Sound Inspections: Hyundai applies AI system using ‘sound’ for quality vehicle parts inspection

Toronto, Ontario – Hyundai Mobis has developed an artificial intelligence (AI) system that utilizes sound to aid in quality inspection and has applied the technology in its production lines. According to the automaker, the use of AI in this way helps to leverage artificial intelligence to analyze the subtle sounds generated during product inspection to determine quality accuracy.

According to a report released by AutoTech news, on June 18th, it was announced that Hyundai Mobis had recently completed a pilot implementation of an Acoustic AI-based inspection system at its Changwon plant in South Korea. This plant specifically produces Electric Power Steering (EPS). 

For the automaker, what makes Acoustic AI special is that it develops algorithms that assign meaning to specific sounds and then facilitates appropriate judgements. 

Acoustic AI is distinguished from generative AI, which relies on language for question and answer-based tasks. At the moment, Acoustic AI remains relatively untested in the manufacturing industry. 

Hyundai expects that the Acoustic AI inspection system from the Changwon plant will be extended to other component production lines, prioritizing parts like braking systems that generate noise due to their operational nature.

Choi Nak-Hyun, Vice President and Head of Digital Transformation at Hyundai Mobis, stated, “this initiative marks a pioneering example of process innovation not only in the automotive sector but across the global manufacturing industry. We will continue introducing differentiated AI-based technologies for production, R&D, and improvements in work environments.”

While generative AI emphasizes versatility for general users, Acoustic AI is designed for industrial applications. It is specialized for processing large volumes of tasks in a short time. The inspection system at the Changwon plant can detect defective products at a rate of one unit per second.

The plant produces around 1.3 million units of EPS annually, which includes a production process of 23 stages. Since EPS directly impacts steering performance and safety through the steering wheel, careful quality checks are necessary. 

Previously, certain defective products below a certain threshold were initially filtered out by an automated system after assembly, followed by manual reevaluation by specialized personnel. To enhance their quality competitiveness, Hyundai Mobis collaborated with on-site engineers, production technology experts and AI specialists for about a year. This has helped the system distinguish defective products and their causes. 

Hyundai Mobis plans to validate and expand the application of Acoustic AI. In the manufacturing sector, the company aims to continuously collect meaningful data through its pioneering Acoustic AI and develop proprietary AI models based on this data. The goal of the project is to improve the efficiency of the technology. 


Sign-up for the Collision Repair daily e-zine and never miss a story –  SUBSCRIBE NOW FOR FREE!

Related Posts

Leave a Reply

Your email address will not be published. Required fields are marked *

IAA Tech video
Arslan Accuvision
previous arrow
next arrow

Recent Products

Recent Posts

Stay on top of the latest INDUSTRY news and trends by subscribing to our daily e-zine!

Our other sites

Our other sites