BLOG
BLOG
2021. 6. 13. | Time to read: 2 min
Dalia Peña is the head of customer experience at Drishti. Dalia brings extensive experience and a keen understanding of lean manufacturing principles to Drishti. She has been able to infuse that background into the company, particularly to members of Drishti who bring less manufacturing expertise to the table. In doing so, Dalia has ensured that Drishti’s AI-powered computer vision technology stays hyper-focused on meeting the needs of discrete manufacturers across North America. Dalia was one of Drishti’s first employees, and at the time, one of the only employees with actual assembly line experience.
Previous blogs in this series have introduced you to how you can use cameras on assembly lines beyond the inspection process.
In this article, we will focus on the only thing that matters: ROI.
When you move beyond inspection for video, you will obviously see ROI from video analytics — namely, defect reduction, process optimization, and training. This is the core of Drishti’s value proposition and is most readily apparent when you read stories like this one.
What’s less obvious is that you will also see ROI by displacing the burden your existing inspection systems place on your assembly lines:
Here’s more details about the benefits of each one.
The drag on throughput
Inspection often takes time. This is the case whether you have a dedicated inspection station at the end of the line, or built in inspection process steps at each station. In either case, this is NVA time that has always been deemed essential.
However, with video analytics technology, you can offload the inspection effort from “end state inspection” to “process validation.” What this means is that your video analytics system is validating the process as it’s being performed. This contrasts to the status quo, in which the end state is manually or digitally validated. The move from post-facto to in-process will cut the production time for each unit, and thus speed throughput.
The cost of labor
Manual inspection is an NVA task. The more you rely on people to pass judgement, the more NVA work you are paying for.
This, again, illustrates the difference between end-state inspection and in-process validation. With in-process validation, you are able to identify suspect units as they move down the line. This gives you much greater confidence in the state of each unit, and allows you to redeploy your inspectors accordingly. To be specific, you can reduce your labor cost by moving from inspection of each unit to inspection of suspicious units.
The cost of maintenance and downtime
The interplay between product design, inception process steps and inspection technologies such as magnetic sensors or Cognex-style cameras often results in a Rube Goldberg-like assembly process. There are many moving parts, and each one of them creates a single point of failure that can slow or stop the line. Or, if the process changes, many of them require reprogramming or reconfiguring, which can slow down the factory output.
On the other hand, video analytics and process validation lets you consolidate many of these moving parts into a single system. This reduces the overhead required to keep the line running, and reduces the number of potential failure points. The payoff, then, is lower maintenance costs and higher OEE.
