AiCAMstir Kick-off Meeting, 29 July 2021: Difference between revisions

From aicamstir.com
Jump to navigation Jump to search
No edit summary
No edit summary
 
(47 intermediate revisions by 2 users not shown)
Line 1: Line 1:
The '''aiCAMstir Kick-off Meeting''' was held online on 29th July 2021 with 16 attendees.
The '''aiCAM<sup>''stir''</sup> Kick-off Meeting''' was held online on 29th July 2021 with 16 attendees.


[[File:AiCAMstir Kick-off Meeting, 29th July 2021 - Slide 01.jpeg ‎|thumb|left|upright=4|alt=Title slide of the aiCAMstir Kick-off Meeting, which was held online on 29th July 2021 with 16 attendees.|Title slide of the aiCAMstir Kick-off Meeting, which was held online on 29th July 2021 with 17 attendees]]
== Link to the video ==
{| width=100% cellpadding="0" cellspacing="0" valign="top"
|-
|style="background:#E5EDDE; border:1px solid #D5DECD"|[https://ftsengineeringanswers-my.sharepoint.com/:v:/g/personal/mike_lewis_fts-engineeringanswers_com/EVQQX36Tmc1JrtIVDVg5U5QBdTNM08bdI7g31awWOLvxOw?e=4%3aAmnZiS&at=9 '''Recording of the aiCAM<sup>''stir''</sup> Kick-off Meeting''' (64 min)]
|}


[[File:AiCAMstir Kick-off Meeting, 29th July 2021 - Slide 02.JPG‎|thumb|left|upright=4|alt=Photos of six attendees and a list of the 17 attendees.|Screenshot of the aiCAMstir Kick-off Meeting]]
== Title slide ==
[[File:AiCAMstir Kick-off Meeting, 29th July 2021 - Slide 01.jpeg ‎|thumb|left|upright=3.2|alt=Title slide of the aiCAMstir Kick-off Meeting, which was held online on 29th July 2021 with 16 attendees.|Title slide of the aiCAM<sup>''stir''</sup> Kick-off Meeting, which was held online on 29th July 2021 with 17 attendees]]
 
<div style="clear:both;">
== Screenshot ==
[[File:AiCAMstir Kick-off Meeting, 29th July 2021 - Slide 02.JPG‎|thumb|left|upright=3.2|alt=Photos of six attendees and a list of the 17 attendees.|Screenshot of the aiCAM<sup>''stir''</sup> Kick-off Meeting. Please click [https://ftsengineeringanswers-my.sharepoint.com/:v:/g/personal/mike_lewis_fts-engineeringanswers_com/EVQQX36Tmc1JrtIVDVg5U5QBdTNM08bdI7g31awWOLvxOw?e=4%3aAmnZiS&at=9 '''here'''] to see the recording of the aiCAM<sup>''stir''</sup> Kick-off Meeting (64 min)]]]


<div style="clear:both;">
<div style="clear:both;">
==List of Attendees (alphabetically sorted by first name)==
 
==List of Attendees ==
(alphabetically sorted by first name)


{| class="wikitable sortable"
{| class="wikitable sortable"
Line 20: Line 31:
| Please enter your company name || Gokhan Tekin_Alcomet_R&D_Director (Konuk) || Guest ||  
| Please enter your company name || Gokhan Tekin_Alcomet_R&D_Director (Konuk) || Guest ||  
|-
|-
| [[LAMEF]] || [[User:Guilherme V. B. Lemos LAMEF|Guilherme V. B. Lemos]] || R&D Institute || 2021-06-01
| [[LAMEF]] || [[User:Guilherme V. B. Lemos|Guilherme V. B. Lemos]] || R&D Institute || 2021-06-01
|-
|-
| [[Two companies - one team: Smart Industry Group and Latrock GmbH|Latrock GmbH]] || [[Two companies - one team: Smart Industry Group and Latrock GmbH#Heorhii Vdovychenko|Heorhii Vdovychenko]] || Data science, machine learning etc || 2021-07-12
| [[Two companies - one team: Smart Industry Group and Latrock GmbH|Latrock GmbH]] || [[Two companies - one team: Smart Industry Group and Latrock GmbH#Heorhii Vdovychenko|Heorhii Vdovychenko]] || Data science, machine learning etc || 2021-07-12
Line 36: Line 47:
| Please enter your company name || MJ Sefat || Guest ||  
| Please enter your company name || MJ Sefat || Guest ||  
|-
|-
| TPO Maharashtra Institute of Technology Aurangabad  || Please enter your name || Guest ||  
| Maharashtra Institute of Technology, Aurangabad  || Sandeep Pankade|| Guest ||  
|-
|-
| Please enter your institute's name || [[User:Renan Landell|Renan Landell]] || R&D Institute || 2021-06-07
| Please enter your institute's name || [[User:Renan Landell|Renan Landell]] || R&D Institute || 2021-06-07
Line 47: Line 58:
|}
|}


