The aiCAMstir Kick-off Meeting was held online on 29th July 2021 with 16 attendees.
Link to the video
Title slide
Title slide of the aiCAM
stir Kick-off Meeting, which was held online on 29th July 2021 with 17 attendees
Screenshot
Screenshot of the aiCAM
stir Kick-off Meeting. Please click
here to see the recording of the aiCAM
stir Kick-off Meeting (64 min)]
List of Attendees
(alphabetically sorted by first name)
Company |
People |
Status |
Signed-up on
|
Please enter your company name |
Azman Ismail - Ts. Dr. |
Guest |
|
Please enter your company name |
Breno Boretti Galizoni |
Guest |
|
Please enter your company name |
Erhard Buchmann |
Guest |
|
Please enter your company name |
Gokhan Tekin_Alcomet_R&D_Director (Konuk) |
Guest |
|
LAMEF |
Guilherme V. B. Lemos |
R&D Institute |
2021-06-01
|
Latrock GmbH |
Heorhii Vdovychenko |
Data science, machine learning etc |
2021-07-12
|
Sabe Technology Ltd |
Josselin Guillozet |
Consultancy service provider |
2021-02-18
|
Please enter your institute's name |
Koen Faes |
R&D Institute |
2021-04-14
|
Please enter your company name |
Laurie Da Silva |
Guest |
|
FTS Engineering Answers Ltd |
Mike Lewis |
Consultancy service provider |
2021-01-14
|
Please enter your company name |
Mansoor, Bilal |
Guest |
|
Please enter your company name |
MJ Sefat |
Guest |
|
Maharashtra Institute of Technology, Aurangabad |
Sandeep Pankade |
Guest |
|
Please enter your institute's name |
Renan Landell |
R&D Institute |
2021-06-07
|
Please enter your institute's name |
Sandeep |
R&D Institute |
2021-07-25
|
Please enter your company name |
Shivraman |
Guest |
|
AluStir |
Stephan Kallee |
Consultancy service provider |
2021-01-14
|
Agenda
Agenda of the aiCAM
stir Kick-off Meeting:
• Welcome and introduction (2-3 sentences each)
• Computer Aided Manufacturing of friction stir welds -
The vision (
Stephan Kallee,
AluStir)
• Computional Fluid Dynamics (Mike Lewis, FTS Engineering Answers Ltd)
• Artificial Intelligence and machine learning algorithms (Josselin Guillozet, Sabe Technology Ltd)
• Analytical models (Simon Smith, Transforming Stress Ltd)
• Friction Stir Welding (LAMEF/UFRGS)
• Two companies – one team (Smart Industry Group and Latrock GmbH)
• Needs and contributions of the attendees (3-5 sentences)
• Discussion
• Organisational comments and date of next meeting
Computer Aided Manufacturing of friction stir welds - The vision
Stephan Kallee commented: "Parameter optimisation is often difficult during prototyping, production ramp-up and production," and he shared his vison: "We want to create an open access cloud, where FSW users can upload and use data and information for machine learning."
Three friction stir welds made at 5000 rev/min, 3000 rev/min and 1300 rev/min at 1000 mm/m welding speed. The weld with the lowest rotation speed has the best visusal apprearance.
Avoid:
• Wrong parameters
• Simple tools
• Inappropriate machines
• Chamfer, radius or taper on workpieces
• Insufficient clamping
Reasons for low-quality welds:
• Downward pressure is too low
• Welding speed is too fast or slow
• Rotation speed is too high or low
• Tool position is too high
• Tool rotates in the wrong direction
• Gap between the work pieces
FSW: Data to be processed: Input data and output data. The quality depends on parameters, variables and boundary values
Hooking, thinning and remant joint lines are typical challenges if conventinal FSW butt welding tools are used for Lap welding
Improved tool designs to be investigated in the aiCAM
stir project
Computional Fluid Dynamics
FSW Simulation using Computional Fluid Dynamics (CFD) – Butt Weld
Torque Comparison:
• Test = 38 Nm
• CFD = 30 Nm
Heat Input Comparison:
• Test = 2000 W
• CFD = 1800 W
FTS is also involved in:
• Standard Setting (energy Institute Subsea Guidelines)
• Joint Industry Projects
• Multiphase FIV JIP
• Multiphase FIV SIG
• Many trouble shooting projects
FSW Simulation using Computerised Fluid Dynamics (CFD) – Butt Weld
Comparison with Aldanonda Work for conventional thread at 1200 rpm and 250 mm/min
www.mdpi.com/2075-4701/10/7/872
Artificial Intelligence and machine learning algorithms
•The first step is the construction of a
high-quality dataset of good and bad welding. This dataset may consist of experimental and/or numerical samples.
