Welding Defect Analysis
Welding Defect Analysis

Welding Defect Analysis

Welding defects are common in the manufacturing process, and it’s impossible to form a defect-free welding joint, but the defects can be reduced to a particular extent using machine vision enabled by Artificial Intelligence and Machine Learning.

Advantages of implementing Machine Vision and Machine Learning for
defect analysis in Welding

  • No more human errors
  • Quality product
  • Avoid damages due to defect
  • Less time for quality inspection
  • High accuracy in defect identification and classification

Types of Welding Defects that can be analyzed using
Machine Learning / Deep Learning

01

Porosity

A common type of welding defect which has air bubbles
in the weld zone.

02

Spatter

Spatter is meta drop expelled during welding in the surrounding surface.
arrow-right
arrow-left

03

Incomplete Fusion

Welding gap is not filled by the molten metal.

04

Under filling

When the joint is not filled with a proper amount of molten metal.
arrow-right
arrow-left

05

Inclusion

It occurs along a V-Joint when joining thick plate using flux coated rods and the slag covering the run is not removed.

06

Incomplete Penetration

The base of the metal melts away from the weld zone, and the generation of the groove is in the shape of sharp notch.
arrow-right
arrow-left

07

Lamellar Tears

This is the main problem in low-quality steel it occurs in steel plate which has low ductility in the thickness direction which causes by non-metallic inclusions like sulphides, oxides that have been elongated during the rolling process.

08

Cracks

Cracks occur in various location and direction in the welding zone and classified
as longitudinal, transverse, cater, under bead and toe
cracks.
arrow-right
arrow-left

09

Slag Inclusions

Compounds such as oxides, fluxes and electrode materials get trapped in the weld zone is said to be slag inclusions. slag inclusions occurred due to, insufficient cleaning between welds, incorrect electrode, a high temperature which causes undercut, incomplete penetration and lack of fusion in the weld. Slag inclusion reduces the cross-section area strength of the joint and it will be the serious cause of cracking.
Types of Welding Defects

Root Causes

  • Welding temperature is too high
  • Welding temperature is too low
  • Welding pool is too large
  • Joint included angle is too low
  • Electrode and torch angle is incorrect
  • Welding arc is too long
  • The polarity is incorrect
  • Insufficient gas shielded
  • Unfavourable bead position
  • High electrode speed

Realtime Welding Defect
Analysis

The main defects in laser welding are lack of penetration and spatters. The root cause are Heat Input, Mismatching parts, and nozzle deviation There will be defects in automated laser welding, but checking them manually during the production in realtime is not possible. We need to have a live welding monitoring system, which will analyse the Heat temperature, Mismatching parts & Nozzle deviation in realtime to find the root cause immediately. After the production, there will be a separate visual inspection process to find the defects in the welding.

Identification and classification of welding defects using HD / X-Ray images

Inspection of the welded structure is very important and is essential to ensure the quality of welds to meet the requirements of the system and to assure safety and reliability. The traditional way of non-destructive inspection, radiography is still essential to findout issues in the welded joints. But still humans need to eveluate the defects in the film where we face human errors. By implementing AI/ML & DL the defects can be identified and classified with a high level of accuracy. This Intelligent defect analysis can be deployed for all industries like Gas & Oil, Nuclear Power plant, Defense, chemical and aeronautical industries.
“Welding inspection needs two processes, A live welding monitoring system & defect analysis system to ensure the quality without any human errors.”

How we find welding defects using
machine learning?

We developed AI, Machine Learning & Deep learning Models which will use various sensor data and image data to detect anomalies in welding . To identify the root cause, specifically for the heat, we use Photo diode sensors and cameras. These data are used to train the machine learning algorithms, which will help use to find out the heat variations, nozzle deviation and the quality of the welding. Our smart cameras and image processing techniques will find out the issues real-time using metal vapor plume and splatters captured during the welding. Using these data we will calculate, the height of the plume, centroid, perimeter, welding dust and the quantity of spatters. This will help to find out the root causes immediately in the laser welding. We use state of the art AI/ ML & deep-learning technologies.

The correct and incorrect images will be collected, the visual features will be extracted using image processing from the image which will be used as input for the classifiers. We implement a deep learning system with supervised learning which will help us to achieve the best detection and high accurate defect classification.

welding defects using machine learning

Technology Stack

Numpy

Numpy

Scipy

Scipy

Scikit -Learn

Scikit -Learn

Theano

Theano

TensorFlow

TensorFlow

Keras

Keras

Pytorch

Pytorch

Pandas

Pandas

Matplotlib

Matplotlib

Apache Singa

Apache Singa