[[File:AiCAMstir Kick-off Meeting, 29th July 2021 - Slide 03.JPG‎|thumb|left|upright=4|alt=Agenda of the aiCAMstir Kick-off Meeting.|Agenda of the aiCAMstir Kick-off Meeting:
<div style="clear:both;">
 
== Agenda ==
[[File:AiCAMstir Kick-off Meeting, 29th July 2021 - Slide 03.JPG‎|thumb|left|upright=3.2|alt=Agenda of the aiCAMstir Kick-off Meeting.|Agenda of the aiCAM<sup>''stir''</sup> Kick-off Meeting: <br />
• Welcome and introduction (2-3 sentences each) <br />
• Welcome and introduction (2-3 sentences each) <br />
• Computer Aided Manufacturing of friction stir welds - [[Vision|The vision]] ([[User:Stephan Kallee at AluStir|Stephan Kallee]], [[AluStir]]) <br />
• Computer Aided Manufacturing of friction stir welds - [[Vision|The vision]] ([[User:Stephan Kallee at AluStir|Stephan Kallee]], [[AluStir]]) <br />
Line 59: Line 73:
• Organisational comments and date of next meeting]]
• Organisational comments and date of next meeting]]


<div style="clear:both;">
== Computer Aided Manufacturing of friction stir welds - The vision ==
[[File:AiCAMstir Kick-off Meeting, 29th July 2021 - Slide 04.JPG|thumb|left|upright=3.2|alt=Stephan Kallee being interviewed: "Parameter optimisation is often difficult during prototyping, production ramp-up and production. We want to create an open access cloud, where FSW users can upload and use data and information for machine learning."|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."]]


[[File:AiCAMstir Kick-off Meeting, 29th July 2021 - Slide 04.JPG|thumb|left|upright=4|alt=Stephan Kallee being interviewed: "Parameter optimisation is often difficult during prototyping, production ramp-up and production. We want to create an open access cloud, where FSW users can upload and use data and information for machine learning."|Stephan Kallee commented: "Parameter optimisation is often difficult during prototyping, production ramp-up and production," and shared the vison: "We want to create an open access cloud, where FSW users can upload and use data and information for machine learning."]]


[[File:AiCAMstir Kick-off Meeting, 29th July 2021 - Slide 05.jpg|thumb|left|upright=3.2|alt=aiCAMstir: artificial intelligence (machine learning) in Computer Aided Manufacturing of friction stir welds - The friction stir weld made at 1300 rev/min and 1000 mm/m welding speed shows the visually best results so far.|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.]]


[[File:AiCAMstir Kick-off Meeting, 29th July 2021 - Slide 05.jpg|thumb|left|upright=4|alt=aiCAMstir: artificial intelligence (machine learning) in Computer Aided Manufacturing of friction stir welds - The friction stir weld made at 1300 rev/min and 1000 mm/m welding speed shows the visually best results so far.|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.]]
[[File:AiCAMstir Kick-off Meeting, 29th July 2021 - Slide 06.JPG|thumb|left|upright=3.2|alt=|Avoid: <br />
 
 
[[File:AiCAMstir Kick-off Meeting, 29th July 2021 - Slide 06.JPG|thumb|left|upright=4|alt=|Avoid: <br />
• Wrong parameters <br />
• Wrong parameters <br />
• Simple tools <br />
• Simple tools <br />
Line 81: Line 95:
• Gap between the work pieces ]]
• Gap between the work pieces ]]


[[File:AiCAMstir Kick-off Meeting, 29th July 2021 - Slide 07 .JPG|thumb|left|upright=4|alt=Quality depends on Parameters, Variables and Boundary values |FSW: Data to be processed: Input data and output data. The quality depends on parameters, variables and boundary values]]
[[File:AiCAMstir Kick-off Meeting, 29th July 2021 - Slide 07 .JPG|thumb|left|upright=3.2|alt=Quality depends on Parameters, Variables and Boundary values |FSW: Data to be processed: Input data and output data. The quality depends on parameters, variables and boundary values]]


