Night shot of a bridge_edited.jpg

Automotive Industry

By digitalizing the processes surrounding incident root cause analysis in their production lines, VISENSE helps a large automotive manufacturer to cut the time needed to identify and resolve errors by 50%. 

EXPLORE

The case:
Endless Doorsealing Application

The Machine:

Application of rubber sealing on car door through a robotic arm with gripper and application head.

 

Cycle production, 60s cycle time, 960 applications per day, 5% error rate.

The Initial Situation:

  • New door sealing machines were implemented

  • Initial ramp-up and handover phase was planned to take 3 months

  • Production is not yet at desired capacity now over a year later

  • There is a (door sealing) center of competency uniting machine experts to facilitate exchange of information across plants

 

The opportunity:

The machine is not yet operating at the desired capacity and is experiencing significant production issues. The error rate in production process is high (e.g. bubbles, overlaps, gaps), while available data on production errors is very limited. Thus, constant engagement of high-paid machine experts / planners is required. Production quality differences between the plants are not fully explained.

green Exit signage hanging on wall_edited_edited_edited.jpg
Lack of standardized, digitalized tools and processes
  • Large amount of manual data. No standardized data format and no strategy to consolidate or digitalize it
     

  • Error types and location are not tracked and analyzed systematically
     

  • Significant amount of time spent on manual report generation. Information is not shared across the plant network

green Exit signage hanging on wall_edited_edited_edited_edited.jpg
Lack of availability of
high quality data
  • Machine error messages are too generic
     

  • No way to see errors happening without standing next to the machine
     

  • Using regular cameras requires work council approval (GDPR compliance) and results in hundreds of hours of footage

green Exit signage hanging on wall_edited_edited.jpg
Heavy reliance on machine experts
  • Heavy reliance on the expertise of the machine operators, maintenance and planners
     

  • Individual knowledge and coordination between the stakeholder is essential
     

  • Learnings are not systematically captured and leveraged

green Exit signage hanging on wall_edited_edited_edited_edited.jpg
No standardized
exchange of information
  • The exchange of information between the plants is not standardi-zed
     

  • Processes around error management are not standardized
     

  • Cultural challenges make remote support by machine experts challenging

background 1.png

The approach:

Installation of VISENSE hardware kits consisting of cameras,

sensors and edge device on machine

Cycle Detection

Automated cycle detection through a

laser sensor at the

point of rubber

injection

Recording

Recording of video footage of the application head and rubber throughput from five different angles.
Tracking of temperature, humidity, and vibration as anomaly indicators (impacting rubber quality)

Triggering

Triggering of incidents through integration with central production system (machine-triggered incidents) and manual triggering

Visualization

Visualization of error incidents and corresponding data on the dashboard.
Access to all machines across plants, facilitation of remote support by machine experts. Ability to communicate & share learnings through the platform

Reporting

Automated report generation, digitalized data outputs such as lop lists (ramp up error tracking list)

The impact:
 

Digitalization and support in error root cause identification, ramp-up process, information exchange and capture of learnings, detailed machine monitoring, repeat error prevention.

9'900

hours of capacity freed up among operators, maintenance and planners per year.

1/2

man-year saved during ramp-up phase of a new or re-calibrated machine.

50%

reduction of time spent on error type and root cause identification.

2

international travels of machine experts saved per year.

50%

reduction of time needed for reporting through automation.