Development of a human-friendly visual inspection method for painted vehicle bodies

Area of Science:

• Automotive manufacturing
• Quality control
• Human-computer interaction

Background:

• Visual inspections are vital for vehicle body quality assurance.
• Prolonged inspections cause eye fatigue, reducing accuracy and efficiency.
• A need exists for improved, human-friendly inspection methods.

Purpose of the Study:

• To develop and evaluate a novel human-friendly visual inspection method for detecting vehicle body defects.
• To compare the new method against conventional techniques using objective and subjective measures.

Main Methods:

• Developed a method projecting linear stripes onto vehicle surfaces to reveal defects as distortions.
• Compared the new method with a conventional approach over a 30-minute inspection task.
• Measured critical fusion frequency (eye fatigue), defect detectability, and subjective satisfaction.

Main Results:

• The new method showed a minor decrease (3.7%) in critical fusion frequency, indicating less eye fatigue compared to the conventional method's 11.0% drop.
• Defect detectability was significantly higher with the new method (92.1%) versus the conventional (73.4%).
• Subjective satisfaction scores favored the new method (5.8/7) over the conventional (3.5/7).

Conclusions:

• The developed human-friendly visual inspection method is effective in detecting vehicle body defects.
• This method significantly reduces eye fatigue and improves inspection performance and user satisfaction.
• The new technique offers a promising advancement for quality control in automotive manufacturing.