[[File:AiCAMstir Kick-off Meeting, 29th July 2021 - Slide 08.JPG|thumb|left|upright=4|alt=Main challenges: hooking, thinning and Rremnant joint line|Hooking, thinning and remant joint lines are typical challenges if conventinal FSW butt welding tools are used for Lap welding]]
[[File:AiCAMstir Kick-off Meeting, 29th July 2021 - Slide 08.JPG|thumb|left|upright=3.2|alt=Main challenges: hooking, thinning and Rremnant joint line|Hooking, thinning and remant joint lines are typical challenges if conventinal FSW butt welding tools are used for Lap welding]]


[[File:AiCAMstir Kick-off Meeting, 29th July 2021 - Slide 09.JPG|thumb|left|upright=4|alt=Three concepts for improved FSW tools|Improved tool designs to be investigated in the aiCAMstir project]]
[[File:AiCAMstir Kick-off Meeting, 29th July 2021 - Slide 09.JPG|thumb|left|upright=3.2|alt=Three concepts for improved FSW tools|Improved tool designs to be investigated in the aiCAM<sup>''stir''</sup> project]]


<div style="clear:both;">


[[File:AiCAMstir Kick-off Meeting, 29th July 2021 - Slide 10.JPG|thumb|left|upright=4|alt=|FSW Simulation using Computerised Fluid Dynamics (CFD) – Butt Weld <br />
== Computional Fluid Dynamics ==
[[File:AiCAMstir Kick-off Meeting, 29th July 2021 - Slide 10.JPG|thumb|left|upright=3.2|alt=|FSW Simulation using Computional Fluid Dynamics (CFD) – Butt Weld <br />
Torque Comparison: <br />
Torque Comparison: <br />
• Test = 38 Nm <br />
• Test = 38 Nm <br />
Line 97: Line 113:
• CFD = 1800 W <br />
• CFD = 1800 W <br />
<br />
<br />
FTS is also involved in:  
FTS is also involved in: <br />
• Standard Setting (energy Institute Subsea Guidelines) <br />
• Standard Setting (energy Institute Subsea Guidelines) <br />
• Joint Industry Projects <br />
• Joint Industry Projects <br />
:• Multiphase FIV JIP <br />
&nbsp;&nbsp;• Multiphase FIV JIP <br />
:• Multiphase FIV SIG <br />
&nbsp;&nbsp;• Multiphase FIV SIG <br />
• Many trouble shooting projects]]
• Many trouble shooting projects]]


[[File:AiCAMstir Kick-off Meeting, 29th July 2021 - Slide 11.JPG|thumb|left|upright=4|alt=|FSW Simulation using Computerised Fluid Dynamics (CFD) – Butt Weld <br />
[[File:AiCAMstir Kick-off Meeting, 29th July 2021 - Slide 11.JPG|thumb|left|upright=3.2|alt=|FSW Simulation using Computerised Fluid Dynamics (CFD) – Butt Weld <br />


Comparison with Aldanonda Work for conventional thread at 1200 rpm and 250 mm/min
Comparison with Aldanonda Work for conventional thread at 1200 rpm and 250 mm/min
[https://www.mdpi.com/2075-4701/10/7/872 www.mdpi.com/2075-4701/10/7/872]]]
[https://www.mdpi.com/2075-4701/10/7/872 www.mdpi.com/2075-4701/10/7/872]]]


[[File:AiCAMstir Kick-off Meeting, 29th July 2021 - Slide 12.JPG|thumb|left|upright=4|alt=|•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.<br />
<div style="clear:both;">
 
== Artificial Intelligence and machine learning algorithms ==
[[File:AiCAMstir Kick-off Meeting, 29th July 2021 - Slide 12.JPG|thumb|left|upright=3.2|alt=|•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.<br />
<br />
<br />
•'''Machine learning''' models could then be trained to predict the right set of tool parameters to achieve a good welding (supervised learning)<br />
•'''Machine learning''' models could then be trained to predict the right set of tool parameters to achieve a good welding (supervised learning)<br />
<br />
<br />
• '''Input parameters (features)''' of the models may be: <br />
• '''Input parameters (features)''' of the models may be: <br />
::• Physical quantities and derivatives <br />
&nbsp;&nbsp;• Physical quantities and derivatives <br />
::• Time series of these same physical quantities <br />
&nbsp;&nbsp;• Time series of these same physical quantities <br />
::• Images/videos <br />
&nbsp;&nbsp;• Images/videos <br />
<br />
<br />
• '''Output (target)''' may be a continuous variable like the torque ('''regression''') or whether the welding is expected to be good or bad ('''classification''')]]
• '''Output (target)''' may be a continuous variable like the torque ('''regression''') or whether the welding is expected to be good or bad ('''classification''')]]


