Artificial Neural Network in Welding!!!

Have you ever thought how human brains functions???

Training, inputs, target, feedback system, correction, learning, testing, validation, output, multivariate analysis, benchmarking, randomizing… these are few terms which when combined together and functioned together, wonders happens and that’s the secret behind functioning of human brain,

Now think… what if these all terms made to function together under one artificial system, will it simulate human brain?

Answer is YES… Researchers have successfully developed Artificial Intelligence System as popularly known to be Artificial Neural Network. These has its own axon, neurons, synapses, dendrites just as biological human brain has.

It has started creating wonders in many other fields. Here, we will see how this can be benefited in welding field. These are some of the examples, Self-Learning robots, Prediction model for the experimentation, online defect detecting technique, Precision positioning and welding.

theweldingsy

Neural-network guided self-adjusting welding system. Credit: Teemu Leinonen, LUT

  • Self-Learning Robots: Lappeenranta University of Technology (LUT) is developing an entirely new kind of welding system, one which solves quality and productivity problems related to automated and mechanized 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. Its 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. 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 center of the value range and the possible defect is prevented.
  • Prediction Model: With the help of supervised learning in neural network one can predict things. This can be useful while development of any new welding process. Weld bead geometry, strength, chemical composition of weld, ferrite number and many other responses can be predicted using Neural Network. This can save time and money of your development project.
  • Online defect monitoring: Capturing the sound of welding and studying its waveform, one can gather many information. Defects will have certain waveform. These waveform is captured by experimentation for number of defects and processed in neural network model. This model can tell us while welding where the defect is and its type if it has occurred.

Many such technological development can be possible if we start applying Neural network for all the small work we carry out on the daily basis.

Reference: Article – The welding system of the future is self-learning.

Keep reading, Happy welding

Thank you,

KP Bhatt

 

 

Advertisements

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out /  Change )

Google+ photo

You are commenting using your Google+ account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

w

Connecting to %s