Acrovision provide a Deep Learning Vision Solution for Toyota

About

ToyotaToyota is a multinational automotive manufacturer and is the second largest in the world. Toyota produce more than 10 million vehicles per year and is the market leader in hybrid electric vehicles.

Acrovision, one of the UK’s leading suppliers of Automatic Identification and Vision solutions, were asked by Toyota’s manufacturing plant in the UK to provide an automated inspection system to replace, automate and enhance the current manual inspection process to improve quality reliability and efficiency.

After vehicle assembly, the quality and specification of the vehicle is assured by team members before passing vehicles onto the dealership. The requirements were for Acrovision to enhance this inspection process to include the following:

  • An Automated Inspection system to replace current manual inspection
  • For the data to communicate directly with Toyota’s tracking system
  • The system to hold up to 50 vehicle body numbers in advance of inspections
  • That the use of AI / Deep Learning technology would benefit these inspections
  • The ability to install the system during limited line-availability

Business challenge

A Toyota team member would previously carry out manual specification checks on a vehicle. They would know the vehicle specification based on the broadcast data. The Team member would then inspect the parts fitted on the vehicle based on the specification data. They would then walk around the vehicle to check every item is correct. As this method was time consuming, it was proposed that Acrovision’s automated solution would speed up the time to inspect vehicles by automating the specification check process that is currently carried out manually. Toyota required the system to implement more than 80 auto specification checks.

Acrovision solution

Acrovision recognised that replacing a human decision-making process could not be achieved using traditional “rule-based” camera technology. The development of AI or Deep Learning vision has enabled vision inspection solutions to work more like a human brain by using neural network training of good / bad examples.

Acrovision therefore designed a solution using a combination of Cognex’s VisionPro PC Vision platform and ViDi Deep Learning tools, to create a bespoke offering with a customised front-end. This would communicate directly with Toyota’s host tracking system via broadcast messaging providing the required individual vehicle information, which in turn determines what inspections are required for that particular vehicle.  

This solution consisted of 17 x GiGi PC Cameras with external lights, which are fitted onto the inspection line.  As the vehicle moves along the track, the cameras are triggered multiple times to acquire images of the various inspection areas. These images are communicated back to the central PC for processing and decision making using a combination of the VPro and Deep Learning ViDi tools.

All relevant data is fed back to Toyota’s tracking system for logging of results / defects. This triggers any faulty vehicles to be removed at the next checkpoint for corrections to be made

Toyota

Result

Toyota now have a fully working solution which automates their vehicle inspection checks – there is now no requirement for a team to be moving around the vehicle to carry out these tasks.

The solution was designed to enable Toyota to add new or edit existing inspections. In-depth training was provided to facilitate this.

Due to the success of this installation, which has now been successfully working for a few months, Toyota have already purchased a second system and is looking to implement similar Deep Learning technology for various other project ideas.

This bespoke project implementation has further enhanced the strong relationship that has developed between Acrovision and Toyota over the past few years.

Comments

Paul Morrison, Key Account Manager at Acrovision added, “Fulfilling the customer requirements for this solution, had many difficult elements with the communication to the host and tracking of data. This was made easier by the relationship with Toyota and the willingness to find suitable developments with ourselves to these challenges. The final bespoke system that has been provided, gives the automated inspection required and ease of use for Toyota. The flexibility of the system allows Toyota to make changes when required and quickly.”

Marios Souzou, Engineer at Toyota Manufacturing UK added, “Throughout the last few years, we have developed a close working relationship with Acrovision and selecting them to deliver this innovative, bespoke and challenging system was the right choice. From concept development to day-to-day problem solving, Acrovision engineers always go above and beyond to support TMUK. We have now increased our quality and productivity while decreasing cost and I am more certain than ever that our customers receive the highest quality vehicles.”

Toyota

Sign up to our newsletter!

You agree to our Privacy Policy when signing up.