 
[[File:AiCAMstir Kick-off Meeting, 29th July 2021 - Slide 13.JPG|thumb|left|upright=3.2|alt=|• “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. <br />
[[File:AiCAMstir Kick-off Meeting, 29th July 2021 - Slide 13.JPG|thumb|left|upright=4|alt=|• “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. <br />
<br />
<br />
• '''Signal/Image processing''' and Computer Vision methods may help extract relevant features from images or videos. <br />
• '''Signal/Image processing''' and Computer Vision methods may help extract relevant features from images or videos. <br />
Line 127: Line 145:
• '''Deep Neural Networks''' may be used to extract more subtle patterns from images/videos or time series (e.g. Convolutional Neural Network - CNN).]]
• '''Deep Neural Networks''' may be used to extract more subtle patterns from images/videos or time series (e.g. Convolutional Neural Network - CNN).]]


[[File:AiCAMstir Kick-off Meeting, 29th July 2021 - Slide 14.JPG|thumb|left|upright=4|alt=|Predictions of FSW power: <br />
<div style="clear:both;">
 
== Analytical models ==
[[File:AiCAMstir Kick-off Meeting, 29th July 2021 - Slide 14.JPG|thumb|left|upright=3.2|alt=|Predictions of [[FSW Power]]: <br />
• Torque, 𝑡, needed to make a weld is unknown <br />
• Torque, 𝑡, needed to make a weld is unknown <br />
• Power consumed by tool rotation is 𝑡𝜔 <br />
• Power consumed by tool rotation is 𝑡𝜔 <br />
• Can these be calculated?]]
• Can these be calculated?]]


 
[[File:AiCAMstir Kick-off Meeting, 29th July 2021 - Slide 15.JPG|thumb|left|upright=3.2|alt=|The FSW circle: <br />
[[File:AiCAMstir Kick-off Meeting, 29th July 2021 - Slide 15.JPG|thumb|left|upright=4|alt=|The FSW circle: <br />
• Torque, 𝒕, Function of strength <br />
• Torque, 𝒕, Function of strength <br />
• FSW Power, 𝑷, Function of torque <br />
• FSW Power, 𝑷, Function of torque <br />
Line 139: Line 159:
• Strength, 𝝈, Function of temperature]]
• Strength, 𝝈, Function of temperature]]


 
[[File:AiCAMstir Kick-off Meeting, 29th July 2021 - Slide 16.JPG|thumb|left|upright=3.2|alt=|Baseline variables for analysis <br />
[[File:AiCAMstir Kick-off Meeting, 29th July 2021 - Slide 16.JPG|thumb|left|upright=4|alt=|Baseline variables for analysis <br />
• Temperature, 𝑇 is a function of the unknown power, and: <br />
• Temperature, 𝑇 is a function of the unknown power, and: <br />
::• Distance from tool axis, 𝑥 <br />
&nbsp;&nbsp;• Distance from tool axis, 𝑥 <br />
::• Travel speed, 𝑣 <br />
&nbsp;&nbsp;• Travel speed, 𝑣 <br />
::• Thermal properties, conductivity, 𝑘 and diffusivity, 𝑎 <br />
&nbsp;&nbsp;• Thermal properties, conductivity, 𝑘 and diffusivity, 𝑎 <br />
::• Room temperature, 𝑇<sub>0</sub> <br />
&nbsp;&nbsp;• Room temperature, 𝑇<sub>0</sub> <br />
• Strength, 𝜎 is a function of the unknown temperature, and: <br />
• Strength, 𝜎 is a function of the unknown temperature, and: <br />
::• Room temperature strength, 𝜎<sub>𝑅𝑇</sub> <br />
&nbsp;&nbsp;• Room temperature strength, 𝜎<sub>𝑅𝑇</sub> <br />
::• Material melting temperature, 𝑇<sub>𝑀</sub> <br />
&nbsp;&nbsp;• Material melting temperature, 𝑇<sub>𝑀</sub> <br />
• Torque, 𝑡 is a function of the unknown material strength near the tool, and:<br />
• Torque, 𝑡 is a function of the unknown material strength near the tool, and:<br />
::• The radius of the tool, 𝑅 <br />
&nbsp;&nbsp;• The radius of the tool, 𝑅 <br />
• FSW power is equal to the unknown torque, 𝑡 times the rotation speed, &#969;]]
• FSW power is equal to the unknown torque, 𝑡 times the rotation speed, &#969;]]


