3D Weld Inspection With Resolution Correction for Fast Scanning

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing weld appearance inspection systems face challenges in accurately evaluating the three-dimensional shape of welds when inspection conditions change, leading to inconsistencies in measurement resolution and reduced inspection accuracy.

Innovation Solution

An appearance inspection apparatus equipped with a shape measurement unit attached to a robot, a data processor for correcting shape data resolution, and a determination model generator using learning data sets to accurately assess the weld's shape regardless of changing inspection conditions.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If inspection speed is increased to reduce production takt time, then productivity is improved, but measurement resolution deteriorates and inspection accuracy is reduced

Engineering Contradiction:
Improveinspection speedVSAvoidmeasurement resolution
Core Design Contradiction:
ProductivityVSMeasurement precision

Solution Approach 1:

The patent applies preliminary action by pre-processing the shape data through resolution correction before it is input to the determination model. The shape data processor corrects the resolution of shape data acquired at high inspection speeds to match the resolution of sample shape data used for model training. This preliminary correction ensures that even when inspection speed increases and measurement resolution decreases, the corrected data maintains the quality needed for accurate defect detection.

Inventive Principle:
Principle #10Preliminary action

2Measurement precision

If measurement resolution is increased to improve inspection accuracy, then measurement precision is improved, but production takt time increases

Engineering Contradiction:
Improvemeasurement resolutionVSAvoidproduction takt time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The patent applies parameter changes by transforming the resolution parameter of the shape data. Instead of changing the physical measurement conditions to achieve high resolution, the system changes the data parameter through computational correction. The shape data processor modifies the resolution parameter of acquired shape data to match the reference resolution, enabling accurate inspection without requiring slow, high-resolution physical measurements.

Inventive Principle:
Principle #35Parameter changes

3Adaptability or versatility

If inspection conditions are changed to adapt to different workpiece shapes and materials, then adaptability is improved, but measurement precision deteriorates due to resolution mismatches

Engineering Contradiction:
Improveinspection condition flexibilityVSAvoidshape data feature consistency
Core Design Contradiction:
Adaptability or versatilityVSMeasurement precision

Solution Approach 1:

The patent applies universality by creating a resolution correction mechanism that works across all inspection conditions, workpiece shapes, and materials. The shape data processor universally corrects resolution mismatches regardless of the specific inspection scenario. This universal correction ensures that the determination model receives consistently formatted data with matching features, maintaining precision across diverse applications while preserving the ability to adapt inspection conditions to different workpieces.

Inventive Principle:
Principle #6Universality (Multi-functionality)

Data Source

PatentUS20240337604A1Appearance inspecting device, welding system, shape data correcting method, and method for appearance inspection of a weld
Publication Date: 2024.10.10 PANASONIC INTELLECTUAL PROPERTY MANAGEMENT CO LTD
  • US20240337604A1 patent drawing
  • US20240337604A1 patent drawing
  • US20240337604A1 patent drawing

AI summary

An appearance inspection apparatus includes a shape measurement unit configured to measure the three-dimensional shape of a weld and a data processor configured to process shape data acquired by the shape measurement unit. The data processor includes a shape data processor configured to correct a resolution of the shape data, a learning data set generator configured to generate a plurality of learning data sets by performing data augmentation on multiple pieces of sample shape data acquired in advance, a determination model generator configured to generate a determination model using the plurality of learning data sets, and a first determination unit configured to determine whether the shape of the weld is good or bad based on the shape data having the corrected resolution and the determination model.