LUT is developing an entirely new kind of welding system, one which solves quality and productivity problems related to automated and mechanised welding.
The system is self-adjusting, flexible and adaptable, such that it can be integrated as part of different robotic systems and different manufacturers’ power supplies.
It’s self-adjusting properties are based on a new kind of sensor system which is controlled by a neural network program. Most often in welding a monitoring sensor is used which tracks the bevel angle, an essential part of the welding process. In the system being developed by LUT, there are also monitoring sensors for the thermal profile (the weld pool’s heat values) and the weld form. The monitoring data is transferred from the sensors to the neural network, which is able to deduce and react to simultaneous changes in multiple variables.
‘When a mistake is detected, the system is able both to correct it during the welding process and also calculate what other faults may arise. Thus the final product is flawless. The problem with welding automation systems is that certain values are set for the work, based on which the whole weld is carried out, and only then is it checked whether the result is good. Now the welding is monitored throughout the whole process’, explains Project Manager Markku Pirinen.
In the gas-shielded arc welding process, factors affecting outcome quality include the welding current, the arc voltage, the wire feeding and transporting speeds, and the position of the welding gun. With the help of the neural network, a regulating window can be set for these system variables, and they can then be controlled so that they remain within certain limits, which ensures that final product is as required.
‘In practice this means that when the welding values approach the boundary values set in the parameter window, the system corrects the process so that the welding values move back towards the centre of the value range and the possible defect is prevented.’
Added value for Arctic steel construction
The new system works very well with high-strength steel welding, as the parameter windows for the high-strength materials are significantly narrower than those for construction steel, and the harder the steel is, the more difficult it is to weld. High-strength steel is used, for example, in arctic steel construction work, where the materials used must be light, robust, and strong.
‘In the Arctic, welds must be of higher quality than in warmer regions. In the North, errors would have catastrophic consequences. For example, the welds must be able to withstand temperature of up to -60 °C, and they must be flawless. Operating safety must be so high that no accidents occur at all’, says Pirinen.
The Latest on: Self-learning robots
via Google News
The Latest on: Self-learning robots
- AI algorithm identifies new compound potentially useful for photonic devices, biologically inspired computerson November 24, 2020 at 4:54 am
This is the basis for CAMEO, a self-learning AI that uses prediction and ... "CAMEO has the intelligence of a robot scientist, and it's built to design, run and learn from experiments in a very ...
- NIST AI system discovers new materialon November 24, 2020 at 2:06 am
When the words ''artificial intelligence'' (AI) come to mind, your first thoughts may be of super-smart computers, or robots that perform tasks without needing any help from humans. Now, a ...
- Autonomous Mobile Robots Market Insights, Current and Future Trends & Forecast 2018-2028on November 23, 2020 at 2:12 pm
The new report on the Autonomous Mobile Robots Market provides estimations of the size of the global market and share and size of key regional markets during the historical period of 2014 – 2018. The ...
- AI system discovers useful new materialon November 19, 2020 at 4:00 pm
When the words 'artificial intelligence' (AI) come to mind, your first thoughts may be of super-smart computers, or robots that perform tasks without needing any help from humans. Now, a ...
- Gartner announces winners of the 2020 Gartner Healthcare and Life Sciences Eye on Innovation Awardon November 18, 2020 at 1:56 am
By making the entire hospital operation “smart” – from automated patient check in to pharmacy robots – Stanford has improved ... Research Center created an analytical platform with self-learning AI ...
- Remember Sophia the robot that argued with Elon Musk? Version 2.0 is coming, thanks to Covid-19, and her name is Graceon November 1, 2020 at 7:45 pm
That self-learning process can customise future conversations ... Meet Sophia, the world’s first robot to get citizenship For now that remains a vision, as Grace is yet to be built.
via Bing News