 
[[File:AiCAMstir Kick-off Meeting, 29th July 2021 - Slide 17.JPG|thumb|left|upright=3.2|alt=|Assumed relationships:<br />
[[File:AiCAMstir Kick-off Meeting, 29th July 2021 - Slide 17.JPG|thumb|left|upright=4|alt=|Assumed relationships:<br />
• Temperature, 𝑇 predicted using a Rosenthal equation, assuming  
• Temperature, 𝑇 predicted using a Rosenthal equation, assuming  
power, 𝑃<br />
power, 𝑃<br />
Line 162: Line 180:
• Power straightforward function of torque, 𝑡 and rotation speed, &#969;<br />
• Power straightforward function of torque, 𝑡 and rotation speed, &#969;<br />
• Hence:<br />
• Hence:<br />
::• Four equations<br />
&nbsp;&nbsp;• Four equations<br />
::• Four unknowns (𝑇, 𝑡, 𝜎, 𝑃)<br />
&nbsp;&nbsp;• Four unknowns (𝑇, 𝑡, 𝜎, 𝑃)<br />
• Answer: FSW power based upon (𝑣, 𝜎𝑅𝑇, 𝑇<sub>𝑀</sub>, 𝑅, &#969;, 𝑘, 𝑎)
• Answer: FSW power based upon (𝑣, 𝜎𝑅𝑇, 𝑇<sub>𝑀</sub>, 𝑅, &#969;, 𝑘, 𝑎)
]]
]]


 
[[File:AiCAMstir Kick-off Meeting, 29th July 2021 - Slide 18.JPG|thumb|left|upright=3.2|alt=|Example:<br />
[[File:AiCAMstir Kick-off Meeting, 29th July 2021 - Slide 18.JPG|thumb|left|upright=4|alt=|Example:
• Thick plate Rosenthal gives: [[FSW_Power#Power.2C_.7F.27.22.60UNIQ-MathJax28-QINU.60.22.27.7F |Power 𝑃]]
• Thick plate Rosenthal gives: [[FSW_Power#Power.2C_.7F.27.22.60UNIQ-MathJax28-QINU.60.22.27.7F |Power 𝑃]]
]]
]]


<div style="clear:both;">
== Friction Stir Welding ==
Eight introductory slides were presented by Laboratório de Metalurgia Física ([[LAMEF]]):
<div style="clear:both;">
[[File:Friction stir welding (LAMEF, UFRGS), Set 2021, 01.JPG|thumb|left|upright=3.2|alt=Slide of the aiCAMstir Kick-off Meeting, which was held online on 29th July 2021 with 16 attendees|Friction stir welding (LAMEF/UFRGS)]]
[[File:Friction stir welding (LAMEF, UFRGS), Set 2021, 02.JPG|thumb|left|upright=3.2|alt=Slide of the aiCAMstir Kick-off Meeting, which was held online on 29th July 2021 with 16 attendees|'''Physical Metallurgy Laboratory (LAMEF):''' <br/> 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. <br />
• Please have a look at https://vimeo.com/261297853 <br />
• Visit our website on https://www.ufrgs.br/lamef/english/index.html]]
<div style="clear:both;">
== Friction stir welding ==
[[File:Friction stir welding (LAMEF, UFRGS), Set 2021, 04.JPG|thumb|left|upright=3.2|alt=Slide of the aiCAMstir Kick-off Meeting, which was held online on 29th July 2021 with 16 attendees|Friction stir welding (FSW): FSW machine (4000 rpm, 70 kN, 2000 mm) and process.]]
<div style="clear:both;">
== Friction stir welding: weld characterization: ==
[[File:Friction stir welding (LAMEF, UFRGS), Set 2021, 05.JPG|thumb|left|upright=3.2|alt=Slide of the aiCAMstir Kick-off Meeting, which was held online on 29th July 2021 with 16 attendees|'''FSW: Weld characterisation''' <br/>
• Mechanical properties <br />
&nbps;&nbsp;• Bending tests <br />
&nbps;&nbsp;• Tensile tests <br />
• Metallurgical characterisation <br />
&nbps;&nbsp;• Tool wear analysis]]
<div style="clear:both;">
== FSW: Numerical Simulation ==
[[File:Friction stir welding (LAMEF, UFRGS), Set 2021, 06.JPG|thumb|left|upright=3.2|alt=Slide of the aiCAMstir Kick-off Meeting, which was held online on 29th July 2021 with 16 attendees|FSW: Numerical Simulation: https://youtu.be/d0_as7Nf_Q0]]
<div style="clear:both;">
== Friction-based welding processes at LAMEF/UFRGS ==
[[File:Friction stir welding (LAMEF, UFRGS), Set 2021, 07.JPG|thumb|left|upright=3.2|alt=Slide of the aiCAMstir Kick-off Meeting, which was held online on 29th July 2021 with 16 attendees|*Friction-based welding processes at LAMEF/UFRGS: <br />
&nbps;&nbsp;• Friction Stir Welding (FSW): https://youtu.be/mYYn7O_w06s
&nbps;&nbsp;• Friction hydro-pillar processing: https://youtu.be/j--FMNFIYVI <br />
&nbps;&nbsp;• Linear friction welding: https://youtu.be/j3pm_rTK1GE <br />
&nbps;&nbsp;• Friction welding of pipes: https://youtu.be/DoNgR33GDnA <br />
* Recent publication on FSW of AA 5083: http://dx.doi.org/10.4322/2176-1523.20202450]]


