow coupling | |
| Alghamdi et al. | The thermal behavior analysis of a human Eye subjected to laser radiation under the Non-Fourier Law of heat conduction | |
| CN117610390A (en) | Modeling method for the growth process of Czochralski silicon single crystal based on adaptive lattice structure LBM |
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 | ||
| OL01 | Intention to license declared |