Layer Surface Imaging for Additive Welding Defect Prediction

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

In additive manufacturing, predicting and optimizing welding conditions for complex shapes is challenging due to the increased number of paths and path lengths, leading to potential welding defects like narrow portions where defects such as melting defects can occur.

Innovation Solution

An image information generating device and method that approximates the design shape of each layer using a welding bead model, extracts surface profiles, and converts concave-convex shapes into image information, along with a defect predicting device that extracts and calculates features of narrow portions to predict defects.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If the number of paths and path length increase to manufacture complex shaped objects, then the manufacturing capability is improved, but the difficulty of predicting shape and optimizing welding conditions increases

Engineering Contradiction:

Improvemanufacturing capability for complex shapesVSAvoidprediction and optimization complexity

Core Design Contradiction:

Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The patent creates a virtual copy of the manufactured object through 3D CAD modeling and simulates the welding process on this digital replica. This allows prediction of shape unevenness and defect occurrence without physically manufacturing the complex component, thereby reducing prediction complexity while maintaining manufacturing capability for complex shapes

Inventive Principle:

Principle #26Copying

Solution Approach 2:

The system performs preliminary simulation of the welding process before actual manufacturing by calculating predicted shape unevenness and defect probabilities on the virtual model. This advance prediction enables optimization of welding conditions and paths before committing to the actual complex manufacturing process

Inventive Principle:

Principle #10Preliminary action

2Measurement precision

If traditional welding detection methods are used, then simple welding quality can be determined, but complex manufactured objects with many paths cannot be effectively predicted for defects

Engineering Contradiction:

Improvewelding quality detection accuracyVSAvoiddefect prediction difficulty for complex shapes

Core Design Contradiction:

Measurement precisionVSDifficulty of detecting and measuring

Solution Approach 1:

The patent transitions from traditional 2D welding detection to 3D shape analysis by calculating predicted shape unevenness across the three-dimensional surface of complex manufactured objects. This dimensional extension enables effective defect prediction for complex geometries that cannot be adequately assessed by conventional 2D methods

Inventive Principle:

Principle #17Another dimension (Dimensionality change)

Solution Approach 2:

The system introduces a computational prediction model as an intermediary between the welding process and defect detection. This model calculates predicted shape unevenness and defect occurrence probabilities, serving as a bridge that enables accurate defect prediction for complex shapes without requiring direct physical measurement during manufacturing

Inventive Principle:

Principle #24Intermediary (Mediator)

3Reliability

If welding conditions are optimized to prevent narrow portions, then defect occurrence is reduced, but the complexity of selecting appropriate conditions increases

Engineering Contradiction:

Improvedefect prevention capabilityVSAvoidwelding condition selection complexity

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

The system provides feedback by calculating predicted shape unevenness and defect probabilities based on the proposed welding paths and conditions. This feedback loop enables iterative optimization of welding parameters to prevent narrow portions and defects, reducing the complexity of condition selection through data-driven guidance

Inventive Principle:

Principle #23Feedback

Data Source

PatentUS20260030401A1Image-information generating device and image-information generating method, image processing device and image processing method, defect predicting device and defect predicting method, and program

Publication Date: 2026.01.29 KOBE STEEL LTD

AI summary

An image information generating device generates image information representing a shape of a manufactured object obtained by depositing layers each made of a plurality of welding beads. The image information generating device includes: a coordinate information acquisition unit configured to approximate a design shape of each layer of the manufactured object using a model simulating a shape of the welding bead and acquire coordinate information on a plurality of points of the approximated model; a profile extraction unit configured to obtain a profile representing a surface shape of the specified layer based on the coordinate information; and an image information conversion unit configured to convert a concave-convex shape of a surface of the specified layer into image information using the profile.