[[File:Zeichen 123 - Baustelle, StVO 1992.svg|thumb|left|upright=0.5|'''More information will soon be provided''']]
<div style="clear:both;">


[[File:Friction stir welding (LAMEF, UFRGS), Set 2021, 08.JPG|thumb|left|upright=3.2|alt=Slide of the aiCAMstir Kick-off Meeting, which was held online on 29th July 2021 with 16 attendees| Universidade Federal do Rio Grande do Sul – UFRGSF, ProEng - Unidade EMBRAPII, Laboratório de Metalurgia Física – LAME]]


<div style="clear:both;">


== Two companies – one team  ==
[[File:Two companies - one team; Smart Industry Group and Latrock GmbH 01.jpg|thumb|left|upright=4|alt=Smart Industry Group: Ukrainian company specializing in developing software for PLC, SCADA-systems, and software solutions in various industries - Latrock GmbH: German company specializing in Data Science, Machine Learning, Web Development, DevOps, Embedded System, IoT and Mobile Applications.|Two companies - one team: Smart Industry Group and Latrock GmbH]]


[[File:Two companies - one team; Smart Industry Group and Latrock GmbH 01.jpg|thumb|left|upright=4|alt=Smart Industry Group: Ukrainian company specializing in developing software for PLC, SCADA-systems, and software solutions in various industries - Latrock GmbH: German company specializing in Data Science, Machine Learning, Web Development, DevOps, Embedded System, IoT and Mobile Applications.
|Two companies - one team: Smart Industry Group and Latrock GmbH]]
[[File:Two companies - one team; Smart Industry Group and Latrock GmbH 02.jpg|thumb|left|upright=4|alt=Computer vision, Machine learning, Data science - Cloud-based platforms - IoT - Embedded systems - Desktop, mobile and Web-applications - Industrial automation|Our Competencies]]
[[File:Two companies - one team; Smart Industry Group and Latrock GmbH 02.jpg|thumb|left|upright=4|alt=Computer vision, Machine learning, Data science - Cloud-based platforms - IoT - Embedded systems - Desktop, mobile and Web-applications - Industrial automation|Our Competencies]]
[[File:Two companies - one team; Smart Industry Group and Latrock GmbH 03.jpg|thumb|left|upright=4|alt=Web, Data Science, Embedded Systems, DevOps, Mobile, Industrial Automation|Relaed Technologies]]
[[File:Two companies - one team; Smart Industry Group and Latrock GmbH 03.jpg|thumb|left|upright=4|alt=Web, Data Science, Embedded Systems, DevOps, Mobile, Industrial Automation|Relaed Technologies]]
[[File:Two companies - one team; Smart Industry Group and Latrock GmbH 04.jpg|thumb|left|upright=4|alt=Removing defects and flaws from marble surfaces is a great deal of time and manual effort. Zella-Mehlis machine fully automates marble refinishing and makes this significantly faster.
[[File:Two companies - one team; Smart Industry Group and Latrock GmbH 04.jpg|thumb|left|upright=4|alt=Removing defects and flaws from marble surfaces is a great deal of time and manual effort. Zella-Mehlis machine fully automates marble refinishing and makes this significantly faster.
|Key projects: Marble Processing Machine]]
|Key projects: Marble Processing Machine: [https://www.zim.de/ZIM/Redaktion/DE/Publikationen/Erfolgsbeispiele/Internationale-Kooperationen/202-en-an-automated-way-to-refinish-marble.html Mention on the website of German Federal Ministry for Economic Affairs and Energy]]]
 