•
Machine learning models could then be trained to predict the right set of tool parameters to achieve a good welding (supervised learning)
•
Input parameters (features) of the models may be:
• Physical quantities and derivatives
• Time series of these same physical quantities
• Images/videos
•
Output (target) may be a continuous variable like the torque (
regression) or whether the welding is expected to be good or bad (
classification)
• “Non-deep” learning models like
Linear Regression, Support Vector Machine or Decision Trees may be directly used with well-designed input features. The model may be inspired by equations of the expected physics.
•
Signal/Image processing and Computer Vision methods may help extract relevant features from images or videos.
•
Deep Neural Networks may be used to extract more subtle patterns from images/videos or time series (e.g. Convolutional Neural Network - CNN).
Analytical models
Predictions of
FSW Power:
• Torque, 𝑡, needed to make a weld is unknown
• Power consumed by tool rotation is 𝑡𝜔
• Can these be calculated?
The FSW circle:
• Torque, 𝒕, Function of strength
• FSW Power, 𝑷, Function of torque
• Temperature, 𝑻, Function of power
• Strength, 𝝈, Function of temperature
Baseline variables for analysis
• Temperature, 𝑇 is a function of the unknown power, and:
• Distance from tool axis, 𝑥
• Travel speed, 𝑣
• Thermal properties, conductivity, 𝑘 and diffusivity, 𝑎
• Room temperature, 𝑇
0 • Strength, 𝜎 is a function of the unknown temperature, and:
• Room temperature strength, 𝜎
𝑅𝑇 • Material melting temperature, 𝑇
𝑀 • Torque, 𝑡 is a function of the unknown material strength near the tool, and:
• The radius of the tool, 𝑅
• FSW power is equal to the unknown torque, 𝑡 times the rotation speed, ω
Assumed relationships:
• Temperature, 𝑇 predicted using a Rosenthal equation, assuming power, 𝑃
• Strength, 𝜎 assumed to be a known function of 𝑇 between the room
temperature value, 𝜎
𝑅𝑇 and zero at the melting point, 𝑇
𝑀 • Torque based upon the need to “yield” the material with strength, 𝜎
• Power straightforward function of torque, 𝑡 and rotation speed, ω
• Hence:
• Four equations
• Four unknowns (𝑇, 𝑡, 𝜎, 𝑃)
• Answer: FSW power based upon (𝑣, 𝜎𝑅𝑇, 𝑇
𝑀, 𝑅, ω, 𝑘, 𝑎)
Example:
• Thick plate Rosenthal gives:
Power 𝑃
Friction Stir Welding
Eight introductory slides were presented by Laboratório de Metalurgia Física (LAMEF):
Friction stir welding (LAMEF/UFRGS)
Physical Metallurgy Laboratory (LAMEF): We are part of the Metallurgy Department, School of Engineering, Federal University of Rio Grande do Sul (UFRGS), Brazil. We have four professors, thirty engineers and one technician who together with PhD students, Masters and undergraduates compose a workgroup of around 200 people in different areas of expertise. We have an impressive infrastructure for the characterization of engineering materials, as well as performing mechanical tests in air and in corrosive media, numerical simulation (finite element) and non-destructive tests.
• Please have a look at
https://vimeo.com/261297853 • Visit our website on
https://www.ufrgs.br/lamef/english/index.html
Friction stir welding
Friction stir welding (FSW): FSW machine (4000 rpm, 70 kN, 2000 mm) and process.
Friction stir welding: weld characterization:
FSW: Weld characterisation • Mechanical properties
&nbps; • Bending tests
&nbps; • Tensile tests
• Metallurgical characterisation
&nbps; • Tool wear analysis
FSW: Numerical Simulation
Friction-based welding processes at LAMEF/UFRGS
Universidade Federal do Rio Grande do Sul – UFRGSF, ProEng - Unidade EMBRAPII, Laboratório de Metalurgia Física – LAME
Two companies – one team
Two companies - one team: Smart Industry Group and Latrock GmbH
Contacts:•
Smart Industry Group, Kharkiv, Poltavsky Shlyakh str., 123, Phone: +38 (067) 765 27 40 and +38 (067) 573 79 99, E-mail:
ceo@sig-automation.com,
www.sig-automation.com•
Latrock GmbH, Darmstädter Landstr. 116, 60598 Frankfurt am Main, Phone: +49 6128 8600121, E-mail:
contact@latrock.com www.latrock.com