[[File:Two companies - one team; Smart Industry Group and Latrock GmbH 05.jpg|thumb|left|upright=4|alt=AI coach in a mobile app which analyses fitness exercises and provides statistic.
[[File:Two companies - one team; Smart Industry Group and Latrock GmbH 05.jpg|thumb|left|upright=4|alt=AI coach in a mobile app which analyses fitness exercises and provides statistic.
|Key projects: Kerebra]]
|Key projects: Kerebra]]
[[File:Two companies - one team; Smart Industry Group and Latrock GmbH 06.jpg|thumb|left|upright=4|alt=Technologies: С++, Rust, Golang, Python, TensorFlow, Flutter, Firebase, PostgreSQL - Platform: Google Cloud Platform, Kubernetes, Android, iOS, Web|Key projects: Insolar]]
[[File:Two companies - one team; Smart Industry Group and Latrock GmbH 06.jpg|thumb|left|upright=4|alt=Technologies: С++, Rust, Golang, Python, TensorFlow, Flutter, Firebase, PostgreSQL - Platform: Google Cloud Platform, Kubernetes, Android, iOS, Web|Key projects: Insolar]]
[[File:Two companies - one team; Smart Industry Group and Latrock GmbH 07.jpg|thumb|left|upright=4|alt=Smart Industry Group, Kharkiv, Poltavsky Shlyakh str., 123 - Latrock GmbH, Darmstädter Landstr. 116, 60598 Frankfurt am Main|'''Contacts:'''<br/>• '''Smart Industry Group''', Kharkiv, Poltavsky Shlyakh str., 123, Phone: +38 (067) 765 27 40 and +38 (067) 573 79 99, E-mail: [mailto:ceo@sig-automation.com ceo@sig-automation.com], [https://sig-automation.com/en www.sig-automation.com]<br/>• '''Latrock GmbH''', Darmstädter Landstr. 116, 60598 Frankfurt am Main, Phone: +49 6128 8600121, E-mail: [mailto:contact@latrock.com contact@latrock.com] [https://latrock.com/ www.latrock.com]]]
[[File:Two companies - one team; Smart Industry Group and Latrock GmbH 07.jpg|thumb|left|upright=4|alt=Smart Industry Group, Kharkiv, Poltavsky Shlyakh str., 123 - Latrock GmbH, Darmstädter Landstr. 116, 60598 Frankfurt am Main|'''Contacts:'''<br/>• '''Smart Industry Group''', Kharkiv, Poltavsky Shlyakh str., 123, Phone: +38 (067) 765 27 40 and +38 (067) 573 79 99, E-mail: [mailto:ceo@sig-automation.com ceo@sig-automation.com], [https://sig-automation.com/en www.sig-automation.com]<br/>• '''Latrock GmbH''', Darmstädter Landstr. 116, 60598 Frankfurt am Main, Phone: +49 6128 8600121, E-mail: [mailto:contact@latrock.com contact@latrock.com] [https://latrock.com/ www.latrock.com]]]
<div style="clear:both;">
== Date of next meeting ==
[[File:AiCAMstir Kick-off Meeting, 29th July 2021 - Slide 36.JPG|thumb|left|upright=3.2|alt=|The next meeting will be held as shown on [[Upcoming events]]. Please contact [mailto:stephan.kallee@alustir.com stephan.kallee@alustir.com] if you want to participate in this meeting and/or the aiCAM<sup>''stir''</sup> project]]

Latest revision as of 09:31, 6 October 2021

The aiCAMstir Kick-off Meeting was held online on 29th July 2021 with 16 attendees.

Link to the video

Recording of the aiCAMstir Kick-off Meeting (64 min)

Title slide

Title slide of the aiCAMstir Kick-off Meeting, which was held online on 29th July 2021 with 16 attendees.
Title slide of the aiCAMstir Kick-off Meeting, which was held online on 29th July 2021 with 17 attendees

Screenshot

Photos of six attendees and a list of the 17 attendees.
Screenshot of the aiCAMstir Kick-off Meeting. Please click here to see the recording of the aiCAMstir 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 aiCAMstir Kick-off Meeting.
Agenda of the aiCAMstir 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 being interviewed: "Parameter optimisation is often difficult during prototyping, production ramp-up and production. We want to create an open access cloud, where FSW users can upload and use data and information for machine learning."
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."


aiCAMstir: artificial intelligence (machine learning) in Computer Aided Manufacturing of friction stir welds - The friction stir weld made at 1300 rev/min and 1000 mm/m welding speed shows the visually best results so far.
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
Quality depends on Parameters, Variables and Boundary values
FSW: Data to be processed: Input data and output data. The quality depends on parameters, variables and boundary values
Main challenges: hooking, thinning and Rremnant joint line
Hooking, thinning and remant joint lines are typical challenges if conventinal FSW butt welding tools are used for Lap welding
Three concepts for improved FSW tools
Improved tool designs to be investigated in the aiCAMstir 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, 𝑇0
• Strength, 𝜎 is a function of the unknown temperature, and:
  • Room temperature strength, 𝜎𝑅𝑇
  • Material melting temperature, 𝑇𝑀
• 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, 𝜎𝑅𝑇 and zero at the melting point, 𝑇𝑀
• 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, 𝑇𝑀, 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):

Slide of the aiCAMstir Kick-off Meeting, which was held online on 29th July 2021 with 16 attendees
Friction stir welding (LAMEF/UFRGS)
Slide of the aiCAMstir Kick-off Meeting, which was held online on 29th July 2021 with 16 attendees
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

Slide of the aiCAMstir Kick-off Meeting, which was held online on 29th July 2021 with 16 attendees
Friction stir welding (FSW): FSW machine (4000 rpm, 70 kN, 2000 mm) and process.

Friction stir welding: weld characterization:

Slide of the aiCAMstir Kick-off Meeting, which was held online on 29th July 2021 with 16 attendees
FSW: Weld characterisation
• Mechanical properties
&nbps; • Bending tests
&nbps; • Tensile tests
• Metallurgical characterisation
&nbps; • Tool wear analysis

FSW: Numerical Simulation

Slide of the aiCAMstir Kick-off Meeting, which was held online on 29th July 2021 with 16 attendees
FSW: Numerical Simulation: https://youtu.be/d0_as7Nf_Q0

Friction-based welding processes at LAMEF/UFRGS

Slide of the aiCAMstir Kick-off Meeting, which was held online on 29th July 2021 with 16 attendees
*Friction-based welding processes at LAMEF/UFRGS:
&nbps; • Friction Stir Welding (FSW): https://youtu.be/mYYn7O_w06s &nbps; • Friction hydro-pillar processing: https://youtu.be/j--FMNFIYVI
&nbps; • Linear friction welding: https://youtu.be/j3pm_rTK1GE
&nbps; • Friction welding of pipes: https://youtu.be/DoNgR33GDnA
* Recent publication on FSW of AA 5083: http://dx.doi.org/10.4322/2176-1523.20202450
Slide of the aiCAMstir Kick-off Meeting, which was held online on 29th July 2021 with 16 attendees
Universidade Federal do Rio Grande do Sul – UFRGSF, ProEng - Unidade EMBRAPII, Laboratório de Metalurgia Física – LAME

Two companies – one team

Smart Industry Group: Ukrainian company specializing in developing software for PLC, SCADA-systems, and software solutions in various industries - Latrock GmbH: German company specializing in Data Science, Machine Learning, Web Development, DevOps, Embedded System, IoT and Mobile Applications.
Two companies - one team: Smart Industry Group and Latrock GmbH
Computer vision, Machine learning, Data science - Cloud-based platforms - IoT - Embedded systems - Desktop, mobile and Web-applications - Industrial automation
Our Competencies
Web, Data Science, Embedded Systems, DevOps, Mobile, Industrial Automation
Relaed Technologies
Removing defects and flaws from marble surfaces is a great deal of time and manual effort. Zella-Mehlis machine fully automates marble refinishing and makes this significantly faster.
Key projects: Marble Processing Machine: Mention on the website of German Federal Ministry for Economic Affairs and Energy
AI coach in a mobile app which analyses fitness exercises and provides statistic.
Key projects: Kerebra
Technologies: С++, Rust, Golang, Python, TensorFlow, Flutter, Firebase, PostgreSQL - Platform: Google Cloud Platform, Kubernetes, Android, iOS, Web
Key projects: Insolar
Smart Industry Group, Kharkiv, Poltavsky Shlyakh str., 123 - Latrock GmbH, Darmstädter Landstr. 116, 60598 Frankfurt am Main
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

Date of next meeting

The next meeting will be held as shown on Upcoming events. Please contact stephan.kallee@alustir.com if you want to participate in this meeting and/or the aiCAMstir project
Retrieved from ‘http:///index.php?title=AiCAMstir_Kick-off_Meeting,_29_July_2021&oldid=780’